CN111930792B - Labeling method and device for data resources, storage medium and electronic equipment - Google Patents

Abstract

The embodiment of the application discloses a method and a device for labeling data resources, a storage medium and electronic equipment, and belongs to the technical field of computers. The method comprises the following steps: the server pre-processes the original data resources to obtain text data, calculates the similarity between the text data and a plurality of target knowledge points to obtain a similarity value, generates a basic knowledge point label set of the original data resources according to a comparison result of the similarity value and a similarity threshold value, and generates a comprehensive knowledge point label set of the original data resources according to characteristic information of the original data resources and the basic knowledge point label set, so that knowledge point labels related to the original data resources can be marked quickly and accurately, and marking efficiency and marking accuracy are improved.

Description

Data resource labeling method, device, storage medium and electronic device

Technical Field

The present application relates to the field of computer technology, and in particular to a data resource labeling method, device, storage medium and electronic device.

Background technique

With the development of the Internet, data plays an increasingly important role in the Internet industry. For example, various industries such as retail, transportation, social networking, search, education, and medical care all involve large-scale data analysis. Take online education as an example. In online education scenarios, staff usually need to analyze users' teaching data to obtain users' teaching and learning situations, so as to provide better services to users in the future. The process of analyzing users' learning data requires obtaining the knowledge point labels associated with the data resources that users have learned. Similar application scenarios are also common in other fields. However, in related technologies, the knowledge point labels associated with data resources usually need to be manually labeled in advance. This method of labeling knowledge point labels is inefficient and will be affected by the subjective factors of the labeler, resulting in the inability to accurately label the data resources with knowledge point labels.

Summary of the invention

The embodiments of the present application provide a method, device, storage medium and electronic device for labeling data resources, which can solve the problem of inaccurate and inefficient labeling of knowledge points in data resources in related technologies.

The technical solution is as follows:

In a first aspect, an embodiment of the present application provides a method for labeling data resources, the method comprising:

Preprocess the original data resources to obtain text data;

Calculating similarity between the text data and multiple target knowledge points to obtain similarity values; wherein each of the multiple target knowledge points is associated with a basic knowledge point label;

Generate a basic knowledge point label set of the original data resource according to the comparison result of the similarity value and the similarity threshold; wherein the basic knowledge point labels included in the basic knowledge point label set are: basic knowledge point labels associated with target knowledge points whose similarity values are greater than the similarity threshold;

A comprehensive knowledge point label set of the original data resource is generated according to the feature information of the original data resource and the basic knowledge point label set.

In a second aspect, an embodiment of the present application provides a data resource annotation device, the data resource annotation device comprising:

A preprocessing module is used to preprocess the original data resources to obtain text data;

A calculation module, used for calculating similarity between the text data and a plurality of target knowledge points to obtain similarity values; wherein each of the plurality of target knowledge points is associated with a basic knowledge point label;

A first processing module is used to generate a basic knowledge point label set of the original data resource according to a comparison result of the similarity value and the similarity threshold; wherein the basic knowledge point labels included in the basic knowledge point label set are: basic knowledge point labels associated with target knowledge points whose similarity values are greater than the similarity threshold;

The second processing module is used to generate a comprehensive knowledge point label set of the original data resource according to the feature information of the original data resource and the basic knowledge point label set.

In a third aspect, an embodiment of the present application provides a computer storage medium, wherein the computer storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the above-mentioned method steps.

In a fourth aspect, an embodiment of the present application provides an electronic device, which may include: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the above-mentioned method steps.

The beneficial effects brought about by the technical solutions provided by some embodiments of the present application include at least:

When the scheme of the embodiment of the present application is executed, the server preprocesses the original data resource to obtain text data, calculates the similarity between the text data and multiple target knowledge points to obtain similarity values, generates a basic knowledge point label set of the original data resource based on the comparison result of the similarity value and the similarity threshold, and generates a comprehensive knowledge point label set of the original data resource based on the feature information of the original data resource and the basic knowledge point label set. The original data resource can be quickly and accurately labeled with relevant knowledge point labels, thereby improving the efficiency and accuracy of labeling.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

FIG1 is a system architecture diagram provided by an embodiment of the present application;

FIG2 is a schematic diagram of a flow chart of a method for labeling data resources provided in an embodiment of the present application;

FIG3 is another schematic diagram of a flow chart of a method for labeling data resources provided in an embodiment of the present application;

FIG4 is a schematic diagram of a similarity calculation process of a data resource annotation method provided in an embodiment of the present application;

FIG5 is a schematic diagram of the structure of a device provided in an embodiment of the present application;

FIG6 is a schematic diagram of the structure of a device provided in an embodiment of the present application.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present application more clear, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

FIG. 1 is a schematic diagram showing an exemplary system architecture 100 to which a data resource annotation method or a data resource annotation device according to an embodiment of the present application can be applied.

As shown in FIG1 , the system architecture 100 may include one or more of terminal devices 101, 102, and 103, a network 104, and a server 105. The network 104 is used to provide a medium for a communication link between the terminal devices 101, 102, and 103 and the server 105. Various communication client applications may be installed on the terminal devices 101, 102, and 103, such as video recording applications, video playback applications, voice interaction applications, search applications, instant messaging tools, email clients, social platform software, etc. The network 104 may include various connection types, such as wired or wireless communication links or optical fiber cables, etc.

Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Terminal devices 101, 102, 103 can be various electronic devices with display screens, including but not limited to smart phones, tablet computers, portable computers, desktop computers, etc. Network 104 can include various types of wired communication links or wireless communication links, for example: wired communication links include optical fibers, twisted pairs or coaxial cables, and wireless communication links include Bluetooth communication links, wireless fidelity (WIreless-FIdelity, Wi-Fi) communication links or microwave communication links, etc. Terminal devices 101, 102, 103 can be hardware or software. When terminal devices 101, 102, 103 are software, they can be installed in the electronic devices listed above. It can be implemented as multiple software or software modules (for example: used to provide distributed services), or it can be implemented as a single software or software module, which is not specifically limited here. When the terminal devices 101, 102, and 103 are hardware, a display device and a camera may be installed thereon. The display device may be any device capable of realizing a display function, and the camera is used to collect video streams; for example, the display device may be a cathode ray tube display (CR), a light-emitting diode display (LED), an electronic ink screen, a liquid crystal display (LCD), a plasma display panel (PDP), etc. The user may use the display device on the terminal devices 101, 102, and 103 to view displayed text, pictures, videos, and other information.

It should be noted that the data resource annotation method provided in the embodiment of the present application is usually performed by the server 105, and accordingly, the data resource annotation device is usually arranged in the server 105. The server 105 can be a server that provides various services, and the server 105 can be hardware or software. When the server 105 is hardware, it can be implemented as a distributed server cluster composed of multiple servers, or it can be implemented as a single server. When the server 105 is software, it can be implemented as multiple software or software modules (for example, used to provide distributed services), or it can be implemented as a single software or software module, which is not specifically limited here.

The server 105 in the present application can be a terminal device that provides various services, such as: the server pre-processes the original data resources to obtain text data, calculates the similarity between the text data and multiple target knowledge points to obtain similarity values, generates a basic knowledge point label set of the original data resources based on the comparison results of the similarity values and the similarity thresholds, and generates a comprehensive knowledge point label set of the original data resources based on the feature information of the original data resources and the basic knowledge point label set.

It should be noted here that the data resource labeling method provided in the embodiment of the present application can be executed by one or more of the terminal devices 101, 102, 103, and/or the server 105. Accordingly, the data resource labeling device provided in the embodiment of the present application is generally set in the corresponding terminal device, and/or the server 105, but the present application is not limited to this.

It should be understood that the number of terminal devices, networks and servers in Figure 1 is only illustrative. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

The following will introduce the data resource annotation method provided by the embodiment of the present application in detail in conjunction with Figures 2 to 4. It should be noted here that for the convenience of description, the embodiment is described by taking the online education industry as an example, but those skilled in the art understand that the application of the present application is not limited to the online education industry, and the data resource annotation method described in the present application can be effectively applied to various industries and fields of the Internet.

Please refer to Figure 2, which is a flow chart of a method for labeling data resources provided in an embodiment of the present application. As shown in Figure 2, the method in the embodiment of the present application may include the following steps:

S201, pre-processing the original data resources to obtain text data.

Among them, raw data resources refer to data resources in the form of text, audio, video, etc., such as exercises, picture books, learning audio, learning video, etc. The raw data resources contain the corresponding learning levels and subjects. Text data refers to data after raw data resources of text, audio, video, etc. are uniformly converted into text type.

Generally, when the original data resource is an audio or video type, the original data resource can be converted into text data of a preset text type by ASR (Automatic Speech Recognition) technology. ASR technology is a technology that converts audio into text based on a keyword list, converts the audio (or audio in a video) content into speech features through a spectrum, and matches the speech features with the entries in the keyword list, and uses the best matching result obtained as the recognition result. When the original data resource is a text type, but not a preset text type, it is necessary to convert the text type into a preset text type. Common text types include: txt., doc., hlp., wps., rtf., htm., pdf, etc., and the preset text type can set different text types according to actual needs.

S202, calculating similarity between the text data and a plurality of target knowledge points respectively to obtain similarity values.

Among them, the target knowledge points include at least one of target content vocabulary, target high-frequency vocabulary, target verb vocabulary, target mathematical vocabulary, target phonetic symbols, target sentence patterns and target grammar, which are knowledge points that can be obtained from the knowledge graph. Different learning levels correspond to different target knowledge points, and multiple target knowledge points are each associated with a basic knowledge point label. The similarity value refers to the similarity relationship between the two quantities being compared. Generally, the larger the similarity value, the more similar the two quantities are.

Generally, before calculating the similarity between the text data and multiple target knowledge points to obtain similarity values, it is necessary to obtain the course information corresponding to the original data resource, query the course information from the preset knowledge graph to obtain multiple target knowledge points corresponding thereto, and the knowledge graph contains target knowledge points of different learning levels and different grades. Calculate the similarity between the text data and multiple target knowledge points, that is, calculate the similarity values between the basic knowledge points in the text data and the target knowledge points, and based on the similarity values, determine the basic knowledge point labels corresponding to the text data, that is, the basic knowledge point labels corresponding to the original data resource. The basic knowledge points in the text data may include one or more of reference content vocabulary, reference high-frequency vocabulary, reference verb vocabulary, reference mathematical vocabulary, reference phonetic symbols, reference sentence patterns, and reference grammar.

S203: Generate a basic knowledge point tag set of the original data resource according to the comparison result between the similarity value and the similarity threshold.

The similarity threshold refers to the lowest lower limit value at which the similarity value can meet the conditions, that is, the similarity critical value. The basic knowledge point label set is a set of basic knowledge point labels corresponding to the original data resources, which may include knowledge point labels associated with target content vocabulary, target high-frequency vocabulary, target verb vocabulary, target mathematical vocabulary, target phonetic symbols, target sentence patterns, and target grammar. The basic knowledge point labels included in the basic knowledge point label set are basic knowledge point labels associated with target knowledge points whose similarity values are greater than the similarity threshold.

Generally, depending on the different basic knowledge points and the different similarity value calculation methods, the corresponding similarity values, similarity thresholds, and basic knowledge point labels are all different. When the target knowledge point is a target content vocabulary, a basic knowledge point label set of the original data resource is generated based on the comparison results of the similarity value and the similarity threshold, including: performing sentence segmentation processing on the text data to obtain a sentence set, and performing block processing on the sentence set to obtain a word block set, calculating the importance weight of each word block in the word block set based on the keyword extraction TF-IDF algorithm, taking the word block with an importance weight greater than a first preset weight as a reference content vocabulary, calculating the similarity value between the reference content vocabulary and the target content vocabulary, and when the similarity value is greater than the similarity threshold, obtaining the basic knowledge point label associated with the target content vocabulary, and adding the basic knowledge point label associated with the target content vocabulary to the basic knowledge point label set.

When the target knowledge point is a target high-frequency word, a basic knowledge point label set of the original data resource is generated according to the comparison result of the similarity value and the similarity threshold, including: performing sentence segmentation processing on the text data to obtain a sentence set, and performing block processing on the sentence set to obtain a word block set, calculating the importance weight of each word block in the word block set based on the keyword extraction TF-IDF algorithm, taking the word block with an importance weight less than or equal to a second preset weight as a reference high-frequency word, calculating the similarity value between the reference high-frequency word and the target high-frequency word, and when the similarity value is greater than the similarity threshold, obtaining the basic knowledge point label associated with the target high-frequency word, and adding the basic knowledge point label associated with the target high-frequency word to the basic knowledge point label set.

When the target knowledge point is a target verb vocabulary, a basic knowledge point label set of the original data resource is generated according to the comparison result of the similarity value and the similarity threshold, including: performing sentence segmentation processing on the text data to obtain a sentence set, performing word segmentation processing on the sentence set to obtain a word set, performing part-of-speech tagging on each word in the word set based on the word set to obtain a part-of-speech tagging set, taking words with the verb part-of-speech as reference verb vocabulary, calculating the similarity value between the reference verb vocabulary and the target verb vocabulary, obtaining the basic knowledge point label associated with the target verb vocabulary when the similarity value is greater than the similarity threshold, and adding the basic knowledge point label associated with the target verb vocabulary to the basic knowledge point label set.

When the target knowledge point is a target mathematical vocabulary, a basic knowledge point label set of the original data resource is generated according to a comparison result of the similarity value and the similarity threshold, including: performing sentence segmentation processing on the text data to obtain a sentence set, performing word segmentation processing on the sentence set to obtain a word set, performing part-of-speech tagging on each word in the word set based on the word set to obtain a part-of-speech tagging set, taking words whose part of speech is a numeral as a reference mathematical vocabulary, calculating a similarity value between the reference mathematical vocabulary and the target mathematical vocabulary, obtaining a basic knowledge point label associated with the target mathematical vocabulary when the similarity value is greater than the similarity threshold, and adding the basic knowledge point label associated with the target mathematical vocabulary to the basic knowledge point label set.

When the target knowledge point is a target phonetic symbol, a basic knowledge point label set of the original data resource is generated according to the comparison result of the similarity value and the similarity threshold, including: performing sentence segmentation processing on the text data to obtain a sentence set, performing word segmentation processing on the sentence set to obtain a word set, analyzing each word in the word set, and marking each word with a phonetic symbol to obtain a phonetic symbol set, calculating the similarity value between the word phonetic symbol in the phonetic symbol set and the target phonetic symbol, and when the similarity value is greater than the similarity threshold, obtaining the basic knowledge point label associated with the target phonetic symbol, and adding the basic knowledge point label associated with the target phonetic symbol to the basic knowledge point label set.

When the target knowledge point is a target sentence pattern, a basic knowledge point label set of the original data resource is generated according to a comparison result between the similarity value and the similarity threshold, including: performing sentence segmentation processing on the text data to obtain a sentence set, performing word segmentation processing on the sentence set to obtain a word set, performing part-of-speech tagging on each word in the word set based on the word set to obtain a part-of-speech tagging set, performing dependency syntactic analysis on the sentences in the sentence set to obtain a dependency syntactic tree, calculating similarity values corresponding to the words in the word set, the parts of speech in the part-of-speech tagging set, and the dependency syntactic tree with the words, parts of speech, and syntactic trees in the target sentence pattern, respectively; when the similarity value is greater than the similarity threshold, obtaining the basic knowledge point label associated with the target sentence pattern, and adding the basic knowledge point label associated with the target sentence pattern to the basic knowledge point label set.

When the target knowledge point is the target grammar, a basic knowledge point label set of the original data resource is generated according to the comparison result of the similarity value and the similarity threshold, including: performing sentence segmentation processing on the text data to obtain a sentence set, and performing word segmentation processing on the sentence set to obtain a word set, based on the word set, performing part-of-speech tagging on each word in the word set to obtain a part-of-speech tagging set, and calculating the similarity value between the grammar contained in the sentence set and the target grammar based on the word set and the part-of-speech tagging set, when the similarity value is greater than the similarity threshold, obtaining the basic knowledge point label associated with the target grammar, and adding the basic knowledge point label associated with the target grammar to the basic knowledge point label set.

S204: Generate a comprehensive knowledge point label set of the original data resource according to the feature information of the original data resource and the basic knowledge point label set.

Among them, the characteristic information refers to the type of the original data resource, such as the type of the original data resource can include audio, video, text, picture book and other types, and different types can train/exercise different learning abilities (such as listening, speaking, reading and writing abilities). The comprehensive knowledge point label in the comprehensive knowledge point label set refers to the knowledge point label that can reflect the ability of the original data resource to train the user (student) based on the characteristic information of the original data resource and the basic knowledge point label set. There can be multiple comprehensive knowledge point labels corresponding to one original data resource. For example, if the original data resource contains audio, and the basic knowledge point label set contains knowledge point labels associated with the target phonetic symbol, then it can be analyzed that the comprehensive knowledge point label corresponding to the original data resource is a listening label.

Generally, the comprehensive knowledge point labels of the original data resources are related to the characteristics of the original data resources themselves. The comprehensive knowledge point labels in the comprehensive knowledge point label set and the basic knowledge point labels in the basic knowledge point label set are both associated with the original data resources. After the basic knowledge point label set and the comprehensive knowledge point label set are generated, it means that the original data resources have been marked with relevant knowledge point labels (including basic knowledge point labels and comprehensive knowledge point labels).

When the scheme of the embodiment of the present application is executed, the server preprocesses the original data resource to obtain text data, calculates the similarity between the text data and multiple target knowledge points to obtain similarity values, generates a basic knowledge point label set of the original data resource based on the comparison result of the similarity value and the similarity threshold, and generates a comprehensive knowledge point label set of the original data resource based on the feature information of the original data resource and the basic knowledge point label set. The original data resource can be quickly and accurately labeled with relevant knowledge point labels, thereby improving the efficiency and accuracy of labeling.

As described above, the embodiments of the present application are mainly described by taking the online education industry as an example, but those skilled in the art understand that the applicability of the present method is not limited to the online education industry. For example, the method described in the present application can be applied to user tag processing in various industries such as retail, transportation, social networking, search, education, and medical care.

Please refer to FIG3 , which is a flowchart of a method for labeling data resources provided in an embodiment of the present application. The method for labeling data resources may include the following steps:

S301, preprocessing the original data resources to obtain text data.

Among them, raw data resources refer to data resources in the form of text, audio, video, etc., such as exercises, picture books, learning audio, learning video and other teaching resources, and the raw data resources contain the corresponding learning levels and subjects. Text data refers to the data after raw data resources of text, audio, video and other types are uniformly converted into text type. The basic knowledge points in the text data can include one or more of reference content vocabulary, reference high-frequency vocabulary, reference verb vocabulary, reference mathematical vocabulary, reference phonetic symbols, reference sentence patterns and reference grammar.

Generally, when the original data resource is an audio or video type, the original data resource can be converted into text data of a preset text type by ASR (Automatic Speech Recognition) technology. ASR technology is a technology that converts audio into text based on a keyword list, converts the audio (or audio in a video) content into speech features through a spectrum, and matches the speech features with the entries in the keyword list, and uses the best matching result obtained as the recognition result. When the original data resource is a text type, but not a preset text type, it is necessary to convert the text type into a preset text type. Common text types include: txt., doc., hlp., wps., rtf., htm., pdf, etc., and the preset text type can set different text types according to actual needs.

S302, querying the attribute information corresponding to the original data resource from the preset knowledge graph to obtain multiple target knowledge points corresponding to the attribute information.

Among them, the original data resources are teaching resources, and the attribute information is course information. Course information refers to information related to courses such as learning levels and learning subjects corresponding to the original data resources. Target knowledge points include at least one of target content vocabulary, target high-frequency vocabulary, target verb vocabulary, target mathematical vocabulary, target phonetic symbols, target sentence patterns, and target grammar. They are knowledge points that can be obtained from the knowledge graph. Different learning levels correspond to different target knowledge points, and multiple target knowledge points are each associated with a basic knowledge point label. The knowledge graph contains target knowledge points for different learning levels, different grades, and different learning subjects. It is also understood as a knowledge domain visualization or knowledge domain mapping map. It is a series of various graphic data that show the knowledge development process and structural relationship. It uses visualization technology to describe knowledge resources and their carriers, and mine, analyze, construct, draw and display knowledge and their mutual connections.

Generally, before calculating the similarity between the text data and multiple target knowledge points to obtain similarity values, it is necessary to obtain the course information corresponding to the original data resource, query the course information from the preset knowledge graph to obtain multiple corresponding target knowledge points, and the knowledge graph contains target knowledge points of different learning levels, different grades, and different learning subjects. Calculate the similarity between the text data and multiple target knowledge points, that is, calculate the similarity values between the basic knowledge points in the text data and the target knowledge points, and based on the similarity values, determine the basic knowledge point labels corresponding to the text data, that is, the basic knowledge point labels corresponding to the original data resources. Depending on the original data resources, different corresponding course information can be obtained. Based on the course information, multiple target knowledge points corresponding to the original data resources can be queried from the preset knowledge graph, but the original data resources may not completely contain all the target knowledge points queried from the preset knowledge graph. The original data resources may contain one or more target knowledge points queried from the preset knowledge graph. Therefore, it is necessary to analyze the similarity values between the basic knowledge points in the original data resources and the target knowledge points in the preset knowledge graph. Based on the similarity values, the target knowledge points contained in the original data resources can be determined, and then the basic knowledge point labels that can be associated with the original data resources can be determined.

S303, performing sentence segmentation processing on the text data to obtain a sentence set, and performing block processing on the sentence set to obtain a word block set, and performing word segmentation processing on the sentence set to obtain a word set.

Among them, the sentence set refers to a set of multiple sentences obtained by performing sentence segmentation processing on text data, and the sentences in the sentence set are one or more complete sentences obtained by segmentation processing based on the text content, line breaks, punctuation marks, etc. of the text data. The word block set refers to a set of multiple phrases (word blocks) obtained by performing phrase segmentation on each sentence in the sentence set. The word set refers to a set of multiple words obtained by performing word segmentation on each sentence in the sentence set.

S304, calculating the importance weight of each word block in the word block set based on the keyword extraction TF-IDF algorithm.

Among them, the importance weight refers to the importance weight corresponding to each word block obtained after analyzing the word block based on the keyword extraction TF-IDF algorithm, that is, the TF-IDF value, and the weight refers to the frequency of each number in the weighted average, also known as the weight or weight.

Generally, TF-IDF (Term Frequency–Inverse Document Frequency) is a commonly used weighting technique for information retrieval and data mining. TF-IDF is a statistical method used to evaluate the importance of a word for a document set or one of the documents in a corpus. The importance of a word increases in direct proportion to the number of times it appears in the document, but at the same time it decreases in inverse proportion to the frequency of its appearance in the corpus. TF stands for term frequency, which means the number of times a corpus appears divided by the total number of sentences in the question-answer database. IDF stands for weight, which means the inverse document frequency of a word block. The main idea of IDF is: if there are fewer documents containing term t, that is, the smaller n is, the larger the IDF is, it means that term t has a good ability to distinguish categories. If the number of documents containing term t in a certain category of documents C is m, and the total number of documents containing t in other categories is k, it is obvious that the number of all documents containing t is n=m+k. When m is large, n is also large, and the IDF value obtained according to the IDF formula will be small, which means that the term t has a poor ability to distinguish categories.

The calculation process of the TF-IDF algorithm based on keyword extraction mainly includes: calculating word frequency, comparing text contents of different lengths, and standardizing the "word frequency" of word blocks; calculating inverse document frequency, using a corpus to simulate the language usage environment. If a word appears more times, the larger the denominator, the smaller the inverse document frequency (the closer to 0), and the denominator is added by 1 to avoid the situation where the denominator is 0 (that is, all documents do not contain the word); calculating the TF-IDF value. The TF-IDF value is proportional to the number of times a word appears in the text and inversely proportional to the number of times the word appears in the entire language. After calculating the TF-IDF value of each word in the text, it can be arranged in descending order according to the TF-IDF value.

S305: taking word blocks whose importance weight is greater than a first preset weight as reference content words, and taking word blocks whose importance weight is less than or equal to a second preset weight as reference high-frequency words.

The first preset value is the basis for screening reference content vocabulary, and the first preset weight and the second preset weight can be set according to actual needs. Reference content vocabulary refers to a phrase containing a certain meaning. The second preset weight is the basis for screening reference high-frequency vocabulary, and usually the first preset weight is less than the second preset weight.

Generally, after scoring the importance of each word block in the word block set based on the keyword extraction TF-IDF algorithm, the word blocks with importance weights can be sorted in descending order, and the first 1/3 of the word blocks in descending order are taken as reference content words, and the last 1/3 of the word blocks in descending order are taken as reference high-frequency words.

S306, calculating the similarity value between the reference content vocabulary and the target content vocabulary, and the similarity value between the reference high-frequency vocabulary and the target high-frequency vocabulary.

Among them, the similarity value refers to the similarity relationship between the two quantities being compared. Generally, the larger the similarity value, the more similar the two quantities are. Here, the similarity value can be the similarity value between the reference content vocabulary and the target content vocabulary and the similarity value between the reference high-frequency vocabulary and the target high-frequency vocabulary. The target content vocabulary and the target high-frequency vocabulary are both target knowledge points in the knowledge graph corresponding to the course information of the original data resource, and the reference content vocabulary and the reference high-frequency vocabulary are basic knowledge points in the text data of the original data resource.

S307 , when the similarity value is greater than the similarity threshold, obtaining basic knowledge point labels associated with the target content vocabulary and basic knowledge point labels associated with the target high-frequency vocabulary.

Among them, the similarity threshold refers to the lowest lower limit value at which the similarity value can meet the conditions, that is, the similarity critical value. Depending on the basic knowledge points, the corresponding similarity thresholds may also be different. The similarity threshold corresponding to the reference content vocabulary is different from the similarity threshold corresponding to the reference high-frequency vocabulary. The basic knowledge point label is associated with the target knowledge point in the knowledge graph. If the basic knowledge points of the original data resource contain basic knowledge points whose similarity values with the target knowledge points in the knowledge graph are greater than the similarity threshold, then the basic knowledge point can be associated with the basic knowledge point label of the corresponding target knowledge point. Labels are data used to describe the characteristics of data resources. Different data resources correspond to different label data. Labels can effectively represent the knowledge points, learning content or learning abilities involved in the data resources, and by marking data resources with different labels, the screening and analysis of data resources can be achieved.

For example: the sentence set {S1, S2…Sn} obtained by segmentation is divided into chunks (Chunk) by sentence to obtain the word chunk sets {B11, B12…B1m1}, {B21, B22…}… corresponding to each sentence. Since the reference content vocabulary is mostly based on the vocabulary of the learning topic, in order to speed up the calculation speed, the TF-IDF algorithm based on keyword extraction is used to score the importance of each word chunk set {B11, B12…B1m1}, {B21, B22…}… to obtain the importance weight of the word chunk in each word chunk set. After sorting the importance weight in descending order, the first 1/3 of the word chunks are taken as the reference content vocabulary, that is, the word chunks with importance weights greater than the first preset weight are taken as reference content vocabulary. According to the content vocabulary, similarity is calculated with the target content vocabulary in turn. The reference content vocabulary is denoted as Bi and the target content vocabulary is denoted as Kj. The edit distance similarity sim_raw1, the edit distance familiarity sim_lemma1 and the semantic similarity sim_sem1 of Bi and Kj are calculated respectively. According to the above similarities, the total similarity value voc_score1 = vocα·sim_raw+vocβ··sim_lemma+vocγ·sim_sem is calculated. If the total similarity value is higher than the first preset similarity threshold voc_score_threshold1, the reference content vocabulary Bi is marked with the knowledge point label associated with the target content vocabulary Kj.

For example: the sentence set {S1, S2…Sn} obtained by segmentation is divided into chunks (Chunk) according to the sentences to obtain the word chunk sets {B11, B12…B1m1}, {B21, B22…}… corresponding to each sentence. Since the reference content vocabulary is mostly based on the vocabulary of the learning topic, in order to speed up the calculation, the TF-IDF algorithm based on keyword extraction is used to score the importance of each word chunk set {B11, B12…B1m1}, {B21, B22…}… to obtain the importance weight of the word chunk in each word chunk set. After sorting the importance weights in descending order, the last 1/3 of the word chunks are taken as reference high-frequency words, and are sequentially compared with the target high-frequency words. The reference high-frequency vocabulary is denoted as Ba, and the target high-frequency vocabulary is denoted as Kb. The edit distance similarity sim_raw2, the edit distance familiarity sim_lemma2 and the semantic similarity sim_sem2 of Ba and Kb are calculated respectively. According to the above similarities, the total similarity value voc_score2 = vocα·sim_raw+vocβ·sim_lemma+vocγ·sim_sem is calculated. If the total similarity value is higher than the preset similarity threshold voc_score_threshold2, the reference high-frequency vocabulary Ba will be annotated with the knowledge point label associated with the target high-frequency vocabulary Kb.

S308: Add the basic knowledge point tags associated with the target content vocabulary and the basic knowledge point tags associated with the target high-frequency vocabulary to the basic knowledge point tag set.

Among them, the basic knowledge point label set is a set of basic knowledge point labels corresponding to the original data resources. The basic knowledge point labels included in the basic knowledge point label set are basic knowledge point labels associated with target knowledge points whose similarity values are greater than the similarity threshold. Depending on the basic knowledge point, the corresponding similarity threshold is also different. The number of basic knowledge point labels in the basic knowledge point label set is related to the content of the original data resources, and the basic knowledge point labels in the basic knowledge point label set are associated with the original data resources, that is, the basic knowledge point labels in the basic knowledge point label set are equivalent to the basic knowledge point labels corresponding to the original data resources that have been annotated.

S309, performing part-of-speech tagging on each word in the word set to obtain a part-of-speech tagging set.

Among them, the part-of-speech tag set refers to the part-of-speech set corresponding to each word in the word set, and each word in the word set has a one-to-one mapping relationship with each part-of-speech in the part-of-speech tag set. The parts of speech in the part-of-speech tag set can include nouns, verbs, adjectives, numerals, quantifiers, pronouns, adverbs, prepositions, conjunctions, auxiliary words, interjections, onomatopoeia, etc. The specific part of speech is still related to the learning content in the original data resources.

Generally, the part-of-speech tagging process usually needs to determine the most appropriate part-of-speech corresponding to each word based on the context of the sentence. In the part-of-speech tagging process, there may be a situation where a word has multiple parts, such as a word that can be used as both a noun and a verb, also known as a polysemous word, which has a high probability of appearing in common words. This situation can be solved by using probability methods, such as using HMM (Hidden Markov Model) to process the tagging of such words. In addition, words can also be tagged based on conversion ideas or classification ideas.

S310, taking the words whose part of speech is a verb as reference verb vocabulary, and taking the words whose part of speech is a numeral as reference mathematical vocabulary.

Generally, by performing part-of-speech analysis on the words in the word set, the parts of speech corresponding to the words contained in the original data resource can be obtained. Therefore, the words with the verb part-of-speech and the numeral part-of-speech can be screened out separately according to the part-of-speech, and the words with the verb part-of-speech can be used as reference verb vocabulary knowledge points, and the words with the numeral part-of-speech can be used as reference mathematical vocabulary knowledge points.

S311, calculating the similarity value between the reference verb vocabulary and the target verb vocabulary, and the similarity value between the reference math vocabulary and the target math vocabulary.

Among them, the reference verb vocabulary and the reference math vocabulary are both basic knowledge points contained in the original data resources, and the target verb vocabulary and the target math vocabulary are both target knowledge points in the knowledge graph corresponding to the course information of the original data resources. The similarity value refers to the similarity relationship between the two quantities being compared. Generally, the larger the similarity value, the more similar the two quantities are. Here, the similarity value can be the similarity value between the reference verb vocabulary and the target verb vocabulary and the similarity value between the reference math vocabulary and the target math vocabulary.

S312, when the similarity value is greater than the similarity threshold, obtaining basic knowledge point labels associated with the target verb vocabulary and basic knowledge point labels associated with the target mathematics vocabulary.

Among them, the similarity threshold refers to the lowest lower limit value at which the similarity value can meet the conditions, that is, the similarity critical value. Depending on the basic knowledge points, the corresponding similarity thresholds may also be different. The similarity threshold corresponding to the reference verb vocabulary is different from the similarity threshold corresponding to the reference mathematical vocabulary.

S313, adding the basic knowledge point labels associated with the target verb vocabulary and the basic knowledge point labels associated with the target mathematics vocabulary to the basic knowledge point label set.

Among them, the basic knowledge point label is associated with the target knowledge point in the knowledge graph. If the basic knowledge points of the original data resource contain basic knowledge points whose similarity value with the target knowledge point in the knowledge graph is greater than the similarity threshold, then the basic knowledge point can be associated with the basic knowledge point label of the corresponding target knowledge point. Labels are data used to describe the characteristics of data resources. Different data resources correspond to different label data. Labels can effectively represent the knowledge points, learning content or learning ability involved in the data resources, and by marking data resources with different labels, the screening and analysis of data resources can be realized.

For example: the sentence set {S1, S2…Sn} obtained by segmentation is processed sentence by sentence to obtain the word set {{T11, T12…T1o1}, {T21, T22…T2o2}…} corresponding to each sentence, each word in the word set is tagged with part of speech to obtain a part of speech tagging set, and the words with the part of speech of verb part of speech are used as reference verb vocabulary, and the words with the part of speech of numeral part of speech are used as reference mathematical vocabulary; the reference verb vocabulary is calculated with the target verb vocabulary in turn, the reference verb vocabulary is recorded as Vi, and the target verb vocabulary is recorded as Uj; the numeral vocabulary is calculated with the target numeral vocabulary in turn, the numeral vocabulary is recorded as Va, and the target numeral vocabulary is recorded as Ub, and the edit distance similarity value sim_raw3 of Vi and Uj is calculated respectively, and the edit distance familiarity sim_lemma3 and semantic similarity sim_sem3 after part of speech restoration are calculated, and the total similarity value vo is calculated based on the above similarities c_score3=vocα·sim_raw+vocβ·sim_lemma+vocγ·sim_sem. If the total similarity value is higher than the third preset similarity threshold voc_score_threshold3, the knowledge point label associated with the target verb vocabulary Uj will be marked with the reference verb vocabulary Vi; and the edit distance similarity value sim_raw4 of Va and Ub, the edit distance familiarity sim_lemma4 and the semantic similarity sim_sem4 after part-of-speech restoration are calculated respectively. According to the above similarities, the total similarity value voc_score4=vocα·sim_raw+vocβ·sim_lemma+vocγ·sim_sem is calculated. If the total similarity value is higher than the fourth preset similarity threshold voc_score_threshold4, the numeral vocabulary Va will be marked with the knowledge point label associated with the target numeral vocabulary Ub.

S314, analyzing each word in the word set, and adding phonetic symbols to each word to obtain a phonetic symbol set.

The phonetic symbol set is a set containing phonetic symbols corresponding to each word in the word set, and there is a one-to-one mapping relationship between each word in the word set and each phonetic symbol in the phonetic symbol set.

S315, calculating the similarity value between the word phonetic symbol in the phonetic symbol set and the target phonetic symbol.

Among them, the word phonetic symbols in the phonetic symbol set are the basic knowledge points contained in the original data resources, and the target phonetic symbols are the target knowledge points in the knowledge graph corresponding to the course information of the original data resources. The similarity value refers to the similarity relationship between the two quantities being compared. Generally, the larger the similarity value, the more similar the two quantities are. Here, the similarity value can be the similarity value between the word phonetic symbols and the target phonetic symbols.

S316: When the similarity value is greater than the similarity threshold, obtain the basic knowledge point label associated with the target phonetic symbol.

Among them, the similarity threshold refers to the lowest lower limit value at which the similarity value can meet the conditions, that is, the similarity critical value. Depending on the basic knowledge points, the corresponding similarity thresholds may also be different. The similarity thresholds corresponding to the word phonetic symbols can be set arbitrarily according to needs, and may also be different from the similarity thresholds mentioned above.

S317, adding the basic knowledge point label associated with the target phonetic symbol to the basic knowledge point label set.

Among them, the basic knowledge point label is associated with the target knowledge point in the knowledge graph. If the basic knowledge points of the original data resource contain basic knowledge points whose similarity value with the target knowledge point in the knowledge graph is greater than the similarity threshold, then the basic knowledge point can be associated with the basic knowledge point label of the corresponding target knowledge point. Labels are data used to describe the characteristics of data resources. Different data resources correspond to different label data. Labels can effectively represent the knowledge points, learning content or learning ability involved in the data resources, and by marking data resources with different labels, the screening and analysis of data resources can be realized.

For example: the sentence set {S1, S2…Sn} obtained by segmentation is processed sentence by sentence to obtain the word set {{T11, T12…T1o1}, {T21, T22…T2o2}…} corresponding to each sentence, and the words in the word set are converted into the corresponding phonetic symbol set {{P11, P12…P1o1}, {P21, P22…P2o2}…} through the dictionary tool, and the word phonetic symbol Pi in the phonetic symbol set is calculated with the target phonetic symbol Kj in turn for similarity, including whether the pronunciation combination is in the source word Ti corresponding to the word phonetic symbol Pi The similarity sim_in, the edit distance similarity sim_edit between Pi and Kj, and the longest common substring similarity sim_lcs between the word phonetic symbol Pi and the target phonetic symbol Kj are included. According to the above scores, the total similarity value phon_score = phonα·sim_in+phonβ·sim_edit+phonγ·sim_lcs is calculated. If the total similarity value is higher than the preset similarity threshold phon_score_threshold, the word phonetic symbol Pi is annotated with the knowledge point label associated with the target phonetic symbol Kj.

S318, performing dependency syntactic analysis on the sentences in the sentence set to obtain a dependency syntactic tree.

Among them, the dependency syntax tree refers to a relationship tree that can describe the dependency relationship between each word in the data resource, and can express the syntactic collocation relationship between each word, which is related to semantics. The basic task of dependency syntax analysis is to determine the syntactic structure of a sentence or the dependency relationship between words in a sentence. It mainly includes two aspects: determining the grammatical system of the language, that is, giving a formal definition of the grammatical structure of legal sentences in the language; syntactic analysis technology, that is, automatically deriving the syntactic structure of a sentence based on a given grammatical system, and analyzing the syntactic units contained in the sentence and the relationship between the syntactic units.

S319, calculating the similarity values between the words in the word set, the parts of speech in the part-of-speech tag set, and the dependency syntax tree and the words, parts of speech, and syntax trees in the target sentence respectively.

Among them, the similarity value refers to the similarity relationship between the two quantities being compared. Generally, the larger the similarity value, the more similar the two quantities are. Here, the similarity value can be the similarity value corresponding to the words in the word set of the original data resource, the parts of speech in the part-of-speech tag set and the dependency syntax tree with the words, parts of speech and syntax tree in the target sentence.

S320: When the similarity value is greater than the similarity threshold, obtain a basic knowledge point label associated with the target sentence.

Among them, the similarity threshold refers to the lowest lower limit value at which the similarity value can meet the conditions, that is, the similarity critical value. Depending on the basic knowledge points, the corresponding similarity thresholds may also be different. The similarity thresholds corresponding to the words in the word set, the parts of speech in the part-of-speech tag set, and the dependency syntax tree can be set arbitrarily according to needs, and may also be different from the similarity thresholds mentioned above.

S321, adding the basic knowledge point tag associated with the target sentence pattern to the basic knowledge point tag set.

Among them, the basic knowledge point label is associated with the target knowledge point in the knowledge graph. If the basic knowledge points of the original data resource contain basic knowledge points whose similarity value with the target knowledge point in the knowledge graph is greater than the similarity threshold, then the basic knowledge point can be associated with the basic knowledge point label of the corresponding target knowledge point. Labels are data used to describe the characteristics of data resources. Different data resources correspond to different label data. Labels can effectively represent the knowledge points, learning content or learning ability involved in the data resources, and by marking data resources with different labels, the screening and analysis of data resources can be realized.

For example: the sentence set {S1, S2…Sn} obtained by segmentation is processed by sentence segmentation to obtain the word set {{T11, T12…T1o1}, {T21, T22…T2o2}…} corresponding to each sentence, and the sentence set {S1, S2…Sn} is processed by part-of-speech tagging and dependency syntax analysis to obtain the part-of-speech tagging set {{Pos11, Pos12…Pos1o1}, {Pos21, Pos22…Pos2o2}…}, dependency syntax tree {Tree1, Tree2…Treen}, and then the jaccard similarity value sim_token_jaccard, part-of-speech tagging of the word set {Ti1, Ti2…Tim}, Ti1＝{T11, T12…T1o1} and the example sentence set {KTj1, KTj2…KTjn} of the target sentence knowledge point are calculated in turn. The edit distance similarity sim_pos_edit between the set {Posi1, Posi2…Posio1} and the part-of-speech tagging set {KPosj1, KPosj2…KPosjn} of the target sentence knowledge point example, the longest common substring similarity value sim_pos_lcs, the tree similarity sim_tree between Treei and the target sentence knowledge point example KTreej, and the total similarity value sent_score = sentα·sim_token_jaccard+sentβ·sim_pos_edit+sentγ·sim_pos_lcs+sentθ·sim_tree is calculated based on the above similarity values. If the total similarity value is higher than the preset similarity threshold sent_score_threshold, the sentence Si is annotated with the basic knowledge point label associated with the Kj sentence.

S322, calculating the similarity value between the grammar included in the sentence set and the target grammar based on the word set and the part-of-speech tag set.

The grammar contained in the sentence set is the basic knowledge point of the original data resource, and the target grammar is the target knowledge point in the knowledge graph corresponding to the course information of the original data resource. The similarity value refers to the similarity relationship between the two quantities being compared. Generally, the larger the similarity value, the more similar the two quantities are. Here, the similarity value can be the similarity value between the grammar in the word set of the original data resource and the target grammar.

S323: When the similarity value is greater than the similarity threshold, obtain the basic knowledge point label associated with the target grammar.

Among them, the similarity threshold refers to the lowest lower limit value at which the similarity value can meet the conditions, that is, the similarity critical value. Depending on the basic knowledge points, the corresponding similarity thresholds may also be different. The similarity threshold corresponding to the grammar in the word set can be set arbitrarily according to needs, and may also be different from the similarity threshold described above.

S324, adding the basic knowledge point label associated with the target grammar to the basic knowledge point label set.

Among them, the basic knowledge point label is associated with the target knowledge point in the knowledge graph. If the basic knowledge points of the original data resource contain basic knowledge points whose similarity value with the target knowledge point in the knowledge graph is greater than the similarity threshold, then the basic knowledge point can be associated with the basic knowledge point label of the corresponding target knowledge point. Labels are data used to describe the characteristics of data resources. Different data resources correspond to different label data. Labels can effectively represent the knowledge points, learning content or learning ability involved in the data resources, and by marking data resources with different labels, the screening and analysis of data resources can be realized.

For example: the sentence set {S1, S2…Sn} obtained after segmentation is processed sentence by sentence to obtain the word set {{T11, T12…T1o1}, {T21, T22…T2o2}…} corresponding to each sentence, and the sentence set {S1, S2…Sn} is processed by part-of-speech tagging to obtain the part-of-speech tagging set {{Pos11, Pos12…Pos1o1}, {Pos21, Pos22…Pos2o2}…}, and calculate whether the grammatical fragment is included in the word set {Ti1, Ti2…Tim}, Ti1＝{T11, T12…T1o1}, Ti2＝{T21, T22…T2o2}… or the part-of-speech tagging set {KPosj1, KPosj2…KPosjn}, KPosj1＝{Pos11 ,Pos12…Pos1o1}, KPosj2＝{Pos21,Pos22…Pos2o2}…in inclusion similarity sim_in, position similarity sim_position of the grammatical fragment in the word Ti1＝{T11,T12…T1o1} and the target word {KTj1,KTj2…KTjn}, part-of-speech similarity sim_pos of the grammatical fragment, according to the above similarities, calculate the total similarity value gram＝gramα·sim_in+gramβ·sim_position+gramγ·sim_pos, if the total similarity value is higher than the preset similarity threshold gram_score_threshold, then mark the sentence Si with the basic knowledge point label associated with the target sentence Kj grammar.

For example, the calculation can obtain the labels and quantities of basic knowledge points corresponding to the original data resources, which can be recorded as: Tag(Text) = {voc:num1,verb:num2,math:num3,hfw:num4,phon:num5,sent:num5,gram:num7|numi> = 0}. The entire process of calculating the similarity between the basic knowledge points of the original data resources and the target knowledge points corresponding to the course information of the original data resources in the knowledge graph can be seen in Figure 4.

S325 , generating a comprehensive knowledge point label set of the original data resource according to the feature information of the original data resource and the basic knowledge point label set.

Among them, the characteristic information refers to the type of the original data resource, such as the type of the original data resource can include audio, video, text, picture book and other types, and different types can train/exercise different learning abilities (such as listening, speaking, reading and writing abilities). The comprehensive knowledge point label in the comprehensive knowledge point label set refers to the knowledge point label that can reflect the ability of the original data resource to train the user (student) based on the characteristic information of the original data resource and the basic knowledge point label set. There can be multiple comprehensive knowledge point labels corresponding to one original data resource. For example, if the original data resource contains audio, and the basic knowledge point label set contains knowledge point labels associated with the target phonetic symbol, then it can be analyzed that the comprehensive knowledge point label corresponding to the original data resource is a listening label.

Generally, the comprehensive knowledge point labels of the original data resources are related to the characteristics of the original data resources themselves. The comprehensive knowledge point labels in the comprehensive knowledge point label set and the basic knowledge point labels in the basic knowledge point label set are both associated with the original data resources. After the basic knowledge point label set and the comprehensive knowledge point label set are generated, it means that the original data resources have been marked with relevant knowledge point labels (including basic knowledge point labels and comprehensive knowledge point labels).

When the scheme of the embodiment of the present application is executed, the server pre-processes the original data resource to obtain text data, queries the attribute information corresponding to the original data resource from the preset knowledge graph, obtains multiple target knowledge points corresponding to the attribute information, performs sentence segmentation processing on the text data to obtain a sentence set, and performs block processing on the sentence set to obtain a word block set, calculates the importance weight of each word block in the word block set based on the keyword extraction TF-IDF algorithm, takes the word block with an importance weight greater than the first preset weight as the reference content word, takes the word block with an importance weight less than or equal to the second preset weight as the reference high-frequency word, calculates the reference content word and the target content word, and the reference high-frequency word The similarity value between the target high-frequency vocabulary and the target content vocabulary is calculated. When the similarity value is greater than the similarity threshold, the basic knowledge point label associated with the target content vocabulary and the basic knowledge point label associated with the target high-frequency vocabulary are obtained, and the basic knowledge point label associated with the target content vocabulary and the basic knowledge point label associated with the target high-frequency vocabulary are added to the basic knowledge point label set. Based on the word set, each word in the word set is tagged with a part of speech to obtain a part of speech tag set. The words with a verb part of speech are used as reference verb vocabulary, and the words with a numeral part of speech are used as reference mathematical vocabulary. The similarity value between the reference verb vocabulary and the target verb vocabulary, as well as the similarity value between the reference mathematical vocabulary and the target mathematical vocabulary are calculated. When the similarity value is greater than the similarity threshold, When the target verb vocabulary is obtained, the basic knowledge point label associated with the target mathematical vocabulary is obtained, and the basic knowledge point label associated with the target verb vocabulary and the basic knowledge point label associated with the target mathematical vocabulary are added to the basic knowledge point label set, each word in the word set is analyzed, and each word is marked with a phonetic symbol to obtain a phonetic symbol set, and the similarity value between the word phonetic symbol in the phonetic symbol set and the target phonetic symbol is calculated. When the similarity value is greater than the similarity threshold, the basic knowledge point label associated with the target phonetic symbol is obtained, and the basic knowledge point label associated with the target phonetic symbol is added to the basic knowledge point label set, and the sentences in the sentence set are subjected to dependency syntactic analysis to obtain a dependency syntactic tree, and the words, words and phrases in the word set are calculated. The similarity values of the parts of speech and dependency syntax trees in the part-of-speech tagging set and the words, parts of speech and syntax trees in the target sentence are respectively obtained. When the similarity value is greater than the similarity threshold, the basic knowledge point labels associated with the target sentence are obtained, and the basic knowledge point labels associated with the target sentence are added to the basic knowledge point label set. The similarity values of the grammar contained in the sentence set and the target grammar are calculated based on the word set and the part-of-speech tagging set. When the similarity value is greater than the similarity threshold, the basic knowledge point labels associated with the target grammar are obtained, and the basic knowledge point labels associated with the target grammar are added to the basic knowledge point label set. The comprehensive knowledge point label set of the original data resource is generated according to the feature information of the original data resource and the basic knowledge point label set. In this way, the original data resource can be quickly and accurately labeled with the knowledge point labels related to it, thereby improving the efficiency and accuracy of the labeling.

As described above, the embodiments are mainly described by taking the online education industry as an example, but those skilled in the art understand that the applicability of the present method is not limited to the online education industry. For example, the method described in this application can be applied to user tag processing in various industries such as retail, transportation, social networking, search, education, and medical care.

The following are device embodiments of the present application, which can be used to execute the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.

Please refer to FIG5 , which shows a schematic diagram of the structure of a data resource annotation device provided by an exemplary embodiment of the present application. Hereinafter referred to as device 5, device 5 can be implemented as all or part of a terminal through software, hardware, or a combination of both. Device 5 includes a preprocessing module 501, a computing module 502, a first processing module 503, and a second processing module 504.

A preprocessing module 501 is used to preprocess the original data resources to obtain text data;

A calculation module 502 is used to calculate similarity values between the text data and multiple target knowledge points respectively to obtain similarity values; wherein each of the multiple target knowledge points is associated with a basic knowledge point label;

The first processing module 503 is used to generate a basic knowledge point label set of the original data resource according to the comparison result of the similarity value and the similarity threshold; wherein the basic knowledge point labels included in the basic knowledge point label set are: basic knowledge point labels associated with target knowledge points whose similarity values are greater than the similarity threshold;

The second processing module 504 is used to generate a comprehensive knowledge point label set of the original data resource according to the feature information of the original data resource and the basic knowledge point label set.

Optionally, the device 5 further comprises:

A query unit is used to query the attribute information corresponding to the original data resource from the preset knowledge graph to obtain the multiple target knowledge points corresponding to the attribute information.

Optionally, the original data resource in the device 5 is a teaching resource, and the attribute information is course information.

Optionally, the first processing module 503 includes:

A first processing unit is used to perform sentence segmentation processing on the text data to obtain a sentence set, and to perform block processing on the sentence set to obtain a word block set, and to perform word segmentation processing on the sentence set to obtain a word set;

A first calculation unit is used to analyze the word block set and the word set to obtain a reference word set, and calculate the similarity value between each reference word in the reference word set and the corresponding target knowledge point; wherein the reference word set includes reference content words, reference high-frequency words, reference verb words and reference mathematics words, the target knowledge point corresponding to the reference content words is the target content words, the target knowledge point corresponding to the reference high-frequency words is the target high-frequency words, the target knowledge point corresponding to the reference verb words is the target verb words, and the target knowledge point corresponding to the reference mathematics words is the target mathematics words;

A first adding unit is used to add the basic knowledge point labels corresponding to the respective corresponding target knowledge points to the basic knowledge point label set when the similarity values of the respective corresponding target knowledge points are greater than the respective corresponding similarity thresholds; or

A second processing unit is used to perform sentence segmentation processing on the text data to obtain a sentence set, and perform word segmentation processing on the sentence set to obtain a word set;

The second calculation unit is used to analyze the word set to obtain a phonetic symbol set, a part-of-speech tag set and a dependency syntax tree, and calculate the similarity values between the word phonetic symbols in the phonetic symbol set, the sentence patterns in the sentence set and the grammar in the sentence set and their corresponding target knowledge points; wherein the target knowledge point corresponding to the word phonetic symbol is the target phonetic symbol, the target knowledge point corresponding to the sentence pattern is the target sentence pattern, and the target knowledge point corresponding to the grammar is the target grammar;

The second adding unit is used to add the basic knowledge point labels corresponding to the respective corresponding target knowledge points to the basic knowledge point label set when the similarity values of the respective corresponding target knowledge points are greater than the respective corresponding similarity thresholds.

Optionally, the first processing module 503 includes:

A third processing unit is used to perform sentence segmentation processing on the learning text data to obtain a sentence set, and to perform block processing on the sentence set to obtain a word block set;

A third calculation unit is used to calculate the importance weight of each word block in the word block set based on the keyword extraction TF-IDF algorithm;

A first selection unit, configured to select the word block whose importance weight is greater than a first preset weight as the reference content vocabulary;

a fourth calculation unit, configured to calculate a similarity value between the reference content vocabulary and the target content vocabulary;

A first acquisition unit, configured to acquire a basic knowledge point label associated with the target content vocabulary when the similarity value is greater than a similarity threshold;

The first adding unit is used to add the basic knowledge point tag associated with the target content vocabulary to the basic knowledge point tag set.

Optionally, the first processing module 503 includes:

A fourth processing unit, configured to perform sentence segmentation processing on the text data to obtain a sentence set, and to perform block processing on the sentence set to obtain a word block set;

A fourth calculation unit, used for calculating the importance weight of each word block in the word block set based on the keyword extraction TF-IDF algorithm;

A second selection unit, configured to select the word block whose importance weight is less than or equal to a second preset weight as the reference high-frequency word;

a fifth calculation unit, configured to calculate a similarity value between the reference high-frequency vocabulary and the target high-frequency vocabulary;

A second acquisition unit, configured to acquire a basic knowledge point label associated with the target high-frequency vocabulary when the similarity value is greater than a similarity threshold;

The second adding unit is used to add the basic knowledge point label associated with the target high-frequency vocabulary into the basic knowledge point label set.

Optionally, the first processing module 503 includes:

A fifth processing unit, configured to perform sentence segmentation processing on the text data to obtain a sentence set, and perform word segmentation processing on the sentence set to obtain a word set;

A first tagging unit, configured to perform part-of-speech tagging on each word in the word set to obtain a part-of-speech tagging set;

A third selection unit is used to use the word whose part of speech is a verb as a reference verb vocabulary;

a sixth calculation unit, configured to calculate a similarity value between the reference verb vocabulary and the target verb vocabulary;

A third acquisition unit, configured to acquire a basic knowledge point label associated with the target verb vocabulary when the similarity value is greater than a similarity threshold;

The third adding unit is used to add the basic knowledge point label associated with the target verb vocabulary to the basic knowledge point label set.

Optionally, the first processing module 503 includes:

a sixth processing unit, configured to perform sentence segmentation processing on the text data to obtain a sentence set, and perform word segmentation processing on the sentence set to obtain a word set;

A second tagging unit, configured to perform part-of-speech tagging on each word in the word set to obtain a part-of-speech tagging set;

A fourth selection unit, configured to use the words whose part of speech is a numeral as reference mathematical vocabulary;

a seventh calculation unit, configured to calculate a similarity value between the reference mathematical vocabulary and the target mathematical vocabulary;

A fourth acquisition unit, configured to acquire a basic knowledge point label associated with the target mathematical vocabulary when the similarity value is greater than a similarity threshold;

The fourth adding unit is used to add the basic knowledge point label associated with the target mathematical vocabulary into the basic knowledge point label set.

Optionally, the first processing module 503 includes:

a seventh processing unit, configured to perform sentence segmentation processing on the text data to obtain a sentence set, and perform word segmentation processing on the sentence set to obtain a word set;

A third marking unit is used to analyze each word in the word set and mark the words with phonetic symbols to obtain a phonetic symbol set;

an eighth calculation unit, configured to calculate a similarity value between the word phonetic symbol in the phonetic symbol set and the target phonetic symbol;

A fifth selection unit, configured to obtain a basic knowledge point label associated with the target phonetic symbol when the similarity value is greater than a similarity threshold;

The fifth adding unit is used to add the basic knowledge point label associated with the target phonetic symbol to the basic knowledge point label set.

Optionally, the first processing module 503 includes:

an eighth processing unit, configured to perform sentence segmentation processing on the text data to obtain a sentence set, and perform word segmentation processing on the sentence set to obtain a word set;

A fourth tagging unit, configured to perform part-of-speech tagging on each word in the word set based on the word set to obtain a part-of-speech tagging set;

An analysis unit, configured to perform dependency syntactic analysis on the sentences in the sentence set to obtain a dependency syntactic tree;

A ninth calculation unit, configured to calculate similarity values corresponding to the words in the word set, the parts of speech in the part-of-speech tag set, and the dependency syntax tree and the words, parts of speech, and syntax tree in the target sentence respectively;

A fifth acquisition unit, configured to acquire a basic knowledge point label associated with the target sentence when the similarity value is greater than a similarity threshold;

The sixth adding unit is used to add the basic knowledge point tag associated with the target sentence pattern to the basic knowledge point tag set.

Optionally, the first processing module 503 includes:

A ninth processing unit, configured to perform sentence segmentation processing on the text data to obtain a sentence set, and perform word segmentation processing on the sentence set to obtain a word set;

A fifth tagging unit, configured to perform part-of-speech tagging on each word in the word set based on the word set to obtain a part-of-speech tagging set;

a tenth calculation unit, configured to calculate a similarity value between the grammar included in the sentence set and the target grammar based on the word set and the part-of-speech tag set;

A sixth acquisition unit, configured to acquire a basic knowledge point label associated with the target grammar when the similarity value is greater than a similarity threshold;

A seventh adding unit is used to add the basic knowledge point label associated with the target grammar to the basic knowledge point label set.

It should be noted that the device 5 provided in the above embodiment only uses the division of the above functional modules as an example when executing the data resource labeling method. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the data resource labeling method embodiments provided in the above embodiment belong to the same concept, and the implementation process thereof is detailed in the method embodiment, which will not be repeated here.

As described above, the embodiments are mainly described by taking the online education industry as an example, but those skilled in the art understand that the applicability of the present method is not limited to the online education industry. For example, the method described in this application can be applied to user tag processing in various industries such as retail, transportation, social networking, search, education, and medical care.

Figure 6 is a schematic diagram of the structure of a data resource annotation device provided in an embodiment of the present application, hereinafter referred to as device 6. Device 6 can be integrated into the aforementioned server or terminal device. As shown in Figure 6, the device includes: a memory 602, a processor 601, an input device 603, an output device 604 and a communication interface.

The memory 602 may be an independent physical unit, and may be connected to the processor 601, the input device 603, and the output device 604 via a bus. The memory 602, the processor 601, the input device 603, and the output device 604 may also be integrated together and implemented by hardware.

The memory 602 is used to store programs for implementing the above method embodiments or various modules of the device embodiments, and the processor 601 calls the program to execute the operations of the above method embodiments.

The input device 602 includes but is not limited to a keyboard, a mouse, a touch panel, a camera and a microphone; the output device includes but is not limited to a display screen.

The communication interface is used to send and receive various types of messages, and the communication interface includes but is not limited to a wireless interface or a wired interface.

Optionally, when part or all of the distributed task scheduling method in the above embodiment is implemented by software, the device may also include only a processor. The memory for storing the program is located outside the device, and the processor is connected to the memory through a circuit/wire to read and execute the program stored in the memory.

The processor may be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and a NP.

The processor may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD) or a combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL) or any combination thereof.

The memory may include volatile memory, such as random-access memory (RAM); the memory may also include non-volatile memory, such as flash memory, hard disk drive (HDD) or solid-state drive (SSD); the memory may also include a combination of the above types of memory.

The processor 601 calls the program code in the memory 602 to perform the following steps:

Preprocess the original data resources to obtain text data;

Calculating similarity values between the text data and multiple target knowledge points respectively to obtain similarity values; wherein each of the multiple target knowledge points is associated with a basic knowledge point label;

Generate a basic knowledge point label set of the original data resource according to the comparison result of the similarity value and the similarity threshold; wherein the basic knowledge point labels included in the basic knowledge point label set are: basic knowledge point labels associated with target knowledge points whose similarity values are greater than the similarity threshold;

A comprehensive knowledge point label set of the original data resource is generated according to the feature information of the original data resource and the basic knowledge point label set.

In one or more embodiments, the processor 601 is further configured to:

The attribute information corresponding to the original data resource is queried from a preset knowledge graph to obtain the multiple target knowledge points corresponding to the attribute information.

In one or more embodiments, the processor 601 is further configured to:

Performing sentence segmentation processing on the text data to obtain a sentence set, and performing block processing on the sentence set to obtain a word block set, and performing word segmentation processing on the sentence set to obtain a word set;

Analyze the word block set and the word set to obtain a reference word set, and calculate the similarity value between each reference word in the reference word set and the corresponding target knowledge point; wherein the reference word set includes reference content words, reference high-frequency words, reference verb words and reference mathematics words, the target knowledge point corresponding to the reference content words is the target content words, the target knowledge point corresponding to the reference high-frequency words is the target high-frequency words, the target knowledge point corresponding to the reference verb words is the target verb words, and the target knowledge point corresponding to the reference mathematics words is the target mathematics words;

When the similarity values of the respective corresponding target knowledge points are greater than the respective corresponding similarity thresholds, adding the basic knowledge point labels corresponding to the respective corresponding target knowledge points to the basic knowledge point label set; or

Performing sentence segmentation processing on the text data to obtain a sentence set, and performing word segmentation processing on the sentence set to obtain a word set;

Analyze the word set to obtain a phonetic symbol set, a part-of-speech tag set and a dependency syntax tree, and calculate similarity values between the word phonetic symbols in the phonetic symbol set, the sentence patterns in the sentence set and the grammar in the sentence set and their corresponding target knowledge points; wherein the target knowledge point corresponding to the word phonetic symbol is the target phonetic symbol, the target knowledge point corresponding to the sentence pattern is the target sentence pattern, and the target knowledge point corresponding to the grammar is the target grammar;

When the similarity values of the respectively corresponding target knowledge points are greater than the respectively corresponding similarity thresholds, the basic knowledge point labels corresponding to the respectively corresponding target knowledge points are added to the basic knowledge point label set.

In one or more embodiments, the processor 601 is further configured to:

Performing sentence segmentation processing on the text data to obtain a sentence set, and performing block processing on the sentence set to obtain a word block set;

Calculate the importance weight of each word block in the word block set based on the keyword extraction TF-IDF algorithm;

The word block whose importance weight is greater than the first preset weight is used as the reference content vocabulary;

Calculating a similarity value between the reference content vocabulary and the target content vocabulary;

When the similarity value is greater than the similarity threshold, obtaining a basic knowledge point label associated with the target content vocabulary;

The basic knowledge point tags associated with the target content vocabulary are added to the basic knowledge point tag set.

In one or more embodiments, the processor 601 is further configured to:

Performing sentence segmentation processing on the text data to obtain a sentence set, and performing block processing on the sentence set to obtain a word block set;

Calculate the importance weight of each word block in the word block set based on the keyword extraction TF-IDF algorithm;

The word block whose importance weight is less than or equal to the second preset weight is used as the reference high-frequency word;

Calculating a similarity value between the reference high-frequency vocabulary and the target high-frequency vocabulary;

When the similarity value is greater than the similarity threshold, obtaining a basic knowledge point label associated with the target high-frequency vocabulary;

The basic knowledge point labels associated with the target high-frequency vocabulary are added to the basic knowledge point label set.

In one or more embodiments, the processor 601 is further configured to:

Performing sentence segmentation processing on the text data to obtain a sentence set, and performing word segmentation processing on the sentence set to obtain a word set;

Performing part-of-speech tagging on each word in the word set to obtain a part-of-speech tagging set;

The word whose part of speech is a verb is used as a reference verb vocabulary;

Calculating a similarity value between the reference verb vocabulary and the target verb vocabulary;

When the similarity value is greater than the similarity threshold, obtaining a basic knowledge point label associated with the target verb vocabulary;

The basic knowledge point label associated with the target verb vocabulary is added to the basic knowledge point label set.

In one or more embodiments, the processor 601 is further configured to:

Performing sentence segmentation processing on the text data to obtain a sentence set, and performing word segmentation processing on the sentence set to obtain a word set;

Performing part-of-speech tagging on each word in the word set to obtain a part-of-speech tagging set;

The words whose part of speech is numeral part of speech are used as reference mathematical words;

Calculating a similarity value between the reference mathematical vocabulary and the target mathematical vocabulary;

When the similarity value is greater than the similarity threshold, obtaining a basic knowledge point label associated with the target mathematical vocabulary;

The basic knowledge point labels associated with the target mathematical vocabulary are added to the basic knowledge point label set.

In one or more embodiments, the processor 601 is further configured to:

Performing sentence segmentation processing on the text data to obtain a sentence set, and performing word segmentation processing on the sentence set to obtain a word set;

Analyze each word in the word set, and add phonetic symbols to the words to obtain a phonetic symbol set;

Calculating the similarity between the word phonetic symbol in the phonetic symbol set and the target phonetic symbol;

When the similarity value is greater than the similarity threshold, obtaining a basic knowledge point label associated with the target phonetic symbol;

The basic knowledge point label associated with the target phonetic symbol is added to the basic knowledge point label set.

In one or more embodiments, the processor 601 is further configured to:

Performing sentence segmentation processing on the text data to obtain a sentence set, and performing word segmentation processing on the sentence set to obtain a word set;

Based on the word set, each word in the word set is tagged with a part of speech to obtain a part of speech tag set;

Performing dependency syntactic analysis on the sentences in the sentence set to obtain a dependency syntactic tree;

Calculate the similarity values of the words in the word set, the parts of speech in the part-of-speech tag set, and the dependency syntax tree with the words, parts of speech, and syntax tree in the target sentence respectively;

When the similarity value is greater than the similarity threshold, obtaining a basic knowledge point label associated with the target sentence;

The basic knowledge point tag associated with the target sentence pattern is added to the basic knowledge point tag set.

In one or more embodiments, the processor 601 is further configured to:

Performing sentence segmentation processing on the text data to obtain a sentence set, and performing word segmentation processing on the sentence set to obtain a word set;

Performing part-of-speech tagging on each word in the word set to obtain a part-of-speech tagging set;

Calculating a similarity value between the grammar included in the sentence set and the target grammar based on the word set and the part-of-speech tag set;

When the similarity value is greater than the similarity threshold, obtaining a basic knowledge point label associated with the target grammar;

The basic knowledge point labels associated with the target grammar are added to the basic knowledge point label set.

It should be noted that the device 6 provided in the above embodiment only uses the division of the above functional modules as an example when executing the data resource labeling method. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the data resource labeling method embodiments provided in the above embodiment belong to the same concept, and the implementation process thereof is detailed in the method embodiment, which will not be repeated here.

As described above, the embodiments are mainly described by taking the online education industry as an example, but those skilled in the art understand that the applicability of the present method is not limited to the online education industry. For example, the method described in this application can be applied to user tag processing in various industries such as retail, transportation, social networking, search, education, and medical care.

The serial numbers of the embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

The embodiment of the present application also provides a computer storage medium, which can store multiple instructions, and the instructions are suitable for being loaded by a processor and executing the method steps of the embodiments shown in Figures 2 to 3 above. The specific execution process can be found in the specific description of the embodiments shown in Figures 2 to 3, and will not be repeated here.

Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

The present application is described with reference to the flowchart and/or block diagram of the method, device (system) and computer program product according to the embodiment of the present application. It should be understood that each process and/or box in the flowchart and/or block diagram, and the combination of the process and/or box in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for realizing the function specified in one process or multiple processes in the flowchart and/or one box or multiple boxes in the block diagram.

These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.

Claims (13)

1. A method for labeling data resources, the method comprising:

preprocessing an original data resource to obtain text data;

carrying out similarity calculation on the text data and a plurality of target knowledge points respectively to obtain a similarity value; wherein, each of the plurality of target knowledge points is associated with a basic knowledge point tag;

generating a basic knowledge point tag set of the original data resource according to a comparison result of the similarity value and the similarity threshold value; the basic knowledge point labels included in the basic knowledge point label set are as follows: basic knowledge point labels associated with target knowledge points with similarity values greater than a similarity threshold;

generating a comprehensive knowledge point tag set of the original data resource according to the characteristic information of the original data resource and the basic knowledge point tag set; the characteristic information refers to the type of the original data resource, and the comprehensive knowledge point labels in the comprehensive knowledge point label set refer to knowledge point labels which are generated based on the characteristic information of the original data resource and the basic knowledge point label set and can reflect the exercise user capacity of the original data resource;

The generating the basic knowledge point label set of the original data resource according to the comparison result of the similarity value and the similarity threshold value comprises the following steps:

sentence segmentation processing is carried out on the text data to obtain sentence sets, and the sentence sets are respectively subjected to block segmentation processing to obtain word block sets, and word segmentation processing is carried out to obtain word sets;

analyzing the word block set and the word set to obtain a reference word set, and calculating similarity values of each reference word in the reference word set and each corresponding target knowledge point; the reference vocabulary set comprises a reference content vocabulary, a reference high-frequency vocabulary, a reference verb vocabulary and a reference math vocabulary, wherein a target knowledge point corresponding to the reference content vocabulary is a target content vocabulary, a target knowledge point corresponding to the reference high-frequency vocabulary is a target high-frequency vocabulary, a target knowledge point corresponding to the reference verb vocabulary is a target verb vocabulary, and a target knowledge point corresponding to the reference math vocabulary is a target math vocabulary;

when the similarity value of each corresponding target knowledge point is larger than the similarity threshold value, adding the basic knowledge point label corresponding to each corresponding target knowledge point into the basic knowledge point label set; or (b)

Sentence segmentation processing is carried out on the text data to obtain sentence sets, and word segmentation processing is respectively carried out on the sentence sets to obtain word sets;

analyzing the word set to obtain a phonetic symbol set, a part-of-speech labeling set and a dependency syntax tree respectively, and calculating similarity values of word phonetic symbols in the phonetic symbol set, sentence patterns in the sentence set and grammar in the sentence set and corresponding target knowledge points respectively; the target knowledge points corresponding to the word phonetic symbols are target phonetic symbols, the target knowledge points corresponding to the sentence patterns are target sentence patterns, and the target knowledge points corresponding to the grammar are target grammar;

and when the similarity value of each corresponding target knowledge point is larger than the similarity threshold value, adding the basic knowledge point label corresponding to each corresponding target knowledge point into the basic knowledge point label set.

2. The method of claim 1, wherein the method of determining the plurality of target knowledge points comprises:

inquiring attribute information corresponding to the original data resources from a preset knowledge graph to obtain a plurality of target knowledge points corresponding to the attribute information.

3. The method of claim 2, wherein the raw data resource is a teaching resource and the attribute information is course information.

4. The method of claim 1, wherein the target knowledge point comprises: a target content vocabulary;

the method comprises the steps of carrying out sentence segmentation on text data to obtain sentence sets, carrying out block segmentation on the sentence sets to obtain word block sets, and carrying out word segmentation to obtain word sets;

analyzing the word block set and the word set to obtain a reference word set, and calculating similarity values of each reference word in the reference word set and each corresponding target knowledge point; the reference vocabulary set comprises a reference content vocabulary, a reference high-frequency vocabulary, a reference verb vocabulary and a reference math vocabulary, wherein a target knowledge point corresponding to the reference content vocabulary is a target content vocabulary, a target knowledge point corresponding to the reference high-frequency vocabulary is a target high-frequency vocabulary, a target knowledge point corresponding to the reference verb vocabulary is a target verb vocabulary, and a target knowledge point corresponding to the reference math vocabulary is a target math vocabulary;

When the similarity value of each corresponding target knowledge point is greater than each corresponding similarity threshold, adding the basic knowledge point label corresponding to each corresponding target knowledge point into the basic knowledge point label set, wherein the method comprises the following steps:

sentence segmentation processing is carried out on the text data to obtain a sentence set, and block segmentation processing is carried out on the sentence set to obtain a word block set;

calculating importance degree weights of each word block in the word block set based on a keyword extraction TF-IDF algorithm;

taking the word blocks with the importance degree weight larger than a first preset weight as the reference content vocabulary;

calculating a similarity value of the reference content vocabulary and the target content vocabulary;

when the similarity value is larger than a similarity threshold value, acquiring a basic knowledge point tag associated with the target content vocabulary;

and adding the basic knowledge point labels associated with the target content vocabulary into the basic knowledge point label set.

5. The method of claim 1, wherein the target knowledge point comprises: target frequency vocabulary;

the method comprises the steps of carrying out sentence segmentation on text data to obtain sentence sets, carrying out block segmentation on the sentence sets to obtain word block sets, and carrying out word segmentation to obtain word sets;

Analyzing the word block set and the word set to obtain a reference word set, and calculating similarity values of each reference word in the reference word set and each corresponding target knowledge point; the reference vocabulary set comprises a reference content vocabulary, a reference high-frequency vocabulary, a reference verb vocabulary and a reference math vocabulary, wherein a target knowledge point corresponding to the reference content vocabulary is a target content vocabulary, a target knowledge point corresponding to the reference high-frequency vocabulary is a target high-frequency vocabulary, a target knowledge point corresponding to the reference verb vocabulary is a target verb vocabulary, and a target knowledge point corresponding to the reference math vocabulary is a target math vocabulary;

when the similarity value of each corresponding target knowledge point is greater than each corresponding similarity threshold, adding the basic knowledge point label corresponding to each corresponding target knowledge point into the basic knowledge point label set, wherein the method comprises the following steps:

sentence segmentation processing is carried out on the text data to obtain a sentence set, and block segmentation processing is carried out on the sentence set to obtain a word block set;

calculating importance degree weights of each word block in the word block set based on a keyword extraction TF-IDF algorithm;

Taking the word blocks with the importance degree weight less than or equal to a second preset weight as the reference high-frequency vocabulary;

calculating the similarity value of the reference high-frequency vocabulary and the target high-frequency vocabulary;

when the similarity value is larger than a similarity threshold value, acquiring a basic knowledge point tag associated with the target high-frequency vocabulary;

and adding the basic knowledge point labels associated with the target high-frequency words into the basic knowledge point label set.

6. The method of claim 1, wherein the target knowledge point comprises: target verb vocabulary;

the method comprises the steps of carrying out sentence segmentation on text data to obtain sentence sets, carrying out block segmentation on the sentence sets to obtain word block sets, and carrying out word segmentation to obtain word sets;

analyzing the word block set and the word set to obtain a reference word set, and calculating similarity values of each reference word in the reference word set and each corresponding target knowledge point; the reference vocabulary set comprises a reference content vocabulary, a reference high-frequency vocabulary, a reference verb vocabulary and a reference math vocabulary, wherein a target knowledge point corresponding to the reference content vocabulary is a target content vocabulary, a target knowledge point corresponding to the reference high-frequency vocabulary is a target high-frequency vocabulary, a target knowledge point corresponding to the reference verb vocabulary is a target verb vocabulary, and a target knowledge point corresponding to the reference math vocabulary is a target math vocabulary;

When the similarity value of each corresponding target knowledge point is greater than each corresponding similarity threshold, adding the basic knowledge point label corresponding to each corresponding target knowledge point into the basic knowledge point label set, wherein the method comprises the following steps:

sentence segmentation processing is carried out on the text data to obtain a sentence set, and word segmentation processing is carried out on the sentence set to obtain a word set;

performing part-of-speech tagging on each word in the word set to obtain a part-of-speech tagging set;

taking the words with the parts of speech being verbs as reference verb words;

calculating a similarity value of the reference verb vocabulary and the target verb vocabulary;

when the similarity value is larger than a similarity threshold value, acquiring a basic knowledge point label associated with the target verb vocabulary;

and adding the basic knowledge point labels associated with the target verb words into the basic knowledge point label set.

7. The method of claim 1, wherein the target knowledge point comprises: a target mathematical vocabulary;

the method comprises the steps of carrying out sentence segmentation on text data to obtain sentence sets, carrying out block segmentation on the sentence sets to obtain word block sets, and carrying out word segmentation to obtain word sets;

Analyzing the word block set and the word set to obtain a reference word set, and calculating similarity values of each reference word in the reference word set and each corresponding target knowledge point; the reference vocabulary set comprises a reference content vocabulary, a reference high-frequency vocabulary, a reference verb vocabulary and a reference math vocabulary, wherein a target knowledge point corresponding to the reference content vocabulary is a target content vocabulary, a target knowledge point corresponding to the reference high-frequency vocabulary is a target high-frequency vocabulary, a target knowledge point corresponding to the reference verb vocabulary is a target verb vocabulary, and a target knowledge point corresponding to the reference math vocabulary is a target math vocabulary;

when the similarity value of each corresponding target knowledge point is greater than each corresponding similarity threshold, adding the basic knowledge point label corresponding to each corresponding target knowledge point into the basic knowledge point label set, wherein the method comprises the following steps:

sentence segmentation processing is carried out on the text data to obtain a sentence set, and word segmentation processing is carried out on the sentence set to obtain a word set;

performing part-of-speech tagging on each word in the word set to obtain a part-of-speech tagging set;

Taking the words with the parts of speech being words with the parts of speech as reference mathematical words;

calculating a similarity value of the reference mathematical vocabulary and the target mathematical vocabulary;

when the similarity value is larger than a similarity threshold value, acquiring a basic knowledge point label associated with the target mathematical vocabulary;

and adding the basic knowledge point labels associated with the target mathematics into the basic knowledge point label set.

8. The method of claim 1, wherein the target knowledge point comprises: target phonetic symbols;

the text data is subjected to sentence segmentation processing to obtain sentence sets, and word segmentation processing is respectively carried out on the sentence sets to obtain word sets;

analyzing the word set to obtain a phonetic symbol set, a part-of-speech labeling set and a dependency syntax tree respectively, and calculating similarity values of word phonetic symbols in the phonetic symbol set, sentence patterns in the sentence set and grammar in the sentence set and corresponding target knowledge points respectively; the target knowledge points corresponding to the word phonetic symbols are target phonetic symbols, the target knowledge points corresponding to the sentence patterns are target sentence patterns, and the target knowledge points corresponding to the grammar are target grammar;

When the similarity value of each corresponding target knowledge point is greater than each corresponding similarity threshold, adding the basic knowledge point label corresponding to each corresponding target knowledge point into the basic knowledge point label set, wherein the method comprises the following steps:

sentence segmentation processing is carried out on the text data to obtain a sentence set, and word segmentation processing is carried out on the sentence set to obtain a word set;

analyzing each word in the word set, and marking phonetic symbols on each word to obtain a phonetic symbol set;

calculating similarity values of word phonetic symbols in the phonetic symbol set and the target phonetic symbol;

when the similarity value is larger than a similarity threshold value, acquiring a basic knowledge point label associated with the target phonetic symbol;

and adding the basic knowledge point labels associated with the target phonetic symbols into the basic knowledge point label set.

9. The method of claim 1, wherein the target knowledge point comprises: a target sentence pattern;

the text data is subjected to sentence segmentation processing to obtain sentence sets, and word segmentation processing is respectively carried out on the sentence sets to obtain word sets;

analyzing the word set to obtain a phonetic symbol set, a part-of-speech labeling set and a dependency syntax tree respectively, and calculating similarity values of word phonetic symbols in the phonetic symbol set, sentence patterns in the sentence set and grammar in the sentence set and corresponding target knowledge points respectively; the target knowledge points corresponding to the word phonetic symbols are target phonetic symbols, the target knowledge points corresponding to the sentence patterns are target sentence patterns, and the target knowledge points corresponding to the grammar are target grammar;

When the similarity value of each corresponding target knowledge point is greater than each corresponding similarity threshold, adding the basic knowledge point label corresponding to each corresponding target knowledge point into the basic knowledge point label set, wherein the method comprises the following steps:

sentence segmentation processing is carried out on the text data to obtain a sentence set, and word segmentation processing is carried out on the sentence set to obtain a word set;

performing part-of-speech tagging on each word in the word set to obtain a part-of-speech tagging set;

performing dependency syntax analysis on sentences in the sentence set to obtain a dependency syntax tree;

calculating similarity values of the words in the word set, the parts of speech in the part-of-speech tagging set and the dependency syntax tree corresponding to the words, the parts of speech and the syntax tree in the target sentence pattern respectively;

when the similarity value is larger than a similarity threshold value, acquiring a basic knowledge point label associated with the target sentence pattern;

and adding the basic knowledge point labels associated with the target sentence patterns into the basic knowledge point label set.

10. The method of claim 1, wherein the target knowledge point comprises: target grammar;

the text data is subjected to sentence segmentation processing to obtain sentence sets, and word segmentation processing is respectively carried out on the sentence sets to obtain word sets;

Analyzing the word set to obtain a phonetic symbol set, a part-of-speech labeling set and a dependency syntax tree respectively, and calculating similarity values of word phonetic symbols in the phonetic symbol set, sentence patterns in the sentence set and grammar in the sentence set and corresponding target knowledge points respectively; the target knowledge points corresponding to the word phonetic symbols are target phonetic symbols, the target knowledge points corresponding to the sentence patterns are target sentence patterns, and the target knowledge points corresponding to the grammar are target grammar;

when the similarity value of each corresponding target knowledge point is greater than each corresponding similarity threshold, adding the basic knowledge point label corresponding to each corresponding target knowledge point into the basic knowledge point label set, wherein the method comprises the following steps:

sentence segmentation processing is carried out on the text data to obtain a sentence set, and word segmentation processing is carried out on the sentence set to obtain a word set;

performing part-of-speech tagging on each word in the word set to obtain a part-of-speech tagging set;

calculating the similarity value of grammar contained in the sentence set and the target grammar based on the word set and the part-of-speech tagging set;

when the similarity value is larger than a similarity threshold value, acquiring a basic knowledge point tag associated with the target grammar;

And adding the basic knowledge point labels associated with the target grammar into the basic knowledge point label set.

11. A device for labeling data resources, the device comprising:

the preprocessing module is used for preprocessing the original data resources to obtain text data;

the calculation module is used for calculating the similarity between the text data and a plurality of target knowledge points to obtain a similarity value; wherein, each of the plurality of target knowledge points is associated with a basic knowledge point tag;

the first processing module is used for generating a basic knowledge point tag set of the original data resource according to a comparison result of the similarity value and the similarity threshold value; the basic knowledge point labels included in the basic knowledge point label set are as follows: basic knowledge point labels associated with target knowledge points with similarity values greater than a similarity threshold;

the second processing module is used for generating a comprehensive knowledge point tag set of the original data resource according to the characteristic information of the original data resource and the basic knowledge point tag set; the characteristic information refers to the type of the original data resource, and the comprehensive knowledge point labels in the comprehensive knowledge point label set refer to knowledge point labels which are generated based on the characteristic information of the original data resource and the basic knowledge point label set and can reflect the exercise user capacity of the original data resource;

The first processing module includes:

the first processing unit is used for carrying out sentence segmentation processing on the text data to obtain sentence sets, respectively carrying out block segmentation processing on the sentence sets to obtain word block sets, and carrying out word segmentation processing to obtain word sets;

the first calculation unit is used for analyzing the word block set and the word set to obtain a reference word set, and calculating similarity values of each reference word in the reference word set and each corresponding target knowledge point; the reference vocabulary set comprises a reference content vocabulary, a reference high-frequency vocabulary, a reference verb vocabulary and a reference math vocabulary, wherein a target knowledge point corresponding to the reference content vocabulary is a target content vocabulary, a target knowledge point corresponding to the reference high-frequency vocabulary is a target high-frequency vocabulary, a target knowledge point corresponding to the reference verb vocabulary is a target verb vocabulary, and a target knowledge point corresponding to the reference math vocabulary is a target math vocabulary;

the first adding unit is used for adding the basic knowledge point labels corresponding to the respective corresponding target knowledge points into the basic knowledge point label set when the similarity value of the respective corresponding target knowledge points is larger than the respective corresponding similarity threshold value; or (b)

The second processing unit is used for carrying out sentence segmentation processing on the text data to obtain sentence sets, and carrying out word segmentation processing on the sentence sets to obtain word sets;

the second calculation unit is used for analyzing the word set to respectively obtain a phonetic symbol set, a part-of-speech labeling set and a dependency syntax tree, and calculating similarity values of word phonetic symbols in the phonetic symbol set, sentence patterns in the sentence set and grammar in the sentence set and corresponding target knowledge points; the target knowledge points corresponding to the word phonetic symbols are target phonetic symbols, the target knowledge points corresponding to the sentence patterns are target sentence patterns, and the target knowledge points corresponding to the grammar are target grammar;

and the second adding unit is used for adding the basic knowledge point labels corresponding to the respective corresponding target knowledge points into the basic knowledge point label set when the similarity value of the respective corresponding target knowledge points is larger than the respective corresponding similarity threshold value.

12. A computer storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform the method steps of any one of claims 1 to 10.

13. An electronic device, comprising: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to perform the method steps of any of claims 1-10.