CN111400340B - Natural language processing method, device, computer equipment and storage medium - Google Patents
Natural language processing method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111400340B CN111400340B CN202010170324.5A CN202010170324A CN111400340B CN 111400340 B CN111400340 B CN 111400340B CN 202010170324 A CN202010170324 A CN 202010170324A CN 111400340 B CN111400340 B CN 111400340B
- Authority
- CN
- China
- Prior art keywords
- natural language
- user
- matching
- determining
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/242—Query formulation
- G06F16/243—Natural language query formulation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Machine Translation (AREA)
Abstract
The invention is applicable to the technical field of artificial intelligence, and provides a natural language processing method, a device, computer equipment and a storage medium, wherein the natural language processing method comprises the following steps: acquiring natural language information input by a user; identifying the natural language information and determining user intention information; extracting keywords from the user intention information; and determining the label matched with the keyword in a knowledge base, acquiring a matching answer corresponding to the determined label, and outputting the matching answer to a user. On one hand, the interference of the traditional word segmentation technology on language processing is reduced, the accuracy of natural language understanding is greatly improved, and on the other hand, the unique mosaic technology is adopted, the method is more friendly and humanized in human-computer interaction results, and better service customers are facilitated.
Description
Technical Field
The invention belongs to the technical field of artificial intelligence, and particularly relates to a natural language processing method, a natural language processing device, computer equipment and a storage medium.
Background
Man-machine interaction refers to the process of information exchange between a person and a computer for completing a determined task in a certain interaction mode by using a certain dialogue language between the person and the computer.
In recent years, human-computer interaction has advanced in various fields, and is gradually replacing graphical user interfaces to become new user interfaces. However, due to the limitations of the technology adopted, when the current man-machine interaction is aimed at natural language processing, more single models are adopted for processing, the related industry is single, the data representing results of different industries are common, and aiming at Chinese language, the expressive force of the models is often greatly influenced by word segmentation technology, and the problems of simple dialogue and simple processing can only be carried out, in some cases, the client intention cannot be effectively understood, and when the problem which cannot be answered or the expression which cannot be understood is encountered, the search engine is generally only simply called to search the keywords in the input of the user, and the web pages of the search results are directly returned to the user, so that better service clients are not facilitated.
Therefore, the existing natural language processing method relates to single industry, has common data presentation results for different industries, often needs to use word segmentation technology, has great influence on the expressive force of a model, and is not beneficial to better service clients.
Disclosure of Invention
The embodiment of the invention aims to provide a natural language processing method, and aims to solve the problems that the existing natural language processing method relates to a single industry, has general data presentation results for different industries, often needs to use word segmentation technology, has great influence on the expressive force of a model and is not beneficial to better service customers.
The embodiment of the invention is realized in such a way that a natural language processing method comprises the following steps:
acquiring natural language information input by a user;
identifying the natural language information and determining user intention information;
extracting keywords from the user intention information;
and determining the label matched with the keyword in a knowledge base, acquiring a matching answer corresponding to the determined label, and outputting the matching answer to a user.
Another object of an embodiment of the present invention is to provide a natural language processing apparatus, including:
the acquisition unit is used for acquiring natural language information of the user;
the intention determining unit is used for identifying the natural language information and determining user intention information;
the keyword extraction unit is used for extracting keywords from the user intention information; and
and the output unit is used for determining the label matched with the keyword in the knowledge base, acquiring a matching answer corresponding to the determined label and outputting the matching answer to a user.
Another object of an embodiment of the present invention is a computer device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of the natural language processing method.
Another object of an embodiment of the present invention is a computer-readable storage medium, in which a computer program is stored, which when executed by a processor causes the processor to perform the steps of the natural language processing method.
According to the natural language processing method provided by the embodiment of the invention, the natural language information input by the user is identified and the intention information of the user is determined; further, determining a label matched with the keyword of the user intention information in a knowledge base, acquiring a matching answer corresponding to the determined label, and outputting the matching answer to a user; on one hand, the interference of the traditional word segmentation technology on language processing is reduced, the accuracy of natural language understanding is greatly improved, and on the other hand, the unique mosaic technology is adopted, the method is more friendly and humanized in human-computer interaction results, and better service customers are facilitated.
Drawings
FIG. 1 is a flowchart of a natural language processing method according to an embodiment of the present invention;
FIG. 2 is a flowchart of a natural language processing method according to a second embodiment of the present invention;
FIG. 3 is a flowchart illustrating a method for processing natural language according to a third embodiment of the present invention;
FIG. 4 is a flowchart of a method for processing natural language according to a fourth embodiment of the present invention;
FIG. 5 is a flowchart of a natural language processing method according to a fifth embodiment of the present invention;
FIG. 6 is a flowchart of a method for processing natural language according to a sixth embodiment of the present invention;
FIG. 7 is a flowchart illustrating a method for processing natural language according to a seventh embodiment of the present invention;
fig. 8 is a block diagram of a natural language processing device according to a ninth embodiment of the present invention;
FIG. 9 is a block diagram of the internal architecture of a computer device in one embodiment.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, etc. may be used in embodiments of the present invention to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another.
According to the natural language processing method provided by the embodiment of the invention, the natural language information input by the user is identified and the intention information of the user is determined; further, determining a label matched with the keyword of the user intention information in a knowledge base, acquiring a matching answer corresponding to the determined label, and outputting the matching answer to a user; on one hand, the interference of the traditional word segmentation technology on language processing is reduced, the accuracy of natural language understanding is greatly improved, and on the other hand, the unique mosaic technology is adopted, the method is more friendly and humanized in human-computer interaction results, and better service customers are facilitated.
In order to further describe the technical means and effects adopted by the present invention for achieving the intended purpose, the following detailed description is given of the specific embodiments, structures, features and effects according to the present invention with reference to the accompanying drawings and preferred embodiments.
Fig. 1 shows an implementation flow of a natural language processing method according to the first embodiment of the present invention, and for convenience of explanation, only the portions related to the embodiment of the present invention are shown in detail as follows:
in step S101, natural language information input by a user is acquired.
In the embodiment of the invention, the natural language information input by the user can be natural language information in a text format directly input by the user, for example, when the user searches for the position information of the relevant store by using the mall guide board, the text information input by the user can be analyzed; the natural language information of the voice format input by the user may be recognized by the voice recognition model and processed into the natural language information of the text format, for example, when the user uses the telephone to make consultation, the voice information of the user can be analyzed.
In step S102, the natural language information is identified and user intention information is determined.
In the embodiment of the invention, the user intention information can pass through a preset intention recognition model, and the specific intention recognition model is not required by the invention because the existing intention recognition model has a plurality of types, and a proper intention recognition model can be selected by a person skilled in the art according to actual requirements, for example, the intention recognition model can be a path characteristic pair intention recognition model constructed based on a semantic analysis tree, and also can be an intention recognition model of a convolutional neural network based on an attention mechanism.
In the embodiment of the invention, the natural language information is identified and the user intention information is determined, so that the professional industry field to which the natural language information belongs can be determined after the text identification is performed on the natural language information, and the user intention information is identified by combining with the user intention identification model of the determined professional industry field.
In step S103, keyword extraction is performed on the user intention information.
In an embodiment of the present invention, in the present invention,
in step S104, a tag matching the keyword is determined in the knowledge base, and a matching answer corresponding to the determined tag is obtained and output to the user.
In an embodiment of the present invention, in the present invention,
according to the natural language processing method provided by the embodiment of the invention, the natural language information input by the user is identified and the intention information of the user is determined; further, determining a label matched with the keyword of the user intention information in a knowledge base, acquiring a matching answer corresponding to the determined label, and outputting the matching answer to a user; on one hand, the interference of the traditional word segmentation technology on language processing is reduced, the accuracy of natural language understanding is greatly improved, and on the other hand, the unique mosaic technology is adopted, the method is more friendly and humanized in human-computer interaction results, and better service customers are facilitated.
Fig. 2 shows a flow of implementation of the natural language processing method according to the second embodiment of the present invention, for convenience of explanation, only a portion related to the embodiment of the present invention is shown, which is similar to the embodiment, and the difference is that the step 102 specifically includes:
in step S201, the natural language information is identified and a semantic representation is generated.
In the embodiment of the present invention, one implementation way to identify the natural language information and generate the semantic representation may be to pre-process the natural language information and convert it into a structured query language (SQL statement) for identifying the industry and the requirement information thereof.
In step S202, a text classification is determined from the semantic representation.
In the embodiment of the present invention, one implementation way of determining the text classification according to the semantic representation may be to determine, according to the converted structured query language, the technical field to which the natural language information belongs.
In step S203, user intention information is determined from the semantic representation and the text classification.
According to the natural language processing method provided by the embodiment of the invention, the natural language information is firstly identified and the semantic representation is generated, so that the semantic representation is subjected to professional domain identification processing, and after the professional domain to which the natural language information belongs is acquired, the corresponding intention identification model corresponding to the professional domain can be positioned in time for processing, thereby effectively improving the accuracy of user intention identification.
Fig. 3 shows a flow of implementation of the natural language processing method according to the third embodiment of the present invention, and for convenience of explanation, only the portion related to the third embodiment of the present invention is shown, which is different from the second embodiment in that the step S203 includes the following steps:
in step S301, the semantic representation is converted into a semantic vector based on the text classification.
In the embodiment of the present invention, based on the text classification, the implementation manner of converting the semantic representation into the semantic vector may be that, by locating in time to the corresponding technical field of expertise, the semantic representation in each time sequence is converted into the word vector in the corresponding time state, the obtained word vector is modeled by a long short time memory network (LSTM), and the last time state vector is used as the representation of the whole sentence, that is, the sentence vector. In practical application, since each time corresponds to a sentence input by the user, word segmentation is followed by a word sequence, and LSTM may extract features of the time sequence, and for each sentence, the last state vector is obtained through LSTM as the code of the whole sentence.
In the embodiment of the invention, text input of a user is converted into vector input, word2vec (word vector) training is generally performed by using a user chat log, and then the user input is converted through an Embedding layer, namely, each word of the user input (input after word segmentation) is converted into a vector through an Embedding layer, which is a general processing mode in the industry and is not repeated herein.
In step S302, probability distribution information of the user intention is determined according to the semantic vector and a preset training model, and output.
In the embodiment of the invention, the preset training model may be a neural network, which is a concept, and a generic algorithm may be used as a general rnn (recurrent neural network), cnn (convolutional neural network) or fully-connected network.
In step S303, the user intention with the largest probability distribution threshold is determined as the user intention information.
Fig. 4 shows a flow of implementation of the natural language processing method according to the fourth embodiment of the present invention, and for convenience of explanation, only the portion related to the embodiment of the present invention is shown, which is similar to the embodiment, except that the step S104 specifically includes the following steps:
in step S401, it is determined whether the matching degree between the tag in the knowledge base and the keyword exceeds a preset matching threshold; if yes, go to step S402; if not, the process advances to step S403.
In step S402, a matching answer corresponding to the label that is exactly matched with the keyword is obtained and output to the user.
In step S403, a matching answer corresponding to at least one tag that is fuzzy matched with the keyword is obtained, the matching answer is calculated, and the processed matching answer is output to the user.
Fig. 5 shows a flow of implementation of the natural language processing method provided in the fifth embodiment of the present invention, for convenience of explanation, only the portion related to the embodiment of the present invention is shown, which is similar to the embodiment, and the difference is that the step S104 specifically includes the following steps:
in step S501, the keywords are analyzed and processed to obtain related words with the same meaning as the keywords.
In step S502, a tag matching the related word is determined in a knowledge base, and a matching answer corresponding to the determined tag is obtained and output to a user.
Fig. 6 shows a flow of implementation of the natural language processing method provided in the sixth embodiment of the present invention, and for convenience of explanation, only the portion related to the embodiment of the present invention is shown, which is similar to the embodiment, and the method further includes the following steps:
in step S601, when it is determined that the user is not satisfied with the matching answer, a manual addition reminder is output, and the received correct matching answer is used as a training set.
In step S602, when it is determined that the user is satisfied with the matching answer, the matching answer is taken as a verification set.
In step S603, according to the training set and the verification set, the preset training model is optimized according to a preset optimization period.
Fig. 7 shows a flow of implementation of the natural language processing method according to the seventh embodiment of the present invention, and for convenience of explanation, only the portion related to the embodiment of the present invention is shown, which is similar to the embodiment, and the method further includes the following steps:
in step S701, the knowledge base and the labels thereof are updated according to the training set and the verification set.
In the embodiment of the invention, the error matching answers are adjusted to serve as a training set, the correct answers are continued to serve as a verification set, and the knowledge base and the labels thereof are updated, so that the knowledge base can be reversely optimized, and the accuracy and the stability of the matching result are further improved.
Fig. 8 shows the structure of a natural language processing device 800 according to an eighth embodiment of the present invention, and for convenience of explanation, only the portions related to the embodiments of the present invention are shown in detail as follows:
the natural language processing apparatus 800 includes an acquisition unit 801, an intention determination unit 802, a keyword extraction unit 803, and an output unit 804.
An obtaining unit 801, configured to obtain natural language information of a user.
In the embodiment of the invention, the natural language information input by the user can be natural language information in a text format directly input by the user, for example, when the user searches for the position information of the relevant store by using the mall guide board, the text information input by the user can be analyzed; the natural language information of the voice format input by the user may be recognized by the voice recognition model and processed into the natural language information of the text format, for example, when the user uses the telephone to make consultation, the voice information of the user can be analyzed.
An intention determining unit 802 for identifying the natural language information and determining user intention information.
In the embodiment of the invention, the user intention information can pass through a preset intention recognition model, and the specific intention recognition model is not required by the invention because the existing intention recognition model has a plurality of types, and a proper intention recognition model can be selected by a person skilled in the art according to actual requirements, for example, the intention recognition model can be a path characteristic pair intention recognition model constructed based on a semantic analysis tree, and also can be an intention recognition model of a convolutional neural network based on an attention mechanism.
In the embodiment of the invention, the natural language information is identified and the user intention information is determined, so that the professional industry field to which the natural language information belongs can be determined after the text identification is performed on the natural language information, and the user intention information is identified by combining with the user intention identification model of the determined professional industry field.
And a keyword extraction unit 803 configured to perform keyword extraction on the user intention information.
And the output unit 804 is configured to determine a tag matching the keyword in the knowledge base, obtain a matching answer corresponding to the determined tag, and output the matching answer to the user.
The natural language processing device provided by the embodiment of the invention recognizes natural language information input by a user and determines user intention information; further, determining a label matched with the keyword of the user intention information in a knowledge base, acquiring a matching answer corresponding to the determined label, and outputting the matching answer to a user; on one hand, the interference of the traditional word segmentation technology on language processing is reduced, the accuracy of natural language understanding is greatly improved, and on the other hand, the unique mosaic technology is adopted, the method is more friendly and humanized in human-computer interaction results, and better service customers are facilitated.
FIG. 9 illustrates an internal block diagram of a computer device in one embodiment. The computer device may in particular be a terminal (or a server). As shown in fig. 9, the computer device includes a processor, a memory, a network interface, an input device, and a display screen connected by a system bus. The memory includes a nonvolatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system, and may also store a computer program that, when executed by a processor, causes the processor to implement a natural language processing method. The internal memory may also have stored therein a computer program which, when executed by the processor, causes the processor to perform the natural language processing method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in fig. 9 is merely a block diagram of a portion of the structure associated with the present application and is not limiting of the computer device to which the present application applies, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, the natural language processing apparatus provided herein may be implemented in the form of a computer program that is executable on a computer device as shown in fig. 9. The memory of the computer device may store therein respective program modules constituting the natural language processing apparatus, such as an acquisition unit 801, an intention determination unit 802, a keyword extraction unit 803, and an output unit 804 shown in fig. 8. The computer program constituted by the respective program modules causes the processor to execute the steps in the natural language processing method of the respective embodiments of the present application described in the present specification.
For example, the computer apparatus shown in fig. 9 may execute step S101 by the acquisition unit 801 in the natural language processing device shown in fig. 8. The computer apparatus may perform step S102 through the intention determining unit 802. The computer apparatus may perform step S103 through the keyword extraction unit 803. The computer apparatus may perform step S104 through the output unit 804.
In one embodiment, a computer device is presented, the computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
acquiring natural language information input by a user;
identifying the natural language information and determining user intention information;
extracting keywords from the user intention information;
and determining the label matched with the keyword in a knowledge base, acquiring a matching answer corresponding to the determined label, and outputting the matching answer to a user.
In one embodiment, a computer readable storage medium is provided, having a computer program stored thereon, which when executed by a processor causes the processor to perform the steps of:
acquiring natural language information input by a user;
identifying the natural language information and determining user intention information;
extracting keywords from the user intention information;
and determining the label matched with the keyword in a knowledge base, acquiring a matching answer corresponding to the determined label, and outputting the matching answer to a user.
It should be understood that, although the steps in the flowcharts of the embodiments of the present invention are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in various embodiments may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the sub-steps or stages of other steps or other steps.
Those skilled in the art will appreciate that all or part of the processes in the methods of the above embodiments may be implemented by a computer program for instructing relevant hardware, where the program may be stored in a non-volatile computer readable storage medium, and where the program, when executed, may include processes in the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the invention and are described in detail herein without thereby limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (6)
1. A method of natural language processing, comprising:
acquiring natural language information input by a user;
identifying the natural language information and determining user intention information;
extracting keywords from the user intention information;
determining a label matched with the keyword in a knowledge base, acquiring a matching answer corresponding to the determined label, and outputting the matching answer to a user;
the step of identifying the natural language information and determining the user intention information specifically comprises the following steps:
identifying the natural language information and generating a semantic representation, including: preprocessing the natural language information to obtain a structured query language;
determining a text classification from the semantic representation, comprising: determining the technical field to which the natural language information belongs according to the structured query language;
determining user intention information according to the semantic representation and the text classification;
the step of determining user intention information according to the semantic representation and the text classification specifically comprises the following steps:
converting the semantic representation into a semantic vector based on the text classification;
according to the semantic vector and a preset training model, determining probability distribution information of user intention and outputting the probability distribution information;
determining the user intention with the maximum probability distribution threshold as user intention information;
the step of determining the label matched with the keyword in the knowledge base, acquiring a matching answer corresponding to the determined label and outputting the matching answer to a user specifically comprises the following steps:
judging whether the matching degree of the labels in the knowledge base and the keywords exceeds a preset matching threshold value or not;
when the matching degree of the labels in the knowledge base and the keywords exceeds a preset matching threshold, obtaining matching answers corresponding to the labels which are accurately matched with the keywords, and outputting the matching answers to a user;
when the matching degree of the labels in the knowledge base and the keywords does not exceed a preset matching threshold, a matching answer corresponding to at least one label which is subjected to fuzzy matching with the keywords is obtained, the matching answer is calculated, and the processed matching answer is output to a user.
2. The natural language processing method of claim 1, further comprising:
outputting a manual addition reminder when the user is not satisfied with the matching answer, and taking the received correct matching answer as a training set;
when the user is satisfied with the matching answer, the matching answer is used as a verification set;
and according to the training set and the verification set, optimizing the preset training model according to a preset optimization period.
3. The natural language processing method of claim 2, further comprising:
and updating the knowledge base and the labels thereof according to the training set and the verification set.
4. A natural language processing apparatus, comprising:
the acquisition unit is used for acquiring natural language information of the user;
the intention determining unit is used for identifying the natural language information and determining user intention information;
the keyword extraction unit is used for extracting keywords from the user intention information; and
the output unit is used for determining the label matched with the keyword in the knowledge base, acquiring a matching answer corresponding to the determined label and outputting the matching answer to a user;
the identifying the natural language information and determining the user intention information specifically comprises the following steps:
identifying the natural language information and generating a semantic representation, including: preprocessing the natural language information to obtain a structured query language,
determining a text classification from the semantic representation, comprising: determining the technical field to which the natural language information belongs according to the structured query language;
determining user intention information according to the semantic representation and the text classification;
the determining the user intention information according to the semantic representation and the text classification specifically comprises the following steps:
converting the semantic representation into a semantic vector based on the text classification;
according to the semantic vector and a preset training model, determining probability distribution information of user intention and outputting the probability distribution information;
determining the user intention with the maximum probability distribution threshold as user intention information;
the method comprises the steps of determining the label matched with the keyword in a knowledge base, obtaining a matching answer corresponding to the determined label, and outputting the matching answer to a user, wherein the method specifically comprises the following steps:
judging whether the matching degree of the labels in the knowledge base and the keywords exceeds a preset matching threshold value or not;
when the matching degree of the labels in the knowledge base and the keywords exceeds a preset matching threshold, obtaining matching answers corresponding to the labels which are accurately matched with the keywords, and outputting the matching answers to a user;
when the matching degree of the labels in the knowledge base and the keywords does not exceed a preset matching threshold, a matching answer corresponding to at least one label which is subjected to fuzzy matching with the keywords is obtained, the matching answer is calculated, and the processed matching answer is output to a user.
5. A computer device comprising a memory and a processor, the memory having stored therein a computer program which, when executed by the processor, causes the processor to perform the steps of the natural language processing method of any one of claims 1 to 3.
6. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed by a processor, causes the processor to perform the steps of the natural language processing method of any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010170324.5A CN111400340B (en) | 2020-03-12 | 2020-03-12 | Natural language processing method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010170324.5A CN111400340B (en) | 2020-03-12 | 2020-03-12 | Natural language processing method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111400340A CN111400340A (en) | 2020-07-10 |
| CN111400340B true CN111400340B (en) | 2024-01-09 |
Family
ID=71436224
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010170324.5A Active CN111400340B (en) | 2020-03-12 | 2020-03-12 | Natural language processing method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111400340B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112182058B (en) * | 2020-08-17 | 2024-04-09 | 北京来也网络科技有限公司 | Content acquisition method, device, computer equipment and medium combining RPA and AI |
| CN112527965A (en) * | 2020-12-18 | 2021-03-19 | 国家电网有限公司客户服务中心 | Automatic question answering implementation method and device based on combination of professional library and chatting library |
| CN113450075A (en) * | 2021-07-05 | 2021-09-28 | 中国工商银行股份有限公司 | Work order processing method and device based on natural language technology |
| CN114911916A (en) * | 2022-06-06 | 2022-08-16 | 中国工商银行股份有限公司 | Method, apparatus, device and medium for updating natural language processing system |
| CN115034232A (en) * | 2022-06-17 | 2022-09-09 | 平安普惠企业管理有限公司 | Anti-interference method and device based on intelligent conversation, electronic equipment and storage medium |
| CN115097740B (en) * | 2022-06-17 | 2025-08-22 | 京东科技信息技术有限公司 | Device control method, device, system and storage medium |
| CN117636855A (en) * | 2023-09-19 | 2024-03-01 | 深圳市西迪特科技股份有限公司 | Device configuration method, computer device and computer-readable storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104951458A (en) * | 2014-03-26 | 2015-09-30 | 华为技术有限公司 | Method and equipment for helping processing based on semantic recognition |
| WO2018000279A1 (en) * | 2016-06-29 | 2018-01-04 | 深圳狗尾草智能科技有限公司 | Diversion-based intention recognition method and system |
| CN108304444A (en) * | 2017-11-30 | 2018-07-20 | 腾讯科技（深圳）有限公司 | Information query method and device |
| CN109241259A (en) * | 2018-08-24 | 2019-01-18 | 国网江苏省电力有限公司苏州供电分公司 | Natural language querying method, apparatus and system based on ER model |
| CN109543030A (en) * | 2018-10-12 | 2019-03-29 | 平安科技（深圳）有限公司 | Customer service machine conference file classification method and device, equipment, storage medium |
| WO2019085697A1 (en) * | 2017-10-31 | 2019-05-09 | 科沃斯商用机器人有限公司 | Man-machine interaction method and system |
| WO2019085236A1 (en) * | 2017-10-31 | 2019-05-09 | 北京小度信息科技有限公司 | Search intention recognition method and apparatus, and electronic device and readable storage medium |
| CN110162611A (en) * | 2019-04-23 | 2019-08-23 | 苏宁易购集团股份有限公司 | A kind of intelligent customer service answer method and system |
| CN110266899A (en) * | 2019-06-11 | 2019-09-20 | 平安科技（深圳）有限公司 | The recognition methods and customer service system that client is intended to |
| CN110334344A (en) * | 2019-06-13 | 2019-10-15 | 腾讯科技（深圳）有限公司 | A kind of semanteme intension recognizing method, device, equipment and storage medium |
| CN110472035A (en) * | 2019-08-26 | 2019-11-19 | 杭州城市大数据运营有限公司 | A kind of intelligent response method, apparatus, computer equipment and storage medium |
| CN110674639A (en) * | 2019-09-24 | 2020-01-10 | 拾音智能科技有限公司 | Natural language understanding method based on pre-training model |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106528531B (en) * | 2016-10-31 | 2019-09-03 | 北京百度网讯科技有限公司 | Artificial intelligence-based intent analysis method and device |
| CN108287858B (en) * | 2017-03-02 | 2021-08-10 | 腾讯科技（深圳）有限公司 | Semantic extraction method and device for natural language |
| US10832003B2 (en) * | 2018-08-26 | 2020-11-10 | CloudMinds Technology, Inc. | Method and system for intent classification |
-
2020
- 2020-03-12 CN CN202010170324.5A patent/CN111400340B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104951458A (en) * | 2014-03-26 | 2015-09-30 | 华为技术有限公司 | Method and equipment for helping processing based on semantic recognition |
| WO2018000279A1 (en) * | 2016-06-29 | 2018-01-04 | 深圳狗尾草智能科技有限公司 | Diversion-based intention recognition method and system |
| WO2019085697A1 (en) * | 2017-10-31 | 2019-05-09 | 科沃斯商用机器人有限公司 | Man-machine interaction method and system |
| WO2019085236A1 (en) * | 2017-10-31 | 2019-05-09 | 北京小度信息科技有限公司 | Search intention recognition method and apparatus, and electronic device and readable storage medium |
| CN108304444A (en) * | 2017-11-30 | 2018-07-20 | 腾讯科技（深圳）有限公司 | Information query method and device |
| CN109241259A (en) * | 2018-08-24 | 2019-01-18 | 国网江苏省电力有限公司苏州供电分公司 | Natural language querying method, apparatus and system based on ER model |
| CN109543030A (en) * | 2018-10-12 | 2019-03-29 | 平安科技（深圳）有限公司 | Customer service machine conference file classification method and device, equipment, storage medium |
| CN110162611A (en) * | 2019-04-23 | 2019-08-23 | 苏宁易购集团股份有限公司 | A kind of intelligent customer service answer method and system |
| CN110266899A (en) * | 2019-06-11 | 2019-09-20 | 平安科技（深圳）有限公司 | The recognition methods and customer service system that client is intended to |
| CN110334344A (en) * | 2019-06-13 | 2019-10-15 | 腾讯科技（深圳）有限公司 | A kind of semanteme intension recognizing method, device, equipment and storage medium |
| CN110472035A (en) * | 2019-08-26 | 2019-11-19 | 杭州城市大数据运营有限公司 | A kind of intelligent response method, apparatus, computer equipment and storage medium |
| CN110674639A (en) * | 2019-09-24 | 2020-01-10 | 拾音智能科技有限公司 | Natural language understanding method based on pre-training model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111400340A (en) | 2020-07-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111400340B (en) | Natural language processing method, device, computer equipment and storage medium | |
| CN111708703B (en) | Test case set generation method, device, equipment and computer readable storage medium | |
| CN111160017B (en) | Keyword extraction method, phonetics scoring method and phonetics recommendation method | |
| CN110765763B (en) | Error correction method and device for voice recognition text, computer equipment and storage medium | |
| CN110598206B (en) | Text semantic recognition method and device, computer equipment and storage medium | |
| CN110334179B (en) | Question-answer processing method, device, computer equipment and storage medium | |
| CN114139551A (en) | Method and device for training intention recognition model and method and device for recognizing intention | |
| CN110955761A (en) | Method and device for acquiring question and answer data in document, computer equipment and storage medium | |
| CN112766319A (en) | Dialogue intention recognition model training method and device, computer equipment and medium | |
| CN113064980A (en) | Intelligent question and answer method and device, computer equipment and storage medium | |
| CN112580329B (en) | Text noise data identification method, device, computer equipment and storage medium | |
| CN113343711B (en) | Work order generation method, device, equipment and storage medium | |
| CN113688636B (en) | Recommended method, device, computer equipment and storage medium for extended questions | |
| CN119539095B (en) | Financial question-answering method, system, device and medium based on multi-agent interaction | |
| CN112989829B (en) | Named entity recognition method, device, equipment and storage medium | |
| CN110569486A (en) | sequence labeling method and device based on double architectures and computer equipment | |
| Hafeth et al. | Semantic representations with attention networks for boosting image captioning | |
| CN111859916B (en) | Method, device, equipment and medium for extracting key words of ancient poems and generating poems | |
| CN110309504B (en) | Text processing methods, devices, equipment and storage media based on word segmentation | |
| CN110377618B (en) | Method, device, computer equipment and storage medium for analyzing decision result | |
| CN111104422A (en) | Training method, device, equipment and storage medium of data recommendation model | |
| CN120338111A (en) | Product information question-answering method and system based on semantic coding model | |
| CN117540004B (en) | Industrial domain intelligent question-answering method and system based on knowledge graph and user behavior | |
| CN114238553A (en) | A document duplication checking method and terminal | |
| CN113297353B (en) | Text matching method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: No.6 and No.9, jiurenhe village, Shangcheng District, Hangzhou City, Zhejiang Province, 310000 Patentee after: Hangzhou City Big Data Operation Co.,Ltd. Country or region after: China Patentee after: Zhejiang Shuzhi Operation Technology Co.,Ltd. Patentee after: Hangzhou zhongyun Data Technology Co.,Ltd. Address before: No.6 and No.9, jiurenhe village, Shangcheng District, Hangzhou City, Zhejiang Province, 310000 Patentee before: Hangzhou City Big Data Operation Co.,Ltd. Country or region before: China Patentee before: Huzhou big data operation Co.,Ltd. Patentee before: Hangzhou zhongyun Data Technology Co.,Ltd. |