CN109933681A - Image searching method, device and computer readable storage medium - Google Patents

Abstract

The invention discloses a kind of image searching methods.This method comprises: obtaining text information；Keyword extraction is carried out to the text information, obtains the keyword of the text information；It is retrieved in preset picture library according to the keyword, obtains picture corresponding with the keyword.The invention also discloses a kind of picture searching device and computer readable storage mediums.The present invention can be realized after obtaining text information, divide to text information and extracts acquisition keyword, and searches for relevant picture automatically according to keyword.

Description

Image search method, apparatus and computer-readable storage medium

technical field

The present invention relates to the field of picture processing, and in particular, to a picture search method, device and computer-readable storage medium.

Background technique

With the development of science and technology, the teaching methods of knowledge are more and more diverse, from the past plain text information to the later video information, which greatly enrich people's teaching methods and teaching experience. Especially in many text information teaching, the text is equipped with illustrations, which can more vividly and directly display the information in the text, attract the attention of readers, and have the characteristics of image and intuition.

However, at present, the illustrations in the text information are mostly added by manually searching for pictures based on the understanding of the text. This method not only requires manual mental work, but also takes a long time.

SUMMARY OF THE INVENTION

The main purpose of the present invention is to provide a picture search method, device and computer-readable storage medium, aiming to realize that after obtaining text data, the text data is divided and extracted to obtain keywords, and related pictures are automatically searched according to the keywords.

In order to achieve the above object, the present invention provides a picture search method, and the picture search method includes the following steps:

get text information;

Perform keyword extraction on the text information to obtain keywords of the text information;

Search in a preset gallery according to the keyword to obtain a picture corresponding to the keyword.

Optionally, the step of performing keyword extraction on the text information to obtain keywords of the text information includes:

Partitioning the text information into multiple parts of speech words;

Screening the words of the multiple parts of speech, and selecting the words of the preset part of speech as keywords.

Optionally, the step of performing retrieval in a preset gallery according to the keyword, and obtaining a picture corresponding to the keyword includes:

Determine the priority of the keywords according to the part of speech corresponding to each keyword, and sort the keywords according to the determined priorities;

According to the sorting results, the database is searched in sequence to obtain the pictures corresponding to the keywords.

Optionally, the priority of each word in the keyword is a noun, a verb, and an adjective in descending order.

Optionally, the step of determining the priority of the keyword according to the part of speech corresponding to each keyword includes:

The positions of the verbs and adjectives corresponding to the nouns are determined, and the priority of the verbs and adjectives is determined according to the positions of the verbs and adjectives corresponding to the nouns.

Optionally, the step of sequentially retrieving in the database according to the sorting results, and obtaining the pictures corresponding to the keywords includes:

Search in the database according to the keyword with the highest priority among the keywords, and obtain the corresponding first category of pictures;

The first category of pictures is searched in sequence according to the priority order of each keyword to obtain corresponding pictures.

Optionally, when there are multiple keywords with the highest priority, the step of performing retrieval in the database according to the keyword with the highest priority among the keywords, and obtaining the corresponding first category of pictures includes:

Respectively search for each keyword in the word class with the highest priority, and obtain a plurality of corresponding first-class pictures.

Optionally, the step of obtaining text information further includes:

get voice information;

The voice information is converted into text information by text conversion.

In addition, in order to achieve the above object, the present invention also provides a picture search device, the picture search device includes: a memory, a processor and a picture search program stored in the memory and running on the processor, When the picture search program is executed by the processor, the steps of the picture search method as described above are realized.

In addition, in order to achieve the above object, the present invention also provides a computer-readable storage medium, where a picture search program is stored on the computer-readable storage medium, and when the picture search program is executed by a processor, the above-mentioned picture search method is realized. step.

The present invention provides a picture search method, device and computer storage medium. In this method, text information is obtained; keyword extraction is performed on the text information to obtain the keywords of the text information; according to the keywords, a preset gallery is searched to obtain the corresponding keywords. picture. Through the above method, the present invention can automatically search for relevant pictures according to the obtained text data, so that the searched pictures can be inserted into the text information and displayed as text illustrations, thereby making the text data more vivid and enriching the expression form of the text information, It is more beneficial to readers, especially children's reading comprehension.

Description of drawings

1 is a schematic diagram of a device structure of a hardware operating environment involved in an embodiment of the present invention;

2 is a schematic flowchart of a first embodiment of a picture search method according to the present invention;

3 is a schematic flowchart of a second embodiment of a picture search method according to the present invention;

4 is a schematic flowchart of a third embodiment of a picture search method according to the present invention;

5 is a schematic flowchart of a fourth embodiment of a picture search method according to the present invention;

6 is a schematic flowchart of a fifth embodiment of a picture search method according to the present invention;

The realization, functional characteristics and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments.

Detailed ways

It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention.

As shown in FIG. 1 , FIG. 1 is a schematic diagram of a device structure of a hardware operating environment involved in the solution of an embodiment of the present invention.

The terminal in the embodiment of the present invention may be a PC, or may be a terminal device with a data processing function, such as a smart phone, a tablet computer, and a portable computer.

As shown in FIG. 1 , the terminal may include: a processor 1001 , such as a CPU, a network interface 1004 , a user interface 1003 , a memory 1005 , and a communication bus 1002 . Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. Optionally, the network interface 1004 may include a standard wired interface and a wireless interface (eg, a WI-FI interface). The memory 1005 may be high-speed RAM memory, or may be non-volatile memory, such as disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001 .

Optionally, the terminal may further include a camera, an RF (Radio Frequency, radio frequency) circuit, a sensor, an audio circuit, a Wi-Fi module, and the like. Among them, sensors such as light sensors, motion sensors and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display screen according to the brightness of the ambient light, and the proximity sensor may turn off the display screen and/or turn off the display screen when the mobile terminal is moved to the ear. Backlight. As a kind of motion sensor, the gravitational acceleration sensor can detect the magnitude of acceleration in all directions (generally three axes), and can detect the magnitude and direction of gravity when stationary, and can be used for applications that recognize the posture of mobile terminals (such as horizontal and vertical screen switching, related games, magnetometer attitude calibration), vibration recognition related functions (such as pedometer, tapping), etc.; of course, the mobile terminal can also be equipped with other sensors such as gyroscope, barometer, hygrometer, thermometer, infrared sensor, etc. No longer.

Those skilled in the art can understand that the terminal structure shown in FIG. 1 does not constitute a limitation on the terminal, and may include more or less components than the one shown, or combine some components, or arrange different components.

As shown in FIG. 1 , the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module and a picture search program.

In the terminal shown in FIG. 1 , the network interface 1004 is mainly used to connect to the background server and perform data communication with the background server; the user interface 1003 is mainly used to connect to the client (client) and perform data communication with the client; and the processor 1001 can be used to invoke the picture search program stored in memory 1005 and perform the following operations:

get text information;

Perform keyword extraction on the text information to obtain keywords of the text information;

Search in a preset gallery according to the keyword to obtain a picture corresponding to the keyword.

Further, the processor 1001 can call the picture search program stored in the memory 1005, and also perform the following operations:

Partitioning the text information into multiple parts of speech words;

Screening the words of the multiple parts of speech, and selecting the words of the preset part of speech as keywords.

Further, the processor 1001 can call the picture search program stored in the memory 1005, and also perform the following operations:

Determine the priority of the keywords according to the part of speech corresponding to each keyword, and sort the keywords according to the determined priorities;

According to the sorting results, the database is searched in sequence to obtain the pictures corresponding to the keywords.

Further, the processor 1001 can call the picture search program stored in the memory 1005, and also perform the following operations:

The priority of each word in the keyword is noun, verb and adjective in descending order.

Further, the processor 1001 can call the picture search program stored in the memory 1005, and also perform the following operations:

The positions of the verbs and adjectives corresponding to the nouns are determined, and the priority of the verbs and adjectives is determined according to the positions of the verbs and adjectives corresponding to the nouns.

Further, the processor 1001 can call the picture search program stored in the memory 1005, and also perform the following operations:

Search in the database according to the keyword with the highest priority among the keywords, and obtain the corresponding first category of pictures;

The first category of pictures is searched in sequence according to the priority order of each keyword to obtain corresponding pictures.

Further, the processor 1001 can call the picture search program stored in the memory 1005, and also perform the following operations:

Respectively search for each keyword in the word class with the highest priority, and obtain a plurality of corresponding first-class pictures.

Further, the processor 1001 can call the picture search program stored in the memory 1005, and also perform the following operations:

get voice information;

The voice information is converted into text information by text conversion.

The specific embodiments of the picture search device of the present invention are basically the same as the embodiments of the following picture search methods, and are not repeated here.

Referring to FIG. 2, FIG. 2 is a schematic flowchart of a first embodiment of a picture search method according to the present invention. The picture search method includes:

Step S100, obtaining text information;

The present invention mainly searches for pictures according to text information, and searches for pictures related to the text information. In this embodiment, the text information that needs to be searched for pictures can be obtained according to various ways such as played voice information or electronic documents, and the present invention does not limit the way of obtaining the text information. The text information is text information, which can be an article such as a fairy tale, or a paragraph input by the user, or text information converted from text according to the voice input by the user. The text information may be a sentence or a long text, and the length of the text information is not limited. For example, a paragraph of text may be obtained from an electronic book of children's books, and the obtained paragraph of text is the text information mentioned in the present invention.

Step S200, performing keyword extraction on the text information to obtain keywords of the text information;

After the text information is obtained, keyword extraction is performed on the text information. The keyword extraction may be performed according to the sentence structure of the text information according to the part of speech of each word in the text information, and may also be extracted by other methods. For example, the noun words, verb words, etc. in a sentence are extracted as keywords. Words have a variety of parts of speech, such as nouns, verbs, adjectives, adverbs and other fourteen types of word parts of speech.

Step S300, searching in a preset gallery according to the keyword to obtain a picture corresponding to the keyword.

In this embodiment, retrieval is performed in a preset gallery according to keywords. The preset gallery contains multiple pictures, each picture has a corresponding label, and the pictures are classified according to the labels of the pictures. By comparing the image tags in the preset gallery, you can obtain images related to keywords. In this way, the keywords can be used to search in the preset gallery, and the pictures corresponding to the keywords can be obtained.

After obtaining the keywords in the text information, sort the keywords so that the keywords have a priority order, such as noun words are better than verb words, and verb words are better than adjective words, etc., and then according to the priority order of part of speech words in the database First, search a large set of pictures according to the previous part of speech words, and then perform fuzzy matching in the previous large set of pictures according to the following part of speech words in a gradually narrowing manner to obtain a small set of pictures, until the final search results in the corresponding picture , of course, a combination of keywords can also be used to search in a preset gallery to obtain a picture corresponding to the keyword.

When searching according to the following part-of-speech words in the previous large collection of pictures, if the search result is a picture, then the picture is the picture we need, but most of the time, the corresponding picture may not be found, and the previous picture is returned. A picture in the large set is the picture corresponding to the keyword, which can be the first picture in the previous large set of pictures, or other pictures set according to other requirements or rules.

The present invention provides a picture search method, device and computer storage medium. In this method, a picture search instruction is received, and text information is obtained according to the picture search instruction; keyword extraction is performed on the text information to obtain keywords of the text information; Search to obtain a picture corresponding to the keyword. Through the above method, the present invention can automatically search for relevant pictures according to the obtained text data, so that the searched pictures can be inserted into the text information and displayed as text illustrations, thereby making the text data more vivid and enriching the expression form of the text information, It is more beneficial to readers, especially children's reading comprehension.

Please refer to FIG. 3 , which is a schematic flowchart of a second embodiment of a picture search method according to the present invention.

Based on the foregoing embodiment, in this embodiment, step S200 includes:

Step S210, the text information is divided into parts of speech, and divided into multiple parts of speech words;

This embodiment is an embodiment of performing keyword extraction on the text information to obtain keyword explanations in the text information. After obtaining the text information, firstly, according to the text information, the parts of speech in the text information are divided, and the text information is divided into multiple parts of speech words, such as multiple noun words, multiple verb words, multiple adjective words and other word patterns. For example, the text information is "Snow White is eating apples", according to the word class, the text can be divided into nouns "Snow White" and "apples", verbs "eat", and adverbs "zai".

Step S220: Screening the multiple part-of-speech words, and selecting a word of a preset part-of-speech as a keyword.

Then, the divided part-of-speech words are screened according to the part-of-speech of the words, and the words of the preset part-of-speech are selected as keywords, for example, noun words, verb words and adjective words are selected as keywords. The part of speech of the selected word can be set according to the situation. For example, in the text information "Snow White is eating apples", the nouns "Snow White" and "apple" are selected, and the verb "eat" is the keyword.

Please refer to FIG. 4 , which is a schematic flowchart of a third embodiment of a picture search method according to the present invention.

Based on the foregoing embodiment, in this embodiment, step S300 includes:

Step S310, determining the priority of the keywords according to the part of speech corresponding to each keyword, and sorting the keywords according to the determined priorities;

In this embodiment, searching in a preset thesaurus according to the keywords to obtain pictures corresponding to the keywords may first be sorted according to the parts of speech corresponding to the keywords, for example, noun words in the keywords Set to the highest priority part-of-speech words, followed by verb words, and adjective words. In this way, the priorities of the set words are nouns, verbs and adjectives in descending order. You can also choose other sorting rules to sort keywords.

Further, in this embodiment, after it is determined that the priorities of each word are nouns, verbs and adjectives in descending order, and after the noun words are the first priority search words, the verbs and adjectives can be set according to the following rules: determine The verbs and adjectives correspond to the positions of the nouns, and the priority of the verbs and adjectives is determined according to the positions of the verbs and adjectives corresponding to the nouns.

First determine the positions of the verbs and adjectives corresponding to the noun, and then determine the priority of the verbs and adjectives according to the positions of the verbs and adjectives corresponding to the noun. Verbs in front take precedence over verbs that follow nouns.

Step S320, according to the sorting result, the database is searched in sequence to obtain the picture corresponding to the keyword.

After the priority order of the keywords is obtained, searches are performed in the database according to the priorities of the keywords in order to obtain pictures corresponding to the keywords. The retrieval method is to retrieve according to the words in the front, first retrieve a large category, and then in the detected large category, retrieve a small category based on the words in the back, and use this as a rule. Retrieve, retrieve the pictures we need.

Similarly, in the large category of pictures searched for by nouns, first search based on the preceding adjectives, search for the sub-category pictures corresponding to the adjectives of the noun, and then perform further searches based on the following adjectives in this sub-category of pictures. For example, the text information "The blue sea is beautiful", first search according to the noun "sea", and search for the picture category corresponding to the noun "sea", and then, in the category of the noun "sea", search for the adjective "blue" The picture sub-category corresponding to the adjective "blue", and then search for the picture sub-category corresponding to the adjective "beautiful" in the picture sub-category corresponding to the adjective "blue". In this way, the pictures corresponding to the text information are searched.

Please refer to FIG. 5 , which is a schematic flowchart of a fourth embodiment of a picture search method according to the present invention.

Based on the foregoing embodiment, in this embodiment, step S320 includes:

Step S321, searching in the database according to the keyword with the highest priority in the keywords, and obtaining the corresponding first category of pictures;

According to the sentence structure of the text information, when the extracted keywords are few, for example, when the extracted keywords have only one noun and one verb, you can first search for a large category based on this noun. When the text information is long, according to the sentence structure of the text information, when there are many keywords extracted, such as the extracted keywords are multiple nouns, multiple verbs, multiple adjectives, according to the priority order, such as nouns If the verb is superior to the verb, and the verb is superior to the adjective, the highest priority word class words and multiple nouns are retrieved separately, and a plurality of first-class pictures are retrieved. For example: text information "child fell on the black floor", according to the text information, extract the keyword noun "child" "floor" verb "fall down" adjective "black", then first search for the first according to the highest part of speech noun A large category of pictures, that is, a large category of pictures is searched according to "children", and a large category of pictures is searched according to "floor", that is, two juxtaposed first categories are searched according to two different nouns. picture.

Step S322: Search in the first category of pictures in sequence according to the priority order of each keyword to obtain a corresponding picture.

After the first category of pictures is retrieved, the retrieval is performed in sequence according to the priority order of the words. However, when there are multiple keywords with the highest priority, each keyword in the class of speech with the highest priority is searched to obtain a plurality of corresponding pictures of the first category. For example, when there are many keywords extracted, such as multiple nouns, multiple verbs, and multiple adjectives, after retrieving multiple first-category pictures according to multiple nouns, then according to the corresponding nouns The verbs and adjectives are retrieved in order of priority, and each picture sub-category is retrieved. For example: text information "The child fell on the black floor", according to the text information, after searching for two different first category pictures based on the nouns "children" and "floor", in the first picture category noun " In the first category of pictures corresponding to "children", a second search is performed according to the verb "fall" corresponding to the noun "children", and the second category of pictures corresponding to "fall" is found; in the second category of pictures In the first category of pictures corresponding to the noun "floor", a second search is performed according to the adjective "black" corresponding to the noun "floor", and the second category of pictures corresponding to "black" is searched. In this way, according to the text information, two pictures are searched, one is searched for "children"/"fallen", and the other is searched for "floor"/"black".

Please refer to FIG. 6 , which is a schematic flowchart of a fifth embodiment of a picture search method according to the present invention.

Based on the foregoing embodiment, in this embodiment, step S100 includes:

Step S110, obtaining voice information;

Step S120, performing text conversion on the voice information to convert it into text information.

In this embodiment, the voice information input by the user can also be obtained. After the user inputs the voice information, the voice information input by the user is converted into text, and then keyword extraction and image search are performed according to the text information. In this way, the scope of the text can be expanded, the solution is more beneficial to the application, and the user has a better use experience.

In addition, the embodiments of the present invention also provide a computer-readable storage medium.

The computer-readable storage medium of the present invention stores a picture search program, and when the picture search program is executed by the processor, implements the steps of the above-mentioned picture search method.

For the method implemented when the picture search program running on the processor is executed, reference may be made to the various embodiments of the picture search method of the present invention, which will not be repeated here.

It should be noted that, herein, the terms "comprising", "comprising" or any other variation thereof are intended to encompass non-exclusive inclusion, such that a process, method, article or system comprising a series of elements includes not only those elements, It also includes other elements not expressly listed or inherent to such a process, method, article or system. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in the process, method, article or system that includes the element.

The above-mentioned serial numbers of the embodiments of the present invention are only for description, and do not represent the advantages or disadvantages of the embodiments.

From the description of the above embodiments, those skilled in the art can clearly understand that the method of the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is better implementation. Based on such understanding, the technical solutions of the present invention can be embodied in the form of software products in essence or the parts that make contributions to the prior art, and the computer software products are stored in a storage medium (such as ROM/RAM) as described above. , magnetic disk, optical disk), including several instructions to make a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the methods described in the various embodiments of the present invention.

The above are only preferred embodiments of the present invention, and are not intended to limit the scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the description and drawings of the present invention, or directly or indirectly applied in other related technical fields , are similarly included in the scope of patent protection of the present invention.

Claims (10)

1. a picture search method, is characterized in that, described picture search method comprises the following steps: get text information; Perform keyword extraction on the text information to obtain keywords of the text information; Search in a preset gallery according to the keyword to obtain a picture corresponding to the keyword. 2. The image search method according to claim 1, wherein the step of performing keyword extraction on the text information, and obtaining the keywords of the text information comprises: Partitioning the text information into multiple parts of speech words; Screening the words of the multiple parts of speech, and selecting the words of the preset part of speech as keywords. 3. The image search method according to claim 2, wherein the step of performing retrieval in a preset gallery according to the keyword, and obtaining a picture corresponding to the keyword comprises: Determine the priority of the keywords according to the part of speech corresponding to each keyword, and sort the keywords according to the determined priorities; According to the sorting results, the database is searched in sequence to obtain the pictures corresponding to the keywords. 4 . The image search method according to claim 3 , wherein the priority of each word in the keyword is noun, verb and adjective in descending order. 5 . 5. The image search method according to claim 3, wherein the step of determining the priority of the keyword according to the part of speech corresponding to each keyword comprises: The positions of the verbs and adjectives corresponding to the nouns are determined, and the priority of the verbs and adjectives is determined according to the positions of the verbs and adjectives corresponding to the nouns. 6. The image search method according to claim 3, wherein the step of sequentially retrieving in the database according to the sorting result, and obtaining the image corresponding to the keyword comprises: Search in the database according to the keyword with the highest priority among the keywords, and obtain the corresponding first category of pictures; The first category of pictures is searched in sequence according to the priority order of each keyword to obtain corresponding pictures. 7. The image search method according to claim 6, wherein when there are multiple keywords with the highest priority, the retrieval is performed in the database according to the keyword with the highest priority in the keywords, The steps of obtaining the corresponding first category pictures include: Respectively search for each keyword in the word class with the highest priority, and obtain a plurality of corresponding first-class pictures. 8. The image search method according to claim 1, wherein the step of obtaining text information further comprises: get voice information; The voice information is converted into text information by text conversion. 9. A picture search device, characterized in that the picture search device comprises: a memory, a processor, and a picture search program stored on the memory and executable on the processor, the picture search program being The processor implements the steps of the image search method according to any one of claims 1 to 8 when executed. 10. A computer-readable storage medium, characterized in that, a picture search program is stored on the computer-readable storage medium, and when the picture search program is executed by a processor, any one of claims 1 to 8 is implemented. Describe the steps of the image search method.