WO2018209845A1

WO2018209845A1 - Method and apparatus for generating stories on the basis of picture content

Info

Publication number: WO2018209845A1
Application number: PCT/CN2017/100329
Authority: WO
Inventors: 张学华; 刘宇翔; 雷超然; 季雨晴
Original assignee: 北京金山安全软件有限公司
Priority date: 2017-05-19
Filing date: 2017-09-04
Publication date: 2018-11-22
Also published as: CN107193941A

Abstract

A method and apparatus for generating stories on the basis of picture content, said method comprising: identifying picture content and extracting a keyword (101); obtaining a generalized word which is related to the keyword (102); generating sentences which are related to the keyword and the generalized word according to a pre-trained a story word and sentence correlation information base (103); sorting the sentences according to a preset logic rule in order to generate a story corresponding to the picture, and playing back the story (104). Hence, a story corresponding to a picture is generated and played back after further generalization processing is carried out on identified picture content, thus increasing the convenience of artificial intelligence and making artificial intelligence more interesting, while improving user experience.

Description

Story generation method and device based on picture content

Cross-reference to related applications

The present application claims the priority of the Chinese patent application No. "201710359135.0" filed on May 19, 2017 by Beijing Jinshan Security Software Co., Ltd., entitled "Method and Apparatus for Generating Story Based on Picture Content".

Technical field

The present invention relates to the field of picture recognition technologies, and in particular, to a method and apparatus for generating a story based on picture content.

Background technique

Artificial Intelligence, abbreviated as AI in English. It is a new technical science that studies and develops theories, methods, techniques, and applications for simulating, extending, and extending human intelligence. Artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new kind of intelligent machine that can react in a way similar to human intelligence. Research in this field includes robotics, speech recognition, image recognition, Natural language processing and expert systems.

At present, the recognition of a picture is only to obtain the content information of the picture, which is relatively simple, and cannot apply the picture recognition to the artificial intelligence.

Summary of the invention

The object of the present invention is to solve at least one of the technical problems in the related art to some extent.

Therefore, an object of the present invention is to provide a method for generating a story based on a picture content, which is used to solve the problem that the image recognition cannot be applied to the artificial intelligence in the prior art, by further performing the recognized image content. After the generalization process, the story corresponding to the picture is generated and played, which improves the convenience and interest of the artificial intelligence and improves the user experience.

A second object of the present invention is to provide a story generating device based on picture content.

A third object of the present invention is to propose a computer device.

A fourth object of the present invention is to provide a non-transitory computer readable storage medium.

A fifth object of the present invention is to provide a computer program product.

In order to achieve the above object, a first aspect of the present invention provides a method for generating a story based on a picture content, including: identifying a picture content extraction keyword; acquiring a generalization word related to the keyword; and according to a pre-trained story The sentence-related information base generates a sentence related to the keyword and the generalized word; sorting the sentence according to a preset logic rule to generate a story corresponding to the picture and playing the same.

A method for generating a story based on a picture content according to an embodiment of the present invention, extracting a keyword by recognizing a picture content, and acquiring a generalized word related to the keyword, and then generating a sentence related to the keyword and the generalized word according to the pre-trained story-word-related information base, and finally sorting the sentence according to the preset logical rule to generate a story corresponding to the image and The playback is performed, and the recognized picture content is further generalized to generate a story corresponding to the picture and played, thereby improving the convenience and interest of the artificial intelligence and improving the user experience.

In addition, the picture content-based story generation method of the embodiment of the present invention further has the following additional technical features:

Optionally, the obtaining the generalized word related to the keyword includes: querying a preset synonym database to obtain a synonym corresponding to the keyword, and querying the pre-trained related vocabulary to obtain the keyword Corresponding related words.

Optionally, the method further includes: performing word segmentation processing on the information content in the sample set to generate a plurality of word units; and generating a related term database according to the co-occurrence number between the word units and the preset threshold.

Optionally, the method further includes: performing word segmentation and sentence segment processing on the information content in the story sample to generate a plurality of word units and sentence units; and according to the number of co-occurrences between the word unit and the sentence unit and the preset threshold Generating the story information related information library.

Optionally, before the step of sorting the sentence according to the preset logic rule to generate a story corresponding to the image and playing the file, the method further includes: acquiring a first weight corresponding to the keyword and Determining a second weight corresponding to the generalized word; and filtering the related sentence according to the first weight and the second weight.

In order to achieve the above objective, the second aspect of the present invention provides a story generating device based on a picture content, comprising: an extracting module, configured to identify a picture content extraction keyword; and a first acquiring module, configured to acquire the key a word-related generalization word; a first generation module, configured to generate a sentence related to the keyword and the generalization word according to a pre-trained story-word association information library; and a processing module, configured to use a preset logic rule The sentence is sorted to generate a story corresponding to the picture and played.

The picture content-based story generating apparatus according to the embodiment of the present invention extracts keywords by recognizing the picture content, acquires generalized words related to the keywords, and then generates keywords and generalized words according to the pre-trained story-word-related information base. In the related sentence, the sentence is sorted according to the preset logic rule to generate a story corresponding to the picture and played, so that the recognized picture content is further generalized to generate a story corresponding to the picture and played. Improve the convenience and fun of artificial intelligence and enhance the user experience.

In addition, the picture content-based story generating apparatus of the embodiment of the present invention further has the following additional technical features:

Optionally, the obtaining module is configured to: query a preset synonym database to obtain a synonym corresponding to the keyword, and query a pre-trained related vocabulary to acquire an associated word corresponding to the keyword.

Optionally, the obtaining module is further configured to: perform word segmentation processing on the information content in the sample set to generate a plurality of word units; and generate a related term database according to the co-occurrence number between the word units and the preset threshold.

Optionally, the device further includes: a second generating module, configured to perform word cutting and sentence processing on the information content in the story sample to generate a plurality of word units and sentence units; and a third generating module, configured to use the words according to the words Co-occurrence between unit and sentence unit The number of times and the preset threshold generate the library of related information of the story words.

Optionally, the device further includes: a second acquiring module, configured to acquire a first weight corresponding to the keyword and a second weight corresponding to the generalized word; and a screening module, configured to The first weight and the second weight filter the related sentences.

In order to achieve the above object, a third aspect of the present invention provides a computer device comprising: a memory, a processor, and a computer program stored on the memory and operable on the processor, wherein the processor When the program is executed, enabling a story content generation method based on picture content, the method comprising: identifying a picture content extraction keyword; acquiring a generalization word related to the keyword; and correlating according to a pre-trained story phrase The information base generates a sentence related to the keyword and the generalized word; sorting the sentence according to a preset logic rule to generate a story corresponding to the picture and playing the same.

In order to achieve the above object, a fourth aspect of the present invention provides a non-transitory computer readable storage medium capable of executing a story based on picture content when an instruction in the storage medium is executed by a processor a generating method, the method comprising: identifying a picture content extraction keyword; acquiring a generalization word related to the keyword; generating, according to the pre-trained story word association information library, the keyword and the generalization word a sentence; sorting the sentence according to a preset logic rule to generate a story corresponding to the picture and playing the same.

In order to achieve the above object, a fifth aspect of the present invention provides a computer program product, when executed by an instruction processor in the computer program product, a method for generating a story based on a picture content, the method comprising: Identifying a picture content extraction keyword; acquiring a generalization word related to the keyword; generating a sentence related to the keyword and the generalization word according to a pre-trained story word association information base; according to a preset logic rule The sentence is sorted to generate a story corresponding to the picture and played.

The additional aspects and advantages of the invention will be set forth in part in the description which follows.

DRAWINGS

1 is a flowchart of a method for generating a story based on a picture content according to an embodiment of the present invention;

2 is a schematic diagram of a sample of a picture according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of generating a story based on picture content according to another embodiment of the present invention; FIG.

FIG. 4 is a flowchart of a method for generating a story based on a picture content according to another embodiment of the present invention; FIG.

FIG. 5 is a schematic structural diagram of a story content generating apparatus based on a picture content according to an embodiment of the present invention; FIG.

FIG. 6 is a schematic structural diagram of a story content generating apparatus based on a picture content according to another embodiment of the present invention; FIG.

FIG. 7 is a schematic structural diagram of a story content generating apparatus based on a picture content according to another embodiment of the present invention.

detailed description

The embodiments of the present invention are described in detail below, and the examples of the embodiments are illustrated in the drawings, wherein the same or similar reference numerals are used to refer to the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the drawings are intended to be illustrative of the invention and are not to be construed as limiting.

A method and apparatus for generating a story based on picture content according to an embodiment of the present invention will be described below with reference to the accompanying drawings.

FIG. 1 is a flowchart of a method for generating a story based on a picture content according to an embodiment of the present invention.

It should be noted that the picture content-based story generation method in the embodiment of the present application can be applied to devices (mobile phones, tablets, computers, etc.) of Android, IOS, PC, and the like.

Specifically, the picture content recognition refers to interpreting the picture, and can identify an object included in the picture, a shooting scene of the picture, and the like. Usually the image content recognition method is object detection, that is, by defining a series of templates, each template captures a certain type of object.

However, the above recognition results are relatively simple and cannot be applied to the artificial image recognition technology. In order to further improve the convenience and interest of artificial intelligence, the present invention provides a story generation method based on picture content, and further generalizes the recognized picture content to generate a story corresponding to the picture and play it. details as follows:

As shown in FIG. 1, the image content-based story generation method includes the following steps:

Step 101: Identify a picture content extraction keyword.

Step 102: Obtain a generalized word related to the keyword.

Specifically, the picture may be processed by a picture recognition software or an algorithm to identify the picture content, and the picture content is processed to extract keywords. It can be understood that a number of words or phrases representing picture content are extracted as keywords.

Further, the generalized word related to the keyword can be obtained in a plurality of ways. As an example, the predetermined synonym database is used to obtain a synonym corresponding to the keyword, and the pre-trained related vocabulary is obtained by querying the corresponding vocabulary. Related words.

For example, by extracting keywords from the picture shown in FIG. 2, the keywords are “girl”, “woman”, etc., and then querying the synonyms of “girl”, “woman”, etc. in the preset synonym database, for example. “Girls”, “Goddess”, “Beautiful People”, etc., and then query the pre-trained related vocabulary. For example, “girls” correspond to “cute” and “meng Meng”, so that “Goddess” and “Girls” can be obtained. Synonyms and related words such as "model", "beauty", "cute", "beautiful", "beautiful", "beauty", "meng Meng" are used as generalization words related to keywords.

Among them, the thesaurus is pre-set, such as "beauty" and "girl" are synonymous words; "severe", "great" is a synonym, etc., and the lexicon can be adjusted as needed to increase or decrease the number of synonyms. The synonym database holds the relationship of multiple synonyms (the form can be a mapping table, etc.), for example, by keyword X. Find the corresponding mapping table (which can also be calculated by related algorithms, etc.) to find the synonym Y, Z, or more synonyms.

It should be noted that the related vocabulary can be trained in a plurality of ways. As an example, the information content in the sample set is subjected to word-cutting processing to generate a plurality of word units, according to the number of co-occurrences between the word units and a preset threshold. Generate a related term library. That is, the correlation between a large number of word units can be evaluated. For example, if the number of occurrences of two word units together is greater than a preset threshold, for example, 10 times, the two word units are set as related words and stored in the associated thesaurus.

Step 103: Generate a sentence related to the keyword and the generalized word according to the pre-trained story-word-related information base.

Step 104: Sort the sentence according to a preset logic rule to generate a story corresponding to the picture and play it.

Specifically, it is necessary to train and generate a story-to-speech information base in advance. It can be understood that there are many ways to generate a story-word-related information base, which can be selected according to actual application requirements, as illustrated below:

As an example, the information content in the story sample is subjected to word-cutting and sentence-breaking processing to generate a plurality of word units and sentence units; and the story-word-related information base is generated according to the number of co-occurrences between the word unit and the sentence unit and the preset threshold. That is, the relationship between the word unit and the sentence unit can be determined by the information content in a large number of story samples. For example, if a word unit and a sentence unit appear together more than a preset threshold, for example, 10 times, the word unit and the sentence unit are Saved in the story-related information library.

For example, if the unit "has a little cat" and the unit of "howling" always appear in one story at the same time, then the score of the unit and the unit of the word will be higher, that is, the number of occurrences is greater than The threshold is preset so as to be stored in the story-related information base as the story-related information.

Further, the sentence related to the keyword and the generalized word is generated according to the pre-trained story-word-related information base, that is, the related sentence that can be obtained through the keyword, the generalized word, and the pre-trained story-word-related information base is associated. Create a whole new story.

Further, the story is continuous, that is, has a certain plot. It can be understood that there are many related sentences, and it is necessary to sort and process a plurality of sentences through a preset logic rule to generate a story corresponding to the image and play it.

As a scene implementation, the user uploads a picture as shown in Figure 3. It can automatically match the story corresponding to the generated picture. "In the past, there was a very beautiful little girl. She was very funny, she also had a beautiful hair. She loves the sun, she is a very cheerful person, everyone likes her, why do everyone like her? Just because people like people who love to laugh, you have to smile more." Thereby, the interest of artificial intelligence is further improved.

In summary, the method for generating a story based on a picture content according to an embodiment of the present invention extracts a keyword by recognizing a picture content, acquires a generalization word related to the keyword, and then generates and keys according to the pre-trained story phrase association information base. The words related to the generalized words are finally sorted according to the preset logic rules to generate a story corresponding to the picture and played, so that the recognized picture content is further generalized and then generated corresponding to the picture. The story goes hand in hand Line playback improves the convenience and fun of artificial intelligence and enhances the user experience.

FIG. 4 is a flowchart of a method for generating a story based on a picture content according to another embodiment of the present invention. As shown in FIG. 4, before step 104, the method further includes:

Step 201: Acquire a first weight corresponding to the keyword and a second weight corresponding to the generalized word.

Step 202: Filter related sentences according to the first weight and the second weight.

Specifically, the user may give different weights to the keyword and the generalized word according to actual application requirements, for example, the first weight corresponding to the keyword is 0.4; the second weight corresponding to the generalized word is 0.6. Thereby, relevant sentences satisfying the requirements can be obtained, and the user experience is further improved.

In order to implement the above embodiment, the present invention proposes a story generating device based on picture content.

FIG. 5 is a flowchart of a picture content based story generating apparatus according to an embodiment of the present invention.

As shown in FIG. 5, the picture content-based story generating apparatus includes an extracting module 11, a first obtaining module 12, a first generating module 13, and a processing module 14.

The extraction module 11 is configured to identify a picture content extraction keyword.

The first obtaining module 12 is configured to obtain a generalized word related to the keyword.

The first generating module 13 is configured to generate a sentence related to the keyword and the generalized word according to the pre-trained story-word-related information base.

The processing module 14 is configured to perform a sorting process on the sentence according to a preset logic rule to generate a story corresponding to the picture and play the same.

Further, the obtaining module 12 is configured to query a preset synonym database to obtain a synonym corresponding to the keyword, and query the pre-trained related vocabulary to acquire an associated word corresponding to the keyword.

Further, the obtaining module 12 is further configured to perform word segmentation processing on the information content in the sample set to generate a plurality of word units; and generate a related term database according to the co-occurrence number between the word units and the preset threshold.

Further, as shown in FIG. 6, on the basis of FIG. 5, the picture content-based story generating apparatus further includes: a second generating module 15, a third generating module 16, a second obtaining module 17, and a screening module 18.

The second generation module 15 is configured to perform word segmentation and sentence segment processing on the information content in the story sample to generate a plurality of word units and sentence units.

The third generation module 16 is configured to generate a story-word association information base according to the number of co-occurrences between the word unit and the sentence unit and the preset threshold.

The second obtaining module 17 is configured to acquire a first weight corresponding to the keyword and a second weight corresponding to the generalized word.

The screening module 18 is configured to filter related sentences according to the first weight and the second weight.

It should be noted that the foregoing explanation of the embodiment of the method for generating a story based on the picture content is also applicable to the image content-based story generating device of the embodiment, and details are not described herein again.

In summary, the picture content-based story generating apparatus of the embodiment of the present invention extracts keywords by recognizing the picture content, acquires generalized words related to the keywords, and then generates and keys according to the pre-trained story words and related information bases. The words related to the generalized words are finally sorted according to the preset logic rules to generate a story corresponding to the picture and played, so that the recognized picture content is further generalized and then generated corresponding to the picture. The story is played and played, which improves the convenience and fun of artificial intelligence and enhances the user experience.

FIG. 7 is a flowchart of a picture content-based story generating apparatus according to still another embodiment of the present invention. As shown in FIG. 7, the picture content-based story generating device includes:

The memory 21, the processor 22, and a computer program stored on the memory 21 and operable on the processor 22.

The processor 22 executes the program to implement the picture content based story generation method provided in the above embodiment.

Further, the story content generating device based on the image content further includes:

Communication interface 23 is used for communication between memory 21 and processor 22.

The memory 21 is for storing a computer program executable on the processor 22.

The memory 21 may include a high speed RAM memory and may also include a non-volatile memory such as at least one disk memory.

The processor 22 is configured to implement the picture content-based story generation method described in the foregoing embodiment when the program is executed.

If the memory 21, the processor 22, and the communication interface 23 are independently implemented, the communication interface 21, the memory 21, and the processor 22 can be connected to each other through a bus and complete communication with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Wait. The bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, only one thick line is shown in Figure 7, but it does not mean that there is only one bus or one type of bus.

Optionally, in a specific implementation, if the memory 21, the processor 22, and the communication interface 23 are integrated on one chip, the memory 21, the processor 22, and the communication interface 23 can complete communication with each other through the internal interface.

The processor 22 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more configured to implement the embodiments of the present invention. integrated circuit.

In order to achieve the above embodiments, the present invention also provides a computer device, comprising: a memory, a processor, and a computer program stored on the memory and operable on the processor, wherein the processor executes the program </ RTI> enabling a story content generation method based on picture content, the method comprising: identifying a picture content extraction keyword; acquiring a generalization word related to the keyword; generating and keywords according to the pre-trained story word association information base A sentence related to a generalized word; sorting the sentence according to a preset logical rule to generate a story corresponding to the picture and playing it.

In order to implement the above embodiments, the present invention also provides a non-transitory computer readable storage medium, enabling execution of a story content generation method based on picture content when instructions in the storage medium are executed by a processor The method includes: identifying a picture content extraction keyword; acquiring a generalization word related to the keyword; generating a sentence related to the keyword and the generalization word according to the pre-trained story word association information base; and the sentence according to the preset logic rule Sorting is performed to generate a story corresponding to the picture and play it.

In order to achieve the above embodiments, the present invention also provides a computer program product, which, when executed by an instruction processor in the computer program product, enables execution of a picture content based story generation method, the method comprising: identifying a picture Content extraction keywords; obtaining generalization words related to keywords; generating sentences related to keywords and generalization words according to pre-trained story-word association information base; sorting processing sentences according to preset logic rules to generate images Corresponding stories are played and played.

Moreover, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, features defining "first" or "second" may include at least one of the features, either explicitly or implicitly. In the description of the present invention, the meaning of "a plurality" is at least two, such as two, three, etc., unless specifically defined otherwise.

In the description of the present specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" and the like means a specific feature described in connection with the embodiment or example. A structure, material or feature is included in at least one embodiment or example of the invention. In the present specification, the schematic representation of the above terms is not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. In addition, various embodiments or examples described in the specification, as well as features of various embodiments or examples, may be combined and combined.

Any process or method description in the flowcharts or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logic function or process. And the scope of the preferred embodiments of the invention includes additional implementations, in which the functions may be performed in a substantially simultaneous manner or in an opposite order depending on the functions involved, in the order shown or discussed. It will be understood by those skilled in the art to which the embodiments of the present invention pertain.

The logic and/or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be embodied in any computer readable medium, Used in conjunction with, or in conjunction with, an instruction execution system, apparatus, or device (eg, a computer-based system, a system including a processor, or other system that can fetch instructions and execute instructions from an instruction execution system, apparatus, or device) Or use with equipment. For the purposes of this specification, a "computer-readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport a program for use in an instruction execution system, apparatus, or device, or in conjunction with the instruction execution system, apparatus, or device. Computer More specific examples (non-exhaustive list) of readable media include the following: electrical connections (electronic devices) with one or more wires, portable computer disk cartridges (magnetic devices), random access memory (RAM), only Read memory (ROM), erasable editable read only memory (EPROM or flash memory), fiber optic devices, and portable compact disk read only memory (CDROM). In addition, the computer readable medium may even be a paper or other suitable medium on which the program can be printed, as it may be optically scanned, for example by paper or other medium, followed by editing, interpretation or, if appropriate, other suitable The method is processed to obtain the program electronically and then stored in computer memory.

It should be understood that portions of the invention may be implemented in hardware, software, firmware or a combination thereof. In the above-described embodiments, multiple steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware and in another embodiment, it can be implemented by any one or combination of the following techniques well known in the art: discrete with logic gates for implementing logic functions on data signals Logic circuits, application specific integrated circuits with suitable combinational logic gates, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), and the like.

One of ordinary skill in the art can understand that all or part of the steps carried by the method of implementing the above embodiments can be completed by a program to instruct related hardware, and the program can be stored in a computer readable storage medium. When executed, one or a combination of the steps of the method embodiments is included.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. The integrated modules, if implemented in the form of software functional modules and sold or used as stand-alone products, may also be stored in a computer readable storage medium.

The above mentioned storage medium may be a read only memory, a magnetic disk or an optical disk or the like. Although the embodiments of the present invention have been shown and described, it is understood that the above-described embodiments are illustrative and are not to be construed as limiting the scope of the invention. The embodiments are subject to variations, modifications, substitutions and variations.

Claims

A method for generating a story based on picture content, comprising the steps of:

Identifying picture content extraction keywords;

Obtaining generalized words related to the keyword;

Generating a sentence related to the keyword and the generalized word according to a pre-trained story-phrase association information base;

The sentence is sorted according to a preset logic rule to generate a story corresponding to the picture and played.
The method of claim 1 wherein said obtaining a generalized word associated with said keyword comprises:

Querying a preset synonym to obtain a synonym corresponding to the keyword, and

Querying the pre-trained related vocabulary to obtain the related words corresponding to the keyword.
The method of claim 2, further comprising:

Performing word-cutting on the information content in the sample set to generate a plurality of word units;

A related vocabulary is generated according to the number of co-occurrences between word units and a preset threshold.
The method of any of claims 1-3, further comprising:

Performing word-cutting and sentence-breaking processing on the information content in the sample of the story to generate a plurality of word units and sentence units;

The story-word association information base is generated according to the co-occurrence number between the word unit and the sentence unit and a preset threshold.
The method according to any one of claims 1-4, wherein before the step of sorting the sentence according to a preset logic rule to generate a story corresponding to the picture and playing the file, the method further includes:

Obtaining a first weight corresponding to the keyword and a second weight corresponding to the generalized word;

The related sentences are filtered according to the first weight and the second weight.
A story generating device based on picture content, comprising:

An extraction module, configured to identify a picture content extraction keyword;

a first obtaining module, configured to acquire a generalized word related to the keyword;

a first generating module, configured to generate a sentence related to the keyword and the generalized word according to a pre-trained story-word association information base;

And a processing module, configured to perform a sorting process on the sentence according to a preset logic rule to generate a story corresponding to the image and play the same.
The apparatus according to claim 6, wherein said obtaining module is configured to:

Querying a preset synonym to obtain a synonym corresponding to the keyword, and

Querying the pre-trained related vocabulary to obtain the related words corresponding to the keyword.
The device according to claim 7, wherein the obtaining module is further configured to:

Performing word-cutting on the information content in the sample set to generate a plurality of word units;

A related vocabulary is generated according to the number of co-occurrences between word units and a preset threshold.
The device of any of claims 6-8, further comprising:

a second generating module, configured to perform word cutting and sentence processing on the information content in the story sample to generate a plurality of word units and sentence units;

The third generation module is configured to generate the story-word association information base according to the co-occurrence number between the word unit and the sentence unit and the preset threshold.
The device of any of claims 6-9, further comprising:

a second acquiring module, configured to acquire a first weight corresponding to the keyword and a second weight corresponding to the generalized word;

a screening module, configured to filter the related sentence according to the first weight and the second weight.
A computer device, comprising: a memory, a processor, and a computer program stored on the memory and operable on the processor, wherein when the processor executes the program, the implementation is as claimed in claim 1 The method of any of 5.
A non-transitory computer readable storage medium having stored thereon a computer program, wherein the program, when executed by a processor, implements the method of any of claims 1-5.
A computer program product for performing the method of any of claims 1-5 when the instructions in the computer program product are executed by a processor.