A text keyword search method, device, equipment and storage medium
Through named entity recognition and neural network model processing, text keywords are extracted and irrelevant information is filtered, which solves the problem that users cannot quickly find the required content when obtaining text, and improves reading efficiency.
Patent Information
- Application Number
- CN202010844970.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-08-20
- Publication Date
- 2024-11-19
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
When obtaining text, users cannot effectively skip the interlaced advertising information, cannot quickly and accurately find the required content, and cannot judge whether the text meets the needs through the text title.
Named entity recognition technology is used to extract entity words in text and input them into pre-trained neural network model to obtain word vectors, determine the center point and keywords, filter irrelevant words, and analyze paragraph similarity through twin neural network models to display Related content.
It realizes the rapid and accurate acquisition of text keywords, helps users determine whether the text needs to be read, improves reading efficiency, and reduces the impact of invalid information.
Smart Images

Figure CN111949767B_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present invention relate to text technology, and more particularly to a text keyword searching method, device, equipment and storage medium. Background Art
[0002] In an era of attracting attention and earning clicks, the contents of many texts are inconsistent with each other. Advertisements or some meaningless content may be interspersed in paragraphs. Merchants get clicks, but users' time is wasted.
[0003] However, in the current process of users obtaining texts for reading, there is no way to filter out advertisements in these texts. Users have no way to skip these interspersed invalid information, cannot directly find the information they want to see, and cannot directly determine whether the text is what they need just by the text title. Therefore, in order to make reading or searching more efficient, it is increasingly urgent to directly obtain the keywords of a text to help users determine whether they need to read or whether the text is what they want. Summary of the invention
[0004] The embodiments of the present invention provide a text keyword search method, device, equipment and storage medium to achieve fast and accurate acquisition of text keywords.
[0005] To achieve this purpose, an embodiment of the present invention provides a method for searching text keywords, the method comprising:
[0006] Get the target text;
[0007] Using named entity recognition technology to extract the first entity word in the target text;
[0008] Inputting the first entity words into a pre-trained first neural network model to obtain a first word vector for each of the first entity words;
[0009] Determine the center point of the first word vector;
[0010] The first entity word corresponding to the second word vector is used as a keyword of the target text, and the second word vector is the first word vector of the first preset number that is closest to the center point.
[0011] Further, the determining of the center point of the first word vector includes:
[0012] Acquire a first entity word corresponding to the third word vector as a filter word of the target text, wherein the third word vector is a first word vector of a second preset number that is farthest from the center point;
[0013] The filter words are adjusted to display the target text.
[0014] Further, the adjusting the filtering words to display the target text includes:
[0015] The filter words are folded to display the target text.
[0016] Further, the adjusting the filtering words to display the target text includes:
[0017] After adjusting the filter words, the sentences in the same paragraph of the target text are input into the pre-trained second neural network model in pairs to obtain the similarity between the sentences in the same paragraph;
[0018] The target text is displayed according to the similarity between sentences in the same paragraph.
[0019] Furthermore, displaying the target text according to the similarity between sentences in the same paragraph includes:
[0020] Obtaining a similarity score for each sentence in the same paragraph according to the similarity between the sentences in the same paragraph;
[0021] The target text is displayed according to the similarity score.
[0022] Furthermore, the first neural network model is a Word2vec model.
[0023] Furthermore, the second neural network model is a twin neural network model.
[0024] On the one hand, an embodiment of the present invention further provides a text keyword search device, the device comprising:
[0025] A text acquisition module is used to acquire the target text;
[0026] A word extraction module, used to extract a first entity word in the target text by using a named entity recognition technology;
[0027] A vector acquisition module, used for inputting the first entity words into a pre-trained first neural network model to obtain a first word vector for each of the first entity words;
[0028] A center determination module, used to determine the center point of the first word vector;
[0029] A keyword acquisition module is used to use the first entity word corresponding to the second word vector as the keyword of the target text, and the second word vector is the first word vector of the first preset number that is closest to the center point.
[0030] On the other hand, an embodiment of the present invention further provides a computer device, which includes: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement a method provided in any embodiment of the present invention.
[0031] On the other hand, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method provided in any embodiment of the present invention.
[0032] The embodiment of the present invention obtains a target text; uses named entity recognition technology to extract first entity words in the target text; inputs the first entity words into a pre-trained first neural network model to obtain a first word vector for each first entity word; determines the center point of the first word vector; and uses the first entity word corresponding to the second word vector as a keyword of the target text, wherein the second word vector is a first preset number of first word vectors that are closest to the center point. This solves the problem that users have no way to skip these interspersed invalid information, cannot directly find the information they want to see, and cannot directly determine whether the text is what they need based on the text title alone, thereby achieving the effect of quickly and accurately obtaining text keywords. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] Figure 1 It is a flowchart of a text keyword search method provided in the first embodiment of the present invention;
[0034] Figure 2 This is a flow chart of a method for searching text keywords provided in Embodiment 2 of the present invention;
[0035] Figure 3 It is a structural schematic diagram of a text keyword search device provided by Embodiment 3 of the present invention;
[0036] Figure 4 A schematic diagram of the structure of a computer device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION
[0037] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only the parts related to the present invention, rather than all structures, are shown in the accompanying drawings.
[0038] It should be mentioned before discussing the exemplary embodiments in more detail that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe the steps as sequential processes, many of the steps therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of the steps can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the accompanying drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.
[0039] In addition, the terms "first", "second", etc. can be used in this article to describe various directions, actions, steps or elements, but these directions, actions, steps or elements are not limited by these terms. These terms are only used to distinguish a first direction, action, step or element from another direction, action, step or element. For example, without departing from the scope of the present application, the first module can be referred to as the second module, and similarly, the second module can be referred to as the first module. Both the first module and the second module are modules, but they are not the same module. The terms "first", "second", etc. cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Thus, the features defined as "first" and "second" can expressly or implicitly include one or more of the features. In the description of the embodiment of the present invention, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.
[0040] Embodiment 1
[0041] like Figure 1 As shown, the first embodiment of the present invention provides a method for searching text keywords, the method comprising:
[0042] S110: Obtain target text.
[0043] S120: extracting a first entity word from the target text using named entity recognition technology.
[0044] In this embodiment, the target text input by the user is obtained, and then the first entity word in the target text is extracted using the named entity recognition technology, wherein the named entity recognition technology (NER) can recognize three major categories (entity class, time class and number class) and seven minor categories (name, organization name, place name, time, date, currency and percentage) of named entities in the target text. Exemplarily, the target text includes the sentence "Xiao Ming goes to school at 8 o'clock in the morning", then the named entity recognition technology can be used to extract the name: "Xiao Ming", time: "8 o'clock in the morning", and place: "school". Recognize sentence by sentence until the entire target text is recognized.
[0045] S130: Input the first entity words into a pre-trained first neural network model to obtain a first word vector for each of the first entity words.
[0046] S140: Determine the center point of the first word vector.
[0047] S150: Use the first entity word corresponding to the second word vector as a keyword of the target text, wherein the second word vector is a first preset number of first word vectors that are closest to the center point.
[0048] In this embodiment, after obtaining the first entity word, the first entity word is input into the pre-trained first neural network model to obtain the first word vector of each first entity word. The first neural network model has been trained, and the corresponding word vector can be obtained after the entity word is input, and then the center point of the first word vector is determined. Because there are multiple first entity words, there are also multiple first word vectors, and then the center point of these first word vectors is determined, that is, the center in the target text is represented, and finally the first word vectors with the closest distance to the center point are obtained from the first word vector as the second word vector, wherein the first preset number is set by the user, and the user sets the first preset number according to the number of keywords to be obtained, and then the first entity word corresponding to the second word vector is obtained, and it is used as the keyword of the target text.
[0049] Preferably, the user can also set the category of keywords. Since named entity recognition technology can identify three major categories (entity category, time category and number category) and seven minor categories (personal names, organization names, place names, time, date, currency and percentage) of named entities in the target text, the user can also select the category of keywords. The first entity word corresponding to the obtained second word vector is the named entity category selected by the user.
[0050] As a preferred method, before obtaining the target text, if the user inputs multiple target texts, the target text can be further filtered to filter out the target text whose text title and text content do not match. Specifically, the target text and the text title of the target text are obtained, and then a first preset number of first keywords are extracted from the target text, and a second preset number of second keywords are extracted from the text title, the first keyword is input into a pre-trained Word2vec (word to vector) neural network model to obtain a first phrase vector, and the second keyword is input into a pre-trained Word2vec neural network model to obtain a second phrase vector, and then the average vector of the first phrase vector is determined as the first vector, and the average vector of the second phrase vector is determined as the second vector, and finally the first cosine similarity of the first vector and the second vector is determined, and the target text is filtered according to the first cosine similarity, and it is determined whether the first cosine similarity is less than the first threshold value. If the first cosine similarity is less than the first threshold value, the target text is filtered out to avoid the display of invalid text. As a preferred method, before obtaining the target text, a first preset number of first keywords can also be extracted from any paragraph of the target text, and the above method is used to filter out paragraphs in the target text that are not related to the text title.
[0051] The embodiment of the present invention obtains a target text; uses named entity recognition technology to extract first entity words in the target text; inputs the first entity words into a pre-trained first neural network model to obtain a first word vector for each first entity word; determines the center point of the first word vector; and uses the first entity word corresponding to the second word vector as a keyword of the target text, wherein the second word vector is a first preset number of first word vectors that are closest to the center point. This solves the problem that users have no way to skip these interspersed invalid information, cannot directly find the information they want to see, and cannot directly determine whether the text is what they need based on the text title alone, thereby achieving the effect of quickly and accurately obtaining text keywords.
[0052] Embodiment 2
[0053] like Figure 2 As shown, the second embodiment of the present invention provides a method for searching text keywords. The second embodiment of the present invention is further explained on the basis of the first embodiment of the present invention. After step S140 in the first embodiment of the present invention, the method further includes:
[0054] S141. Obtain a first entity word corresponding to the third word vector as a filter word for the target text, wherein the third word vector is a first word vector of a second preset number that is farthest from the center point.
[0055] In this embodiment, the first word vectors of the first second preset number that are farthest from the center point can also be obtained from the first word vector as the third word vector, wherein the second preset number is set by the user, and the user sets the second preset number according to the filtering requirements, and then the first entity word corresponding to the third word vector is obtained. Since the third word vector is far from the center point, it means that the first entity word corresponding to the third word vector has a low correlation with the main meaning of the target text, so it is used as the filter word of the target text. After filtering out the filter word, the target text is displayed.
[0056] S142, after adjusting the filter words, input the sentences in the same paragraph of the target text into the pre-trained second neural network model in pairs in sequence to obtain the similarity between the sentences in the same paragraph.
[0057] S143. Obtain a similarity score for each sentence in the same paragraph according to the similarity between the sentences in the same paragraph.
[0058] S144: Display the target text according to the similarity score.
[0059] In this embodiment, after obtaining the filter words of the target text, the filter words can be adjusted, deleted or folded. After that, the target text can be further divided into paragraphs, each paragraph can be divided into sentences, and the sentences in the same paragraph of the target text are input into the pre-trained second neural network model in pairs to obtain the similarity between the sentences in the same paragraph, and the similarity score of each sentence in the same paragraph is obtained according to the similarity between the sentences in the same paragraph, and finally the sentences are filtered according to the similarity score and the target text is displayed. Among them, the first neural network model is the Word2vec model. The second neural network model is the Siamese Network model.
[0060] Exemplarily, the target text includes paragraph one, which includes sentence A, sentence B and sentence C. Then, sentence A and sentence B are grouped as one, sentence A and sentence C are grouped as one, and sentence B and sentence C are grouped as one, and are input into a pre-trained neural network model at one time, wherein the neural network model has been pre-trained, and after inputting two sentences, the similarity of the two sentences can be obtained, thereby obtaining the similarity between sentence A and sentence B, the similarity between sentence A and sentence C, and the similarity between sentence B and sentence C. Then, paragraph two, paragraph three, etc. are processed in the same way until the entire target text is processed. Among them, the similarity between sentence A and sentence B is high, the similarity between sentence A and sentence C is low, and the similarity between sentence B and sentence C is low, then it can be said that sentence C is invalid information in the paragraph, so sentence C is filtered out and the target text is displayed.
[0061] Further, after obtaining the similarity between sentences in the same paragraph, the similarity score of each sentence in the same paragraph can be obtained accordingly. Exemplarily, the similarity between sentence A and sentence B is high and is set to 1 point, the similarity between sentence A and sentence C is low and is set to 0.5 points, and the similarity between sentence B and sentence C is low and is set to 0.5 points. Then the similarity score of sentence A is the average of 1 point and 0.5 points, 0.75 points, the similarity score of sentence B is the average of 1 point and 0.5 points, 0.75 points, and the similarity score of sentence C is the average of 0.5 points and 0.5 points, 0.5 points. Then the similarity scores are sorted from high to low, and the first sentence whose similarity score ranking is greater than the first threshold and the second sentence whose similarity score ranking is less than the second threshold are obtained. The first threshold and the second threshold can be 2, then the first sentence is sentence A and sentence B, and the second sentence is sentence C. Finally, the first sentence is displayed in the first way, and the second sentence is displayed in the second way, that is, sentences A and B are displayed in a highlighted and bold way, and sentence C is displayed in a low light and gray way. In this way, users can easily notice the relevant content such as sentences A and B when reading, and ignore the invalid content such as sentence C.
[0062] Embodiment 3
[0063] like Figure 3 As shown, the third embodiment of the present invention provides a text keyword search device 100. The text keyword search device 100 provided by the third embodiment of the present invention can execute the text keyword search method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. The text keyword search device 100 includes a text acquisition module 200, a word extraction module 300, a vector acquisition module 400, a center determination module 500 and a keyword acquisition module 600.
[0064] Specifically, the text acquisition module 200 is used to acquire the target text; the word extraction module 300 is used to extract the first entity words in the target text by adopting the named entity recognition technology; the vector acquisition module 400 is used to input the first entity words into a pre-trained first neural network model to obtain the first word vector of each first entity word; the center determination module 500 is used to determine the center point of the first word vector; the keyword acquisition module 600 is used to use the first entity word corresponding to the second word vector as the keyword of the target text, and the second word vector is the first word vector of the first preset number that is closest to the center point.
[0065] Furthermore, the text keyword search device 100 also includes a text display module 700, which is used to obtain a first entity word corresponding to the third word vector as a filter word of the target text, and the third word vector is the first word vector of the first second preset number that is farthest from the center point; the filter word is adjusted to display the target text. The text display module 700 is specifically used to fold the filter word to display the target text. The text display module 700 is also specifically used to input the sentences in the same paragraph of the target text into a pre-trained second neural network model in pairs after adjusting the filter word to obtain the similarity between the sentences in the same paragraph; and display the target text according to the similarity between the sentences in the same paragraph. The text display module 700 is also specifically used to obtain the similarity score of each sentence in the same paragraph according to the similarity between the sentences in the same paragraph; and display the target text according to the similarity score.
[0066] Preferably, the first neural network model is a Word2vec model. The second neural network model is a twin neural network model.
[0067] Embodiment 4
[0068] Figure 4 This is a schematic diagram of the structure of a computer device 12 provided in Embodiment 4 of the present invention. Figure 4 A block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention is shown. Figure 4 The computer device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.
[0069] like Figure 4 As shown, the computer device 12 is in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).
[0070] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.
[0071] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.
[0072] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 4 not shown, usually called a "hard drive"). Although Figure 4 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.
[0073] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in the memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods of the embodiments described herein.
[0074] The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), may communicate with one or more devices that enable a user to interact with the computer device 12, and / or may communicate with any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the computer device 12 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the computer device 12 via a bus 18. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the computer device 12, including, but not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
[0075] The processing unit 16 executes various functional applications and data processing by running the programs stored in the system memory 28, for example, implementing the method provided in the embodiment of the present invention:
[0076] Get the target text;
[0077] Using named entity recognition technology to extract the first entity word in the target text;
[0078] Inputting the first entity words into a pre-trained first neural network model to obtain a first word vector for each of the first entity words;
[0079] Determine the center point of the first word vector;
[0080] The first entity word corresponding to the second word vector is used as a keyword of the target text, and the second word vector is the first word vector of the first preset number that is closest to the center point.
[0081] Embodiment 5
[0082] Embodiment 5 of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method provided in all the embodiments of the present invention is implemented:
[0083] Get the target text;
[0084] Using named entity recognition technology to extract the first entity word in the target text;
[0085] Inputting the first entity words into a pre-trained first neural network model to obtain a first word vector for each of the first entity words;
[0086] Determine the center point of the first word vector;
[0087] The first entity word corresponding to the second word vector is used as a keyword of the target text, and the second word vector is the first word vector of the first preset number that is closest to the center point.
[0088] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.
[0089] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.
[0090] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
[0091] Computer program code for performing the operations of the present invention may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).
[0092] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims
1. A method for searching text keywords, characterized in that: include: Get the target text; Using named entity recognition technology to extract the first entity word in the target text; Inputting the first entity words into a pre-trained first neural network model to obtain a first word vector for each of the first entity words; Determine the center point of the first word vector; Using a first entity word corresponding to a second word vector as a keyword of the target text, wherein the second word vector is a first preset number of first word vectors that are closest to the center point; The determining of the center point of the first word vector includes: Acquire a first entity word corresponding to a third word vector as a filter word of the target text, wherein the third word vector is a first word vector of a second preset number that is farthest from the center point; After adjusting the filter words, the sentences in the same paragraph of the target text are input into the pre-trained second neural network model in pairs to obtain the similarity between the sentences in the same paragraph; Obtaining a similarity score for each sentence in the same paragraph according to the similarity between the sentences in the same paragraph; The target text is displayed according to the similarity score.
2. The method according to claim 1, characterized in that The adjusting the filtering words to display the target text comprises: The filter words are folded to display the target text.
3. The method according to claim 1, characterized in that The first neural network model is a Word2vec model.
4. The method according to claim 1, characterized in that The second neural network model is a twin neural network model.
5. A text keyword search device, characterized in that: include: A text acquisition module is used to acquire the target text; A word extraction module, used to extract a first entity word in the target text by using a named entity recognition technology; A vector acquisition module, used for inputting the first entity words into a pre-trained first neural network model to obtain a first word vector for each of the first entity words; A center determination module, used to determine the center point of the first word vector; A keyword acquisition module, used to use a first entity word corresponding to a second word vector as a keyword of the target text, wherein the second word vector is a first preset number of first word vectors that are closest to the center point; The text display module is used to obtain a first entity word corresponding to a third word vector as a filter word of the target text, wherein the third word vector is a first word vector of a second preset number that is farthest from the center point; The text display module is also used to input the sentences in the same paragraph of the target text into a pre-trained second neural network model in pairs after adjusting the filter words to obtain the similarity between the sentences in the same paragraph; obtain the similarity score of each sentence in the same paragraph according to the similarity between the sentences in the same paragraph; and display the target text according to the similarity score.
6. A computer device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 4.
7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.
