Text information processing method, device and electronic device based on artificial intelligence

Through the text information processing method based on artificial intelligence, using word segmentation, vocabulary extraction and semantic correlation coefficient calculation, the accuracy and efficiency of traditional text processing methods in semantic understanding are solved, and the accurate analysis of text semantics and information retrieval is realized. promote.

CN118568204BActive Publication Date: 2024-11-01BEIJING CHENGSHI WANGLIN INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411018310.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-29
Publication Date
2024-11-01
Estimated Expiration
2044-07-29

AI Technical Summary

Technical Problem

Traditional text processing methods have accuracy and efficiency problems in semantic understanding, and it is difficult to deal with complex semantic relationships and polysynonyms, resulting in bias in understanding information retrieval and intelligent question-and-answer systems.

Method used

Using artificial intelligence-based text information processing method, precise analysis and information retrieval of text semantics are achieved through word segmentation processing, vocabulary extraction, word correlation model and semantic correlation coefficient calculation.

Benefits of technology

It improves the ability to understand the meaning of the text, improves the efficiency and accuracy of information retrieval, provides more targeted information retrieval results, and enhances the intelligence level of information processing.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118568204B_ABST
    Figure CN118568204B_ABST
Patent Text Reader

Abstract

The present disclosure relates to the field of information processing technology, and discloses a text information processing method, device and electronic device based on artificial intelligence, the method comprising: performing word segmentation processing on text information to obtain a vocabulary list; performing vocabulary extraction on a first target vocabulary in the vocabulary list according to a preset window to obtain a vocabulary tag sequence corresponding to the first target vocabulary; inputting the first target vocabulary, the vocabulary tag sequence and the second target vocabulary in the preset window into a trained word correlation model to determine a word correlation factor; determining a semantic correlation coefficient based on the first target vocabulary, the vocabulary tag sequence, the second target vocabulary and the word correlation factor, wherein the semantic correlation coefficient is used for information retrieval, solves the accuracy and efficiency problems existing in the traditional text processing method in semantic understanding, and realizes a more accurate and comprehensive semantic analysis, thereby improving the intelligent level of information processing, and improving user experience and information processing efficiency.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of information processing technology, and in particular to a text information processing method, device and electronic device based on artificial intelligence. Background Art

[0002] With the increasing popularity of Internet technology, various forms of text data are growing rapidly, covering a variety of sources such as news, social media posts, and forum comments. These texts contain rich semantic information, which is essential for applications such as understanding the meaning of texts, conducting information retrieval, and building knowledge graphs. However, traditional text processing methods face challenges such as massive amounts of information and complex semantics. How to accurately and quickly understand the connotation of texts has become one of the urgent problems to be solved in the field of information processing.

[0003] Existing text information processing methods are mainly divided into traditional methods based on rule matching and statistical models. The rule-based matching method usually relies on artificially set rules to match specific problems, but it is often unable to handle complex semantic relationships and polysemy. The statistical model learns semantic information through a large-scale corpus, but has certain limitations in the accuracy of semantic understanding.

[0004] In view of this, the present invention is proposed. Summary of the invention

[0005] In order to solve the above technical problems or at least partially solve the above technical problems, the embodiments of the present disclosure provide a text information processing method, device, electronic device and storage medium based on artificial intelligence, which solves the accuracy and efficiency problems of traditional text processing methods in semantic understanding, and realizes more precise and comprehensive semantic analysis, thereby improving the intelligence level of information processing, improving user experience and information processing efficiency.

[0006] In a first aspect, an embodiment of the present disclosure provides a text information processing method based on artificial intelligence, the text information processing method comprising:

[0007] Perform word segmentation on the text information to obtain a vocabulary list;

[0008] Performing vocabulary extraction on the first target vocabulary in the vocabulary list according to a preset window to obtain a vocabulary tag sequence corresponding to the target vocabulary;

[0009] Inputting the target vocabulary, the vocabulary tag sequence and the second target vocabulary in the preset window into a trained word correlation model to determine a word correlation factor;

[0010] A semantic correlation coefficient is determined based on the first target vocabulary, the vocabulary token sequence, the second target vocabulary and the word correlation factor, wherein the semantic correlation coefficient is used for information retrieval.

[0011] In a second aspect, the present disclosure also provides an artificial intelligence-based text information processing device, the text information processing device comprising:

[0012] The vocabulary list acquisition module is used to perform word segmentation on the text information to obtain a vocabulary list;

[0013] A vocabulary tag sequence acquisition module, used to extract the first target vocabulary in the vocabulary list according to a preset window to obtain a vocabulary tag sequence corresponding to the first target vocabulary;

[0014] A word correlation factor acquisition module, used for inputting the first target vocabulary, the vocabulary tag sequence and the second target vocabulary in the preset window into a trained word correlation model to determine a word correlation factor;

[0015] A semantic correlation coefficient acquisition module is used to determine a semantic correlation coefficient based on the first target vocabulary, the vocabulary tag sequence, the second target vocabulary and the word correlation factor, wherein the semantic correlation coefficient is used for information retrieval.

[0016] In a third aspect, an embodiment of the present disclosure further provides an electronic device, comprising: 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 text information processing method as described above.

[0017] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium having a computer program stored thereon, which implements the text information processing method as described above when executed by a processor.

[0018] The embodiment of the present disclosure provides an artificial intelligence-based text information processing method, which improves the ability to understand the meaning of the text by extracting words from a preset window corresponding to the first target word, and can capture the rich semantic information behind the text more comprehensively and accurately. It uses the trained word correlation model to more intelligently process the text information, and then uses the semantic correlation coefficient to realize the association and retrieval between words, thereby improving the efficiency and accuracy of information retrieval, performing text matching and search more intelligently, and providing users with more targeted information retrieval results. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0020] Figure 1 is a flowchart of a text information processing method based on artificial intelligence in an embodiment of the present disclosure;

[0021] Figure 2 is a structural diagram of a text information processing device based on artificial intelligence in an embodiment of the present disclosure;

[0022] Figure 3 It is a structural schematic diagram of an electronic device in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0023] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0024] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0025] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0026] Rule-based matching methods usually rely on artificially set rules to match specific problems, but they are often unable to handle complex semantic relationships and polysemy. Statistical models learn semantic information through large-scale corpora, but have certain limitations in the accuracy of semantic understanding. In addition, traditional text processing methods can only match and count literal meanings, and it is difficult to accurately understand the deep semantic information behind the text. This leads to understanding deviations in tasks such as information retrieval and intelligent question-answering systems. There are a large number of polysemous words in the text, and the same word may have multiple different meanings. Traditional methods often cannot accurately parse the semantics of polysemous words, resulting in unclear understanding of the meaning of the text. Traditional text processing methods often require a lot of manpower and time for rule setting or large-scale corpus learning, with low processing efficiency, and it is difficult to achieve fast and efficient semantic analysis in large-scale text data.

[0027] In this context, natural language processing (NLP) technology came into being, but traditional NLP methods still have problems such as inaccurate semantic understanding and low processing efficiency. Existing text information processing systems can often only achieve basic text matching and vocabulary statistics, and it is difficult to deeply mine the rich semantic information behind the text. Therefore, the present invention proposes a text information processing method based on artificial intelligence.

[0028] In response to the above problems, the embodiments of the present disclosure provide a text information processing method based on artificial intelligence, which solves the accuracy and efficiency problems of traditional text processing methods in semantic understanding, and achieves more precise and comprehensive semantic analysis, thereby improving the intelligence level of information processing, improving user experience and information processing efficiency.

[0029] Figure 1 : is a flowchart of a text information processing method based on artificial intelligence in an embodiment of the present disclosure. The method can be executed by a text information processing device based on artificial intelligence, which can be implemented in software and / or hardware, and can be configured in an electronic device. Figure 1 As shown, the method may specifically include the following steps:

[0030] S110, processing the text information and constructing a vocabulary list.

[0031] The text information may be collected from news websites, social media platforms, etc. The source of the text information may be obtained from different channels and used as the original text for the text information processing method. The text information is segmented using a word segmentation algorithm to obtain a vocabulary list. Commonly used word segmentation algorithms include Jiepa, SnowNLP, hanNLP, LTP, etc., for example, as shown below: in, represents a list of words, Represents a specific word in the vocabulary list, Represents the total number of words in the vocabulary list, that is, the boundary of the vocabulary list.

[0032] For example, I want to buy apples and bananas. The text information is segmented to get the vocabulary list [I, want, buy, apples, and, bananas].

[0033] S120: Perform vocabulary extraction on the first target vocabulary in the vocabulary list according to a preset window to obtain a vocabulary tag sequence corresponding to the first target vocabulary.

[0034] Based on the above embodiment, any word is selected in the vocabulary list as the first target word, and then the first target word is taken as the center, and n-1 words on the left and right sides of the first target word are taken according to the preset window, and the first target word and the n-1 words on the left and right sides of the first target word are combined to form a vocabulary tag sequence corresponding to the target word. For example, the first target word is , the size of the preset window is n, and the words extracted in the preset window are used as the second target words. , the vocabulary token sequence is , target vocabulary The corresponding sequence of vocabulary tokens It can be expressed by the following formula:

[0035] in, represents a sequence of vocabulary tokens, represents the first target word, represents the second target vocabulary, Indicates the default window size, express location, express location, Indicates the boundaries of the vocabulary list.

[0036] It should be noted that the present disclosure adopts the position of the vocabulary in the vocabulary list as a tag, and uses the tag to construct a vocabulary tag sequence. For example, assuming the vocabulary list: [I, want, buy, apples, and, bananas], the preset window is 2, and "buy" is used as the first target vocabulary. The position corresponding to "buy" is 3. It can be seen that the second target vocabulary is I, want, apples, and, and the corresponding positions of the second target vocabulary are 1, 2, 4, and 5. The vocabulary tag sequence corresponding to the first target vocabulary 3 can be [1, 2, 3, 4, 5].

[0037] S130: Input the first target vocabulary, the vocabulary tag sequence and the second target vocabulary in the preset window into a trained word correlation model to determine a word correlation factor.

[0038] On the basis of the above embodiment, the position mark corresponding to the first target vocabulary, the vocabulary mark sequence and the position mark corresponding to the second target vocabulary are input into the trained word correlation model, and the word correlation factor is output.

[0039] In one embodiment, before inputting the first target vocabulary, the vocabulary tag sequence and the second target vocabulary in the preset window into the trained word correlation model, the method further includes:

[0040] Performing gradient processing on the word error function to determine the model parameters of the word correlation model;

[0041] Based on the model parameters, a trained word correlation model is obtained.

[0042] Among them, the following formula is used to express the word correlation model: in, represents word related factors, represents a sequence of vocabulary tokens, represents the first model parameter, represents the hyperparameter, represents the second model parameter, represents the exponential function, express and The probability density function of .

[0043] The word correlation model provided in this embodiment can accurately calculate and model the semantic relationship and semantic similarity of words in a text, and consider factors such as the polysemy of words and contextual information to improve the accurate capture of text semantic information.

[0044] Specifically, before obtaining a trained word-related model, it is necessary to construct a word error function, and to derive the word error function, and to continuously optimize the value of the word error function. When the value of the word error function is minimized and tends to be stable, the model parameters of the word-related model are obtained. The word error function can be expressed by the following formula: in, represents the word error function, Indicates the window and The number of co-occurrences, represents the first target word, represents the second target vocabulary, represents a sequence of vocabulary tokens, represents the first model parameter, represents the second model parameter, express The logarithm of represents the hyperparameter, express and The probability density function of .

[0045] After obtaining the word error function, it is necessary to solve the gradient of the word error function by derivation to obtain the model parameters of the word error function, and the model parameters corresponding to the word error function when the value is minimum and stable, including the first model parameters and the second model parameters. The first model parameters and the second model parameters are input into the word-related model to obtain a trained word-related model. The following formula is used to derive the word error function: in, represents a sequence of vocabulary tokens, represents the first model parameter, represents the hyperparameter, represents the second model parameter, express and The probability density function of express and The probability density function of .

[0046] S140. Determine a semantic correlation coefficient based on the first target vocabulary, the vocabulary tag sequence, the second target vocabulary and the word correlation factor, wherein the semantic correlation coefficient is used for information retrieval.

[0047] Exemplarily, the position mark and the word mark sequence corresponding to the first target word, the position mark corresponding to the second target word, and the word correlation factor solved above are calculated by the following formula to obtain the semantic correlation coefficient. By performing semantic analysis through the semantic correlation coefficient, the semantic connection between words can be established, which helps to improve the efficiency and accuracy of information retrieval. Among them, the expression of the semantic correlation coefficient is: in, represents the semantic correlation coefficient, represents word related factors, represents the first target word, represents the second target vocabulary, represents a sequence of vocabulary tokens, represents the first model parameter, represents the second model parameter, Represents the norm symbol.

[0048] The artificial intelligence-based text information processing method provided by the embodiment of the present disclosure improves the ability to understand the meaning of the text by extracting words from a preset window corresponding to the first target word, and can capture the rich semantic information behind the text more comprehensively and accurately. It uses the trained word correlation model to more intelligently process the text information, and then uses the semantic correlation coefficient to realize the association and retrieval between words, thereby improving the efficiency and accuracy of information retrieval, performing text matching and search more intelligently, and providing users with more targeted information retrieval results.

[0049] Figure 2 FIG. 1 is a schematic diagram of the structure of a text information processing device based on artificial intelligence in an embodiment of the present disclosure. Figure 2 As shown: the device includes: a vocabulary list acquisition module 210, a vocabulary tag sequence acquisition module 220, a word correlation factor acquisition module 230 and a semantic correlation coefficient acquisition module 240.

[0050] The vocabulary list acquisition module is used to perform word segmentation on the text information to obtain a vocabulary list;

[0051] A vocabulary tag sequence acquisition module, used to extract the first target vocabulary in the vocabulary list according to a preset window to obtain a vocabulary tag sequence corresponding to the first target vocabulary;

[0052] A word correlation factor acquisition module, used for inputting the first target vocabulary, the vocabulary tag sequence and the second target vocabulary in the preset window into a trained word correlation model to determine a word correlation factor;

[0053] A semantic correlation coefficient acquisition module is used to determine a semantic correlation coefficient based on the first target vocabulary, the vocabulary tag sequence, the second target vocabulary and the word correlation factor, wherein the semantic correlation coefficient is used for information retrieval.

[0054] The expression of the vocabulary token sequence is: in, represents a sequence of vocabulary tokens, represents the first target word, represents the second target vocabulary, Indicates the default window size. express location, express location, Indicates the boundaries of the vocabulary list.

[0055] Optionally, the device also includes a model acquisition module, which is used to perform gradient processing on the word error function to determine model parameters of the word-related model; based on the model parameters, a trained word-related model is obtained.

[0056] Among them, the expression of the word error function is: in, represents the word error function, Indicates the window and The number of co-occurrences, represents the first target word, represents the second target vocabulary, represents a sequence of vocabulary tokens, represents the first model parameter, represents the second model parameter, express The logarithm of represents the hyperparameter, express and The probability density function of .

[0057] Optionally, the model acquisition module is further used to derive the word error function, so that when the value of the word error function is minimum and stable, the optimal parameters of the text information processing model are obtained, wherein the word error function is derived using the following formula: in, represents a sequence of vocabulary tokens, represents the first model parameter, represents the hyperparameter, represents the second model parameter, express and The probability density function of express and The probability density function of .

[0058] In one embodiment, the expression of the word correlation model is: in, represents word related factors, represents a sequence of vocabulary tokens, represents the first model parameter, represents the hyperparameter, represents the second model parameter, represents the exponential function, express and The probability density function of .

[0059] In one embodiment, the expression of the semantic relevance coefficient is: in, represents the semantic correlation coefficient, represents word related factors, represents the first target word, represents the second target vocabulary, represents a sequence of vocabulary tokens, represents the first model parameter, represents the second model parameter, Represents the norm symbol.

[0060] The artificial intelligence-based text information processing device provided in the embodiment of the present disclosure can execute the steps of the artificial intelligence-based text information processing method provided in the method embodiment of the present disclosure, and the execution steps and beneficial effects are no longer repeated here.

[0061] Figure 3 Schematic diagram of the structure of an electronic device in the embodiment of the present disclosure. Figure 3 , which shows a structural schematic diagram of an electronic device 500 suitable for implementing the embodiments of the present disclosure. Figure 3The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0062] like Figure 3 As shown, the electronic device 500 may include a processing device 501, a read-only memory (ROM) 502, a random access memory (RAM) 503, a bus 504, an input / output (I / O) interface 505, an input device 506, an output device 507, a storage device 508, and a communication device 509. The processing device (e.g., a central processing unit, a graphics processor, etc.) 501 can perform various appropriate actions and processes according to the program in the ROM 502 or the program loaded from the storage device 508 to the RAM 503 to implement the method of the embodiment described in the present disclosure. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other through the bus 504. The input / output (I / O) interface 505 is also connected to the bus 504.

[0063] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart, thereby realizing the text information processing method based on artificial intelligence as described above. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0064] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may 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 of computer-readable storage media may include, but are not limited to: 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 the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0065] The computer-readable medium may be included in the electronic device; or it may exist independently without being installed in the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: performs word segmentation processing on the text information to obtain a vocabulary list; performs vocabulary extraction on the first target vocabulary in the vocabulary list according to a preset window to obtain a vocabulary tag sequence corresponding to the target vocabulary; inputs the target vocabulary, the vocabulary tag sequence and the second target vocabulary in the preset window into a trained word correlation model to determine a word correlation factor; determines a semantic correlation coefficient based on the first target vocabulary, the vocabulary tag sequence, the second target vocabulary and the word correlation factor, wherein the semantic correlation coefficient is used for information retrieval.

[0066] Optionally, when the above one or more programs are executed by the electronic device, the electronic device may also execute other steps described in the above embodiments.

[0067] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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 foregoing.

[0068] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

Claims

1. A text information processing method based on artificial intelligence, characterized in that: The text information processing method based on artificial intelligence includes: Perform word segmentation on the text information to obtain a vocabulary list; Performing vocabulary extraction on the first target vocabulary in the vocabulary list according to a preset window to obtain a vocabulary tag sequence corresponding to the target vocabulary; Inputting the first target vocabulary, the vocabulary tag sequence and the second target vocabulary in the preset window into a trained word correlation model to determine a word correlation factor; determining a semantic correlation coefficient based on the first target vocabulary, the vocabulary token sequence, the second target vocabulary and the word correlation factor, wherein the semantic correlation coefficient is used for information retrieval, Before inputting the first target vocabulary, the vocabulary tag sequence and the second target vocabulary in the preset window into the trained word correlation model, the artificial intelligence-based text information processing method further includes: Performing gradient processing on the word error function to determine the model parameters of the word correlation model; Based on the model parameters, a trained word correlation model is obtained. Among them, the expression of the word error function is: L=∑∑(X i,j +1) α (θ i w i w j -log(X i,j )+w i b i +P(w i |w j )) 2 Among them, L represents the word error function, X i,j Indicates w in the window i and w j The number of co-occurrences, w i represents the first target word, w j represents the second target vocabulary, θ i represents the first model parameter, b i represents the second model parameter, log(X i,j ) indicates X i,j The logarithm of α represents the hyperparameter, P(w i |w j ) indicates w i and w j The probability density function of Among them, the word error function is subjected to gradient processing to determine the model parameters of the word related model, including: The word error function is derived, and when the value of the word error function is minimum and stable, the optimal parameters of the text information processing model are obtained, wherein the word error function is derived using the following formula: Among them, C i represents the vocabulary token sequence, P(w i |C i ) indicates w i and C i The probability density function of Among them, the expression of the word correlation model is: Among them, M(w i ,θ i ,b i ) represents the word correlation factor, exp(w i b i ) represents the exponential function.

2. The text information processing method based on artificial intelligence according to claim 1 is characterized in that: The expression of the semantic correlation coefficient is: Among them, S(w i ,C i ) represents the semantic correlation coefficient, and |||| represents the norm symbol.

3. The text information processing method based on artificial intelligence according to claim 1 is characterized in that: The expression of the vocabulary token sequence is: C i ={w i ,w j |max(1,i-n+1)≤j≤min(N,i+n)} Among them, n represents the preset window size, i represents w i Position, j represents w j , and N represents the boundary of the vocabulary list.

4. An artificial intelligence-based text information processing device, using the artificial intelligence-based text information processing method according to any one of claims 1 to 3, characterized in that: include: The vocabulary list acquisition module is used to perform word segmentation on the text information to obtain a vocabulary list; A vocabulary tag sequence acquisition module, used to extract the first target vocabulary in the vocabulary list according to a preset window to obtain a vocabulary tag sequence corresponding to the first target vocabulary; A word correlation factor acquisition module, used for inputting the first target vocabulary, the vocabulary tag sequence and the second target vocabulary in the preset window into a trained word correlation model to determine a word correlation factor; A semantic correlation coefficient acquisition module is used to determine a semantic correlation coefficient based on the first target vocabulary, the vocabulary tag sequence, the second target vocabulary and the word correlation factor, wherein the semantic correlation coefficient is used for information retrieval.

5. An electronic 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 execute the artificial intelligence-based text information processing method according to any one of claims 1-3.