Official document analysis early warning method and system based on artificial intelligence

Through artificial intelligence-based document analysis early warning methods and systems, word segmentation, semantic analysis and deep learning technologies, the problem of inefficient official document analysis is solved, efficient and accurate text analysis and early warning information generation are achieved, and decision-making and application scenarios are supported.

CN119026603APending Publication Date: 2024-11-26INSPUR GENERSOFT CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411079207.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-07
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

The existing technology lacks an efficient, accurate and standardized automated document analysis system, resulting in inefficient document analysis and prone to omissions or misjudgments.

Method used

Using artificial intelligence-based official document analysis and early warning methods and systems, the word segmentation preprocessing and semantic analysis are obtained by obtaining original text data, early warning information and analysis reports are generated, and the text classification, sentiment analysis and other technologies are used to classify and analyze text and analyze sentiment. Topic modeling, combining decision tree models to predict future warning events.

Benefits of technology

It realizes efficient and accurate text analysis, generates accurate analysis reports and early warning information, supports decision-making and application scenarios, and improves the automation level of official document analysis.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119026603A_ABST
    Figure CN119026603A_ABST
Patent Text Reader

Abstract

The invention discloses an official document analysis early warning method and system based on artificial intelligence, belongs to the technical field of text analysis, and is used for solving the technical problem that an efficient, accurate and standard-unified automatic official document analysis system is lacked at present. The method comprises the steps of obtaining original text data of a to-be-analyzed official document; performing word segmentation preprocessing on the original text data to obtain labeled segmented words; performing semantic analysis on the annotated segmented words to obtain a semantic analysis result; generating corresponding early warning information according to the semantic analysis result; and generating an analysis report according to the semantic analysis result, and sending the analysis report and the early warning information to a principal terminal. The invention relates to an official document analysis early warning method and system based on artificial intelligence, and aims to provide an efficient and accurate text analysis solution to cope with ever-increasing text data processing requirements. The method can be applied to the fields of news media, social networks, financial markets and the like, and has high practicability and economic value.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of text analysis, and in particular to an official document analysis and early warning method and system based on artificial intelligence. Background Art

[0002] In government departments, enterprises, institutions and organizations, official documents, meeting minutes and other formal texts are very important and of great significance. The information contained in them is often of reference value for decision-making, and it is necessary to deeply analyze and extract the information contained in them, and then record and preserve them.

[0003] However, the traditional way of document analysis is manual analysis, which is not only inefficient, but also prone to omissions or misjudgments. In addition, the document information obtained by manual analysis depends on the experience and ability of the analyst. The information obtained by manual analysis varies and cannot truly represent the information that the document wants to convey. Therefore, there is currently a lack of an efficient, accurate and standardized automated document analysis system. Summary of the invention

[0004] The embodiment of the present invention provides an artificial intelligence-based official document analysis and early warning method and system, which are used to solve the following technical problems: There is currently a lack of an efficient, accurate and standardized automated official document analysis system.

[0005] The embodiment of the present invention adopts the following technical solution:

[0006] On the one hand, an embodiment of the present invention provides an official document analysis and early warning method based on artificial intelligence, the method comprising: obtaining original text data of the official document to be analyzed;

[0007] Performing word segmentation preprocessing on the original text data to obtain marked word segments;

[0008] Performing semantic analysis on the marked word segmentation to obtain a semantic analysis result;

[0009] Generate corresponding warning information according to the semantic analysis result;

[0010] An analysis report is generated according to the semantic analysis result, and the analysis report and the warning information are sent to a terminal of a responsible person.

[0011] In a feasible implementation manner, the original text data is subjected to word segmentation preprocessing to obtain marked word segments, specifically including:

[0012] Based on the statistical word segmentation technology, the original text data is segmented to obtain a number of initial word segments;

[0013] Based on neural network technology, a part-of-speech prediction model is constructed;

[0014] The parts of speech of the several initial participles are predicted by the part-of-speech prediction model, and the marked participles are obtained by the initial participles corresponding to the part-of-speech tags.

[0015] In a feasible implementation, based on the statistical word segmentation technology, the original text data is segmented to obtain a number of initial word segments, specifically including:

[0016] Based on the statistical word segmentation technology, a word segmentation model is constructed, and the word segmentation model is trained through a large-scale corpus;

[0017] The original text data is input into the trained word segmentation model to perform word segmentation processing to obtain a plurality of initial word segmentations corresponding to the original text data.

[0018] In a feasible implementation manner, semantic analysis is performed on the marked word segment to obtain a semantic analysis result, which specifically includes:

[0019] Perform keyword extraction on the marked word segmentation to obtain representative keywords in the original text data;

[0020] According to the marked word segmentation, the original text data is classified to obtain the text topic;

[0021] According to the marked word segmentation, sentiment analysis is performed on the original text data to obtain the text sentiment attitude;

[0022] Based on the text topic, performing topic modeling on the original text data to obtain a text topic model;

[0023] The representative keywords, the text theme, the text sexy attitude and the text theme model are summarized as the semantic analysis result.

[0024] In a feasible implementation, keyword extraction is performed on the marked word segmentation to obtain representative keywords in the original text data, specifically including:

[0025] Calculate the importance of the marked word segmentation by using a word frequency-inverse document frequency algorithm;

[0026] The most important marked word among all the marked words is determined as a representative keyword in the original text data.

[0027] In a feasible implementation manner, the original text data is classified according to the marked word segmentation to obtain the text topic, which specifically includes:

[0028] Build and train convolutional neural networks and recurrent neural networks through deep learning algorithms;

[0029] The convolutional neural network and the recurrent neural network are used to perform text classification on the marked word segmentation to identify the text topic or category of the original text data.

[0030] In a feasible implementation, based on the marked word segmentation, sentiment analysis is performed on the original text data to obtain the text sentiment attitude, which specifically includes:

[0031] Based on the long short-term memory network, sentiment analysis is performed on the marked segmented words to obtain the sentiment tendency corresponding to each marked segmented word; wherein the sentiment tendency is at least any one of the following: positive sentiment, negative sentiment, and neutral sentiment;

[0032] The text sentiment attitude of the original text data is determined according to the proportion of each type of sentiment tendency in all the marked word segments.

[0033] In a feasible implementation manner, generating corresponding warning information according to the semantic analysis result specifically includes:

[0034] The semantic analysis result is matched with the pre-set warning rules in the warning rule library. If the match is successful, a warning event is triggered and corresponding warning information is generated; wherein the warning event includes at least one or more of the following: policy change warning, important decision warning.

[0035] In a feasible implementation manner, after generating corresponding warning information according to the semantic analysis result, the method further includes:

[0036] Build a decision tree model based on machine learning;

[0037] Training the decision tree model through historical semantic analysis results and historical warning information;

[0038] The trained decision tree model is used to predict possible warning events that may occur within a preset time period in the future, and the possible warning events are sent to the responsible terminal in advance for prevention.

[0039] On the other hand, an embodiment of the present invention further provides an official document analysis and early warning system based on artificial intelligence, the system comprising:

[0040] The data acquisition module is used to obtain the original text data of the official document to be analyzed;

[0041] A data preprocessing module, used to perform word segmentation preprocessing on the original text data to obtain marked word segments;

[0042] A semantic analysis module, used to perform semantic analysis on the marked word segmentation to obtain a semantic analysis result;

[0043] An early warning generation module is used to generate corresponding early warning information according to the semantic analysis result;

[0044] The result output module is used to generate an analysis report according to the semantic analysis result, and send the analysis report and the warning information to the responsible person terminal.

[0045] Compared with the prior art, the document analysis and early warning method and system based on artificial intelligence provided by the embodiment of the present invention has the following beneficial effects:

[0046] The present invention relates to a text analysis system and method based on artificial intelligence, aiming to provide an efficient and accurate text analysis solution to cope with the growing demand for text data processing. The system uses natural language processing technology, including text classification, sentiment analysis, topic modeling and other methods, to comprehensively analyze and mine text data. Through preprocessing steps such as word segmentation and part-of-speech tagging, the text data is converted into a form that can be processed by a computer. Subsequently, the system uses a deep learning model and traditional machine learning algorithms to classify, sentiment analyze and topic model the text, thereby realizing the understanding and extraction of the text content. Finally, the system generates corresponding analysis reports and conclusions, provides users with accurate and comprehensive text information, and supports the realization of decision-making and application scenarios. The system can be applied to news media, social networks, financial markets and other fields, and has high practicality and economic value. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0048] Figure 1 A flowchart of an artificial intelligence-based document analysis and early warning method provided in an embodiment of the present invention;

[0049] Figure 2 A schematic diagram of the structure of an official document analysis and early warning system based on artificial intelligence provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0051] The embodiment of the present invention provides a document analysis and early warning method based on artificial intelligence, such as Figure 1 As shown, the official document analysis and early warning method based on artificial intelligence specifically includes steps S101-S105:

[0052] S101. Obtain original text data of the official document to be analyzed.

[0053] Specifically, the text content in the official document to be analyzed is extracted through the data acquisition module to form original text data, and the original text data is sent to the data preprocessing module.

[0054] S102: Perform word segmentation preprocessing on the original text data to obtain marked word segments.

[0055] Specifically, firstly, the original text data is segmented based on the statistical segmentation technology to obtain a number of initial segmented words, which specifically includes: constructing a segmentation model based on the statistical segmentation technology, and training the segmentation model through a large-scale corpus. The original text data is input into the trained segmentation model to perform segmentation processing to obtain a number of initial segmented words corresponding to the original text data.

[0056] Furthermore, based on the neural network technology, a part-of-speech prediction model is constructed. The part-of-speech prediction model is used to predict the part-of-speech of several initial segmented words, and the initial segmented words corresponding to the part-of-speech tag are obtained to obtain the tagged segmented words.

[0057] As a feasible implementation method, the data preprocessing module is the primary step of the official document analysis and early warning system, which is used to convert the original text data into a computer-processable form. In this module, the present invention adopts two main technologies: word segmentation and part-of-speech tagging.

[0058] 1) Word segmentation: Word segmentation is the process of dividing a continuous text sequence into discrete words. Commonly used word segmentation techniques include rule-based methods and statistical-based methods. The present invention adopts statistical-based word segmentation technology and uses a large-scale corpus for training to improve the accuracy and generalization ability of word segmentation.

[0059] 2) Part-of-speech tagging: Part-of-speech tagging is the task of determining the grammatical role played by a word in a sentence. This invention uses a part-of-speech tagging technology based on deep learning to predict the part-of-speech of a word by training a neural network model to enhance the understanding of the text semantics.

[0060] S103: Perform semantic analysis on the marked word segmentation to obtain semantic analysis results.

[0061] Specifically, firstly, keyword extraction is performed on the marked word segmentation to obtain representative keywords in the original text data.

[0062] Furthermore, the original text data is classified according to the marked word segmentation to obtain the text topic.

[0063] Furthermore, based on the marked word segmentation, sentiment analysis is performed on the original text data to obtain the text sentiment attitude.

[0064] Furthermore, based on the text topics, topic modeling is performed on the original text data to obtain a text topic model.

[0065] Finally, representative keywords, text themes, text sexy attitudes, and text topic models are summarized as semantic analysis results.

[0066] As a feasible implementation method, keyword extraction is performed on the annotated word segment to obtain representative keywords in the original text data. The specific implementation method is: the importance of the annotated word segment is calculated through the word frequency-inverse document frequency algorithm, and then the annotated word segment with the greatest importance among all the annotated word segment is determined as the representative keyword in the original text data.

[0067] As a feasible implementation method, the original text data is classified according to the marked word segmentation to obtain the text theme. The specific implementation method is: through the deep learning algorithm, a convolutional neural network and a recurrent neural network are constructed and trained. The marked word segmentation is classified by the convolutional neural network and the recurrent neural network to identify the text theme or category of the original text data.

[0068] As a feasible implementation method, sentiment analysis is performed on the original text data based on the marked segmented words to obtain the text sentiment attitude. The specific implementation method is: based on the long short-term memory network, sentiment analysis is performed on the marked segmented words to obtain the sentiment tendency corresponding to each marked segmented word; wherein the sentiment tendency is at least any one of the following: positive sentiment, negative sentiment, and neutral sentiment. Then, the text sentiment attitude of the original text data is determined according to the proportion of each type of sentiment tendency in all the marked segmented words.

[0069] The semantic analysis module is the core part of this system, which adopts a variety of natural language processing technologies, including keyword extraction, text classification, sentiment analysis and topic modeling.

[0070] 1) Keyword extraction: Keyword extraction is the process of automatically extracting representative and important words or phrases from a text. This system uses the word frequency-inverse document frequency algorithm to calculate the importance of words and select the most representative keywords in the text.

[0071] 2) Text classification: Text classification is the task of dividing text data into predefined categories or labels. The system uses deep learning-based text classification methods, such as convolutional neural networks (CNN) and recurrent neural networks (RNN), to identify the topic or category of the text.

[0072] 3) Sentiment analysis: Sentiment analysis is the task of identifying the emotional tendencies contained in text, including positive, negative, and neutral emotions. The system uses deep learning models, such as long short-term memory networks (LSTM), to classify the text sentiment in order to understand the emotional attitude of the author of the text.

[0073] 4) Topic Modeling: Topic modeling is the process of discovering hidden topic structures in text data.

[0074] S104, generating corresponding warning information according to the semantic analysis result;

[0075] Specifically, the semantic analysis results are matched with the pre-set warning rules in the warning rule library. If the match is successful, a warning event is triggered and corresponding warning information is generated; wherein, the warning event includes at least one or more of the following: policy change warning, important decision warning.

[0076] Furthermore, a decision tree model based on machine learning is constructed. Then, the decision tree model is trained through historical semantic analysis results and historical warning information. Through the trained decision tree model, the warning events that may occur in the future preset time period are predicted, and the possible warning events are sent to the responsible terminal in advance for prevention.

[0077] As a feasible implementation method, the warning generation module generates corresponding warning information based on the results of the semantic analysis module, such as policy changes, important decisions, etc. This module combines a variety of technical means, including rule engines, decision tree models, etc.

[0078] 1) Rule Engine: The system has a built-in warning rule library, which matches and filters according to the semantic analysis results and pre-set rules to determine whether the content of the document to be analyzed is positive and whether it is urgent, and then triggers warning events of different degrees of urgency.

[0079] 2) Decision tree model: The system also uses a decision tree-based machine learning model to predict possible warning events in the future by training historical data, thereby improving the accuracy, reliability and foresight of warnings.

[0080] S105. Generate an analysis report based on the semantic analysis results, and send the analysis report and warning information to the responsible person's terminal.

[0081] Specifically, the result output module is responsible for generating corresponding analysis reports and conclusions, and sending warning information to relevant personnel in the form of emails, text messages, etc. In this module, the present invention uses text typesetting and information transmission technology to ensure that the output results are clear and easy to understand and communicated in a timely manner.

[0082] In addition, the embodiment of the present invention also provides an official document analysis and early warning system based on artificial intelligence, such as Figure 2 As shown, the official document analysis and early warning system 200 based on artificial intelligence specifically includes:

[0083] The data acquisition module 210 is used to obtain the original text data of the official document to be analyzed;

[0084] The data preprocessing module 220 is used to perform word segmentation preprocessing on the original text data to obtain marked word segments;

[0085] A semantic analysis module 230, configured to perform semantic analysis on the marked word segmentation to obtain a semantic analysis result;

[0086] The warning generation module 240 is used to generate corresponding warning information according to the semantic analysis result;

[0087] The result output module 250 is used to generate an analysis report according to the semantic analysis result, and send the analysis report and the warning information to the responsible person terminal.

[0088] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0089] For the convenience of description, the above device is described by dividing it into various units according to its functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0090] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0091] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0092] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0093] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0094] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0095] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0096] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0097] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0098] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0099] Each embodiment of the present invention is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0100] The above describes specific embodiments of the present invention. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0101] The above description is only an embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the embodiments of the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present invention should be included in the protection scope of the present invention.

Claims

1. An official document analysis and early warning method based on artificial intelligence, characterized in that: The method comprises: Obtaining the original text data of the official document to be analyzed; Performing word segmentation preprocessing on the original text data to obtain marked word segments; Performing semantic analysis on the marked word segmentation to obtain a semantic analysis result; Generate corresponding warning information according to the semantic analysis result; An analysis report is generated according to the semantic analysis result, and the analysis report and the warning information are sent to a terminal of a responsible person.

2. The method for analyzing and warning official documents based on artificial intelligence according to claim 1 is characterized in that: The original text data is preprocessed with word segmentation to obtain marked word segmentation, which specifically includes: Based on the statistical word segmentation technology, the original text data is segmented to obtain a number of initial word segments; Based on neural network technology, a part-of-speech prediction model is constructed; The parts of speech of the several initial participles are predicted by the part-of-speech prediction model, and the marked participles are obtained by the initial participles corresponding to the part-of-speech tags.

3. The method for analyzing and warning official documents based on artificial intelligence according to claim 2 is characterized in that: Based on the statistical word segmentation technology, the original text data is segmented to obtain a number of initial word segments, including: Based on the statistical word segmentation technology, a word segmentation model is constructed, and the word segmentation model is trained through a large-scale corpus; The original text data is input into the trained word segmentation model to perform word segmentation processing to obtain a plurality of initial word segmentations corresponding to the original text data.

4. The method for analyzing and warning official documents based on artificial intelligence according to claim 1 is characterized in that: Performing semantic analysis on the marked word segmentation to obtain semantic analysis results, specifically including: Perform keyword extraction on the marked word segmentation to obtain representative keywords in the original text data; According to the marked word segmentation, the original text data is classified to obtain the text topic; According to the marked word segmentation, sentiment analysis is performed on the original text data to obtain the text sentiment attitude; Based on the text topic, performing topic modeling on the original text data to obtain a text topic model; The representative keywords, the text theme, the text sexy attitude and the text theme model are summarized as the semantic analysis result.

5. The method for document analysis and early warning based on artificial intelligence according to claim 4 is characterized in that: Perform keyword extraction on the marked word segmentation to obtain representative keywords in the original text data, specifically including: Calculate the importance of the marked word segmentation by using a word frequency-inverse document frequency algorithm; The most important marked word among all the marked words is determined as a representative keyword in the original text data.

6. The method for document analysis and early warning based on artificial intelligence according to claim 4 is characterized in that: According to the marked word segmentation, the original text data is classified to obtain the text topic, which specifically includes: Build and train convolutional neural networks and recurrent neural networks through deep learning algorithms; The convolutional neural network and the recurrent neural network are used to perform text classification on the marked word segmentation to identify the text topic or category of the original text data.

7. The method for analyzing and warning official documents based on artificial intelligence according to claim 4 is characterized in that: According to the marked word segmentation, sentiment analysis is performed on the original text data to obtain the text sentiment attitude, which specifically includes: Based on the long short-term memory network, sentiment analysis is performed on the marked segmented words to obtain the sentiment tendency corresponding to each marked segmented word; wherein the sentiment tendency is at least any one of the following: positive sentiment, negative sentiment, and neutral sentiment; The text sentiment attitude of the original text data is determined according to the proportion of each type of sentiment tendency in all the marked word segments.

8. The method for document analysis and early warning based on artificial intelligence according to claim 1 is characterized in that: According to the semantic analysis results, corresponding warning information is generated, including: The semantic analysis result is matched with the pre-set warning rules in the warning rule library. If the match is successful, a warning event is triggered and corresponding warning information is generated; wherein the warning event includes at least one or more of the following: policy change warning, important decision warning.

9. The method for document analysis and early warning based on artificial intelligence according to claim 1 is characterized in that: After generating corresponding warning information according to the semantic analysis result, the method further includes: Build a decision tree model based on machine learning; Training the decision tree model through historical semantic analysis results and historical warning information; The trained decision tree model is used to predict possible warning events that may occur within a preset time period in the future, and the possible warning events are sent to the responsible terminal in advance for prevention.

10. An artificial intelligence-based official document analysis and early warning system, characterized in that: The system comprises: The data acquisition module is used to obtain the original text data of the official document to be analyzed; A data preprocessing module, used to perform word segmentation preprocessing on the original text data to obtain marked word segments; A semantic analysis module, used to perform semantic analysis on the marked word segmentation to obtain a semantic analysis result; An early warning generation module is used to generate corresponding early warning information according to the semantic analysis result; The result output module is used to generate an analysis report according to the semantic analysis result, and send the analysis report and the warning information to the responsible person terminal.