Financial market public opinion analysis method, system and device, medium and product

Abstract

The invention discloses a financial market public opinion analysis method, system and device, a medium and a product, and relates to the field of public opinion analysis, and the method comprises the steps: carrying out the preprocessing of multi-source data, and determining the preprocessed multi-source data; the multi-source data comprises financial market negative public opinion data, city investment data, announcement files, industry and commerce data and enterprise internal business data; based on a large model technology, classifying the preprocessed multi-source data by using a public opinion analysis model special for the financial field, and determining a subject type; the main body types comprise city investment enterprises and non-city investment enterprises; according to the subject type, a structured public opinion analysis report is automatically generated, the method has efficient data processing capacity, the analysis efficiency can be improved, and trend prediction and decision suggestions can be provided.

Description

Technical Field

[0001] This application relates to the field of public opinion analysis, and in particular to a method, system, device, medium and product for analyzing public opinion in the financial market. Background Technology

[0002] By analyzing public opinion regarding industry trends, competitors, and customer needs, financial institutions can stay informed about market changes, seize opportunities, optimize products and services, and enhance their market competitiveness. Current technologies for analyzing public opinion in the financial market mainly suffer from the following problems:

[0003] 1. Limited data integration capabilities: Traditional corporate public opinion analysis systems typically rely on single or limited data sources, making it difficult to effectively integrate various internal and external data, especially complex information such as negative public opinion data in the financial sector and local government financing vehicle (LGFV) data, which limits the comprehensiveness and accuracy of the analysis.

[0004] 2. Insufficient analysis efficiency and accuracy: Traditional rule-based sentiment analysis methods are inefficient when dealing with massive amounts of data and struggle to accurately capture complex market sentiment and potential financial risks. Existing analytical methods are also weak in processing non-quantitative data, making it difficult to meet the financial market's demand for real-time, comprehensive risk assessment.

[0005] 3. Lack of intelligent decision support: Existing systems mostly remain at the level of simple data statistics and classification, and cannot provide in-depth market risk analysis and decision-making suggestions. Summary of the Invention

[0006] The purpose of this application is to provide a method, system, device, medium and product for analyzing public opinion in the financial market, in order to solve the problems of limited data integration capabilities, insufficient analysis efficiency and accuracy, and lack of intelligent decision support in traditional public opinion analysis methods.

[0007] To achieve the above objectives, this application provides the following solution:

[0008] Firstly, this application provides a method for analyzing public opinion in the financial market, including:

[0009] The multi-source data is preprocessed to determine the preprocessed multi-source data; the multi-source data includes negative public opinion data in the financial market, local government financing vehicle (LGFV) data, announcements and documents, business registration data, and internal business data of enterprises.

[0010] Based on large model technology, the preprocessed multi-source data is classified using a financial sector-specific public opinion analysis model to determine the subject types; the subject types include urban investment enterprises and non-urban investment enterprises.

[0011] Based on the subject type, a structured public opinion analysis report is automatically generated.

[0012] Secondly, this application provides a financial market public opinion analysis system, including:

[0013] The preprocessing module is used to preprocess multi-source data and determine the preprocessed multi-source data; the multi-source data includes negative public opinion data in the financial market, local government financing vehicle data, announcements and documents, business registration data, and internal business data of enterprises;

[0014] The subject type determination module is used to classify the preprocessed multi-source data based on large-scale model technology and a financial-specific public opinion analysis model to determine the subject type; the subject type includes urban investment enterprises and non-urban investment enterprises.

[0015] The public opinion analysis report generation module is used to automatically generate a structured public opinion analysis report based on the subject type.

[0016] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described financial market sentiment analysis method.

[0017] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the aforementioned financial market sentiment analysis method.

[0018] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the aforementioned financial market sentiment analysis method.

[0019] According to the specific embodiments provided in this application, this application has the following technical effects:

[0020] This application utilizes multi-source data integration and large-scale model technology to process massive amounts of financial public opinion data and local government financing vehicle (LGFV) information data in real time. The analysis structure exhibits high timeliness and efficient data processing capabilities. Furthermore, based on large-scale model technology, it classifies the preprocessed multi-source data using a specialized financial public opinion analysis model, identifying the types of entities involved. Leveraging the powerful data analysis capabilities of the large-scale model, it accurately identifies market risks and public opinion trends, significantly improving analysis efficiency. Finally, based on different entity types, it automatically generates structured public opinion analysis reports, which not only include risk identification but also provide trend predictions and decision-making suggestions, thereby helping users make more informed market decisions. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 A flowchart illustrating a financial market sentiment analysis method provided in an embodiment of this application;

[0023] Figure 2 This is a schematic diagram of the structure of a financial market sentiment analysis system provided in an embodiment of this application. Detailed Implementation

[0024] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0025] To make the objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0026] like Figure 1 As shown in the figure, this application provides a method for analyzing public opinion in the financial market, including:

[0027] S1: Preprocess the multi-source data to determine the preprocessed multi-source data; the multi-source data includes negative public opinion data in the financial market, urban investment data, announcements and documents, business registration data, and internal business data of enterprises.

[0028] S2: Based on large model technology, the preprocessed multi-source data is classified using a financial field-specific public opinion analysis model to determine the subject type; the subject type includes urban investment enterprises and non-urban investment enterprises.

[0029] S3: Automatically generate a structured public opinion analysis report based on the subject type.

[0030] In an exemplary embodiment, S1 specifically includes:

[0031] S11: Data integration, including the integration of multiple sources of data such as negative public opinion data in the financial market, local government financing vehicle data, announcements, business registration data, and internal business data of enterprises (such as indicators and assets).

[0032] S12: Data preprocessing, including cleaning, deduplication, and formatting of data to ensure data quality and consistency.

[0033] In an exemplary embodiment, S3 specifically includes:

[0034] S31: For the aforementioned urban investment companies, use the financial sector-specific public opinion analysis model to extract the urban investment company's public opinion summary from the corresponding corporate public opinion data.

[0035] S32: Based on the aforementioned public opinion summary of urban investment enterprises, conduct risk level analysis and importance analysis. According to the data nature, analyze the main urban investment enterprise data based on prompts. Simultaneously, utilize tool components to process the corresponding corporate public opinion data of the urban investment enterprises, generating an urban investment enterprise public opinion analysis report. The prompts include analysis dimensions, key indicators, expected report structure and content. The main urban investment enterprise data includes regional data, urban investment entity financial data, and third-party scoring data. The tool components include a calculator, a time judgment tool, and a search tool. The urban investment enterprise public opinion analysis report includes a public opinion overview, risk level analysis, importance analysis, enterprise business overview, surrounding risks, financial status, regional economic analysis, and risk avoidance suggestions.

[0036] S33: For the non-local government financing vehicles (LGFVs), use the financial sector-specific public opinion analysis model to extract the non-LGFV public opinion summary of the corresponding corporate public opinion data.

[0037] S34: Based on the public opinion summary of the non-urban investment enterprises, conduct risk level analysis and importance analysis, and at the same time, dispatch tool components to process the public opinion data of the corresponding enterprises of the non-urban investment enterprises to generate a public opinion analysis report of the non-urban investment enterprises; the public opinion analysis report of the non-urban investment enterprises includes a public opinion overview, risk level analysis, importance analysis, enterprise business overview, surrounding risks, and risk avoidance suggestions.

[0038] In one exemplary embodiment, the model selection is as follows: Based on large AI models such as DeepSeek, leveraging their powerful data processing and natural language processing capabilities, a dedicated public opinion analysis model for the financial sector is constructed.

[0039] To establish an application service workflow, the data is first cleaned. Based on the subject type condition judgment node, the analysis subjects are divided into urban investment enterprises and non-urban investment enterprises. Different analysis strategies are executed for different subject types.

[0040] For local government financing vehicles (LGFVs), DeepSeek is used to conduct a comprehensive analysis of corporate public opinion data, extracting public opinion summaries, conducting risk level analysis, and importance analysis. Based on the analysis dimensions, key indicators, expected report structure and content, prompt words are compiled. Based on the prompt words, professional analysis is conducted on regional data, LGFV financial data, and third-party scoring data (i.e., public opinion analysis workflow). At the same time, predefined tool components such as calculators, time judgment tools, and Bing search tools are used to process the data. Finally, the report generation assistant is used to output the analysis conclusions in the form of a long report, which includes a public opinion overview, risk level analysis, importance analysis, corporate business overview, surrounding risks, financial status, regional economic analysis, and risk avoidance suggestions.

[0041] For non-local government financing vehicles (LGFVs), DeepSeek is used to conduct a comprehensive analysis of corporate public opinion data, extracting public opinion summaries, performing risk level analysis, and importance analysis. Predefined tools such as calculators, time judgment tools, and Bing search tools are used to process the data. Based on the above analysis, information on corporate business risks and surrounding risks is further enriched. Finally, a report generation assistant is used to output the analysis conclusions in the form of a long report, which includes a public opinion overview, risk level analysis, importance analysis, corporate business overview, surrounding risks, and risk avoidance suggestions.

[0042] Domain Adaptation: By adjusting the corpus in the financial field, the model's ability to understand financial terminology, industry background, and market logic is enhanced.

[0043] In an exemplary embodiment, before S3, the method further includes: performing semantic understanding and sentiment analysis on the corporate public opinion data using the financial sector-specific public opinion analysis model; classifying the corporate public opinion data into positive, neutral, and negative categories based on sentiment tendency; and classifying the corporate public opinion data into important and ordinary categories based on the degree of negative public opinion impact; the corporate public opinion data includes corporate public opinion data corresponding to the urban investment companies and corporate public opinion data corresponding to the non-urban investment companies; the sentiment analysis includes risk level analysis and importance analysis.

[0044] In an exemplary embodiment, before S3, the method further includes: for the main urban investment data, dividing the main urban investment data into regional data, urban investment entity financial data, and third-party rating data according to the nature of the data; and for urban investment enterprises, identifying potential market risks based on multi-dimensional factors, capturing public opinion hotspots of bond issuers from third-party data sources, and analyzing the development trend of bond issuers by combining key financial data, financing guarantees, and bond issuance scale; the multi-dimensional factors include the development status of the industry and region in which the bond issuer is located, relevant policies, government support willingness, and third-party institutional ratings.

[0045] In an exemplary embodiment, for local government financing vehicles (LGFVs), potential market risks are identified based on multi-dimensional factors, and public opinion hotspots of bond issuers are captured from third-party data sources. The development trend of bond issuers is analyzed by combining key financial data, financing guarantees, and bond issuance scale. The method also includes providing risk avoidance suggestions to users based on the degree of risk, importance, and development trend of bond issuers.

[0046] In practical applications, the public opinion analysis workflow specifically includes:

[0047] Data Input and Processing: Real-time acquisition and processing of multi-source data; classification and clustering of data through models; and classification of data into corporate public opinion data and main urban investment data based on data content.

[0048] risk assessment:

[0049] For corporate public opinion data, a large-scale model is used for semantic understanding and sentiment analysis (including risk level analysis, importance analysis, etc.), categorizing it into positive, neutral, and negative based on sentiment tendency. Negative public opinion is further categorized into important and moderate based on the degree of its impact. For example, if negative public opinion data in the financial market contains keywords such as fines, warnings, losses, and bankruptcy, the sentiment tendency is negative; if the public opinion text contains keywords such as profit growth and upward revision, the sentiment tendency is positive.

[0050] For the main urban investment (LGFV) data, it is divided into regional data, LGFV financial data, and third-party rating data based on the nature of the data. For LGFVs, potential market risks are identified based on dimensions such as the industry and regional development of the bond issuer, relevant policies, government support intentions, and third-party ratings. Hot topics in public opinion regarding the bond issuer are captured from mainstream financial websites, news websites, and other third-party data sources. Further analysis of the bond issuer's development trend is conducted by combining key financial data, financing guarantees, and bond issuance scale.

[0051] Based on the assessment results, including the degree of risk, its importance, and the development trend of the bond issuer, users are given risk avoidance advice.

[0052] Correlation analysis: Using models to analyze the risk trends of entities from a time-series perspective, and to analyze the potential impact on entities based on their geographical location.

[0053] ① Risk trend analysis:

[0054] First, we acquire the entity's business registration data, including basic business information, legal proceedings information, tax violation information, information on restrictions on high-level consumption, data on defaulters, and data on abnormal operations. We then analyze the company's key risk indicators from a quantitative data perspective. Second, we acquire the entity's negative public opinion information for the past six months, analyzing the company's risk trends based on the frequency, impact, and amount (if applicable) of negative public opinion. Simultaneously, based on the entity's corporate relationships, such as subsidiaries, parent company, invested companies, and shareholders, we collect peripheral risk data and analyze the potential impact of these peripheral risks on the entity.

[0055] ②Regional correlation analysis:

[0056] It should be noted that non-local government financing vehicles (LGFVs) do not require regional correlation analysis.

[0057] For urban investment companies, it is necessary to locate the region to which the entity belongs, obtain the administrative planning attributes of the district / county / city, such as municipality, provincial capital or other administrative level, and assess the overall level of the region in combination with the government's willingness to support the region, regional policies, economic level, population situation, distribution of high-speed rail / airports, etc., and then analyze the entity's development prospects and potential risks in the region.

[0058] Risk Mitigation Recommendations: Based on the analysis of the entity's own risks, surrounding risks, financial indicators, and regional economic conditions, we provide users with risk mitigation recommendations from the perspective of cooperation with financial institutions. Specific content includes, but is not limited to: measures to address negative public opinion, measures to respond to market changes, key risk focuses, and investment and financing channel combinations.

[0059] In one exemplary embodiment, S3 is followed by:

[0060] S4: Based on the financial sector-specific public opinion analysis model, receive and understand user instructions.

[0061] S5: Based on the public opinion analysis report, answer the user's questions according to the user's instructions, or modify the public opinion analysis report.

[0062] In practical applications, this application also includes: information system integration and report generation, user interactive Q&A, and hardware and software support.

[0063] Information system integration and report generation specifically include:

[0064] System integration: Embed the financial sentiment analysis model into the existing risk management information system (i.e., the enterprise's internal risk management platform) to achieve real-time monitoring and analysis of data.

[0065] Automated report generation: Based on the analysis results, automatically generate structured public opinion analysis reports, including risk orientation (positive, neutral, negative), public opinion analysis summary, financial analysis, regional economic analysis, risk trend forecast, risk avoidance suggestions, etc.

[0066] Decision support: Provides downloadable public opinion analysis reports to help users quickly understand market dynamics and formulate response strategies.

[0067] User-interactive question and answer specifically includes:

[0068] Natural Language Understanding: Based on the analysis report, users can ask questions about the report details or send revision instructions. The model can understand the user's instructions, answer the user's questions, or optimize the report.

[0069] ① User instruction analysis.

[0070] The system segments user commands, determines the data content the user wants to know based on keywords in the command, automatically generates SQL statements to retrieve data from the underlying data, extracts the data indicators needed to answer the user command, and processes the data.

[0071] ② User command response.

[0072] Based on the data indicators and data processing results retrieved in the previous step, and combined with the analysis report above, the latest content will be re-output.

[0073] Hardware and software support specifically includes:

[0074] Hardware infrastructure: High-performance computing equipment and distributed storage systems are used to ensure the stability of large-scale data processing and model operation.

[0075] Software architecture: Based on cloud-native architecture design, it supports real-time analysis needs with high concurrency and low latency.

[0076] like Figure 2 As shown, this application also provides a financial market sentiment analysis system, including:

[0077] The preprocessing module is used to preprocess multi-source data and determine the preprocessed multi-source data; the multi-source data includes negative public opinion data in the financial market, urban investment data, announcement documents, industrial and commercial data, and internal business data of enterprises.

[0078] The subject type determination module is used to classify the preprocessed multi-source data based on large model technology and a financial field-specific public opinion analysis model to determine the subject type; the subject type includes urban investment enterprises and non-urban investment enterprises.

[0079] The public opinion analysis report generation module is used to automatically generate a structured public opinion analysis report based on the subject type.

[0080] This application has the following significant advantages over the prior art:

[0081] 1. Highly efficient data processing capabilities: Through the integration of multiple data sources and large model technology, the system can process massive amounts of financial public opinion data and urban investment information data in real time, and the analysis results have high timeliness.

[0082] 2. Precise risk assessment: The powerful data analysis capabilities of the large model enable the system to more accurately identify market risks and public opinion trends, significantly improving analysis efficiency.

[0083] 3. Comprehensive decision support: The generated public opinion analysis reports not only include risk identification, but also provide trend forecasts and decision-making suggestions to help users make more informed market decisions.

[0084] 4. Flexibility and scalability: The system supports access to multiple data sources and business scenarios, and can be customized according to user needs.

[0085] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments. The computer device can be a server or a terminal. The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. The processor, memory, and I / O are connected via a system bus, and the communication interface is connected to the system bus via the I / O interface. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device stores data to be processed. The I / O interface of the computer device is used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a financial market sentiment analysis method.

[0086] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0087] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0088] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0089] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0090] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by hardware related to computer program instructions. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0091] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0092] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0093] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for analyzing public opinion in the financial market, characterized in that, include: The multi-source data is preprocessed to determine the preprocessed multi-source data; the multi-source data includes negative public opinion data in the financial market, local government financing vehicle (LGFV) data, announcements and documents, business registration data, and internal business data of enterprises. Based on large model technology, the preprocessed multi-source data is classified using a financial sector-specific public opinion analysis model to determine the subject types; the subject types include urban investment enterprises and non-urban investment enterprises. Based on the subject type, a structured public opinion analysis report is automatically generated.

2. The financial market public opinion analysis method according to claim 1, characterized in that, Based on the aforementioned subject type, a structured public opinion analysis report is automatically generated, specifically including: For the aforementioned urban investment companies, the urban investment company public opinion summary is extracted from the corresponding corporate public opinion data of the urban investment companies using the financial field-specific public opinion analysis model. Based on the aforementioned public opinion summary of urban investment enterprises, risk level and importance analysis are conducted. According to data nature, the main urban investment enterprise data is analyzed based on prompts. Simultaneously, the scheduling tool components process the corresponding corporate public opinion data of the urban investment enterprises to generate an urban investment enterprise public opinion analysis report. The prompts include analysis dimensions, key indicators of focus, and expected report structure and content. The main urban investment enterprise data includes regional data, financial data of the urban investment entity, and third-party scoring data. The tool components include a calculator, a time-based assessment tool, and a search tool. The urban investment enterprise public opinion analysis report includes a public opinion overview, risk level analysis, importance analysis, enterprise business overview, surrounding risks, financial status, regional economic analysis, and risk avoidance suggestions. For the non-local government financing vehicles (LGFVs), the financial sector-specific public opinion analysis model is used to extract the non-LGFV public opinion summary of the corresponding corporate public opinion data. Based on the public opinion summary of the non-urban investment enterprises, risk level analysis and importance analysis are performed. At the same time, the scheduling tool component processes the public opinion data of the corresponding enterprises of the non-urban investment enterprises to generate a public opinion analysis report of the non-urban investment enterprises. The public opinion analysis report of the non-urban investment enterprises includes a public opinion overview, risk level analysis, importance analysis, enterprise business overview, surrounding risks, and risk avoidance suggestions.

3. The financial market public opinion analysis method according to claim 2, characterized in that, Based on the aforementioned subject type, a structured public opinion analysis report is automatically generated, which previously included: For corporate public opinion data, the financial sector-specific public opinion analysis model is used for semantic understanding and sentiment analysis. The corporate public opinion data is divided into positive, neutral, and negative based on sentiment tendency, and further divided into important and ordinary based on the degree of negative public opinion impact. The corporate public opinion data includes the public opinion data corresponding to the urban investment companies and the public opinion data corresponding to the non-urban investment companies. The sentiment analysis includes risk level analysis and importance analysis.

4. The financial market sentiment analysis method according to claim 2, characterized in that, Based on the aforementioned subject type, a structured public opinion analysis report is automatically generated, which previously included: For the main urban investment data, the main urban investment data is divided into regional data, urban investment entity financial data, and third-party rating data according to the nature of the data. For urban investment enterprises, potential market risks are identified based on multi-dimensional factors, and the public opinion hotspots of the bond issuers are captured from the third-party data sources. The development trend of the bond issuers is analyzed by combining key financial data, financing guarantees, and bond issuance scale. The multi-dimensional factors include the development status of the industry and region in which the bond issuer is located, relevant policies, government support willingness, and the rating of the third-party institutions.

5. The financial market public opinion analysis method according to claim 4, characterized in that, For local government financing vehicles (LGFVs), the analysis includes identifying potential market risks based on multi-dimensional factors, capturing public opinion hotspots of bond issuers from three data sources, and combining key financial data, financing guarantees, and bond issuance scale to analyze the development trends of bond issuers. This also includes: We provide users with risk avoidance advice based on the level of risk, its importance, and the development trend of the bond issuer.

6. The financial market public opinion analysis method according to claim 1, characterized in that, Based on the aforementioned subject type, a structured public opinion analysis report is automatically generated, which then includes: Based on the financial sector-specific public opinion analysis model, user instructions are received and understood. Based on the public opinion analysis report, answer user questions according to user instructions, or modify the public opinion analysis report.

7. A financial market public opinion analysis system, characterized in that, include: The preprocessing module is used to preprocess multi-source data and determine the preprocessed multi-source data; the multi-source data includes negative public opinion data in the financial market, local government financing vehicle data, announcements and documents, business registration data, and internal business data of enterprises; The subject type determination module is used to classify the preprocessed multi-source data based on large-scale model technology and a financial-specific public opinion analysis model to determine the subject type; the subject type includes urban investment enterprises and non-urban investment enterprises. The public opinion analysis report generation module is used to automatically generate a structured public opinion analysis report based on the subject type.

8. A computer device, comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that the processor executes the computer program to implement the financial market sentiment analysis method according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the financial market sentiment analysis method according to any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the financial market sentiment analysis method according to any one of claims 1-6.

Images