Public opinion data processing method and device, equipment and storage medium

Abstract

The embodiment of the invention provides a public opinion data processing method and device, equipment and a storage medium. The method comprises the steps of obtaining to-be-analyzed target public opinion data; performing information extraction on the target public opinion data to obtain target key information corresponding to the target public opinion data; performing weighted summation operation on the industry attention, the market subject rating and the price fluctuation value according to a preset weight to obtain an importance score of the public opinion data; performing emotion analysis on the target public opinion data through an emotion analysis model to obtain an emotion analysis result; wherein the emotion analysis result comprises a positive emotion, a negative emotion and a neutral emotion; and executing public opinion early warning operation of the target public opinion data in response to the fact that the importance score is greater than a preset importance threshold and the emotion analysis result is the negative emotion. The embodiment of the invention aims to improve the processing efficiency and accuracy of public opinion processing.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method for processing public opinion data, a device for processing public opinion data, a computer device, and a computer-readable storage medium. Background Art

[0002] The financial industry is highly correlated with market dynamics, and negative information in public opinion may quickly trigger market fluctuations. Therefore, public opinion data processing in the financial industry is an important part of financial market analysis and risk management.

[0003] In related technologies, financial public opinion data processing uses neural network-based methods: one is based on a convolutional neural network method, which can capture the performance of local features of text and extract local continuous phrase features in the text. The other is based on a long-short-term memory neural network method, which can effectively capture short-term contextual information and long-distance dependencies and extract sequence information from the text. However, both methods have their shortcomings. The convolutional neural network method cannot fully extract long-distance dependencies in financial texts, such as some emotional transitions that appear in the text, and is time-consuming. The long-short-term memory neural network method tends to focus on information at the beginning and end of the text, which is not very effective in extracting local information from the text and is unable to integrate multi-scale information in the text. Therefore, public opinion data processing in related technologies suffers from slow processing efficiency and low accuracy.

[0004] Based on the above reasons, it is necessary to propose a method for processing public opinion data in order to improve the processing efficiency and accuracy of public opinion processing. Summary of the Invention

[0005] The present application provides a method for processing public opinion data, a device for processing public opinion data, a computer device, and a computer-readable storage medium, aiming to improve the processing efficiency and accuracy of public opinion processing.

[0006] To achieve the above objectives, this application also provides a method for processing public opinion data, including:

[0007] Obtain target public opinion data to be analyzed;

[0008] Extracting information from the target public opinion data to obtain target key information corresponding to the target public opinion data, wherein the target key information includes industry attention, market entity rating, and price fluctuation value;

[0009] Performing a weighted sum operation on the industry attention, the market entity rating, and the price fluctuation value according to preset weights to obtain an importance score of the public opinion data; and performing sentiment analysis on the target public opinion data using a sentiment analysis model to obtain a sentiment analysis result; wherein the sentiment analysis result includes positive sentiment, negative sentiment, and neutral sentiment;

[0010] In response to the importance score being greater than a preset importance threshold and the sentiment analysis result being the negative sentiment, a public opinion warning operation of the target public opinion data is performed.

[0011] To achieve the above objectives, the present application also provides a device for processing public opinion data, comprising:

[0012] The acquisition module is used to obtain the target public opinion data to be analyzed;

[0013] An information extraction module is used to extract information from the target public opinion data to obtain target key information corresponding to the target public opinion data, wherein the target key information includes industry attention, market entity rating and price fluctuation value;

[0014] An importance scoring module is configured to perform a weighted sum operation on the industry attention, the market entity rating, and the price fluctuation value according to preset weights to obtain an importance score for the public opinion data; and perform sentiment analysis on the target public opinion data using a sentiment analysis model to obtain a sentiment analysis result; wherein the sentiment analysis result includes positive sentiment, negative sentiment, and neutral sentiment;

[0015] The public opinion warning execution module is used to execute the public opinion warning operation of the target public opinion data in response to the importance score being greater than the preset importance threshold and the sentiment analysis result being the negative sentiment.

[0016] In addition, to achieve the above-mentioned purpose, the present application also provides a computer device, which includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement the steps of the method for processing public opinion data provided in any one of the embodiments of the present application when executing the computer program.

[0017] In addition, to achieve the above-mentioned purpose, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the processor implements the steps of the method for processing public opinion data provided in any one of the embodiments of the present application.

[0018] The embodiments of the present application disclose a method for processing public opinion data, a device for processing public opinion data, a computer device, and a computer-readable storage medium. The method includes obtaining target public opinion data to be analyzed, and extracting information from the target public opinion data to obtain target key information corresponding to the target public opinion data, wherein the target key information includes industry attention, market entity rating, and price fluctuation value. Furthermore, the industry attention, market entity rating, and price fluctuation value can be weighted and summed according to preset weights to obtain an importance score of the public opinion data; and the target public opinion data can be subjected to sentiment analysis through a sentiment analysis model to obtain a sentiment analysis result; wherein the sentiment analysis result includes positive sentiment, negative sentiment, and neutral sentiment. Thus, in response to the importance score being greater than the preset importance threshold and the sentiment analysis result being a negative sentiment, a public opinion warning operation for the target public opinion data can be executed. This application extracts information, performs weighted scoring, and performs sentiment analysis on target public opinion data. This allows for a rapid and accurate assessment of the importance of the target data and the market sentiment. When the importance score of the target public opinion data exceeds a preset threshold and indicates negative sentiment, it promptly triggers a public opinion warning. This helps financial institutions identify and respond to potential risks in advance, optimize resource allocation, and improve decision-making efficiency. Furthermore, through the generation of structured data and model-assisted analysis, the workload of manual information screening is significantly reduced, improving the automation and intelligence of public opinion management. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0020] Figure 1 This is a scenario diagram of a method for processing public opinion data provided by an embodiment of the present application;

[0021] Figure 2 This is a flowchart of a method for processing public opinion data provided by an embodiment of the present application;

[0022] Figure 3 This is a schematic block diagram of a device for processing public opinion data provided by an embodiment of the present application;

[0023] Figure 4 This is a schematic block diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0025] The flowcharts shown in the accompanying drawings are illustrative only and do not necessarily include all content and operations / steps, nor do they necessarily need to be executed in the order described. For example, some operations / steps may be decomposed, combined, or partially merged, so the actual order of execution may vary depending on the actual situation. In addition, although the functional modules are divided in the device schematics, in some cases, the module division may be different from that shown in the device schematics.

[0026] The term "and / or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0027] The following describes some embodiments of the present application in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features therein may be combined with each other.

[0028] like Figure 1 As shown, the method for processing public opinion data provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. The application environment includes a terminal device 110 and a server 120, wherein the terminal device 110 can communicate with the server 120 through a network. Specifically, the server 120 can obtain the target public opinion data to be analyzed, and extract information from the target public opinion data to obtain the target key information corresponding to the target public opinion data, wherein the target key information includes industry attention, market entity ratings and price fluctuation values. Further, the industry attention, market entity ratings and price fluctuation values ​​can be weighted and summed according to preset weights to obtain the importance score of the public opinion data; and, the target public opinion data can be subjected to sentiment analysis through a sentiment analysis model to obtain a sentiment analysis result; wherein the sentiment analysis result includes positive emotions, negative emotions and neutral emotions. Thus, in response to the importance score being greater than the preset importance threshold and the sentiment analysis result being a negative emotion, the public opinion warning operation of the target public opinion data can be executed through the terminal device 110. Among them, the server 120 can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. The terminal device 110 can be a smart phone, tablet computer, laptop computer, desktop computer, smart speaker, smart watch, etc., but is not limited to these. The terminal and the server can be directly or indirectly connected via wired or wireless communication, and this application does not limit this.

[0029] See also Figure 2 , Figure 2 This is a flow chart of a method for processing public opinion data provided by an embodiment of the present application. Figure 2 As shown, the method for processing public opinion data can be implemented through steps S11 to S14.

[0030] Step S11: Obtain target public opinion data to be analyzed.

[0031] For example, the target public opinion data can be obtained through government announcements (such as policy releases, regulatory documents, etc.), news media (such as financial media or industry news websites), and market data interfaces (such as financial data platforms), and the format of the target public opinion data may include but is not limited to web page format, text format, etc., which is not limited in this application.

[0032] Step S12: extract information from the target public opinion data to obtain target key information corresponding to the target public opinion data.

[0033] Among them, the target key information includes industry attention, market entity ratings and price fluctuation values.

[0034] It should be noted that industry attention is used to reflect the discussion heat or importance related to a specific industry in the target public opinion data; market entity rating is used to reflect the evaluation indicators of the credit or operating conditions of market entities such as companies or institutions involved in public opinion; price fluctuation value is used to reflect the fluctuation range or change trend of the prices of related assets (such as stocks, bonds and futures, etc.) mentioned in the target public opinion data.

[0035] For example, this application does not limit the above-mentioned information extraction method. For example, the target public opinion data can be extracted through a learning model to obtain target key information. For example, the industry category involved in the target public opinion data can be identified through keywords or topic models, and then the industry relevance can be calculated based on the word frequency statistics and heat index of the target public opinion data to obtain the industry attention of the target public opinion data. Alternatively, the target public opinion data can be analyzed through a scenario prediction model to obtain the price fluctuation value corresponding to the target public opinion data.

[0036] Through the above-mentioned information extraction method, the target public opinion data can be converted into structured target key information (industry attention, market entity ratings, price fluctuation values), thereby laying a data foundation for subsequent scoring calculations and sentiment analysis, improving the efficiency of public opinion analysis, and making the results more objective and operational.

[0037] Step S13: Perform weighted summation operations on industry attention, market entity ratings, and price fluctuation values ​​according to preset weights to obtain the importance score of the public opinion data; and perform sentiment analysis on the target public opinion data through the sentiment analysis model to obtain the sentiment analysis results.

[0038] Among them, the sentiment analysis results include positive emotions, negative emotions and neutral emotions; the importance score is used to reflect the importance and priority level of the target public opinion data.

[0039] It should be noted that this application does not limit the preset weights, which can be customized by the user. For example, the weights corresponding to industry attention, market entity ratings, and price fluctuation values ​​can be assigned according to the degree of public opinion influence. For another example, the weight corresponding to industry attention is set to be the lowest, which is 0.3, the weight of price fluctuation value is set to be the highest, which is 0.8, and the weight of market entity rating is set to be 0.5. In this way, the weighted sum operation of industry attention, market entity rating, and price fluctuation value can be performed to obtain the importance score of public opinion data.

[0040] Furthermore, positive sentiment is used to reflect the market's optimism, such as performance growth, stock price increases, etc.; negative sentiment is used to reflect the market's pessimism, such as losses, defaults, layoffs, etc.; neutral sentiment is used to reflect content that is relatively neutral or cannot be clearly classified.

[0041] For example, the sentiment analysis model may include a large language model or a sentiment analysis algorithm, which is not limited in this application. Furthermore, the sentiment analysis model may perform sentiment analysis on the target public opinion data to obtain the sentiment classification and probability distribution corresponding to each public opinion in the target public opinion data. For example, positive sentiment: 0.25; neutral sentiment: 0.15; negative sentiment: 0.60. The sentiment classification corresponding to the maximum value of the probability distribution can then be determined as the sentiment analysis result.

[0042] The above implementation methods can achieve efficient and accurate identification of important public opinions through scoring and sentiment analysis, and provide a data basis for subsequent public opinion warning operations.

[0043] Step S14: In response to the importance score being greater than the preset importance threshold and the sentiment analysis result being a negative sentiment, a public opinion warning operation of the target public opinion data is executed.

[0044] Among them, the preset importance threshold can be manually configured in advance or dynamically adjusted according to the actual application scenario, and this application does not limit this. For example, the preset importance threshold can be set to 70 points. If the importance score of the target public opinion data is 85 points, and the preset importance threshold is 70 points, it is determined that the importance score is greater than the preset importance threshold. At the same time, if the sentiment analysis result is a negative sentiment, it is confirmed that the target public opinion data may have an adverse impact on the market entity or industry, and therefore the public opinion warning operation of the target public opinion data can be executed.

[0045] For example, public opinion warning operations include: generating detailed reports, which is to quickly generate complete risk analysis reports based on the public opinion database; updating internal ratings, which is to adjust the internal scores of relevant entities based on public opinion; and adjusting investment strategies, which is to notify the investment team to reduce the proportion of holdings of relevant assets, etc. This application does not limit these operations. Through public opinion warning operations, it is possible to quickly respond to potential risks and convey high-importance and negative public opinion to relevant parties, ensuring that enterprises can respond efficiently and accurately to market fluctuations and crisis events.

[0046] The method for processing public opinion data disclosed in an embodiment of the present application includes obtaining target public opinion data to be analyzed, extracting information from the target public opinion data, and obtaining target key information corresponding to the target public opinion data, wherein the target key information includes industry attention, market entity rating, and price fluctuation value. Furthermore, a weighted summation operation can be performed on the industry attention, market entity rating, and price fluctuation value according to preset weights to obtain an importance score for the public opinion data; and sentiment analysis can be performed on the target public opinion data using a sentiment analysis model to obtain a sentiment analysis result, wherein the sentiment analysis result includes positive sentiment, negative sentiment, and neutral sentiment. Thus, in response to the importance score being greater than a preset importance threshold and the sentiment analysis result being negative, a public opinion warning operation can be executed for the target public opinion data. By performing information extraction, weighted scoring, and sentiment analysis on the target public opinion data, the present application can quickly and accurately assess the importance and market sentiment of the target public opinion data. When the importance score of the target public opinion data exceeds the preset importance threshold and the sentiment is negative, a public opinion warning operation is triggered in a timely manner, thereby helping financial institutions to identify and respond to potential risks in advance, optimize resource allocation, and improve decision-making efficiency. At the same time, through the generation of structured data and model-assisted analysis, the workload of manual information screening has been significantly reduced, and the automation and intelligence level of public opinion management has been improved.

[0047] Optionally, sentiment analysis is performed on the target public opinion data through a sentiment analysis model to obtain a sentiment analysis result, including: performing a preprocessing operation on the target public opinion data to obtain the preprocessed target public opinion data; performing a feature extraction operation on the target public opinion data through the sentiment analysis model to obtain a target sentiment factor of the target public opinion data; scoring and quantifying the positive sentiment factor, the negative sentiment factor and the neutral sentiment factor to obtain a sentiment intensity score of the target public opinion data; comparing the sentiment intensity score with a preset sentiment intensity threshold to obtain a sentiment analysis result.

[0048] It should be understood that in order to improve the processing efficiency and accuracy of the sentiment analysis model and reduce the impact of noise data on the results, the target public opinion data can be preprocessed to obtain preprocessed target public opinion data. The preprocessing operation includes at least one of word segmentation, stop word removal, and named entity recognition, which is not limited in this application.

[0049] It should be noted that word segmentation is used to split the target public opinion data into words or phrases, which is convenient for the model to perform feature extraction and sentiment judgment. For example, splitting "The company's profit exceeded expectations and the stock price rose" into ["company", "profit", "exceeded expectations", "stock price", "rose"]; stop word removal is used to remove meaningless or high-frequency words that have no direct impact on sentiment analysis, such as "of", "and", "is", etc.; named entity recognition is used to identify and label specific entities in the target public opinion data, such as company names, products, place names, time, etc., making the subsequent sentiment analysis more focused and improving the accuracy of sentiment judgment.

[0050] Exemplarily, a sentiment analysis model can be applied to perform feature extraction operations on the target public opinion data. By analyzing the semantics, relationships between words, and context meanings in the target public opinion data through the model, the target sentiment factors of the target public opinion data can be extracted. Among them, the target sentiment factors include positive sentiment factors, negative sentiment factors, and neutral sentiment factors.

[0051] It should be noted that positive sentiment factors are used to represent features related to positive events or emotions (such as "profit", "growth", "success", etc.). Negative sentiment factors are used to represent features related to negative events or emotions (such as "loss", "layoff", "default", etc.). Neutral sentiment factors are used to represent features related to neutral events or events without a clear sentiment tendency. The above sentiment factors can accurately reflect various sentiment features contained in the target public opinion data and provide data support for subsequent scoring.

[0052] Exemplarily, preset scoring criteria or model outputs can be used to assign scores to positive sentiment factors, negative sentiment factors, and neutral sentiment factors respectively. For example, the positive sentiment factor (such as "profit growth") has a score of +0.7, the negative sentiment factor (such as "layoff plan") has a score of -0.8, and the neutral sentiment factor (such as "market flat") has a score of 0. Further, the sum (or weighted sum) of the scores of the target sentiment factors can be calculated to obtain the sentiment intensity score, and the sentiment intensity score can be compared with a preset sentiment intensity threshold to obtain the sentiment analysis result.

[0053] Optionally, comparing the sentiment intensity score with a preset sentiment intensity threshold to obtain the sentiment analysis result includes: in response to the sentiment intensity score being higher than the preset sentiment intensity threshold, determining the sentiment analysis result as positive sentiment; in response to the sentiment intensity score being the same as the preset sentiment intensity threshold, determining the sentiment analysis result as neutral sentiment; in response to the sentiment intensity score being lower than the preset sentiment intensity threshold, determining the sentiment analysis result as negative sentiment.

[0054] Among them, the preset sentiment intensity threshold is used to represent the classification standard for determining sentiment. For example, the preset sentiment intensity threshold is 0.5, 0.6, etc., and this application does not limit this.

[0055] For example, the preset emotion intensity threshold is 0.5. Based on this, if the emotion intensity score is higher than 0.5, the emotion analysis result is determined to be positive emotion; if the emotion intensity score is equal to 0.5, the emotion analysis result is determined to be neutral emotion; if the emotion intensity score is lower than 0.5, the emotion analysis result is determined to be negative emotion.

[0056] The above embodiments can be quantified through sentiment factor scoring, which facilitates comparison of sentiment intensity scores of different public opinion data. At the same time, sentiment analysis results (positive, negative, neutral) can be used to support public opinion early warning, decision analysis and risk management.

[0057] Optionally, after performing weighted summation operations on industry attention, market entity ratings, and price fluctuation values ​​according to preset weights to obtain the importance score of the public opinion data, it also includes: storing the public opinion data and the importance score in an initial public opinion database to obtain a target public opinion database; wherein, the initial public opinion database is obtained by classifying and structuring the initial public opinion data according to the prompt word project through a large language model, and includes a number of initial public opinion data and corresponding importance scores; determining the public opinion data within a preset time period from the target public opinion database, and analyzing the public opinion data within the preset time period through a large language model to obtain a public opinion analysis summary within the preset time period.

[0058] Optionally, the classification includes one of classification by industry, classification by market type, and classification by indicator; the structured processing includes at least one of adding timestamp processing and index number processing to the initial public opinion data.

[0059] For example, the public opinion data and importance scores may also be stored in an initial public opinion database to obtain a target public opinion database for subsequent query, analysis, or archiving.

[0060] Among them, the public opinion data in the initial database can be classified and structured through a large language model. Classification includes classification by industry: such as finance, technology, energy, medicine, etc.; classification by market type: such as stock market, bond market, commodity market, etc.; classification by indicators: such as public opinion with high industry attention, public opinion with large price fluctuations, etc. Structural processing includes: adding timestamps, that is, marking the time for each piece of public opinion data, to facilitate subsequent time series analysis; index numbering, that is, adding a unique identifier for each piece of public opinion data, to facilitate retrieval. After the above processing, the structure of the classified initial public opinion database is clearer, which is convenient for data management, and the structured processing improves the retrieval efficiency and analysis operability of public opinion data.

[0061] For example, data within a specific time period (such as the past week or month) can be filtered from the target public opinion database, and then the filtered data can be batch analyzed through a large language model to extract core information and generate a summary.

[0062] The above implementation method generates an initial public opinion database through classification and structured processing, and then stores the target public opinion data in the initial public opinion database to generate the target database. This allows public opinion data to be systematically organized, resulting in more accurate analysis. The large language model's prompt word engineering and automated analysis accelerate the generation of public opinion summaries. Furthermore, public opinion summaries can be used to promptly identify risks and opportunities, assisting market players in developing response strategies.

[0063] Optionally, the initial public opinion database also includes an original information structure table and an index architecture, wherein the original information structure table includes original policy documents and market dynamic information; the index architecture includes a hash index intermediate table, and the hash index timetable uses preset time periods as nodes to provide a public opinion information query path based on the preset time period.

[0064] The raw information structure table is used to store raw, unprocessed public opinion data, serving as a foundational source for subsequent analysis and processing. Original policy documents include government-issued policies and regulations, financial regulatory notices, and other information. Market dynamics information reflects real-time financial market dynamics, such as stock market news, price fluctuation data, and economic indicator reports, though this application does not limit this information.

[0065] Furthermore, the hash index intermediate table is used to generate a unique hash value for each piece of public opinion data using a hash function, which facilitates the rapid location and query of specific data; the hash index timetable represents a hash index table established based on time nodes, which is used to quickly locate public opinion data within a specific time period.

[0066] For example, you can enter query conditions (such as time period, keywords, etc.), and then locate the hash value set that meets the conditions in the hash index time table, then find the storage address of the corresponding hash value in the hash index intermediate table, and finally return the public opinion data.

[0067] In the embodiment of the present application, the hash index architecture improves the speed of data query, which is particularly suitable for large-scale public opinion databases. The original information structure table retains complete public opinion data, and the index architecture ensures rapid positioning and accurate acquisition of data.

[0068] Optionally, the analysis method proposed in this application also includes: in response to receiving public opinion question and answer information sent by a user, analyzing the public opinion question and answer information through a machine learning model to determine the public opinion time and public opinion subject corresponding to the public opinion question and answer information; matching in the target database based on the public opinion time and public opinion subject to obtain matching results; and displaying the matching results through a display page.

[0069] For example, user-submitted public opinion Q&A information can be queries entered in natural language, such as "What is the public opinion situation of a certain company in November 2024?" or "What are the public opinion trends about the new energy industry in the past month?" This information includes time dimensions (such as date and time range) and subject dimensions (such as company name, industry, and market entity). Therefore, user-entered Q&A requests can be received in real time and used as input data for analysis.

[0070] For example, the above input data can be analyzed through a machine learning model to determine the public opinion time and public opinion subject corresponding to the public opinion question and answer information, and the extracted public opinion time and public opinion subject can be used in combination with the target database for matching to obtain matching results (for example, including time, subject, specific content summary, etc.). As a result, the matching results can be displayed through a display page.

[0071] This approach automatically analyzes user Q&A information through machine learning models, extracting key insights and reducing manual intervention to improve efficiency. Furthermore, it leverages both time and subject matching criteria to ensure that query results are highly relevant to user needs. Furthermore, the visual display of matching results enables users to quickly access information and make decisions.

[0072] See also Figure 3 , Figure 3 This is a schematic block diagram of a public opinion data processing device provided in an embodiment of the present application. The public opinion data processing device can be configured in a server to execute the aforementioned public opinion data processing method.

[0073] like Figure 4 As shown, the public opinion data processing device 200 includes: an acquisition module 201, an information extraction module 202, an importance scoring module 203 and a public opinion warning execution module 204.

[0074] Acquisition module 201, used to acquire target public opinion data to be analyzed;

[0075] An information extraction module 202 is configured to extract information from the target public opinion data to obtain target key information corresponding to the target public opinion data, wherein the target key information includes industry attention, market entity rating, and price fluctuation value;

[0076] Importance scoring module 203 is used to perform a weighted sum operation on the industry attention, the market entity rating, and the price fluctuation value according to preset weights to obtain an importance score of the public opinion data; and perform sentiment analysis on the target public opinion data using a sentiment analysis model to obtain a sentiment analysis result; wherein the sentiment analysis result includes positive sentiment, negative sentiment, and neutral sentiment;

[0077] The public opinion warning execution module 204 is used to execute the public opinion warning operation of the target public opinion data in response to the importance score being greater than the preset importance threshold and the sentiment analysis result being the negative sentiment.

[0078] The importance scoring module 203 is also used to perform preprocessing operations on the target public opinion data to obtain preprocessed target public opinion data; wherein, the preprocessing operation includes at least one of word segmentation processing, stop word removal processing and named entity recognition; the target public opinion data is subjected to feature extraction operations through the sentiment analysis model to obtain the target emotion factor of the target public opinion data; wherein, the target emotion factor includes a positive emotion factor, a negative emotion factor and a neutral emotion factor; the positive emotion factor, the negative emotion factor and the neutral emotion factor are scored and quantified to obtain the emotion intensity score of the target public opinion data; the emotion intensity score is compared with a preset emotion intensity threshold to obtain the emotion analysis result.

[0079] The importance scoring module 203 is also used to determine that the emotion analysis result is the positive emotion in response to the emotion intensity score being higher than the preset emotion intensity threshold; to determine that the emotion analysis result is the neutral emotion in response to the emotion intensity score being the same as the preset emotion intensity threshold; and to determine that the emotion analysis result is the negative emotion in response to the emotion intensity score being lower than the preset emotion intensity threshold.

[0080] The importance scoring module 203 is also used to store the public opinion data and the importance score in an initial public opinion database to obtain a target public opinion database; wherein, the initial public opinion database is obtained by classifying and structuring the initial public opinion data according to the prompt word project through a large language model, and includes a number of the initial public opinion data and the corresponding importance score; determine the public opinion data within a preset time period from the target public opinion database, and analyze the public opinion data within the preset time period through the large language model to obtain a public opinion analysis summary within the preset time period.

[0081] Optionally, the public opinion data processing device 200 further includes a question-answering module (not shown)

[0082] The question and answer module is used to respond to public opinion question and answer information sent by users, analyze the public opinion question and answer information through a machine learning model, determine the public opinion time and public opinion subject corresponding to the public opinion question and answer information; match the public opinion time and the public opinion subject in the target database to obtain a matching result; and display the matching result through the display page.

[0083] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0084] The methods and apparatus of the present application can be used in a wide variety of general-purpose or specialized computing system environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above.

[0085] For example, the above method and apparatus may be implemented in the form of a computer program. The computer program may be implemented in the form of a computer program. Figure 4 Runs on the computer device shown.

[0086] See also Figure 4 , Figure 4 1 is a schematic diagram of a computer device provided in an embodiment of the present application. The computer device may be a server.

[0087] like Figure 4 As shown, the computer device includes a processor, a memory, and a network interface connected via a system bus, wherein the memory may include a volatile storage medium, a non-volatile storage medium, and an internal memory.

[0088] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions that, when executed, enable the processor to execute any method for processing public opinion data.

[0089] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0090] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any method for processing public opinion data.

[0091] The network interface is used for network communication, such as sending assigned tasks. Those skilled in the art will understand that the structure of the computer device is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0092] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0093] Among them, in some embodiments, the processor is used to obtain target public opinion data to be analyzed; perform information extraction on the target public opinion data to obtain target key information corresponding to the target public opinion data, wherein the target key information includes industry attention, market entity rating and price fluctuation value; perform weighted sum operation on the industry attention, the market entity rating and the price fluctuation value according to preset weights to obtain the importance score of the public opinion data; and perform sentiment analysis on the target public opinion data through a sentiment analysis model to obtain a sentiment analysis result; wherein the sentiment analysis result includes positive emotions, negative emotions and neutral emotions; in response to the importance score being greater than a preset importance threshold and the sentiment analysis result being the negative emotion, execute a public opinion warning operation for the target public opinion data.

[0094] In some embodiments, the processor is also used to perform a preprocessing operation on the target public opinion data to obtain preprocessed target public opinion data; wherein, the preprocessing operation includes at least one of word segmentation processing, stop word removal processing and named entity recognition; the target public opinion data is subjected to a feature extraction operation through the sentiment analysis model to obtain a target sentiment factor of the target public opinion data; wherein, the target sentiment factor includes a positive sentiment factor, a negative sentiment factor and a neutral sentiment factor; the positive sentiment factor, the negative sentiment factor and the neutral sentiment factor are scored and quantified to obtain a sentiment intensity score of the target public opinion data; the sentiment intensity score is compared with a preset sentiment intensity threshold to obtain the sentiment analysis result.

[0095] In some embodiments, the processor is further used to determine that the emotion analysis result is the positive emotion in response to the emotion intensity score being higher than the preset emotion intensity threshold; to determine that the emotion analysis result is the neutral emotion in response to the emotion intensity score being the same as the preset emotion intensity threshold; and to determine that the emotion analysis result is the negative emotion in response to the emotion intensity score being lower than the preset emotion intensity threshold.

[0096] In some embodiments, the processor is further used to store the public opinion data and importance scores in an initial public opinion database to obtain a target public opinion database; wherein, the initial public opinion database is obtained by classifying and structuring the initial public opinion data according to the prompt word project through a large language model, and includes a number of the initial public opinion data and corresponding importance scores; determine the public opinion data within a preset time period from the target public opinion database, and analyze the public opinion data within the preset time period through the large language model to obtain a public opinion analysis summary within the preset time period.

[0097] In some embodiments, the processor is also used to respond to receiving public opinion question and answer information sent by a user, analyze the public opinion question and answer information through a machine learning model, determine the public opinion time and public opinion subject corresponding to the public opinion question and answer information; match the public opinion time and the public opinion subject in the target database to obtain a matching result; and display the matching result through the display page.

[0098] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. The computer program includes program instructions, and when the program instructions are executed, any one of the methods for processing public opinion data provided in the embodiments of the present application is implemented.

[0099] The computer-readable storage medium may be an internal storage unit of the computer device described in the aforementioned embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a SmartMedia Card (SMC), a Secure Digital (SD) card, a flash memory card, etc., equipped on the computer device.

[0100] Furthermore, the computer-readable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function, and the like.

[0101] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present application, and such modifications or substitutions should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A method for processing public opinion data, characterized in that: The analysis method comprises: Obtain target public opinion data to be analyzed; Extracting information from the target public opinion data to obtain target key information corresponding to the target public opinion data, wherein the target key information includes industry attention, market entity rating, and price fluctuation value; Performing a weighted sum operation on the industry attention, the market entity rating, and the price fluctuation value according to preset weights to obtain an importance score of the public opinion data; and performing sentiment analysis on the target public opinion data using a sentiment analysis model to obtain a sentiment analysis result; wherein the sentiment analysis result includes positive sentiment, negative sentiment, and neutral sentiment; In response to the importance score being greater than a preset importance threshold and the sentiment analysis result being the negative sentiment, a public opinion warning operation of the target public opinion data is performed.

2. The method according to claim 1, characterized in that The sentiment analysis of the target public opinion data is performed using a sentiment analysis model to obtain a sentiment analysis result, including: Performing a preprocessing operation on the target public opinion data to obtain preprocessed target public opinion data; wherein the preprocessing operation includes at least one of word segmentation, stop word removal, and named entity recognition; Performing a feature extraction operation on the target public opinion data through the sentiment analysis model to obtain a target sentiment factor of the target public opinion data; wherein the target sentiment factor includes a positive sentiment factor, a negative sentiment factor, and a neutral sentiment factor; Scoring and quantifying the positive emotion factor, the negative emotion factor, and the neutral emotion factor to obtain an emotion intensity score of the target public opinion data; The emotion intensity score is compared with a preset emotion intensity threshold to obtain the emotion analysis result.

3. The method according to claim 2, characterized in that The step of comparing the emotion intensity score with a preset emotion intensity threshold to obtain the emotion analysis result includes: In response to the emotion intensity score being higher than the preset emotion intensity threshold, determining the emotion analysis result as the positive emotion; In response to the emotion intensity score being the same as the preset emotion intensity threshold, determining that the emotion analysis result is the neutral emotion; In response to the emotion intensity score being lower than the preset emotion intensity threshold, determining the emotion analysis result as the negative emotion.

4. The method according to claim 1, wherein After performing a weighted sum operation on the industry attention, the market entity rating, and the price fluctuation value according to preset weights to obtain the importance score of the public opinion data, the method further includes: Storing the public opinion data and importance scores in an initial public opinion database to obtain a target public opinion database; wherein the initial public opinion database is obtained by classifying and structuring the initial public opinion data according to the prompt word project using a large language model, and includes a plurality of the initial public opinion data and corresponding importance scores; The public opinion data within a preset time period is determined from the target public opinion database, and the public opinion data within the preset time period is analyzed by the large language model to obtain a public opinion analysis summary within the preset time period.

5. The method according to claim 4, characterized in that The classification includes one of classification by industry, classification by market type, and classification by indicator; the structured processing includes adding at least one of timestamp processing and index number processing to the initial public opinion data.

6. The method according to claim 4, characterized in that The analysis method further comprises: In response to receiving a public opinion question and answer message from a user, analyzing the public opinion question and answer message through a machine learning model to determine the public opinion time and public opinion subject corresponding to the public opinion question and answer message; Matching the public opinion time and the public opinion subject in the target database to obtain a matching result; The matching result is displayed on the display page.

7. The method according to claim 4, characterized in that The initial public opinion database also includes an original information structure table and an index architecture, wherein the original information structure table includes original policy documents and market dynamic information; the index architecture includes a hash index intermediate table, and the hash index timetable uses preset time periods as nodes to provide a public opinion information query path based on the preset time period.

8. A device for processing public opinion data, characterized in that: The processing device comprises: The acquisition module is used to obtain the target public opinion data to be analyzed; An information extraction module is used to extract information from the target public opinion data to obtain target key information corresponding to the target public opinion data, wherein the target key information includes industry attention, market entity rating and price fluctuation value; An importance scoring module is configured to perform a weighted sum operation on the industry attention, the market entity rating, and the price fluctuation value according to preset weights to obtain an importance score for the public opinion data; and perform sentiment analysis on the target public opinion data using a sentiment analysis model to obtain a sentiment analysis result; wherein the sentiment analysis result includes positive sentiment, negative sentiment, and neutral sentiment; The public opinion warning execution module is used to execute the public opinion warning operation of the target public opinion data in response to the importance score being greater than the preset importance threshold and the sentiment analysis result being the negative sentiment.

9. A computer device, characterized in that: include: A memory and a processor; wherein the memory is connected to the processor for storing a program; the processor is used to implement the steps of the method for processing public opinion data as described in any one of claims 1-7 by running the program stored in the memory.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the steps of the method for processing public opinion data according to any one of claims 1 to 7.

Images