Data processing method based on operation planning optimization and related equipment

Abstract

The embodiment of the invention belongs to the technical field of computers, and relates to a data processing method based on operation planning optimization, and the method comprises the steps: obtaining to-be-processed customer feedback data; inputting the client feedback data into a preset big language model, performing data analysis on the client feedback data through the big language model, and outputting an analysis result; and converting the analysis result into visual information, and displaying the visual information on a preset interface. The invention further provides a data processing device based on operation planning optimization, computer equipment and a storage medium. In addition, the invention also relates to a block chain technology, and client feedback data and analysis results can be stored in a block chain. According to the method, the client feedback data is automatically analyzed by introducing the large language model, and the analysis result is converted into the visual information, so that high cost and low efficiency of manual processing can be avoided, and the accuracy of data processing is improved.

Description

Technical Field

[0001] This application relates to the field of computer technology and is applied to the scenario of intelligently processing customer feedback information. In particular, it relates to a data processing method and related devices based on operations research optimization. Background Art

[0002] In the current business environment, customer feedback is crucial for the continuous improvement of products or services. Effective collection and utilization of customer feedback can help enterprises better understand market demands, optimize the user experience, and enhance market competitiveness.

[0003] Currently, in the pre-sales stage, many enterprises still collect customer feedback information manually during actual operations, analyze the customer feedback information, and finally store it in the form of a spreadsheet. However, this traditional method consumes high time and labor costs, and is easily affected by personal subjective factors during analysis, resulting in poor accuracy of the analysis results. In addition, with the growth of data volume, the efficiency of converting unstructured text data into valuable data is getting lower and lower, making it difficult to meet the needs of quickly responding to market changes. Summary of the Invention

[0004] The purpose of the embodiments of this application is to propose a method for processing customer feedback information and related devices to solve the technical problems of low efficiency and poor effect when collecting and organizing customer feedback information manually.

[0005] To solve the above technical problems, the embodiments of this application provide a data processing method based on operations research optimization, adopting the following technical solutions:

[0006] A data processing method based on operations research optimization includes the following steps:

[0007] Obtain customer feedback data to be processed;

[0008] Input the customer feedback data into a preset large language model, perform data analysis on the customer feedback data through the large language model, and output the analysis result;

[0009] Convert the analysis result into visual information and display the visual information on a preset interface.

[0010] Further, the analysis result includes feedback feature information and professional advice information. The step of inputting the customer feedback data into a preset large language model, performing data analysis on the customer feedback data through the large language model, and outputting the analysis result specifically includes:

[0011] Input the customer feedback data into the large language model;

[0012] Using the large language model, extract the feedback feature information from the customer feedback data;

[0013] Through the large language model, analyze the feedback feature information and generate the professional advice information;

[0014] Output the feedback feature information and the professional advice information as the analysis result.

[0015] Furthermore, the feedback feature information includes sentiment tendency information, main theme information, and customer pain point information. The step of using the large language model to extract the feedback feature information from the customer feedback data specifically includes:

[0016] According to the large language model, perform semantic understanding on the customer feedback data to obtain feedback content information;

[0017] According to the large language model, perform sentiment analysis on the feedback content information to obtain the sentiment tendency information;

[0018] According to the large language model, perform theme extraction on the feedback content information to obtain the main theme information;

[0019] According to the large language model, perform pain point analysis on the feedback content information to obtain the customer pain point information.

[0020] Furthermore, before the step of outputting the feedback feature information and the professional advice information as the analysis result, it further includes:

[0021] Perform data verification on the feedback feature information and the professional advice information to determine whether there is data abnormality;

[0022] If there is data abnormality, perform abnormality handling according to the preset abnormality handling rules and record the abnormality log;

[0023] If there is no data abnormality, use the feedback feature information and the professional advice information as the analysis result.

[0024] Furthermore, the step of converting the analysis result into visual information and displaying the visual information on a preset interface specifically includes:

[0025] Fill a preset visual template according to the analysis result to generate the visual information;

[0026] Send the visual information to the preset interface for display and generate an interaction button corresponding to the visual information on the preset interface.

[0027] Further, after the step of sending the visualization information to the preset interface for display and generating an interaction button corresponding to the visualization information on the preset interface, the method further includes:

[0028] In response to an interaction instruction triggered by the interaction button, updating the content and layout of the visualization information in the preset interface.

[0029] Further, after the step of inputting the customer feedback data into a preset large language model, performing data analysis on the customer feedback data through the large language model, and outputting an analysis result, the method further includes:

[0030] Converting the analysis result into a target file in a preset format and storing the target file in a preset database;

[0031] Storing the customer feedback data and the analysis result in a preset blockchain node.

[0032] To solve the above technical problems, an embodiment of the present application further provides a data processing device based on operational research optimization, adopting the following technical solutions:

[0033] A data processing device based on operational research optimization includes:

[0034] An acquisition module, configured to acquire customer feedback data to be processed;

[0035] An analysis module, configured to input the customer feedback data into a preset large language model, perform data analysis on the customer feedback data through the large language model, and output an analysis result;

[0036] A display module, configured to convert the analysis result into visualization information and display the visualization information on a preset interface.

[0037] To solve the above technical problems, an embodiment of the present application further provides a computer device, adopting the following technical solutions:

[0038] A computer device includes a memory and a processor, where computer-readable instructions are stored in the memory, and when the processor executes the computer-readable instructions, the steps of the data processing method based on operational research optimization described above are implemented.

[0039] To solve the above technical problems, an embodiment of the present application further provides a computer-readable storage medium, adopting the following technical solutions:

[0040] A computer-readable storage medium stores computer-readable instructions thereon, and when the computer-readable instructions are executed by a processor, the steps of the data processing method based on operations research optimization as described above are implemented.

[0041] Compared with the prior art, the embodiments of the present application mainly have the following beneficial effects:

[0042] The data processing method based on operations research optimization disclosed in the present application includes: obtaining customer feedback data to be processed; inputting the customer feedback data into a preset large language model, performing data analysis on the customer feedback data through the large language model, and outputting an analysis result; converting the analysis result into visual information and displaying the visual information on a preset interface. By introducing a large language model to automatically analyze customer feedback data and converting the analysis result into visual information, the customer feedback data can complete complex semantic understanding, sentiment analysis, etc. in a shorter time. Therefore, the processing efficiency is improved, the high cost and low efficiency of manual processing can be avoided, the accuracy of data processing is improved, and the result is more intuitive, facilitating quick understanding and response. Description of the Drawings

[0043] To more clearly illustrate the solutions in the present application, the following will briefly introduce the drawings required for the description of the embodiments of the present application. Obviously, the following drawings are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0044] Figure 1 is an exemplary system architecture diagram to which the present application can be applied;

[0045] Figure 2 is a flowchart of an embodiment of the data processing method based on operations research optimization according to the present application;

[0046] Figure 3 is a schematic structural diagram of an embodiment of the data processing device based on operations research optimization according to the present application;

[0047] Figure 4 is a schematic structural diagram of an embodiment of the computer device according to the present application. Detailed Embodiments

[0048] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this application belongs; the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above drawings are intended to cover non-exclusive inclusion. The terms "first", "second", etc. in the specification and claims of this application or the above drawings are used to distinguish different objects and not to describe a specific order.

[0049] Reference to "embodiment" herein means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of this application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0050] In order to enable those skilled in the art of this technology to better understand the solution of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0051] As Figure 1 shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0052] Users can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications may be installed on the terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0053] The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 (Moving Picture Experts Group Audio Layer III) players, MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop portable computers, and desktop computers, etc.

[0054] Server 105 may be a server that provides various services, such as a background server that supports the pages displayed on the terminal devices 101, 102, and 103.

[0055] It should be noted that the data processing method based on operations research optimization provided in the embodiments of the present application is generally executed by a server. Correspondingly, the data processing device based on operations research optimization is generally set in the server.

[0056] It should be understood that Figure 1 the numbers of the terminal devices, networks, and servers in are merely illustrative. According to the implementation requirements, there can be any number of terminal devices, networks, and servers.

[0057] Continuing to refer to Figure 2 , a flowchart of an embodiment of the data processing method based on operations research optimization according to the present application is shown. The data processing method based on operations research optimization includes the following steps:

[0058] Step S201, obtain the customer feedback data to be processed.

[0059] In this embodiment, the electronic device (such as the server shown in Figure 1 ) on which the data processing method based on operations research optimization runs can send or receive data through a wired connection or a wireless connection. It should be noted that the above wireless connection methods may include, but are not limited to, 3G / 4G / 5G connections, WiFi connections, Bluetooth connections, WiMAX connections, Zigbee connections, UWB (ultra wideband) connections, and other currently known or future-developed wireless connection methods.

[0060] In this embodiment, it mainly refers to collecting the feedback information provided by customers. These feedback data may come from various channels, such as customer questionnaires, online reviews, social media comments, customer service communication records, etc. The customer feedback data to be processed can be in the form of text, voice, pictures, etc. The key to this step is to ensure that complete and high-quality customer feedback data can be obtained from various sources, ensuring the comprehensiveness and representativeness of the data. To improve the accuracy of data collection, data collection techniques can be used, such as using Web crawler technology to automatically crawl customer feedback from social media and online platforms; or directly connecting to a customer feedback system (such as a CRM system) through an integrated API interface for data collection.

[0061] Step S202, input the customer feedback data into a preset large language model, perform data analysis on the customer feedback data through the large language model, and output the analysis result.

[0062] In this embodiment, the key is to use large language models (such as GPT, BERT, etc.) to perform natural language processing (NLP) on customer feedback data. Large language models can analyze the sentiment tendency, potential problems, keyword extraction, etc. in the text and provide analysis results. For example, sentiment analysis can help identify customer satisfaction, and topic modeling can extract common topics in customer feedback. To improve the accuracy of the analysis results, multiple NLP techniques can be combined, such as sentiment analysis, entity recognition, topic modeling, etc. At the same time, combining machine learning models (such as classifiers, regression analysis, etc.) can perform deeper processing on the feedback, such as predicting customer needs or foreseeing potential negative emotions.

[0063] Step S203, convert the analysis result into visual information and display the visual information on a preset interface.

[0064] In this embodiment, by converting the analysis result output by the large language model into visual information, it can be presented to the user intuitively and understandably. The visual forms may include bar charts, pie charts, trend charts, etc., helping the user quickly understand the overall situation of customer feedback. This method is particularly suitable for management and decision-makers to help them make more accurate decisions. To improve the visual effect, dynamic interactive visualization techniques can be adopted, such as using Power BI, Tableau or custom Web interfaces, supporting user interaction, such as filtering feedback data in different dimensions and viewing the feedback trends of specific time periods or specific groups. In addition, the AI-assisted decision-making system can give intelligent business suggestions or automated operation guidelines based on the analysis results.

[0065] It should be explained that operations research optimization is to optimize complex decision-making problems through mathematical modeling, computational methods and algorithm design, so as to find the optimal solution or approximate optimal solution. The optimization goal is usually to maximize or minimize certain key indicators, such as cost, time, efficiency, profit, etc. The process of operations research optimization generally includes the following important links. First, the actual problem needs to be transformed into a mathematical model, clarifying the problem's constraints, objective function and decision variables. For example, the logistics distribution problem can be modeled through the shortest path model. Then, a solution algorithm is carried out, and appropriate algorithms (such as linear programming, integer programming, dynamic programming, heuristic algorithms, etc.) are used to solve the optimization problem. These algorithms can be implemented by a computer and give the optimal solution or approximate solution of the problem in a short time. Finally, result analysis and decision support are carried out. The optimization results need to be analyzed in combination with the actual situation to make reasonable decisions and support the decision-making of enterprises, governments and other institutions.

[0066] This application introduces a large language model to automatically analyze customer feedback data and convert the analysis results into visual information. The customer feedback data can complete complex semantic understanding, sentiment analysis and other tasks in a shorter time, thus improving the processing efficiency, avoiding the high cost and low efficiency of manual processing, improving the accuracy of data processing, and making the results more intuitive, facilitating quick understanding and response.

[0067] In some alternative implementation manners of this embodiment, the above analysis results include feedback feature information and professional advice information. The step of inputting the customer feedback data into a preset large language model, performing data analysis on the customer feedback data through the large language model, and outputting the analysis results specifically includes:

[0068] Input the customer feedback data into the large language model;

[0069] Use the large language model to extract the feedback feature information from the customer feedback data;

[0070] Through the large language model, analyze the feedback feature information and generate the professional advice information;

[0071] Output the feedback feature information and the professional advice information as the analysis results.

[0072] In this embodiment, first, the collected customer feedback data is input into a pre-set large language model. The large language model is a deep learning-based model that can understand and process natural language. The customer feedback data may contain text information (such as customer messages, evaluations, complaints, etc.), or may include other forms of data (such as input after converting speech to text). To ensure accurate data input, text preprocessing techniques such as word segmentation and noise removal can be used to convert the unstructured customer feedback data into a structured format suitable for analysis by the large language model. Then, the large language model is used to extract features from the customer feedback data. The so-called "feedback feature information" refers to the key information extracted from customer feedback, which may include the customer's emotional tendency (such as positive, negative, neutral), problem points of the product or service (such as function deficiencies, quality problems, user experience problems, etc.), as well as customer needs or expectations. To improve the accuracy of feedback feature extraction, multiple techniques can be combined, such as sentiment analysis, entity recognition, keyword extraction, topic modeling, etc. The large language model will extract the key features of the feedback based on context understanding to avoid missing potential information expressed by the customer. After extracting the feedback feature information, the next step is to further analyze this information through the large language model to generate "professional advice information". This stage aims to automatically generate professional suggestions or improvement measures based on the problems or needs in customer feedback. For example, for frequently occurring quality problems, the system can provide corresponding product improvement suggestions, or based on the customer's emotional tendency, propose communication strategies for customer care. The generated professional advice information can be combined with a domain knowledge base, or personalized recommendations can be made using machine learning algorithms. An expert system can also be introduced to combine the customer's feedback information with historical data through a rule engine to provide more accurate suggestions. Finally, the feedback feature information and the professional advice information are combined to form a complete analysis result. The purpose of this step is to convert the analysis result of the large language model into actionable decision-making information to help enterprises or relevant decision-makers understand the true needs of customers and take corresponding actions. The output analysis result may be in the form of text, tables, reports, etc. To facilitate subsequent analysis and decision-making, the output result can support multiple formats, such as structured reports, chart analysis, etc., and can be docked with other systems (such as customer relationship management systems, product management systems, etc.) to provide one-stop customer feedback analysis and decision support.

[0073] It should be noted that, in combination with the analysis results of the large language model, an automated feedback classification and priority ranking module can be added. For example, the system can automatically classify problems according to the urgency and scope of influence of customer feedback and give the processing priorities. This can help managers quickly identify the most critical problems and optimize resource allocation. When generating professional advice information, a multi-dimensional analysis mechanism can be introduced. In addition to sentiment analysis and problem identification, comprehensive analysis can also be carried out based on the customer's historical feedback data, purchase behavior, user profile, etc., so as to provide more personalized and accurate advice. For example, for customers who have been dissatisfied for a long time, the system can give more in-depth improvement suggestions, while for new customers, it may focus more on product guidance or usage training.

[0074] By extracting in detail the sentiment tendency, theme information, and pain points of customer feedback, the professional advice information automatically generated by the large language model can help the business department make targeted improvement plans, enabling a more comprehensive understanding of customer needs and supporting more accurate subsequent decisions.

[0075] In some alternative implementation manners of this embodiment, the above feedback feature information includes sentiment tendency information, main theme information, and customer pain point information. The step of using the large language model to extract the feedback feature information from the customer feedback data specifically includes:

[0076] According to the large language model, perform semantic understanding on the customer feedback data to obtain feedback content information;

[0077] According to the large language model, perform sentiment analysis on the feedback content information to obtain the sentiment tendency information;

[0078] According to the large language model, perform theme extraction on the feedback content information to obtain the main theme information;

[0079] According to the large language model, perform pain point analysis on the feedback content information to obtain the customer pain point information.

[0080] In this embodiment, first, the large language model is required to perform semantic understanding on the input customer feedback data and extract higher-level feedback content information from it. Customer feedback data is often in natural language form, so the large language model needs to be able to recognize and understand the semantic meaning in the text and extract the core content that is useful for analyzing subsequent steps. For example, if the customer feedback contains complaints about product quality, the large language model will identify keywords such as "poor quality" and associate it with the theme of quality. The implementation of semantic understanding can be achieved with the help of technologies in natural language processing (NLP), such as word vectors (Word2Vec, GloVe) or more complex pre-trained language models (such as BERT, GPT). This step not only extracts literal keywords, but also captures implicit information in the context, further improving the depth of understanding of customer feedback. Then, according to the large language model, the feedback content information is subjected to sentiment analysis to obtain the sentiment tendency information. Sentiment analysis aims to evaluate the emotional tendency in customer feedback and judge the emotional state of the customer (such as positive, negative, neutral). Through sentiment analysis, the large language model can identify the emotional polarity in customer feedback, which is crucial for understanding customer satisfaction, experience, etc. For example, feedback may contain words such as "very satisfied" or "very disappointed", and sentiment analysis will evaluate the customer's emotional tendencies based on this information. The accuracy of sentiment analysis can be improved by training the model to identify more emotion categories (such as anger, surprise, confusion, etc.) and improving the accuracy of analysis through context understanding. In addition, sentiment analysis can not only reflect the emotional state of customers, but also analyze the potential needs or improvement directions that may be implied in customer feedback. Then, according to the large language model, the feedback content information is subjected to topic extraction to obtain the main topic information. Topic extraction refers to identifying the main content topics or issues discussed from customer feedback. This process requires a large language model to analyze customer feedback, identify recurring keywords or concepts, and classify them into one or more topics. For example, if customer feedback focuses on issues such as "delivery time is too long" or "product functions are incomplete", the model will identify these topics and extract "delivery problems" and "functional problems" as topics. Topic extraction technology can use a statistical-based LDA (latent Dirichlet allocation) method, or a deep learning-based technology such as a BERT model for topic modeling. Through these technologies, not only can explicit topics be extracted, but also potential, deep-level topics can be identified, such as potential needs of customers or problems that are not directly expressed. Then, according to the large language model, the feedback content information is subjected to pain point analysis to obtain the customer pain point information. Pain point analysis refers to identifying the main difficulties and problems encountered by customers in the process of using products or services from customer feedback. Customer pain points are usually the key factors affecting customer experience and need to be mined from the customer's language through detailed analysis.In this step, the large language model analyzes the customer feedback, combines the context information, and identifies the main pain points of the customer, such as "complicated operation", "unprompted customer service", or "excessive price". The pain point analysis process can be deeply mined by combining the results of sentiment analysis and topic extraction. For example, when the customer expresses negative emotions, combined with the results of topic extraction, the system can further explore the reasons for the emotions and summarize the real pain points. Pain point analysis can not only help enterprises discover existing problems, but also predict potential reasons for customer churn.

[0081] This application can more accurately capture the key information in customer feedback through a detailed feedback feature information extraction process, including sentiment analysis, topic extraction, and pain point analysis. This process makes data processing more refined and comprehensive, helps to more accurately identify customer needs and pain points, and thus provides more targeted and practical information support for subsequent decision-making.

[0082] In some alternative implementation manners of this embodiment, before the step of outputting the feedback feature information and the professional advice information as the analysis result, the following is further included:

[0083] Perform data verification on the feedback feature information and the professional advice information to determine whether there is data abnormality;

[0084] If there is data abnormality, perform abnormality handling according to the preset abnormality handling rules and record the abnormality log;

[0085] If there is no data abnormality, use the feedback feature information and the professional advice information as the analysis result.

[0086] In this embodiment, first, data verification is performed on the feedback feature information and the professional advice information to determine whether there is data anomaly. Before outputting the analysis result, the system will perform data verification on the extracted feedback feature information and professional advice information to ensure that these information are free of problems in terms of format, accuracy, and consistency. Data anomaly can refer to various situations, such as missing data, logical conflicts (e.g., the sentiment analysis result is "very satisfied" but the theme is "complaint"), data exceeding the reasonable range, or the format not meeting the requirements, etc. The verification process can adopt a series of rules or algorithms to automatically detect data anomaly. For example, statistical methods (such as Z-score) are used to identify extreme values in the data, or a rule engine (such as verification rules based on business logic) is used to determine whether there are obvious errors. Data verification is a prerequisite for ensuring the high quality and credibility of the output analysis result. If the verification step finds data anomaly, the system will process it according to the preset anomaly handling rules. For example, missing data can be filled by interpolation or using default values, data with format errors may be marked as "to be corrected", and logical conflicts may require manual intervention or further automated correction. During the anomaly handling process, the system will also automatically record the anomaly log for subsequent traceability and analysis. If no anomaly data is found during the verification process, the system will directly use the feedback feature information and professional advice information after analysis and processing as the final analysis result, and these results will be presented on the user-predefined interface for subsequent decision-making or operation. Only fully verified data can be used as a reliable output result to avoid decision-making errors or data misleading caused by data anomaly.

[0087] This application can ensure the accuracy and reliability of the analysis result by introducing a data verification and anomaly handling mechanism. By automatically identifying and handling data anomaly, it avoids decision-making mistakes or inaccurate analysis results caused by data errors, thereby improving the quality and credibility of data processing. The recording of the anomaly log is also convenient for subsequent traceability and problem troubleshooting, further enhancing the robustness of the system.

[0088] In some optional implementation manners of this embodiment, the step of converting the analysis result into visual information and displaying the visual information on the preset interface specifically includes:

[0089] Fill a preset visual template according to the analysis result to generate the visual information;

[0090] Send the visual information to the preset interface for display, and generate an interaction button corresponding to the visual information on the preset interface.

[0091] In this embodiment, the system first maps these analysis results (including information such as the emotional tendency, main theme, and customer pain points feedback by customers) to a preset visualization template according to the previously analyzed results. The visualization template can be a pre-designed chart, dashboard, or other data display forms, which are used to clearly display the analysis results. This step involves data formatting and graphing, enabling the data to be presented to users in an intuitive way. The visualization template can include different types of charts, such as bar charts, pie charts, line charts, heat maps, etc. The specific choice of chart form depends on the type of analysis results and the display requirements. To enhance the visualization effect, dynamic data display (such as real-time updated charts or trend charts) or a highly interactive graphical interface can also be introduced, allowing users to select detailed information or time periods for display according to their needs. In addition, the visualization template should have a certain degree of flexibility to be adjusted or customized according to different business scenarios and user requirements. After completing the visualization filling of the data, the system sends the generated visualization information to the user's preset interface. This interface may be a Web interface, a desktop application interface, or a mobile application interface, which displays the processed and transformed data. While displaying, relevant interactive buttons will also be generated for users to further interact with the visualization information, such as viewing detailed information, switching data views, adjusting display settings, etc. These interactive buttons can enhance the user experience and improve the operability of the data.

[0092] By converting the analysis results into visualization information and displaying them, this application can help decision-makers quickly identify key issues in complex data and make timely decisions; by adding interactive buttons, users can freely adjust and view information at different levels according to their needs, enhancing the flexibility of the system and the user experience.

[0093] In some optional implementation manners of this embodiment, after the step of sending the visualization information to the preset interface for display and generating interactive buttons corresponding to the visualization information on the preset interface, it further includes:

[0094] In response to the interaction instruction triggered by the interactive button, update the content and layout of the visualization information in the preset interface.

[0095] In this embodiment, when the user interacts with the interaction button on the interface (such as clicking, selecting, or other operations), the system will dynamically update the content or layout of the visual information according to the user's instructions or selections. Such interactions can include adjusting the displayed data range, updating the way data is displayed, or changing the format and style of the visual display. The updated content and layout may include modifying the display mode of the chart, changing the time range or filtering conditions for data display, or reorganizing the various elements of the display (such as charts, data tables, buttons, etc.). The user may wish to see different data or more specific content, for example, view data for different time periods in the time dimension, or view data for different regions in the region dimension. At this time, the system will update the data content in real time according to the instructions of the interaction button and redisplay the visual information that meets the requirements. Updating the layout usually means rearranging the display mode of the visual information. For example, when the user selects a certain data point or switches the data type, the system can rearrange the visual components, such as enlarging the display of certain charts or metrics, or presenting different data dimensions in different layout ways to enhance the visual effect. Interaction instructions are not limited to button clicks, but can also include slider operations, selection box options, timeline scrolling, data filtering, and other forms. The system can respond to these instructions and adjust the interface display content and layout in real time. By using front-end technologies (such as AJAX or WebSocket) to achieve dynamic interaction with the background data source, the data content can be updated in real time without reloading the entire page. This method can greatly improve the user experience and make the data update smoother and more efficient. The front-end interface should support responsive design to ensure that users on different devices (such as desktops, tablets, mobile phones) can obtain a good interaction experience. When the user triggers an interaction instruction, the system can automatically adjust the displayed content and layout according to different screen sizes to ensure that the visual information is always presented in the most appropriate way.

[0096] By introducing the interaction function in this application, users can dynamically update the content and layout of the visual information during the display process. This function improves the real-time response ability of the system, enabling decision-makers to quickly adjust the information display according to current needs, helping them obtain the latest data and analysis results. This interactivity enhances the personalization and adaptability of the system and improves user participation and satisfaction.

[0097] In some alternative implementation manners of this embodiment, after the step of inputting the customer feedback data into a preset large language model, performing data analysis on the customer feedback data through the large language model, and outputting an analysis result, the method further includes:

[0098] Converting the analysis result into a target file according to a preset format and storing the target file in a preset database;

[0099] Store the customer feedback data and the analysis results in a preset blockchain node.

[0100] In this embodiment, the results after being analyzed by the large language model will be converted into a predetermined format (such as JSON, CSV, XML, PDF, etc.) for storage and further use. The choice of this format usually depends on subsequent processing requirements or data sharing standards. For example, if the results need to be further statistically analyzed or report generated, a structured format (such as CSV or JSON) may be selected; if it is for display and printing, a format such as PDF may be chosen. Subsequently, the converted target file will be stored in a preset database, which can be a relational database (such as MySQL, PostgreSQL) or a non-relational database (such as MongoDB, Cassandra), or it can also be a cloud storage platform, ensuring that the data can be stored efficiently and securely and can be accessed, queried, and analyzed at any time. Then, store the customer feedback data and the analysis results in a preset blockchain node, not only storing the customer feedback data and the analysis results in a traditional database, but also storing them in the blockchain node. The introduction of blockchain technology can ensure the immutability, transparency, and decentralization of data, thereby enhancing the credibility and security of data storage. Storing the original customer feedback data in the blockchain node can ensure that these data cannot be modified or forged during storage and access. This is crucial for ensuring the authenticity of data and preventing malicious tampering, especially when dealing with sensitive or high-value information. In addition, storing the results after being analyzed by the large language model in the blockchain can ensure that these analysis results also have immutability. If it is necessary to trace the analysis process or prove the reliability of a certain analysis result, the transparency and publicity of the blockchain can be used to query the relevant data and analysis records.

[0101] By storing the analysis results in both the database and the blockchain, this application not only ensures the efficient access and storage of data, but also provides an immutable storage guarantee. The use of blockchain technology ensures the transparency and traceability of data, enhances the trust and security of the system. At the same time, the data stored in the long term can also provide a reliable historical basis for subsequent analysis and auditing, enhancing the long-term value of the data.

[0102] It should be emphasized that to further ensure the privacy and security of the above customer feedback data and analysis results information, the above customer feedback data and analysis results information can also be stored in a node of a blockchain.

[0103] The blockchain referred to in this application is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, and encryption algorithms. Blockchain, in essence, is a decentralized database, a series of data blocks generated by using cryptographic methods. Each data block contains information about a batch of network transactions, which is used to verify the validity of the information (anti-counterfeiting) and generate the next block. The blockchain can include the blockchain underlying platform, the platform product service layer, and the application service layer, etc.

[0104] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Among them, Artificial Intelligence (AI) is to use a digital computer or a machine controlled by a digital computer to simulate, extend, and expand human intelligence, sense the environment, acquire knowledge, and use knowledge to obtain the best results of theory, methods, technologies, and application systems.

[0105] Artificial intelligence basic technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation / interaction systems, and mechatronics. Artificial intelligence software technologies mainly include several major directions such as computer vision technology, robotics, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0106] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through computer-readable instructions. The computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above various methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a Random Access Memory (RAM), etc.

[0107] It should be understood that although the steps in the flowchart of the accompanying drawings are shown in sequence according to the indication of the arrows, these steps do not necessarily need to be executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings can include multiple sub-steps or multiple stages. These sub-steps or stages do not necessarily need to be completed at the same moment, but can be executed at different moments. Their execution order does not necessarily need to be sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0108] For further referenceFigure 3 , as an implementation of the method shown above Figure 2 , this application provides an embodiment of a data processing device based on operations research optimization. This device embodiment corresponds to Figure 2 the method embodiment shown, and this device can be specifically applied to various electronic devices.

[0109] As Figure 3 shown, the data processing device 300 based on operations research optimization described in this embodiment includes: an acquisition module 301, an analysis module 302, and a display module 303. Among them:

[0110] The acquisition module 301 is used to acquire customer feedback data to be processed;

[0111] The analysis module 302 is used to input the customer feedback data into a preset large language model, perform data analysis on the customer feedback data through the large language model, and output an analysis result;

[0112] The display module 303 is used to convert the analysis result into visual information and display the visual information on a preset interface.

[0113] The data processing device based on operations research optimization provided by this application introduces a large language model to automatically analyze customer feedback data, and converts the analysis result into visual information. The customer feedback data can complete complex semantic understanding, sentiment analysis and other tasks in a shorter time. Therefore, the processing efficiency is improved, the high cost and low efficiency of manual processing can be avoided, the accuracy of data processing is improved, and the result is more intuitive, which is convenient for quick understanding and response.

[0114] In some alternative implementation manners of this embodiment, the above analysis result includes feedback feature information and professional advice information, and the analysis module 302 is further used for:

[0115] Input the customer feedback data into the large language model;

[0116] Use the large language model to extract the feedback feature information from the customer feedback data;

[0117] Analyze the feedback feature information through the large language model and generate the professional advice information;

[0118] Output the feedback feature information and the professional advice information as the analysis result.

[0119] The data processing device based on operations research optimization provided by this application can help the business department make targeted improvement plans by extracting in detail the sentiment tendency, theme information, and pain points from customer feedback. It can comprehensively understand customer needs and support more accurate subsequent decision-making.

[0120] In some alternative implementation manners of this embodiment, the above feedback feature information includes sentiment tendency information, main theme information, and customer pain point information. The analysis module 302 is further configured to:

[0121] Perform semantic understanding on the customer feedback data according to the large language model to obtain feedback content information;

[0122] Perform sentiment analysis on the feedback content information according to the large language model to obtain the sentiment tendency information;

[0123] Perform theme extraction on the feedback content information according to the large language model to obtain the main theme information;

[0124] Perform pain point analysis on the feedback content information according to the large language model to obtain the customer pain point information.

[0125] The data processing device based on operations research optimization provided by this application can more precisely capture the key information in customer feedback through a detailed feedback feature information extraction process, including sentiment analysis, theme extraction, and pain point analysis. This process makes data processing more refined and comprehensive, helps to more accurately identify customer needs and pain points, and thus provides more targeted and practically valuable information support for subsequent decision-making.

[0126] In some alternative implementation manners of this embodiment, the analysis module 302 is further configured to:

[0127] Perform data verification on the feedback feature information and the professional advice information to determine whether there is data abnormality;

[0128] If there is data abnormality, perform abnormality handling according to the preset abnormality handling rules and record the abnormality log;

[0129] If there is no data abnormality, use the feedback feature information and the professional advice information as the analysis result.

[0130] The data processing device based on operations research optimization provided by this application can ensure the accuracy and reliability of the analysis results by introducing a data verification and exception handling mechanism. By automatically identifying and handling data anomalies, it avoids decision-making mistakes or inaccurate analysis results caused by data errors, thereby improving the quality and credibility of data processing. The recording of exception logs also facilitates subsequent traceability and problem troubleshooting, further enhancing the robustness of the system.

[0131] In some alternative implementation manners of this embodiment, the display module 303 is further configured to:

[0132] Fill a preset visualization template according to the analysis result to generate the visualization information;

[0133] Send the visualization information to the preset interface for display, and generate an interaction button corresponding to the visualization information on the preset interface.

[0134] The data processing device based on operations research optimization provided by this application can help decision-makers quickly identify key issues in complex data and make timely decisions by converting the analysis result into visualization information and displaying it; by adding interaction buttons, users can freely adjust and view information at different levels according to their needs, improving the flexibility of the system and the user experience.

[0135] In some alternative implementation manners of this embodiment, the display module 303 is further configured to:

[0136] Respond to an interaction instruction triggered by the interaction button to update the content and layout of the visualization information on the preset interface.

[0137] The data processing device based on operations research optimization provided by this application can enable users to dynamically update the content and layout of visualization information during the display process by introducing an interaction function. This function improves the real-time response ability of the system, enabling decision-makers to quickly adjust information display according to current needs, helping them obtain the latest data and analysis results. This interactivity enhances the personalization and adaptability of the system, improving the user's sense of participation and satisfaction.

[0138] In some alternative implementation manners of this embodiment, the display module 303 is further configured to:

[0139] Convert the analysis result into a target file according to a preset format, and store the target file in a preset database;

[0140] Store the customer feedback data and the analysis result in a preset blockchain node.

[0141] The data processing device based on operations research optimization provided by this application stores the analysis results in the database and the blockchain, which not only ensures the efficient access and storage of data, but also provides an immutable storage guarantee. The use of blockchain technology ensures the transparency and traceability of data, enhances the trust and security of the system. At the same time, the long-term stored data can also provide a reliable historical basis for subsequent analysis and auditing, enhancing the long-term value of the data.

[0142] To solve the above technical problems, the embodiments of this application also provide a computer device. For details, please refer to Figure 4 , Figure 4 which is the basic structural block diagram of the computer device in this embodiment.

[0143] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are communicatively connected to each other through a system bus. It should be noted that only the computer device 4 with components 41-43 is shown in the figure, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be alternatively implemented. Among them, those skilled in the art of this technology can understand that a computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0144] The computer device can be a desktop computer, a notebook, a palm computer, a cloud server and other computing devices. The computer device can interact with the user through a keyboard, a mouse, a remote control, a touchpad or a voice control device and other means.

[0145] The memory 41 at least includes one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disc, etc. In some embodiments, the memory 41 may be an internal storage unit of the computer device 4, such as the hard disk or memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, FlashCard, etc. equipped on the computer device 4. Of course, the memory 41 may also include both the internal storage unit and the external storage device of the computer device 4. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of the data processing method based on operations research optimization. In addition, the memory 41 may also be used to temporarily store various types of data that have been output or will be output.

[0146] In some embodiments, the processor 42 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run the computer-readable instructions stored in the memory 41 or process data, such as running the computer-readable instructions of the data processing method based on operations research optimization.

[0147] The network interface 43 may include a wireless network interface or a wired network interface, and the network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0148] The computer device provided by the present application introduces a large language model to automatically analyze customer feedback data and convert the analysis results into visual information. The customer feedback data can complete complex semantic understanding, sentiment analysis and other tasks in a shorter time, thus improving the processing efficiency, avoiding the high cost and low efficiency of manual processing, and improving the accuracy of data processing. Moreover, the results are more intuitive, facilitating quick understanding and response.

[0149] The present application also provides another implementation manner, that is, to provide a computer-readable storage medium storing computer-readable instructions that can be executed by at least one processor, so that the at least one processor executes the steps of the data processing method based on operations research optimization as described above.

[0150] For the computer-readable storage medium provided by the present application, by introducing a large language model to automatically analyze customer feedback data and converting the analysis results into visual information, the customer feedback data can complete complex semantic understanding, sentiment analysis and other tasks in a shorter time. Therefore, the processing efficiency is improved, the high cost and low efficiency of manual processing can be avoided, the accuracy of data processing is improved, and the results are more intuitive, facilitating quick understanding and response.

[0151] Through the description of the above implementation manners, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation manner. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc) and includes several instructions for causing a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in various embodiments of the present application.

[0152] Obviously, the embodiments described above are only a part of the embodiments of the present application, rather than all the embodiments. The preferred embodiments of the present application are given in the drawings, but do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure content of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions described in the foregoing specific embodiments, or perform equivalent replacements on some of the technical features. Any equivalent structure directly or indirectly using the content of the specification and drawings of the present application in other related technical fields shall be equally within the scope of the patent protection of the present application.

Claims

1. A data processing method based on operations research optimization, characterized in that: The steps include: Get customer feedback data to be processed; Inputting the customer feedback data into a preset large language model, performing data analysis on the customer feedback data through the large language model, and outputting analysis results; The analysis results are converted into visual information, and the visual information is displayed on a preset interface.

2. The data processing method based on operations optimization according to claim 1 is characterized in that: The analysis result includes feedback feature information and professional suggestion information. The step of inputting the customer feedback data into a preset large language model, performing data analysis on the customer feedback data through the large language model, and outputting the analysis result specifically includes: Inputting the customer feedback data into the large language model; Extracting the feedback feature information from the customer feedback data using the large language model; Analyzing the feedback feature information through the large language model and generating the professional suggestion information; The feedback feature information and the professional suggestion information are output as the analysis result.

3. The data processing method based on operations optimization according to claim 2 is characterized in that: The feedback feature information includes sentiment tendency information, main topic information and customer pain point information. The step of extracting the feedback feature information from the customer feedback data using the large language model specifically includes: According to the large language model, semantic understanding is performed on the customer feedback data to obtain feedback content information; Performing sentiment analysis on the feedback content information according to the large language model to obtain the sentiment tendency information; Extracting topics from the feedback content information according to the large language model to obtain the main topic information; The feedback content information is subjected to pain point analysis according to the large language model to obtain the customer pain point information.

4. The data processing method based on operations research optimization according to claim 2 is characterized in that: Before the step of outputting the feedback feature information and the professional suggestion information as the analysis result, the method further includes: Performing data verification on the feedback feature information and the professional advice information to determine whether there is data anomaly; If there is data anomaly, it will be handled according to the preset exception handling rules and the exception log will be recorded; If there is no data anomaly, the feedback feature information and the professional advice information are used as the analysis result.

5. The data processing method based on operations optimization according to claim 1 is characterized in that: The step of converting the analysis result into visual information and displaying the visual information on a preset interface specifically includes: Filling a preset visualization template according to the analysis result to generate the visualization information; The visualization information is sent to the preset interface for display, and an interactive button corresponding to the visualization information is generated on the preset interface.

6. The data processing method based on operations optimization according to claim 5 is characterized in that: After the step of sending the visualization information to the preset interface for display and generating an interactive button corresponding to the visualization information on the preset interface, the method further includes: In response to the interactive instruction triggered by the interactive button, the content and layout of the visual information in the preset interface are updated.

7. The data processing method based on operations optimization according to any one of claims 1 to 6, characterized in that: After the step of inputting the customer feedback data into a preset large language model, performing data analysis on the customer feedback data through the large language model, and outputting the analysis result, the method further includes: Convert the analysis result into a target file according to a preset format, and store the target file in a preset database; The customer feedback data and the analysis results are stored in a preset blockchain node.

8. A data processing device based on operations optimization, characterized in that: include: An acquisition module is used to acquire customer feedback data to be processed; An analysis module, used for inputting the customer feedback data into a preset large language model, performing data analysis on the customer feedback data through the large language model, and outputting analysis results; The display module is used to convert the analysis results into visual information and display the visual information on a preset interface.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the data processing method based on operations research optimization as claimed in any one of claims 1 to 7 when executing the computer-readable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the data processing method based on operations research optimization according to any one of claims 1 to 7 are implemented.

Images