Data analysis method and device, electronic equipment and computer readable storage medium
By performing streaming and incremental analysis on online meeting data, personalized meeting recommendation information is generated, which solves the problem of accuracy in online meeting effect evaluation and improves the effectiveness of meeting planning and improvement.
Patent Information
- Application Number
- CN202510856417.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-24
- Publication Date
- 2025-10-03
AI Technical Summary
Existing online meetings make it difficult to accurately obtain feedback from participants and evaluate meeting effectiveness, which makes planning and improvement difficult.
By obtaining the original meeting data and preprocessing it, we use the pre-trained streaming data mining model to perform streaming analysis to obtain preliminary analysis information on emotions, user behavior and topics. We then use the pre-trained incremental data mining model to perform incremental analysis to generate personalized meeting recommendation information.
It has achieved accurate evaluation of the effectiveness of online meetings, improved the efficiency of meeting planning and improvement, and enhanced participant satisfaction and meeting effectiveness.
Smart Images
Figure CN120744541A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to, but are not limited to, the field of data analysis, and in particular to a data analysis method, device, electronic device, and computer-readable storage medium. Background Art
[0002] With the rapid development of society and the continuous advancement of science and technology, people's lives are moving towards intelligence. Online meetings have also been widely promoted and applied. They allow people to communicate conveniently and quickly, regardless of location. For example, in the financial sector, bank staff use online meetings to discuss work and report to their superiors. Or, in the medical field, medical staff can use online meetings to discuss patient conditions and develop relevant treatment plans. However, current online meetings struggle to obtain accurate feedback from participants and evaluate meeting effectiveness, making the planning and improvement of online meetings difficult. Summary of the Invention
[0003] The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.
[0004] In order to solve the problems mentioned in the above background technology, the embodiments of the present application provide a data analysis method, device, electronic device and computer-readable storage medium, which can more accurately evaluate the effectiveness of online meetings, thereby facilitating online meeting planning and improvement.
[0005] In a first aspect, an embodiment of the present application provides a data analysis method, comprising:
[0006] Obtain original meeting data;
[0007] Preprocessing the original conference data to obtain preprocessed conference data;
[0008] Performing streaming analysis on the conference preprocessed data based on a pre-trained streaming data mining model to obtain preliminary sentiment analysis information, preliminary user behavior analysis information, and preliminary topic analysis information;
[0009] Based on the pre-trained incremental data mining model, incremental analysis processing is performed on the preliminary emotion analysis information, the preliminary user behavior analysis information, and the preliminary topic analysis information, respectively, to obtain incremental emotion analysis information corresponding to the preliminary emotion analysis information, incremental user behavior analysis information corresponding to the preliminary user behavior analysis information, and incremental topic analysis information corresponding to the preliminary topic analysis information;
[0010] Personalized conference recommendation information is generated based on the sentiment incremental analysis information, the user behavior incremental analysis information, and the topic incremental analysis information.
[0011] In a second aspect, an embodiment of the present application further provides a data analysis device, the device comprising:
[0012] An acquisition unit, used to acquire original conference data;
[0013] A preprocessing unit, configured to preprocess the original conference data to obtain preprocessed conference data;
[0014] A first analysis unit is configured to perform streaming analysis on the conference preprocessed data based on a pre-trained streaming data mining model to obtain preliminary sentiment analysis information, preliminary user behavior analysis information, and preliminary topic analysis information;
[0015] a second analysis unit, configured to perform incremental analysis processing on the preliminary sentiment analysis information, the preliminary user behavior analysis information, and the preliminary topic analysis information based on a pre-trained incremental data mining model, to obtain incremental sentiment analysis information corresponding to the preliminary sentiment analysis information, incremental user behavior analysis information corresponding to the preliminary user behavior analysis information, and incremental topic analysis information corresponding to the preliminary topic analysis information;
[0016] A construction unit is used to generate personalized conference recommendation information based on the sentiment incremental analysis information, the user behavior incremental analysis information and the topic incremental analysis information.
[0017] In a third aspect, an embodiment of the present application further provides an electronic device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the data analysis method as described in the first aspect above is implemented.
[0018] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to execute the data analysis method described in the first aspect above.
[0019] According to the data analysis method of the embodiment provided in the present application, there are at least the following beneficial effects: in the process of data analysis, the original data of the meeting is first obtained, and then the original data of the meeting can be pre-processed to obtain the pre-processed data of the meeting, and then the pre-processed data of the meeting is subjected to streaming analysis based on the pre-trained streaming data mining model to obtain preliminary analysis information of sentiment, preliminary analysis information of user behavior and preliminary analysis information of topic; then, based on the pre-trained incremental data mining model, the preliminary analysis information of sentiment, preliminary analysis information of user behavior and preliminary analysis information of topic are respectively subjected to incremental analysis to obtain incremental analysis information of sentiment, incremental analysis information of user behavior and incremental analysis information of topic; finally, personalized meeting recommendation information can be obtained based on the incremental analysis information of sentiment, incremental analysis information of user behavior and incremental analysis information of topic. Through the above technical solution, the pre-processed data of the meeting is subjected to streaming analysis and incremental analysis, which can more accurately evaluate the effect of online meetings, thereby facilitating the planning and improvement of online meetings. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] The accompanying drawings are used to provide a further understanding of the technical solution of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present application and do not constitute a limitation on the technical solution of the present application.
[0021] Figure 1 This is a flow chart of a data analysis method provided by one embodiment of the present application;
[0022] Figure 2 yes Figure 1 A schematic flow chart of a specific implementation of step S200;
[0023] Figure 3 yes Figure 1 A schematic flow chart of a specific implementation of step S300;
[0024] Figure 4 yes Figure 1 A schematic flow chart of a specific implementation of step S400;
[0025] Figure 5 yes Figure 1 A schematic flow chart of a specific implementation of step S500;
[0026] Figure 6 It is executed Figure 5 A flowchart of a specific implementation of step S520;
[0027] Figure 7 It is executed Figure 1 A schematic flow chart of a specific implementation method after step S500;
[0028] Figure 8 is a schematic diagram of a data analysis device provided by one embodiment of the present application;
[0029] Figure 9 This is a schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION
[0030] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.
[0031] It should be noted that although the device schematics illustrate functional module divisions and the flowcharts illustrate logical sequences, in certain circumstances, the steps shown or described may be performed in a sequence that differs from the module divisions in the device or the sequence in the flowcharts. The terms "first," "second," and so on, used in the specification, claims, and drawings, are used to distinguish similar items and are not necessarily used to describe a specific sequence or precedence.
[0032] It should be noted that, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.
[0033] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.
[0034] AI is a new technical discipline that studies and develops theories, methods, technologies, and application systems for simulating, extending, and expanding human intelligence. Artificial intelligence is a branch of computer science that seeks to understand the essence of intelligence and produce new intelligent machines that can respond in a manner similar to human intelligence. Research in this field includes robotics, speech recognition, image recognition, natural language processing, and expert systems. Artificial intelligence can simulate the information processes of human consciousness and thinking. It also refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results.
[0035] Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.
[0036] Artificial intelligence, or AI, is a theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.
[0037] The servers involved in artificial intelligence technology can be independent servers or cloud servers that provide 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), as well as big data and artificial intelligence platforms.
[0038] The present application provides a data analysis method, device, electronic device and computer-readable storage medium. In the process of data analysis, the original data of the meeting is first obtained, and then the original data of the meeting can be pre-processed to obtain the pre-processed data of the meeting. Then, based on the pre-trained streaming data mining model, the pre-processed data of the meeting is subjected to streaming analysis to obtain preliminary analysis information of sentiment, preliminary analysis information of user behavior and preliminary analysis information of topic; then, based on the pre-trained incremental data mining model, the preliminary analysis information of sentiment, preliminary analysis information of user behavior and preliminary analysis information of topic are subjected to incremental analysis to obtain incremental analysis information of sentiment, incremental analysis information of user behavior and incremental analysis information of topic; finally, personalized meeting recommendation information can be obtained based on the incremental analysis information of sentiment, incremental analysis information of user behavior and incremental analysis information of topic. Through the above technical solution, the pre-processed data of the meeting is subjected to streaming analysis and incremental analysis, which can more accurately evaluate the effect of online meetings, thereby facilitating the planning and improvement of online meetings.
[0039] The data analysis method provided in the embodiment of the present application relates to the field of data analysis. The data analysis method provided in the embodiment of the present application can be applied to a terminal, can be applied to a server side, or can be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or as a server cluster or distributed system composed of multiple physical servers, or as 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, CDN, and big data and artificial intelligence platforms.
[0040] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.
[0041] It should be noted that in each specific embodiment of the present application, when it comes to the need to perform relevant processing based on data related to the user's identity or characteristics, such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of such data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.
[0042] The embodiments of the present application are further described below with reference to the accompanying drawings.
[0043] like Figure 1 As shown, Figure 1 This is a flow chart of a data analysis method provided by an embodiment of the present application, which includes the following steps:
[0044] Step S100: Obtaining original conference data.
[0045] The data analysis method provided in the embodiment of the present application first needs to obtain the original meeting data during the data analysis process, wherein the original meeting data may include the behavioral data of the participants, such as chat records, discussion content, camera interaction logs, user click behavior, and voice transcription text, etc. For example, in the insurance business field, when insurance agents are in a meeting, they can use a microphone to collect the voice information of each insurance agent, and can also use a camera to collect the interactive images of each insurance agent, and can also use an online conference module to collect the user click behavior information of each insurance agent, etc. The above collected voice information, interactive images, and user click behavior information are all original meeting data. Alternatively, in the medical field, when medical staff are in an online meeting to discuss the patient's treatment plan, they can also use a microphone to collect the voice information of each medical staff, and can also use a camera to collect the interactive images of each medical staff, and can also use an online conference module to collect the user click behavior information of each medical staff, etc. The above collected voice information, interactive images, and user click behavior information are also original meeting data.
[0046] It is worth noting that after obtaining the original meeting data, the obtained original meeting data can be preprocessed to obtain the meeting preprocessed data. In order to prepare for subsequent data analysis and processing, the meeting preprocessed data can be subjected to streaming analysis based on the streaming data mining model. Subsequently, the information obtained from the streaming analysis can be incrementally analyzed based on the incremental data mining model to prepare for the generation of personalized meeting recommendation information.
[0047] It is worth noting that in the process of obtaining the original data of the meeting, when it comes to the need to perform relevant processing based on data related to the user's identity or characteristics, such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of such data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.
[0048] Step S200: Preprocessing the original conference data to obtain preprocessed conference data.
[0049] The data analysis method provided in the embodiment of the present application can pre-process the original conference data after obtaining the original conference data, and thus obtain the conference pre-processed data; on the premise of obtaining the conference pre-processed data, the conference pre-processed data can be stream-analyzed, and thus preliminary emotion analysis information, preliminary user behavior analysis information and preliminary topic analysis information can be obtained; subsequently, the incremental data mining model can be used to perform incremental analysis on the preliminary emotion analysis information, preliminary user behavior analysis information and preliminary topic analysis information respectively, and thus obtain incremental emotion analysis information, incremental user behavior analysis information and incremental topic analysis information; finally, personalized conference recommendation information can be generated based on the incremental emotion analysis information, incremental user behavior analysis information and incremental topic analysis information obtained by analysis.
[0050] It is worth noting that in the process of preprocessing the original meeting data to obtain the preprocessed meeting data, the original meeting data can first be cleaned to obtain the valid meeting data, and then the valid meeting data can be formatted to obtain the formatted meeting data. Finally, the formatted meeting data can be aggregated based on a pre-set sliding time window to obtain the corresponding preprocessed meeting data.
[0051] like Figure 2 As shown, preprocessing the original conference data to obtain preprocessed conference data may include the following steps:
[0052] Step S210: Clean the original meeting data to obtain valid meeting data.
[0053] Step S220, formatting the valid conference data to obtain formatted conference data;
[0054] Step S230 : Aggregate the formatted conference data based on a preset sliding time window to obtain conference pre-processed data.
[0055] In steps S210 to S230, during the preprocessing of the original meeting data to obtain the preprocessed meeting data, the original meeting data is first cleaned to obtain the valid meeting data; the valid meeting data is then formatted to obtain the formatted meeting data; and finally, the formatted meeting data is aggregated based on a pre-set sliding time window to obtain the corresponding preprocessed meeting data. Through the above technical solution, preprocessing the original meeting data prepares for subsequent data streaming analysis and incremental analysis.
[0056] It is worth noting that by performing data cleaning on the original meeting data, the interference data in the original meeting data can be eliminated, thereby obtaining the effective meeting data. Eliminating the interference data makes subsequent data analysis more accurate. After obtaining the effective meeting data, the effective meeting data can be formatted, and then formatted meeting data can be obtained, making subsequent data analysis simpler and faster. The formatted meeting data is aggregated based on a pre-set sliding time window to perform statistical processing on the indicators of the relevant data, preparing for the subsequent generation of meeting preprocessing data.
[0057] It is worth noting that preprocessing the raw meeting data can filter out invalid data, such as garbled messages and blank click events, and remove duplicate records to improve the accuracy of subsequent data analysis. Formatting the valid meeting data can generate formatted meeting data, for example, unifying multi-source heterogeneous data into a structured format to facilitate subsequent data analysis. Aggregating the formatted meeting data based on a pre-set sliding time window allows statistical aggregation of relevant data indicators to generate preprocessed meeting data. After obtaining the preprocessed meeting data, it can also be written to a distributed database and data lake in real time to prepare for subsequent data analysis.
[0058] For example, in the insurance business, after obtaining the original meeting data during an online meeting of an insurance agent, the original meeting data can be cleaned to obtain the effective meeting data; then the effective meeting data can be formatted to obtain formatted meeting data, and finally the formatted meeting data can be aggregated to obtain the pre-processed meeting data. Alternatively, in the smart healthcare field, after obtaining the original meeting data during an online meeting of medical staff, the original meeting data can be cleaned to obtain the effective meeting data; then the effective meeting data can be formatted to obtain formatted meeting data, and finally the formatted meeting data can be aggregated to obtain the pre-processed meeting data.
[0059] Step S300: Perform streaming analysis on the conference pre-processed data based on the pre-trained streaming data mining model to obtain preliminary emotion analysis information, preliminary user behavior analysis information and preliminary topic analysis information.
[0060] The data analysis method provided in the embodiment of the present application, during the data analysis process, first obtains the original data of the meeting, and then pre-processes the original data of the meeting to obtain the pre-processed data of the meeting; then, the pre-processed data of the meeting can be subjected to streaming analysis based on the pre-trained streaming data mining model, and preliminary analysis information of emotions, preliminary analysis information of user behaviors and preliminary analysis information of topics can be obtained, in preparation for subsequent data analysis.
[0061] It is worth noting that the pre-trained streaming data mining model is a pre-trained streaming data mining model; after pre-processing the original meeting data to obtain the meeting pre-processed data, the meeting pre-processed data can be subjected to streaming analysis based on the pre-set streaming data mining model, that is, preliminary streaming data analysis and processing can be performed on the meeting pre-processed data, and then preliminary emotional analysis information, user behavior preliminary analysis information and topic preliminary analysis information can be obtained, and the collected data can be analyzed and mined in real time to capture dynamic changes and potential trends in the meeting, understand the behavior and feedback of the participants more accurately, and prepare for subsequent meeting feedback.
[0062] It is worth noting that the streaming data mining model can cluster user behavior data in real time, such as speaking frequency and stay time, and dynamically identify active user groups and silent user groups; extract topic distribution from real-time chat text and dynamically update topic popularity; the streaming data mining model can also detect abnormal behavior, such as a large number of users leaving the meeting in a short period of time, triggering an early warning mechanism.
[0063] like Figure 3 As shown, the pre-trained streaming data mining model is used to perform streaming analysis on the conference pre-processed data to obtain preliminary analysis information on sentiment, preliminary analysis information on user behavior, and preliminary analysis information on topics. The steps may include:
[0064] Step S310, determining multimodal data, user behavior data, and text information from the conference pre-processed data;
[0065] Step S320: clustering the multimodal data based on the streaming data mining model to obtain preliminary sentiment analysis information;
[0066] Step S330: clustering the user behavior data based on the streaming data mining model to obtain preliminary analysis information of the user behavior;
[0067] Step S340 , performing topic distribution analysis on the speech text information based on the streaming data mining model to obtain preliminary topic analysis information.
[0068] For steps S310 to S340, in the process of performing streaming analysis on the conference pre-processing data based on the pre-trained streaming data mining model to obtain preliminary emotion analysis information, user behavior preliminary analysis information and topic preliminary analysis information, first determine the multimodal data, user behavior data and text information from the conference pre-processing data; then cluster the multimodal data based on the streaming data mining model to obtain preliminary emotion analysis information; then cluster the user behavior data based on the streaming data mining model to obtain preliminary user behavior analysis information; subsequently, perform topic distribution analysis on the speech text information based on the streaming data mining model to obtain the corresponding preliminary topic analysis information; through the above technical solution, preparations are made for subsequent data analysis.
[0069] It is worth noting that multimodal data, user behavior data and text information are determined from the conference preprocessing data. Among them, multimodal data includes visual information and sound information, user behavior data includes the frequency of users' speeches and length of stay in the meeting, etc., and text information is the text information converted from the voice discussed in the meeting.
[0070] It is worth noting that based on the streaming data mining model, multimodal data can be clustered to obtain preliminary emotional analysis information; based on the streaming data mining model, user behavior data can be clustered to obtain preliminary user behavior analysis information; and based on the streaming data mining model, topic distribution analysis can be performed on voice text information to obtain preliminary topic analysis information.
[0071] For example, in the insurance business, during an online meeting to discuss relevant matters, insurance agents can obtain raw meeting data. Preprocessing the raw meeting data can then yield preprocessed meeting data. Multimodal data, user behavior data, and text information can then be determined from the preprocessed meeting data. Preliminary analysis and processing can then be performed on the multimodal data, user behavior data, and text information based on a streaming data mining model. Sentimental preliminary analysis information, user behavior preliminary analysis information, and topic preliminary analysis information can then be obtained, respectively, to prepare for subsequent data analysis. Alternatively, in the medical field, during an online meeting to discuss a patient's treatment plan, medical staff can obtain raw meeting data. Preprocessing the raw meeting data can then yield preprocessed meeting data. Multimodal data, user behavior data, and text information can then be determined from the preprocessed meeting data. Preliminary analysis and processing can then be performed on the multimodal data, user behavior data, and text information based on a streaming data mining model. Sentimental preliminary analysis information, user behavior preliminary analysis information, and topic preliminary analysis information can then be obtained, respectively, to prepare for subsequent data analysis.
[0072] Step S400: Based on the pre-trained incremental data mining model, incremental analysis processing is performed on the sentiment preliminary analysis information, the user behavior preliminary analysis information and the topic preliminary analysis information respectively to obtain sentiment incremental analysis information corresponding to the sentiment preliminary analysis information, user behavior incremental analysis information corresponding to the user behavior preliminary analysis information and topic incremental analysis information corresponding to the topic preliminary analysis information.
[0073] The data analysis method provided in the embodiment of the present application can, after obtaining the preliminary emotion analysis information, the preliminary user behavior analysis information and the preliminary topic analysis information, perform incremental analysis processing on the preliminary emotion analysis information based on the pre-trained incremental data mining model to obtain the incremental emotion analysis information; perform incremental analysis processing on the preliminary user behavior analysis information based on the pre-trained incremental data mining model to obtain the incremental user behavior analysis information; perform incremental analysis processing on the preliminary topic analysis information based on the pre-trained incremental data mining model to obtain the incremental topic analysis information; and prepare for the subsequent generation of personalized meeting recommendation information.
[0074] It is worth noting that preprocessing the original meeting data can obtain the meeting preprocessed data, and then the meeting preprocessed data can be subjected to streaming analysis and incremental analysis, and the collected data can be analyzed and mined in real time to capture dynamic changes and potential trends in the meeting, understand the behavior and feedback of the participants more accurately, and prepare for subsequent meeting feedback.
[0075] like Figure 4 As shown, based on the pre-trained incremental data mining model, incremental analysis processing is performed on the preliminary emotion analysis information, the preliminary user behavior analysis information, and the preliminary topic analysis information, respectively, to obtain incremental emotion analysis information corresponding to the preliminary emotion analysis information, incremental user behavior analysis information corresponding to the preliminary user behavior analysis information, and incremental topic analysis information corresponding to the preliminary topic analysis information, which may include the following steps:
[0076] Step S410, performing incremental adjustment processing on the preliminary sentiment analysis information based on the incremental data mining model to obtain incremental sentiment analysis information;
[0077] Step S420: performing incremental adjustment processing on the preliminary analysis information of user behavior based on the incremental data mining model to obtain incremental analysis information of user behavior;
[0078] Step S430 : performing incremental adjustment processing on the preliminary topic analysis information based on the incremental data mining model to obtain incremental topic analysis information.
[0079] For steps S410 to S430, in the process of performing incremental analysis and processing on the preliminary emotion analysis information, the preliminary user behavior analysis information and the preliminary topic analysis information respectively based on the pre-trained incremental data mining model, first, the preliminary emotion analysis information is incrementally adjusted based on the incremental data mining model to obtain the incremental emotion analysis information; the preliminary user behavior analysis information is incrementally adjusted based on the incremental data mining model to obtain the incremental user behavior analysis information; the preliminary topic analysis information is incrementally adjusted based on the incremental data mining model to obtain the incremental topic analysis information, and the collected data is analyzed and mined in real time to capture the dynamic changes and potential trends in the meeting, to understand the behavior and feedback of the participants more accurately, and to prepare for subsequent meeting feedback.
[0080] It is worth noting that after preliminary streaming data analysis and processing of multimodal data, preliminary emotion analysis information can be obtained, and then the preliminary emotion analysis information can be incrementally adjusted to obtain incremental emotion analysis information; after preliminary streaming data analysis and processing of user behavior data, preliminary user behavior analysis information can be obtained, and then the preliminary user behavior analysis information can be incrementally adjusted to obtain incremental user behavior analysis information; after preliminary streaming data analysis and processing of voice and text information, preliminary topic analysis information can be obtained, and then the preliminary topic analysis information can be incrementally adjusted to obtain incremental topic analysis information; subsequently, personalized meeting recommendation information can be generated based on the incremental emotion analysis information, the incremental user behavior analysis information and the incremental topic analysis information. After two rounds of data analysis and processing, the generated personalized meeting recommendation information can be more accurate.
[0081] Notably, for streaming sentiment analysis, incremental machine learning algorithms, such as online learning and incremental training, are used. These algorithms automatically update the sentiment classifier as new data arrives, eliminating the need to reprocess historical data. By continuously updating the sentiment classifier, the system can analyze attendees' emotional states and responses to discussion topics and content in real time. For sentiment analysis, a deeper emotion recognition model, such as a pre-trained deep sentiment classifier, is introduced to improve the accuracy and generalization of sentiment analysis. Furthermore, multimodal information, such as visual and audio information, is incorporated for multimodal sentiment analysis, which more accurately captures the emotions conveyed by the agent during the presentation. Incremental data mining algorithms are used to process user behavior data, such as engagement, speaking frequency, and interaction patterns. User behavior analysis aims to identify different groups of participants and analyze their behavioral characteristics. For incremental user behavior analysis, incremental clustering algorithms are used, which dynamically adjust clustering results as new data arrives. Through incremental user behavior analysis, the system can identify different types of attendees in real time and make personalized recommendations and increase engagement based on their behavioral characteristics. To better understand attendee behavior, the algorithm was optimized, combining user behavior analysis with user profile modeling. By employing technologies such as graph neural networks, a social network graph of attendees can be constructed within real-time data streams to analyze social relationships and interaction patterns. Combining user behavior characteristics with user profiles allows for a more accurate characterization of the engagement characteristics of different attendee types and personalized presentation content. Topic attention analysis involves real-time analysis of discussion content, extracting key themes, and calculating attention metrics for each topic. For streaming topic attention analysis, streaming topic modeling algorithms are used. These algorithms update topic models in real time within the data stream, enabling real-time analysis of discussion content. This allows the system to capture attendees' interest and attention in different topics in real time during the meeting, enabling adjustments to meeting content and agendas to improve meeting participation and effectiveness. For topic attention analysis, an incremental topic model is further employed, combined with streaming data mining algorithms to update the topic model in real time. This incremental topic model allows topic distributions to be updated as new data arrives while retaining historical topic information. This allows the system to more quickly adapt to changes and evolution in meeting topics, enabling real-time topic attention analysis.
[0082] Step S500: Generate personalized conference recommendation information based on the sentiment incremental analysis information, the user behavior incremental analysis information, and the topic incremental analysis information.
[0083] The data analysis method provided in the embodiment of the present application can generate personalized conference recommendation information based on the sentiment incremental analysis information, user behavior incremental analysis information and topic incremental analysis information after obtaining the sentiment incremental analysis information, user behavior incremental analysis information and topic incremental analysis information. Through the above technical solution, the behavioral data of the participants are deeply analyzed through machine learning and deep learning algorithms to extract personalized needs and preferences. Through such innovative improvements, topics and content that suit their interests can be recommended to each participant, thereby providing a customized conference experience. The innovative application of personalized recommendations can further improve the satisfaction and participation of the participants, so that each participant can obtain more targeted content and explanations, thereby improving the overall conference effect.
[0084] It is worth noting that based on the above technical solutions, accurate meeting effect evaluation is provided: through data analysis, the organizer can understand the participation, interactive effect, topic popularity, etc. of the meeting, evaluate the actual effect of the meeting, and provide personalized participant feedback: by analyzing the behavioral data of the participants, the system can generate personalized participant feedback reports to help the organizer understand the participants' attitudes and opinions on the meeting. Through insight reports and statistical analysis, the organizer can understand the participants' preferences, discussion hotspots, etc., and provide a basis for planning and improving the next meeting; improve user experience and satisfaction: with accurate data analysis and insights, the organizer can optimize meeting planning and provide a better user experience based on the needs and feedback of the participants, thereby improving the satisfaction of the participants.
[0085] like Figure 5 As shown, generating personalized conference recommendation information based on sentiment incremental analysis information, user behavior incremental analysis information, and topic incremental analysis information may include the following steps:
[0086] Step S510: performing comprehensive evaluation processing on the sentiment incremental analysis information, the user behavior incremental analysis information, and the topic incremental analysis information based on a preset personalized recommendation module to obtain comprehensive evaluation information;
[0087] Step S520 : Obtaining personalized conference recommendation information based on the preset conference recommendation strategy set and comprehensive evaluation information.
[0088] For steps S510 to S520, in the process of generating personalized conference recommendation information based on the sentiment incremental analysis information, user behavior incremental analysis information, and topic incremental analysis information, the sentiment incremental analysis information, user behavior incremental analysis information, and topic incremental analysis information are first comprehensively evaluated based on a pre-set personalized recommendation module to obtain comprehensive evaluation information; subsequently, personalized conference recommendation information can be matched based on a pre-set conference recommendation strategy set and comprehensive evaluation information. Through the above technical solution, with accurate data analysis and insights, the organizer can optimize conference planning and provide a better user experience based on the needs and feedback of the participants, thereby improving the satisfaction of the participants.
[0089] For example, in the insurance business field, based on the preset meeting recommendation strategy set and comprehensive evaluation information, the process of obtaining personalized meeting recommendation information may include but is not limited to the following situations: real-time topic popularity changes (such as a sudden increase in attention to "Product B") trigger the recommendation system to prioritize pushing relevant materials (such as PPT and case documents of Product B). Dynamic adjustment of the agenda: If it is detected that the discussion time of a certain topic exceeds the preset time (such as "technical dispute" lasting 30 minutes), the system suggests that the host extend the session or arrange a subsequent special meeting. Based on the user's emotional trend (such as the accumulation of negative emotions), the soothing strategy (such as inserting a break reminder, switching to a light topic) is automatically triggered. Or, in the medical field, if medical staff detect that the discussion time of a certain topic exceeds the preset time (such as "treatment plan determination process" lasting 30 minutes) during the discussion of the patient's condition, the system will also suggest that the host extend the session or arrange a subsequent special meeting.
[0090] like Figure 6 As shown, the conference recommendation strategy set includes multiple conference recommendation strategies, each of which carries an evaluation attribute value. Based on the preset conference recommendation strategy set and comprehensive evaluation information, obtaining personalized conference recommendation information may include the following steps:
[0091] Step S521 , matching the comprehensive evaluation information with the evaluation attribute value of each conference recommendation strategy to obtain the target conference recommendation strategy;
[0092] Step S522: Determine the target conference recommendation strategy as personalized conference recommendation information.
[0093] For steps S521 to S522, in the process of obtaining personalized conference recommendation information based on the preset conference recommendation strategy set and comprehensive evaluation information, the comprehensive evaluation information is first matched with the evaluation attribute value of each conference recommendation strategy to obtain the target conference recommendation strategy, and then the target conference recommendation strategy can be used to determine the personalized conference recommendation information. Through the above technical solution, the corresponding personalized conference recommendation information can be determined from the conference recommendation strategy set.
[0094] It is worth noting that by matching the comprehensive evaluation information with the evaluation attribute values of each conference recommendation strategy, the target conference recommendation strategy can be obtained. Subsequently, the target conference recommendation strategy can be determined as personalized conference recommendation information to optimize conference planning, provide a better user experience, and improve participant satisfaction.
[0095] like Figure 7 As shown, after generating personalized conference recommendation information based on sentiment incremental analysis information, user behavior incremental analysis information, and topic incremental analysis information, the following steps may be included:
[0096] Step S610: verifying the personalized conference recommendation information to obtain a verification feedback value;
[0097] Step S620: When the verification feedback value is less than a preset verification threshold, the personalized conference recommendation information is updated.
[0098] For steps S610 to S620, after generating personalized meeting recommendation information based on the sentiment incremental analysis information, user behavior incremental analysis information and topic incremental analysis information, the personalized meeting recommendation information can be verified to obtain a verification feedback value, and when the verification feedback value is less than a pre-set verification threshold, the personalized meeting recommendation information will be updated; and when the verification feedback value is not less than the pre-set verification threshold, the personalized meeting recommendation information will remain unchanged.
[0099] It is worth noting that after generating personalized conference recommendation information, the personalized conference recommendation information can be verified to obtain a verification feedback value. Subsequently, when the verification feedback value is less than the pre-set verification threshold, the personalized conference recommendation information can be updated so that the personalized conference recommendation information can be adjusted in real time according to the user's perception, optimize conference planning, provide a better user experience, and improve the satisfaction of participants.
[0100] In addition, if Figure 8 As shown, an embodiment of the present application further provides a data analysis device 10, the device comprising:
[0101] The acquisition unit 100 is used to acquire original conference data;
[0102] The preprocessing unit 200 is used to preprocess the original conference data to obtain preprocessed conference data;
[0103] The first analysis unit 300 is used to perform streaming analysis on the conference pre-processed data based on the pre-trained streaming data mining model to obtain preliminary sentiment analysis information, preliminary user behavior analysis information, and preliminary topic analysis information;
[0104] The second analysis unit 400 is configured to perform incremental analysis on the preliminary sentiment analysis information, the preliminary user behavior analysis information, and the preliminary topic analysis information based on a pre-trained incremental data mining model, to obtain incremental sentiment analysis information corresponding to the preliminary sentiment analysis information, incremental user behavior analysis information corresponding to the preliminary user behavior analysis information, and incremental topic analysis information corresponding to the preliminary topic analysis information;
[0105] The construction unit 500 is used to generate personalized conference recommendation information based on the sentiment incremental analysis information, the user behavior incremental analysis information and the topic incremental analysis information.
[0106] It should be noted that in the process of data analysis, the original data of the meeting is first obtained, and then the original data of the meeting can be pre-processed to obtain the pre-processed data of the meeting. Then, based on the pre-trained streaming data mining model, the pre-processed data of the meeting is subjected to streaming analysis to obtain preliminary analysis information of sentiment, preliminary analysis information of user behavior, and preliminary analysis information of topic; then, based on the pre-trained incremental data mining model, the preliminary analysis information of sentiment, preliminary analysis information of user behavior, and preliminary analysis information of topic are incrementally analyzed to obtain incremental analysis information of sentiment, incremental analysis information of user behavior, and incremental analysis information of topic; finally, personalized meeting recommendation information can be obtained based on the incremental analysis information of sentiment, incremental analysis information of user behavior, and incremental analysis information of topic. Through the above technical solution, streaming analysis and incremental analysis of the pre-processed data of the meeting can more accurately evaluate the effect of online meetings, which is conducive to the planning and improvement of online meetings.
[0107] The specific implementation of the data analysis device 10 is basically the same as the specific embodiment of the above-mentioned data analysis method, and will not be repeated here.
[0108] In addition, if Figure 9 As shown, an embodiment of the present application further provides an electronic device 700 , which includes: a memory 720 , a processor 710 , and a computer program stored in the memory 720 and executable on the processor 710 .
[0109] The processor 710 and the memory 720 may be connected via a bus or other means.
[0110] The non-transitory software programs and instructions required to implement the data analysis methods of the above embodiments are stored in the memory 720 , and when executed by the processor 710 , the data analysis methods of the above embodiments are performed.
[0111] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.
[0112] In addition, an embodiment of the present application also provides a computer-readable storage medium, which stores computer-executable instructions, and the computer-executable instructions are executed by a processor 710 or a controller, for example, by a processor 710 in the above-mentioned device embodiment, so that the above-mentioned processor 710 can execute the data analysis method in the above-mentioned embodiment.
[0113] The above embodiments may be used in combination, and modules with the same name in different embodiments may be the same or different.
[0114] The foregoing description describes specific embodiments of the present application, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in an order different from that described in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0115] The various embodiments in this application are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the device, equipment, and computer-readable storage medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simple. For relevant portions, refer to the descriptions of the method embodiments.
[0116] The apparatus, device, computer-readable storage medium and method provided in the embodiments of the present application correspond to each other. Therefore, the apparatus, device and non-volatile computer storage medium also have similar beneficial technical effects as the corresponding method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the corresponding apparatus, device and computer storage medium will not be repeated here.
[0117] In the 1990s, technological improvements could be clearly distinguished as either hardware improvements (for example, improvements to circuit structures like diodes, transistors, and switches) or software improvements (improvements to process flows). However, with the advancement of technology, many process flow improvements today can now be considered direct improvements to hardware circuit structures. Designers almost always create the corresponding hardware circuit structure by programming the improved process flow into the hardware circuit. Therefore, it cannot be said that a process flow improvement cannot be implemented using hardware modules. For example, a programmable logic device (PLD), such as a field programmable gate array (FPGA), is an integrated circuit whose logical function is determined by user programming. Designers can "integrate" a digital system on a PLD through their own programming, without having to hire a chip manufacturer to design and manufacture a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly performed using "logic compiler" software. This is similar to the software compilers used during program development. Before compilation, the original code must be written in a specific programming language, called a hardware description language (HDL). There are many HDLs, including ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art will also appreciate that simply programming a method flow in one of these hardware description languages and programming it into an integrated circuit can easily create a hardware circuit that implements the logic method flow.
[0118] The controller can be implemented in any suitable manner. For example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also know that in addition to implementing the controller in a purely computer-readable program code manner, it is entirely possible to implement the same function in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be considered as structures within the hardware component. Or even, the devices for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.
[0119] The systems, devices, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
[0120] For the convenience of description, the above devices are described as being divided into various units according to their functions. Of course, when implementing the embodiments of the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.
[0121] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the embodiments of the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0122] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0123] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.
[0124] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.
[0125] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.
[0126] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.
[0127] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.
[0128] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.
[0129] In the embodiments of the present application, "at least one" refers to one or more, and "more" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can represent: a, b, c, a and b, a and c, b and c or a and b and c, where a, b, c can be single or multiple.
[0130] Embodiments of the present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. Embodiments of the present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communications network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.
[0131] The various embodiments in this application are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiment is generally similar to the method embodiment, so the description is relatively simple. For relevant parts, refer to the partial description of the method embodiment.
[0132] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included within the scope of the claims of the present application.
Claims
1. A data analysis method, characterized in that: include: Obtain original meeting data; Preprocessing the original conference data to obtain preprocessed conference data; Performing streaming analysis on the conference preprocessed data based on a pre-trained streaming data mining model to obtain preliminary sentiment analysis information, preliminary user behavior analysis information, and preliminary topic analysis information; Based on the pre-trained incremental data mining model, incremental analysis processing is performed on the preliminary emotion analysis information, the preliminary user behavior analysis information, and the preliminary topic analysis information, respectively, to obtain incremental emotion analysis information corresponding to the preliminary emotion analysis information, incremental user behavior analysis information corresponding to the preliminary user behavior analysis information, and incremental topic analysis information corresponding to the preliminary topic analysis information; Personalized conference recommendation information is generated based on the sentiment incremental analysis information, the user behavior incremental analysis information, and the topic incremental analysis information.
2. The data analysis method according to claim 1, characterized in that The preprocessing of the original conference data to obtain preprocessed conference data includes: Performing data cleaning on the original meeting data to obtain valid meeting data; Formatting the valid conference data to obtain formatted conference data; The formatted conference data is aggregated based on a preset sliding time window to obtain the conference pre-processed data.
3. The data analysis method according to claim 1, wherein: The pre-trained streaming data mining model performs streaming analysis on the conference pre-processed data to obtain preliminary sentiment analysis information, preliminary user behavior analysis information, and preliminary topic analysis information, including: determining multimodal data, user behavior data, and text information from the conference preprocessed data; Performing clustering processing on the multimodal data based on the streaming data mining model to obtain the preliminary sentiment analysis information; Performing clustering processing on the user behavior data based on the streaming data mining model to obtain preliminary analysis information of the user behavior; The topic distribution analysis process is performed on the speech text information based on the streaming data mining model to obtain the preliminary analysis information of the topic.
4. The data analysis method according to claim 1, wherein: The pre-trained incremental data mining model performs incremental analysis on the sentiment preliminary analysis information, the user behavior preliminary analysis information, and the topic preliminary analysis information, respectively, to obtain sentiment incremental analysis information corresponding to the sentiment preliminary analysis information, user behavior incremental analysis information corresponding to the user behavior preliminary analysis information, and topic incremental analysis information corresponding to the topic preliminary analysis information, including: Performing incremental adjustment processing on the preliminary sentiment analysis information based on the incremental data mining model to obtain the incremental sentiment analysis information; Performing incremental adjustment processing on the preliminary analysis information of user behavior based on the incremental data mining model to obtain the incremental analysis information of user behavior; Incremental adjustment processing is performed on the topic preliminary analysis information based on the incremental data mining model to obtain the topic incremental analysis information.
5. The data analysis method according to claim 1, wherein: Generating personalized conference recommendation information based on the sentiment incremental analysis information, the user behavior incremental analysis information, and the topic incremental analysis information includes: Performing a comprehensive evaluation process on the sentiment incremental analysis information, the user behavior incremental analysis information, and the topic incremental analysis information based on a preset personalized recommendation module to obtain comprehensive evaluation information; The personalized conference recommendation information is obtained based on a preset conference recommendation strategy set and the comprehensive evaluation information.
6. The data analysis method according to claim 5, characterized in that: The conference recommendation strategy set includes a plurality of conference recommendation strategies, each of which carries an evaluation attribute value. The personalized conference recommendation information is obtained based on the preset conference recommendation strategy set and the comprehensive evaluation information, including: Matching the comprehensive evaluation information with the evaluation attribute value of each conference recommendation strategy to obtain a target conference recommendation strategy; The target conference recommendation strategy is determined as the personalized conference recommendation information.
7. The data analysis method according to claim 1, characterized in that: After generating personalized conference recommendation information based on the sentiment incremental analysis information, the user behavior incremental analysis information, and the topic incremental analysis information, the method further includes: Performing verification processing on the personalized conference recommendation information to obtain a verification feedback value; When the verification feedback value is less than a preset verification threshold, the personalized conference recommendation information is updated.
8. A data analysis device, characterized in that: The device comprises: An acquisition unit, used to acquire original conference data; A preprocessing unit, configured to preprocess the original conference data to obtain preprocessed conference data; A first analysis unit is configured to perform streaming analysis on the conference preprocessed data based on a pre-trained streaming data mining model to obtain preliminary sentiment analysis information, preliminary user behavior analysis information, and preliminary topic analysis information; a second analysis unit, configured to perform incremental analysis processing on the preliminary sentiment analysis information, the preliminary user behavior analysis information, and the preliminary topic analysis information based on a pre-trained incremental data mining model, to obtain incremental sentiment analysis information corresponding to the preliminary sentiment analysis information, incremental user behavior analysis information corresponding to the preliminary user behavior analysis information, and incremental topic analysis information corresponding to the preliminary topic analysis information; A construction unit is used to generate personalized conference recommendation information based on the sentiment incremental analysis information, the user behavior incremental analysis information and the topic incremental analysis information.
9. An electronic device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the data analysis method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium storing computer-executable instructions, characterized in that: The computer-executable instructions are used to execute the data analysis method according to any one of claims 1 to 7.