Sports big data accurate decision support system
By using the sports big data precision decision support system for data cleaning, verification, encryption, and quality management, the problem of data loss or distortion has been solved, ensuring the integrity and accuracy of the data and providing timely and accurate support for decision-makers.
Patent Information
- Application Number
- CN202410914599.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-09
- Publication Date
- 2024-11-12
AI Technical Summary
Existing sports big data analysis systems face the risk of data loss or distortion in their data extraction modules due to the diversity and complexity of data sources, especially when the quality of data sources varies, resulting in inaccurate analysis results.
A sports big data precision decision support system was designed, including data acquisition, extraction, storage, decision support, and user interface interaction modules. Through data cleaning, verification, encryption, backup, and quality management, the integrity and accuracy of the data are ensured, and a big data analysis engine and semantic understanding model are used for in-depth analysis and sentiment detection.
It effectively addresses the risk of data loss or distortion, ensuring the reliability and accuracy of data quality, and providing decision-makers with comprehensive, accurate, and timely support.
Smart Images

Figure CN118939722A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of big data and network information technology, and in particular to a sports big data accurate decision support system. Background Art
[0002] The sports big data precision decision support system is a system based on big data technology and analysis methods to provide comprehensive, accurate and timely data support and decision support for the sports field. Existing big data analysis solutions have many defects. For example, when processing big data, a large amount of data needs to be contextualized and semantically analyzed, which brings certain challenges to sentiment analysis and decision support.
[0003] Existing publication number CN116629275A discloses an intelligent decision support system and method based on big data. The system includes: a data extraction module for extracting data to be analyzed from a big data source; a data analysis module for performing semantic understanding on the data to be analyzed to obtain a multi-granularity semantic understanding feature vector; and a text emotion detection module for determining whether the text has positive emotions, the text has negative emotions, or the text has neutral emotions based on the multi-granularity semantic understanding feature vector. In this way, the semantic understanding model based on deep learning performs semantic analysis on the text data, thereby performing emotion detection of the text semantics, so as to provide decision makers with more accurate decision-making basis.
[0004] However, the diversity and complexity of data sources in the above-mentioned big data-based intelligent decision support system and method may cause challenges in data integration and standardization for the data extraction module. There may be a risk of data loss or distortion during the data extraction process, especially when the quality of data sources is uneven, resulting in inaccurate analysis results. Summary of the invention
[0005] The purpose of the present invention is to provide a sports big data accurate decision support system, which solves the risk of data loss or distortion in the data extraction process, especially when the quality of data sources is uneven, resulting in inaccurate analysis results.
[0006] To achieve the above-mentioned purpose, the present invention provides a sports big data precision decision support system, comprising a data extraction module, a data acquisition module, a data storage module, a data decision support module and a user interface interaction module, wherein the data extraction module is connected to the data acquisition module, the data storage module is connected to the data extraction module, the data decision support module is connected to the data storage module, and the user interface interaction module is connected to the data decision support module;
[0007] The data collection module is used to collect data from various channels and scenarios, including basic information of athletes, training data, competition data, injury data, user physical fitness, physical health data, tracking resource purchase and sale, event activities and professional training;
[0008] The data extraction module is used to extract various types of data related to sports decision-making from the collected data, and automatically perform data cleaning and verification during the data extraction process to identify and correct errors, missing items and duplicate items in the data;
[0009] The data storage module is used to receive data from the data extraction module, store it in a database, and use data quality management tools to perform quality assessment, monitoring and reporting on the data;
[0010] The data decision support module is used to obtain data from the data storage module, process and analyze the data using a big data analysis engine, and present the data analysis results to the decision maker;
[0011] The user interface interaction module is used to interact with the data decision support module to provide a user interface to display analysis results and receive user input.
[0012] Wherein, the data extraction module includes a data source interface unit and a data cleaning unit, the data source interface unit is connected to the data acquisition module, and the data cleaning unit is connected to the data source interface unit;
[0013] The data source interface unit is used to provide a variety of data source interfaces to cope with data from different sources and formats;
[0014] The data cleaning unit is used to automatically clean and verify the extracted data to identify and correct errors, omissions and duplications in the data.
[0015] Wherein, the data extraction module further includes a data verification unit, and the data verification unit is connected to the data cleaning unit;
[0016] The data verification unit is used to ensure the security of data transmission by using data encryption technology, and to ensure the integrity and accuracy of data by using data verification algorithm.
[0017] Wherein, the data storage module includes a database unit and a data backup unit, the database unit is connected to the data verification unit, and the data backup unit is connected to the database unit;
[0018] The database unit is used to store the data obtained from the data verification unit and support data query and analysis;
[0019] The data backup unit is used to regularly back up the data of the database unit and establish a data recovery mechanism to cope with the risk of data loss or damage.
[0020] Wherein, the data storage module further comprises a data quality management unit, and the data quality management unit is connected to the database unit;
[0021] The data quality management unit is used to use data quality management tools to evaluate, monitor and report data quality to ensure that data quality meets requirements.
[0022] Wherein, the data decision support module includes a data analysis engine unit and a semantic understanding model unit, the data analysis engine unit is connected to the database unit, and the semantic understanding model unit is connected to the data analysis engine unit;
[0023] The data analysis engine unit is used to analyze and mine the data of the database unit using a big data analysis engine;
[0024] The semantic understanding model unit is used to develop or adopt a semantic understanding model suitable for the sports field based on the characteristics of the sports field, and to perform in-depth semantic analysis and sentiment detection on text data.
[0025] Wherein, the data decision support module further comprises a visualization unit, and the visualization unit is connected to the semantic understanding model unit;
[0026] The visualization unit is used to display the data analysis results to the decision maker using visualization tools, so as to help the decision maker understand the data more intuitively and make decisions.
[0027] Wherein, the user interface interaction module includes an interface unit and a reporting unit, the interface unit is connected to the visualization unit, and the reporting unit is connected to the semantic understanding model unit;
[0028] The interface unit is used for the user to interact with the system;
[0029] The reporting unit is used to generate customized data reports and analysis results according to user needs.
[0030] The present invention provides a sports big data precision decision support system, wherein the data extraction module establishes a connection with the data acquisition module to extract the required sports-related data, and the extracted data will be sent to the data storage module, which receives the data from the data extraction module and stores it in a high-performance database, and implements a data backup and recovery mechanism to ensure the integrity and availability of the data, wherein the data decision support module obtains the data from the data storage module, processes and analyzes the data using a big data analysis engine, and integrates the data with a semantic understanding model to perform in-depth semantic analysis and sentiment detection on text data, wherein the user interface interaction module interacts with the data decision support module to provide a user-friendly interface to display analysis results and receive user input, and collects user feedback, and transmits this information to other modules for improvement and optimization, which can effectively solve the risk of data loss or distortion that may exist in the data extraction process, ensure the reliability and accuracy of data quality, and provide decision makers with comprehensive, accurate and timely decision support. BRIEF DESCRIPTION OF THE DRAWINGS
[0031] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below.
[0032] Figure 1 It is a structural block diagram of the sports big data precise decision support system according to the first embodiment of the present invention.
[0033] Figure 2 It is a structural block diagram of the data extraction module of the first embodiment of the present invention.
[0034] Figure 3 It is a structural block diagram of a data storage module according to a first embodiment of the present invention.
[0035] Figure 4 It is a structural block diagram of a data decision support module according to the second embodiment of the present invention.
[0036] Figure 5 It is a structural block diagram of a user interface interaction module according to a second embodiment of the present invention.
[0037] Figure 6 It is a structural block diagram of the sports big data accurate decision support system of the third embodiment of the present invention.
[0038] In the figure: 101-data extraction module, 102-data acquisition module, 103-data storage module, 104-data decision support module, 105-user interface interaction module, 106-data source interface unit, 107-data cleaning unit, 108-data verification unit, 109-database unit, 110-data backup unit, 111-data quality management unit, 201-data analysis engine unit, 202-semantic understanding model unit, 203-visualization unit, 204-interface unit, 205-report unit, 206-feedback unit, 301-protection module. DETAILED DESCRIPTION
[0039] Embodiments of the present invention are described in detail below. Examples of the embodiments are shown in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, but should not be construed as limiting the present invention.
[0040] The first embodiment of the present application is:
[0041] See also Figures 1 to 3 ,in, Figure 1 It is a structural block diagram of the sports big data precise decision support system according to the first embodiment of the present invention. Figure 2 is a structural block diagram of the data extraction module 101 according to the first embodiment of the present invention. Figure 3 It is a structural block diagram of the data storage module 103 of the first embodiment of the present invention. The present invention provides a sports big data precision decision support system: including a data extraction module 101, a data acquisition module 102, a data storage module 103, a data decision support module 104 and a user interface interaction module 105, the data extraction module 101 includes a data source interface unit 106, a data cleaning unit 107 and a data verification unit 108, the data storage module 103 includes a database unit 109, a data backup unit 110 and a data quality management unit 111, and the above-mentioned scheme solves the risk of data loss or distortion in the data extraction process, especially when the quality of the data source is uneven, resulting in inaccurate analysis results. It can be understood that the above-mentioned scheme can be used for decision support and can also be used to solve data security problems.
[0042] For this specific implementation, the data storage module 103 is connected to the data extraction module 101, the data decision support module 104 is connected to the data storage module 103, and the user interface interaction module 105 is connected to the data decision support module 104;
[0043] The data collection module 102 is used to collect data from various channels and scenarios, including basic information of athletes, training data, competition data, injury data, user physical fitness, physical health data, tracking resource purchase and sale, event activities and professional training;
[0044] The data extraction module 101 is used to extract various types of data related to sports decision-making from the collected data, and automatically perform data cleaning and verification during the data extraction process to identify and correct errors, missing items and duplicate items in the data;
[0045] The data storage module 103 is used to receive data from the data extraction module 101, store it in a database, and use data quality management tools to perform quality assessment, monitoring and reporting on the data;
[0046] The data decision support module 104 is used to obtain data from the data storage module 103, process and analyze the data using a big data analysis engine, and present the data analysis results to the decision maker;
[0047] The user interface interaction module 105 is used to interact with the data decision support module 104 and provide a user interface to display analysis results and receive user input.
[0048] The data acquisition module 102 collects sports-related data through various channels, including the physique, physical fitness, training, and competition data of athletes, the organization and participation of events, the distribution and utilization of sports resources, as well as market trends, user feedback, etc. These data come from different data sources, such as sensors, game videos, social media, market research, etc. The data extraction module 101 establishes a connection with the data acquisition module 102 to extract the required sports-related data. The extracted data will be sent to the data storage module 103. The data storage module 103 receives data from the data extraction module 101 and stores it in a high-performance database, and implements a data backup and recovery mechanism to ensure the integrity and availability of the data. The data decision support module 104 obtains data from the data storage module 103 and uses a big data analysis engine to process and analyze it. The user interface interaction module 105 interacts with the data decision support module 104 to provide a user-friendly interface to display analysis results and receive user input.
[0049] The data source interface unit 106 is connected to the data acquisition module 102, and the data cleaning unit 107 is connected to the data source interface unit 106;
[0050] The data source interface unit 106 is used to provide a variety of data source interfaces to cope with data from different sources and formats;
[0051] The data cleaning unit 107 is used to automatically clean and verify the extracted data to identify and correct errors, omissions and duplications in the data.
[0052] In order to deal with data from different sources and formats, the data source interface unit 106 provides a variety of data source interfaces, such as API interface, database connection, file parsing, etc. The data cleaning unit 107 first performs a preliminary analysis on the extracted data to identify possible data quality problems, such as errors, missing and duplicate items, through statistical analysis, data visualization, data comparison, etc. According to the results of the preliminary analysis, define the strategy and rules for data cleaning, including determining the specific methods and thresholds for processing missing values, outliers, duplicate values, etc., identifying the types and distribution of missing values in the data set, and selecting appropriate methods to process missing values according to business needs and data characteristics, such as deleting records with missing values, using interpolation or filling methods (such as mean, median, mode, etc.) to estimate missing values, and then cleaning the data. Missing values, or fill in according to common sense in a specific field, identify outliers in the data, which may be far away from other data points or not meet the expected business rules, and process outliers. You can choose to remove or replace them with other values (such as median, mode, etc.), or conduct more in-depth analysis based on specific situations, identify duplicate records in the data, and use methods such as "delete duplicate values" function, conditional formatting identification method, advanced filtering method or function method (such as COUNTIF function) to remove or merge duplicate records. During or after data cleaning, perform data verification to ensure the accuracy, completeness and consistency of the data, including data format verification, business rule verification, etc. If necessary, convert the data, such as unit conversion, data format conversion, etc., to meet the requirements of subsequent analysis or system.
[0053] Secondly, the data checking unit 108 is connected to the data cleaning unit 107;
[0054] The data verification unit 108 is used to ensure the security of data transmission by using data encryption technology, and to ensure the integrity and accuracy of data by using data verification algorithm.
[0055] The encryption method uses symmetric encryption: the same key is used for encryption and decryption. Common algorithms include AES, DES, 3DES, etc. The security of this method depends on the length and randomness of the key. Or asymmetric encryption is used: the public key is used for encryption and the private key is used for decryption. Common algorithms include RSA, ECC, etc. This method provides higher security and is suitable for scenarios where secure key exchange is required. Select the appropriate encryption algorithm and key length according to the sensitivity of the data and the security requirements of the transmission environment. Encrypt the data by category, and use stronger encryption algorithms and longer keys for confidential and sensitive data. Strengthen the management and protection of keys, and use password protection, physical protection, decentralized protection and other methods to avoid key leakage. The verification algorithm uses a checksum: divide the data into multiple sub-units and add them, and then complement the result. If the checksum calculated by the receiving end is the same as that of the sending end, it means that there is no error in the data, or use a cyclic redundancy check (CRC): a more complex verification algorithm that calculates the check code through polynomial division and verifies it at the receiving end. CRC has a higher error detection capability. The checksum is calculated before the data is sent and appended to the end of the data packet. The checksum is recalculated after the data is received and compared with the checksum provided by the sender. If the checksum does not match, it indicates that an error or tampering has occurred during the data transmission process, and appropriate error handling measures need to be taken. The use of data encryption technology and data verification algorithms can effectively ensure the security of data transmission and the integrity and accuracy of data.
[0056] At the same time, the database unit 109 is connected to the data verification unit 108, and the data backup unit 110 is connected to the database unit 109;
[0057] The database unit 109 is used to store the data obtained from the data verification unit 108 and support data query and analysis;
[0058] The data backup unit 110 is used to regularly back up the data in the database unit 109 and establish a data recovery mechanism to cope with the risk of data loss or damage.
[0059] The database unit 109 uses a high-performance database system (such as a distributed database, a NoSQL database, etc.) to store a large amount of data and supports efficient data query and analysis. The data backup unit 110 is used to deal with the risk of data loss or damage.
[0060] In addition, the data quality management unit 111 is connected to the database unit 109;
[0061] The data quality management unit 111 is used to use data quality management tools to evaluate, monitor and report data quality to ensure that data quality meets requirements.
[0062] The data quality management unit 111 evaluates the integrity of the data by checking whether there are missing values in the data, wherein statistical methods, visualization methods or data mining techniques are used to discover and process missing values, and the accuracy of the data is evaluated by verifying the consistency of the data with the actual situation, wherein expert evaluation, data comparison, logical verification and other methods are used to ensure the accuracy and reliability of the data, and to check whether there are duplicate records or duplicate values in the data to ensure the uniqueness of the data, wherein data sorting, deduplication, aggregation and other methods are used for evaluation and processing, and the data is compared with accurate standard data to evaluate the accuracy of the data, and through data comparison and evaluation, it is ensured that the data meets the required accuracy and precision requirements. Data monitoring tools (such as Splunk, Graylog, etc.) are used to monitor the data in real time, timely discover data quality problems and take corresponding treatment measures. Data quality management tools (such as Data quality manager (DQM), Dataprofiling, etc.) are used to manage and monitor data quality in an all-round way. Statistical analysis is performed on the log data generated by the system during operation to obtain the health status of the system and ensure the stable operation of the data quality control system. The data quality management team will submit data quality assessment reports regularly (such as monthly), summarize the data quality situation of the month, and adjust the inspection strategy for the level of each topic based on the changes in the frequency of data quality issues.
[0063] A sports big data precision decision support system using the present embodiment cleans and verifies the collected data through the data cleaning unit 107, ensures the integrity and accuracy of the transmitted data through the data verification unit 108, and evaluates and monitors the data quality through the data quality management unit 111 to ensure that the data quality meets the requirements. Thus, the risk of data loss or distortion that may exist in the data extraction process is effectively solved, the reliability and accuracy of the data quality are ensured, and comprehensive, accurate and timely decision support is provided to decision makers.
[0064] The second embodiment of the present application is:
[0065] Based on the first embodiment, please refer to Figure 4 and Figure 5 ,in, Figure 4 It is a structural block diagram of the data decision support module 104 according to the second embodiment of the present invention. Figure 51 is a structural block diagram of the user interface interaction module 105 of the second embodiment of the present invention. The data decision support module 104 of this embodiment includes a data analysis engine unit 201, a semantic understanding model unit 202 and a visualization unit 203, and the user interface interaction module 105 includes an interface unit 204, a report unit 205 and a feedback unit 206.
[0066] For this specific implementation, the data analysis engine unit 201 is connected to the database unit 109, and the semantic understanding model unit 202 is connected to the data analysis engine unit 201;
[0067] The data analysis engine unit 201 is used to analyze and mine the data of the database unit 109 using a big data analysis engine;
[0068] The semantic understanding model unit 202 is used to develop or adopt a semantic understanding model suitable for the sports field according to the characteristics of the sports field, and to perform in-depth semantic analysis and sentiment detection on text data.
[0069] The data analysis engine unit 201 uses the distributed computing capabilities of the big data analysis engine (such as MapReduce, Spark's RDD, etc.) to quickly and efficiently analyze and mine massive data to extract valuable information and insights. The semantic understanding model unit 202 develops or adopts a semantic understanding model suitable for the sports field based on the characteristics of the sports field. These models are usually based on natural language processing (NLP) technology, which can recognize words, phrases, sentences, etc., and perform in-depth analysis, interpretation and processing on them. The data extracted by the big data analysis engine is used as input, and the semantic understanding model is used to perform in-depth semantic analysis and sentiment detection on the text data. This includes tasks such as entity recognition, relationship extraction, and sentiment tendency analysis to obtain richer semantic information and sentiment tags. The analysis results of the big data analysis engine and the semantic understanding model are integrated to form a comprehensive and in-depth data analysis result. These results may include data association, trend prediction, sentiment tendency, etc.
[0070] Wherein, the visualization unit 203 is connected to the semantic understanding model unit 202;
[0071] The visualization unit 203 is used to display the data analysis results to the decision maker using visualization tools, so as to help the decision maker understand the data more intuitively and make decisions.
[0072] The visualization unit 203 uses visualization tools (such as Tableau, Power BI, D3.js, etc.) to display the data analysis results to decision makers in the form of charts, reports, etc. These visualization tools can convert complex data into intuitive and easy-to-understand graphics and images, helping decision makers to understand the data more intuitively and make decisions. Through the interactive functions provided by visualization tools (such as data drilling, interactive charts, etc.), decision makers can further explore and analyze data and discover the laws and trends behind the data. According to the data analysis results displayed by the visualization tools, decision makers can formulate or adjust corresponding strategies, plans or decisions.
[0073] Secondly, the interface unit 204 is connected to the visualization unit 203, and the reporting unit 205 is connected to the semantic understanding model unit 202;
[0074] The interface unit 204 is used for user interaction with the system;
[0075] The reporting unit 205 is used to generate customized data reports and analysis results according to user needs.
[0076] The interface unit 204 designs an intuitive and easy-to-use user interface to facilitate user interaction with the system. The report unit 205 generates customized data reports and analysis results according to user needs to meet the personalized needs of different users.
[0077] At the same time, the feedback unit 206 is used to collect users' experience and suggestions on the system to continuously improve and optimize system performance.
[0078] The feedback unit 206 collects user feedback and transmits this information to other modules for improvement and optimization.
[0079] Using a sports big data precision decision support system of this embodiment, the data analysis engine unit 201 and the semantic understanding model unit 202 integrate the analysis results of the big data analysis engine and the semantic understanding model to form a comprehensive and in-depth data analysis result. The analysis structure is displayed through the visualization unit 203, and the user interacts through the interface unit 204 to further explore and analyze the data and discover the rules and trends behind the data. According to the displayed data analysis results, the decision maker can formulate or adjust the corresponding strategy, plan or decision.
[0080] The third embodiment of the present application is:
[0081] Based on the second embodiment, please refer to Figure 6 ,in, Figure 63 is a structural block diagram of a sports big data accurate decision support system according to a third embodiment of the present invention. The sports big data accurate decision support system according to this embodiment further includes a protection module 301 .
[0082] For this specific implementation, the protection module 301 is connected to the data acquisition module 102, the data storage module 103, the data decision support module 104 and the user interface interaction module 105 respectively;
[0083] The protection module 301 is used to implement access control and authority management, data desensitization and encryption technology, and monitoring and auditing tools in the entire system.
[0084] The protection module implements strict access control and authority management mechanisms to ensure that only authorized users can access sensitive data. Sensitive data is desensitized and data encryption technology is used to protect the security of data during storage and transmission. Monitoring and auditing tools are used to monitor and record system operations and data access in real time to ensure that system operations comply with security specifications.
[0085] A sports big data precision decision support system using the present embodiment implements access control and authority management, data desensitization and encryption technology, as well as monitoring and auditing tools in the entire system to ensure data security and privacy protection.
[0086] What is disclosed above is only one or more preferred embodiments of the present application, and cannot be used to limit the scope of rights of the present application. Ordinary technicians in this field can understand that all or part of the processes of implementing the above embodiments and equivalent changes made according to the claims of the present application are still within the scope covered by the present application.
Claims
1. A sports big data accurate decision support system, including a data extraction module, It is characterized in that It also includes a data acquisition module, a data storage module, a data decision support module and a user interface interaction module, wherein the data extraction module is connected to the data acquisition module, the data storage module is connected to the data extraction module, the data decision support module is connected to the data storage module, and the user interface interaction module is connected to the data decision support module; The data collection module is used to collect data from various channels and scenarios, including basic information of athletes, training data, competition data, injury data, user physical fitness, physical health data, tracking resource purchase and sale, event activities and professional training; The data extraction module is used to extract various types of data related to sports decision-making from the collected data, and automatically perform data cleaning and verification during the data extraction process to identify and correct errors, missing items and duplicate items in the data; The data storage module is used to receive data from the data extraction module, store it in a database, and use data quality management tools to perform quality assessment, monitoring and reporting on the data; The data decision support module is used to obtain data from the data storage module, process and analyze the data using a big data analysis engine, and present the data analysis results to the decision maker; The user interface interaction module is used to interact with the data decision support module to provide a user interface to display analysis results and receive user input.
2. The sports big data accurate decision support system as claimed in claim 1, It is characterized in that The data extraction module includes a data source interface unit and a data cleaning unit, wherein the data source interface unit is connected to the data acquisition module, and the data cleaning unit is connected to the data source interface unit; The data source interface unit is used to provide a variety of data source interfaces to cope with data from different sources and formats; The data cleaning unit is used to automatically clean and verify the extracted data to identify and correct errors, omissions and duplications in the data.
3. The sports big data accurate decision support system as claimed in claim 2, It is characterized in that The data extraction module also includes a data verification unit, and the data verification unit is connected to the data cleaning unit; The data verification unit is used to ensure the security of data transmission by using data encryption technology, and to ensure the integrity and accuracy of data by using data verification algorithm.
4. The sports big data accurate decision support system as claimed in claim 3, It is characterized in that The data storage module includes a database unit and a data backup unit, the database unit is connected to the data verification unit, and the data backup unit is connected to the database unit; The database unit is used to store the data obtained from the data verification unit and support data query and analysis; The data backup unit is used to regularly back up the data of the database unit and establish a data recovery mechanism to cope with the risk of data loss or damage.
5. The sports big data accurate decision support system as claimed in claim 4, It is characterized in that The data storage module further comprises a data quality management unit, and the data quality management unit is connected to the database unit; The data quality management unit is used to use data quality management tools to evaluate, monitor and report data quality to ensure that data quality meets requirements.
6. The sports big data accurate decision support system as claimed in claim 4, It is characterized in that The data decision support module includes a data analysis engine unit and a semantic understanding model unit, wherein the data analysis engine unit is connected to the database unit, and the semantic understanding model unit is connected to the data analysis engine unit; The data analysis engine unit is used to analyze and mine the data of the database unit using a big data analysis engine; The semantic understanding model unit is used to develop or adopt a semantic understanding model suitable for the sports field based on the characteristics of the sports field, and to perform in-depth semantic analysis and sentiment detection on text data.
7. The sports big data accurate decision support system as claimed in claim 6, It is characterized in that The data decision support module further comprises a visualization unit, and the visualization unit is connected to the semantic understanding model unit; The visualization unit is used to display the data analysis results to the decision maker using visualization tools, so as to help the decision maker understand the data more intuitively and make decisions.
8. The sports big data accurate decision support system as claimed in claim 7, It is characterized in that The user interface interaction module includes an interface unit and a reporting unit, wherein the interface unit is connected to the visualization unit, and the reporting unit is connected to the semantic understanding model unit; The interface unit is used for the user to interact with the system; The reporting unit is used to generate customized data reports and analysis results according to user needs.
Citation Information
Cited By
Method and system for constructing data reaction for periodic table of data elements
CN119721220A
