Data processing method and device for data interface

By grouping user group characteristics and data adaptive model training, a personalized data statistics board is generated, which solves the shortcomings of data interface processing methods in the existing technology in user behavior analysis and data display, and improves the accuracy of data analysis and Practicality, supports corporate decision-making.

CN119046357APending Publication Date: 2024-11-29紫金诚征信有限公司
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202411134481.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-19
Publication Date
2024-11-29

AI Technical Summary

Technical Problem

The existing data interface processing methods have shortcomings in user behavior analysis, model optimization, data classification and display, which are difficult to meet the diverse needs of users, and lack in-depth analysis of data relationships and trends, resulting in intuitiveness and insight of the presentation results. insufficient.

Method used

By grouping historical user identifiers based on user group characteristics, initial model training and knowledge migration optimization are carried out to generate data source classification models; adaptive model training is carried out on the target data, determining the Kanban parameters, and generating data statistics Kanban through data fusion, and cached to the database.

Benefits of technology

Improve the accuracy and practicality of data analysis, supports scientific decision-making and business optimization of enterprises and organizations, and provides personalized analysis and in-depth data insights.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119046357A_ABST
    Figure CN119046357A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides a data processing method and device for a data interface, and the method comprises the steps: receiving target data sent by a data source, and determining a corresponding first billboard parameter according to a user identifier of the data source and a data source classification model; performing data analysis on the target data, determining a corresponding data type and a data size, performing model training on a preset adaptive model according to the data type and the data size to obtain a target data classification model after model training, and determining a corresponding second billboard parameter according to the output of the target data classification model; performing data fusion on the first Kanban parameter and the second Kanban parameter, inputting the fused parameters into a set data Kanban generation model to obtain a data statistics Kanban output by the data Kanban generation model, and caching the data statistics Kanban into a preset database; according to the invention, the accuracy and practicability of data analysis can be improved, and scientific decision and business optimization of enterprises and organizations are supported.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and in particular to a data processing method and device for a data interface. Background Art

[0002] In the context of modern information technology and data analysis, data interface processing methods have become an important tool for enterprises and organizations to optimize decision-making. With the diversification of data sources and the rapid growth of data volume, how to efficiently process and analyze this data to obtain valuable insights has become a key issue in the current technology field. Although existing technologies have made some progress in data interface processing, there are still many deficiencies and challenges in user behavior analysis, model optimization, data classification and display.

[0003] In terms of data display and dashboard generation, existing technologies mainly rely on preset templates and static displays. Although this method can provide basic data visualization functions, it has obvious deficiencies in the dynamic changes and personalized display of data. Users' needs for data display are often diverse and personalized, and existing technologies are difficult to provide customized display solutions based on users' specific needs and data characteristics. In addition, existing methods often lack in-depth analysis of data relationships and trends during data fusion and dashboard generation, resulting in insufficient intuitiveness and insight into the display results.

[0004] In summary, existing data interface processing methods still face many challenges and shortcomings in terms of user behavior analysis, model optimization, data classification and display. Summary of the invention

[0005] In response to the problems in the prior art, the present application provides a data processing method and device for a data interface, which can improve the accuracy and practicality of data analysis and support scientific decision-making and business optimization of enterprises and organizations.

[0006] In order to solve at least one of the above problems, the present application provides the following technical solutions:

[0007] In a first aspect, the present application provides a data processing method for a data interface, comprising:

[0008] Perform grouping operations on historical user identifiers according to user group characteristics, perform initial model training on each obtained user group, determine corresponding user behavior patterns, optimize the initial model through a preset knowledge transfer algorithm and the user behavior patterns, obtain a data source classification model after the model optimization, receive target data sent by the data source, and determine corresponding first dashboard parameters according to the user identifier of the data source and the data source classification model;

[0009] Performing data analysis on the target data to determine the corresponding data type and data size, performing model training on a preset adaptive model according to the data type and the data size to obtain a target data classification model after the model training, and determining the corresponding second dashboard parameters according to the output of the target data classification model;

[0010] The first dashboard parameter and the second dashboard parameter are data-fused and input into a set data dashboard generation model to obtain a data statistics dashboard output by the data dashboard generation model, and the data statistics dashboard is cached in a preset database.

[0011] Furthermore, the grouping operation of the historical user identifiers according to the user group characteristics, performing initial model training on each obtained user group, and determining the corresponding user behavior pattern includes:

[0012] Extracting implicit semantic association features between different user groups through a preset graph inference algorithm, and performing grouping operations on historical user identifiers through the implicit semantic association features;

[0013] The obtained user groups are represented by user feature vectorization and joint modeling and federated model training are performed, and the corresponding user behavior pattern is determined according to the output of the federated model.

[0014] Furthermore, the initial model is optimized by using a preset knowledge transfer algorithm and the user behavior pattern to obtain a data source classification model after the model optimization, including:

[0015] Using a preset knowledge transfer algorithm, implicit semantic association features in the graph are transferred to the initial model as a model optimization direction;

[0016] The initial model is automatically hyper-parameter optimized according to the user behavior pattern to obtain a data source classification model.

[0017] Further, the receiving target data sent by the data source and determining the corresponding first dashboard parameter according to the user identifier of the data source and the data source classification model include:

[0018] Receive target data sent by a data source, and perform normalization and formatting processing on the target data;

[0019] The user identifier in the target data after the normalization and formatting processing is extracted and input into the data source classification model to obtain the first dashboard parameter output by the data source classification model, wherein the first dashboard parameter at least includes the personalized analysis indicator corresponding to the current data source.

[0020] Further, the performing data analysis on the target data to determine the corresponding data type and data size includes:

[0021] Performing data format and data distribution analysis operations on the target data;

[0022] The corresponding data type and data size are determined according to the data format and the results of the respective analysis operations on the data.

[0023] Further, the performing model training on a preset adaptive model according to the data type and the data size to obtain a target data classification model after the model training, and determining corresponding second dashboard parameters according to an output of the target data classification model, includes:

[0024] Performing a data preprocessing operation on the target data according to the different data types, wherein the data preprocessing operation includes at least one of text noise reduction, image enhancement, and video framing;

[0025] Model training is performed according to an adaptive model corresponding to the data type and the data size, and the model is optimized through an automatic hyperparameter optimization algorithm to obtain a target data classification model, and corresponding second dashboard parameters are determined according to an output of the target data classification model, wherein the second dashboard parameters at least include a data analysis perspective corresponding to the current target data.

[0026] Furthermore, the first dashboard parameter and the second dashboard parameter are subjected to data fusion and then input into a setting data dashboard generation model to obtain a data statistics dashboard output by the data dashboard generation model, including:

[0027] The first signboard parameter and the second signboard parameter are fused into a unified feature vector by using a weighted fusion algorithm;

[0028] The unified feature vector is input into a set data dashboard generation model to obtain a data statistics dashboard output by the data dashboard generation model, wherein the data dashboard generation model is used to output a mapping relationship between the feature vector and a visualized data statistics dashboard.

[0029] In a second aspect, the present application provides a data processing device for a data interface, comprising:

[0030] A first dashboard parameter determination module is used to group historical user identifiers according to user group characteristics, perform initial model training on each obtained user group, determine corresponding user behavior patterns, optimize the initial model through a preset knowledge transfer algorithm and the user behavior pattern, obtain a data source classification model after the model optimization, receive target data sent by a data source, and determine corresponding first dashboard parameters according to the user identifier of the data source and the data source classification model;

[0031] a second dashboard parameter determination module, configured to perform data analysis on the target data to determine a corresponding data type and data size, perform model training on a preset adaptive model according to the data type and the data size, obtain a target data classification model after the model training, and determine a corresponding second dashboard parameter according to an output of the target data classification model;

[0032] The data dashboard generation module is used to perform data fusion on the first dashboard parameter and the second dashboard parameter and input them into a set data dashboard generation model to obtain the data statistics dashboard output by the data dashboard generation model, and cache the data statistics dashboard in a preset database.

[0033] In a third aspect, the present application provides 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 steps of the data processing method of the data interface when executing the program.

[0034] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the data processing method of the data interface.

[0035] In a fifth aspect, the present application provides a computer program product, comprising a computer program / instruction, which, when executed by a processor, implements the steps of the data processing method of the data interface.

[0036] It can be seen from the above technical scheme that the present application provides a data processing method and device for a data interface, which receives target data sent by a data source, determines a corresponding first dashboard parameter according to a user identifier of the data source and a classification model of the data source; performs data analysis on the target data to determine the corresponding data type and data size, performs model training on a preset adaptive model according to the data type and data size, obtains a target data classification model after model training, and determines a corresponding second dashboard parameter according to the output of the target data classification model; performs data fusion on the first dashboard parameter and the second dashboard parameter and inputs them into a set data dashboard generation model to obtain a data statistics dashboard output by the data dashboard generation model, and caches the data statistics dashboard in a preset database, thereby improving the accuracy and practicality of data analysis and supporting scientific decision-making and business optimization of enterprises and organizations. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] 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 will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0038] Figure 1 This is one of the flowcharts of the data processing method of the data interface in the embodiment of the present application;

[0039] Figure 2 This is a second flow chart of the data processing method of the data interface in the embodiment of the present application;

[0040] Figure 3 This is a third flow chart of the data processing method of the data interface in the embodiment of the present application;

[0041] Figure 4 This is a fourth flow chart of the data processing method of the data interface in the embodiment of the present application;

[0042] Figure 5 This is a fifth flow chart of the data processing method of the data interface in the embodiment of the present application;

[0043] Figure 6 This is a sixth flow chart of the data processing method of the data interface in the embodiment of the present application;

[0044] Figure 7 7 is a flow chart of a data processing method of a data interface in an embodiment of the present application;

[0045] Figure 8 A structural diagram of a data processing device for a data interface in an embodiment of the present application;

[0046] Fig. 9 It is a schematic diagram of the structure of an electronic device in an embodiment of the present application.

[0047] Reference numerals:

[0048] Electronic device 9600, central processing unit 9100, memory 9140, communication module 9110, input unit 9120, audio processor 9130, display 9160, power supply 9170, buffer memory 9141, application / function storage unit 9142, data storage unit 9143, driver program storage unit 9144, antenna 9111, speaker 9131, microphone 9132. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0050] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0051] In view of the problems existing in the prior art, the present application provides a data processing method and device for a data interface, which receives target data sent by a data source, determines a corresponding first dashboard parameter according to a user identifier of the data source and a classification model of the data source; performs data analysis on the target data to determine the corresponding data type and data size, performs model training on a preset adaptive model according to the data type and data size to obtain a target data classification model after model training, and determines a corresponding second dashboard parameter according to the output of the target data classification model; performs data fusion on the first dashboard parameter and the second dashboard parameter and inputs them into a set data dashboard generation model to obtain a data statistics dashboard output by the data dashboard generation model, and caches the data statistics dashboard in a preset database, thereby improving the accuracy and practicality of data analysis and supporting scientific decision-making and business optimization of enterprises and organizations.

[0052] In order to improve the accuracy and practicality of data analysis and support scientific decision-making and business optimization of enterprises and organizations, this application provides an embodiment of a data processing method of a data interface, see Figure 1 , the data processing method of the data interface specifically includes the following contents:

[0053] Step S101: grouping historical user identifiers according to user group characteristics, performing initial model training on each obtained user group, determining corresponding user behavior patterns, optimizing the initial model through a preset knowledge transfer algorithm and the user behavior patterns, obtaining a data source classification model after the model optimization, receiving target data sent by a data source, and determining corresponding first dashboard parameters according to the user identifier of the data source and the data source classification model;

[0054] Optionally, in this embodiment, in step S101, the system first groups historical user identifiers according to user group characteristics. User group characteristics may include information such as age, geographic location, interests and hobbies, and user identifiers are reasonably grouped based on these characteristics. The purpose of this process is to better capture the behavior patterns of different user groups, thereby improving the accuracy of the model.

[0055] Next, the initial model training is performed on each user group. The data of each user group is used to train an initial model, which is used to capture the user behavior patterns of each group. The training process usually uses machine learning algorithms such as support vector machines and random forests. These algorithms can extract features from user data and identify potential behavior patterns.

[0056] Once the initial model training is completed, the system will optimize the initial model through the preset knowledge transfer algorithm. The core of the knowledge transfer algorithm is to apply the knowledge learned in one field to another related field, which can effectively improve the performance of the model on new data. Specifically, the system will analyze the similarities between different user groups, transfer the behavior patterns of certain user groups to other groups, and optimize the initial model.

[0057] After optimization through knowledge transfer, the system obtains a more accurate data source classification model, which can better adapt to the characteristics of different user groups and improve the accuracy of prediction.

[0058] The system then receives the target data sent by the data source. The target data usually includes new user behavior information, such as click records, browsing history, etc. The system combines this data with the user identifier of the data source and determines the corresponding first dashboard parameters through the data source classification model.

[0059] The first dashboard parameters refer to key indicators predicted based on user behavior, such as user activity, purchase intention, etc. These parameters are used to generate personalized user interfaces and improve user experience. For example, for a certain type of user, the system may recommend specific products or services through dashboard parameters to increase conversion rates.

[0060] This solution effectively solves the problems of personalization and accuracy in user behavior prediction. By grouping users by their group characteristics, the system can build exclusive behavior models for different user groups. Through the knowledge transfer algorithm, the system can share effective behavior features across groups and improve the generalization ability of the model.

[0061] In terms of technical effects, the system improves the utilization efficiency and prediction accuracy of user data through model optimization. The initial model captures group characteristics, while knowledge transfer optimization improves the model's cross-group adaptability. Ultimately, the optimized data source classification model can provide accurate data support for personalized recommendations and user interface customization.

[0062] For example, suppose an e-commerce platform wants to make personalized recommendations based on user behavior. The system first groups users into groups, such as young users and elderly users. Initial models are trained for the two groups to capture their respective shopping habits. Then, through knowledge transfer, the trendy product preference characteristics of young users are partially transferred to the elderly user model in order to tap into potential consumption tendencies. Finally, after receiving the user's browsing history, the data source classification model can quickly generate a list of recommended products and a personalized interface to improve user satisfaction and purchase rate.

[0063] In summary, step S101 achieves accurate prediction of user behavior and personalized interface customization through user grouping, model training, knowledge transfer and classification model optimization. This solution not only improves the accuracy of the model, but also enhances the adaptability of the system among different user groups, providing a solid foundation for subsequent user experience optimization.

[0064] Step S102: performing data analysis on the target data to determine the corresponding data type and data size, performing model training on a preset adaptive model according to the data type and the data size to obtain a target data classification model after the model training, and determining the corresponding second dashboard parameters according to the output of the target data classification model;

[0065] Optionally, in this embodiment, in step S102, the system first performs data analysis on the target data to determine the data type and data size. The data type may include text, numerical values, images, etc., and the data size involves the scale and dimension of the data set. This analysis step is to ensure that subsequent processing can be optimized for different data features.

[0066] Next, the system trains the preset adaptive model based on the determined data type and size. An adaptive model is a machine learning model that can automatically adjust parameters and structure according to the characteristics of the input data. In this way, the model can adapt to data of different types and sizes more efficiently. For example, for text data, the model may use natural language processing technology, while for image data, a convolutional neural network (CNN) may be more appropriate.

[0067] During model training, the system will use the results of data analysis to adjust the model's hyperparameters and structure. For example, for large-scale data sets, the system may choose a distributed computing solution to improve training speed and efficiency. For complex data types, the number of layers or nodes in the model may be increased to improve its expressiveness.

[0068] After training the adaptive model, the system generates a target data classification model. This classification model can accurately classify and predict based on the characteristics of the input data. The core is to enable the model to handle specific data types and scales through targeted training, ensuring the accuracy and stability of the output results.

[0069] Subsequently, the system determines the corresponding second dashboard parameters based on the output of the target data classification model. Second dashboard parameters are key indicators extracted from the prediction results of the classification model to guide business decisions and optimize the user interface. For example, in an e-commerce platform, second dashboard parameters may include user preference categories, potential purchase items, etc., which can be used for personalized recommendations and inventory management.

[0070] The technical problem solved by this solution is mainly how to efficiently process and classify diverse target data. Traditional methods often require building a dedicated model for each data type, which is time-consuming and inflexible. Through adaptive model training, the system can uniformly process different data characteristics, improving efficiency and accuracy.

[0071] In terms of technical effects, through data analysis and adaptive model training, the system significantly improves the ability to classify and predict target data. The model can automatically adjust to different data types and scales to ensure the accuracy of the output results. At the same time, the extraction of the second dashboard parameters provides direct data support for business decisions, enhancing the practical application value of the system.

[0072] For example, suppose a financial institution needs to analyze user transaction data to predict potential risky customers. The system first analyzes the transaction data, determines that it is numerical data, and evaluates the data size. Then, it uses an adaptive model for training. The model may use a decision tree or a neural network to automatically adjust the structure according to the data characteristics. The target data classification model generated after training can accurately identify high-risk customers. Based on the model output, the system extracts the second dashboard parameters, such as "high-risk customer ratio" and "potential risk transactions", to provide decision support for financial institutions.

[0073] In summary, step S102 achieves efficient processing and classification of target data through data analysis, adaptive model training and dashboard parameter extraction.

[0074] Step S103: After data fusion of the first dashboard parameter and the second dashboard parameter, the data is input into a set data dashboard generation model to obtain a data statistics dashboard output by the data dashboard generation model, and the data statistics dashboard is cached in a preset database.

[0075] Optionally, in this embodiment, in step S103, the system first performs data fusion on the first dashboard parameter and the second dashboard parameter. This process involves integrating parameters from different models into a unified data set. Data fusion technology ensures compatibility and consistency between parameters through standardization, deduplication and completion. The purpose of this is to obtain a more comprehensive and accurate view in subsequent analysis.

[0076] Next, the fused parameters are input into the set data dashboard generation model. The data dashboard generation model is a tool for visualizing data, which can transform complex data sets into easy-to-understand graphs and tables. The model usually contains multiple modules such as data processing, graph generation, and layout design. Through the synergy of these modules, the system can provide users with an intuitive visualization interface.

[0077] In actual applications, the data dashboard generation model automatically selects the best visualization form based on the input parameters. For example, for trend data, the system may choose a line chart or an area chart, while for categorical data, a bar chart or a pie chart may be used. Through this intelligent visualization selection, the system ensures that the output results are easy to read and operate.

[0078] The output of the data statistics dashboard is the result of the system's comprehensive analysis of all input data. It not only shows the current state of the data, but also provides insights into historical trends and future forecasts. This comprehensive view can help decision makers quickly understand the situation and make wise decisions.

[0079] Once the data statistics dashboard is generated, the system will cache it in a preset database. The purpose of caching is to improve the speed and efficiency of subsequent access. Through the caching mechanism, the system can quickly respond to user query requests without regenerating the dashboard every time. This method significantly improves the system's response speed and user experience.

[0080] The technical problem solved by this solution is mainly how to efficiently integrate and visualize multi-source data. Traditional data analysis methods are often limited to a single data source, resulting in one-sided results. However, through data fusion and dashboard generation models, the system can integrate information from multiple data sources and provide users with a comprehensive view.

[0081] In terms of technical effects, through data fusion and visualization, the system significantly improves the depth and breadth of data analysis. The data dashboard generation model can intelligently select the visualization form according to the input parameters to provide users with intuitive decision support. At the same time, the application of the cache mechanism improves the system's response speed and enhances the user experience.

[0082] For example, suppose a retailer wants to monitor the sales data of multiple stores in real time. The system first merges the sales performance of each store (the first dashboard parameter) with the market trend data (the second dashboard parameter). Then, through the data dashboard generation model, a comprehensive dashboard containing information such as sales trends and market share is generated. Finally, these dashboards are cached in the database for managers to access and analyze at any time, so as to optimize inventory and marketing strategies.

[0083] In summary, step S103 achieves efficient integration and visual display of multi-source data through data fusion, dashboard generation and result caching. This solution not only improves the accuracy and practicality of data analysis, but also provides users with strong decision support and has a wide range of practical application value.

[0084] From the above description, it can be seen that the data processing method of the data interface provided in the embodiment of the present application can determine the corresponding first dashboard parameters according to the user identifier of the data source and the data source classification model by receiving the target data sent by the data source; perform data analysis on the target data to determine the corresponding data type and data size, perform model training on the preset adaptive model according to the data type and data size to obtain the target data classification model after model training, and determine the corresponding second dashboard parameters according to the output of the target data classification model; perform data fusion on the first dashboard parameters and the second dashboard parameters and input them into the set data dashboard generation model to obtain the data statistics dashboard output by the data dashboard generation model, and cache the data statistics dashboard in a preset database, thereby improving the accuracy and practicality of data analysis and supporting scientific decision-making and business optimization of enterprises and organizations.

[0085] In one embodiment of the data processing method of the data interface of the present application, see Figure 2 , and can also include the following:

[0086] Step S201: extracting implicit semantic association features between different user groups through a preset graph inference algorithm, and performing grouping operations on historical user identifiers through the implicit semantic association features;

[0087] Step S202: performing user feature vectorization on each obtained user group and performing joint modeling and federated model training, and determining the corresponding user behavior pattern according to the output of the federated model.

[0088] Optionally, in this embodiment, in step S201, the system first extracts implicit semantic association features between different user groups through a preset graph reasoning algorithm. This process uses knowledge graph technology to analyze complex relationships in user data. The graph reasoning algorithm can identify implicit connections between users, such as common interests, similar purchasing behaviors, etc. In this way, the system can capture deep associations that are difficult to discover with traditional analysis methods.

[0089] Once the implicit semantic association features are extracted, the system will use these features to group historical user identifiers. The purpose of grouping is to cluster users based on their potential similarities to form more representative user groups. This implicit feature-based grouping method can better reflect users' real interests and behavior patterns than traditional explicit feature grouping (such as age, geographic location).

[0090] Next, in step S202, the system vectorizes the user features of each user group. Vectorization is the process of converting user behaviors and attributes into numerical form for subsequent machine learning modeling. The feature vector of each user group contains the common features of the group of users, such as preferences, behavior patterns, etc.

[0091] After vectorization, the system performs joint modeling and federated model training. Joint modeling refers to considering the characteristics of multiple user groups at the same time to build a comprehensive model. In this process, federated learning provides an effective distributed training method. Federated learning can use multiple data sources for model training while protecting user privacy. Each participating node updates the model locally and then sends the update to the central server for integration without uploading the original data.

[0092] Through federated model training, the system can obtain more comprehensive user behavior patterns without violating user privacy. The advantage of federated learning is that it can use distributed data for effective training while maintaining a high level of security and privacy protection.

[0093] Finally, the system determines the corresponding user behavior pattern based on the output of the federated model. User behavior patterns refer to the behavioral tendencies and habits of users in specific situations. By understanding user behavior patterns, companies can perform more precise marketing and service optimization. For example, an e-commerce platform can identify potential high-value customers by analyzing user behavior patterns and customize personalized shopping experiences for these customers.

[0094] The technical problem solved by this solution is mainly how to extract implicit associations of users under large-scale data and conduct effective joint modeling under the premise of protecting privacy. Traditional methods often require centralized data processing, which easily leads to the risk of privacy leakage. Through graph reasoning and federated learning, the system can efficiently extract implicit features and conduct secure distributed training.

[0095] In terms of technical effects, through the combination of graph reasoning algorithm and federated learning, the system significantly improves the accuracy and security of user behavior patterns. The extracted implicit semantic association features can reveal deeper user relationships, and the application of federated learning ensures privacy protection during the training process.

[0096] For example, suppose a social media platform wants to optimize its advertising strategy. The system first uses a graph reasoning algorithm to identify implicit social relationships and interest tags between users. Then, users are grouped into small groups with similar interests. Next, these groups are feature vectorized to convert users' interactive behaviors, browsing habits, etc. into numerical features. Under the framework of federated learning, the system trains a comprehensive user behavior model. Based on the output of the model, the platform can identify the user groups that are most interested in a specific advertisement and accurately deliver advertisements, thereby improving advertising effectiveness and user satisfaction.

[0097] In summary, steps S201 and S202 achieve implicit feature extraction and behavioral pattern recognition of user groups through graph reasoning, feature vectorization and federated learning. This solution not only improves the depth and breadth of user analysis, but also protects user privacy through federated learning, and has important practical application value.

[0098] In one embodiment of the data processing method of the data interface of the present application, see Figure 3 , and can also include the following:

[0099] Step S301: Using a preset knowledge transfer algorithm, implicit semantic association features in the graph are transferred to the initial model as a model optimization direction;

[0100] Step S302: Automatically optimize the hyperparameters of the initial model according to the user behavior pattern to obtain a data source classification model.

[0101] Optionally, in this embodiment, in step S301, the system first migrates the implicit semantic association features in the graph to the initial model through a preset knowledge transfer algorithm as the direction of model optimization. The core of the knowledge transfer algorithm is to use the knowledge in the source domain to improve the performance of the target domain model. Here, the source domain is the implicit semantic association features in the graph, and the target domain is the initial model. By migrating these deep-level association features, the initial model can better capture the user's potential behavior patterns, thereby improving the accuracy of the prediction.

[0102] The implementation process of knowledge transfer usually includes feature mapping and model adjustment. First, the system maps the implicit features in the graph to adapt them to the input format of the initial model. Then, by adjusting the weights and structure of the model, it can make full use of these migrated features. In this way, the initial model can not only rely on its own training data, but also absorb more extensive knowledge from the graph, improving its ability to understand complex user behaviors.

[0103] In step S302, the system automatically optimizes the hyperparameters of the initial model based on the user behavior pattern. Hyperparameter optimization is an important part of machine learning model tuning, which involves adjusting the parameters of the model to achieve optimal performance. Through automation, the system can efficiently find the optimal solution among a large number of parameter combinations without manual intervention.

[0104] Methods for achieving automatic hyperparameter optimization usually include grid search, random search, and Bayesian optimization. The system selects the appropriate optimization strategy based on the user's behavior pattern. For example, Bayesian optimization selects the next parameter combination to be evaluated by building a probability model, which can obtain near-optimal results in fewer attempts. This method not only saves computing resources, but also improves the training efficiency of the model.

[0105] After automatic hyperparameter optimization, the system obtains a data source classification model. This model can accurately classify and predict based on the input data source characteristics. The core of this model is that through the combination of knowledge transfer and hyperparameter optimization, the model has stronger generalization ability and higher prediction accuracy.

[0106] The technical problems solved by this solution are mainly how to effectively use the implicit features in the graph to optimize the model, and how to automatically adjust the model parameters to adapt to different user behavior patterns. Traditional methods usually require a lot of manual intervention and experiments, but through knowledge transfer and automated optimization, the system can efficiently achieve self-improvement of the model.

[0107] In terms of technical effects, through the combination of knowledge transfer and hyperparameter optimization, the system significantly improves the model's predictive ability and adaptability. The implicit features of the transfer provide the model with more comprehensive background knowledge, while the automated hyperparameter optimization ensures the model's optimal performance in different scenarios.

[0108] For example, suppose an online education platform wants to optimize its course recommendation system. The system first transfers the learning interests and habit characteristics of students in the graph to the initial recommendation model through knowledge transfer. Then, according to the students' behavior patterns (such as study time, course browsing history, etc.), the model parameters are automatically adjusted using Bayesian optimization. Finally, the generated course recommendation model can accurately provide personalized learning suggestions for each student, thereby improving learning effects and user satisfaction.

[0109] In summary, steps S301 and S302 achieve efficient optimization of the model and improvement of its adaptive capability through knowledge transfer and automated hyperparameter optimization.

[0110] In one embodiment of the data processing method of the data interface of the present application, see Figure 4 , and can also include the following:

[0111] Step S401: receiving target data sent by a data source, and performing normalization and formatting processing on the target data;

[0112] Step S402: extract the user identifier in the target data after the normalization and formatting processing and input it into the data source classification model to obtain the first dashboard parameter output by the data source classification model, wherein the first dashboard parameter at least includes the personalized analysis indicator corresponding to the current data source.

[0113] Optionally, in this embodiment, in step S401, the system receives the target data sent by the data source and performs normalization and formatting on the data. The purpose of normalization and formatting is to convert data from different sources into a unified format for subsequent analysis and processing. This process usually includes operations such as data cleaning, type conversion, and missing value filling. By standardizing the data format, the system can improve the efficiency of data processing and reduce errors caused by inconsistent formats.

[0114] In the specific implementation process, the system will first identify the source and type of the target data and convert it according to the preset format standard. For example, for data with inconsistent date formats, the system will unify them into the standard ISO format. For missing values, the system may use mean filling or interpolation to process them. In this way, the normalized data will have consistency and completeness, which is convenient for subsequent analysis and modeling.

[0115] In step S402, the system extracts the user identifier from the normalized target data and inputs it into the data source classification model. The user identifier is information used to uniquely identify the user in the data, such as a user ID or account name. By extracting the user identifier, the system can associate each piece of data with a specific user, thereby achieving personalized analysis.

[0116] The data source classification model is a machine learning model that has been optimized and trained in advance, and is designed to classify and predict based on the input user ID and related data. After the user ID is input into the model, the system can output the first dashboard parameters based on the user's historical behavior and characteristics. The first dashboard parameters are personalized analysis indicators generated for the current data source, including user preferences, behavior patterns, potential needs, etc.

[0117] These personalized analysis indicators provide companies with tools to gain a deeper understanding of user behavior. For example, e-commerce platforms can use these indicators to identify high-value customers and predict user purchase intentions, thereby conducting precision marketing. In this way, companies can improve user satisfaction and sales conversion rates.

[0118] The technical problem solved by this solution is how to efficiently process multi-source data and achieve personalized analysis. Traditional methods often require manual intervention to process data in different formats, resulting in low efficiency. However, through the combination of automated normalization processing and classification models, the system can quickly respond to and process large-scale data, improving the accuracy and efficiency of analysis.

[0119] In terms of technical effects, the system significantly improves the automation level of data processing and analysis through normalized formatting and data source classification models. The unified data format reduces human errors in data processing, while the application of classification models improves the accuracy of personalized indicators. This not only enhances the user analysis capabilities of enterprises, but also provides strong support for marketing and decision-making.

[0120] For example, suppose a streaming service company wants to optimize its recommendation system. The system first receives target data such as user viewing history, ratings, and search history, and converts these data into a unified format through normalization. Then, the user identifier is extracted and input into the classification model. The first dashboard parameters output by the model may include the user's preferred movie genre, viewing time, and active time period. Using these indicators, the company can provide personalized recommendations for each user and improve user retention and satisfaction.

[0121] In summary, steps S401 and S402 achieve efficient processing and personalized analysis of multi-source data through normalized formatting processing and data source classification model.

[0122] In one embodiment of the data processing method of the data interface of the present application, see Figure 5 , and can also include the following:

[0123] Step S501: performing data format and data distribution analysis operations on the target data;

[0124] Step S502: Determine the corresponding data type and data size according to the data format and the results of the respective analysis operations on the data.

[0125] Optionally, in this embodiment, in step S501, the system first performs data format and data distribution analysis operations on the target data. Data format analysis involves identifying the structure and type of data, such as strings, integers, floating point numbers, dates, etc. This step ensures that the system can correctly understand and process different types of data. Data distribution analysis focuses on the statistical properties of the data, such as mean, variance, distribution shape, etc. This process helps to identify outliers, missing values, or skewed distributions in the data, thereby providing guidance for subsequent processing.

[0126] In the specific implementation process, the system will use automated scripts to scan the data set, identify the data type of each column, and generate corresponding statistical reports. For data distribution analysis, the system may use visualization tools to generate histograms or box-and-whisker plots to intuitively display the distribution of data and outliers.

[0127] In step S502, the system determines the corresponding data type and data size based on the analysis results of the data format and data distribution. The data type is determined based on the results of the format analysis to ensure that each data field can be correctly classified and processed. The data size is determined based on the data distribution analysis, taking into account the size of the data set and the required storage space.

[0128] Through these analyses, the system is able to optimize data storage and processing strategies. For example, for highly skewed data, standardization or transformation may be required to improve the performance of the model. For fields with large data volumes, the system may choose more efficient compression and storage methods.

[0129] The technical problem solved by this solution lies mainly in the automatic processing and optimization of diversified data. Traditional data analysis requires human intervention to identify data characteristics, while through automated analysis, the system can quickly and accurately process large-scale data sets and reduce human errors.

[0130] In terms of technical effects, the system improves the understanding and processing efficiency of data through the analysis of data format and distribution. The automated analysis process not only speeds up data preprocessing, but also improves the accuracy and reliability of data processing. This lays a solid foundation for subsequent data modeling and analysis.

[0131] For example, suppose a financial institution receives customer transaction data from different regions. The system first performs format and distribution analysis on this data to identify the data type of each field (such as floating point numbers for amounts and strings for dates). Then, through distribution analysis, it is found that the transaction amounts in certain regions have skewed distributions. Based on these results, the system decides to adopt a specific data conversion and storage solution to improve the accuracy of subsequent analysis.

[0132] In summary, steps S501 and S502 achieve efficient classification and optimization of target data through analysis of data format and distribution. This solution not only improves the automation level of data processing, but also provides reliable basic support for data modeling and analysis, and has a wide range of practical application value.

[0133] In one embodiment of the data processing method of the data interface of the present application, see Figure 6 , and can also include the following:

[0134] Step S601: performing a data preprocessing operation on the target data according to the data type, wherein the data preprocessing operation includes at least one of text noise reduction, image enhancement, and video frame segmentation;

[0135] Step S602: Perform model training according to the adaptive model corresponding to the data type and the data size, and optimize the model through an automatic hyperparameter optimization algorithm to obtain a target data classification model, and determine the corresponding second dashboard parameters according to the output of the target data classification model, wherein the second dashboard parameters at least include a data analysis perspective corresponding to the current target data.

[0136] Optionally, in this embodiment, in step S601, the system first performs preprocessing operations on the target data according to the data type. Preprocessing is an important step in data analysis to ensure data quality and model performance. For text data, the system performs text noise reduction, including removing stop words, correcting spelling errors, unifying formats, etc. This process improves the clarity and accuracy of text data. For image data, image enhancement techniques are applied, such as adjusting brightness, contrast, reducing noise, etc., to improve image quality and feature extraction effects. For video data, the system will perform video framing and decompose the video into a series of static frames for frame-by-frame analysis. The application of these preprocessing techniques ensures that different types of data are consistent and high quality in subsequent analysis.

[0137] In step S602, the system matches a suitable adaptive model for training according to the data type and data size. The adaptive model can automatically adjust the structure and parameters according to the characteristics of the input data to improve the adaptability and performance of the model. For example, for text data, a Transformer-based model may be selected, while image data may use a convolutional neural network (CNN). After matching the appropriate model, the system optimizes the model through an automatic hyperparameter optimization algorithm. Hyperparameter optimization can be achieved through grid search, random search, or Bayesian optimization to automatically find the best parameter combination to improve model performance.

[0138] After optimization training, the system obtains the target data classification model. The model can accurately classify and predict according to the characteristics of the target data. The second dashboard parameters output by the model provide users with important analysis perspectives. These parameters may include data trends, anomaly detection, user behavior patterns, etc., to help users better understand and use data.

[0139] The key technical problem solved by this solution is how to efficiently process multiple types of data and achieve automatic optimization of the model. Traditional methods usually require manual intervention and adjustment, but through automated preprocessing and optimization, the system can quickly adapt to different data types and improve analysis accuracy and efficiency.

[0140] In terms of technical effects, through the combination of data preprocessing and adaptive models, the system significantly improves the depth and breadth of data analysis. Preprocessing operations ensure the consistency and quality of data, while automated model optimization improves the accuracy of analysis results. This not only enhances the system's analytical capabilities, but also provides users with an intuitive data analysis perspective.

[0141] For example, in medical image analysis, the system first removes noise and enhances MRI images to improve image clarity. Then, it selects a suitable deep learning model for training based on the image size and features, and improves the detection accuracy of the model through hyperparameter optimization. Ultimately, the second-level parameters output by the model may include the location and size of abnormal lesions, providing doctors with reliable diagnostic support.

[0142] In summary, steps S601 and S602 achieve efficient analysis and classification of multi-type data through data preprocessing and model optimization. This solution not only improves the automation level of data processing, but also provides users with an in-depth analysis perspective, which has important practical application value.

[0143] In one embodiment of the data processing method of the data interface of the present application, see Figure 7 , and can also include the following:

[0144] Step S701: fusing the first signboard parameter and the second signboard parameter into a unified feature vector by using a weighted fusion algorithm;

[0145] Step S702: input the unified feature vector into a set data dashboard generation model to obtain a data statistics dashboard output by the data dashboard generation model, wherein the data dashboard generation model is used to output a mapping relationship between the feature vector and a visualized data statistics dashboard.

[0146] Optionally, in this embodiment, in step S701, the system uses a weighted fusion algorithm to fuse the first dashboard parameter and the second dashboard parameter into a unified feature vector. The core of the weighted fusion algorithm is to assign different weights according to the importance of the parameters, thereby integrating information from different sources. In this way, the system can effectively integrate multi-dimensional data to ensure that important information occupies an appropriate proportion in the feature vector. This process usually involves standardizing the parameters to eliminate dimensional differences, and then applying weights for weighted summation to generate a comprehensive feature vector.

[0147] Next, in step S702, the unified feature vector is input into the set data dashboard generation model. The function of this model is to convert the feature vector into an intuitive data statistics dashboard. The data dashboard generation model converts the abstract feature vector into a visual form, such as a chart, an indicator card, etc., through a preset mapping relationship. This visual output not only enhances the readability of the data, but also helps users quickly understand and analyze the trends and patterns behind the data.

[0148] Data dashboard generation models usually use machine learning techniques to learn the mapping relationship between feature vectors and visualization elements. This process can be supervised by training sets. The model generates corresponding visualization results based on the input feature vectors and continuously optimizes them to improve accuracy and expressiveness.

[0149] The technical problem solved by this solution is how to effectively integrate multi-source data and transform it into a user-friendly visualization form. Traditional data analysis methods are often limited to a single dimension or require manual processing. Through weighted fusion and automated dashboard generation, the system can quickly process complex data and improve analysis efficiency.

[0150] In terms of technical effects, through the combination of weighted fusion and data dashboard generation model, the system significantly improves the depth and breadth of data analysis. The weighted fusion algorithm ensures the effective integration of multi-source data, while the automated visualization process improves the intuitiveness of data presentation and user experience. This not only helps users better understand the data, but also provides strong support for decision-making.

[0151] For example, on a retail platform, the system integrates customer purchase behavior (first dashboard parameter) and market trend analysis (second dashboard parameter) through a weighted fusion algorithm. The generated feature vector is input into the data dashboard generation model, and the output statistical dashboard may include sales trend charts, customer preference analysis, etc. These visualization results help the marketing team identify potential opportunities and optimize strategies to increase sales and customer satisfaction.

[0152] In summary, steps S701 and S702 achieve efficient integration and visualization of multi-source data through weighted fusion and automated dashboard generation. This solution not only improves the automation level of data processing, but also provides users with an intuitive and clear analysis perspective, and has a wide range of practical application value.

[0153] In order to improve the accuracy and practicality of data analysis and support scientific decision-making and business optimization of enterprises and organizations, the present application provides an embodiment of a data processing device for a data interface for implementing all or part of the content of the data processing method of the data interface, see Figure 8 , the data processing device of the data interface specifically includes the following contents:

[0154] The first dashboard parameter determination module 10 is used to group historical user identifiers according to user group characteristics, perform initial model training on each obtained user group, determine the corresponding user behavior pattern, optimize the initial model through a preset knowledge transfer algorithm and the user behavior pattern, obtain a data source classification model after the model optimization, receive target data sent by the data source, and determine the corresponding first dashboard parameter according to the user identifier of the data source and the data source classification model;

[0155] A second dashboard parameter determination module 20 is used to perform data analysis on the target data to determine the corresponding data type and data size, perform model training on a preset adaptive model according to the data type and the data size, obtain a target data classification model after the model training, and determine the corresponding second dashboard parameters according to the output of the target data classification model;

[0156] The data dashboard generation module 30 is used to perform data fusion on the first dashboard parameter and the second dashboard parameter and input them into a set data dashboard generation model to obtain the data statistics dashboard output by the data dashboard generation model, and cache the data statistics dashboard in a preset database.

[0157] From the above description, it can be seen that the data processing device of the data interface provided in the embodiment of the present application can determine the corresponding first dashboard parameters according to the user identifier of the data source and the data source classification model by receiving the target data sent by the data source; perform data analysis on the target data to determine the corresponding data type and data size, perform model training on the preset adaptive model according to the data type and data size to obtain the target data classification model after model training, and determine the corresponding second dashboard parameters according to the output of the target data classification model; perform data fusion on the first dashboard parameters and the second dashboard parameters and input them into the set data dashboard generation model to obtain the data statistics dashboard output by the data dashboard generation model, and cache the data statistics dashboard in a preset database, thereby improving the accuracy and practicality of data analysis and supporting scientific decision-making and business optimization of enterprises and organizations.

[0158] From the hardware level, in order to improve the accuracy and practicality of data analysis and support scientific decision-making and business optimization of enterprises and organizations, the present application provides an embodiment of an electronic device for implementing all or part of the content of the data processing method of the data interface, and the electronic device specifically includes the following content:

[0159] Processor, memory, communication interface and bus; wherein the processor, memory and communication interface communicate with each other through the bus; the communication interface is used to realize information transmission between the data processing device of the data interface and the core business system, user terminal and related database and other related devices; the logic controller can be a desktop computer, a tablet computer and a mobile terminal, etc., but the present embodiment is not limited thereto. In the present embodiment, the logic controller can be implemented with reference to the embodiment of the data processing method of the data interface in the embodiment, and the embodiment of the data processing device of the data interface, and the contents thereof are incorporated herein, and the repeated parts are not repeated.

[0160] It is understandable that the user terminal may include a smart phone, a tablet electronic device, a network set-top box, a portable computer, a desktop computer, a personal digital assistant (PDA), a vehicle-mounted device, a smart wearable device, etc. Among them, the smart wearable device may include smart glasses, a smart watch, a smart bracelet, etc.

[0161] In practical applications, part of the data processing method of the data interface can be executed on the electronic device side as described above, or all operations can be completed in the client device. The selection can be made based on the processing capability of the client device and the limitations of the user's usage scenario. This application does not limit this. If all operations are completed in the client device, the client device may also include a processor.

[0162] The client device may have a communication module (i.e., a communication unit) that can communicate with a remote server to achieve data transmission with the server. The server may include a server on the task scheduling center side, and other implementation scenarios may also include a server on an intermediate platform, such as a server on a third-party server platform that has a communication link with the task scheduling center server. The server may include a single computer device, or a server cluster consisting of multiple servers, or a server structure of a distributed device.

[0163] Fig. 9 FIG. 9 is a schematic block diagram of the system structure of the electronic device 9600 according to an embodiment of the present application. Fig. 9 As shown, the electronic device 9600 may include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. It is worth noting that Fig. 9 is exemplary; other types of structures may also be used to supplement or replace this structure to implement telecommunication functions or other functions.

[0164] In one embodiment, the data processing method function of the data interface may be integrated into the central processing unit 9100. The central processing unit 9100 may be configured to perform the following control:

[0165] Step S101: grouping historical user identifiers according to user group characteristics, performing initial model training on each obtained user group, determining corresponding user behavior patterns, optimizing the initial model through a preset knowledge transfer algorithm and the user behavior patterns, obtaining a data source classification model after the model optimization, receiving target data sent by a data source, and determining corresponding first dashboard parameters according to the user identifier of the data source and the data source classification model;

[0166] Step S102: performing data analysis on the target data to determine the corresponding data type and data size, performing model training on a preset adaptive model according to the data type and the data size to obtain a target data classification model after the model training, and determining the corresponding second dashboard parameters according to the output of the target data classification model;

[0167] Step S103: After data fusion of the first dashboard parameter and the second dashboard parameter, the data is input into a set data dashboard generation model to obtain a data statistics dashboard output by the data dashboard generation model, and the data statistics dashboard is cached in a preset database.

[0168] From the above description, it can be seen that the electronic device provided in the embodiment of the present application receives the target data sent by the data source, determines the corresponding first dashboard parameters according to the user identifier of the data source and the data source classification model; performs data analysis on the target data to determine the corresponding data type and data size, and performs model training on the preset adaptive model according to the data type and data size to obtain the target data classification model after model training, and determines the corresponding second dashboard parameters according to the output of the target data classification model; performs data fusion on the first dashboard parameters and the second dashboard parameters and inputs them into the set data dashboard generation model to obtain the data statistics dashboard output by the data dashboard generation model, and caches the data statistics dashboard in a preset database, thereby improving the accuracy and practicality of data analysis and supporting scientific decision-making and business optimization of enterprises and organizations.

[0169] In another embodiment, the data processing device of the data interface can be configured separately from the central processing unit 9100. For example, the data processing device of the data interface can be configured as a chip connected to the central processing unit 9100, and the data processing method function of the data interface is implemented through the control of the central processing unit.

[0170] like Fig. 9 As shown, the electronic device 9600 may also include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily have to include Fig. 9 In addition, the electronic device 9600 may also include Fig. 9 For components not shown, reference may be made to the prior art.

[0171] like Fig. 9 As shown, the central processing unit 9100 is sometimes also referred to as a controller or an operation control, and may include a microprocessor or other processor device and / or logic device. The central processing unit 9100 receives input and controls the operation of various components of the electronic device 9600.

[0172] The memory 9140 may be, for example, one or more of a cache, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory or other suitable devices. The above-mentioned information related to the failure may be stored, and a program for executing the relevant information may also be stored. The CPU 9100 may execute the program stored in the memory 9140 to implement information storage or processing, etc.

[0173] The input unit 9120 provides input to the central processing unit 9100. The input unit 9120 is, for example, a key or a touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used to display display objects such as images and texts. The display may be, for example, an LCD display, but is not limited thereto.

[0174] The memory 9140 may be a solid-state memory, such as a read-only memory (ROM), a random access memory (RAM), a SIM card, etc. It may also be a memory that saves information even when the power is off, can be selectively erased, and is provided with more data, examples of which are sometimes referred to as EPROMs, etc. The memory 9140 may also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142, which is used to store application programs and function programs or processes for executing the operation of the electronic device 9600 through the central processor 9100.

[0175] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various drivers for communication functions of the electronic device and / or for executing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0176] The communication module 9110 is a transmitter / receiver that sends and receives signals via the antenna 9111. The communication module 9110 (transmitter / receiver) is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as the case of a conventional mobile communication terminal.

[0177] Based on different communication technologies, multiple communication modules 9110 may be provided in the same electronic device, such as a cellular network module, a Bluetooth module and / or a wireless LAN module, etc. The communication module 9110 (transmitter / receiver) is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide an audio output via the speaker 9131 and receive an audio input from the microphone 9132, thereby realizing a common telecommunication function. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. In addition, the audio processor 9130 is also coupled to the central processor 9100, so that recording can be performed on the local machine through the microphone 9132, and the sound stored on the local machine can be played through the speaker 9131.

[0178] The embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps of the data processing method of the data interface of the server or client in the above embodiments. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, all the steps of the data processing method of the data interface of the server or client in the above embodiments are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0179] Step S101: grouping historical user identifiers according to user group characteristics, performing initial model training on each obtained user group, determining corresponding user behavior patterns, optimizing the initial model through a preset knowledge transfer algorithm and the user behavior patterns, obtaining a data source classification model after the model optimization, receiving target data sent by a data source, and determining corresponding first dashboard parameters according to the user identifier of the data source and the data source classification model;

[0180] Step S102: performing data analysis on the target data to determine the corresponding data type and data size, performing model training on a preset adaptive model according to the data type and the data size to obtain a target data classification model after the model training, and determining the corresponding second dashboard parameters according to the output of the target data classification model;

[0181] Step S103: After data fusion of the first dashboard parameter and the second dashboard parameter, the data is input into a set data dashboard generation model to obtain a data statistics dashboard output by the data dashboard generation model, and the data statistics dashboard is cached in a preset database.

[0182] From the above description, it can be seen that the computer-readable storage medium provided in the embodiment of the present application receives the target data sent by the data source, determines the corresponding first dashboard parameters according to the user identifier of the data source and the data source classification model; performs data analysis on the target data to determine the corresponding data type and data size, performs model training on the preset adaptive model according to the data type and data size, obtains the target data classification model after model training, and determines the corresponding second dashboard parameters according to the output of the target data classification model; performs data fusion on the first dashboard parameters and the second dashboard parameters and inputs them into the set data dashboard generation model to obtain the data statistics dashboard output by the data dashboard generation model, and caches the data statistics dashboard in a preset database, thereby improving the accuracy and practicality of data analysis and supporting scientific decision-making and business optimization of enterprises and organizations.

[0183] The embodiments of the present application also provide a computer program product capable of implementing all the steps of the data processing method of the data interface in the above embodiments, where the execution subject is a server or a client. When the computer program / instruction is executed by a processor, the steps of the data processing method of the data interface are implemented. For example, the computer program / instruction implements the following steps:

[0184] Step S101: grouping historical user identifiers according to user group characteristics, performing initial model training on each obtained user group, determining corresponding user behavior patterns, optimizing the initial model through a preset knowledge transfer algorithm and the user behavior patterns, obtaining a data source classification model after the model optimization, receiving target data sent by a data source, and determining corresponding first dashboard parameters according to the user identifier of the data source and the data source classification model;

[0185] Step S102: performing data analysis on the target data to determine the corresponding data type and data size, performing model training on a preset adaptive model according to the data type and the data size to obtain a target data classification model after the model training, and determining the corresponding second dashboard parameters according to the output of the target data classification model;

[0186] Step S103: After data fusion of the first dashboard parameter and the second dashboard parameter, the data is input into a set data dashboard generation model to obtain a data statistics dashboard output by the data dashboard generation model, and the data statistics dashboard is cached in a preset database.

[0187] From the above description, it can be seen that the computer program product provided in the embodiment of the present application receives the target data sent by the data source, determines the corresponding first dashboard parameters according to the user identifier of the data source and the data source classification model; performs data analysis on the target data to determine the corresponding data type and data size, and performs model training on the preset adaptive model according to the data type and data size to obtain the target data classification model after model training, and determines the corresponding second dashboard parameters according to the output of the target data classification model; performs data fusion on the first dashboard parameters and the second dashboard parameters and inputs them into the set data dashboard generation model to obtain the data statistics dashboard output by the data dashboard generation model, and caches the data statistics dashboard in a preset database, thereby improving the accuracy and practicality of data analysis and supporting scientific decision-making and business optimization of enterprises and organizations.

[0188] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0189] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (apparatus), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks 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 generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes 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.

[0190] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate 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 A function specified in one or more boxes.

[0191] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0192] The present invention uses specific embodiments to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A data processing method for a data interface, characterized in that: The method comprises: Perform grouping operations on historical user identifiers according to user group characteristics, perform initial model training on each obtained user group, determine corresponding user behavior patterns, optimize the initial model through a preset knowledge transfer algorithm and the user behavior patterns, obtain a data source classification model after the model optimization, receive target data sent by the data source, and determine corresponding first dashboard parameters according to the user identifier of the data source and the data source classification model; Performing data analysis on the target data to determine the corresponding data type and data size, performing model training on a preset adaptive model according to the data type and the data size to obtain a target data classification model after the model training, and determining the corresponding second dashboard parameters according to the output of the target data classification model; The first dashboard parameter and the second dashboard parameter are data-fused and input into a set data dashboard generation model to obtain a data statistics dashboard output by the data dashboard generation model, and the data statistics dashboard is cached in a preset database.

2. The data processing method of the data interface according to claim 1, characterized in that: The grouping operation of the historical user identifiers according to the user group characteristics, performing initial model training on each obtained user group, and determining the corresponding user behavior pattern includes: Extracting implicit semantic association features between different user groups through a preset graph inference algorithm, and performing grouping operations on historical user identifiers through the implicit semantic association features; The obtained user groups are represented by user feature vectorization and joint modeling and federated model training are performed, and the corresponding user behavior pattern is determined according to the output of the federated model.

3. The data processing method of the data interface according to claim 1, characterized in that: The optimizing the initial model by using the preset knowledge transfer algorithm and the user behavior pattern to obtain the optimized data source classification model includes: Using a preset knowledge transfer algorithm, implicit semantic association features in the graph are transferred to the initial model as a model optimization direction; The initial model is automatically optimized for hyperparameters according to the user behavior pattern to obtain a data source classification model.

4. The data processing method of the data interface according to claim 1, characterized in that: The receiving target data sent by the data source, and determining the corresponding first dashboard parameter according to the user identifier of the data source and the data source classification model, includes: Receive target data sent by a data source, and perform normalization and formatting processing on the target data; The user identifier in the target data after the normalization and formatting processing is extracted and input into the data source classification model to obtain the first dashboard parameter output by the data source classification model, wherein the first dashboard parameter at least includes the personalized analysis indicator corresponding to the current data source.

5. The data processing method of the data interface according to claim 1, characterized in that: The performing data analysis on the target data to determine the corresponding data type and data size includes: Performing data format and data distribution analysis operations on the target data; The corresponding data type and data size are determined according to the data format and the results of the respective analysis operations on the data.

6. The data processing method of the data interface according to claim 1, characterized in that: The performing model training on a preset adaptive model according to the data type and the data size to obtain a target data classification model after the model training, and determining corresponding second dashboard parameters according to an output of the target data classification model, includes: Performing a data preprocessing operation on the target data according to the different data types, wherein the data preprocessing operation includes at least one of text noise reduction, image enhancement, and video framing; Model training is performed according to an adaptive model corresponding to the data type and the data size, and the model is optimized through an automatic hyperparameter optimization algorithm to obtain a target data classification model, and corresponding second dashboard parameters are determined according to an output of the target data classification model, wherein the second dashboard parameters at least include a data analysis perspective corresponding to the current target data.

7. The data processing method of the data interface according to claim 1, characterized in that: The step of fusing the first dashboard parameter and the second dashboard parameter and inputting the resultant data into a data dashboard generation model to obtain a data statistics dashboard output by the data dashboard generation model includes: The first signboard parameter and the second signboard parameter are fused into a unified feature vector by using a weighted fusion algorithm; The unified feature vector is input into a set data dashboard generation model to obtain a data statistics dashboard output by the data dashboard generation model, wherein the data dashboard generation model is used to output a mapping relationship between the feature vector and a visualized data statistics dashboard.

8. A data processing device for a data interface, characterized in that: The device comprises: A first dashboard parameter determination module is used to group historical user identifiers according to user group characteristics, perform initial model training on each obtained user group, determine corresponding user behavior patterns, optimize the initial model through a preset knowledge transfer algorithm and the user behavior pattern, obtain a data source classification model after the model optimization, receive target data sent by a data source, and determine corresponding first dashboard parameters according to the user identifier of the data source and the data source classification model; a second dashboard parameter determination module, configured to perform data analysis on the target data to determine a corresponding data type and data size, perform model training on a preset adaptive model according to the data type and the data size, obtain a target data classification model after the model training, and determine a corresponding second dashboard parameter according to an output of the target data classification model; The data dashboard generation module is used to perform data fusion on the first dashboard parameter and the second dashboard parameter and input them into a set data dashboard generation model to obtain the data statistics dashboard output by the data dashboard generation model, and cache the data statistics dashboard in a preset database.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the data processing method of the data interface described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the data processing method of the data interface described in any one of claims 1 to 7 are implemented.

Citation Information

Patent Citations

  • Application fusion system oriented to big data analysis

    CN117331995A

  • Data management system and device

    CN118170750A

  • Systems and method for optimizing educational outcomes using artificial intelligence

    US20200302296A1