User big data management method and system based on artificial intelligence and visualization

Abstract

The invention relates to the technical field of intelligent medical treatment, and provides a user big data management method and system based on artificial intelligence and visualization. The method has the beneficial effects that the efficiency and the accuracy of user interface design are improved, the continuity and the individuation of user experience are enhanced, and the response speed and the user satisfaction of the user interface in the visual interaction process are improved. The beneficial effects jointly form remarkable advantages and innovation value of the method in the field of user interface design.

Description

[0001] Cross - reference to related applications

[0002] This application claims priority to an application with application number CN202410215894.X, titled "Method and System for User Big Data Management Based on Artificial Intelligence and Visualization", filed on February 27, 2024, the content of which is incorporated herein by reference in its entirety. Technical field

[0003] The present invention relates to the field of intelligent medical technology, and in particular, to a method and system for user big data management based on artificial intelligence and visualization. Background art

[0004] In the field of the design of medical information systems and patient interaction interfaces, how to effectively understand and meet the needs of patients has always been an important challenge. With the development of technology, especially the application of artificial intelligence and machine learning in user interface design, more and more research has focused on how to improve the user experience through data analysis.

[0005] Traditional medical information system interface designs are usually based on fixed templates and processes, lacking consideration for the needs of individual patients. This leads to problems such as complex operations, difficulty in finding or understanding information when patients use the system, thus affecting the quality and efficiency of medical services.

[0006] In recent years, although some research has begun to focus on the behavioral analysis and need identification of patient users, most of these methods rely on simple user behavior statistics or questionnaires and cannot deeply explore the actual needs and potential problems of patients when using medical information systems. Summary of the invention

[0007] To improve the above problems, the present invention provides a method and system for user big data management based on artificial intelligence and visualization.

[0008] In the first aspect of the embodiments of the present invention, there is provided a method for user big data management based on artificial intelligence and visualization, which is applied to an intelligent medical user big data management system. The method includes:

[0009] According to the target patient user label and the visualization interaction interface jump node, obtain the past interface module visual feature relationship network. The past interface module visual feature relationship network includes content semantic description knowledge of multiple visual interfaces. Each content semantic description knowledge includes interface module switching data between the corresponding visual interface and the remaining visual interfaces among the multiple visual interfaces. The multiple visual interfaces include the target visual interface corresponding to the target patient user label;

[0010] Combining the associated visual feature relationship network and the visual feature relationship network of the past interface modules, mining the switching behavior vectors between the visual feature of each visual interface and the remaining visual interfaces to obtain an interface switching behavior description, and performing behavior requirement recognition on the interface switching behavior description to obtain an interface requirement recognition vector;

[0011] Based on the interface requirement recognition vector, performing interface display jump feature analysis to obtain an analysis result;

[0012] Based on the visual feature of the target visual interface under the interface module in the analysis result at the interface jump node of the visual interaction interface, determining the interface module switching decision feature corresponding to the target patient user label under the interface jump node of the visual interaction interface.

[0013] Preferably, the combining the associated visual feature relationship network and the visual feature relationship network of the past interface modules, mining the switching behavior vectors between the visual feature of each visual interface and the remaining visual interfaces to obtain an interface switching behavior description, and performing behavior requirement recognition on the interface switching behavior description to obtain an interface requirement recognition vector includes:

[0014] Through the associated visual feature relationship network of the current residual branch, based on the original visual feature relationship network of the past interface modules and the interface requirement recognition vector generated by the previous residual branch, mining the switching behavior vectors between the visual feature of each visual interface and the remaining visual interfaces to obtain an interface switching behavior description, and performing behavior requirement recognition on the interface switching behavior description to obtain an interface requirement recognition vector. Wherein, if the current residual branch is the first residual branch, the interface requirement recognition vector generated by the previous residual branch is a zero vector;

[0015] Taking the next residual branch of the current residual branch as the new current residual branch, and jumping to the step of mining the switching behavior vectors between the visual feature of each visual interface and the remaining visual interfaces through the associated visual feature relationship network of the current residual branch, based on the original visual feature relationship network of the past interface modules and the interface requirement recognition vector generated by the previous residual branch to obtain an interface switching behavior description, and performing behavior requirement recognition on the interface switching behavior description to obtain an interface requirement recognition vector, until the interface requirement recognition vector is output by the last residual branch.

[0016] Preferably, the residual branch includes a first behavior requirement recognition layer, a second behavior requirement recognition layer, a third behavior requirement recognition layer, and a behavior requirement splicing layer;

[0017] The associated visual feature relationship network of the current residual branch, based on the original visual feature relationship network of the past interface module and the interface requirement recognition vector generated by the previous residual branch, mines the switching behavior vector between the visual feature of each visible interface and the visual feature of the remaining visible interfaces to obtain an interface switching behavior description, and performs behavior requirement recognition on the interface switching behavior description to obtain an interface requirement recognition vector, including:

[0018] Through the associated visual feature relationship network of the first behavior requirement recognition layer in the current residual branch, based on the original visual feature relationship network of the past interface module and the interface requirement recognition vector generated by the previous residual branch, mines the switching behavior vector between the visual feature of each visible interface and the visual feature of the remaining visible interfaces to obtain a first interface switching behavior description, and performs the first behavior requirement recognition process on the first interface switching behavior description to obtain a first interface requirement recognition vector;

[0019] Through the associated visual feature relationship network of the second behavior requirement recognition layer in the current residual branch, based on the original visual feature relationship network of the past interface module and the interface requirement recognition vector generated by the previous residual branch, mines the switching behavior vector between the visual feature of each visible interface and the visual feature of the remaining visible interfaces to obtain a second interface switching behavior description, and performs the second behavior requirement recognition process on the second interface switching behavior description to obtain a second interface requirement recognition vector;

[0020] Through the third behavior requirement recognition layer in the current residual branch, performs a vector multiplication on the second interface requirement recognition vector and the interface requirement recognition vector generated by the previous residual branch to obtain a first linkage requirement feature;

[0021] Through the associated visual feature relationship network of the third behavior requirement recognition layer, based on the original visual feature relationship network of the past interface module and the first linkage requirement feature, mines the switching behavior vector between the visual feature of each visible interface and the visual feature of the remaining visible interfaces to obtain a third interface switching behavior description, and performs the third behavior requirement recognition process on the third interface switching behavior description to obtain a third interface requirement recognition vector;

[0022] Through the behavior requirement splicing layer, determines the second linkage requirement feature between the first interface requirement recognition vector and the interface requirement recognition vector generated by the previous residual branch, and the third linkage requirement feature between the target feature relationship network corresponding to the first interface requirement recognition vector and the third interface requirement recognition vector, determines the sum of the second linkage requirement feature and the third linkage requirement feature to obtain the interface requirement recognition vector generated by the current residual branch, where the target feature relationship network is obtained by taking the difference between the reference feature relationship network and the first interface requirement recognition vector.

[0023] Preferably, the number of the visual feature relationship networks of the past interface modules is at least two. The visual interfaces corresponding to each visual feature relationship network of the past interface modules are the same, and the ranges of the interface analysis nodes are different;

[0024] Mining the switching behavior vectors between the interface module visual features of each visual interface and the remaining visual interfaces by combining the associated visual feature relationship network and the visual feature relationship network of the past interface modules to obtain an interface switching behavior description, and performing behavior requirement recognition on the interface switching behavior description to obtain an interface requirement recognition vector, including: mining the switching behavior vectors between the interface module visual features of each visual interface and the remaining visual interfaces according to each visual feature relationship network of the past interface modules by the associated visual feature relationship network to obtain the interface switching behavior descriptions corresponding to each visual feature relationship network of the past interface modules, and performing behavior requirement recognition on each interface switching behavior description to obtain the interface requirement recognition vectors corresponding to each visual feature relationship network of the past interface modules.

[0025] Preferably, parsing the interface display jump feature according to the interface requirement recognition vector to obtain an analysis result, including:

[0026] Weighting the interface requirement recognition vectors corresponding to each visual feature relationship network of the past interface modules to obtain an interface requirement recognition weighted vector;

[0027] Parsing the interface display jump feature according to the interface requirement recognition weighted vector to obtain an analysis result.

[0028] Preferably, parsing the interface display jump feature according to the interface requirement recognition vector to obtain an analysis result, including: parsing the interface display jump feature according to the interface requirement recognition vector to obtain the analysis results of each visual interface in the multiple visual interfaces;

[0029] Determining the interface module switching decision feature corresponding to the target patient user label under the visualization interaction interface jump node according to the interface module visual feature of the target visual interface in the analysis result under the visualization interaction interface jump node, including: obtaining the interface module visual feature of the target visual interface under the visualization interaction interface jump node according to the analysis results of each visual interface in the multiple visual interfaces, and determining the interface module switching decision feature corresponding to the target patient user label under the visualization interaction interface jump node.

[0030] Preferably, obtaining the visual feature relationship network of the past interface modules according to the target patient user label and the visualization interaction interface jump node, where the visual feature relationship network of the past interface modules includes the content semantic description knowledge of multiple visual interfaces, including:

[0031] Determine at least two ranges of interface analysis nodes before the visual interaction interface jump node according to the visual characteristics of the interface module to be predicted;

[0032] Decompose each range of interface analysis nodes into multiple sets of operation nodes based on a preset node step size;

[0033] Determine the target visual interface corresponding to the target patient user label according to the visual characteristics of the interface module to be predicted, and the sample visual interface corresponding to the target visual interface as the visual interface to be processed;

[0034] For each visual interface to be processed, obtain the interface module switching data between the visual interface to be processed and the remaining visual interfaces to be processed in each set of operation nodes;

[0035] For each range of interface analysis nodes, based on the interface module switching data between each visual interface to be processed and the remaining visual interfaces to be processed in the set of operation nodes of the interface analysis node range, obtain the content semantic description knowledge of each visual interface in the interface analysis node range;

[0036] Based on the content semantic description knowledge corresponding to each range of interface analysis nodes, obtain the visual feature relationship network of the past interface modules corresponding to each range of interface analysis nodes.

[0037] Preferably, perform interface display jump feature analysis based on the interface requirement recognition vector to obtain an analysis result, including:

[0038] Perform knowledge transformation on the interface requirement recognition vector to obtain interface requirement transformation knowledge;

[0039] Perform interface display jump feature analysis according to the interface requirement transformation knowledge to obtain an analysis result.

[0040] In a second aspect of the embodiments of the present invention, a smart medical user big data management system is provided, including: a processor, a memory, and a bus connected to the processor; the processor and the memory complete communication with each other through the bus; the processor is used to call a computer program in the memory to execute the above-mentioned user big data management method based on artificial intelligence and visualization.

[0041] In a third aspect of the embodiments of the present invention, a computer-readable storage medium is provided, on which a program is stored, and when the program is executed by a processor, it implements the above-mentioned user big data management method based on artificial intelligence and visualization.

[0042] The user big data management method and system based on artificial intelligence and visualization provided by the embodiments of the present invention can efficiently obtain the visual feature relationship network of past interface modules by combining target patient user tags and visualization interaction interface jump nodes. This relationship network covers the content semantic description knowledge of multiple visual interfaces and the interface module switching data between them. This innovative method not only enriches the data basis for user interface design, but also improves the switching efficiency between interfaces and the coherence of the user experience.

[0043] Furthermore, the present invention deeply excavates the interface module visual feature switching behavior vectors between each visual interface and the remaining visual interfaces by combining the associated visual feature relationship network and the visual feature relationship network of past interface modules. This vectorized description method makes the interface switching behavior more accurate and quantifiable, providing a solid foundation for subsequent behavior requirement recognition.

[0044] By performing behavior requirement recognition on the interface switching behavior description, the present invention can accurately obtain the interface requirement recognition vector. This vector not only reflects the actual needs of users, but also provides strong support for the personalization and intelligence of interface design.

[0045] In addition, the present invention also analyzes the interface display jump characteristics based on the interface requirement recognition vector, thereby obtaining a targeted analysis result. This result provides clear guidance for the interface module visual features of the target visual interface under the visualization interaction interface jump node, making the interface design more in line with user expectations and usage habits.

[0046] Finally, by determining the interface module switching decision characteristics corresponding to the target patient user tags, the present invention realizes precise decision-making under the visualization interaction interface jump node. This decision not only improves the response speed and accuracy of the user interface, but also greatly enhances the user satisfaction and convenience during use.

[0047] In summary, the beneficial effects of the present invention are reflected in improving the efficiency and accuracy of user interface design, enhancing the coherence and personalization of the user experience, and increasing the response speed and user satisfaction of the user interface during the visualization interaction process. These beneficial effects together constitute the significant advantages and innovative value of the present invention in the field of user interface design. Description of the Drawings

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0049] Figure 1 A flowchart of a user big data management method based on artificial intelligence and visualization provided by an embodiment of the present invention.

[0050] Figure 2 A schematic diagram of product modules of a smart healthcare user big data management system provided by an embodiment of the present invention. Detailed implementation manners

[0051] Hereinafter, exemplary embodiments disclosed by the present invention will be described in more detail with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be completely conveyed to those skilled in the art.

[0052] To better understand the above technical solutions, the technical solutions of the present invention will be described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solutions of the present invention, rather than limitations on the technical solutions of the present invention. Without conflict, the technical features in the embodiments of the present invention and the embodiments can be combined with each other.

[0053] Please refer to Figure 1 , a flowchart of a user big data management method based on artificial intelligence and visualization provided by an embodiment of the present invention. This method is applied to a smart healthcare user big data management system, and the specific content description included in this method includes S110 - S140.

[0054] S110. The smart healthcare user big data management system obtains a past interface module visual feature relationship network according to the target patient user label and the visualization interaction interface jump node. The past interface module visual feature relationship network includes content semantic description knowledge of multiple visual interfaces. Each content semantic description knowledge includes interface module switching data between the corresponding visual interface and the remaining visual interfaces among the multiple visual interfaces. The multiple visual interfaces include the target visual interface corresponding to the target patient user label.

[0055] In S110, the target patient user label: A label used to describe and classify specific attributes or characteristics of patient users. These labels can be defined based on factors such as the patient's age, gender, health status, disease type, treatment preference, etc. For an elderly patient with type 2 diabetes, their user labels may include "over 65 years old", "male", "type 2 diabetes", "oral drug treatment", etc.

[0056] Visual Interaction Interface Jump Node: In a visual interaction interface (such as an application or website for a health management system), it is the intersection or decision point where a user navigates from one interface to another. In a health management application, a user may jump from the "Home Page" to the "Health Data" interface, and then from the "Health Data" to the "Exercise Record" interface. Here, the "Home Page", "Health Data", and "Exercise Record" can all be regarded as jump nodes.

[0057] Visual Feature Relationship Network of Past Interface Modules: A network that records and analyzes the visual features and relationships between different interface modules when a user has used a visual interaction interface in the past. Through analyzing the user's historical data, the system found that whenever a user views the "Blood Glucose Data" interface, they tend to then view the "Diet Advice" interface. This sequence and pattern form part of the visual feature relationship network.

[0058] Visual Interface: An interface that can be presented visually and interact with users, usually containing elements such as graphics, text, images, and controls. The interface of a health management application on a smartphone is a visual interface, and users can interact with the application by touching buttons, sliders, etc. on the screen.

[0059] Content Semantic Description Knowledge: Detailed descriptions and explanations about interface content, elements, and layouts, usually used to understand and interpret the functions and uses of interfaces. In the "Health Data" interface, content semantic description knowledge may include the title of the interface, labels and explanations of each data field, and the visualization method of the data (such as charts or tables).

[0060] Interface Module Switching Data: Data that records a user's switching from one module to another in a visual interaction interface, including the frequency, duration, path, etc. of the switching. System records show that a user switched from the "Health Consultation" module to the "Medication Reminder" module 30 times in the past week, with an average stay time of 2 minutes each time.

[0061] Target Visual Interface: In a visual interaction system, it is the interface associated with a user's specific label or needs that requires special attention or optimization. For elderly patients with type 2 diabetes, the target visual interface may be the "Blood Glucose Monitoring" interface because this interface is directly related to their main health needs (i.e., blood glucose management).

[0062] S120. The intelligent medical user big data management system combines the associated visual feature relationship network and the visual feature relationship network of the past interface modules to mine the switching behavior vectors between the interface module visual features of each visual interface and the remaining visual interfaces, obtains the interface switching behavior description, and performs behavior requirement recognition on the interface switching behavior description to obtain the interface requirement recognition vector.

[0063] In S120, associate the visual feature relationship network: A network structure that describes the visual features (such as layout, color, size, etc.) and their mutual relationships among different visualization elements, interfaces, or modules. This relationship network helps to understand and predict the navigation and behavior of users in the visual interaction environment. In the visual feature relationship network of a health management application, the "Home" button may always be located at the center of the bottom of the screen, adjacent to the "Settings" and "Help" buttons. This layout relationship forms a stable visual feature pattern, and users can quickly find the required functions based on these features.

[0064] Switching behavior vector: A mathematical representation used to describe the behavior of a user switching from one interface or module to another in a visual interaction interface. This vector can include dimensions such as the frequency, direction, and duration of the switch. A switching behavior vector may indicate that the user switches from the "Health Data" interface to the "Exercise Record" interface 5 times a week, with an average switching duration of 3 seconds. This vector can help the system understand the user's navigation habits and needs.

[0065] Interface switching behavior description: A detailed description of the user's switching behavior in a visual interaction interface, including the type, path, trigger conditions, etc. of the switch. This description helps to understand the user's behavior pattern and preferences. The interface switching behavior description may indicate that after viewing the "Blood Glucose Data", the user often switches to the "Diet Advice" interface to view relevant diet adjustment suggestions. This description can help the system optimize the interface layout and navigation process.

[0066] Behavioral requirement identification: Identify and understand the potential needs, expectations, or problems of users by analyzing the user's behavioral data (such as interface switching, clicks, inputs, etc.). This identification helps to improve the user experience and the personalized service ability of the system. Through behavioral requirement identification, the system discovers that users often miss the medication time in the "Medication Reminder" interface. This indicates that users may need a more prominent reminder function or more flexible reminder setting options.

[0067] Interface requirement identification vector: A mathematical representation used to describe the requirements, expectations, or improvement suggestions of users for a specific interface obtained through the behavioral requirement identification process. This vector can include multiple dimensions, such as functional requirements, layout requirements, interaction requirements, etc. An interface requirement identification vector may indicate that the requirements of users for the "Exercise Record" interface include: being able to display more detailed exercise data (such as steps, distance, calories burned, etc.), providing a comparison function for historical exercise data, and optimizing the layout and color matching of the interface. This vector can provide guidance for the subsequent design and optimization of the interface.

[0068] S130. The big data management system for intelligent healthcare users analyzes the interface display jump characteristics based on the interface requirement recognition vector to obtain an analysis result.

[0069] In S130, the analysis of interface display jump characteristics: This is an analysis process aimed at deeply studying and understanding the characteristics and patterns when users jump from one interface display (or module) to another in a visual interaction interface. This kind of analysis usually involves the collection, collation, and analysis of data such as users' navigation paths, jump frequencies, residence times, and possible triggering factors. In a health management application, users often jump from the "health data" interface to the "exercise advice" interface. Through the analysis of interface display jump characteristics, the system discovers that this kind of jump mainly occurs after users view their blood sugar or weight data, and the jump frequency has a certain correlation with the change trend of these data of users. This indicates that users may hope to adjust their exercise plans according to their health data.

[0070] The analysis result is a general term for the conclusions or data obtained from a certain analysis or processing process. In the context of the analysis of interface display jump characteristics, the analysis result usually refers to a series of discoveries, patterns, rules, or suggestions obtained by analyzing users' interface jump behaviors. These results can be used to optimize interface design, improve user experience, or enhance system functions. In the above example of the health management application, the analysis results may include: "Users tend to seek exercise advice after viewing unsatisfactory health data" and "There is a significant correlation between users' jump behaviors and the change trend of their health data". Based on these analysis results, the system can adjust the interface design. For example, when users view poor health data, relevant exercise advice or health consultation links can be automatically popped up to provide a more personalized and responsive user experience.

[0071] S140. The big data management system for intelligent healthcare users determines the interface module switching decision characteristics corresponding to the target patient user label under the visualization interaction interface jump node based on the interface module visual characteristics of the target visual interface in the analysis result under the visualization interaction interface jump node.

[0072] In S140, the interface module switching decision characteristics refer to a series of characteristics and rules based on which decisions are made to switch from one interface module to another in a visual interaction system. These characteristics may include users' interaction behaviors, the content attributes of interface modules, the operating status of the system, etc., and the rules are formulated based on these characteristics and are used to guide the logic or algorithm of switching decisions. Understanding and applying these decision characteristics are crucial for improving user experience, optimizing system performance, and realizing personalized services.

[0073] In a health management application, the interface module switching decision characteristics may include the following aspects:

[0074] User behavior characteristics: The system may record and analyze users' interaction behaviors, such as click frequency, swipe direction, dwell time, etc. For example, if a user frequently clicks on the "Blood Glucose" sub-module in the "Health Data" module, the system may preferentially recommend content or functions related to "Blood Glucose" to the user, or automatically switch to the "Blood Glucose" sub-module when the user next opens the application;

[0075] Interface content attribute characteristics: Each interface module has its specific content attributes, such as importance, urgency, relevance, etc. These attributes can be obtained through content semantic description knowledge. For example, for a diabetic patient, the content of the "Hypoglycemia Warning" module may have higher importance and urgency. Therefore, when the user's blood glucose level is below the safe range, the system may automatically switch to the "Hypoglycemia Warning" module to remind the user to take timely measures;

[0076] System running state characteristics: The running state of the system also affects the interface module switching decision. For example, if the system detects that the user is performing a task that requires concentration (such as filling out a health questionnaire), it may reduce unnecessary interface switching or interference to maintain the user's focus;

[0077] Time and context characteristics: Time and context are also important factors in the switching decision. For example, when the user opens the application in the morning, the system may preferentially display the "Morning Health Check" module; while in the evening, it may switch to the "Sleep Quality Monitoring" module. In addition, if the user is in a specific context such as a hospital or clinic, the system may provide specific interface modules related to these contexts.

[0078] In summary, the interface module switching decision characteristics are multi-dimensional, dynamic, and need to be customized and optimized according to specific user needs and system goals. By reasonably applying these characteristics, a more intelligent, efficient, and user-friendly interface interaction experience can be achieved.

[0079] In the embodiment of the present invention, when the intelligent medical user big data management system executes medical information services, it will perform a series of data analysis and interface optimization decisions according to the specific needs and operation habits of the target patient users. The following is a specific application scenario of how the system is implemented.

[0080] First, the big data management system for intelligent medical users will obtain the visual feature relationship network of past interface modules based on the tags of target patient users (such as age, gender, medical history, preferences, etc.) and the jump nodes when they use the visual interaction interface. This relationship network contains the content semantic description knowledge of multiple visual interfaces, and each description details the module switching data between the corresponding visual interface and other interfaces. These visual interfaces include the target visual interfaces corresponding to the tags of target patient users. That is to say, the system will pay special attention to those interfaces highly relevant to user tags.

[0081] Next, the system will combine the currently associated visual feature relationship network and the past visual feature relationship network of interface modules to deeply mine the switching behavior vectors of each visual interface and the remaining visual interfaces in terms of interface module visual features. These vectors actually describe the switching patterns and habits of users when using different interfaces. By analyzing these switching behavior vectors, the system can generate a detailed description of the interface switching behavior and further identify the behavior requirements for these descriptions, thus obtaining the interface requirement identification vectors. These vectors reflect the possible requirements and expectations of users when operating the interface.

[0082] Then, the system will analyze the interface display jump characteristics based on these interface requirement identification vectors. This process mainly analyzes the possible jump paths and selections of users when operating the interface, as well as the reasons and motivations behind these selections. The results of the analysis will provide important clues for the system on how to optimize the interface layout and navigation process.

[0083] Finally, the system will determine the interface module switching decision characteristics corresponding to the tags of target patient users under the jump node of the visual interaction interface based on the interface module visual features of the target visual interface in the analysis results. These decision characteristics will guide the system on how to provide a more personalized and efficient interface experience for users, including but not limited to adjusting the interface layout, optimizing the navigation process, recommending relevant content, etc.

[0084] Generally speaking, the big data management system for intelligent medical users continuously optimizes and improves the user experience and satisfaction of medical information services by deeply analyzing users' operation habits and requirements, as well as their behaviors and selections when using the visual interaction interface.

[0085] In another specific application scenario, the intelligent medical user big data management system first obtains the visual feature relationship network of past interface modules based on the user tags of elderly patients with type 2 diabetes and the interface jump nodes during their use of the health management system. This relationship network contains the content semantic description knowledge of multiple visual interfaces, which details the switching data between each visual interface and other interfaces, especially the switching data of the target visual interface corresponding to the target patient user tags.

[0086] Next, the system combines the currently associated visual feature relationship network with the past interface module visual feature relationship network to deeply mine the switching behavior vectors of each visual interface and the remaining other visual interfaces in terms of interface module visual features. These vectors actually describe the switching patterns and habits of patients between different interfaces. By analyzing these switching behavior vectors, the system can generate a detailed description of the interface switching behavior and further identify the behavior requirements for these descriptions, thereby obtaining the interface requirement identification vectors. These vectors reflect the possible requirements and expectations of patients when using the interface.

[0087] Then, the system analyzes the interface display jump characteristics based on these interface requirement identification vectors. This process mainly analyzes the possible jump paths and selections of patients when operating the interface, as well as the reasons and motivations behind these selections. The results of the analysis will provide important clues for the system to optimize the interface layout and navigation process.

[0088] Finally, the system determines the interface module switching decision characteristics corresponding to the target patient user tags under the jump node based on the interface module visual features of the target visual interface under the visualization interaction interface jump node in the analysis results. These decision characteristics will guide the system on how to provide a more personalized and efficient interface experience for patients, including but not limited to adjusting the interface layout, optimizing the navigation process, and recommending relevant content.

[0089] Through the application of this intelligent medical user big data management system, the blood glucose control level, self-management level, and quality of life of elderly patients with type 2 diabetes can be effectively improved. At the same time, the system also provides important reference and support for medical staff in the intelligent health management practice of elderly patients with type 2 diabetes outside the hospital.

[0090] In yet another specific application scenario, the system first identifies target patient users, namely elderly patients with type 2 diabetes, and determines their behaviors and preferences when using the health management system based on their user tags (such as age, gender, disease duration, treatment methods, etc.). The system also records and analyzes the jump nodes between different visual interaction interfaces of these patients, and these nodes reflect the navigation paths and selections of patients during use. By collecting and analyzing this data, the system constructs a visual feature relationship network of past interface modules. This relationship network is a complex network structure that contains content semantic description knowledge of multiple visual interfaces. This knowledge describes the functions, layouts, elements of each visual interface, as well as their relationships and switching patterns with other interfaces. In particular, the system will focus on the target visual interface corresponding to the target patient user tags and analyze the switching data between it and other interfaces.

[0091] Then, the system uses the associated visual feature relationship network (which may be a predefined network or a network generated based on machine learning algorithms) and the visual feature relationship network of past interface modules to further explore the switching behaviors between interfaces. It analyzes the similarities and differences in the visual features of interface modules between each visual interface and the remaining other visual interfaces, and calculates the switching behavior vectors between them. These vectors not only describe the switching frequencies and patterns between interfaces, but also reflect the behaviors and preferences of patients during the switching process. Through in-depth analysis of these switching behavior vectors, the system can generate detailed descriptions of interface switching behaviors. These descriptions may include the types of switching (such as sequential switching, random switching, backtracking switching, etc.), the frequencies and durations of switching, and the user behaviors during the switching process (such as clicking, swiping, inputting, etc.). Then, the system conducts behavior requirement recognition on these descriptions and extracts key interface requirement recognition vectors. These vectors reflect the possible requirements, expectations, and problems of patients when using the interface, providing important clues for subsequent interface optimization.

[0092] Next, the system analyzes the display jump characteristics of the interface based on the interface requirement recognition vectors. It analyzes the possible jump paths and selections of patients when operating the interface and tries to understand the reasons and motivations behind these selections. For example, patients may often jump from the "Health Education" interface to the "Exercise Health" interface, indicating that they may be interested in the impact of exercise on diabetes and hope to learn more relevant information. By analyzing the display jump characteristics of the interface, the system can gain an in-depth understanding of how patients use and navigate the health management system. These understandings can not only help the system optimize the interface layout and navigation process (such as placing highly relevant interfaces together or providing a more intuitive navigation method), but also provide a basis for the system to recommend relevant content (such as recommending relevant health education articles or exercise plans according to the interests and needs of patients).

[0093] Finally, the system determines the interface module switching decision features based on the visual features of the interface modules of the target visual interface under the visual interaction interface jump nodes in the parsing result. These decision features are a set of rules and models that describe how the system should switch and display interface modules in different situations. For example, when a patient jumps from the "Basic Information" interface to the "My Blood Glucose" interface, the system may dynamically adjust the display content and layout of the "My Blood Glucose" interface according to the patient's blood glucose data and historical records.

[0094] By applying these interface module switching decision features, the system can provide a more personalized and efficient interface experience for patients. This can not only improve patient satisfaction and compliance (because they can more easily find and use the information and functions they need), but also help medical staff better understand and manage the patient's health condition (because they can evaluate the patient's treatment effect and quality of life through the data collected and analyzed by the system).

[0095] It should be noted that for S110 - S140, according to the target patient user tags and visual interaction interface jump nodes, obtain the historical interface module visual feature relationship network. This step mainly obtains the interface feature relationship network based on user tags and interaction behaviors, and has no direct association with direct disease diagnosis or treatment.

[0096] Combine the associated visual feature relationship network and the historical interface module visual feature relationship network to mine the switching behavior vectors between the interface module visual features of each visual interface and the remaining visual interfaces. This step is a process of data mining and analysis, and also does not directly involve disease diagnosis or treatment.

[0097] Conduct behavior requirement recognition on the interface switching behavior description to obtain the interface requirement recognition vector. This step is the analysis and understanding of user behavior, aiming to optimize the user interface, rather than directly performing disease diagnosis or treatment.

[0098] Based on the interface requirement recognition vector, perform interface display jump feature parsing to obtain the parsing result. This step optimizes the interface display and jump features based on the analysis result of user behavior requirements, and also does not directly involve disease diagnosis or treatment.

[0099] Based on the visual features of the interface modules of the target visual interface under the visual interaction interface jump nodes in the parsing result, determine the interface module switching decision features corresponding to the target patient user tags. This step is the process of determining user interface decisions and also does not directly involve disease diagnosis or treatment.

[0100] In summary, the above content mainly involves the optimization of the user interface and the analysis of user behavior, and does not directly involve methods for diagnosing or treating diseases. These contents are closer to user interface design, user experience optimization, and data analysis and processing methods in the field of computer technology, and are technical solutions that can be patented.

[0101] In some exemplary embodiments, the switching behavior vectors between the interface module visual features of each visible interface and the remaining visible interfaces are mined by combining the associated visual feature relationship network and the visual feature relationship network of the past interface modules, obtaining a description of the interface switching behavior, and performing behavior requirement recognition on the description of the interface switching behavior to obtain an interface requirement recognition vector, including: through the associated visual feature relationship network of the current residual branch, based on the original visual feature relationship network of the past interface modules, and the interface requirement recognition vector generated by the previous residual branch, mining the switching behavior vectors between the interface module visual features of each visible interface and the remaining visible interfaces, obtaining a description of the interface switching behavior, and performing behavior requirement recognition on the description of the interface switching behavior to obtain an interface requirement recognition vector, where, if the current residual branch is the first residual branch, the interface requirement recognition vector generated by the previous residual branch is a zero vector; taking the next residual branch of the current residual branch as the new current residual branch, and jumping to the step of mining the switching behavior vectors between the interface module visual features of each visible interface and the remaining visible interfaces through the associated visual feature relationship network of the current residual branch, based on the original visual feature relationship network of the past interface modules, and the interface requirement recognition vector generated by the previous residual branch, obtaining a description of the interface switching behavior, and performing behavior requirement recognition on the description of the interface switching behavior to obtain an interface requirement recognition vector, until the end residual branch outputs the interface requirement recognition vector.

[0102] In some exemplary embodiments, the system implements a deep technical solution to finely understand and optimize the navigation behavior of users in the visual interaction interface. The following is a detailed example explanation of this technical solution.

[0103] First, the system maintains two key relationship networks: the associated visual feature relationship network and the visual feature relationship network of the past interface modules. The associated visual feature relationship network captures the associations and mutual influences of visual features between different visible interfaces; while the visual feature relationship network of the past interface modules records the relationships and transformation patterns between the visual features of each interface module when the user interacted with the interface in the past.

[0104] The workflow of the system begins with delving into the switching behavior vectors between the visual feature relationships of each visible interface and the remaining visible interfaces by means of the associated visual feature relationship network of the current residual branch, in combination with the original visual feature relationship network of the past interface modules and the interface requirement recognition vector generated by the previous residual branch (for the first residual branch, this vector is a zero vector). This switching behavior vector encodes the behavior patterns, frequencies, and trends when the user switches from one interface module to another.

[0105] Next, the system generates interface switching behavior descriptions using these switching behavior vectors. These descriptions reflect in detail information such as the user's navigation paths, dwell times, switching preferences, etc. between interfaces, providing rich context for the system to understand user behavior.

[0106] Then, the system conducts behavior requirement recognition on the interface switching behavior descriptions. By analyzing the user's switching behavior, the system can identify the user's potential needs, expectations, or problems encountered. These needs may be the desire for specific functions, suggestions for improving the interface layout, or requirements for optimizing the interaction process, etc. The results of the behavior requirement recognition are encoded into an interface requirement recognition vector, which contains the user's improvement and optimization suggestions for each interface module.

[0107] After that, the system takes the next residual branch of the current residual branch as the new current residual branch and repeats the above process: mining the switching behavior vector through the associated visual feature relationship network, generating interface switching behavior descriptions, conducting behavior requirement recognition, and obtaining a new interface requirement recognition vector. This process is iterated between residual branches, and each residual branch further refines and optimizes the understanding of user behavior based on the previous branch.

[0108] Finally, when the last residual branch outputs its interface requirement recognition vector, the system completes a comprehensive analysis of user behavior. This final interface requirement recognition vector contains the system's in-depth understanding of user behavior requirements, providing strong data support for subsequent interface design optimization and personalized services.

[0109] Through this technical solution, the system can not only accurately capture the navigation behavior patterns of users in the visual interaction interface but also deeply understand the potential needs and expectations of users, thereby providing a more intelligent, efficient, and user-friendly interface interaction experience for users.

[0110] It should be understood that the above content describes a process of processing the visual feature relationship network of interface modules through multiple residual branches to mine interface switching behavior vectors and conduct behavior requirement recognition. This process seems to be a technical solution for user interface optimization and user experience analysis. It identifies the user's needs by analyzing the switching behavior of the user between visible interfaces and optimizes the interface design accordingly.

[0111] Specifically, this process includes using the associated visual feature relationship network and the past interface module visual feature relationship network to mine the interface switching behavior vectors, obtaining the interface switching behavior descriptions, and then performing behavior requirement recognition on these descriptions to obtain the interface requirement recognition vectors. This process is iteratively carried out among multiple residual branches, and each residual branch generates a new interface requirement recognition vector based on the output of the previous branch and the original past interface module visual feature relationship network.

[0112] Judging from the description, this process does not directly involve the diagnosis or treatment of diseases. It focuses more on user interface design and user experience optimization. By analyzing the interface switching behavior of users, it identifies the needs of users and improves the interface design accordingly. Therefore, this process does not belong to the method of disease diagnosis and treatment.

[0113] In summary, the above content mainly involves the optimization of the user interface and the analysis of the user experience, and does not directly involve the method of disease diagnosis or treatment. Therefore, it can be determined that the above content is not a method of disease diagnosis and treatment. These contents are closer to the user interface design, user experience optimization, and data analysis and processing methods in the field of computer technology, and are technical solutions that can be patented.

[0114] In some further preferred embodiments, the residual branch includes a first behavior requirement recognition layer, a second behavior requirement recognition layer, a third behavior requirement recognition layer, and a behavior requirement splicing layer; through the associated visual feature relationship network of the current residual branch, based on the original past interface module visual feature relationship network and the interface requirement recognition vector generated by the previous residual branch, mining the switching behavior vectors between the visual feature of each visible interface and the remaining visible interfaces to obtain an interface switching behavior description, and performing behavior requirement recognition on the interface switching behavior description to obtain an interface requirement recognition vector, including: through the associated visual feature relationship network of the first behavior requirement recognition layer in the current residual branch, based on the original past interface module visual feature relationship network and the interface requirement recognition vector generated by the previous residual branch, mining the switching behavior vectors between the visual feature of each visible interface and the remaining visible interfaces to obtain a first interface switching behavior description, and performing first behavior requirement recognition processing on the first interface switching behavior description to obtain a first interface requirement recognition vector; through the associated visual feature relationship network of the second behavior requirement recognition layer in the current residual branch, based on the original past interface module visual feature relationship network and the interface requirement recognition vector generated by the previous residual branch, mining the switching behavior vectors between the visual feature of each visible interface and the remaining visible interfaces to obtain a second interface switching behavior description, and performing second behavior requirement recognition processing on the second interface switching behavior description to obtain a second interface requirement recognition vector; through the third behavior requirement recognition layer in the current residual branch, performing vector multiplication on the second interface requirement recognition vector and the interface requirement recognition vector generated by the previous residual branch to obtain a first linkage requirement feature; through the associated visual feature relationship network of the third behavior requirement recognition layer, based on the original past interface module visual feature relationship network and the first linkage requirement feature, mining the switching behavior vectors between the visual feature of each visible interface and the remaining visible interfaces to obtain a third interface switching behavior description, and performing third behavior requirement recognition processing on the third interface switching behavior description to obtain a third interface requirement recognition vector; through the behavior requirement splicing layer, determining the second linkage requirement feature between the first interface requirement recognition vector and the interface requirement recognition vector generated by the previous residual branch, and the third linkage requirement feature between the target feature relationship network corresponding to the first interface requirement recognition vector and the third interface requirement recognition vector, determining the sum of the second linkage requirement feature and the third linkage requirement feature to obtain the interface requirement recognition vector generated by the current residual branch, wherein the target feature relationship network is obtained by subtracting the first interface requirement recognition vector from the reference feature relationship network.

[0115] In some other preferred embodiments, the technical solution of the system further refines the structure and function of the residual branch to improve the recognition accuracy of user behavior requirements. Specifically, each residual branch now includes four key layers: the first behavior requirement recognition layer, the second behavior requirement recognition layer, the third behavior requirement recognition layer, and the behavior requirement splicing layer. These layers work together to analyze and understand the user's interface switching behavior in a step-by-step manner.

[0116] First, the system uses the first behavior demand recognition layer in the current residual branch, and uses its associated visual feature relationship network, combined with the original past interface module visual feature relationship network and the interface demand recognition vector generated by the previous residual branch, to mine the switching behavior vector between the interface module visual features of each visual interface and the remaining visual interfaces. This process reveals the user's initial behavior pattern when switching between interfaces and generates a first interface switching behavior description. Next, the system performs first behavior demand recognition processing on the first interface switching behavior description, identifies the user's initial needs, and encodes them into the first interface demand recognition vector.

[0117] Then, the system enters the second behavior demand recognition layer, and also uses the associated visual feature relationship network and related information to further mine the interface switching behavior vector and obtain the second interface switching behavior description. This description provides more details and contextual information of the user's behavior. The system performs second behavior demand recognition processing on the second interface switching behavior description, identifies the user's deeper needs, and encodes them into the second interface demand recognition vector.

[0118] At the third behavior demand identification layer, the system first performs a special operation: vector multiplication of the second interface demand identification vector and the interface demand identification vector generated by the previous residual branch to obtain the first linkage demand feature. This feature reflects the association and interaction between the current branch and the previous branch in terms of user behavior needs. Then, the system again uses the associated visual feature relationship network, combined with the original past interface module visual feature relationship network and the first linkage demand feature, to dig deeper interface switching behavior vectors and generate a third interface switching behavior description. The third interface switching behavior description is processed for third behavior demand identification, and the system obtains the third interface demand identification vector, which contains higher-level needs and trends of user behavior.

[0119] Finally, the behavioral requirement splicing layer is responsible for integrating the requirement recognition results of each layer. It first determines the second linkage requirement feature between the first interface requirement recognition vector and the interface requirement recognition vector generated by the previous residual branch, which reflects the requirement linkage relationship between the current layer and the previous layer. At the same time, it also determines the third linkage requirement feature between the target feature relationship network corresponding to the first interface requirement recognition vector and the third interface requirement recognition vector. The target feature relationship network is obtained by subtracting the reference feature relationship network from the first interface requirement recognition vector, and it represents the user requirement features unique to the current layer. The behavioral requirement splicing layer adds the second linkage requirement feature and the third linkage requirement feature to obtain the final interface requirement recognition vector generated by the current residual branch.

[0120] Through this refined residual branch structure and workflow, the system can more accurately capture and understand the complex behavior patterns of users in the visual interaction interface, providing more powerful support for subsequent interface optimization and personalized services.

[0121] In some application scenarios of intelligent health management for elderly patients with type 2 diabetes, on a smart medical health management platform, Mr. Li, a 65-year-old patient with type 2 diabetes, has just registered and logged in to the system. He hopes to better manage his health through this platform.

[0122] Patient-side user interface

[0123] Mr. Li uploaded his medical record information and personal information, including medical history, drug allergy history, family medical history, etc., on the [Patient-side User Center Interface]. This information was synchronized to the [Medical Staff-side Data Information Interface] for medical staff to view and reference.

[0124] Patient-side health education interface

[0125] Mr. Li browsed the [Patient-side Health Education Interface], watched videos and articles on dietary guidance, exercise health, psychological guidance, etc. for type 2 diabetes. He completed some knowledge test questionnaires, and the system gave corresponding points according to his completion. These points can be used to exchange health-related products in the platform's point mall.

[0126] Patient-side exercise health interface and diet management interface

[0127] Mr. Li checks the exercise guidance tutorials on the [Patient-side Exercise Health Interface] every day and exercises moderately according to the tutorials. His exercise data is monitored in real time by a smart bracelet and uploaded to the platform. At the same time, he also records his diet situation, including the types of food and intake for each meal, on the [Patient-side Diet Management Interface]. These data are synchronized to the [Medical Staff-side Data Information Interface] for medical staff to analyze and evaluate.

[0128] Patient-side Online Interaction Interface

[0129] Mr. Li consulted medical staff about his condition and medication questions in the [Cloud Doctors] module of the [Patient-side Online Interaction Interface] and received a timely response. He also shared his blood sugar control experience and insights with other diabetes patients in the [Diabetes Forum] and actively participated in the discussions in the forum.

[0130] Medical Staff-side Data Information Interface and Online Consultation Interface

[0131] Medical staff viewed Mr. Li's medical record information, personal information, life management data, and health dynamic data in the [Medical Staff-side Data Information Interface]. They evaluated Mr. Li's condition based on this data and replied to his consultation questions in the [Medical Staff-side Online Consultation Interface]. At the same time, they also participated in the discussions in the [Diabetes Forum] and provided professional advice and guidance to patients.

[0132] Technical Implementation

[0133] In this intelligent medical and health management platform, patients' behavioral data is collected and analyzed in real time. Through the associated visual feature relationship network of the current residual branch, based on the original visual feature relationship network of the past interface module and the interface requirement recognition vector generated by the previous residual branch, the system mines the switching behavior vectors between the visual features of each visible interface and the remaining visible interfaces. These vectors describe the switching behavior and frequency of patients between different interfaces.

[0134] Through multi-level in-depth analysis and processing, the system obtains the interface switching behavior description and performs behavior requirement recognition processing on these descriptions to obtain the interface requirement recognition vector. These vectors reflect patients' needs and expectations for interface functions, layouts, interaction processes, and user experiences.

[0135] Finally, through the behavior requirement splicing layer, the system integrates the behavior requirement recognition results of each previous layer to obtain the final interface requirement recognition vector generated by the current residual branch. This vector is a comprehensive description that combines patients' basic needs, deep needs, and personalized needs.

[0136] Based on this requirement recognition vector, the platform can optimize and improve the interface design in a targeted manner to improve patients' satisfaction and compliance. At the same time, medical staff can also provide more accurate and personalized health management services for patients based on this data.

[0137] It should be understood that the above description involves a complex technical process, which includes multiple behavior demand identification layers and a behavior demand splicing layer, which work together to mine and analyze the switching behavior between user interfaces and ultimately generate an interface demand identification vector. This process involves multiple steps, including using the associated visual feature relationship network and the past interface module visual feature relationship network to mine the switching behavior vector, performing multi-level behavior demand identification processing, and linking and integrating various identification results through different methods (such as vector multiplication and difference).

[0138] Although this process may seem complex and involves a lot of data analysis and processing, its core purpose is not to diagnose or treat diseases. Instead, it focuses more on understanding and optimizing the behavior and needs of users when interacting with visual interfaces. This is achieved by deeply analyzing the user's switching patterns between interfaces, identifying their behavioral needs, and generating an interface demand identification vector based on this. This vector can be used to improve the user interface design and provide a better user experience.

[0139] Therefore, from the core purpose and actual application scenarios, the content does not belong to the diagnosis and treatment of diseases. It is more of a technical means of user interface optimization and user experience analysis. Although it may involve the analysis and processing of user behavior and needs, these analyses and processing are not for the purpose of diagnosing or treating any disease. Instead, they are for improving user interface design and enhancing user experience. In summary, it can be concluded that the content is not a disease diagnosis and treatment method, but a technical means of user interface optimization and user experience analysis.

[0140] In other possible embodiments, the number of the visual feature relationship networks of the past interface modules is at least two, the visual interfaces corresponding to each visual feature relationship network of the past interface modules are the same, and the interface analysis node ranges are different; the combined associated visual feature relationship network and the visual feature relationship network of the past interface modules mine the switching behavior vectors between the visual features of the interface modules of each visual interface and the remaining visual interfaces to obtain an interface switching behavior description, and perform behavioral requirement identification on the interface switching behavior description to obtain an interface requirement identification vector, including: mining the switching behavior vectors between the visual features of the interface modules of each visual interface and the remaining visual interfaces based on the visual feature relationship networks of each past interface module through the associated visual feature relationship network to obtain the interface switching behavior description corresponding to each of the visual feature relationship networks of the past interface modules, and perform behavioral requirement identification on each of the interface switching behavior descriptions to obtain the interface requirement identification vector corresponding to each of the visual feature relationship networks of the past interface modules.

[0141] In some embodiments, the technical solution involves processing visual feature relationship networks of multiple past interface modules. These relationship networks each correspond to the same visual interface, but their ranges of interface analysis nodes are different. This means that although they are all analyzing the same visual interface, the nodes or elements they focus on may vary.

[0142] First, each visual feature relationship network of past interface modules captures the relationships between module visual features in the visual interface. These relationships may include positional relationships, size relationships, color relationships, etc. between modules. Due to the different ranges of analysis nodes, even for the same visual interface, different relationship networks may reveal different visual feature relationships.

[0143] Next, the technical solution combines the associated visual feature relationship network and these visual feature relationship networks of past interface modules to mine the switching behavior vectors of interface module visual features between each visual interface and the remaining visual interfaces. Here, the "switching behavior vector" can be understood as a quantitative representation describing how one interface transforms into another, and it may include information such as which modules have changed and how these changes occur.

[0144] By mining these switching behavior vectors, the technical solution can obtain interface switching behavior descriptions. These descriptions detail all the changes that occur when switching from one interface to another. Then, behavior requirement recognition is performed on these interface switching behavior descriptions. The purpose of this step is to understand the user requirements or intentions reflected behind these switching behaviors.

[0145] Finally, the results of behavior requirement recognition are transformed into interface requirement recognition vectors. These vectors express the user's requirements for the interface in a way that can be understood and processed by a computer system. Each visual feature relationship network of past interface modules will correspond to such an interface requirement recognition vector, thus forming a vector set, which provides an important reference basis for subsequent user interface design or optimization.

[0146] In this process, newly emerging technical terms such as "switching behavior vector" and "interface requirement recognition vector" are key tools used to quantitatively describe interface switching behaviors and user requirements. They enable the technical solution to understand and meet user requirements in a more precise and operable manner.

[0147] In the application scenario of intelligent health management for elderly patients with type 2 diabetes, the technical solution can be implemented in detail as follows.

[0148] First, the system constructs at least two visual feature relationship networks for past interface modules. These relationship networks are all associated with the same visual interface, but the range of interface nodes analyzed by each relationship network is different. For example, one relationship network may focus on analyzing the button layout and color combination of the blood glucose monitoring interface, while another relationship network may focus on the font size and contrast of the user's personal information setting interface.

[0149] These visual feature relationship networks for past interface modules are established by analyzing the interface interaction behaviors of elderly patients with type 2 diabetes when using a health management application. The system records information such as the visual focus movement trajectory, click events, and dwell time of patients when using different function interfaces, and then uses this data to construct the visual feature relationship network between interface modules.

[0150] Next, the system combines the associated visual feature relationship network and these visual feature relationship networks for past interface modules to deeply mine the switching behavior vectors of the visual features of interface modules between each visual interface and the remaining visual interfaces. Here, the "switching behavior vector" is a quantitative description that reveals the change rules of visual focus and interaction behaviors when a patient switches from one interface to another.

[0151] For example, when a patient switches from the blood glucose monitoring interface to the diet record interface, the system can capture that the modules the patient focuses on change from the blood glucose data chart to the food intake and nutritional composition table. This switching behavior vector contains information such as the moving distance, speed, and direction of the patient's visual focus.

[0152] By mining these switching behavior vectors, the system can obtain a detailed description of the interface switching behavior. These descriptions not only record the patient's behavior trajectory during the interface switching process but also reflect the patient's usage habits and preferences.

[0153] Then, the system conducts behavior demand recognition on these interface switching behavior descriptions. The purpose of this step is to understand the patient's interface usage needs in order to provide them with more personalized and convenient health management services. For example, if the system finds that patients often get lost or cannot find the desired function module when switching interfaces, then the system can optimize the interface design for these problems, such as adding navigation prompts or adjusting the module layout.

[0154] Finally, the results of the behavior demand recognition will be converted into interface demand recognition vectors. These vectors express the patient's needs for the interface in a way that can be understood and processed by a computer system. The system can adjust the interface design according to these vectors to meet the patient's usage needs and improve their user experience.

[0155] Throughout the process, through continuous learning and optimization, the system can gradually adapt to the usage habits and preferences of different patients, providing them with more accurate and personalized health management services. At the same time, this technical solution based on the visual feature relationship network also provides useful references for other types of intelligent health management applications.

[0156] It should be understood that the above embodiments involve using the visual feature relationship network of past interface modules and the associated visual feature relationship network to mine the switching behavior vectors between visual interfaces and obtain the interface switching behavior descriptions. Then, behavior requirement recognition is performed on these descriptions to obtain the interface requirement recognition vectors. This process mainly analyzes and understands the user's needs based on the user's interface interaction behavior in order to optimize the user interface design.

[0157] As can be seen from the description, this process does not involve any medical examinations, tests, analyses, or treatment means. It mainly focuses on user interface design and user experience optimization, rather than disease diagnosis or treatment. Although this process may involve the analysis of user behavior and needs, the purpose of these analyses is to improve the user interface, rather than to diagnose or treat diseases.

[0158] In addition, terms such as "visual feature relationship network of past interface modules" and "associated visual feature relationship network" mentioned in the above content, as well as the mining and recognition processes between them, are all concepts and methods in the fields of computer technology and user interface design, and have no direct association with disease diagnosis and treatment in the medical field.

[0159] In summary, it can be concluded that the above content is not a disease diagnosis and treatment method. It is more like a technical means for user interface optimization and user experience analysis, belonging to the applications in the fields of computer technology and user interface design.

[0160] In some other exemplary embodiments, parsing the interface display jump features according to the interface requirement recognition vector to obtain a parsing result includes: weighting the interface requirement recognition vectors corresponding to each of the visual feature relationship networks of past interface modules to obtain a weighted interface requirement recognition vector; parsing the interface display jump features according to the weighted interface requirement recognition vector to obtain a parsing result.

[0161] In the application scenario of intelligent health management for elderly patients with type 2 diabetes, the implementation of the technical solution can be further refined as follows.

[0162] The system will first process the interface requirement recognition vectors generated by multiple visual feature relationship networks of past interface modules. These vectors reflect the needs and preferences of elderly patients for different interface elements when using the health management application. Since the range of interface nodes analyzed by each relationship network is different, the interface requirement recognition vectors generated by them may also vary.

[0163] To obtain a comprehensive interface requirement recognition vector that can reflect the overall needs of patients, the system will perform weighted processing on the interface requirement recognition vectors corresponding to the visual feature relationship networks of each past interface module. The basis for weighting can be the importance, reliability of each relationship network, or the usage frequency of patients for the corresponding interface, etc. Through weighted processing, the system can obtain an interface requirement recognition weighted vector, which more accurately reflects the actual needs and preferences of patients.

[0164] Next, the system will parse the interface display jump characteristics based on this interface requirement recognition weighted vector. The purpose of this step is to understand the characteristics of interface display and jump when patients use the application, and how these characteristics meet the needs of patients. For example, the system can analyze the switching frequency, switching path, and stay time between different interfaces of patients to obtain the characteristics of interface display jump.

[0165] During the parsing process, the system will consider factors such as patients' usage habits, cognitive abilities, and health conditions. For example, for elderly patients with poor eyesight, the system may increase the font size and contrast to reduce their reading difficulties; for patients who often forget the operation steps, the system may provide more detailed navigation and prompt information to help them complete the operation smoothly.

[0166] Finally, the system will obtain an analysis result of the interface display jump characteristics. This result contains specific suggestions on how to optimize the interface design, improve the user experience, and meet the needs of patients. For example, the system may suggest adjusting the position or size of a certain button, adding a shortcut for a certain function, or optimizing the layout of a certain interface, etc.

[0167] Through this technical solution, the system can more accurately understand the needs and preferences of elderly patients with type 2 diabetes, and provide them with more personalized and convenient health management services. At the same time, this data-driven method also provides useful references for other types of intelligent health management applications.

[0168] In some possible embodiments, parsing the interface display jump features based on the interface requirement identification vector to obtain a parsing result includes: parsing the interface display jump features based on the interface requirement identification vector to obtain the parsing result of each visual interface among the multiple visual interfaces; determining the interface module switching decision feature corresponding to the target patient user label under the visual interaction interface jump node according to the interface module visual feature of the target visual interface under the visual interaction interface jump node in the parsing result includes: obtaining the interface module visual feature of the target visual interface under the visual interaction interface jump node according to the parsing result of each visual interface among the multiple visual interfaces, and determining the interface module switching decision feature corresponding to the target patient user label under the visual interaction interface jump node.

[0169] In the application scenario of intelligent health management for elderly patients with type 2 diabetes, the technical solution can be specifically implemented as follows.

[0170] First, the system will parse the interface display jump features based on the previously generated interface requirement identification vectors. These vectors are generated based on the interface interaction behaviors of elderly patients when using the health management application, reflecting their needs and preferences for different interface elements.

[0171] The parsing process will be carried out for each of the multiple visual interfaces. The system will analyze the interface requirement identification vectors of each visual interface and extract the features related to interface display and jump. These features may include the layout of the interface, the position and size of buttons, the color and size of fonts, the use of pictures, etc., as well as the switching behaviors of patients between these interfaces, such as the frequency, path, and order of switching.

[0172] For example, the system may find that elderly patients prefer to use an interface with large fonts and high contrast when viewing blood glucose data, while they prefer to use an interface with food pictures and detailed nutrition composition tables when recording their diet. These findings are the parsing results of the interface display jump features.

[0173] Next, the system will determine the interface module visual features of the target visual interface under the visual interaction interface jump node according to these parsing results. Here, the "target visual interface" refers to the interface that the patient is currently using or about to use, and the "visual interaction interface jump node" refers to the decision point for the patient to switch between different interfaces.

[0174] The system will analyze the interface requirement identification vectors and interface display jump features of the patient at these decision points to determine what interface module visual features the target visual interface should have. These features should be able to meet the needs of the patient, improve their usage experience, and guide them to perform effective interface switching.

[0175] For example, when an elderly patient jumps from the blood glucose monitoring interface to the diet record interface, the system may, based on the previous parsing results, design the food pictures and nutritional composition tables on the diet record interface to be more prominent and legible, so that the patient can quickly find and understand the relevant information.

[0176] Finally, the system will determine the interface module switching decision features corresponding to the target patient user label under the visual interaction interface jump node. Here, the "target patient user label" refers to the personalized labels set by the system for elderly patients, such as age, gender, vision condition, cognitive ability, etc. These labels help the system to more accurately understand the needs and preferences of the patients.

[0177] The system will combine the patient's user labels and their behavioral data during interface switching to determine the interface module switching decision features that are most suitable for them. These features should be able to reflect the patients' usage habits and preferences, and help them complete the interface switching operation more smoothly and efficiently.

[0178] Through this technical solution, the system can provide more personalized and convenient health management services for elderly patients with type 2 diabetes, improving their usage experience and quality of life. At the same time, this data-driven method also provides useful reference for other types of intelligent health management applications.

[0179] In some alternative embodiments, for obtaining the past interface module visual feature relationship network according to the target patient user label and the visual interaction interface jump node, the past interface module visual feature relationship network includes content semantic description knowledge of multiple visual interfaces, including: determining at least two interface analysis node ranges before the visual interaction interface jump node according to the visual interaction interface jump node of the visual feature of the interface module to be predicted; disassembling each interface analysis node range into multiple operation node sets based on a preset node step size; determining the target visual interface corresponding to the target patient user label of the visual feature of the interface module to be predicted and the sample visual interface corresponding to the target visual interface as the visual interfaces to be processed; for each visual interface to be processed, obtaining the interface module switching data between the visual interface to be processed and the remaining visual interfaces to be processed in each operation node set; for each interface analysis node range, obtaining the content semantic description knowledge of each visual interface in the interface analysis node range according to the interface module switching data between the visual interfaces to be processed and the remaining visual interfaces to be processed in the operation node set of the interface analysis node range; and obtaining the past interface module visual feature relationship network corresponding to each interface analysis node range according to the content semantic description knowledge corresponding to each interface analysis node range.

[0180] In the application scenario of intelligent health management for elderly patients with type 2 diabetes, the implementation of the technical solution can be specifically refined as follows.

[0181] First, the system will obtain the past interface module visual feature relationship network according to the target patient user tags and the current visual interaction interface jump nodes. This relationship network contains the content semantic description knowledge of multiple visual interfaces, which is a deep understanding of the interface elements and the patient's interaction behavior.

[0182] To construct this relationship network, the system will first determine at least two interface analysis node ranges before the current jump node. These node ranges represent the interface sequence that the patient has passed through before reaching the current jump node. For example, if the patient jumps from the main interface to the blood glucose monitoring interface and then to the diet record interface, the main interface and the blood glucose monitoring interface are the first two analysis node ranges for the diet record interface.

[0183] Next, the system will disassemble each interface analysis node range into multiple operation node sets. Here, the operation node set refers to the specific operations that the patient performs on each interface, such as clicking a button, swiping the screen, etc. The basis for disassembly can be a pre-set node step, which can be adjusted according to the patient's operation habits and the complexity of the interface.

[0184] Then, the system will determine the corresponding target visual interface and sample visual interface according to the target patient user tags. The target visual interface is the interface that the patient is currently using or about to use, while the sample visual interface is the interface used for reference and comparison. They can be different interfaces of the same type or interfaces of different types.

[0185] Next, for each visual interface to be processed, the system will obtain the interface module switching data between it and the remaining visual interfaces to be processed in each operation node set. These data reflect the patient's behavior patterns and preferences when switching between different interfaces.

[0186] Then, for each interface analysis node range, the system will obtain the content semantic description knowledge of each visual interface within this range according to the interface module switching data in its operation node set. These knowledge are a deep understanding of the interface elements and the patient's interaction behavior, which can help the system better understand the patient's needs and preferences.

[0187] Finally, the system will obtain the past interface module visual feature relationship network corresponding to this range according to the content semantic description knowledge corresponding to each interface analysis node range. This relationship network is the system's understanding and memory of the patient's past interaction behavior, which can help the system more accurately predict the patient's future interaction behavior and provide them with more personalized and convenient health management services.

[0188] In some alternative embodiments, the interface display jump feature is analyzed based on the identified vector of interface requirements to obtain an analysis result, including: performing a knowledge transformation on the identified vector of interface requirements to obtain transformed knowledge of interface requirements; and analyzing the interface display jump feature according to the transformed knowledge of interface requirements to obtain an analysis result.

[0189] In the application scenario of intelligent health management for elderly patients with type 2 diabetes, the technical solution executed by the system can be explained in detail as follows:

[0190] First, the system performs a knowledge transformation on the already obtained identified vector of interface requirements. This knowledge transformation is a processing process that converts the original identified vector of interface requirements into a form that is easier to understand and analyze, namely, the transformed knowledge of interface requirements. This process may involve operations such as data standardization, normalization, dimensionality reduction, or feature extraction to better reveal the hidden information and patterns in the vector.

[0191] For example, the system may standardize certain elements in the identified vector of interface requirements so that their values fall within a unified range, thereby eliminating the dimensionality differences between different elements. Or, the system may use methods such as principal component analysis to perform dimensionality reduction on the vector and extract its main features to simplify the subsequent analysis process.

[0192] After obtaining the transformed knowledge of interface requirements, the system uses this knowledge to analyze the interface display jump feature. This process mainly analyzes the jump behavior of patients between different interfaces and the relationship between these behaviors and interface elements. The system will identify features such as the residence time, click frequency, and jump path of patients on different interfaces according to the information in the transformed knowledge of interface requirements, as well as the relationship between these features and interface elements such as interface layout, button position, and font size.

[0193] For example, the system may find that when the position of a button on a certain interface is too close to the edge of the screen, it is difficult for elderly patients to accurately click on the button due to vision or finger dexterity limitations. At this time, the system will record this feature as a reference for optimizing the interface design.

[0194] Finally, the system will obtain an analysis result, which is a comprehensive description of the jump behavior of patients between different interfaces and the relationship between interface elements. Based on this analysis result, the system can evaluate whether the current interface design meets the needs of patients, whether there are areas that need to be optimized, and give specific optimization suggestions.

[0195] Through this technical solution, the system can more deeply understand the interface interaction behaviors of elderly patients with type 2 diabetes, discover the existing problems and obstacles, and provide them with more considerate and efficient health management services. At the same time, this data-driven method can also provide useful references for other types of intelligent health management applications.

[0196] In summary, the beneficial effects of the present invention are that by combining the target patient user tags and the visual interaction interface jump nodes, it is possible to efficiently obtain the visual feature relationship network of the past interface modules, which covers the content semantic description knowledge of multiple visual interfaces and the interface module switching data between them. This innovative method not only enriches the data basis for user interface design but also improves the switching efficiency between interfaces and the coherence of the user experience.

[0197] Furthermore, the present invention deeply excavates the interface module visual feature switching behavior vectors between each visual interface and the remaining visual interfaces by combining the associated visual feature relationship network and the visual feature relationship network of the past interface modules. This vectorized description method makes the interface switching behavior more accurate and quantifiable, providing a solid foundation for subsequent behavior requirement recognition.

[0198] By performing behavior requirement recognition on the interface switching behavior description, the present invention can accurately obtain the interface requirement recognition vector. This vector not only reflects the actual needs of users but also provides strong support for the personalization and intelligence of interface design.

[0199] In addition, the present invention also analyzes the interface display jump characteristics based on the interface requirement recognition vector, thereby obtaining a targeted analysis result. This result provides clear guidance for the interface module visual features of the target visual interface under the visual interaction interface jump node, making the interface design more in line with user expectations and usage habits.

[0200] Finally, by determining the interface module switching decision characteristics corresponding to the target patient user tags, the present invention realizes precise decision-making under the visual interaction interface jump node. This decision not only improves the response speed and accuracy of the user interface but also greatly enhances the user satisfaction and convenience during use.

[0201] In summary, the beneficial effects of the present invention are reflected in improving the efficiency and accuracy of user interface design, enhancing the coherence and personalization of the user experience, and increasing the response speed and user satisfaction of the user interface during visual interaction. These beneficial effects together constitute the significant advantages and innovative value of the present invention in the field of user interface design.

[0202] Please refer to Figure 2, an embodiment of the present invention further provides a big data management system 100 for intelligent medical users, including a processor 111, and a memory 112 and a bus 113 connected to the processor 111. Among them, the processor 111 and the memory 112 complete mutual communication through the bus 113. The processor 111 is used to call program instructions in the memory 112 to execute the above-mentioned user big data management method based on artificial intelligence and visualization.

[0203] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity or system including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent in such a process, method, commodity or system. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, commodity or system including the element.

[0204] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems or computer program products. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention can 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.

[0205] The above are only the embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the scope of the claims of the present invention.

Claims

1. A user big data management method based on artificial intelligence and visualization, characterized in that: Applied to the smart medical user big data management system, the method includes: According to the target patient user tag and the visual interactive interface jump node, a visual feature relationship network of past interface modules is obtained, wherein the visual feature relationship network of past interface modules includes content semantic description knowledge of multiple visual interfaces, each content semantic description knowledge includes interface module switching data between a corresponding visual interface and the remaining visual interfaces in the multiple visual interfaces, and the multiple visual interfaces include the target visual interface corresponding to the target patient user tag; Combine the associated visual feature relationship network and the past interface module visual feature relationship network to mine the switching behavior vector between the interface module visual features of each visual interface and the remaining visual interfaces, obtain an interface switching behavior description, perform behavior demand identification on the interface switching behavior description, and obtain an interface demand identification vector; Performing interface display jump feature analysis according to the interface requirement identification vector to obtain an analysis result; According to the interface module visual features of the target visual interface under the visualization interaction interface jump node in the analysis result, the interface module switching decision features corresponding to the target patient user label under the visualization interaction interface jump node are determined.

2. The user big data management method based on artificial intelligence and visualization according to claim 1 is characterized in that: The method combines the associated visual feature relationship network and the past interface module visual feature relationship network to mine the switching behavior vector between the interface module visual features of each visual interface and the remaining visual interfaces to obtain an interface switching behavior description, and performs behavior requirement recognition on the interface switching behavior description to obtain an interface requirement recognition vector, including: Through the associated visual feature relationship network of the current residual branch, based on the original past interface module visual feature relationship network and the interface requirement recognition vector generated by the previous residual branch, the switching behavior vector between the interface module visual features of each visual interface and the remaining visual interfaces is mined to obtain an interface switching behavior description, and the behavior requirement recognition is performed on the interface switching behavior description to obtain an interface requirement recognition vector, wherein, if the current residual branch is the first residual branch, the interface requirement recognition vector generated by the previous residual branch is a zero vector; The next residual branch of the current residual branch is used as the new current residual branch, and the branch is jumped to the associated visual feature relationship network through the current residual branch. Based on the original past interface module visual feature relationship network and the interface requirement recognition vector generated by the previous residual branch, the switching behavior vectors between the interface module visual features of each visual interface and the remaining visual interfaces are mined to obtain an interface switching behavior description, and the behavior requirement recognition is performed on the interface switching behavior description to obtain an interface requirement recognition vector, until the last residual branch outputs the interface requirement recognition vector.

3. The user big data management method based on artificial intelligence and visualization according to claim 2 is characterized in that: The residual branch includes a first behavior demand recognition layer, a second behavior demand recognition layer, a third behavior demand recognition layer, and a behavior demand splicing layer; The method comprises mining the switching behavior vectors between the visual features of the interface modules of each visual interface and the remaining visual interfaces through the associated visual feature network of the current residual branch, based on the original visual feature network of the past interface modules and the interface requirement recognition vector generated by the previous residual branch, obtaining an interface switching behavior description, and performing behavior requirement recognition on the interface switching behavior description to obtain an interface requirement recognition vector, including: Through the associated visual feature relationship network of the first behavior demand identification layer in the current residual branch, based on the original past interface module visual feature relationship network and the interface demand identification vector generated by the previous residual branch, the switching behavior vector between the interface module visual features of each visual interface and the remaining visual interfaces is mined to obtain a first interface switching behavior description, and the first behavior demand identification processing is performed on the first interface switching behavior description to obtain a first interface demand identification vector; Through the associated visual feature relationship network of the second behavior demand identification layer in the current residual branch, based on the original past interface module visual feature relationship network and the interface demand identification vector generated by the previous residual branch, the switching behavior vector between the interface module visual features of each visual interface and the remaining visual interfaces is mined to obtain the second interface switching behavior description, and the second behavior demand identification processing is performed on the second interface switching behavior description to obtain the second interface demand identification vector; Through the third line demand identification layer in the current residual branch, vector multiplication is performed on the second interface demand identification vector and the interface demand identification vector generated by the previous residual branch to obtain a first linkage demand feature; By using the associated visual feature relationship network of the third behavior demand identification layer, mining the switching behavior vectors between the interface module visual features of each visual interface and the remaining visual interfaces according to the original past interface module visual feature relationship network and the first linkage demand feature, obtaining a third interface switching behavior description, performing third behavior demand identification processing on the third interface switching behavior description, and obtaining a third interface demand identification vector; Through the behavior requirement splicing layer, determine the second linkage requirement feature of the first interface requirement identification vector and the interface requirement identification vector generated by the previous residual branch, as well as the third linkage requirement feature of the target feature relationship network corresponding to the first interface requirement identification vector and the third interface requirement identification vector, determine the sum of the second linkage requirement feature and the third linkage requirement feature, and obtain the interface requirement identification vector generated by the current residual branch, wherein the target feature relationship network is obtained by subtracting the reference feature relationship network from the first interface requirement identification vector.

4. The user big data management method based on artificial intelligence and visualization according to claim 1 is characterized in that: The number of the visual feature relationship networks of the past interface modules is at least two, and the visual interfaces corresponding to each visual feature relationship network of the past interface modules are the same, but the interface analysis node ranges are different; The combined associated visual feature relationship network and the visual feature relationship network of the past interface modules mine the switching behavior vectors between the visual features of the interface modules of each visual interface and the remaining visual interfaces to obtain an interface switching behavior description, and perform behavioral requirement identification on the interface switching behavior description to obtain an interface requirement identification vector, including: mining the switching behavior vectors between the visual features of the interface modules of each visual interface and the remaining visual interfaces based on the visual feature relationship network of each past interface module through the associated visual feature relationship network to obtain the interface switching behavior description corresponding to each of the visual feature relationship networks of the past interface modules, and perform behavioral requirement identification on each of the interface switching behavior descriptions to obtain the interface requirement identification vector corresponding to each of the visual feature relationship networks of the past interface modules.

5. The user big data management method based on artificial intelligence and visualization according to claim 4 is characterized in that: The performing of interface display jump feature analysis according to the interface requirement identification vector to obtain the analysis result includes: Weighting the interface requirement recognition vectors corresponding to the visual feature relationship networks of the past interface modules to obtain an interface requirement recognition weighted vector; According to the interface requirement identification weighted vector, interface display jump feature analysis is performed to obtain an analysis result.

6. The user big data management method based on artificial intelligence and visualization according to claim 1 is characterized in that: The performing interface display jump feature analysis according to the interface requirement identification vector to obtain the analysis result includes: performing interface display jump feature analysis according to the interface requirement identification vector to obtain the analysis result of each visual interface in the multiple visual interfaces; The method of determining the interface module switching decision feature corresponding to the target patient user tag under the visual interaction interface jump node based on the interface module visual features of the target visual interface under the visual interaction interface jump node in the analysis result includes: obtaining the interface module visual features of the target visual interface under the visual interaction interface jump node based on the analysis result of each visual interface in the multiple visual interfaces, and determining the interface module switching decision feature corresponding to the target patient user tag under the visual interaction interface jump node.

7. The user big data management method based on artificial intelligence and visualization according to claim 4 is characterized in that: According to the target patient user label and the visual interactive interface jump node, a visual feature relationship network of past interface modules is obtained, wherein the visual feature relationship network of past interface modules includes content semantic description knowledge of multiple visual interfaces, including: According to the visual interaction interface jump node of the visual feature of the interface module to be predicted, determining at least two interface analysis node ranges before the visual interaction interface jump node; The analysis node range of each interface is decomposed into multiple operation node sets based on the pre-set node step size; According to the target patient user label of the visual feature of the interface module to be predicted, determining the target visual interface corresponding to the target patient user label and the sample visual interface corresponding to the target visual interface as the visual interface to be processed; For each visual interface to be processed, obtaining interface module switching data of the visual interface to be processed and the remaining visual interfaces to be processed in each of the operation nodes; For each interface analysis node range, the interface module switching data of each to-be-processed visual interface and the remaining to-be-processed visual interfaces are concentrated according to the operation node of the interface analysis node range, and the content semantic description knowledge of each visual interface in the interface analysis node range is obtained; According to the content semantic description knowledge corresponding to the range of each interface analysis node, the visual feature relationship network of the past interface modules corresponding to the range of each interface analysis node is obtained.

8. The method for managing user big data based on artificial intelligence and visualization according to any one of claims 1 to 4, characterized in that: Performing interface display jump feature analysis based on the interface requirement identification vector to obtain analysis results, including: Performing knowledge transformation on the interface requirement identification vector to obtain interface requirement transformation knowledge; The interface display jump feature is analyzed according to the interface requirement transformation knowledge to obtain an analysis result.

9. A smart medical user big data management system, characterized in that: It comprises a processor, a memory and a bus connected to the processor; the processor and the memory communicate with each other via the bus; The processor is used to call the computer program in the memory to execute the user big data management method based on artificial intelligence and visualization as described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that: A program is stored thereon, and when the program is executed by a processor, the user big data management method based on artificial intelligence and visualization as described in any one of claims 1 to 8 is implemented.

Images