Intelligent display method for health state of object

Abstract

The invention is suitable for the technical field of computers, and particularly relates to an intelligent display method and device for the health state of an object. The method comprises the following steps: acquiring multi-modal health data of a target object, wherein the multi-modal health data comprises vital sign data of the target object under different sign dimensions; determining health states of a plurality of physiological nodes of the target object according to the multi-modal health data, wherein the physiological nodes are entity parts used for representing physiological structures and functions of the object; and rendering a preset simulation object model according to the health states of the plurality of physiological nodes, and generating and displaying a model rendering result. Visualization of the health state of the human body can be achieved in combination with traditional Chinese medicine knowledge.

Description

Technical Field

[0001] This application belongs to the field of computer technology, and in particular relates to an intelligent display method and device for the health status of an object. Background Technology

[0002] A digital TCM health system refers to a technical solution that uses mobile applications to collect users' vital sign data, and then uses artificial intelligence algorithms to comprehensively process and analyze the data to generate TCM constitution identification or health status assessment conclusions.

[0003] However, currently, most of these systems still rely on non-concrete forms such as pure text descriptions, abstract numerical scores, or static simple charts to provide users with assessment results. This presentation method lacks a direct and intuitive connection with body parts, making the assessment conclusions difficult to understand. Users struggle to form a clear understanding of their own bodies, and it also increases the difficulty for doctors to explain and communicate with patients, affecting the efficiency and trust of health management. Summary of the Invention

[0004] This application provides an intelligent display method and device for the health status of an object, which can visualize the health status of the human body by combining traditional Chinese medicine knowledge.

[0005] In a first aspect, embodiments of this application provide an intelligent method for displaying the health status of an object, the method comprising: Acquire multimodal health data of the target object, which includes vital sign data of the target object under different vital sign dimensions; The health status of multiple physiological nodes of the target object is determined based on multimodal health data. Physiological nodes are physical parts used to characterize the physiological structure and function of the object. The multiple physiological nodes include a first physiological node and a second physiological node. The health status of the first physiological node meets the health requirements, while the health status of the second physiological node does not meet the health requirements. The model of the preset simulation object is rendered based on the health status of multiple physiological nodes, and the model rendering result is generated and displayed. The first physiological node and the second physiological node are displayed in different ways in the model rendering result.

[0006] The first aspect of the beneficial effects is as follows: This method acquires multimodal health data of the target object across different vital signs and maps it to corresponding physiological nodes based on traditional Chinese medicine (TCM) diagnostic logic to determine health status. Finally, it uses differentiated rendering to display the simulation object model based on the status of each node. This approach effectively integrates multi-source heterogeneous data, breaking down data silos and making health assessment more comprehensive. By linking modern data with TCM theories of organs and meridians, it improves the theoretical consistency and interpretability of status judgment. Utilizing a 3D model to visually differentiate abnormal and normal nodes enables intuitive, accurate positioning and dynamic tracking of health status, providing a visual interactive platform for personalized health management.

[0007] In one possible implementation, the health status of multiple physiological nodes of the target object is determined based on multimodal health data, including: Obtain the feature mapping table, which is generated based on the diagnostic logic of traditional Chinese medicine. The feature mapping table includes the correspondence between the features of vital sign data under each sign dimension and the health status of physiological nodes. The association between each physiological node and the vital sign data under each dimension of the multimodal health data is determined based on the feature mapping table. For each physiological node, the health status of the physiological node is determined from the feature mapping table based on the characteristics of its associated vital sign data, so as to determine the health status of multiple physiological nodes of the target object.

[0008] This implementation provides a clear and interpretable technical path from multi-source heterogeneous data to standardized health status quantification. Through a two-stage processing approach using a "Traditional Chinese Medicine knowledge graph" and a "feature mapping table," semantic association is first performed based on theory, and then health status is mapped based on features. This ensures that the entire data processing flow strictly follows the diagnostic logic of Traditional Chinese Medicine, making the final output both data-driven objectivity and theoretical interpretability.

[0009] In one possible implementation, for each physiological node, the health status of that physiological node is determined from a feature mapping table based on the characteristics of its associated vital sign data, thereby determining the health status of multiple physiological nodes of the target object, including: For each physiological node, if the physiological node is associated with vital sign data from multiple vital sign dimensions, then weights are assigned to the vital sign data under each of the multiple vital sign dimensions respectively. The health status of a physiological node is determined from the feature mapping table based on the characteristics and weights of vital sign data across multiple dimensions.

[0010] This implementation introduces a dynamic weighting mechanism. For scenarios where the same physiological node is associated with multiple data sources, weights are dynamically assigned to different data points using preset rules. The final health status of the node is then determined based on a weighted fusion or priority filtering strategy. This improves the accuracy and efficiency of health status assessment.

[0011] In one possible implementation, the vital signs data under each dimension of multimodal health data have different priorities; For each physiological node, if the physiological node is associated with vital sign data from multiple dimensions, then weights are assigned to the vital sign data under each of the multiple dimensions, including: The weights are determined based on the priority of vital sign data under multiple vital sign dimensions. Alternatively, the weight can be determined based on the correlation between the physiological node and vital sign data across multiple dimensions. This implementation offers two methods for determining weights. The first, a weight allocation method based on global priority, prioritizes data with the highest confidence level, taking into account the differences in objectivity and reliability among various data sources. This effectively avoids interference from low-quality or indirect data, ensuring the scientific validity and stability of the evaluation results. The second method, a weight allocation based on node type and data correlation, can differentiate and integrate the most relevant data according to the TCM theoretical characteristics of different nodes such as viscera, meridians, and acupoints. This makes the evaluation results more aligned with the logic of TCM theory, enhancing interpretability and applicability.

[0012] In one possible implementation, the simulation object model includes node model components corresponding to multiple physiological nodes; The model is rendered based on the health status of multiple physiological nodes, generating and displaying the model rendering results, including: The rendering parameters of each node model component are determined based on the health status of multiple physiological nodes. The rendering parameters are used to indicate how the node model component is displayed in the model rendering result. The simulation object model is rendered according to the rendering parameters, and the model rendering result is generated and displayed.

[0013] In this implementation, by dynamically generating rendering parameters for each node model component, the visual representation of the 3D model can reflect subtle changes in the underlying health data in real time and accurately. This is a key technical step in achieving personalized and dynamic visualization rendering.

[0014] In one possible implementation, the multiple physiological nodes include multiple organ nodes, multiple meridian nodes, and multiple acupoint nodes; In the model rendering results, the health status of the viscera nodes is presented through changes in the color and / or brightness of their corresponding node model components; the health status of the meridian nodes is presented through changes in the path flow speed and / or path width of their corresponding node model components; and the health status of the acupoint nodes is presented through changes in the display size and / or flicker frequency of their corresponding node model components.

[0015] This implementation defines a hierarchical visualization semantic system that aligns with the cognitive framework of Traditional Chinese Medicine (TCM). Differentiated visual variables (color / brightness, flow speed / width, size / frequency) are used to encode abnormal states for nodes representing different aspects of the internal organs, meridians, and acupoints. This results in visualizations with high information density and strong professional focus, enabling users to quickly understand the nature and location of different types of health problems.

[0016] In one possible implementation, the method further includes: The relationships between multiple physiological nodes are determined based on a pre-defined TCM knowledge graph, where physiological nodes with relationships are mutually related nodes. Based on multimodal health data and the relationships between multiple physiological nodes, health analysis data and intervention guidance data are generated for each physiological node. The health analysis data includes the mutual influence between the physiological node and its corresponding associated nodes, and the intervention guidance data includes guidance information for intervening in abnormal states of physiological nodes.

[0017] In this implementation, by mining and utilizing the relationships between physiological nodes, analytical data that reveals the intrinsic connections of health problems and targeted intervention guidance can be generated, thereby providing users with deeper and more actionable health insights and providing intelligent assistance based on traditional Chinese medicine knowledge.

[0018] In one possible implementation, the method further includes: In response to receiving an interactive operation on the target physiological node in the model rendering result, the system displays the health analysis data and intervention guidance data corresponding to the target physiological node.

[0019] In this implementation, users can trigger and obtain detailed professional interpretations and suggestions for the corresponding part by directly clicking on the part of interest on the 3D model. This achieves a seamless jump between the visual interface and detailed information, greatly improving the system's usability and information acquisition efficiency.

[0020] In one possible implementation, the method further includes: Receive filtering instructions, which indicate the target type of candidate physiological nodes that should be highlighted in the model rendering results; Candidate physiological nodes are highlighted in the model rendering results based on the filtering instructions.

[0021] This implementation empowers users with the ability to customize information views, enhancing the flexibility and focus of interaction. By highlighting specific types of nodes in response to filtering commands, it helps users quickly focus on the health dimensions they are interested in from a sea of ​​information (such as only viewing abnormal organs or device-related nodes), effectively managing visual complexity and meeting personalized viewing needs in different scenarios.

[0022] Secondly, embodiments of this application provide an intelligent display device for the health status of an object, comprising: The data acquisition module is used to acquire multimodal health data of the target object, which includes vital sign data of the target object under different vital sign dimensions. The analysis module is used to determine the health status of multiple physiological nodes of the target object based on multimodal health data. Physiological nodes are physical parts defined according to the diagnostic logic of traditional Chinese medicine to characterize the physiological structure and function of the object. The multiple physiological nodes include a first physiological node and a second physiological node. The health status of the first physiological node meets the health requirements, while the health status of the second physiological node does not meet the health requirements. The display module is used to render a preset simulation object model based on the health status of multiple physiological nodes, generate and display the model rendering results, wherein the first physiological node and the second physiological node correspond to different display methods in the model rendering results.

[0023] Thirdly, this application also provides an electronic device. The electronic device includes a memory, one or more processors, and a computer program stored in the memory and executable on the processor. The electronic device executes the computer program to implement any of the implementations of the first aspect described above.

[0024] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the method of any of the implementations of the first aspect described above.

[0025] Fifthly, this application also provides a computer program product that, when run on an electronic device, causes the electronic device to execute any of the implementation methods of the first aspect described above.

[0026] It is understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant descriptions in the first aspect above, and will not be repeated here. Attached Figure Description

[0027] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 This is a schematic diagram of an intelligent display system for the health status of an object provided in an embodiment of this application; Figure 2 This is a flowchart of an intelligent display method for the health status of an object provided in an embodiment of this application; Figure 3 This is a schematic diagram of the interface of the AI ​​face diagnosis function provided in one embodiment of this application; Figure 4 This is a schematic diagram of the interface of the AI ​​voice diagnosis function provided in one embodiment of this application; Figure 5 This is a schematic diagram of the interface of the AI ​​tongue diagnosis function provided in one embodiment of this application; Figure 6 This is a schematic diagram of a smart device data acquisition interface provided in an embodiment of this application; Figure 7 This is a schematic diagram of the model rendering result provided in an embodiment of this application; Figure 8 This is a structural block diagram of an intelligent display device for the health status of an object provided in an embodiment of this application; Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0029] With the advancement of mobile internet and artificial intelligence technologies, the digitalization and intelligentization of TCM diagnosis has become an important development direction. Among related technologies, digital systems have emerged that collect users' vital sign data through mobile applications and analyze it using artificial intelligence algorithms to generate TCM constitution or health status assessment conclusions.

[0030] However, such systems still have several significant shortcomings in practical applications, which restrict their full potential in diagnostic assistance and health management.

[0031] First, there are serious deficiencies in the visualization of health status. The aforementioned digital systems primarily present analysis results in the form of plain text descriptions, abstract numerical scores, or static two-dimensional charts. These methods of expression lack a direct connection to the specific physiological structure and spatial relationships of the human body, resulting in highly abstract assessment conclusions. Users struggle to understand the specific body parts referred to in the assessment conclusions and the degree of abnormality. Communication between doctors and patients based on such abstract results is inefficient, severely impacting the credibility and operability of health management.

[0032] Secondly, the diagnostic data cannot be effectively correlated. Such systems typically process data from different diagnostic methods through independent modules, with each module only outputting isolated analytical fragments. Due to the lack of a semantic-level fusion mechanism, the inherent connections between different data dimensions are severed, preventing the system from forming a unified and in-depth comprehensive diagnostic analysis, thus limiting the accuracy and clinical applicability of the overall assessment.

[0033] Furthermore, current technical solutions generally lack the visualization capabilities to deeply integrate with TCM diagnostic analysis, failing to transform the core elements upon which TCM diagnostic analysis is based (such as the functional state of the internal organs, the deficiency and excess of Qi and blood in the meridians, and the reactive characteristics of acupoints) into an interactive and understandable dynamic visual language. The analysis process and the presentation results are severely disconnected, making it impossible to convey and verify the rich diagnostic information of TCM through intuitive and visual means.

[0034] In summary, digital health systems have significant limitations in areas such as the intuitiveness of assessment results, the integration of data processing, and the deep integration of traditional Chinese medicine knowledge with visual expression.

[0035] To address the aforementioned issues and achieve visualization, interactivity, and traceability of TCM diagnostic results, thereby enhancing the overall efficiency and user experience of TCM digital services, this application provides a technical solution. It constructs a complete technical chain from multi-source health data collection to three-dimensional dynamic visualization presentation, integrating TCM diagnostic logic with data processing and graphics rendering processes to obtain visualization results.

[0036] This application first acquires users' multimodal health data, including vital signs and AI (Artificial Intelligence)-based image and voice feature data, through mobile applications and smart devices. Then, based on a pre-defined TCM diagnostic logic (specifically, a feature mapping table or TCM knowledge graph), these heterogeneous data are fused, analyzed, and feature-mapped, transforming them into a set of quantitative health status values ​​for specific physiological nodes (i.e., physical locations defined according to TCM theory, such as internal organs, meridians, and acupoints). During this process, the system uses priority rules to process different data sources, ensuring the robustness of the analysis results. Furthermore, the solution uses these quantitative values ​​as driving signals to apply to a pre-defined three-dimensional digital human body model. Through a set of predefined mapping rules, the system converts the quantitative values ​​of different physiological nodes and severity levels into differentiated rendering parameters (e.g., color, brightness, flow rate, flicker frequency) for corresponding node model components (such as internal organs, meridian paths, and acupoint light points) within the model. Ultimately, a dynamic and interactive rendered model is generated, in which physiological nodes with abnormal health conditions are presented in a prominent visual form, thereby transforming the abstract diagnostic analysis results into a spatialized and structured body map that users can intuitively perceive and understand.

[0037] Figure 1 This is a schematic diagram of an intelligent display system for the health status of an object provided in an exemplary embodiment of this application. The system 100 is implemented by an application (APP) in a mobile terminal and its supporting intelligent device. The system 100 includes: a data acquisition and display layer (APP) 110, a data processing layer 120, a rendering parameter conversion layer 130, and a modeling and rendering layer 140.

[0038] Data Acquisition and Display Layer 110: Through the AI ​​functions integrated into the mobile terminal APP, including AI face diagnosis, AI tongue diagnosis and AI voice diagnosis, it collects the user's diagnostic data; at the same time, it receives the user's self-selected symptom data and connects to smart devices to collect vital sign data, thereby constructing a multimodal health dataset, covering vital sign data (such as EEG, sleep data, etc.) and feature data based on image and audio analysis.

[0039] Data processing layer 120: Based on the preset TCM diagnostic logic and feature mapping table, the layer extracts features from the multimodal health data. First, it selects candidate sub-data that match each physiological node from the multimodal health data. Then, based on the data priority, it maps the multimodal health data to the health status quantification values ​​of multiple physiological nodes (such as visceral nodes, meridian nodes, and acupoint nodes) of the target object. It can also further combine the TCM knowledge graph to generate node association relationships, health analysis data, and conditioning suggestion data.

[0040] Rendering parameter conversion layer 130 and modeling rendering layer 140: Based on the quantitative values ​​of the health status of multiple physiological nodes, the rendering parameters (such as color, brightness, flow speed, width, size, flicker frequency, etc.) of the three-dimensional model components corresponding to each node are determined, and then the preset simulation object model is rendered to generate and display a visualization model.

[0041] The rendered visualization model is displayed through the data acquisition and display layer 110. In this model, physiological nodes with abnormal states will be presented in a different way than normal nodes, and users can interact to query detailed information or filter and highlight specific nodes by type.

[0042] Figure 2 This is a flowchart of an intelligent display method for the health status of an object provided in an embodiment of this application. The method is executed by a mobile terminal, and a target application is deployed in the mobile terminal. The target application is an application developed based on traditional Chinese medicine diagnostic logic and digital twin visualization technology, which can provide multimodal health data fusion analysis and three-dimensional visualization functions. The method includes the following steps.

[0043] Step 201: Obtain multimodal health data of the target object.

[0044] Multimodal health data includes vital sign data of the target subject under different dimensions of vital signs.

[0045] The target person wears a smart device that is compatible with the target application. The types of smart devices include, but are not limited to, head-mounted smart devices, smart bracelets, and smartwatches. The smart device is capable of collecting the target person's vital signs data.

[0046] Optionally, multimodal health data mainly comes from two sources: one is data automatically and continuously collected through supporting smart devices (such as smartwatches and head-mounted devices); the other is user health information obtained through human-computer interaction functions provided by mobile terminals (such as cameras, microphones, and touch screen input).

[0047] For example, the target application integrates multiple data collection and analysis modules, including AI facial diagnosis, AI voice diagnosis, AI tongue diagnosis, and user information entry. These modules work together to collect user health information from different dimensions, collectively forming multimodal health data.

[0048] 1. The AI ​​facial diagnosis function utilizes the front-facing camera of a mobile device to guide the target subject to capture one or more facial images that meet specific requirements. The raw data collected is a digital facial image. This image is then processed by a computer vision processing algorithm or model built into the mobile application. Multiple facial visual features are extracted and quantified from the image to obtain vital sign data in the facial dimension, including but not limited to: complexion, skin luster, wrinkles, face shape, and other visual features.

[0049] Indicative, such as Figure 3 As shown, Figure 3 This is a schematic diagram of an AI-powered facial diagnosis function, which displays vital sign data collected through this function.

[0050] The face consultation interface 300 includes the following information display areas: (1) Local problem identification area 310: such as the detection mark of problems such as pigmentation, pores, dark circles, acne, wrinkles, etc. (2) Quantitative scoring and evaluation area 320: gives a quantitative score and level evaluation for each problem. For example, the report shows "pigmentation: 54 points, more than 24% of skin test users, needs improvement", and further distinguishes freckles, melasma, etc.; at the same time, it provides "pores: 54 points, more than 31% of skin test users, number of obvious pores: 281". (3) Severity classification and suggestion area 330: classifies the identified problems (such as mild, moderate, severe) and provides brief care or improvement suggestions. For example, for pigmentation, it gives text suggestions such as "obvious pigmentation on the face, many in number, avoid direct sun exposure".

[0051] 2. The AI-powered voice diagnosis function uses the mobile device's microphone to record the user reading a fixed text aloud in a quiet environment. The raw data collected is a digital audio signal. This signal is processed by the application's built-in voice diagnosis analysis engine, which is based on acoustic signal processing and a traditional Chinese medicine (TCM) phonetic recognition model. The engine analyzes the audio's spectrum, energy distribution, frequency characteristics, etc., mapping them to the TCM "Five Tones" system and the organ-related model, ultimately generating vital sign data in the sound dimension, including but not limited to: pitch, volume, speech rate, and intonation.

[0052] Indicative, such as Figure 4 As shown, Figure 4 This is a schematic diagram of the AI ​​voice diagnosis function, which displays vital sign data collected through the AI ​​voice diagnosis function.

[0053] The sound diagnosis interface 400 includes the following information display areas: (1) Five-tone differentiation conclusion display area 410: outputs the visceral state judgment based on the five-tone analysis. For example, the report conclusion is: the kidney qi mechanism is in a state of mild hyperactivity, and conditioning can be considered. (2) Corresponding symptom description area 420: lists the typical symptom set that may be associated with the differentiation conclusion, such as "yellow and greasy tongue coating, slippery and rapid pulse". (3) Conditioning suggestion area 430: provides targeted conditioning directions, such as dietary taboos ("do not eat too much sweet food"), dietary conditioning ("eat more salty or dark-colored food") and tea conditioning ("drink black tea appropriately") and other classified suggestions.

[0054] 3. The AI ​​tongue diagnosis function uses the mobile device's camera to guide the user to take a close-up image of their tongue in a protruding position under natural light. The raw data collected is a digital image of the tongue. This image is processed by the application's built-in tongue diagnosis analysis engine, which is based on image segmentation and color and texture analysis. The engine divides the tongue body and coating into sections, extracts color, shape, and texture features, and integrates them with the rules of traditional Chinese medicine tongue diagnosis for comprehensive judgment, ultimately generating vital sign data in the tongue dimension, including but not limited to: tongue color, tongue coating, cracks, teeth marks, and other morphological features.

[0055] Indicative, such as Figure 5 As shown, Figure 5 This is a schematic diagram of the interface for an AI tongue diagnosis function, which displays vital sign data collected through the AI ​​tongue diagnosis function.

[0056] The tongue diagnosis interface 500 includes the following information display areas: (1) Constitution description area 510: describes the specific symptoms corresponding to the constitution in a list format, such as "sticky and uncomfortable mouth upon waking, bitter taste, bad breath", "feeling depressed and feverish all over the body", etc. (2) Cause analysis 520: provides TCM theoretical explanations for the possible causes of this state, such as "dampness stagnation leading to heat and blood stasis", "improper diet", "prolonged illness", etc. (3) Tongue diagnosis analysis mode selection area 530: provides multiple analysis modes, such as constitution state analysis mode, tongue image analysis mode, detailed analysis mode, and conditioning plan analysis mode.

[0057] By integrating or connecting to multiple data sources through the target application on the mobile terminal, health data of the target object is collected across multiple independent dimensions of vital signs. These data dimensions cover the complete spectrum from objective physiological signals to subjective symptom perceptions.

[0058] The target application also provides a display interface for showing vital sign data collected by smart devices. The vital sign data collected by smart devices includes, but is not limited to, various features such as sleep, heart rate variability, blood oxygenation, and brain waves.

[0059] like Figure 6 As shown, Figure 6 This is a schematic diagram of a smart device's data collection interface.

[0060] The data collection interface 600 includes the following information display areas: (1) Activity data display area 610, specifically step count (e.g., "22049 steps"), with a simple timeline from "00:00" to "23:00" below the area to intuitively represent the monitoring coverage of the data; (2) Sleep data display area 620; (3) Heart rate data display area 630, presented in clear numerical values ​​and units (e.g., "78 beats / min"); (4) Blood oxygen data display area 640: not only providing saturation percentage values ​​(e.g., "99%), but also giving a "normal" status assessment conclusion.

[0061] The data collection interface 600 also displays the last update time of each data item (e.g., "Data updated: December 12, 2024, 12:42:05").

[0062] In some embodiments, the target application's display interface also includes a "View More" interactive control next to the key data area, which users can click to view detailed historical records or trend analysis charts.

[0063] Step 202: Determine the health status of multiple physiological nodes of the target object based on multimodal health data.

[0064] Physiological nodes are physical parts defined according to the diagnostic logic of traditional Chinese medicine to characterize the physiological structure and function of an object. Multiple physiological nodes include a first physiological node and a second physiological node. The health status of the first physiological node meets the health requirements, while the health status of the second physiological node does not meet the health requirements.

[0065] Among them, multiple physiological nodes include multiple organ nodes, multiple meridian nodes, and multiple acupoint nodes. These physiological nodes constitute a hierarchical TCM human body model, such as: organ nodes (heart, liver, spleen, lung, kidney), meridian nodes (such as the Twelve Regular Meridians such as the Lung Meridian of Hand-Taiyin and the Liver Meridian of Foot-Jueyin), and acupoint nodes (such as Zusanli, Taichong, Neiguan).

[0066] Health requirements refer to the judgment criteria based on the diagnostic logic of traditional Chinese medicine, which are used to comprehensively evaluate whether physiological nodes are in a balanced and normal functional state.

[0067] The first and second physiological nodes are two node types derived from classifying multiple physiological nodes based on their health status. The first physiological node refers to a normal, healthy physiological node, while the second physiological node refers to an abnormal physiological node with health problems. This classification method aims to provide a clear categorization basis for subsequent model rendering logic, ensuring that abnormal physiological nodes can be clearly identified in the model through prominent visual forms (such as changes in color, brightness, and dynamic effects), thereby intuitively conveying health risks and distinguishing normal physiological nodes from abnormal ones.

[0068] The health requirements for each physiological node may differ, and the type of physiological node is determined based on the corresponding health requirements.

[0069] For example, for a physiological node called "spleen," the health requirement indicates that this node can normally metabolize and transport nutrients, and regulate the ascending and descending of clear and turbid substances. In terms of data, this can be reflected in specific tongue appearance characteristics, corresponding vital sign intervals, and the absence of specific associated symptoms. When determining the health status of the "spleen" node based on multimodal health data, if a thick, greasy tongue coating, accompanied by abdominal distension (as described by the user), and abnormal pulse data are found, then the current state of the "spleen" node will be judged to deviate from / not meet the preset health requirements, and it will be classified as a second physiological node. Conversely, if all data are within the normal range specified by the preset health requirements, it will be classified as a first physiological node.

[0070] In some embodiments, when determining the health status of each physiological node based on multimodal health data, the data in the multimodal health data that have a corresponding relationship with the physiological node are feature-transformed to obtain a quantified value. This quantified value is used to classify the health status of each physiological node in numerical form, indicating the degree to which it deviates from the ideal health status.

[0071] Optionally, this quantified value can be called the health status quantified value. Using the health status quantified value to represent the health status of each physiological node can transform rich semantic expressions into concise numerical features.

[0072] For example, if the health status of each physiological node is represented by a health status quantification value, then the health requirement means that the health status quantification value of the physiological node belongs to a preset numerical range.

[0073] Optionally, a feature mapping table is obtained. The feature mapping table is generated based on the diagnostic logic of traditional Chinese medicine. The feature mapping table includes the correspondence between the features of vital sign data under each sign dimension and the health status of physiological nodes. The association between each physiological node and the vital sign data under each dimension of the multimodal health data is determined based on the feature mapping table.

[0074] For each physiological node, the health status of the physiological node is determined from the feature mapping table based on the characteristics of its associated vital sign data, so as to determine the health status of multiple physiological nodes of the target object.

[0075] For example, the feature mapping table is organized in a modular structure, defining the semantic association between vital sign data and multiple physiological nodes under different vital sign dimensions.

[0076] For example, the feature mapping table includes a Qi and Blood system module (representing physiological nodes, such as Qi, Blood, Body Fluids, Essence, Vessels, and Meridians), an Zang-Fu system module (representing physiological nodes, such as Heart, Liver, Spleen, Lung, and Kidney), and a Meridian system module (representing physiological nodes, such as the Twelve Regular Meridians and the Eight Extraordinary Meridians). The feature mapping table also clarifies the hierarchical relationships between nodes: the Qi and Blood system module is associated with the Meridian layer and the Acupoint layer; the Zang-Fu system module is associated with the Zang-Fu layer, the Meridian layer, and the Acupoint layer; and the Meridian system module is associated with the Meridian layer and the Acupoint layer.

[0077] In addition, the feature mapping table also integrates more detailed graph relationships, which are used to explain the specific physiological nodes associated with various substances (qi, blood, body fluids, essence) in the qi and blood system module.

[0078] When analyzing multimodal health data to determine the health status of multiple physiological nodes of a target object, the feature mapping table first extracts feature data for each type of data in the multimodal health data, maps it to different dimensions, and then determines the correspondence between the mapped dimensions and each physiological node.

[0079] Table 1 below serves as an example of a feature mapping table. The dimensions of this feature data extraction mapping include: Qi and Blood features, Zang-Fu (internal organs) features, and Meridian features. The feature dimensions corresponding to each type of vital sign data in the multimodal health data are shown in Table 1 below.

[0080] Table 1

[0081] Table 1 above does not show all the information. Among them, the substances corresponding to the characteristics of Qi and Blood are not physiological nodes, but they can affect the health status of physiological nodes.

[0082] Specifically, when determining the health status of each physiological node based on the feature mapping table and multimodal health data, in addition to directly determining the health status of each physiological node based on the mapping relationship between the characteristics of the internal organs, the characteristics of the meridians and the data, the qi and blood characteristics corresponding to the multimodal health data can also be determined to obtain the associated data that can explain the health status of the physiological nodes.

[0083] Each feature corresponds to a numerical value, which is a quantitative value representing the health status of a physiological node. For example, the Qi and Blood feature corresponds to the Qi and Blood value, the Zang-Fu feature corresponds to the Zang-Fu value, and the Meridian feature corresponds to the Meridian value.

[0084] For example, the process of determining the health status of each physiological node based on the feature mapping table is as follows.

[0085] Based on the AI ​​facial diagnosis data, the system extracts and maps the values ​​of Qi and blood and the values ​​of internal organs from the core dimensions collected, such as complexion (red / yellow / white / dark), skin luster, oil distribution, and wrinkle density.

[0086] For AI voice diagnosis data, the system extracts and maps Qi and blood values ​​from core dimensions such as pitch, volume, speech rate, formants, and emotional tone recognition.

[0087] For AI-generated tongue diagnosis data, the system extracts and maps Qi and blood values ​​and organ values ​​from core dimensions such as tongue color (pale red / dark red / purple / pale), thickness and color of tongue coating, crack shape, and degree of teeth marks. Finally, for user-initiated (self-reported symptoms) data, the system directly maps and generates standardized Qi and blood values, organ values, and meridian values ​​based on the user's described symptoms.

[0088] Based on vital sign data, the system extracts and maps Qi and blood values, organ values, and meridian values ​​from core dimensions monitored by smart devices, such as sleep quality (REM / deep sleep / light sleep), heart rate variability (HRV), blood oxygen saturation (SpO2), electroencephalogram (α / β / θ / δ), and stress index.

[0089] For user-initiated (self-reported symptoms) data, the system directly maps and generates standardized values ​​for Qi and blood, internal organs, and meridians based on the symptoms described by the user.

[0090] The feature mapping table standardizes the definition and quantization range of the extracted feature values: (1) Qi and Blood Value: Used to represent the constitution type. Its value is a discrete key-value pair. A key-value pair is a data storage structure. The key represents the feature name, and the value represents the specific value of the feature. The value result actually represents the classification result. For example, the values ​​of features (key) such as "Qi", "Blood", "Body Fluids", and "Essence" can all be -1, 0 or 1, which correspond to the following constitution types: "Insufficient", "Normal / Healthy" or "Vigorous".

[0091] (2) Organ Values: These represent the current health status of the organs and are discrete key-value pairs. For example, the values ​​of “heart”, “liver”, “spleen”, “lung”, and “kidney” can be -2, -1, 0, 1, or 2, which correspond to the following organ health statuses: “potential risk”, “potential abnormal”, “normal”, “good”, or “excellent”.

[0092] (3) Meridian value: used to represent the current state of a meridian or acupoint. Its value is also a discrete key-value pair. For example, the value of a certain "meridian" or a certain "acupoint" can be -1, 0 or 1, corresponding to the following states: "abnormal", "normal" or "strong".

[0093] It is worth noting that if there are multiple meridians and acupoints, then the meridian value is recorded for each acupoint or meridian as a unit.

[0094] Of the three types of feature values ​​mentioned above, the Zang-Fu (organ) values ​​are associated with Zang-Fu nodes, while the Meridian values ​​are associated with Meridian nodes and Acupoint nodes. Zang-Fu and Meridian values ​​directly reflect the health status of each physiological node. In other words, the Zang-Fu value corresponding to each Zang-Fu node is the quantified health status value of that Zang-Fu node; the Meridian value corresponding to each Meridian node is the quantified health status value of that Meridian node; and the Meridian value corresponding to each Acupoint node is the quantified health status value of that Acupoint node. Since the above content collectively refers to Acupoint nodes and Meridian nodes as Meridian features, and the feature values ​​corresponding to these Meridian features are all called Meridian values, the quantified health status values ​​corresponding to these two types of nodes are indicated by Meridian values. In some embodiments, Meridian nodes and Acupoint nodes can be further distinguished and renamed, which will not be elaborated here.

[0095] Qi and blood values ​​reflect the state of various substances related to the qi and blood system in the human body. These substances do not manifest as physiological structural entities like physiological nodes, but qi and blood values ​​indirectly affect the values ​​of the internal organs and meridians, and can also represent the health status of each physiological node from the perspective of qi and blood. Therefore, in this application, although qi and blood values ​​cannot be used as direct explanatory data for the health status of physiological nodes, the analysis of qi and blood characteristics is still retained when analyzing multimodal health data to determine the health status of each physiological node, resulting in qi and blood values. In some embodiments, multimodal health data can be mapped first to obtain qi and blood values, and then the multimodal health data can be mapped again using qi and blood values ​​to obtain the values ​​of the internal organs and meridians, thereby improving the accuracy of the analysis results of the health status of each physiological node.

[0096] Through the processing of the aforementioned feature mapping table, the unstructured or heterogeneous original features in various multimodal health data are uniformly transformed and standardized into structured values ​​of Qi and Blood, Zang-Fu organs, and Meridians with clear TCM semantics and grading standards. These standardized values ​​constitute the direct data foundation for subsequent steps in the comprehensive quantitative assessment of health status and for driving differentiated rendering in the three-dimensional digital twin model.

[0097] In some embodiments, the reliability of vital sign data under each dimension of multimodal health data and the degree of matching with the actual physiological state of the target object are different. Therefore, the analytical effects produced by each type of vital sign data as the data source used to determine the health status of each physiological node are also different. In order to improve the accuracy of health status assessment and system processing efficiency, this scheme dynamically assigns weights to vital sign data from different data sources and uses the weights to fuse and determine the final quantitative value of the health status of the physiological node.

[0098] For example, for each physiological node, if the physiological node is associated with vital sign data from multiple vital sign dimensions, then weights are assigned to the vital sign data under each of the multiple vital sign dimensions; the health status of the physiological node is determined from the feature mapping table based on the features and weights of the vital sign data under the multiple vital sign dimensions.

[0099] The methods for allocating weights include, but are not limited to, the following two: (1) The priority of vital signs data under each dimension of multimodal health data is different. The weight is determined according to the priority of vital signs data under multiple dimensions.

[0100] For example, the specific priority rules are set as follows: vital sign data collected by smart devices > user-initiated (self-reported symptoms) > AI facial diagnosis data > AI tongue diagnosis data > AI voice diagnosis data.

[0101] A corresponding weight is pre-assigned for each priority level. Vital sign data across multiple dimensions are sorted according to priority and assigned weights from high to low. Typically, the total weight is 1, and each type of vital sign data receives a non-zero weight value based on its priority. When determining the health status of physiological nodes, the feature values ​​determined for each type of vital sign data are weighted and calculated according to their respective weights to obtain a quantitative value of health status.

[0102] For example, when assessing the health status of the "heart" node, the highest priority vital sign data might be assigned a weight of 0.5, the vital sign data for user-reported symptoms 0.2, the vital sign data for AI facial diagnosis 0.1, the vital sign data for AI tongue diagnosis 0.1, and the vital sign data for AI voice diagnosis 0.1. The final quantified health status value will be determined by a weighted fusion of the feature values ​​and weights corresponding to the "heart" node from these five vital sign data points.

[0103] In an optional embodiment, the highest priority data can be assigned a weight of 1, and the rest can be assigned a weight of 0. In this case, the method exhibits an efficient priority filtering strategy.

[0104] For example, for each physiological node, if the physiological node is associated with vital sign data from multiple vital sign dimensions, then the feature of the highest priority vital sign data is selected from the vital sign data from multiple vital sign dimensions.

[0105] The health status of a physiological node is determined from the feature mapping table based on the features of the highest priority vital sign data.

[0106] For example, the specific priority rules are set as follows: vital sign data collected by smart devices > user-initiated data (self-reported symptoms) > AI facial diagnosis data > AI tongue diagnosis data > AI voice diagnosis data. During processing, the system will traverse the associated data sources according to this priority order for each physiological node. As long as a valid feature value is successfully obtained from the higher-priority data, it will not repeatedly collect or extract data from subsequent lower-priority data sources, thereby avoiding information redundancy and improving decision-making efficiency.

[0107] Here, "highest priority" is a relative concept: when a data source of a certain priority fails to provide a valid feature value, the next priority data source is accessed sequentially. At this time, the data source is regarded as the current "highest priority" data, with a weight of 1, and the rest are 0.

[0108] For example, when assessing the health status of the physiological node "heart," it was found that related feature data existed simultaneously in high-priority vital sign data (such as heart rate variability HRV) and low-priority AI tongue diagnosis data (such as the "red tongue tip" feature). The HRV feature showed a strong correlation with the "heart" node. Subsequently, a feature mapping table was consulted to map the specific measured value of HRV (e.g., below the normal threshold) to a quantitative value for the health status of the "heart" node (e.g., mapped to "-0.5," indicating moderate abnormality). During this process, since a definite quantitative value had already been obtained from the highest-priority data source, the system would not repeatedly extract and map the "red tongue tip" feature from the AI ​​tongue diagnosis data, thus ensuring that the assessment results were based on the most objective and direct physiological evidence, while also improving processing efficiency.

[0109] It is worth noting that the above logic of feature selection and determination based on data priority can be applied not only to the analysis of each physiological node, but also to the state assessment of various substances (qi, blood, body fluids, and essence) under the qi and blood characteristic dimension. This means that when attempting to obtain quantitative values ​​of specific substances such as "qi" and "blood," the established data priority order is followed, traversing and selecting the most reliable data source.

[0110] For example, when assessing the state of the substance "qi", its quantitative value will be sought from the relevant characteristics of different data types in a preset priority order.

[0111] Specifically, the process first attempts to extract "Qi"-related features from the highest-priority vital sign data, such as analyzing heart rate variability (HRV). If the HRV analysis provides a valid "Qi" status value (e.g., reduced low-frequency HRV power might map to "Qi deficiency," corresponding to a value of -1), this value is directly adopted, and the search for supplementary "Qi" information in subsequent data sources ceases. If a valid "Qi" value cannot be obtained from the vital sign data, the process is downgraded to the next priority user-entered data, checking whether users have reported related symptoms such as "shortness of breath" or "fatigue," and mapping these symptoms to quantitative "Qi" values. This process continues, sequentially considering relevant features from AI facial diagnosis, AI tongue diagnosis, and AI voice diagnosis data, until a value for "Qi" is successfully assigned or all data sources have been traversed.

[0112] By applying priority rules to both the node and blood and qi substance dimensions, the health status assessment results fused from multimodal data are ensured to be both comprehensive and efficient, avoiding redundant calculations and prioritizing the most objective and direct data.

[0113] (2) Alternatively, the weight can be determined based on the correlation between the physiological node and the vital signs data under multiple vital signs dimensions.

[0114] This method pre-determines and dynamically assigns weights based on the inherent correlation between different physiological nodes and various vital sign data according to the diagnostic logic of Traditional Chinese Medicine (TCM). Different weighting strategies are employed for different types of physiological nodes (such as internal organs, meridians, and acupoints). For each type of physiological node, specific weight values ​​are pre-set for the associated vital sign data types (including those collected by smart devices, user-reported symptoms, AI facial diagnosis, AI tongue diagnosis, and AI voice diagnosis). Data types that are more closely and directly related to a specific node type in TCM theory are assigned higher weights; data types with weak or no direct correlation are assigned lower or even zero weights. For example, for the internal organ node (such as "heart"), the pre-determined weighting strategy is as follows: smart device vital sign data (such as HRV, heart rate) weight 0.6, user-reported symptoms (such as "chest tightness") weight 0.15, AI facial diagnosis data (such as "flushed complexion") weight 0.15, AI tongue diagnosis data (such as "red tongue tip") weight 0.1, and AI voice diagnosis data weight 0.0 (set to 0 due to low direct correlation).

[0115] For example, for acupoint nodes (such as the "Taixi" acupoint related to the kidneys), the preset weighting strategy may be as follows: AI sound diagnosis data (such as the "Yu" sound feature) weight 0.5, smart device vital sign data (such as foot skin temperature) weight 0.3, user-reported local symptoms (such as "heel pain") weight 0.1, AI tongue diagnosis data (such as "peeling of the tongue root coating") weight 0.1, and AI facial diagnosis data weight 0.0.

[0116] When determining the health status of a specific physiological node, the system first identifies its type and then invokes a pre-defined strategy with fully defined weights for each data type. Based on the weight set, the preliminary quantified values ​​of various related data converted through a feature mapping table are weighted and fused to calculate the final quantified health status value of the node.

[0117] Step 203: Render the preset simulation object model according to the health status of multiple physiological nodes, and generate and display the model rendering result.

[0118] The first and second physiological nodes are displayed differently in the model rendering results, thereby enabling rapid location and intuitive understanding of abnormal states.

[0119] The simulation object model is a human digital twin model constructed around the five internal organs, meridians, and acupoints. The simulation object model includes node model components corresponding to multiple physiological nodes. The simulation object model can be either a two-dimensional model or a three-dimensional model; this application uses a three-dimensional model as an example for illustration.

[0120] Optionally, the rendering parameters of each node model component are determined based on the health status of multiple physiological nodes. The rendering parameters are used to indicate how the node model component is displayed in the model rendering result. The simulation object model is rendered according to the rendering parameters to generate and display the model rendering result.

[0121] In the model rendering results, the health status of the viscera nodes is presented through changes in the color and / or brightness of their corresponding node model components; the health status of the meridian nodes is presented through changes in the path flow speed and / or path width of their corresponding node model components; and the health status of the acupoint nodes is presented through changes in the display size and / or flicker frequency of their corresponding node model components.

[0122] For example, in step 202, the health status quantification value of each physiological node is determined through a feature mapping table, and the health status of each physiological node is displayed in numerical form. In this embodiment, the health status quantification value is also used as an example to illustrate the method of obtaining rendering parameters.

[0123] (1) For organ nodes (such as heart, liver, spleen, lung, kidney): their health status quantification value / organ value (e.g., an integer in the range of -2 to 2) is directly mapped to the color and brightness parameters of their corresponding model components.

[0124] When the quantification value is "0 / normal", the organ node is displayed in a base color (such as a natural pinkish-red) and standard brightness.

[0125] When the quantization value indicates "-1 / Possible anomaly", corresponding to a general anomaly message, the component rendering parameters are set to the first warning color (such as yellow) and the corresponding brightness.

[0126] When the quantization value indicates "-2 / Possible Risk", the corresponding risk warning is triggered, and the component rendering parameters are set to the second warning color (such as red). The brightness value is usually set higher than that of the first warning color state to indicate a more serious degree of abnormality.

[0127] When the quantization value is "1 / Good", it indicates that the condition is better than the baseline. The component rendering parameters can be set to a positive color (such as light green) and may be accompanied by a slight increase in brightness to visually express a positive health trend.

[0128] When the quantification value is "2 / Excellent", it indicates that the state is significantly excellent. The component rendering parameters can be set to more vivid positive colors (such as bright green or blue), and combined with higher brightness or soft halo effects to give users positive reinforcement feedback.

[0129] (2) For meridian nodes (such as the twelve regular meridians and the eight extraordinary meridians), their health status quantification value / meridian value is mapped to the dynamic pulse velocity and path width parameters of the corresponding luminous path model component.

[0130] When the quantization value is "-1 / abnormal prompt", it indicates that the flow of Qi and blood is not smooth. The component rendering parameters are set to a lower flow speed and a narrower path width, which visually presents as a slow, thin or even intermittent light flow.

[0131] When the quantization value is "0 / normal", it corresponds to the standard blood and qi circulation state, and the rendering parameters are set to the baseline flow speed and a moderate path width.

[0132] When the quantization value is indicated as "1 / Strong", it means that the flow of Qi and blood is more vigorous and smooth than usual. The rendering parameters can be set to a flow speed higher than the baseline and a slightly wider path width to make the optical flow appear more powerful and full.

[0133] When the quantization value is indicated as "2" (which can be defined as "very robust" or other higher levels), the rendering parameters can be further enhanced, for example, by setting a faster flow rate, a wider path, and possibly supplementing it with higher brightness or particle effects to visually emphasize the fullness of the meridian's Qi and blood.

[0134] (3) For acupoint nodes (main acupoint nodes), their health status quantification value / meridian value is mapped to the display size and flicker frequency parameters of the corresponding point light source model component.

[0135] When the quantification value is indicated as "-1 / abnormal indication", it usually means that the acupoint is a pathological reaction point or a key intervention point. The component rendering parameters are set to increase the display size and the flicker frequency to form a striking, pulsating light spot effect to attract attention.

[0136] When the quantification value is "0 / normal", the acupoint appears as a baseline size with a steady or low-frequency flashing state.

[0137] When the quantization value is indicated as "1 / Strong", it means that the acupoint is active in terms of Qi and blood. The rendering parameters can be set to a size slightly larger than the baseline and may be accompanied by a soft, regular pulsating effect.

[0138] When the quantization value is indicated as "2" (higher level), the rendering parameters can be reflected as a larger size, brighter brightness, and possibly a flickering with a special rhythm or halo, intuitively reflecting the excellent condition of the acupoint.

[0139] This visual mapping system, which ranges from abnormal to excellent, allows the state of meridians and acupoints to be presented in a dynamic and intuitive graphical language within a 3D digital twin model. Together with the rendering logic of organ nodes, it forms a holographic and sophisticated health status visualization system.

[0140] Indicative, such as Figure 7 As shown, Figure 7 This is a schematic diagram of the rendering result of a model, including three cases.

[0141] Figure 7 It includes three subgraphs: the first subgraph Figure 7 a. Second son Figure 7 b and the third child Figure 7 c. Among them, the first child Figure 7 'a' represents the model rendering result in a healthy state, and the second sub-item... Figure 7 b represents the model rendering result under general prompts, where the physiological node 701, representing the heart, is displayed in the first prompt color, indicating a possible anomaly; the third sub-node... Figure 7 c represents the model rendering result under the risk warning, where the physiological node 701 representing the heart is displayed in the second warning color, indicating that there may be a risk.

[0142] The generated model rendering results support basic operations such as 3D rotation, two-finger zoom, drag-and-drop panning, and layered browsing. Users can freely observe the human body structure from different angles and zoom levels using gestures, and selectively focus on different layers such as internal organs, meridians, or acupoints. Based on the above multi-dimensional dynamic rendering process, the model becomes a living visualization system reflecting real-time health status: the color and brightness of internal organs reflect their functional status in real time, the speed and width of the light flow in the meridians represent the circulation of Qi and blood, and the pulsation of acupoints indicates the priority of intervention.

[0143] In some embodiments, the target application also provides data association functionality at the interaction level.

[0144] Optionally, the relationships between multiple physiological nodes are determined based on a preset TCM knowledge graph, wherein physiological nodes with relationships are related nodes to each other.

[0145] Based on multimodal health data and the relationships between multiple physiological nodes, health analysis data and intervention guidance data are generated for each physiological node. The health analysis data includes the mutual influence between the physiological node and its corresponding associated nodes, and the intervention guidance data includes guidance information for intervening in abnormal states of physiological nodes.

[0146] The purpose of analyzing the relationships between physiological nodes is to proactively alert the user, based on the pre-defined relationships in the knowledge graph, when a target physiological node is identified as abnormal. This alert may indicate the potential impact of the abnormal node on other related nodes, or reveal that its own state may be a result of influence from other related nodes. This kind of alert helps users develop a holistic view of health and take preventative measures.

[0147] For example, for the "heart" node rendered in red, the data analysis might indicate "excessive heart fire, accompanied by blood stasis, affecting the small intestine meridian," while the guidance data would suggest "avoiding spicy food and massaging the Neiguan acupoint."

[0148] For example, if the knowledge graph defines a relationship of "liver wood overpowering spleen earth" between the "liver" node and the "spleen" node, when the "liver" node is identified as abnormal while the "spleen" node does not show any abnormality, the system will proactively prompt "Currently, liver qi is stagnant, which may overpower spleen earth. It is recommended to pay attention to spleen and stomach function and pay attention to dietary care" when generating health analysis data for the "liver" node.

[0149] Health analysis data will be stored in the mobile device's local storage unit, and users can view it at any time through the interactive functions provided by the target application.

[0150] The health analysis data not only includes the analysis results of the health status of the physiological nodes themselves, but also integrates the Qi and Blood characteristic data (such as the status or Qi and Blood values ​​corresponding to Qi, Blood, Body Fluids, and Essence) obtained through the fusion analysis of multimodal health data in step 202. Since Qi and Blood characteristics are core concepts in Traditional Chinese Medicine representing the overall functional state of the human body, rather than physical physiological nodes with definite spatial locations such as the heart or liver, they cannot be directly visualized in a 3D simulation model using entity rendering methods such as color, brightness, or shape changes. In this embodiment, the Qi and Blood characteristic data and its correlation analysis with the status of specific physiological nodes are integrated into the health analysis data triggered through interaction, and explained and presented in detail through text interpretation.

[0151] Optionally, in response to receiving an interactive operation on the target physiological node in the model rendering result, health analysis data and intervention guidance data corresponding to the target physiological node are displayed.

[0152] Users can click on any highlighted or abnormal organ, meridian, or acupoint node on the model. The application will respond to this interaction by displaying detailed health analysis data and intervention guidance data corresponding to the target physiological node in the sidebar or pop-up window, achieving a seamless transition from a visual overview to text details.

[0153] For example, when a user clicks on the abnormal "heart" node displayed in red in the model, the target application will display health analysis data in the interface including: "Currently, there is excessive heart fire, accompanied by blood stasis (Qi and blood characteristics: blood - poor circulation) and Qi deficiency (Qi and blood characteristics: Qi - insufficient)." Simultaneously, corresponding intervention guidance data will suggest: "It is recommended to promote blood circulation and remove blood stasis; massage the Neiguan and Xuehai acupoints; and pay attention to replenishing Qi and avoiding overexertion." In this way, the abnormal Qi and blood state, which cannot be directly rendered, is transformed into understandable and actionable textual information associated with specific nodes, thus providing users with a more complete health insight.

[0154] In some embodiments, model filtering and view focusing functions are also provided to enhance the flexibility of user interaction and the efficiency of information retrieval.

[0155] This feature allows users to actively issue filtering instructions. These instructions explicitly specify the target type to which physiological nodes require special attention and highlighting in the current model rendering. Upon receiving this instruction, the system dynamically parses its content and applies new visual rules to the 3D model, thereby generating a filtered view with a more focused information.

[0156] Optionally, a filtering instruction is received, which indicates the target type of the candidate physiological nodes to be highlighted in the model rendering result; and the candidate physiological nodes are highlighted in the model rendering result according to the filtering instruction.

[0157] Specifically, the application interface may provide a series of filtering controls. Users can generate filtering instructions containing specific filtering conditions by triggering (e.g., clicking or checking) the corresponding filtering controls. The system parses and determines the target type of candidate physiological nodes that need to be highlighted in the user's intent based on the type of the triggered control.

[0158] For example, the types of filter controls include, but are not limited to: 1. Controls for filtering by health status: These controls allow users to filter nodes based on specific health statuses, such as providing options like "Show only abnormal nodes," "Show only risk warning (red) nodes," or "Show good and above nodes." When the user selects "Show only abnormal nodes," the generated filter instruction indicates the target type as "physiological nodes with a health status quantification value less than 0." Based on this, the system will highlight all abnormal organs, meridians, and acupoints in the model, while significantly downplaying normal nodes.

[0159] 2. Controls for filtering by data source: These controls allow users to filter based on the original data source from which health conclusions are drawn. For example, they may offer options such as "Show nodes related to vital sign data" or "Show nodes related to AI-assisted facial diagnosis." When a user selects "Show nodes related to vital sign data," the target type of the filtering instruction is "physiological nodes whose final health status quantification is primarily contributed by vital sign data." The system will highlight these nodes (e.g., by adding special halos or outlines) to help users trace the visual impact of data from specific devices.

[0160] 3. Controls for filtering by physiological node type: These controls allow users to browse the model hierarchically by node category, providing options such as "Show only the viscera layer," "Show only the meridian layer," "Hide the acupoint layer," or "Combined display of viscera and meridians." When the user selects "Show only the meridian layer," the target type of the filtering instruction is "All meridian nodes." The system will hide or dim the viscera and acupoint layers, making the glowing meridian paths the visual focus, facilitating specialized analysis of the Qi and blood circulation network.

[0161] Based on the received filtering instructions and their clearly defined target types, the model rendering results are dynamically redrawn in real time. This process not only changes the visibility of nodes but may also adjust their highlighting style, such as enhancing the brightness of candidate nodes, adding dynamic outlines, and enlarging their display, while making non-target nodes transparent or grayscale. This feature allows users to quickly extract and focus on the specific health dimension or body system of greatest concern from a complex global view, enabling personalized, exploratory, and in-depth interaction with the 3D health digital twin.

[0162] In summary, the method provided in this application acquires multimodal health data of a target object across different physiological dimensions, maps this data to corresponding physiological nodes based on traditional Chinese medicine diagnostic logic to determine its health status, and finally performs differentiated rendering and display of the 3D simulation object model according to the status of each node. This method, for the first time, integrates the traditional "observation, auscultation, inquiry, and palpation" assessment with real physiological data collected by modern intelligent devices, constructing a visual twin of human health in a 3D digital space. This process effectively breaks down data silos, achieving unified interpretation of multi-source heterogeneous data and making health assessment more comprehensive; by deeply linking modern data with traditional Chinese medicine theories of organs and meridians, it improves the theoretical fit and interpretability of status judgment; furthermore, by using a 3D model to visually present abnormal and normal nodes differently, it enables intuitive, accurate positioning and dynamic tracking of health status. This not only greatly enhances the shared understanding and trust between doctors and patients regarding health information but also provides an innovative visual interactive platform for applications such as personalized health management, status tracking, and intelligent physiotherapy.

[0163] Corresponding to the intelligent display method of object health status in the above embodiment, Figure 8 A structural block diagram of an intelligent display device for the health status of an object provided in an embodiment of this application is shown. For ease of explanation, only the parts related to the embodiments of this application are shown.

[0164] Reference Figure 8 The device 800 includes: The data acquisition module 810 is used to acquire multimodal health data of the target object, which includes vital sign data of the target object under different vital sign dimensions. Analysis module 820 is used to determine the health status of multiple physiological nodes of the target object based on multimodal health data. Physiological nodes are physical parts used to characterize the physiological structure and function of the object. The multiple physiological nodes include a first physiological node and a second physiological node. The health status of the first physiological node meets the health requirements, while the health status of the second physiological node does not meet the health requirements. The display module 830 is used to render a preset simulation object model based on the health status of multiple physiological nodes, generate and display the model rendering results, wherein the first physiological node and the second physiological node correspond to different display methods in the model rendering results.

[0165] It should be noted that the information interaction and execution process between the above-mentioned devices / modules are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0166] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0167] To implement the above embodiments, this application also proposes an electronic device that can be configured as a network device or training device in the above embodiments.

[0168] Figure 9 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application.

[0169] like Figure 9 As shown, the above-mentioned electronic device 900 includes: The system includes a memory 910 and at least one processor 920, and a bus 930 connecting different components (including the memory 910 and the processor 920). The memory 910 stores a computer program, and when the processor 920 executes the program, it implements the method for processing employee change records and the method for training a network quality prediction model according to the embodiments of this application.

[0170] Bus 930 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0171] Electronic device 900 typically includes a variety of electronic device readable media. These media can be any available media that can be accessed by electronic device 900, including volatile and non-volatile media, removable and non-removable media.

[0172] The memory 910 may also include computer system readable media in the form of volatile memory, such as random access memory (RAM) 940 and / or cache memory 950. The electronic device 900 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 960 may be used to read and write non-removable, non-volatile magnetic media (…). Figure 9 Not shown; usually referred to as a "hard drive"). Although Figure 9 As not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 930 via one or more data media interfaces. The memory 910 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this application.

[0173] A program / utility 980 having a set (at least one) of program modules 970 may be stored, for example, in memory 910. Such program modules 970 include—but are not limited to—an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 970 typically perform the functions and / or methods described in the embodiments of this application.

[0174] Electronic device 900 can also communicate with one or more external devices 990 (e.g., keyboard, pointing device, display 991, etc.), and with one or more devices that enable a user to interact with electronic device 900, and / or with any device that enables electronic device 900 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 999. Furthermore, electronic device 900 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 993. As shown, network adapter 993 communicates with other modules of electronic device 900 via bus 930. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0175] The processor 920 performs various functional applications and data processing by running programs stored in the memory 910.

[0176] It should be noted that the implementation process and technical principles of the electronic device in this embodiment are explained in the foregoing description of the method for processing employee change records and the training method for the network quality prediction model in the embodiments of this application, and will not be repeated here.

[0177] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps described in the above-described method embodiments.

[0178] This application provides a computer program product that, when run on an electronic device, enables the electronic device to perform the steps described in the various method embodiments above.

[0179] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. A computer-readable medium can include at least: any entity or device capable of carrying computer program code to a photographic device / electronic device, a recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some regions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0180] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0181] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0182] In the embodiments provided in this application, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0183] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0184] In the foregoing, specific details such as particular system architectures and techniques have been set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application can also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted to avoid unnecessary detail from obscuring the description of this application.

[0185] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0186] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0187] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0188] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0189] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0190] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for intelligently displaying the health status of an object, characterized in that, The method includes: Acquire multimodal health data of the target object, wherein the multimodal health data includes vital sign data of the target object under different vital sign dimensions; The health status of multiple physiological nodes of the target object is determined based on the multimodal health data. The physiological nodes are physical parts used to characterize the physiological structure and function of the object. The multiple physiological nodes include a first physiological node and a second physiological node. The health status of the first physiological node meets the health requirements, while the health status of the second physiological node does not meet the health requirements. The preset simulation object model is rendered based on the health status of the multiple physiological nodes, and the model rendering result is generated and displayed. The first physiological node and the second physiological node correspond to different display methods in the model rendering result.

2. The method according to claim 1, characterized in that, Determining the health status of multiple physiological nodes of the target object based on the multimodal health data includes: Obtain a feature mapping table, which is generated based on the diagnostic logic of traditional Chinese medicine. The feature mapping table includes the correspondence between the features of vital sign data under each sign dimension and the health status of the physiological node. The association between each physiological node in the plurality of physiological nodes and the vital sign data under each vital sign dimension in the multimodal health data is determined according to the feature mapping table. For each physiological node, the health status of the physiological node is determined from the feature mapping table based on the characteristics of its associated vital sign data, so as to determine the health status of multiple physiological nodes of the target object.

3. The method according to claim 2, characterized in that, For each physiological node, the health status of that physiological node is determined from the feature mapping table based on the characteristics of its associated vital sign data, thereby determining the health status of multiple physiological nodes of the target object, including: For each physiological node, if the physiological node is associated with vital sign data from multiple vital sign dimensions, then weights are assigned to the vital sign data under the multiple vital sign dimensions respectively. The health status of the physiological node is determined from the feature mapping table based on the features and weights of the vital sign data under the multiple vital sign dimensions.

4. The method according to claim 3, characterized in that, The vital signs data in each dimension of the multimodal health data have different priorities; For each physiological node, if the physiological node is associated with vital sign data from multiple vital sign dimensions, then weights are assigned to the vital sign data under each of the multiple vital sign dimensions, including: The weights are determined based on the priorities corresponding to the vital sign data under the multiple vital sign dimensions. Alternatively, the weight can be determined based on the correlation between the physiological node and the vital sign data under the multiple vital sign dimensions.

5. The method according to claim 2, characterized in that, The simulation object model includes node model components corresponding to the plurality of physiological nodes; The step of rendering a preset simulation object model based on the health status of the multiple physiological nodes, and generating and displaying the model rendering result, includes: The rendering parameters of each node model component are determined based on the health status of the multiple physiological nodes. The rendering parameters are used to indicate how the node model component is displayed in the model rendering result. The simulation object model is rendered according to the rendering parameters, and the rendering result of the model is generated and displayed.

6. The method according to claim 5, characterized in that, The multiple physiological nodes include multiple organ nodes, multiple meridian nodes, and multiple acupoint nodes; In the model rendering results, the health status of the viscera nodes is presented through changes in the color and / or brightness of their corresponding node model components; the health status of the meridian nodes is presented through changes in the path flow speed and / or path width of their corresponding node model components; and the health status of the acupoint nodes is presented through changes in the display size and / or flicker frequency of their corresponding node model components.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: The relationships between the multiple physiological nodes are determined based on a pre-defined TCM knowledge graph, wherein physiological nodes with relationships are mutually related nodes. Based on the multimodal health data and the correlation between the multiple physiological nodes, health analysis data and intervention guidance data are generated for each physiological node. The health analysis data includes the mutual influence between the physiological node and its corresponding associated nodes, and the intervention guidance data includes guidance information for intervening in the abnormal state of the physiological node.

8. The method according to claim 7, characterized in that, The method further includes: In response to receiving an interactive operation on the target physiological node in the model rendering result, health analysis data and intervention guidance data corresponding to the target physiological node are displayed.

9. The method according to any one of claims 1 to 6, characterized in that, The method further includes: Receive a filtering instruction, which indicates the target type of candidate physiological nodes that need to be highlighted in the model rendering result; According to the filtering instructions, the candidate physiological nodes are highlighted in the model rendering results.

10. An intelligent display device for the health status of an object, characterized in that, The device includes: The data acquisition module is used to acquire multimodal health data of the target object, including vital sign data of the target object under different vital sign dimensions; The analysis module is used to determine the health status of multiple physiological nodes of the target object based on the multimodal health data. The physiological nodes are physical parts used to characterize the physiological structure and function of the object. The multiple physiological nodes include a first physiological node and a second physiological node. The health status of the first physiological node meets the health requirements, while the health status of the second physiological node does not meet the health requirements. The display module is used to render a preset simulation object model based on the health status of the multiple physiological nodes, generate and display the model rendering result, wherein the first physiological node and the second physiological node correspond to different display methods in the model rendering result.

Images