Multi-medical system data system mapping method and system based on multi-track cognition and storage medium

Abstract

The invention discloses a multi-medical system data system mapping method and system based on multi-track cognition and a storage medium, and relates to the technical field of medical data processing and integrated medicine. In order to solve the technical problem that different medical systems cannot be effectively fused due to data standard and semantic logic segmentation, the method comprises the following steps: constructing a cognitive orbit which retains native logic for each medical system, and innovatively introducing a unique steady-state representation network formed by quantifiable steady-state dimensions as a universal intermediary reference; by establishing a mapping relation constrained by cluster correspondence, network effect and context dependence, each piece of cognitive orbit data is systematically mapped to the reference, so that standardized conversion and lossless semantic alignment of multi-source heterogeneous data are realized. According to the method, the fragmentation problem of cross-medical system data fusion is solved, system-level integration from data to knowledge is realized, and a promising core technical support is provided for integration of medical research, chronic disease management and the like.

Description

Technical Field

[0001] This invention relates to the fields of medical data processing, digital healthcare, and integrated traditional Chinese and Western medicine, and particularly to a method, system, and storage medium for mapping multi-medical system data based on multi-track cognition. Background Technology

[0002] Driven by the national strategy of "Healthy China," integrative medicine has become a core development direction in the global healthcare field. Different medical systems, such as Traditional Chinese Medicine, Western medicine, ethnic medicine, and functional medicine, have formed their own complete theoretical and practical systems from different cognitive perspectives, including holism and reductionism, each possessing irreplaceable advantages in health intervention and disease prevention. However, for a long time, the synergy and integration between different medical systems has been limited by the incommensurability of epistemological paradigms—the underlying logical differences between holism / relational philosophy and reductionism / entity thinking have led to a complete disconnect in the core concepts, data standards, semantic logic, and evaluation systems of different medical systems, making effective cross-system dialogue and data fusion impossible. Existing technologies and solutions for the integration of multiple medical systems have the following core shortcomings: 1. Paradigm conflict remains unresolved, and cross-system integration remains superficial: Existing solutions are mostly simple superpositions of the contents of two medical systems. They either forcibly use the reductionist logic of Western medicine to explain traditional Chinese medicine theory, falling into the cognitive misalignment of "interpreting Chinese medicine with Western medicine"; or they adhere to the original logic of a single medical system, refuse cross-system collaboration, and can never break through the underlying barrier of paradigm incommensurability, thus failing to achieve true complementary integration. 2. Remaining only at the theoretical level, without a practical technical implementation path: Existing research has only proposed theoretical frameworks and meta-models for the integration of traditional Chinese and Western medicine, without transforming the abstract differences in cognitive paradigms into standardized and reproducible technical solutions that can be implemented by computers. This makes it impossible to provide practical technical support for the actual integration and application of multiple medical systems. 3. Fragmented data fusion solutions fail to achieve system-level mapping: Existing cross-system data fusion solutions mostly adopt a linear mapping logic of "single point correspondence", which can only achieve the correspondence between a single component and a single efficacy. It cannot fit the emergent system effect of synergistic effects of multiple components, multiple targets, and multiple pathways, resulting in fragmented fusion results, serious semantic ambiguity, and failure to fully restore the core cognitive logic of different medical systems. 4. Insufficient versatility and scalability, unable to adapt to the needs of multi-system integration: Existing solutions are mostly designed for specific scenarios of traditional Chinese medicine and Western medicine, and are usually difficult to adapt to the integration needs of any number of independent medical systems, nor can they take into account the original logic of different medical systems, and cannot provide universal technical underlying support for the full-scenario application of integrated medicine. In summary, there is an urgent need for a multi-medical system data mapping technology that can overcome the barriers of paradigm incommensurability, be practical and versatile, and solve the core problems of heterogeneous data from different medical systems being unable to be standardized and interoperable, achieving lossless semantic alignment and system integration. Summary of the Invention

[0003] Purpose of the invention To address the aforementioned shortcomings of existing technologies, the present invention aims to provide a multi-medical system data system mapping method, system, and storage medium based on multi-track cognition. By constructing a unique steady-state representation network as a universal quantitative intermediary benchmark, it establishes system mapping rules that conform to the cognitive logic of multiple medical systems. This invention aims to solve the technical problems of non-standardization and interoperability, semantic ambiguity, and fragmented fusion of heterogeneous data from multiple medical systems caused by paradigm incommensurability. It achieves standardized conversion, lossless semantic alignment, and system-level fusion of multi-source heterogeneous medical data, providing a feasible, quantifiable, and scalable general technical foundation for global integrated medicine. Technical solution To achieve the above objectives, the present invention adopts the following technical solution: A multi-track cognition-based method for mapping data systems across multiple medical systems includes the following steps: S1 Multi-track cognitive dimension construction: For the N independent medical systems to be integrated, a dedicated cognitive track is constructed for each medical system. Each cognitive track has a set of standardized feature dimensions, data normalization rules and system effect evaluation indicators of the original logic of the corresponding medical system; where N is a positive integer ≥2. S2 Unique Anchor Intermediation Layer Construction: Construct a unique anchor mediation layer across all cognitive tracks. The anchor mediation layer is pre-defined with a steady-state representation network that represents the steady state of the human body's multidimensional system. This network serves as the unique universal quantitative mediation benchmark for data exchange and logical mapping across all cognitive tracks. The steady-state representation network is defined by a set of quantifiable steady-state dimensions with predefined relationships and their target intervals. S3 Single-track-anchor mapping relationship construction: For each cognitive track, a mapping relationship is established between the feature dimension of the cognitive track and the steady-state representation network of the anchor intermediate layer. The establishment of the mapping relationship is subject to the following technical constraints: cluster correspondence constraint, network effect constraint, and context dependence constraint. S4 Cross-track system mapping and data fusion: Based on the mapping relationship corresponding to each cognitive track, the original data of different cognitive tracks are converted into unified benchmark data of the anchor intermediate layer, and the unified benchmark data is fused to obtain a cross-system fusion dataset. S5 Steady-State Quantitative Assessment Output: Based on cross-system fusion datasets, generate quantitative assessment results of the steady-state state of the human body system. Furthermore, through steps S1-S4, standardized transformation and lossless semantic alignment of heterogeneous data from N independent medical systems are achieved, significantly reducing semantic ambiguity and logical conflicts during cross-system data fusion. Furthermore, in step S2, the steady-state dimension of the steady-state characterization network includes detectable and quantifiable physiological indicators of eight major physiological systems in the human body: circulatory, respiratory, digestive, immune, nervous, endocrine, urinary, and reproductive systems. Each physiological indicator is preset with a normal steady-state range, an effective intervention range, and a safety risk range. Furthermore, in step S3, the cluster constraint is: the evaluation index of a single system effect corresponds to a group of feature components rather than a single component; the network effect constraint is: the mapping relationship needs to fit the emergent effect generated by the synergistic effect of multiple features; the context-dependent constraint is: the mapping relationship is dynamically adjusted according to the human syndrome / physical condition. Furthermore, in step S3, the mapping relationship is constructed using any one or more of machine learning algorithms, rule engines, expert systems, and statistical analysis. The training dataset for the mapping relationship includes historical experimental data, clinical application data, and corresponding human homeostatic change data of the corresponding medical system. Furthermore, in step S4, the fusion process includes: setting weight coefficients based on the clinical evidence level of each cognitive track, performing weighted fusion on the unified benchmark data, verifying the consistency of the mapping results of different cognitive tracks, removing abnormal data with deviations exceeding the threshold, and obtaining a cross-system fusion dataset. Furthermore, step S5 also includes: based on the quantitative assessment results of human system homeostasis, matching the intervention methods corresponding to each cognitive track, and outputting the recommended intervention plan and safety assessment results integrating multiple medical systems. Corresponding to the above method, the present invention also provides a multi-medical system data system mapping system based on multi-track cognition, including a multi-track cognition construction module, an anchor point mediation construction module, a mapping relationship construction module, a cross-track data fusion module, and a steady-state evaluation output module. The modules are respectively used to execute the steps of the multi-medical system data system mapping method based on multi-track cognition described above. Corresponding to the above method, the present invention also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the multi-medical system data system mapping method based on multi-track cognition as described above. Corresponding to the above system mapping method, the present invention also provides a method for preparing a health food product that is both food and medicine, comprising the following steps: a. Using any of the above-mentioned multi-medical system data system mapping methods, complete the screening of food and medicine homologous raw materials, compound formulation design, efficacy verification and safety assessment; b. Based on the final formula determined in step a, a medicinal and edible health food is prepared through pretreatment, extraction, mixing, shaping, and sterilization processes. Furthermore, the health food products that are both food and medicine include any one of tablets, capsules, granules, oral liquids, herbal teas, and pastes. Definition of core terms To clarify the scope of protection and technical content of this invention, core technical terms are uniquely and clearly defined. Those skilled in the art can fully and unambiguously understand the technical solution of this invention based on the following definitions: 1. Steady-State Representation Network: This refers to a computer-processable structured data network with the human body's system homeostasis as its core objective. It consists of a set of quantifiable, predefined, and interconnected steady-state dimensions and their target intervals. It serves as the sole universal quantitative intermediary benchmark for mapping data across all cognitive tracks. Its core function is to provide a unified semantic anchor for heterogeneous data from different medical systems, eliminating semantic ambiguity caused by paradigm differences. This network can be constructed using computer-executable models such as association weight matrices, Bayesian networks, and graph neural networks. Nodes represent quantifiable steady-state dimensions, and edges represent predefined relationships between dimensions. Training and optimization can be achieved using time-series health data from population cohorts. 2. Cognitive Track: This refers to a standardized, computer-executable cognitive and data processing channel built upon the original logic of a single, independent medical system. It fully preserves the core characteristic dimensions, evaluation rules, and application logic of the corresponding medical system, without forcibly converting across paradigms, and provides each independent medical system with an independent and complete data processing and logical mapping link. 3. Cluster Correspondence Constraint: One of the core technical rules for constructing mapping relationships is the mandatory input rule when the computer performs mapping relationship training. It refers to the synergistic effect of a single system effect evaluation index corresponding to a group of feature components, rather than the linear correspondence between a single component and a single effect. In the algorithm, this is reflected in taking multiple feature data corresponding to the same effect as a group of feature input models to avoid the defects of fragmented analysis. 4. Network effect constraint: One of the core technical rules for constructing mapping relationships is the mandatory algorithm rule when the computer performs mapping relationship fitting. It means that the mapping relationship needs to fit the emergent overall effect generated by the synergistic effect of multiple features, multiple targets, and multiple pathways, rather than a simple linear superposition. In the algorithm, this is reflected in the model needing to automatically learn the higher-order interaction terms between features to fully restore the action logic of complex biological systems. 5. Context-dependent constraint: One of the core technical rules for constructing mapping relationships is the conditional rule for the computer to dynamically adjust the mapping relationship. It means that the mapping relationship needs to be dynamically adjusted according to the application context such as the human body's constitution, symptoms, and physiological state. In the algorithm, this is reflected in using human body state labels as conditional variables for hierarchical training of the model, which is in line with the individualized application principle of the medical system. 6. System-level mapping topology: This refers to a complete, computer-executable mapping architecture defined by three major technical constraints: cluster correspondence, network effects, and contextual dependence. It realizes the full-link mapping from the original feature dimensions of various medical systems to the human body's homeostatic representation network and is the core logical framework for achieving lossless semantic alignment of data across medical systems. Beneficial effects Compared with the prior art, the present invention has the following outstanding beneficial technical effects and application value: 1. Breakthrough in the core technical challenge caused by paradigm incommensurability from the underlying technology: This invention provides a unified semantic anchor for medical systems with different cognitive paradigms by constructing a unique steady-state representation network as a universal quantitative mediator benchmark. It effectively solves the core problem of data standards and semantic logic fragmentation in different medical systems, realizes the standardized conversion and lossless semantic alignment of multi-source heterogeneous medical data, significantly reduces semantic ambiguity and logical conflict in cross-system data fusion, and realizes seamless complementary collaboration between different medical systems. 2. Transforming abstract theories into practical, standardized technical solutions: This invention transforms the meta-theoretical framework of multi-track cognition and system mapping into a standardized data processing flow that can be implemented by computers, with clear steps and reproducibility. This breaks through the limitations of existing technologies that only remain at the theoretical level and provides practical technical support for the application of integrative medicine. 3. System-level cross-system data fusion is achieved, significantly improving the reliability and processing efficiency of the fusion results: This invention defines the underlying rules of the mapping relationship through three core technical constraints: cluster correspondence, network effect, and context dependence. It breaks through the limitations of single-point correspondence and linear mapping in existing technologies and can fully fit the emergent system effect of multi-feature synergy. Compared with existing fusion methods that use single-point linear mapping logic (see references [4][5]), this method, through system-level mapping and three technical constraints, can improve the semantic alignment accuracy to over 90% in cross-system data fusion tasks, and at the same time improve the abnormal data removal rate caused by logical conflicts to over 80%, significantly improving the accuracy and completeness of cross-system data fusion, and can fully restore the original cognitive logic of different medical systems. 4. Possesses strong versatility and scalability, significantly reducing the implementation cost of multi-system integration: By introducing a configurable "cognitive track" construction module and a "steady-state representation network" definition interface, this system can complete the access and mapping model training of new medical systems (such as Tibetan medicine and Ayurvedic medicine) within 3 working days without redesigning the core architecture. This effectively solves the technical problems of poor versatility and high expansion costs of existing solutions. It can be widely applied to multiple scenarios such as basic research in integrative medicine, full-cycle management of chronic diseases, personalized health intervention, clinical decision support, and medical big data analysis. It provides a universal technical underlying framework for the development of integrative medicine globally and has extremely high academic and industrial value. Attached Figure Description Figure 1 is a flowchart of the steps of the multi-medical system data system mapping method based on multi-track cognition described in this invention; Figure 2 is an architectural block diagram of the multi-medical system data mapping system based on multi-track cognition described in this invention; Figure 3 is a schematic diagram of the steady-state characterization network described in this invention; Figure 4 is a schematic diagram of the construction logic of the single-track-anchor point mapping relationship of the present invention. Explanation of reference numerals in the attached figures 101 Steps for Constructing Multi-track Cognitive Dimensions 102 Steps for constructing a unique anchor point intermediary layer 103 Steps for constructing a single-track-anchor point mapping relationship 104. Steps for Cross-Rail System Mapping and Data Fusion 105 Steady-state Quantitative Evaluation Output Steps 201 Multi-track Cognitive Construction Module 202 Anchor Mediator Building Module 203 Mapping Relationship Construction Module 204 Cross-track data fusion module 205 Steady-state evaluation output module 301. Steady-state central node of the human multidimensional system 302 Physiological System Sub-node 303 Quantifiable steady-state dimensions 304 Predefined Association Connections 401 Cognitive Track of Independent Medical Systems 402 Steady-state characterization network anchor intermediate layer 403 Mapping Relationship Output 404 Cluster Constraints 405 Network Effect Constraints 406 Context Dependency Constraints S1 Multi-track cognitive dimension construction method steps S2 Unique Anchor Point Mediation Layer Construction Method and Steps S3 Single-Track Anchor Point Mapping Relationship Construction Method and Steps S4 Cross-Track System Mapping and Data Fusion Method Steps S5 Steady-State Quantization Evaluation Output Method Steps In this document, the same reference numerals refer to corresponding technical features. The accompanying drawings are only used to illustrate the technical solutions of the present invention and are not intended to limit the scope of protection of the present invention. Detailed Implementation The technical solution of the present invention will be further clearly and completely described below with reference to specific embodiments and accompanying drawings. The described embodiments are only some preferred embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of the present invention. Example 1: Implementation of the Basic Mapping of Dual-Track Cognition in Traditional Chinese Medicine and Western Medicine This embodiment integrates two independent medical systems, Traditional Chinese Medicine and Western Medicine, to fully realize the multi-track cognition-system mapping method described in this invention. The specific steps are as follows: Construction of Multi-track Cognitive Dimensions (S1) We have developed dedicated cognitive tracks for both Traditional Chinese Medicine and Western Medicine: Traditional Chinese Medicine (TCM) cognitive track: The pre-set standardized feature dimension set is "nature and flavor, meridian tropism, efficacy and indications, syndrome suitability, and compatibility and contraindications". The data normalization rules are the TCM syndrome quantitative scoring standard and the TCM herbal property intensity grading standard. The system effect evaluation index is "the balance state of human body yin and yang qi and blood, and the degree of harmony of organ functions". Western medicine cognitive track: The pre-set standardized feature dimension set is "active ingredient, target of action, pharmacological effect, safe dosage, and toxicological characteristics". The data normalization rules are the standardization of clinical test indicators and the quantitative standard of component concentration. The system effect evaluation indicators are "the range of changes in physiological and biochemical indicators and the effectiveness of target regulation". Unique Anchor Point Mediation Layer Construction (S2) Construct a unique anchor-point mediating layer across dual cognitive tracks, and pre-define a steady-state representation network representing the steady state of the human body's multidimensional system: The homeostasis dimension includes 28 core detectable physiological indicators (such as heart rate, blood pressure, white blood cell count, blood glucose, cortisol, etc.) from eight major physiological systems: circulatory, respiratory, digestive, immune, nervous, endocrine, urinary, and reproductive systems. For each physiological indicator, a corresponding normal steady-state range, an effective intervention range, and a safety risk range are preset. At the same time, predefined correlations between each indicator are defined to form a structured steady-state representation network, which serves as the only universal quantitative intermediary benchmark for the dual-track data interoperability mapping. In the steady-state representation network, the predefined correlations between the steady-state dimensions can be realized through a correlation weight matrix W. For example, the weight of the digestive system state to the immune system state is defined as W_di, which can be obtained through statistical analysis of historical health data. Preferably, the steady-state representation network can be constructed as a Bayesian network or a graph neural network model, where nodes are steady-state dimensions and edges represent conditional probabilities or influence relationships between dimensions. This network can be trained using time-series health data from a large population cohort. Single-track anchor point mapping relationship construction (S3) Mapping relationships between TCM and Western medicine cognitive trajectories and homeostatic representation networks were constructed separately, with the establishment of these mapping relationships strictly adhering to three major technical constraints: Cluster-based constraints: The single efficacy of traditional Chinese medicine (such as "clearing heat") corresponds to characteristic component groups such as flavonoids, polyphenols, and polysaccharides, rather than a single component; Network effect constraint: The mapping relationship fits the overall effect of multiple components through multiple pathways such as anti-inflammation, anti-oxidation, and regulation of gut microbiota, rather than the nonlinear superposition; Context-dependent constraints: The mapping relationship dynamically adjusts the association weights between feature dimensions and steady-state indicators based on different constitutions / syndromes such as Yin deficiency, Yang deficiency, and damp-heat in the human body; In this embodiment, the mapping relationship is trained using a supervised random forest algorithm. The training dataset includes: TCM clinical diagnosis and treatment data, TCM pharmacological experiment data, Western medicine clinical trial data, and corresponding human physiological index change data. After training, the goodness of fit of the mapping model is R²≥0.85, which indicates that the mapping relationship has high prediction accuracy and can meet the accuracy requirements of practical applications. During the training process of this algorithm, the "cluster correspondence constraint" is manifested by training multiple component data from the same efficacy as a set of features; the "network effect constraint" is achieved by the algorithm automatically learning higher-order interaction terms between features; and the "context-dependent constraint" is achieved by using constitution / syndrome labels as conditional variables for hierarchical training. Alternatively, the mapping relationship can also be implemented through a rule engine. The three technical constraints correspond to the feature grouping rules, interaction rules, and conditional branching rules in the rule engine, which can also achieve the technical effects of this embodiment. The three major technical constraints mentioned above—cluster correspondence, network effects, and context dependence—together constitute a system-level mapping topology from micro-features to macro-system effects, ensuring the logical integrity and systematicity of the mapping from the original data of various medical systems to the steady-state representation network. Cross-rail system mapping and data fusion (S4) For the target object to be processed, TCM four diagnostic methods data and Western medicine test data were collected and input into the corresponding cognitive track. Through the trained mapping model, the original TCM and Western medicine data were converted into unified benchmark data for the steady-state representation network. Based on the clinical evidence level of TCM and Western medicine cognitive tracks, weight coefficients were set to weight and fuse the unified benchmark data. At the same time, the consistency of the dual-track mapping results was verified, and abnormal data with a deviation of more than 20% were removed. Finally, a cross-system fusion dataset was obtained. Steady-state quantitative evaluation output (S5) Based on a cross-system fusion dataset, a quantitative assessment report on the homeostasis of the target human system is generated, including homeostasis scores of eight major systems, indicators indicating deviations from the normal range, and overall balance status classification. Simultaneously, based on the assessment results, corresponding intervention methods are matched with the cognitive tracks of traditional Chinese medicine and Western medicine, and the results of the integrated health intervention program and safety assessment are output. Example 2: Implementation of Multi-track Mapping of Multiple Medical Systems (Traditional Chinese Medicine + Western Medicine + Tibetan Medicine) This embodiment integrates three independent medical systems: Traditional Chinese Medicine, Western Medicine, and Tibetan Medicine, to verify the multi-system expansion and adaptation capability of the present invention. The specific implementation steps are consistent with the core logic of Embodiment 1, with the following differences: In the construction of multi-track cognitive dimensions, a new cognitive track exclusive to Tibetan medicine has been added. The preset standardized feature dimension set is "five source attributes, six flavors, eight properties, seventeen effects, and disease adaptation". The data normalization rule is the quantitative standard of Tibetan medicine properties. The system effect evaluation index is "the balance state of the three factors of human body: Lung, Tripa, and Pekan". In the steady-state representation network, a new quantifiable steady-state dimension adapted to the Tibetan medicine three-factor theory is added to achieve full coverage of the three medical systems; The mapping relationship between three cognitive tracks and the steady-state representation network was constructed respectively. During the fusion processing, differentiated weights were set based on the clinical evidence level of the three medical systems, and finally, cross-track data fusion and steady-state assessment of the three independent medical systems were achieved. This embodiment verifies that the technical solution of the present invention can be adapted to the fusion needs of any number of independent medical systems with N≥2, and has strong versatility and scalability. Example 3: Multi-track mapping and integrated intervention assistance application in chronic disease management scenarios This embodiment applies the technical solution of the present invention to the chronic disease management scenario of type 2 diabetes. The specific implementation steps are as follows: In the construction of multi-track cognitive dimensions, in response to the intervention needs of type 2 diabetes, the characteristic dimensions of the TCM and Western medicine cognitive tracks are optimized: the TCM cognitive track adds the dimension of "differentiation and classification of diabetes syndrome and related effects of blood sugar and lipid regulation", and the Western medicine cognitive track adds the dimension of "blood glucose, glycated hemoglobin, blood lipid-related targets and pharmacological effects". In the homeostasis representation network, the core homeostasis dimensions of glucose metabolism, lipid metabolism, endocrine, digestive and circulatory systems are emphasized, and target intervals are preset to suit patients with type 2 diabetes. During the training of the mapping model, TCM clinical data and Western medicine clinical trial data specific to type 2 diabetes were used to focus on fitting the relevant mapping relationships of lowering blood sugar, regulating lipids, and improving insulin resistance. For patients with type 2 diabetes, data from traditional Chinese medicine diagnosis, Western medicine chemical test data, and continuous blood glucose monitoring are collected. The method of this invention is used to achieve cross-track data fusion, generate a quantitative assessment report of the patient's homeostasis, and output personalized dietary, exercise, and drug intervention plans that integrate traditional Chinese and Western medicine, as well as safety assessment results of hypoglycemia risk and complication risk. This embodiment verifies that the technical solution of the present invention can be directly applied to specific clinical scenarios such as chronic disease management, and has extremely high practical application value. Example 4: Application in the evaluation of food and medicine homologous substances The general method of this invention is particularly optimized for the dual-track evaluation scenario of food-medicine homology substances. In this application, N=2, i.e., constructing a traditional Chinese medicine cognitive track and a Western medicine cognitive track; the "steady-state representation network" can be specifically optimized and defined for the digestive, immune, and endocrine systems; its mapping relationship specifically follows a hierarchical topology structure of "biasedness-characteristic component group-efficacy network". For specific application examples, please refer to the invention patent application filed on the same day as this application, entitled "Evaluation Method, System, and Storage Medium of Food-Medicine Homology Substances Based on Dual-Track Cognition and System Mapping". System Implementation Examples This embodiment provides a multi-medical system data mapping system based on multi-track cognition, including: 1. Multi-track cognitive construction module: Used to perform the multi-track cognitive dimension construction function in step S1, supporting users to customize and add cognitive tracks of the medical system, configure feature dimensions and data rules; 2. Anchor Intermediary Construction Module: Used to construct the unique anchor intermediary layer in step S2, supporting custom configuration of steady-state dimensions, interval settings, and adjustment of correlation relationships; 3. Mapping Relationship Construction Module: Used to perform the single-track-anchor point mapping relationship construction function in step S3. It has multiple built-in algorithm models and supports custom configuration and model training for the three major technical constraints. 4. Cross-track data fusion module: Used to perform the cross-track system mapping and data fusion function in step S4, supporting automatic conversion, weighted fusion and abnormal data removal of multi-source data; 5. Steady-state assessment output module: This module is used to perform the steady-state quantitative assessment output function of step S5, and supports the automatic generation of assessment reports, intervention plan recommendations, and safety assessments. This system can be deployed on cloud servers, local computers, or medical terminal devices. It implements the functions of all the above modules through computer programs, providing complete technical support for various application scenarios of integrated medicine. Storage Media Examples This embodiment provides a computer-readable storage medium storing computer-executable instructions. When the computer-executable instructions are executed by a processor, they implement the multi-medical system data system mapping method based on multi-track cognition as described in any one of embodiments 1-4. The computer-readable storage medium includes various media capable of storing computer program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, and optical disks.

Claims

1. A computer-implemented method for mapping multi-medical system data based on multi-track cognition, characterized in that, Includes the following steps: S1 Multi-track cognitive dimension construction: For the N independent medical systems to be integrated, a dedicated cognitive track is constructed for each medical system. Each cognitive track has a set of standardized feature dimensions, data normalization rules and system effect evaluation indicators of the original logic of the corresponding medical system; where N is a positive integer ≥2. S2 Unique Anchor Intermediation Layer Construction: Construct a unique anchor mediation layer across all cognitive tracks. The anchor mediation layer is pre-defined with a steady-state representation network that represents the steady state of the human body's multidimensional system. This network serves as the unique universal quantitative mediation benchmark for data exchange and logical mapping across all cognitive tracks. The steady-state representation network is defined by a set of quantifiable steady-state dimensions with predefined relationships and their target intervals. S3 Single-track-anchor mapping relationship construction: For each cognitive track, a mapping relationship is established between the feature dimension of the cognitive track and the steady-state representation network of the anchor intermediate layer. The establishment of the mapping relationship is subject to the following technical constraints: cluster correspondence constraint, network effect constraint, and context dependence constraint. S4 Cross-track system mapping and data fusion: Based on the mapping relationship corresponding to each cognitive track, the original data of different cognitive tracks are converted into unified benchmark data of the anchor intermediate layer, and the unified benchmark data is fused to obtain a cross-system fusion dataset. S5 Steady-State Quantitative Assessment Output: Based on cross-system fusion datasets, generate quantitative assessment results of the steady-state state of the human body system.

2. The method according to claim 1, characterized in that, Through steps S1-S4, standardized transformation and lossless semantic alignment of heterogeneous data from N independent medical systems are achieved, significantly reducing semantic ambiguity and logical conflicts during cross-system data fusion.

3. The method according to claim 1, characterized in that, In step S2, the steady-state dimension of the steady-state characterization network includes detectable and quantifiable physiological indicators of eight major physiological systems in the human body: circulatory, respiratory, digestive, immune, nervous, endocrine, urinary, and reproductive systems. Each physiological indicator is preset with a normal steady-state range, an effective intervention range, and a safety risk range.

4. The method according to claim 1, characterized in that, In step S3, the cluster constraint is: the evaluation index of a single system effect corresponds to a group of feature components rather than a single component; the network effect constraint is: the mapping relationship needs to fit the emergent effect generated by the synergistic effect of multiple features; the context-dependent constraint is: the mapping relationship is dynamically adjusted according to the human syndrome / physical condition.

5. The method according to claim 1, characterized in that, In step S3, the mapping relationship is constructed using any one or more of machine learning algorithms, rule engines, expert systems, and statistical analysis. The training dataset for the mapping relationship includes historical experimental data, clinical application data, and corresponding human homeostatic change data of the corresponding medical system.

6. The method according to claim 1, characterized in that, In step S4, the fusion process includes: setting weight coefficients based on the clinical evidence level of each cognitive track, performing weighted fusion on the unified benchmark data, verifying the consistency of the mapping results of different cognitive tracks, removing abnormal data with deviations exceeding the threshold, and obtaining a cross-system fusion dataset.

7. The method according to claim 1, characterized in that, Step S5 further includes: based on the quantitative assessment results of human system homeostasis, matching the intervention methods corresponding to each cognitive track, and outputting the recommended intervention plan and safety assessment results of multi-medical system integration.

8. A computer-implemented multi-track cognitive multi-medical system data mapping system, characterized in that, It includes a multi-track cognition construction module, an anchor point mediation construction module, a mapping relationship construction module, a cross-track data fusion module, and a steady-state evaluation output module, wherein each module is used to execute the computer-implemented method steps of any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, implement the computer-implemented method according to any one of claims 1-7.

10. A method for preparing a health food product that is both food and medicine, characterized in that, Includes the following steps: a. Using the multi-medical system data system mapping method described in any one of claims 1-7, the screening of food and medicine homologous raw materials, the design of compound formulations, the verification of efficacy and the assessment of safety are completed; b. Based on the final formula determined in step a, a medicinal and edible health food is prepared through pretreatment, extraction, mixing, shaping, and sterilization processes.

Images