A traditional chinese medicine teaching and clinical simulation method and system based on six meridians transmission theory

Abstract

The application discloses a traditional Chinese medicine teaching and clinical simulation method and system based on a six-meridian transmission theory, and particularly relates to the technical field of teaching simulation; the method comprises the following steps: collecting disease course record data and symptom time sequence data, reconstructing a symptom evolution chain and corresponding six-meridian branch labels of each case, and extracting six-meridian disease course node time sequence feature data; constructing a single-path six-meridian transmission candidate network and a six-meridian transmission candidate topology network, obtaining standard single-path six-meridian transmission network data and multi-branch six-meridian transmission topology structure data, and performing graph fusion and path weight re-labeling to generate six-meridian transmission topology network model data; combining patient symptom combinations to determine whether a current disease course node meets a cross-meridian bifurcation simulation trigger condition, and generating corresponding teaching feedback data and comparative learning data, so that a multi-branch nonlinear evolution process of six-meridian transmission can be presented in an information-based teaching and clinical simulation scene.

Description

Technical Field

[0001] This invention relates to the field of teaching simulation technology, and more specifically, to a method and system for teaching and clinical simulation of traditional Chinese medicine based on the theory of the six channels of transmission. Background Technology

[0002] The theory of the Six Channels Transmission and Transformation is an important component of TCM teaching and clinical practice. Currently, it is mainly implemented through traditional methods such as case analysis, case discussion, and study of classical medical texts in clinical teaching and case simulation.

[0003] The teaching and analysis usually focus on a single disease course, and the description of the disease evolution process is relatively simple and linear. It ignores the complexity of disease transmission across meridians, multiple meridians, and disease course bifurcation that are common in clinical practice. As a result, the teaching content and simulation methods are monotonous and lack authenticity, making it difficult to effectively cultivate students' clinical diagnostic ability for complex diseases, and also making it difficult to achieve a full simulation of real diagnosis and treatment scenarios in clinical teaching. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide a method and system for teaching and clinical simulation of traditional Chinese medicine based on the theory of the six channels of transmission to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] A teaching and clinical simulation method for Traditional Chinese Medicine based on the theory of the Six Channels Transmission includes the following steps:

[0007] S1: Collect disease course record data and symptom time series data, perform preprocessing, and output clinical standard case data of the Six Channels Disease Course;

[0008] S2, based on the clinical standard case data of the six meridian disease course, reconstruct the symptom evolution chain and the corresponding six meridian differentiation labels of each case, and output the temporal feature data of the six meridian disease course nodes;

[0009] S3, based on the temporal characteristic data of the disease process nodes of the six meridians, construct a candidate network for the transmission of the six meridians through a single path, and output standard single-path transmission network data of the six meridians through a single path.

[0010] S4. Based on the time-series characteristic data of the disease process nodes of the six meridians, identify the cross-meridian concurrent disease pattern and the multi-meridian mixed pattern, construct the candidate topology network of the six meridians, and output the multi-branch six meridians transmission topology data.

[0011] S5, performs graph fusion and path weight recalibration on the standard single-path six-channel transmission network data and the multi-branch six-channel transmission topology data to generate six-channel transmission topology network model data;

[0012] S6, based on the data of the Six Meridians Transmission Topology Network Model and the combination of patient symptoms, determines whether the current disease process node meets the cross-meridian bifurcation simulation triggering condition, and generates corresponding teaching feedback data and comparative learning data.

[0013] In a preferred embodiment, S1 specifically refers to:

[0014] Collect disease progress records from the TCM electronic medical record system and symptom time series data from the teaching case database;

[0015] Based on the TCM diagnosis names, syndrome descriptions, tongue and pulse information and Western medicine diagnosis codes in the medical record data, corresponding six meridian labels are generated using preset meridian mapping rules;

[0016] The data format of the disease course records and the symptom time series data with the six meridian differentiation labels were standardized and missing data values ​​were filled in, and the clinical standard case data of the six meridian disease course were output.

[0017] In a preferred embodiment, S2 specifically refers to:

[0018] Based on the clinical standard case data of the six meridian disease course, the symptom information recorded in each case is extracted in chronological order and arranged to generate a symptom evolution chain;

[0019] Associate the symptoms at each time point in the symptom evolution chain with the corresponding six meridian differentiation labels;

[0020] Based on the associated symptom evolution chain, characteristic parameters of symptom duration, symptom frequency, and symptom intensity changes are calculated for each disease stage.

[0021] Summarize the symptom evolution chain, the correlation between the six meridians and their corresponding labels, and the characteristic parameters of the disease course nodes, and output the time-series characteristic data of the six meridian disease course nodes.

[0022] In a preferred embodiment, S3 specifically refers to:

[0023] The pre-set rule library for the transmission of the six meridians is invoked to calculate the degree of matching between the characteristic parameters of symptom duration, symptom frequency and symptom intensity changes in the time sequence characteristic data of the six meridian disease process nodes and each classic forward transmission path in the rule library.

[0024] The path weight of each classic forward path is determined based on the degree of matching.

[0025] Based on the path weights of each classic forward transmission path, path selection is performed to construct a single-path Six Classic Transmission Candidate Network with classic forward transmission paths as the main component, and output standard single-path Six Classic Transmission Network data.

[0026] In a preferred embodiment, S4 specifically refers to:

[0027] Identify cross-meridian concurrent disease patterns and multi-meridian mixed disease patterns based on the temporal characteristic data of the six meridian disease process nodes;

[0028] The cross-meridian concurrent disease pattern and the multi-meridian mixed pattern are mapped to graph structures containing nodes and directed edges, respectively. The nodes represent the combination of meridian diseases corresponding to the time point of the disease course, and the directed edges represent the transmission direction between meridian diseases.

[0029] The topology merging and directed cycle detection are performed on the graph structure obtained by mapping to construct a candidate topology network of the six meridians and output multi-branch six meridians topology structure data.

[0030] In a preferred embodiment, S5 specifically refers to:

[0031] Using the pathological nodes in the standard single-path six-channel transmission network data as the reference nodes, the nodes and edges in the multi-branch six-channel transmission topology data are aligned and mapped and merged to form unified graph fusion data.

[0032] Based on graph fusion data, the transmission path weights between nodes in each fusion path are recalculated;

[0033] Based on the transmission path weights, all transmission paths in the graph fusion data are recalibrated to output the six-path transmission topology network model data.

[0034] In a preferred embodiment, S6 specifically refers to:

[0035] Based on the data of the Six Channels Transmission and Transformation Topology Network Model and the patient symptom combinations, channel selection conditions and bifurcation trigger threshold parameters input in the teaching scenario, cross-channel bifurcation trigger condition judgment is performed on the disease process nodes.

[0036] When a disease progression node meets the bifurcation triggering condition, update the disease evolution path in the TCM teaching and clinical simulation interface and generate corresponding teaching feedback data.

[0037] When the disease process node does not meet the bifurcation triggering condition, the existing six meridian transmission path is maintained and comparative learning data is generated.

[0038] In a preferred embodiment, the meridian selection criteria include a candidate meridian set and a meridian priority set.

[0039] In a preferred embodiment, the bifurcation trigger threshold parameters include a symptom matching threshold, a path weight threshold, and a path difference threshold.

[0040] On the other hand, this invention provides a traditional Chinese medicine teaching and clinical simulation system based on the theory of the six channels of transmission, comprising:

[0041] Data processing module: Collects medical record data and symptom time series data, performs preprocessing, and outputs clinical standard case data of the Six Channels disease process;

[0042] Temporal Feature Module: Based on the clinical standard case data of the Six Channels Disease Course, reconstruct the symptom evolution chain and corresponding Six Channels Differentiation Labels for each case, and output the temporal feature data of the Six Channels Disease Course nodes;

[0043] Single network construction module: Based on the temporal characteristic data of the six meridian disease process nodes, construct a single-path six meridian transmission candidate network and output standard single-path six meridian transmission network data;

[0044] Topology mining module: Based on the temporal characteristic data of the six meridian disease process nodes, it identifies cross-meridian concurrent disease patterns and multi-meridian mixed patterns, constructs candidate topology networks of six meridian transmission, and outputs multi-branch six meridian transmission topology structure data.

[0045] Fusion and calibration module: Performs graph fusion and path weight recalibration on standard single-path six-channel transmission network data and multi-branch six-channel transmission topology data to generate six-channel transmission topology network model data;

[0046] Bifurcation Feedback Module: Based on the data of the Six Meridians Transmission Topology Network Model and the combination of patient symptoms, determine whether the current disease stage meets the triggering conditions for cross-meridian bifurcation simulation, and generate corresponding teaching feedback data and comparative learning data.

[0047] The technical effects and advantages of this invention, a teaching and clinical simulation method and system for Traditional Chinese Medicine based on the theory of the Six Channels Transmission:

[0048] By collecting medical record data and symptom time series data, unified encoding and completeness of clinical information from multiple sources and formats were achieved. By reconstructing the symptom evolution chain and corresponding six-channel differentiation labels for each case, fine-grained multi-dimensional representations were provided for dynamic analysis of the disease course. By constructing a single-path six-channel transmission candidate network, standardized disease evolution paths based on the classic sequential transmission model were obtained, meeting the demonstration needs of the core process of the six-channel transmission theory in teaching. By identifying cross-channel concurrent disease patterns and multi-channel mixed patterns, a six-channel transmission candidate topology network was constructed, which can realistically reproduce common nonlinear and multi-channel patterns in clinical practice. The evolution structure of cross-pathway syndromes was studied. Standard single-pathway six-channel transmission network data and multi-branch six-channel transmission topology data were fused using graph fusion and path weight recalibration, forming a six-channel transmission topology network model that balances classical patterns with clinical diversity, thus improving the realism and generalization ability of simulation results. Based on the six-channel transmission topology network model data and patient symptom combinations, it was determined whether the current disease stage met the cross-channel bifurcation simulation triggering conditions and dynamic teaching feedback and comparative learning data were generated. This enabled adaptive demonstration and interaction between TCM teaching and clinical simulation, significantly enhancing the teaching relevance and the training effect of students' clinical decision-making abilities. Attached Figure Description

[0049] Figure 1 This is a schematic diagram of a traditional Chinese medicine teaching and clinical simulation method based on the theory of the six channels of transmission according to the present invention.

[0050] Figure 2 This is a schematic diagram of the structure of a traditional Chinese medicine teaching and clinical simulation system based on the theory of the six channels of transmission according to the present invention. Detailed Implementation

[0051] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0052] Example 1

[0053] Figure 1 This invention presents a method for teaching and clinical simulation of traditional Chinese medicine based on the theory of the six channels, which includes the following steps:

[0054] S1: Collect disease course record data and symptom time series data, perform preprocessing, and output clinical standard case data of the Six Channels Disease Course;

[0055] S2, based on the clinical standard case data of the six meridian disease course, reconstruct the symptom evolution chain and the corresponding six meridian differentiation labels of each case, and output the temporal feature data of the six meridian disease course nodes;

[0056] S3, based on the temporal characteristic data of the disease process nodes of the six meridians, construct a candidate network for the transmission of the six meridians through a single path, and output standard single-path transmission network data of the six meridians through a single path.

[0057] S4. Based on the time-series characteristic data of the disease process nodes of the six meridians, identify the cross-meridian concurrent disease pattern and the multi-meridian mixed pattern, construct the candidate topology network of the six meridians, and output the multi-branch six meridians transmission topology data.

[0058] S5, performs graph fusion and path weight recalibration on the standard single-path six-channel transmission network data and the multi-branch six-channel transmission topology data to generate six-channel transmission topology network model data;

[0059] S6, based on the data of the Six Meridians Transmission Topology Network Model and the combination of patient symptoms, determines whether the current disease process node meets the cross-meridian bifurcation simulation triggering condition, and generates corresponding teaching feedback data and comparative learning data.

[0060] S1 collects medical history records and symptom time-series data, performs preprocessing, and outputs standard clinical case data for the Six Channels disease process, including:

[0061] Collect disease progress records from the TCM electronic medical record system and symptom time series data from the teaching case database;

[0062] The medical record data in the TCM electronic medical record system includes clinical symptoms, TCM diagnosis names, syndrome descriptions, tongue and pulse information, Western medicine diagnostic codes, and medication regimens recorded at different time points during the patient's actual medical visit. For example, clinical symptoms include descriptions of symptoms such as fever, headache, chills, bitter taste in the mouth, dry throat, and abdominal pain; TCM diagnosis names include external wind-cold syndrome, Taiyang meridian syndrome, Yangming meridian syndrome, Shaoyang meridian syndrome, Taiyin meridian syndrome, Shaoyin meridian syndrome, or Jueyin meridian syndrome; syndrome descriptions include textual descriptions of chills and fever, sweating, thirst, fullness and discomfort in the chest and hypochondrium, and abdominal distension; tongue and pulse information includes records of the tongue body, tongue coating, and pulse condition; Western medicine diagnostic codes record the codes corresponding to the disease names according to the current disease classification coding standards; and medication regimens include formulas or drug combinations such as Ma Huang Tang, Ge Gen Tang, and Xiao Chai Hu Tang.

[0063] The symptom time-series data in the teaching case database consists of pre-organized and labeled teaching case data. It includes the clinical symptom types, intensity, duration, and trends at different time points in the course of the disease in multiple typical cases within the database. For example, the clinical symptom types in the symptom time-series data include fever, headache, chills, bitter taste in the mouth, dry throat, and abdominal pain. Symptom intensity is quantitatively assessed and recorded using a numerical scoring method; for example, symptom intensity is defined as a numerical scoring range of 1 to 10, where a score of 1 represents the lowest symptom intensity and a score of 10 represents the highest symptom intensity. Symptom duration records the cumulative duration of each symptom from its onset to the current time point, in hours, such as 2 hours, 4 hours, 12 hours, etc. Symptom trends are described chronologically, showing the gradual increase, decrease, or stabilization of symptom intensity.

[0064] Based on the TCM diagnosis names, syndrome descriptions, tongue and pulse information and Western medicine diagnosis codes in the medical record data, corresponding six meridian labels are generated using preset meridian mapping rules;

[0065] The meridian differentiation mapping rule is established by organizing the correspondence between meridian differentiation and syndrome related to the Six Channels theory. The rule takes as input the meridian differentiation keywords in the TCM diagnostic name, the combination of primary and secondary symptoms in the syndrome description, tongue and pulse information characteristics, and the disease location or nature corresponding to the Western medicine diagnostic code. It outputs one or more meridian differentiation labels from the Taiyang, Yangming, Shaoyang, Taiyin, Shaoyin, or Jueyin channels. For example, the rule stipulates that when the TCM diagnostic name contains Taiyang syndrome, and the syndrome description includes keywords such as aversion to cold, headache, and stiff neck, and the tongue and pulse information records a thin white tongue coating and a floating and tight pulse, and the Western medicine diagnostic code corresponds to an upper respiratory tract infection-related code, the meridian differentiation label for the disease course time node is mapped to the Taiyang channel. When the TCM diagnostic name contains Yangming syndrome, and the syndrome description includes high fever, profuse sweating, thirst, and irritability, and the tongue and pulse information records a yellow and dry tongue coating and a large and forceful pulse, the meridian differentiation label for the disease course time node is mapped to the Yangming channel. In cases where a disease progression time point may simultaneously satisfy multiple meridian mapping rules, the set of all meridians that satisfy the conditions is used as the six meridians label for the disease progression time point.

[0066] The data format of the disease course records and the symptom time series data with the six meridian differentiation labels were standardized and missing data values ​​were filled in, and the clinical standard case data of the six meridian disease course were output.

[0067] The generated medical record data with the Six Channels Differentiation tags were processed to unify the data format: Clinical symptom descriptions were standardized and coded, and a pre-set standard clinical symptom terminology library was used to match and code symptom descriptions in different electronic medical records, unifying heterogeneous symptom descriptions in different medical record systems into standardized symptom names and corresponding standard codes; Traditional Chinese Medicine (TCM) diagnostic names and syndrome descriptions were standardized, and synonymous or near-synonymous diagnostic names were unified into standard diagnostic terms; Medication regimen record data were standardized and coded, and a unified TCM formula terminology library was used for matching and coding; The Six Channels Differentiation tags were unified, and the Six Channels Differentiation tags were labeled with unified standard names, which were limited to six categories: Taiyang, Yangming, Shaoyang, Taiyin, Shaoyin, and Jueyin.

[0068] The symptom time series data were processed to standardize the data format: the symptom type names were standardized, and the symptom names in the symptom time series data were converted into standardized symptom terms and corresponding standard codes using a standard clinical symptom terminology library; the duration of symptoms was standardized to be measured in hours, recording the cumulative duration from the onset of symptoms to the current time point.

[0069] When there are missing data in symptom time series data and disease course record data, different completion strategies are adopted according to the data type: for example, for missing symptom types, the combination of symptoms appearing before and after the time points and other symptom manifestations during the same period are combined to infer and fill the missing data based on clinical experience rules; for missing numerical data such as symptom intensity scores or symptom duration, the data before and after the missing time points are used to fill the missing data using linear interpolation or trend inference based on the overall trend.

[0070] After standardizing the data format and processing missing values, standard clinical case data for the six meridian disease process is formed, including disease process record data and symptom time series data. Each disease process time node in the disease process record data is accompanied by a six meridian label, and each record in the symptom time series data has a symptom name, symptom intensity score and symptom duration in a unified format.

[0071] S2, based on the clinical standard case data of the Six Channels disease course, reconstructs the symptom evolution chain and corresponding Six Channels differentiation labels for each case, and outputs the temporal characteristic data of the Six Channels disease course nodes, including:

[0072] Based on the clinical standard case data of the six meridian disease course, the symptom information recorded in each case is extracted in chronological order and arranged to generate a symptom evolution chain;

[0073] For each case data in the standard clinical case data of the six-channel disease course, the clinical symptoms corresponding to each disease course time node recorded in the case data are extracted sequentially. The extraction method of clinical symptoms includes extracting all clinical symptom types recorded at each disease course time node, such as fever, headache, chills, bitter taste in the mouth, dry throat or abdominal pain, etc., and arranging them in sequence according to the time axis of the case data to obtain the symptom evolution chain. Each symptom evolution chain arranges the symptoms according to the chronological order of the case data time nodes, and multiple symptoms that exist at the same disease course time node are presented as symptom combinations of the disease course node in a combined table to show the changing pattern of symptom combinations over time.

[0074] Associate the symptoms at each time point in the symptom evolution chain with the corresponding six meridian differentiation labels;

[0075] For each generated symptom evolution chain, based on the six meridian differentiation annotation information in the clinical standard case data of the six meridian disease course, an association relationship is established between the clinical symptom combination and the six meridian differentiation label annotated at each disease course time node. The association relationship between the clinical symptom combination and the six meridian differentiation label is expressed in the form of a structured data table, where each row of the structured data table represents a disease course time node, and each row contains the clinical symptom combination and the corresponding six meridian differentiation label. For example, a disease course node data is expressed as: Disease course time node: Day 3; Clinical symptom combination: Fever, headache; Corresponding six meridian differentiation label: Taiyang meridian, Yangming meridian.

[0076] Based on the associated symptom evolution chain, characteristic parameters of symptom duration, symptom frequency, and symptom intensity changes are calculated for each disease stage.

[0077] Based on the clinical symptoms and their corresponding durations (cumulative duration) recorded at each stage of the symptom progression chain, the starting time and ending time of each clinical symptom are identified. The total duration (in hours) of the clinical symptom during the entire observation period is obtained by calculating the difference between the first and last time points. For example, if fever first appears on day 1 (recorded duration 0 hours) and last appears on day 3 (recorded duration 48 hours), and the fever persists, then the total duration of the fever is 48 hours.

[0078] The frequency of each clinical symptom is determined by counting the number of time points in the symptom evolution chain it covers. For example, if headache is recorded at 5 out of 10 time points from day 1 to day 5, the frequency is recorded as 5.

[0079] The characteristic parameter of symptom intensity change is calculated using the symptom intensity difference method at disease course nodes. That is, for each clinical symptom, the difference in symptom intensity score between adjacent disease course nodes is calculated. For example, in the symptom evolution chain, if the symptom intensity score of fever is 5 on day 2 and 7 on day 3, then the characteristic parameter of symptom intensity change is recorded as +2.

[0080] Summarize the symptom evolution chain, the correlation relationship of the six meridians and the characteristic parameters of the disease course nodes, and output the time sequence characteristic data of the six meridian disease course nodes;

[0081] The clinical symptom combinations recorded at each disease stage in the symptom evolution chain, the corresponding six-channel differentiation labels, and the calculated characteristic parameters of symptom duration, symptom frequency, and symptom intensity change are uniformly integrated to form the time-series characteristic data of the six-channel disease stage. For example, the time-series characteristic data of the six-channel disease stage includes: disease stage: day 4; symptom combination: headache, dry throat; six-channel differentiation label: Shaoyang meridian; symptom duration: 48 hours; symptom frequency: 5 times; symptom intensity change: +2.

[0082] S3, based on the temporal characteristic data of the six meridian disease progression nodes, constructs a single-path six-meridian transmission candidate network and outputs standard single-path six-meridian transmission network data, including:

[0083] The pre-set rule library for the transmission of the six meridians is invoked to calculate the degree of matching between the characteristic parameters of symptom duration, symptom frequency and symptom intensity changes in the time sequence characteristic data of the six meridian disease process nodes and each classic forward transmission path in the rule library.

[0084] A pre-constructed rule base for the transmission of diseases through the Six Channels is established. This rule base is based on the classical sequential transmission path of diseases through the Six Channels. Each classical sequential transmission path is defined as a sequence of several disease progression nodes connected sequentially. Each disease progression node includes at least a channel marker, typical clinical symptom combination information, and disease progression time stage information. The channel marker is defined using a unified set of Six Channel channel names, including at least one or more combinations of Taiyang, Yangming, Shaoyang, Taiyin, Shaoyin, and Jueyin channels. The typical clinical symptom combination information is recorded using standard symptom names from a standard clinical symptom terminology database. Each disease progression node records several clinical symptoms representing the typical manifestations of that disease progression stage, such as fever, headache, chills, bitter taste in the mouth, dry throat, and abdominal pain. The disease progression time stage information describes the temporal order of the classical sequential transmission path of diseases through the Six Channels in the clinical course. For example, it can be segmented into early, middle, and late stages of the disease, or marked with time nodes such as day 1, day 2, and day 3. For each classic sequential path of disease evolution of the six channels, the corresponding meridian combination relationship is recorded in the six channel transmission rule base. The meridian combination relationship is used to determine the order and parallel existence of meridians in different disease stages. For example, the classic sequential path of disease evolution of the six channels can be recorded as the sequential structure of the Taiyang channel stage, Yangming channel stage, and Shaoyang channel stage. The meridian combination relationship also records the concurrent diseases of meridians in each stage.

[0085] The Six Channels Transmission Rule Base sets a set of feature template parameters for matching calculations for each classic sequential transmission path of Six Channel diseases. These feature template parameters include a reference range for symptom duration, a reference range for symptom frequency, and a reference pattern for symptom intensity changes. The symptom duration reference range describes the duration interval of typical clinical symptoms at different disease stages within the classic sequential transmission path of Six Channel diseases. For example, it can record the duration of fever symptoms in the Taiyang channel stage as 24 to 72 hours. The symptom frequency reference range describes the frequency interval of a certain type of symptom within a disease stage. For example, it can record the frequency of headache symptoms in the Yangming channel stage as 2 to 6 times. The symptom intensity change reference pattern describes the trend of symptom intensity scores as the disease progresses. For example, it records that the intensity of fever symptoms increases rapidly in the Taiyang channel stage, remains at a high level in the Yangming channel stage, and gradually decreases in intensity in the Taiyin channel stage. The parameter settings for the feature template are determined based on the statistical results of historical clinical standard case data of the six-channel disease process and the experience of TCM clinical experts. Multiple cases that have been confirmed by experts to conform to the typical six-channel transmission process can be selected from the clinical standard case data of the six-channel disease process. The duration distribution, frequency distribution and intensity change curve of each type of symptom are statistically analyzed. Then, the median, quartile or common interval range is extracted as a reference range based on the statistical results.

[0086] For each case in the time-series feature data of the six-channel disease progression nodes, the disease progression node sequence is extracted according to the time sequence of the disease progression. This sequence is considered a candidate disease progression trajectory and is matched against each classic sequential progression path of the six-channel disease progression in the six-channel transmission rule base. The matching degree is calculated separately for the meridian label sequence, symptom duration parameter sequence, symptom frequency parameter sequence, and symptom intensity change characteristic parameter sequence. The meridian label sequence matching degree is obtained by comparing the consistency between the six-channel meridian label sequence recorded in the case's disease progression nodes and the meridian combination relationship sequence in the classic sequential progression path of the six-channel disease progression. The consistency of the meridian label sequence can be quantified using three levels: complete consistency, partial consistency, and inconsistency. Complete consistency is assigned a higher score, such as 1.0 point; partial consistency is assigned a score between 0.3 and 0.9 points depending on the proportion of matched nodes; and inconsistency is assigned 0 points. The symptom duration parameter sequence matching degree is calculated by determining whether the total duration of each clinical symptom in the case falls within the typical duration reference range of that clinical symptom on the corresponding path in the Six Channels Transmission Rule Base. If the total duration falls within the reference range, a high score is assigned to the symptom duration matching degree of the disease course node, such as 1.0. If the symptom duration parameter deviates slightly from the reference range, a medium score is assigned, such as 0.5. If the total duration exceeds the reference range, a score of 0 is assigned. The symptom duration matching degree of all disease course nodes of a case is averaged to obtain the symptom duration parameter sequence matching degree. The matching degree of the symptom frequency parameter sequence is calculated by comparing the total number of occurrences of each clinical symptom in the case with the reference range of symptom frequency for the same symptom in the corresponding classical sequential progression path of the Six Channels disease in the Six Channels Transmission Rule Base. If the total number of occurrences falls within the reference range, a high score is assigned; if it deviates slightly, a medium score is assigned; and if it is completely outside the reference range, a score of 0 is assigned. The matching degree of the overall symptom frequency parameter sequence is obtained by averaging the matching scores of all related symptoms. The matching degree of the symptom intensity change characteristic parameter sequence is calculated by comparing the symptom intensity change difference sequence at each disease stage in the case with the direction and magnitude of change of the symptom intensity change reference pattern recorded in the Six Channels Transmission Rule Base. If the direction and magnitude of change are basically consistent with the reference pattern, a high score is assigned, for example, 0.8 to 1.0 points; if the direction of change is partially consistent but the magnitude of change differs significantly, a medium score is assigned, for example, 0.4 to 0.7 points; and if the direction of change is completely opposite, a score of 0 is assigned. The matching degree of the symptom intensity change characteristic parameter sequence is then obtained by averaging multiple nodes throughout the entire disease course.

[0087] After obtaining the sequence matching degrees of meridian labeling, symptom duration, symptom frequency, and symptom intensity change, a weighted summation method is used to calculate the overall degree of matching between the case's disease progression trajectory and each classic sequential path of the six meridian syndromes. Pre-set weight coefficients for meridian labeling, symptom duration, symptom frequency, and symptom intensity change, with the sum of these weight coefficients equal to 1. For example, among multiple weighting combinations, a combination with a meridian labeling weighting of 0.4, a symptom duration weighting of 0.2, a symptom frequency weighting of 0.2, and a symptom intensity change weighting of 0.2 is selected as the weighting configuration. The overall matching degree value is equal to the meridian label sequence matching degree multiplied by the meridian label sequence matching degree weight coefficient, plus the symptom duration parameter sequence matching degree multiplied by the symptom duration parameter matching degree weight coefficient, plus the symptom frequency parameter sequence matching degree multiplied by the symptom frequency parameter matching degree weight coefficient, plus the symptom intensity change characteristic parameter sequence matching degree multiplied by the symptom intensity change parameter matching degree weight coefficient. The overall matching degree value ranges from 0 to 1. The larger the overall matching degree value, the closer the disease course evolution trajectory of the case is to the evolution path of the six meridian syndromes in the classic sequential transmission.

[0088] The path weight of each classic forward path is determined based on the degree of matching.

[0089] The overall matching score is normalized and used as the path weight. The path weight represents the relative importance of the classical sequential transmission path of the Six Channels disease pattern in the interpretation of the Six Channels disease pattern for a given case. For each case, several classical sequential transmission paths of the Six Channels disease pattern and their corresponding path weights are obtained.

[0090] Based on the path weights of each classic forward transmission path, path selection is performed to construct a single-path Six Classic Transmission Candidate Network with classic forward transmission paths as the main component, and output standard single-path Six Classic Transmission Network data.

[0091] Path selection can be done by sorting, which sorts all the classic sequential transmission paths of the six meridian diseases according to the path weight, and selects the top-ranked paths. For example, the top 3 paths by path weight can be selected as candidate paths to be included in the single-path six meridian transmission candidate network.

[0092] When constructing a single-path candidate network for the transmission of diseases through the six meridians, the selected classical sequential transmission paths of the six meridian diseases are uniformly represented as directed path structures. Nodes in the directed path structure represent the differentiating stages of the disease process during the transmission of diseases through the six meridians. Each node records the differentiating stage's marker and a summary of typical symptoms. Directed edges represent the transmission direction between differentiating stages, recording the relationship from the previous differentiating stage to the next. For cases involving multiple classical sequential transmission paths of diseases through the six meridians, these directed paths are merged by sharing nodes. For example, nodes representing the Taiyang meridian stage that are present in different paths can be merged into a single Taiyang meridian stage node, thus forming a single-path candidate network for the transmission of diseases through the six meridians composed of multiple superimposed directed paths. Each directed path in the network retains its corresponding path identifier and path weight.

[0093] Finally, the node information, edge information, path identification information, and path weight information in the single-path Six Channel Transmission Candidate Network are organized into structured output data to form standard single-path Six Channel Transmission Network data. In the standard single-path Six Channel Transmission Network data, each node records the channel identifier, stage sequence number, and summary of typical symptom characteristics, and each directed edge records the starting node number, ending node number, and the path identifier and path weight associated with the evolution path of the Six Channel disease syndrome in the classical sequential transmission to which the directed edge belongs.

[0094] S4, based on the temporal characteristic data of the six meridian disease progression nodes, identifies cross-meridian concurrent disease patterns and multi-meridian mixed patterns, constructs a candidate topology network for six meridian transmission, and outputs multi-branch six meridian transmission topology structure data, including:

[0095] Identify cross-meridian concurrent disease patterns and multi-meridian mixed disease patterns based on the temporal characteristic data of the six meridian disease process nodes;

[0096] For each case's disease progression sequence, the Six Channels Differentiation Label field in each disease progression time node is examined sequentially. If the Six Channels Differentiation Label in the disease progression time node contains two or more channel names, the disease progression time node is marked as a candidate node for cross-channel concurrent disease. A cross-channel concurrent disease pattern identifier is constructed based on the set of Six Channels Differentiation Labels. The cross-channel concurrent disease pattern identifier can be recorded in the form of ordered concatenation of channel names; for example, different combinations of concurrent diseases can be represented using Taiyang Channel + Yangming Channel, Taiyang Channel + Shaoyang Channel + Yangming Channel, etc. The number of occurrences of each cross-channel concurrent disease pattern identifier in all disease progression time nodes of the same case is counted. Simultaneously, the number of cases with each cross-channel concurrent disease pattern identifier is counted across all cases. The number of cases is used as the support parameter for the cross-channel concurrent disease pattern. Set a screening threshold for the support parameter of the cross-menstrual disease pattern. The screening threshold can be determined by statistically analyzing the distribution of the support parameter of the cross-menstrual disease pattern in all cases. For example, a lower limit of support can be determined based on the median, upper quartile, or certain percentile of the support parameter. Cross-menstrual disease patterns with support parameters greater than or equal to the lower limit of support are retained as valid cross-menstrual disease patterns.

[0097] For each case, the meridian labels of the six meridians in the disease progression sequence are extracted in chronological order to form a meridian label sequence. For example, the meridian label sequence can be in the form of Taiyang meridian, Yangming meridian, Taiyang meridian, Shaoyang meridian, Yangming meridian, etc. When identifying multiple meridian mixed patterns, a sliding time window length parameter is set. This parameter can be empirically set based on the frequency of meridian alternation in the typical six meridian transmission process; for example, it can be set to 3 or 4. The meridian label sequence is slid along with the sliding time window length parameter. Each window corresponds to a continuous meridian label subsequence. If there is an alternating meridian switching relationship in the meridian label subsequence, such as a round-trip structure of Taiyang meridian-Yangming meridian-Taiyang meridian, then the corresponding meridian label subsequence is recorded as a candidate pattern for multiple meridian mixed patterns. For each candidate pattern of mixed diagnoses, the number of times the pattern appears in all cases is counted to obtain the support parameter of the mixed diagnoses pattern. The support parameter of the mixed diagnoses pattern is compared with the preset support threshold of the mixed diagnoses pattern for screening. The screening method can be the same as the support screening method of cross-diagnoses pattern, that is, by statistically analyzing the distribution of the support parameters of all candidate patterns of mixed diagnoses, a lower limit of support is selected, and mixed diagnoses with support parameters greater than or equal to the lower limit of support are retained as valid mixed diagnoses patterns.

[0098] The cross-meridian disease pattern and the multi-meridian mixed pattern are respectively mapped to graph structures containing nodes and directed edges;

[0099] In the mapping process of cross-meridian disease patterns, each cross-meridian disease pattern corresponds to a graph structure representation. The nodes in the graph structure represent the combinations of meridian syndromes involved in the cross-meridian disease pattern. The node identifier can be recorded by splicing the combination of meridian syndromes and a summary of typical clinical symptoms, for example, it can be recorded as disease stage category + Taiyang meridian + Yangming meridian + representative symptom combination. Since the cross-meridian disease pattern reflects the state of multiple meridian syndromes existing in parallel within the same disease stage time node, the combination of meridian syndromes can be regarded as a single node for each cross-meridian disease pattern. Directed edges are not introduced inside the cross-meridian disease pattern. The directed edges corresponding to the cross-meridian disease pattern are mainly established between different disease stage time nodes to represent the direction of transmission between meridian syndromes. For example, for the transmission relationship between the cross-meridian disease pattern Taiyang meridian + Yangming meridian and the meridian syndrome label Yangming meridian + Shaoyang meridian in the next disease stage time node, a directed edge can be added to the graph structure from the node Taiyang meridian + Yangming meridian to the node Yangming meridian + Shaoyang meridian. The directed edge can be attached with the count information of the occurrence of this transmission in the case data.

[0100] In the mapping process of multiple meridian mixing patterns, each multiple meridian mixing pattern also corresponds to a graph structure representation. Each meridian label or meridian combination in the multiple meridian mixing pattern is mapped to a node. If there are multiple meridian label combinations at the same time node in the multiple meridian mixing pattern, the multiple meridian label combinations at the time node are still mapped to a meridian combination node. For example, when the meridian label subsequence of the multiple meridian mixing pattern is Taiyang meridian-Yangming meridian-Taiyang meridian, three nodes can be established in the graph structure. The three nodes correspond to the Taiyang meridian disease at the first time position, the Yangming meridian disease at the second time position, and the Taiyang meridian disease at the third time position, respectively. Then, two directed edges are established between the nodes. One directed edge points from the Taiyang meridian disease node at the first time position to the Yangming meridian disease node at the second time position, and the other directed edge points from the Yangming meridian disease node at the second time position to the Taiyang meridian disease node at the third time position. For more complex mixed meridian patterns, such as Taiyang meridian-Shaoyang meridian-Yangming meridian-Shaoyang meridian, multiple nodes and multiple directed edges can be established sequentially. The node identifier records the meridian name and the corresponding time sequence information, and the directed edge records the starting node identifier and the ending node identifier. Attribute information such as the number of times the pattern appears can also be added.

[0101] Perform topology merging and directed loop detection on the mapped graph structure, construct a candidate topology network of the six meridians, and output multi-branch six meridians topology data.

[0102] The topology merging process specifically involves comparing and identifying all nodes in the cross-meridian disease pattern diagram structure and the multi-meridian mixed pattern diagram structure one by one, merging nodes with completely consistent time nodes and meridian disease combinations into a single unique node; and adjusting and merging the directed edges associated with the merged nodes accordingly. For example, if multiple graph structures contain the same transformation relationship from Taiyang meridian and Yangming meridian nodes to Shaoyang meridian nodes, the same transformation relationship is merged into the same directed edge, and the frequency of the directed edge and the corresponding case data are recorded to reflect the commonness and clinical typicality of disease transformation.

[0103] The directed cycle detection process is as follows: Directed cycle detection is defined as identifying closed paths in a graph structure that start from a specific meridian-differential syndrome node and return to the starting node through several directed edges. A standard graph depth-first search algorithm is used to implement directed cycle detection. During the traversal of each node, the current node access path is recorded. If a node is found to appear repeatedly in the access path, it is marked as a directed cycle, and the path of the directed cycle is recorded. The identified directed cycle paths are marked, and the meridian-differential syndrome combination nodes, the length of the cycle path, and the clinical symptom change characteristics are recorded.

[0104] The method for constructing the candidate topology network for the Six Channel Transmission is as follows: Based on the nodes after topology merging, a node set is constructed in the network. The node set records the disease progression time node information, the name of the meridian-differential syndrome combination, and a summary of clinical symptom characteristics for each node. Based on the directed edges and directed loops after topology merging, an edge set is constructed in the network. The edge set records the starting node information, ending node information, and corresponding clinical transformation characteristics of each directed edge, including the trend of symptom intensity changes and the changes in duration. For example, a directed edge records the transformation from the Taiyang meridian on the 2nd day of the disease progression node to the combined Taiyang and Yangming meridians on the 3rd day of the disease progression node, with an increase of 2 in symptom intensity score and an increase of 24 hours in duration. The node sequence and symptom change characteristics of each directed loop path are recorded to form a special loop structure in the candidate topology network for the Six Channel Transmission. The symptom characteristics and frequency that may lead to repeated fluctuations in clinical condition are recorded in the loop structure to improve the accuracy of clinical teaching simulation. The final output multi-branch Six Channel Transmission topology data includes the network node set, the directed edge set, and the directed loop path information.

[0105] S5 performs graph fusion and path weight recalibration on standard single-path six-channel transmission network data and multi-branch six-channel transmission topology data to generate six-channel transmission topology network model data, including:

[0106] Using the pathological nodes in the standard single-path six-channel transmission network data as the reference nodes, the nodes and edges in the multi-branch six-channel transmission topology data are aligned and mapped and merged to form unified graph fusion data.

[0107] All disease progression nodes are read from the standard single-path Six Channels Transmission Network data to establish a baseline node set, and a unique node number is assigned to each disease progression node. Each disease progression node records the meridian differentiation label, the sequential number of the disease progression stage, and a summary of typical clinical symptom characteristics, such as recording the Taiyang meridian stage, Yangming meridian stage, Shaoyang meridian stage, etc., and recording the representative symptom combinations corresponding to each stage. All nodes are read from the multi-branch Six Channels Transmission Topology data to construct a node set to be aligned. For each node in the node to be aligned, the meridian differentiation syndrome combination information and disease progression time node information recorded by the node are extracted. The meridian differentiation syndrome combination information and disease progression time node information are matched with the nodes in the baseline node set. If the meridian differentiation syndrome combination information is the same and the disease progression time node information belongs to the same disease progression stage interval, it is determined that the node to be aligned is successfully matched with a certain baseline node. The node to be aligned is mapped to the baseline node number and uniformly marked with the baseline node number in the graph fusion data. If the node to be aligned cannot match any baseline node in terms of syndrome combination information or disease course time node information, an extension node is added at the end of the baseline node set. The extension node is used as a new baseline node to participate in the graph fusion data construction, so as to ensure that all nodes in the multi-branch six-channel transmission topology data have corresponding node identifiers.

[0108] After node alignment, the directed edges in the multi-branch Six-Channel Transmission Topology data are mapped and merged. Each directed edge in the multi-branch Six-Channel Transmission Topology data records the transmission direction between the starting and ending nodes, and the number of times the directed edge appears in the case data or its support parameter. The starting and ending nodes of each directed edge are replaced with the corresponding baseline node numbers. If a directed edge with the exact same starting and ending node numbers already exists in the standard single-path Six-Channel Transmission Network data, the directed edge in the multi-branch Six-Channel Transmission Topology data and the directed edge in the standard single-path Six-Channel Transmission Network data are merged into a single fused directed edge. An edge source marker and edge occurrence frequency are added to the fused directed edge record. The edge source marker records whether the directed edge originates from the standard single-path Six-Channel Transmission Network data, the multi-branch Six-Channel Transmission Topology data, or both. The edge occurrence frequency records the number of times the directed edge appears in the multi-branch Six-Channel Transmission Topology data. For example, for a directed edge pointing from a solar meridian stage node to a Yangming meridian stage node, if the directed edge already exists in the standard single-path six-merchantment transmission network data, then only one fused directed edge pointing from the solar meridian stage node number to the Yangming meridian stage node number is retained in the graph fusion data. The record of the fused directed edge is then updated with markers for the standard path source and multi-branch source, as well as the frequency of occurrence of the multi-branch statistics. If a multi-branch directed edge does not exist in the standard single-path six-merchantment transmission network data, then the multi-branch directed edge is added to the edge set of the graph fusion data as a new fused directed edge, and information such as the starting node number, ending node number, and edge occurrence frequency is recorded.

[0109] By merging node alignment and directed edge mapping, a graph fusion data set containing a unified set of nodes and a unified set of directed edges is formed. In the node table of the graph fusion data, each node record includes a node number, the name of the syndrome combination, the sequence number of the disease stage, and a summary of typical symptom characteristics. In the directed edge table of the graph fusion data, each directed edge record includes a starting node number, an ending node number, an edge source marker, the edge frequency, and the edge weight to be calculated.

[0110] Based on graph fusion data, the transmission path weights between nodes in each fusion path are recalculated;

[0111] In the graph fusion data, all fusion transmission paths that meet the time order constraint are enumerated. A fusion transmission path is defined as a sequence of directed nodes starting from a starting disease stage node and sequentially connected to a terminating disease stage node via several directed edges. Each node sequence satisfies the constraint that the disease stage sequence number is monotonically non-decreasing to avoid time-retrogression paths. The starting node set in the six meridian transmission process can be selected from the graph fusion data as the path starting point. For example, the set of nodes with the smallest disease stage sequence number and whose meridian combination belongs to the early stage of exogenous disease can be selected as the starting node set. Then, the path is recursively expanded using a directed graph traversal method until the set of nodes with the largest disease stage sequence number or no successor nodes is reached as the terminating node set, thus enumerating all candidate fusion transmission paths.

[0112] For each standard single path already existing in the standard single-path six-way transmission network data, the corresponding fused transmission path is found in the graph fusion data by matching node number sequences. The original path weights in the standard single path are combined with the multi-branch information in the graph fusion data to calculate the new fused path transmission path weights. The calculation process for the new fused path transmission path weights includes two parts: one part is the basic path weight score from the standard single path, and the other part is the path support score from the multi-branch topology. The basic path weight score is taken from the path weights recorded in the standard single-path six-way transmission network data. The path support score is calculated based on the frequency of occurrence of each directed edge in the fused path in the multi-branch six-way transmission topology data. The edge occurrence frequency of each directed edge in the fused path can be normalized, and the edge occurrence frequency can be divided by the maximum occurrence frequency of the same type of meridian transformation edge in the multi-branch topology data to obtain the edge support coefficient between 0 and 1. The average of the edge support coefficients of all directed edges in the fused path is then calculated to obtain the multi-branch support score of the fused path. The higher the multi-branch support score, the more often the fusion path appears in clinical multi-branch transmission data.

[0113] The new fusion path transmission path weights can be calculated using a linear weighting method, combining the basic path weight score and the multi-branch support score according to a preset weight coefficient. Let the weight coefficient for the basic path weight score be α, and the weight coefficient for the multi-branch support score be β, with the constraint that α plus β equals 1. The range of the new fusion path transmission path weights is also limited to between 0 and 1.

[0114] Based on the transmission path weights, all transmission paths in the graph fusion data are recalibrated to output the six-line transmission topology network model data.

[0115] After obtaining the new fusion path transmission path weights for each fusion path, the transmission path weights of all fusion paths within the same case are normalized to facilitate probabilistic selection of different paths in teaching and clinical simulation.

[0116] The directed edges in the graph fusion data are relabeled with weights so that each directed edge has a clear weight in the final six-way transmission topology network model data. The weight relabeling can be calculated based on the joint contribution of the fusion path transmission path weight and the path length. For each fusion path, assuming the fusion path transmission path weight is W and the number of directed edges in the fusion path is L, the contribution of the fusion path to each directed edge can be defined as W divided by L. For each directed edge in the graph fusion data, all fusion paths containing directed edges are traversed, and the contribution values ​​of each fusion path containing a directed edge are summed to obtain the cumulative edge weight. The larger the cumulative edge weight, the higher the importance of the directed edge in different fusion paths, indicating a more significant role of the meridian transformation relationship in the overall six-way transmission topology. A global normalization is performed on the cumulative edge weights of all directed edges by dividing the cumulative edge weight of all directed edges by the maximum cumulative edge weight or the sum of the cumulative edge weights, so that the edge weights of all directed edges fall within the range of 0 to 1.

[0117] After completing node alignment, edge mapping and merging, recalculation of the weights of the fusion path transmission paths, and recalibration of the directed edge weights, the Six Channels Transmission Topology Network Model Data is generated. This data records all nodes and directed edges in the network, along with their corresponding weights. Node data includes node number, name of the meridian-differential syndrome combination, sequence number of the disease stage, and a summary of typical symptom characteristics, which can be used to generate visual markers for disease stage nodes in the teaching and clinical simulation interface. Directed edge data includes starting node number, ending node number, normalized edge weight, edge source marker, and typical symptom change characteristic parameters associated with the edge, such as recording the average change in symptom intensity and the average change in symptom duration during the edge's corresponding transformation process. Path data records the node sequence, fusion path transmission path weights, and path type marker for each fusion path. The path type marker distinguishes paths primarily originating from the standard single-path Six Channels Transmission Network from paths primarily originating from multi-branch Six Channels Transmission Topology Structures.

[0118] S6, based on the data from the Six Channels Transmission Topology Network Model and the patient's symptom combinations, determines whether the current disease stage meets the triggering conditions for cross-channel bifurcation simulation, and generates corresponding teaching feedback data and comparative learning data, including:

[0119] Based on the data of the Six Channels Transmission and Transformation Topology Network Model and the patient symptom combinations, channel selection conditions and bifurcation trigger threshold parameters input in the teaching scenario, cross-channel bifurcation trigger condition judgment is performed on the disease process nodes.

[0120] The patient symptom combinations input into the teaching scenario are entered by teachers or students in the TCM teaching scenario through the TCM teaching and clinical simulation interface. The patient symptom combinations include the set of symptom types corresponding to the patient's current disease stage, the symptom intensity score for each symptom type, and the symptom duration. The symptom type set is obtained by selecting standardized symptom names from a standard clinical symptom terminology database. The symptom intensity score is recorded using a scoring scale consistent with the time-series characteristic data of the Six Channels disease progression nodes, for example, defined as a numerical score range of 1 to 10, where a score of 1 indicates the lowest symptom intensity and a score of 10 indicates the highest symptom intensity. The symptom duration is recorded in hours as the cumulative duration since the onset of each symptom. For example, if a patient currently has fever with a fever intensity score of 7 and a fever duration of 36 hours, and also has headache with a headache intensity score of 5 and a headache duration of 12 hours, then the patient symptom combination input into the teaching scenario would record the fever symptom as "fever, intensity 7, duration 36 hours" and the headache symptom as "headache, intensity 5, duration 12 hours."

[0121] The meridian selection criteria are pre-defined rules for screening meridians in TCM teaching activities. These criteria limit the range of meridian-related diseases and syndromes that can participate in the cross-meridian bifurcation trigger judgment. The selection criteria include at least a candidate meridian set and a meridian priority set. The candidate meridian set can be set according to the current teaching topic. For example, when teaching the topic of the transmission of Taiyang and Yangming meridians, the candidate meridian set can only include Taiyang and Yangming meridians; when teaching the topic of the three Yang diseases, the candidate meridian set can include Taiyang, Yangming, and Shaoyang meridians. The meridian priority set assigns integer priority levels to several meridians. A higher integer priority level indicates that the transmission path of that meridian is more likely to be shown in the teaching process. The meridian priority set facilitates sorting when multiple candidate cross-meridian bifurcation paths simultaneously meet the trigger conditions.

[0122] The bifurcation trigger threshold parameter is a key control parameter in the judgment of cross-path bifurcation trigger conditions. The bifurcation trigger threshold parameter includes at least a symptom matching degree threshold, a path weight threshold, and a path difference degree threshold. The symptom matching degree threshold is used to limit whether the candidate successor node has sufficient similarity in symptom presentation to the patient symptom combination input in the teaching scenario. The symptom matching degree can be calculated using weighted cosine similarity or weighted Euclidean distance inverse transformation. The patient symptom combination input in the teaching scenario can be converted into a symptom feature vector, and the typical symptom feature summary of the candidate successor node in the six-path transmission topology network model data can be converted into a node symptom feature vector. The symptom matching degree is obtained by calculating the cosine similarity, with a value between 0 and 1. The symptom matching degree threshold can be determined statistically through a large number of teaching cases or clinical review samples. For example, scenarios with symptom matching recognized by teachers can be summarized from historical cases, the symptom matching degree distribution under symptom matching scenarios can be calculated, and the lower quartile or median of the distribution can be taken as the symptom matching degree threshold. For example, the symptom matching degree threshold can be set to 0.6 or 0.7. The path weight threshold is used to limit the importance of candidate cross-paths in the overall six-path bifurcation topology network model data. The path weight threshold can be set using the statistical distribution results of the path weights in the fused path data table. For example, the average value of all path weights can be calculated, and the threshold can be set near this average. The path difference threshold is used to determine the degree of difference between currently used six-path bifurcation paths and potential cross-path bifurcation paths. The path difference can be calculated by comparing the number of differences in meridian combinations, path length differences, and node stage number differences between the two path node sequences. A higher path difference indicates a more significant difference in the topological structure between the two paths.

[0123] When determining the trigger condition for cross-meridian bifurcation, the current disease stage node is first located in the Six Meridian Transmission Topology Network Model data. The current disease stage node can be determined in the following ways: at the start of the teaching simulation, the initial disease stage node is fixed to the Taiyang meridian or another initial meridian node. As the patient's symptom combinations input into the teaching scenario and the simulation time progresses, the current disease stage node is gradually moved forward using directed edges in the Six Meridian Transmission Topology Network Model data; in the teaching scenario, the teacher directly specifies the current disease stage node number. After determining the current disease stage node, all directed edges with an initial node number equal to the current disease stage node number are retrieved from the directed edge data table of the Six Meridian Transmission Topology Network Model data. The terminating nodes of these directed edges are considered as a set of candidate successor nodes. Furthermore, all fusion path records containing the current disease stage node and whose successor nodes belong to the set of candidate successor nodes are retrieved from the fusion path data table. These fusion paths are considered as a set of candidate cross-meridian bifurcation paths.

[0124] For each candidate successor node in the candidate successor node set, the symptom matching degree between the patient symptom combination input from the teaching scenario and the typical symptom feature summary of the candidate successor node is calculated. First, a symptom feature vector space with unified symptom dimensions is constructed. In this space, a fixed dimension is assigned to each standard symptom name. The symptom intensity score and symptom duration appearing in the patient symptom combination input from the teaching scenario are combined using a linear weighting method to form the numerical components of the symptom dimension. The numerical components of the dimension for symptoms not appearing are set to 0. For candidate successor nodes, the same dimensional system is used. The mean symptom intensity and mean symptom duration in the typical symptom feature summary of the candidate successor node are linearly weighted and combined to generate the node symptom feature vector. The similarity between symptom feature vectors can be calculated using the cosine similarity formula; that is, the calculated similarity is the symptom matching degree of the candidate successor node.

[0125] Simultaneously, the path weights for each candidate cross-branching path are extracted from the fusion path data table, and the path difference is calculated by comparing the path node sequence with the node sequence of the existing six-branching paths currently being used in the simulation. The path difference can be described as follows: First, count the number of nodes with different meridian combination names in the two path node sequences, divide the number of different nodes by the total number of nodes in the longer path to obtain the meridian combination difference ratio; count the length difference between the two path node sequences, divide the length difference by the total number of nodes in the longer path to obtain the length difference ratio; then, linearly combine the meridian combination difference ratio and the length difference ratio with certain weights. For example, the weight of the meridian combination difference ratio can be set to 0.7, and the weight of the length difference ratio can be set to 0.3. The path difference is equal to the meridian combination difference ratio multiplied by 0.7 plus the length difference ratio multiplied by 0.3.

[0126] After obtaining the symptom matching degree of candidate successor nodes, the path propagation path weight of candidate cross-path bifurcation paths, and the path difference degree between candidate cross-path bifurcation paths and existing six-path propagation paths, a cross-path bifurcation trigger evaluation function is constructed for each candidate cross-path bifurcation path. The cross-path bifurcation trigger evaluation function can be defined as a weighted sum of three indicators. The value of the cross-path bifurcation trigger evaluation function equals the symptom matching degree multiplied by the symptom matching degree weight coefficient, plus the path propagation path weight multiplied by the path weight coefficient, plus the path difference degree multiplied by the path difference degree weight coefficient. The sum of the symptom matching degree weight coefficient, the path weight coefficient, and the path difference degree weight coefficient equals 1.

[0127] The rules for determining the trigger condition of cross-branching can be set in the form of multiple constraints. The first constraint is a symptom matching degree threshold constraint. When the symptom matching degree of a candidate successor node is greater than or equal to the symptom matching degree threshold, the candidate successor node proceeds to the next step of judgment. The second constraint is a path weight threshold constraint. When the path weight of a candidate cross-branching path is greater than or equal to the path weight threshold, the candidate cross-branching path proceeds to the next step of judgment. The third constraint is a path difference threshold constraint. When the path difference between a candidate cross-branching path and an existing six-branching path is greater than or equal to the path difference threshold, the candidate cross-branching path is considered to have bifurcation significance in the topological structure. For candidate cross-branching paths that simultaneously satisfy all three constraints, the cross-branching trigger evaluation function values ​​can be compared. When the difference between the cross-branching trigger evaluation function values ​​of at least two or more candidate cross-branching paths is lower than the preset upper limit threshold for the evaluation function difference, the current disease node is determined to meet the cross-branching simulation trigger condition. The upper limit threshold for the evaluation function difference can be set through teaching experiments.

[0128] When a disease progression node meets the bifurcation triggering condition, update the disease evolution path in the TCM teaching and clinical simulation interface and generate corresponding teaching feedback data.

[0129] The update process involves displaying multiple future cross-meridian bifurcation paths of the current disease stage in the TCM teaching and clinical simulation interface, distinguishing each path with different colors, line types, or node markers. Each cross-meridian bifurcation path is labeled with its path transmission weight, symptom matching degree, and path difference degree. The interface also displays the key meridian transformation nodes and representative symptom combinations corresponding to each cross-meridian bifurcation path, allowing students to visually observe the differences in meridian transmission structure and symptom changes among different branch paths. Corresponding teaching feedback data includes the current disease stage node number, the triggering bifurcation time, all candidate cross-meridian bifurcation path numbers, the symptom matching degree of each candidate cross-meridian bifurcation path, the path transmission weight, the path difference degree, the cross-meridian bifurcation trigger evaluation function value, and the path number ultimately selected by the teacher or student in the interactive interface. This teaching feedback data can be used in teaching evaluations to analyze students' understanding of the multi-branch topology of the six meridian transmission.

[0130] When the disease process node does not meet the bifurcation triggering condition, the existing six meridian transmission path is maintained and comparative learning data is generated.

[0131] When the current disease progression node does not meet the triggering conditions for cross-meridian bifurcation simulation, the TCM teaching and clinical simulation interface maintains the existing display effect of the six meridian transmission paths, does not generate new branch paths in the interface, and continues to deduce the disease evolution process along the subsequent nodes of the existing six meridian transmission paths. At this time, the learning data records the set of candidate cross-meridian bifurcation paths corresponding to the current disease progression node, the symptom matching degree of each candidate cross-meridian bifurcation path, the path transmission path weight and path difference degree, and the reasons for not meeting the bifurcation triggering conditions, such as the symptom matching degree being lower than the symptom matching degree threshold, the path transmission path weight being lower than the path weight threshold, or the path difference degree being lower than the path difference threshold.

[0132] Example 2

[0133] The difference between Embodiment 2 and Embodiment 1 is that this embodiment introduces a TCM teaching and clinical simulation system based on the theory of the six channels of transmission.

[0134] Figure 2 A schematic diagram of a TCM teaching and clinical simulation system based on the Six Channels Transmission Theory is provided. The TCM teaching and clinical simulation system based on the Six Channels Transmission Theory includes:

[0135] Data processing module: Collects medical record data and symptom time series data, performs preprocessing, and outputs clinical standard case data of the Six Channels disease process;

[0136] Temporal Feature Module: Based on the clinical standard case data of the Six Channels Disease Course, reconstruct the symptom evolution chain and corresponding Six Channels Differentiation Labels for each case, and output the temporal feature data of the Six Channels Disease Course nodes;

[0137] Single network construction module: Based on the temporal characteristic data of the six meridian disease process nodes, construct a single-path six meridian transmission candidate network and output standard single-path six meridian transmission network data;

[0138] Topology mining module: Based on the temporal characteristic data of the six meridian disease process nodes, it identifies cross-meridian concurrent disease patterns and multi-meridian mixed patterns, constructs candidate topology networks of six meridian transmission, and outputs multi-branch six meridian transmission topology structure data.

[0139] Fusion and calibration module: Performs graph fusion and path weight recalibration on standard single-path six-channel transmission network data and multi-branch six-channel transmission topology data to generate six-channel transmission topology network model data;

[0140] Bifurcation Feedback Module: Based on the data of the Six Meridians Transmission Topology Network Model and the combination of patient symptoms, determine whether the current disease stage meets the triggering conditions for cross-meridian bifurcation simulation, and generate corresponding teaching feedback data and comparative learning data.

[0141] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0142] Those skilled in the art will recognize that the modules 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.

[0143] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0144] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules 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 apparatuses or modules may be electrical, mechanical, or other forms.

[0145] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0146] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0147] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0148] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0149] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for teaching and clinical simulation of Traditional Chinese Medicine based on the theory of the Six Channels Transmission, characterized in that, Includes the following steps: S1: Collect disease course record data and symptom time series data, perform preprocessing, and output clinical standard case data of the Six Channels Disease Course; S2, based on the clinical standard case data of the six meridian disease course, reconstruct the symptom evolution chain and the corresponding six meridian differentiation labels of each case, and output the temporal feature data of the six meridian disease course nodes; S3, based on the temporal characteristic data of the disease process nodes of the six meridians, construct a candidate network for the transmission of the six meridians through a single path, and output standard single-path transmission network data of the six meridians through a single path. S4. Based on the time-series characteristic data of the disease process nodes of the six meridians, identify the cross-meridian concurrent disease pattern and the multi-meridian mixed pattern, construct the candidate topology network of the six meridians, and output the multi-branch six meridians transmission topology data. S5 involves graph fusion and path weight recalibration of standard single-path six-channel transmission network data and multi-branch six-channel transmission topology data to generate six-channel transmission topology network model data, specifically: Using the pathological nodes in the standard single-path six-channel transmission network data as the reference nodes, the nodes and edges in the multi-branch six-channel transmission topology data are aligned and mapped and merged to form unified graph fusion data. Based on graph fusion data, the transmission path weights between nodes in each fusion path are recalculated; Based on the transmission path weights, all transmission paths in the graph fusion data are recalibrated to output the six-line transmission topology network model data. S6, based on the data from the Six Channels Transmission Topology Network Model and the patient's symptom combinations, determines whether the current disease stage meets the triggering conditions for cross-channel bifurcation simulation, and generates corresponding teaching feedback data and comparative learning data, specifically: Based on the data of the Six Channels Transmission and Transformation Topology Network Model and the patient symptom combinations, channel selection conditions, and bifurcation trigger threshold parameters input in the teaching scenario, cross-channel bifurcation trigger condition judgment is performed on the disease process nodes; the bifurcation trigger threshold parameters include symptom matching degree threshold, path weight threshold, and path difference threshold. When a disease progression node meets the bifurcation triggering condition, update the disease evolution path in the TCM teaching and clinical simulation interface and generate corresponding teaching feedback data. When the disease process node does not meet the bifurcation triggering condition, the existing six meridian transmission path is maintained and comparative learning data is generated.

2. The method for teaching and clinical simulation of Traditional Chinese Medicine based on the theory of the Six Channels Transmission as described in claim 1, characterized in that, S1, specifically: Collect disease progress records from the TCM electronic medical record system and symptom time series data from the teaching case database; Based on the TCM diagnosis names, syndrome descriptions, tongue and pulse information and Western medicine diagnosis codes in the medical record data, corresponding six meridian labels are generated using preset meridian mapping rules; The data format of the disease course records and the symptom time series data with the six meridian differentiation labels were standardized and missing data values ​​were filled in, and the clinical standard case data of the six meridian disease course were output.

3. The method for teaching and clinical simulation of traditional Chinese medicine based on the theory of the six channels according to claim 2, characterized in that, S2, specifically: Based on the clinical standard case data of the six meridian disease course, the symptom information recorded in each case is extracted in chronological order and arranged to generate a symptom evolution chain; Associate the symptoms at each time point in the symptom evolution chain with the corresponding six meridian differentiation labels; Based on the associated symptom evolution chain, characteristic parameters of symptom duration, symptom frequency, and symptom intensity changes are calculated for each disease stage. Summarize the symptom evolution chain, the correlation between the six meridians and their corresponding labels, and the characteristic parameters of the disease course nodes, and output the time-series characteristic data of the six meridian disease course nodes.

4. The method for teaching and clinical simulation of traditional Chinese medicine based on the theory of the six channels according to claim 3, characterized in that, S3, specifically: The pre-set rule library for the transmission of the six meridians is invoked to calculate the degree of matching between the characteristic parameters of symptom duration, symptom frequency and symptom intensity changes in the time sequence characteristic data of the six meridian disease process nodes and each classic forward transmission path in the rule library. The path weight of each classic forward path is determined based on the degree of matching. Based on the path weights of each classic forward transmission path, path selection is performed to construct a single-path Six Classic Transmission Candidate Network with classic forward transmission paths as the main component, and output standard single-path Six Classic Transmission Network data.

5. The method for teaching and clinical simulation of traditional Chinese medicine based on the theory of the six channels according to claim 4, characterized in that, S4, specifically: Identify cross-meridian concurrent disease patterns and multi-meridian mixed disease patterns based on the temporal characteristic data of the six meridian disease process nodes; The cross-meridian concurrent disease pattern and the multi-meridian mixed pattern are mapped to graph structures containing nodes and directed edges, respectively. The nodes represent the combination of meridian diseases corresponding to the time point of the disease course, and the directed edges represent the transmission direction between meridian diseases. The topology merging and directed cycle detection are performed on the graph structure obtained by mapping to construct a candidate topology network of the six meridians and output multi-branch six meridians topology structure data.

6. The method for teaching and clinical simulation of traditional Chinese medicine based on the theory of the six channels according to claim 5, characterized in that, The selection criteria for meridians include a set of candidate meridians and a set of meridian priorities.

7. A Traditional Chinese Medicine (TCM) teaching and clinical simulation system based on the Six Channels Transmission Theory, used to implement the TCM teaching and clinical simulation method based on the Six Channels Transmission Theory as described in any one of claims 1-6, characterized in that, include: Data processing module: Collects medical record data and symptom time series data, performs preprocessing, and outputs clinical standard case data of the Six Channels disease process; Temporal Feature Module: Based on the clinical standard case data of the Six Channels Disease Course, reconstruct the symptom evolution chain and corresponding Six Channels Differentiation Labels for each case, and output the temporal feature data of the Six Channels Disease Course nodes; Single network construction module: Based on the temporal characteristic data of the six meridian disease process nodes, construct a single-path six meridian transmission candidate network and output standard single-path six meridian transmission network data; Topology mining module: Based on the temporal characteristic data of the six meridian disease process nodes, it identifies cross-meridian concurrent disease patterns and multi-meridian mixed patterns, constructs candidate topology networks of six meridian transmission, and outputs multi-branch six meridian transmission topology structure data. Fusion and calibration module: Performs graph fusion and path weight recalibration on standard single-path six-channel transmission network data and multi-branch six-channel transmission topology data to generate six-channel transmission topology network model data; Bifurcation Feedback Module: Based on the data of the Six Meridians Transmission Topology Network Model and the combination of patient symptoms, determine whether the current disease stage meets the triggering conditions for cross-meridian bifurcation simulation, and generate corresponding teaching feedback data and comparative learning data.

Images