A Traditional Chinese Medicine pre-consultation collection and management system

Abstract

The present invention is applicable to the field of medical technology and provides a traditional Chinese medicine pre-consultation collection and management system, which includes a user information collection module, a traditional Chinese medicine constitution identification module, a symptom correlation analysis module, a personalized consultation path generation module, a data integration and medical record generation module, and a feedback optimization module. By collecting the user's basic information and chief complaints, a constitution identification model is constructed to accurately identify the constitution type; based on the knowledge graph and multi-dimensional weight calculation, a high-correlation symptom sequence is generated, and an interactive consultation tree is constructed through the dynamic branching algorithm to realize the dynamic adjustment of the personalized consultation path; the real-time data and historical diagnosis and treatment records are integrated to generate a structured pre-diagnosis medical record, and the weight of the knowledge graph is optimized through the feedback of clinical diagnosis data to continuously improve the diagnosis accuracy. Through data fusion and intelligent algorithms, the present invention significantly improves the objectivity and accuracy of traditional Chinese medicine diagnosis, reduces missed diagnoses and misdiagnoses, and provides scientific and personalized auxiliary decision-making support for doctors.

Description

Technical Field

[0001] The present invention belongs to the field of medical technology, and particularly relates to a traditional Chinese medicine pre-consultation collection and management system. Background Art

[0002] With the rapid development of information technology and artificial intelligence, the application of intelligent medical technology in traditional Chinese medicine diagnosis and treatment has gradually become a research hotspot. Traditional Chinese medicine diagnosis relies on doctors' experience and subjective judgment of patients' symptoms. However, the subjectivity and experience dependence in the diagnosis process make the diagnosis results vulnerable to individual differences, situational factors, and doctors' experience.

[0003] However, in the existing technology, most intelligent consultation systems still face problems such as inaccurate symptom recognition, inaccurate identification of constitution types, and insufficient analysis of the correlation between symptoms and constitution. In addition, existing systems often lack a dynamic optimization mechanism and are difficult to make feedback adjustments based on the differences between clinically diagnosed data and pre-diagnosed data, resulting in limited diagnostic accuracy of the system and inability to effectively meet the diverse needs of different individuals. Summary of the Invention

[0004] The purpose of the present invention is to provide a traditional Chinese medicine pre-consultation collection and management system, aiming to solve the technical problems existing in the prior art as determined in the background art.

[0005] A traditional Chinese medicine pre-consultation collection and management system includes a user information collection module, a traditional Chinese medicine constitution identification module, a symptom correlation analysis module, a personalized consultation path generation module, a data integration and medical record generation module, and a feedback optimization module, wherein;

[0006] The user information collection module is used to obtain user basic information and chief complaint symptoms, and generate an initial data set including symptom feature vectors;

[0007] The traditional Chinese medicine constitution identification module receives the symptom feature vectors in the initial data set, and combines tongue image and pulse condition parameters to output constitution types and associated symptom groups;

[0008] The symptom correlation analysis module calls the corresponding knowledge graph according to the constitution type, performs multi-dimensional weight calculation on the associated symptom groups, and generates a high-correlation symptom sequence;

[0009] The personalized consultation path generation module generates an interactive consultation tree including mandatory symptom verification items and optional symptom extension items based on the high-correlation symptom sequence through a dynamic branching algorithm;

[0010] The data integration and medical record generation module integrates the interactive data of the consultation tree and historical diagnosis and treatment records, and generates a pre-diagnosis medical record including constitution feature markers and symptom evolution paths;

[0011] The feedback optimization module is used to obtain the differential features between the clinically diagnosed data and the pre-diagnosis medical records, and adjust the knowledge graph weight coefficients through the parameter self-correction unit.

[0012] The beneficial effects of the present invention are as follows:

[0013] Through the collaborative work of the user information collection module, the traditional Chinese medicine constitution identification module, and the symptom association analysis module, the present invention can accurately identify and match the user's constitution type and related symptoms. Especially in the process of constitution identification, the basic information, chief complaint symptoms, tongue image, and pulse condition parameters of the user are combined, and a multi-fusion constitution identification model is constructed to ensure the efficient matching of constitution types (such as yin deficiency, yang deficiency, and qi deficiency) and symptom groups. Through the highly correlated symptom sequence and personalized interrogation path generated by the system, the user's diagnosis can be made more accurate, reducing the probability of misdiagnosis or missed diagnosis.

[0014] The present invention realizes the dynamic optimization function based on the differences between the clinically diagnosed data and the pre-diagnosis medical records through the feedback optimization module. By adjusting the knowledge graph weight coefficients, the optimization module can real-time feedback the correlation between the user's symptom manifestations and constitution types, and self-correct according to the actual diagnosis and treatment results. This mechanism can effectively improve the diagnostic accuracy of the system, and ensure that with the accumulation of more user data, the constitution identification and symptom association analysis functions of the system are continuously optimized, so as to provide more accurate support for doctors and optimize the diagnosis and treatment process.

[0015] Through the data integration and medical record generation module, the system can effectively integrate the user's interrogation tree interaction data and historical diagnosis and treatment records, and generate a pre-diagnosis medical record including constitution feature markers and symptom evolution paths. This medical record can not only reflect the user's current symptoms and constitution features, but also provide a complete symptom evolution process combined with historical records, providing detailed diagnostic basis for doctors. The generation of this medical record not only improves the diagnosis efficiency, but also provides complete reference data for subsequent treatment and follow-up consultations, further improving the quality and accuracy of medical services. Description of the Drawings

[0016] Figure 1 It is a schematic flow chart of a traditional Chinese medicine pre-interrogation collection and management system provided by an embodiment of the present invention;

[0017] Figure 2 It is a schematic flow chart of the traditional Chinese medicine constitution identification module provided by an embodiment of the present invention. Detailed Embodiments

[0018] In order to make the purpose, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0019] As shown Figure 1 - Figure 2 in the figure, a traditional Chinese medicine pre-consultation collection and management system includes a user information collection module, a traditional Chinese medicine constitution identification module, a symptom correlation analysis module, a personalized consultation path generation module, a data integration and medical record generation module, and a feedback optimization module. The operation process of the traditional Chinese medicine pre-consultation collection and management system is as follows:

[0020] User information collection: The user inputs basic information (age, gender, living habits, etc.) and chief complaint symptoms (such as pain location, attack frequency, etc.) through an interactive interface (such as a mobile terminal, a web terminal, or a hospital terminal device). The system converts the information into a numerical symptom feature vector, generates an initial data set, and stores it in the database.

[0021] Traditional Chinese medicine constitution identification: The system calls the symptom feature vector in the initial data set, combines tongue image parameters (acquiring tongue texture, tongue coating, and tongue shape through a tongue image acquisition device) and pulse parameters (acquiring pulse rate, strength, and fluctuation pattern through a pulse diagnosis device), and uses the support vector machine algorithm (SVM) to construct a constitution identification model, and outputs the user's constitution type (such as yin deficiency, yang deficiency, qi deficiency) and associated symptom groups.

[0022] Symptom correlation analysis: According to the constitution type, call the corresponding traditional Chinese medicine symptom knowledge graph, perform multi-dimensional weight calculation on the associated symptoms (including the correlation degree between symptoms and constitution, symptom similarity, and joint relationship weight), and generate a high-correlation symptom sequence sorted by weight (the first 20% are required verification items, and the remaining first 20% are optional expansion items).

[0023] Personalized consultation path generation: Construct an interactive consultation tree through a dynamic branching algorithm, with the required symptom verification items as the core nodes and the optional symptom expansion items as the sub-branches. The system dynamically adjusts the consultation path according to the user's real-time feedback (such as symptom changes, doctor input), and generates a multi-level and expandable personalized process.

[0024] Data integration and medical record generation: Integrate the real-time consultation data and the user's historical diagnosis and treatment records (such as previous constitution type, symptom evolution history), generate a structured pre-diagnosis medical record containing constitution feature markers, symptom evolution paths, and treatment suggestions, and output it to the doctor's terminal.

[0025] Feedback optimization: Compare the differential features between the clinically diagnosed data and the pre-diagnosis medical record (such as symptom correlation deviation, constitution misjudgment), and adjust the weight coefficients of the knowledge graph through a parameter self-correction unit to optimize the subsequent diagnosis logic.

[0026] Specifically:

[0027] User Information Collection Module

[0028] Obtain user basic information: Through the user input device or interaction interface, obtain the user's basic personal information, including age, gender, height, weight, living habits (such as diet, sleep, etc.), family medical history, etc.;

[0029] Obtain the chief complaint symptoms: Through questionnaires, interviews or form input methods, collect the user's chief complaint symptoms, and the symptoms include detailed information such as the body part of discomfort, pain level, attack duration, symptom duration, symptom occurrence frequency, etc.;

[0030] Convert to symptom feature vectors: Through the data processing unit, convert the basic information and chief complaint symptom information input by the user into symptom feature vectors. The symptom feature vectors include the user's physical constitution information (such as age, gender, etc.), chief complaint symptom information (such as symptom type, degree, time sequence, etc.) and symptom-related background information (such as the time period when the symptom occurs, inducing factors, etc.);

[0031] Generate an initial data set: Integrate the generated symptom feature vectors with the user's basic information to construct an initial data set. This initial data set includes the symptom feature vectors of each user and their basic information, which serves as the input data for subsequent processing;

[0032] Upload and store the data: Upload the generated symptom feature vectors and the user's basic information to the system database for storage;

[0033] The user information collection module collects the user's basic information and chief complaint symptoms through systematic steps and converts them into symptom feature vectors, ensuring the accuracy and integrity of the information, and providing a solid data foundation for subsequent physical constitution identification, symptom analysis and generation of personalized interrogation paths.

[0034] Data input methods: Support multiple input channels, including electronic forms, voice input (such as converting interview recordings to text), and sensor devices (such as wearable devices for collecting sleep data).

[0035] Symptom feature vector generation: Convert the chief complaint symptom text (such as "dry mouth and tongue") into a numerical vector through natural language processing (NLP) technology, for example:

[0036] Physical constitution information vector: Age (numerical type), gender (0 / 1 coding), living habits (diet score, sleep duration).

[0037] Symptom vector: Pain level (1-10 points), attack duration (hours), associated background (such as "aggravated at night" coded as a feature value).

[0038] Traditional Chinese Medicine Constitution Identification Module

[0039] Receive symptom feature vectors: Obtain the initial data set from the user information collection module, which includes the user's symptom feature vectors;

[0040] Obtain tongue image parameters: Obtain tongue image parameters through a tongue image acquisition device or manual inspection. The tongue image parameters include tongue color (such as red, light, tender, etc.), tongue coating (such as white, yellow, thick or thin, etc.), and tongue shape (such as tongue size, cracks on the tongue surface, etc.);

[0041] Obtain pulse image parameters: Obtain pulse image parameters through a pulse diagnosis device or manual pulse diagnosis. The pulse image parameters include the speed, strength, and fluctuation pattern of the pulse;

[0042] Establish a constitution identification model: Based on the symptom feature vector, tongue image parameters, and pulse image parameters, use the support vector machine algorithm to establish a constitution identification model;

[0043] Constitution type identification: Analyze the user's symptom feature vector, tongue image parameters, and pulse image parameters through the constitution identification model to identify the user's constitution type, and output the corresponding associated symptom group according to the constitution type. The associated symptom group includes symptoms related to this constitution type, serving as the basis for subsequent symptom association analysis;

[0044] Output the constitution type and the associated symptom group: According to the constitution identification result, output the user's constitution type and its associated symptom group. The constitution types include yin deficiency, yang deficiency, and qi deficiency. The constitution identification model determines the corresponding symptom group according to different constitution types to ensure the personalization and pertinence of the symptom group;

[0045] The traditional Chinese medicine constitution identification module accurately identifies the user's constitution type by comprehensively analyzing the user's symptom feature vector, tongue image, and pulse image parameters, and outputs the symptom group related to this constitution type. This module provides a scientific basis for subsequent symptom association analysis and the generation of personalized interrogation paths, ensuring the accuracy and personalization of the diagnosis.

[0046] Quantification of tongue image and pulse image parameters

[0047] Tongue color: Red (coded 1), light (coded 2), tender (coded 3);

[0048] Pulse: Speed (heart rate value), strength (pressure sensor reading), fluctuation pattern (waveform spectrum analysis result).

[0049] Support vector machine model training:

[0050] Input: Multidimensional feature vector (symptoms, tongue image, pulse image parameters);

[0051] Output: Constitution type label (yin deficiency, yang deficiency, qi deficiency);

[0052] Kernel function selection: Radial basis function (RBF) kernel, penalty parameter C = 1.0, tolerance ε = 0.1.

[0053] Symptom Correlation Analysis Module

[0054] Received physical constitution type and symptom groups: Obtain the user's physical constitution type (yin deficiency, yang deficiency, or qi deficiency) and its corresponding associated symptom groups through the traditional Chinese medicine physical constitution identification module. Each physical constitution type has its corresponding symptom group, and the symptom group includes the symptoms related to this physical constitution type and their attributes;

[0055] Invoke the knowledge graph: According to the user's physical constitution type, invoke the corresponding traditional Chinese medicine symptom knowledge graph, which includes various traditional Chinese medicine symptoms and their relationships with physical constitution types and other symptoms;

[0056] Each node in the knowledge graph represents a symptom, and each edge represents the association relationship between symptoms, including information such as intensity and similarity;

[0057] Multi-dimensional weight calculation: Based on the symptom group and the knowledge graph, perform multi-dimensional weight calculation. For each symptom in the symptom group, assign weights to each symptom according to the following factors:

[0058] Degree of association between symptoms and physical constitution type: Calculate the basic weight of each symptom according to the degree of association between the physical constitution type and the symptom, and this weight is set through historical data, medical literature, or expert knowledge;

[0059] Similarity between symptoms: Calculate the similarity between symptoms, and use cosine similarity to measure the similarity in the manifestation form of symptoms;

[0060] Joint relationship between symptoms and other symptoms: According to the connection relationship of symptoms in the knowledge graph, calculate the joint probability or correlation between symptoms and adjust the weights. A strong association between symptoms will increase their weights in the final sequence;

[0061] Feedback of user input information: Adjust the weights according to the intensity and change of the user's input symptoms, making the calculation of symptom association more personalized;

[0062] Generate a high-degree-of-association symptom sequence: According to the calculated weights, generate a high-degree-of-association symptom sequence by sorting the weights. The high-degree-of-association symptom sequence includes the symptoms related to the user's physical constitution type, arranged from high to low according to the degree of association. According to the sorting result, select the top 20% of the symptoms with the highest degree of association as the high-degree-of-association symptom sequence to ensure the personalization and pertinence of the symptoms. This symptom sequence can be used for the subsequent generation of personalized interrogation paths.

[0063] Output the symptom sequence: Provide the generated high-degree-of-association symptom sequence to the personalized interrogation path generation module for constructing a dynamic interactive interrogation tree. This sequence ensures that the symptom examination during the interrogation process can cover the symptoms related to the user's physical constitution type and conduct in-depth investigations.

[0064] Knowledge graph call: Match the pre-set traditional Chinese medicine symptom knowledge graph according to the constitution type. For example:

[0065] Symptoms associated with yin deficiency constitution: Dry mouth, tidal fever, night sweats;

[0066] Edge weights of the knowledge graph: The association strength between symptoms (0 - 1), joint probability (e.g., the joint probability of "dry mouth" and "red tongue" is 0.85).

[0067] Weight calculation rules:

[0068] Association degree weight: Set the base value according to medical literature (e.g., the association degree between "dry mouth" and "yin deficiency" is 0.9);

[0069] User feedback weight: If the user feedback indicates that the degree of "dry mouth" has increased, the weight is increased by 10%.

[0070] Personalized Inquiry Path Generation Module

[0071] Receive high - correlation symptom sequence: The personalized interview path generation module receives the high - correlation symptom sequence generated by the symptom association analysis module. This sequence includes symptoms that are related to the user's constitution type and have a relatively high degree of association. The high - correlation symptom sequence is arranged from high to low according to the association degree, ensuring the priority and importance of the symptoms.

[0072] Determine the required symptom verification items: According to the high - correlation symptom sequence, the personalized interview path generation module selects the symptom with the highest degree of association in the sequence as the required symptom verification item. The required symptom verification items refer to those symptoms that are crucial for judging the user's constitution type and must be verified during the interview process. The selected required symptom verification items have the following characteristics:

[0073] Symptoms with the highest degree of association;

[0074] High certainty, which can help doctors make a clear diagnosis;

[0075] Highly related to the constitution type and can accurately reflect the user's health status.

[0076] Define optional symptom extension items: According to the remaining symptoms in the high - correlation symptom sequence, the personalized interview path generation module selects the top 20% of the remaining symptoms as optional symptom extension items. The optional symptom extension items are used to further refine and supplement the user's symptom information, helping doctors evaluate the user's health status more comprehensively. The selected optional symptom extension items have the following characteristics:

[0077] Lower degree of association but still have a certain association with the constitution type;

[0078] Have a certain degree of personalization and can be flexibly selected for verification according to the specific situation of the user;

[0079] It can help doctors identify some potential and undetected health problems.

[0080] Construct an interactive interrogation tree: Based on the mandatory symptom verification items and optional symptom extension items, the personalized interrogation path generation module generates an interactive interrogation tree through a dynamic branching algorithm;

[0081] The structure of the interrogation tree includes multiple nodes, each node representing a symptom or a group of symptoms, and the branches representing the relationships between symptoms and the interrogation process. The specific steps are as follows:

[0082] Starting from the root node, the root node represents the user's constitution type and preliminary symptom analysis;

[0083] Each branch node represents a symptom or a group of symptoms, and the branches connecting different nodes represent the dependency relationships between symptoms;

[0084] The mandatory symptom verification items appear as core nodes at the key nodes of the interrogation tree to ensure that these symptoms are verified first during the interrogation process;

[0085] The optional symptom extension items appear as branches or child nodes. After verifying the mandatory symptoms, if conditions permit, continue to expand downward to further improve the symptom information;

[0086] The connection relationship between each node is based on the correlation degree between symptoms and the actual needs of doctors, and the generation rules of branches are dynamically adjusted.

[0087] Dynamically adjust the interrogation path: The personalized interrogation path generation module dynamically adjusts the structure and branches of the interrogation tree according to the user's real-time feedback and the occurrence of symptoms. The specific adjustment bases include:

[0088] Symptom changes: If a certain symptom shows new changes during the interrogation process, the interrogation tree will automatically adjust to add new verification items or extension items;

[0089] User feedback: According to the user's feedback on symptoms (such as symptom intensity, frequency, etc.), dynamically change the order of the interrogation path or add new symptom items;

[0090] Doctor input: According to the doctor's judgment, further refine the interrogation path and adjust the priority between mandatory and optional items.

[0091] Output a personalized interrogation path: According to the generated interactive interrogation tree, the personalized interrogation path generation module outputs a personalized interrogation path, which provides a systematic and personalized interrogation process for doctors, ensuring that the interrogation process is both efficient and targeted, helping doctors quickly lock in the user's core symptoms and make an accurate preliminary diagnosis.

[0092] Based on the mandatory symptom verification items and optional symptom extension items, the personalized consultation path generation module generates an interactive consultation tree through a dynamic branching algorithm, including:

[0093] Define the structure of the interactive consultation tree: The structure of the interactive consultation tree is defined as a hierarchical tree structure, including multiple nodes and branches. The root node of the tree represents the starting point of the consultation (i.e., the user's constitution type and preliminary symptom analysis), the nodes represent symptoms, symptom groups or further verification items of symptoms, and the branches represent the relationships, priorities and dependency conditions between symptoms;

[0094] The basic structure includes:

[0095] Root node: including the user's constitution type and preliminary symptom information;

[0096] Mandatory symptom verification items: Based on highly correlated symptoms (such as symptoms A, B, C), they are used as the core nodes in the consultation path;

[0097] Optional symptom extension items: Based on symptoms with relatively low but still certain correlation (such as symptoms D, E, F), they are used as branch nodes, depending on the mandatory symptom verification items or user feedback.

[0098] Generate a preliminary consultation tree based on mandatory symptoms: The personalized consultation path generation module generates the core part of the consultation tree according to the mandatory symptom verification items. These symptoms are usually the key symptoms that must be verified at the initial stage of the user's consultation. Therefore, they are set as the key nodes in the consultation tree and placed under the child nodes of the root node. The structure of the consultation tree is initially formed:

[0099] Root node: Constitution type information (such as yin deficiency, yang deficiency, qi deficiency);

[0100] Mandatory symptom verification item nodes: Each symptom is added as a child node to the root node;

[0101] For example: Node 1: Symptom A (such as "dry mouth"), Node 2: Symptom B (such as "tiredness"), etc.

[0102] Selectively add optional symptom extension items: According to the remaining symptoms in the highly correlated symptom sequence, the personalized consultation path generation module selects optional symptom extension items as sub-branches through the dynamic branching algorithm and connects them to the relevant nodes of the consultation tree. These symptoms are selected based on the feedback of the mandatory symptom verification items or the correlation of symptom groups.

[0103] Dynamic judgment: Through the user's feedback information or symptom manifestations, the dynamic branching algorithm judges whether to add optional symptom extension items to the consultation path. If the user's symptoms meet the extension conditions, the relevant symptoms are added to the tree as new branches or sub-nodes. For example:

[0104] If the user reports that symptom A, "dry mouth", is relatively severe, the system may guide to further inquiry about symptom C (such as "red tongue").

[0105] If symptom A, "dry mouth", is mild, the system may skip symptom C or, based on the user's response, guide to inquiry about symptom D (such as "constipation").

[0106] Dynamic adjustment of branch generation rules: During the interactive inquiry process, the inquiry tree is generated based on mandatory symptoms and optional symptom expansion items and is dynamically adjusted according to the user's real-time feedback. The dynamic branch algorithm ensures that the inquiry tree can adjust its structure in real time according to changes in the user's symptoms. The specific steps are as follows:

[0107] User feedback: Dynamically adjust the path according to the user's answers, the intensity and frequency of the chief complaint symptoms, etc. For example, if the user reports that a certain symptom has changed during the inquiry (such as symptom A, "dry mouth", getting worse), the system will automatically adjust and add expansion items related to this symptom (such as symptom C or symptom F);

[0108] Symptom dependency relationship: Based on the knowledge graph or empirical data, there may be certain correlations or dependencies between symptoms. The system updates the branches of the inquiry tree in real time according to these dependencies. For example, if symptom A is highly correlated with symptom B, when symptom A is confirmed, the system will automatically expand the further inquiry about symptom B;

[0109] Evolution of user symptoms: If the user shows the evolution of multiple symptoms during the preliminary inquiry, the dynamic branch algorithm can help adjust the inquiry tree, add other optional symptom items, and form a more accurate personalized path.

[0110] Construction of dynamically adjustable inquiry nodes: Through the dynamic branch algorithm, each node dynamically adjusts its content and structure according to the needs of the real-time inquiry process:

[0111] Expandable nodes: For example, the "symptom A" node may include multiple child nodes, dynamically generated expansion items (such as "symptom B", "symptom C");

[0112] Jump logic: Based on the judgment of the algorithm, the system can skip certain nodes and directly jump to the next symptom verification item to ensure the inquiry efficiency and pertinence;

[0113] Output the final interactive inquiry tree: The personalized inquiry path generation module outputs the generated interactive inquiry tree to form a multi-level, dynamically adjustable inquiry process, which includes:

[0114] Mandatory symptom verification items: Ensure that the most critical symptoms are verified first during the inquiry;

[0115] Optional symptom expansion item: Further expand symptom-related information based on user feedback to enhance the comprehensiveness of the medical interview;

[0116] Dynamic adjustment path: Ensure that the medical interview path can be flexibly adjusted as user feedback changes.

[0117] The personalized medical interview path generation module generates an interactive medical interview tree through a dynamic branching algorithm based on the mandatory symptom verification items and optional symptom expansion items. Throughout the process, the system dynamically adjusts the medical interview path according to the user's real-time feedback and symptom changes, making the medical interview process both efficient and able to flexibly handle various clinical situations, thus providing an accurate symptom verification path for doctors.

[0118] Dynamic branching algorithm logic:

[0119] Mandatory symptom verification item: Forcefully verify symptoms (such as "dry mouth"), and terminate the path if it fails;

[0120] Optional symptom expansion item: Selectively expand according to the user's answer (for example, after confirming "dry mouth", jump to the "red tongue" or "constipation" branch);

[0121] Real-time adjustment: If the user feedbacks that "dry mouth" has been relieved, the system automatically skips the sub-symptoms with reduced relevance.

[0122] Data Integration and Medical Record Generation Module

[0123] Obtain interactive data of the medical interview tree: The data integration and medical record generation module obtains the interactive data of the interactive medical interview tree from the personalized medical interview path generation module. The interactive data includes:

[0124] The user's answers during the medical interview (such as the manifestation, severity, and duration of symptoms);

[0125] The selection status of mandatory symptom verification items and optional symptom expansion items;

[0126] The selection and jump records of the paths in the medical interview tree.

[0127] Obtain historical diagnosis and treatment records: The data integration and medical record generation module extracts the user's historical diagnosis and treatment records from the hospital database. The records include:

[0128] The user's past medical history (such as past constitution type, common symptoms, treatment plans, etc.);

[0129] Past diagnosis results, treatment methods and their effects;

[0130] Previous constitution type and symptom evolution history;

[0131] The acquisition of historical medical records is to provide complete background information for the generation of the current medical record and ensure the coherence and comprehensiveness of the medical record;

[0132] Integrating interactive data with historical medical records: After obtaining the interactive data of the interrogation tree and historical medical records, the data integration and medical record generation module integrates the interactive data with historical medical records. The integration process includes:

[0133] Matching symptoms and constitution types: Compare the symptoms obtained from the current interrogation tree with the previous symptoms in the historical medical records and update the symptom evolution path.

[0134] Updating constitution types: Based on the symptoms and feedback of the current user, combined with the constitution types in the historical records, update the constitution characteristic markers of the user. For example, if the current interrogation result matches the historical symptoms, the constitution type marker of the user may be updated to yin deficiency, yang deficiency, or qi deficiency.

[0135] Recording symptom evolution: Combine the historical symptom records and current symptom data to generate a symptom evolution path and integrate it into the preliminary diagnosis medical record to record the change trend of symptoms.

[0136] Generating a preliminary diagnosis medical record including constitution characteristic markers: Based on the integrated interactive data and historical medical records, the data integration and medical record generation module generates a preliminary diagnosis medical record, which includes the following:

[0137] Constitution characteristic markers: Mark the constitution type of the user (such as yin deficiency, yang deficiency, or qi deficiency) according to the current interrogation result and historical medical records;

[0138] Symptom evolution path: Describe the change path of symptoms from the initial stage to the current state, reflecting the time, manifestation, and related factors of symptom changes;

[0139] Interrogation results: Include the diagnostic results of the verified mandatory symptom verification items and optional symptom extension items, as well as the symptom groups related to the constitution type;

[0140] Historical information: Summarize the relevant past symptoms, treatment methods, and their effects in the historical medical records as a reference for the current diagnosis process.

[0141] Outputting the complete preliminary diagnosis medical record: The data integration and medical record generation module outputs the generated preliminary diagnosis medical record to doctors or relevant medical staff. The output preliminary diagnosis medical record includes complete constitution characteristic markers, symptom evolution paths, and historical medical information, providing a scientific basis for the further diagnosis and treatment process.

[0142] The data integration and medical record generation module generates a complete preliminary diagnosis medical record including physical characteristics markers and symptom evolution paths by integrating the interaction data from the personalized consultation path generation module and the user's historical diagnosis and treatment records. This process ensures the coherence and comprehensiveness of the medical record, which helps to provide a more accurate diagnosis and treatment plan for doctors. At the same time, a feedback optimization mechanism is introduced during the medical record generation process, enabling the content of the medical record to be continuously optimized and updated as the diagnosis and treatment process progresses.

[0143] Feedback Optimization Module

[0144] Obtain the differential features between the clinically diagnosed data and the preliminary diagnosis medical record: The feedback optimization module obtains the differential features between the clinically diagnosed data and the preliminary diagnosis medical record, and the steps are as follows:

[0145] Obtain the clinically diagnosed data: Obtain the final diagnosis results confirmed by doctors from the clinical diagnosis system, including:

[0146] Clinically diagnosed symptoms, physical constitution types and their associated symptoms;

[0147] The treatment plan and effect after diagnosis.

[0148] Compare the preliminary diagnosis medical record: Compare the symptoms, physical constitution types, and symptom evolution paths generated based on user feedback and the consultation tree interaction in the preliminary diagnosis medical record with the actual clinically diagnosed data to find the differential features between the two, such as:

[0149] Some symptoms in the preliminary diagnosis medical record were not diagnosed or the diagnosis results were different;

[0150] There are differences between the physical constitution type markers and the finally diagnosed physical constitution types.

[0151] Identify the correlation between the differential features and the knowledge graph: After identifying the differential features in the preliminary diagnosis medical record and the clinically diagnosed data, associate the differential features with the content in the knowledge graph to determine the parts that need to be adjusted. The steps include:

[0152] Extraction of differential features: The differential features include information such as the severity, correlation degree of symptoms, and judgment deviation of physical constitution types. The module extracts key differential features from the diagnosed data and the medical record;

[0153] Knowledge graph matching: Match these differential features with the existing symptoms, physical constitution types, symptom correlation degrees, and the relationship between physical constitution and symptoms in the knowledge graph to determine which knowledge graph entries have deviations or need to be optimized in the current medical record;

[0154] For example, if the correlation degree between the symptom of "dry mouth" in the preliminary diagnosis medical record and the "yin deficiency" physical constitution is low, but the clinical diagnosis shows that the correlation degree between this symptom and the "yin deficiency" physical constitution is high, then the correlation degree between the "dry mouth" symptom and the "yin deficiency" physical constitution needs to be adjusted;

[0155] Adjust the weight coefficients of the knowledge graph: After identifying the differential features and matching them with the relevant content in the knowledge graph, the weight coefficients of the knowledge graph are adjusted by the parameter self-correction unit. The steps are as follows:

[0156] Weight coefficient adjustment: Automatically adjust the weight coefficients between symptoms and constitution types in the knowledge graph according to the differential features and matching results. For example:

[0157] If some symptoms are more prominent in clinical diagnosis but not given enough attention in the pre-diagnosis medical record, the feedback optimization module will increase the weight between this symptom and the relevant constitution type;

[0158] If the correlation between some symptoms and constitution types is too high but the actual diagnosis shows a lower correlation, the feedback optimization module will reduce the weight coefficients of these symptoms;

[0159] Knowledge graph update: After each adjustment of the weight coefficients, the knowledge graph will be updated so that a more accurate symptom-constitution correlation can be referred to in the subsequent consultation process. This adjustment enables the future pre-diagnosis medical records to better match the clinical diagnosis results;

[0160] Feedback optimization effect evaluation: By evaluating the effect of the adjusted knowledge graph, the feedback optimization module continuously monitors the performance of the optimized knowledge graph in the consultation and constitution identification processes;

[0161] Monitor the optimization result: In the process of the new round of user consultation, monitor whether the optimized knowledge graph can effectively reduce the difference from the clinical diagnosis result.

[0162] Feedback correction: If the optimization result is not satisfactory, the feedback optimization module will further analyze the errors or deviations and make a second-round adjustment to ensure that the finally optimized knowledge graph can more accurately support constitution identification and symptom correlation analysis.

[0163] Generate and output the optimized knowledge graph: The optimized knowledge graph will be used in the subsequent consultation and constitution identification and output to the system to ensure the accuracy and rationality of the optimized knowledge graph in the process of generating an interactive consultation tree and symptom correlation analysis;

[0164] The feedback optimization module realizes the dynamic optimization of the knowledge graph by obtaining the differential features between the clinical diagnosis data and the pre-diagnosis medical record and adjusting the weight coefficients of the knowledge graph through the parameter self-correction unit. This process can not only reduce the deviation in system diagnosis but also improve the accuracy of the system in identifying the user's symptoms and constitution types, thus providing more accurate data support for the subsequent consultation process.

[0165] Parameter self-correction unit:

[0166] Differential feature extraction: If the clinical diagnosis is "Yang deficiency" but the preliminary diagnosis is "Qi deficiency", mark the deviation of the constitution type;

[0167] Weight adjustment: Increase the correlation weight between the symptom of "fear of cold" and "Yang deficiency" from 0.7 to 0.9;

[0168] Effect evaluation: The accuracy rate of the constitution identification of the optimized system for new user data has increased by 15%.

[0169] The technical features of the above-described embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0170] The above-described embodiments only represent several implementation manners of the present invention. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention should be subject to the appended claims.

[0171] The above is only the preferred embodiment of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A traditional Chinese medicine pre-consultation collection and management system, characterized in that, The system includes: A user information collection module, which is used to collect the user's basic information and chief complaints, convert them into symptom feature vectors, and generate an initial data set; A traditional Chinese medicine (TCM) constitution identification module, which is used to construct a constitution identification model based on the symptom feature vectors, tongue image parameters, and pulse condition parameters through a support vector machine algorithm, and output the user's constitution type and associated symptom groups; A symptom association analysis module, which is used to call the TCM symptom knowledge graph according to the user's constitution type, and generate a high-correlation symptom sequence through multi-dimensional weight calculation; A personalized interrogation path generation module, which is used to generate an interactive interrogation tree including mandatory symptom verification items and optional symptom extension items based on the high-correlation symptom sequence through a dynamic branching algorithm, and dynamically adjust the path according to the user's feedback; A data integration and medical record generation module, which is used to integrate the interactive data of the interrogation tree and historical diagnosis and treatment records, and generate a preliminary diagnosis medical record including constitution feature markers and symptom evolution paths; A feedback optimization module, which is used to compare the differential features between the clinically diagnosed data and the preliminary diagnosis medical record, and adjust the weight coefficients of the knowledge graph to optimize the system diagnosis accuracy.

2. The system according to claim 1, wherein The specific working process of the user information collection module is as follows: Obtain the user's basic information and chief complaints through the interactive interface and form input content; Convert the user's basic information and chief complaints into a numerical symptom feature vector including constitution information, chief complaints, and background information; Integrate the symptom feature vector and basic information to generate an initial data set, and store it in the system database.

3. The system according to claim 1, wherein In the TCM constitution identification module: The tongue image parameters include the quantified data of the tongue body, tongue coating, and tongue shape; The pulse condition parameters include the numerical parameters of the pulse rate, strength, and fluctuation form; The support vector machine algorithm uses a radial basis function kernel to train the constitution identification model through multi-dimensional feature vectors to identify the constitution types of yin deficiency, yang deficiency, and qi deficiency.

4. The system according to claim 3, wherein The construction of the constitution identification model specifically includes: Integrate the user's symptom feature vectors, tongue image parameters, and pulse condition parameters into a comprehensive multi-dimensional feature vector; Classify the user's constitution type into yin deficiency, yang deficiency, and qi deficiency as classification labels; Construct a constitution identification model through a support vector machine algorithm; Use the multi-dimensional feature vector and the corresponding classification label as inputs to train the constitution identification model; Use the trained constitution identification model to predict the constitution type of new user data.

5. The system according to claim 1, wherein In the symptom association analysis module: The multi-dimensional weight calculation includes the correlation degree between symptoms and constitution types, symptom similarity, joint relationship, and user feedback weight; The high-correlation symptom sequence is sorted by weight. The top 20% of the symptoms are defined as mandatory symptom verification items, and the top 20% of the remaining symptoms except the mandatory symptom verification items are defined as optional symptom extension items.

6. The system according to claim 1, wherein In the personalized interrogation path generation module: The dynamic branching algorithm generates the core nodes of the interrogation tree according to the mandatory symptom verification items, and selectively adds the optional symptom extension items as sub-branches; The nodes of the interactive interrogation tree dynamically adjust the content and structure according to the user's real-time feedback to achieve path jump and extension.

7. The system according to claim 6, wherein The generation of the interactive interrogation tree including mandatory symptom verification items and optional symptom extension items through the dynamic branching algorithm specifically includes: Define the interactive consultation tree structure as a hierarchical tree structure, including several nodes and branches. The root node of the tree represents the starting point of the consultation, the nodes represent symptoms, and the branches represent the relationships, priorities, and dependency conditions between symptoms; Generate the core part of the consultation tree according to the mandatory symptom verification items, and the core part includes the root node and the mandatory symptom nodes; According to the remaining symptoms in the high-correlation symptom sequence, select the optional symptom extension items as sub-branches through the dynamic branching algorithm and connect them to the consultation tree; During the interactive consultation process, generate the interactive consultation tree according to the mandatory symptom verification items and the optional symptom extension items, and make dynamic adjustments according to the user's real-time feedback; Through the dynamic branching algorithm, dynamically adjust the content and structure of each node according to the needs of the real-time consultation process; Output the generated interactive consultation tree to form a multi-level and dynamically adjustable consultation process.

8. The system according to claim 7, wherein The specific working process of the data integration and medical record generation module is as follows: Match the interactive consultation tree interaction data with the past symptoms, constitution types, and treatment results in the historical diagnosis and treatment records; Generate a structured pre-diagnosis medical record containing constitution type markers, symptom evolution paths, and historical information.

9. The system according to claim 1, wherein In the feedback optimization module: The differential features include symptom correlation deviation and constitution type misjudgment, and the weight of the knowledge graph is adjusted by the parameter self-correction unit; The optimized knowledge graph is used to update the operation logics of the symptom correlation analysis module and the constitution identification module.

10. The system according to claim 1, wherein, The traditional Chinese medicine symptom knowledge graph is a dynamic graph, its nodes represent symptoms, and the edges represent the correlation relationships and weight coefficients between symptoms, and the weight is adaptively adjusted through the feedback optimization module.

Images