Traditional Chinese medicine personalized diagnosis and treatment scheme generation method and device

Abstract

The invention relates to the technical field of medical treatment, in particular to a traditional Chinese medicine personalized diagnosis and treatment scheme generation method which comprises the steps of obtaining medical record data related to traditional Chinese medicine from multiple sources, analyzing the medical record data to obtain potential association rule data, and establishing a corresponding traditional Chinese medicine knowledge graph based on the association rule data; health data of a patient are obtained, corresponding diagnosis and treatment suggestion data are generated based on the traditional Chinese medicine knowledge graph and the health data, and the health data comprise symptoms and physique of the patient; and sending the health data and the corresponding diagnosis and treatment suggestion data to different user sides, obtaining diagnosis and treatment feedback data of each user side, optimizing the diagnosis and treatment suggestion data based on all the diagnosis and treatment feedback data, and determining a corresponding target diagnosis and treatment scheme. The traditional Chinese medicine diagnosis and treatment effect can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of medical treatment, and in particular to a method and device for generating a personalized diagnosis and treatment plan of traditional Chinese medicine. Background Art

[0002] With the development of information technology, big data and artificial intelligence technologies have been widely used in the field of medical health, especially in the field of traditional Chinese medicine. Through effective data collection and organization, a large number of traditional Chinese medicine medical records and related knowledge base data can be systematically accumulated and managed; on this basis, advanced data analysis and mining techniques can be used to extract valuable information from massive data, and further combined with modern information technology such as knowledge graph construction technology to achieve structured expression of traditional Chinese medicine theory and practical experience, which will help promote the modernization of traditional Chinese medicine diagnosis and treatment.

[0003] However, the formulation of TCM diagnosis and treatment plans is still highly dependent on the physician's personal experience and intuitive judgment, lacking a standardized and personalized treatment plan generation mechanism, which affects the effectiveness of TCM diagnosis and treatment.

[0004] From the above, we can see that how to improve the diagnosis and treatment effect of traditional Chinese medicine still needs to be solved. Summary of the invention

[0005] In order to improve the diagnosis and treatment effect of traditional Chinese medicine, the present application provides a method and device for generating a personalized diagnosis and treatment plan of traditional Chinese medicine.

[0006] In the first aspect, the present application provides a method for generating a personalized diagnosis and treatment plan of traditional Chinese medicine, which adopts the following technical solution:

[0007] A method for generating personalized diagnosis and treatment plans for traditional Chinese medicine, comprising: obtaining medical record data related to traditional Chinese medicine from multiple sources, analyzing the medical record data to obtain potential association rule data, and establishing a corresponding traditional Chinese medicine knowledge graph based on the association rule data; obtaining the patient's health data, and generating corresponding diagnosis and treatment recommendation data based on the traditional Chinese medicine knowledge graph and the health data, wherein the health data includes the patient's symptoms and constitution; sending the health data and the corresponding diagnosis and treatment recommendation data to different user terminals, obtaining diagnosis and treatment feedback data from each user terminal, optimizing the diagnosis and treatment recommendation data based on all the diagnosis and treatment feedback data, and determining the corresponding target diagnosis and treatment plan.

[0008] By adopting the above technical solutions, by analyzing a large amount of medical record data, discovering potential association rules, and establishing a knowledge graph of traditional Chinese medicine, the symptoms and physical types of the disease can be more accurately identified, thereby improving the accuracy of diagnosis; by collecting users' diagnosis and treatment feedback data, continuously optimizing diagnosis and treatment suggestions, forming a closed loop of continuous improvement, ensuring the effectiveness and applicability of diagnosis and treatment plans, and dynamically adjusting diagnosis and treatment plans to respond to patients' physical changes and treatment effects in a timely manner, it can not only improve patient satisfaction, but also promote effective communication between doctors and patients, so that doctors can better understand the actual situation of patients and adjust treatment plans in a timely manner, which can significantly improve the overall effect of traditional Chinese medicine diagnosis and treatment and provide patients with more accurate and effective medical services.

[0009] Optionally, in the process of analyzing the medical record data to obtain potential association rule data, the method also includes: preprocessing the medical record data to obtain the most relevant categorical features and converting the categorical features into numerical representations; calling a pre-trained analysis model, inputting the categorical features converted into numerical representations into the analysis model, and obtaining corresponding association rule data.

[0010] By adopting the above technical solutions, high-quality processing of medical record data can be ensured, and pre-trained models can be used to efficiently extract potential association rule data, thereby providing a solid foundation for generating personalized diagnosis and treatment plans.

[0011] Optionally, the method also includes: obtaining the patient's physiological parameter data, uploading the physiological parameter data to a cloud server, and synchronizing the physiological parameter data with existing medical record data; evaluating the patient's health status based on the physiological parameter data and determining corresponding physiological parameter changes; matching the physiological parameter changes with existing association rule data, and if new rule data is matched, adjusting the target diagnosis and treatment plan based on the matched new rule data.

[0012] By adopting the above-mentioned technical solutions, we can monitor the changes in the patient's physiological parameters in real time and adjust the diagnosis and treatment plan based on these changes to ensure that the treatment plan can respond to the patient's health changes in a timely manner; based on the patient's latest physiological parameter data, we can dynamically adjust the diagnosis and treatment plan to make the treatment more personalized and accurate.

[0013] Optionally, the method also includes: collecting the patient's external environment, integrating the external environment with the patient's medical record data to form a complete patient file; wherein the external environment includes living environment, working environment, and climatic conditions; retrieving a pre-trained analysis model, inputting the patient file into the analysis model to obtain the impact parameters of the external environment on the patient's health; matching corresponding association rules based on the impact parameters, and judging whether the impact of the external environment on the patient's disease requires adjustment of the target diagnosis and treatment plan based on matching the corresponding association rules.

[0014] By adopting the above-mentioned technical solutions, the diagnosis and treatment plan can be dynamically adjusted based on the parameters of the external environment's impact on the patient's health, making the treatment more personalized and better adapted to the patient's specific situation; through comprehensive and detailed evaluation and dynamic adjustment, the patient's trust in the treatment plan can be enhanced and the patient's treatment compliance can be improved.

[0015] Optionally, including a natural language processing unit, the method also includes: obtaining the patient's input natural language, inputting the input natural speech into the natural language processing unit to obtain the patient's consultation content; querying the traditional Chinese medicine knowledge graph based on the consultation content to obtain corresponding accurate health information; generating corresponding health advice based on the patient's accurate health information, and sending the health advice to the patient based on an interactive interface.

[0016] By adopting the above technical solutions, firstly, through natural language processing technology, patients can consult conveniently and quickly without complicated operations, which improves the user experience; secondly, by using the traditional Chinese medicine knowledge graph, it ensures that the health information provided is accurate and reliable, helping patients to better understand their own health conditions; finally, according to the patient's consultation content and specific circumstances, personalized health suggestions are generated to make the suggestions more in line with the patient's actual situation and improve the treatment effect.

[0017] Optionally, the method also includes: obtaining prescription data issued by the doctor and the patient's schedule; determining a corresponding reminder schedule based on the prescription data and schedule data; reminding the patient based on the reminder schedule and recording each time the patient takes the medicine, and each time the medicine is taken includes the time of taking the medicine and dosage information.

[0018] By adopting the above technical solutions, systematic management and reminders of patients' medication status can be achieved, ensuring the effective implementation of treatment plans, thereby improving the scientificity and effectiveness of personalized diagnosis and treatment plans of traditional Chinese medicine.

[0019] In the second aspect, the present application provides a device for generating a personalized diagnosis and treatment plan of traditional Chinese medicine, which adopts the following technical solution:

[0020] A device for generating personalized diagnosis and treatment plans of traditional Chinese medicine, comprising:

[0021] A TCM knowledge graph building module obtains TCM-related medical record data from multiple sources, analyzes the medical record data to obtain potential association rule data, and uses the association rule data to build a corresponding TCM knowledge graph;

[0022] A diagnosis and treatment recommendation data generation module is used to obtain the patient's health data and generate corresponding diagnosis and treatment recommendation data based on the TCM knowledge graph and the health data, wherein the health data includes the patient's symptoms and constitution;

[0023] The target diagnosis and treatment plan determination module sends the health data and the corresponding diagnosis and treatment recommendation data to different user terminals, obtains the diagnosis and treatment feedback data of each user terminal, optimizes the diagnosis and treatment recommendation data based on all the diagnosis and treatment feedback data and uses it to determine the corresponding target diagnosis and treatment plan.

[0024] In the third aspect, the present application provides a method for generating a personalized diagnosis and treatment plan of traditional Chinese medicine, which adopts the following technical solution:

[0025] A method for generating a personalized TCM diagnosis and treatment plan comprises a processor in which a program of any one of the above-mentioned methods for generating a personalized TCM diagnosis and treatment plan is running.

[0026] In a fourth aspect, the present application provides a storage medium, which adopts the following technical solution:

[0027] A storage medium storing a program for generating a personalized TCM diagnosis and treatment plan according to any one of the above methods.

[0028] In summary, the present application includes at least one of the following beneficial technical effects:

[0029] Improve diagnostic accuracy and personalized treatment: Generate more accurate and personalized diagnosis and treatment plans by analyzing medical record data and patient health data.

[0030] Dynamic adjustment and optimization: By real-time monitoring of changes in patients' physiological parameters and external environmental influences, and continuously adjusting and optimizing diagnosis and treatment plans based on feedback data, we ensure the effectiveness and applicability of treatment.

[0031] Enhance doctor-patient communication and user experience: Through natural language processing and interactive interfaces, improve patients' consultation experience and doctor-patient communication, and enhance patients' trust and treatment compliance.

[0032] Improve medication compliance: Through system management and reminders, ensure that patients take medication on time and in the right amount to improve treatment outcomes. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 The present invention is a flowchart of a method for generating a personalized TCM diagnosis and treatment plan according to an exemplary embodiment.

[0034] Figure 2 It is a structural block diagram of a device for generating a personalized diagnosis and treatment plan of traditional Chinese medicine according to an exemplary embodiment. DETAILED DESCRIPTION

[0035] Embodiments of the present application are described in detail below, examples of which are shown in the accompanying drawings.

[0036] In the description of this specification, the description with reference to the terms "certain embodiments", "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiments or examples are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0037] The present application embodiment discloses a method for generating a personalized diagnosis and treatment plan of traditional Chinese medicine, referring to Figure 1 ,include:

[0038] S100, obtaining medical record data related to traditional Chinese medicine from multiple sources, analyzing the medical record data to obtain potential association rule data, and establishing a corresponding traditional Chinese medicine knowledge graph based on the association rule data.

[0039] Among them, medical record data related to traditional Chinese medicine are obtained from various sources, including but not limited to electronic medical record systems (EMR), hospital information systems (HIS), research literature, clinical trial data, etc.; the obtained medical record data are preprocessed, including data cleaning (removing noise, missing values ​​or outliers), data conversion (converting unstructured data into structured data) and data integration (merging data from different sources into a unified data set to eliminate redundancy).

[0040] Secondly, analyze the medical record data to discover potential association rule data. For example, find out the correlation between symptoms, constitution, and treatment methods through association rule learning algorithms (such as Apriori, FP-growth, etc.), build a TCM knowledge graph based on the discovered association rule data, and represent the association rules in a graphical way for easy understanding and application.

[0041] By analyzing a large amount of medical record data and discovering potential association rules, we can more accurately identify the symptoms and physical types of the disease. The discovered association rules are then constructed into a knowledge graph to facilitate doctors and researchers to understand and apply them, thereby improving the scientificity and effectiveness of diagnosis and treatment plans.

[0042] S110, obtaining the patient's health data, and generating corresponding diagnosis and treatment recommendation data based on the TCM knowledge graph and the health data.

[0043] Among them, health data includes the patient's symptoms and constitution; the patient's health data is integrated with the TCM knowledge graph, and by comparing the patient's symptoms and constitution information with the association rules in the knowledge graph, based on the integrated data, personalized diagnosis and treatment recommendation data is generated, including specific diagnostic opinions, treatment plans, etc.; generating personalized diagnosis and treatment recommendations based on individual differences of patients can improve the treatment effect, and at the same time, by comparing with the knowledge graph, the accuracy and rationality of the diagnosis can be ensured.

[0044] S120, sending the health data and the corresponding diagnosis and treatment recommendation data to different user terminals, obtaining the diagnosis and treatment feedback data of each user terminal, optimizing the diagnosis and treatment recommendation data based on all the diagnosis and treatment feedback data and determining the corresponding target diagnosis and treatment plan.

[0045] Among them, the user end here can be the patient end and the doctor end, and the corresponding diagnosis and treatment feedback data includes information such as the patient's treatment effect, medication status, and physical reaction; based on the collected feedback data, the actual effect of the diagnosis and treatment plan is analyzed, and according to the feedback data, the diagnosis and treatment suggestion data is optimized to form the final target diagnosis and treatment plan.

[0046] It should be pointed out here that when all users are doctors, the diagnosis and treatment feedback data at this time means that all doctors may have different opinions or suggestions on the diagnosis and treatment recommendation data, and the system will optimize the corresponding diagnosis and treatment recommendation data based on these opinions or suggestions.

[0047] Through the above steps, firstly, by analyzing a large amount of medical record data and discovering potential association rules, the accuracy of diagnosis can be improved; secondly, according to the individual differences of patients, personalized diagnosis and treatment suggestions can be generated to improve the treatment effect; at the same time, by collecting users' diagnosis and treatment feedback data, the diagnosis and treatment suggestions are continuously optimized to form a closed loop of continuous improvement. Through the feedback mechanism, the communication between doctors and patients is enhanced to ensure the effective implementation of the treatment plan, which can not only significantly improve the overall effect of TCM diagnosis and treatment, but also provide patients with more accurate and effective medical services.

[0048] It should be pointed out here that in the process of analyzing medical record data and obtaining potential association rule data, the method also includes:

[0049] S101, preprocessing the medical record data, obtaining the most relevant categorical features and converting the categorical features into numerical representations.

[0050] Among them, the medical record data is first preprocessed, including data cleaning, data conversion and data integration; data cleaning: remove noise, missing values ​​or outliers in the medical record data to ensure the quality of the data; data conversion: convert unstructured data (such as text reports) into structured data for subsequent analysis; data integration: merge data from different sources into a unified data set to eliminate redundancy and ensure consistency.

[0051] Then, the most relevant categorical features are selected from the preprocessed data. For example, the features most relevant to disease diagnosis can be selected from the medical record data, such as symptoms, physical type, treatment methods, etc.; It should be pointed out here that the feature selection method is specifically: using domain knowledge and preliminary exploratory data analysis (EDA) to select the features most relevant to the target variable (such as disease diagnosis); feature conversion is specifically: converting categorical features into numerical representations. Common methods include One-Hot Encoding, Label Encoding, etc.

[0052] By selecting the most relevant features and reducing the interference of irrelevant features on the model, the efficiency and accuracy of the model can be improved; and by converting categorical features into numerical representations, it is easier for machine learning models to process and improve the training effect of the model.

[0053] S102, calling a pre-trained analysis model, inputting the categorical features converted into numerical representation into the analysis model, and obtaining corresponding association rule data.

[0054] The training process of the analysis model includes: preprocessing the historical medical record data, removing noise and missing values, and converting unstructured data into structured data; then, converting categorical features into numerical representations through feature selection and transformation; then, selecting a suitable machine learning model, you can choose an association rule learning algorithm (such as Apriori, FP-growth), and use the processed data for training; finally, evaluate the model performance through cross-validation and other techniques, and optimize it to ensure that the model has good generalization ability.

[0055] By executing the above steps, the most relevant features are selected and the categorical features are converted into numerical representations. The pre-trained model is used to efficiently extract potential association rule data, improve analysis efficiency and rule reliability, and reduce manual workload through automated analysis, thereby improving the speed and accuracy of data analysis.

[0056] In addition, in the embodiment of the present application, the method further includes:

[0057] S121, obtaining the patient's physiological parameter data, uploading the physiological parameter data to the cloud server, and synchronizing the physiological parameter data with the existing medical record data.

[0058] Among them, the patient's physiological parameter data, such as heart rate, blood pressure, blood sugar level, body temperature, etc., are collected in real time through wearable devices, mobile applications or other health monitoring tools; the collected physiological parameter data are then uploaded to the cloud server to ensure the safe storage and real-time update of the data, and the uploaded physiological parameter data is synchronized with the existing medical record data to ensure that all relevant data are in a unified data set for comprehensive analysis.

[0059] S122, assessing the health status of the patient based on the physiological parameter data and determining corresponding physiological parameter changes.

[0060] Among them, the patient's health status is evaluated based on the collected physiological parameter data, and the changes in the patient's physiological parameters are determined through comparative analysis, such as whether the heart rate is abnormally high, whether the blood pressure fluctuates, etc. By evaluating the physiological parameter data in real time and dynamically monitoring the patient's health status, abnormal situations can be discovered in time.

[0061] S123, matching the physiological parameter changes with the existing association rule data, and if new rule data is matched, adjusting the target diagnosis and treatment plan based on the matched new rule data.

[0062] Among them, the determined physiological parameter changes are matched with the existing association rule data to find out whether there is new rule data that matches the current changes. If new rule data is matched, the target diagnosis and treatment plan is adjusted based on these new rule data, such as adjusting the drug dosage, changing the drug, or adding other treatment methods.

[0063] By executing steps S121 to S123, the patient's health changes can be discovered in time by collecting physiological parameter data in real time, and the physiological parameter data can be synchronized with the medical record data to form a complete patient file, which can facilitate doctors to fully understand the patient's health status. At the same time, by evaluating the physiological parameter data in real time, the patient's health status can be dynamically monitored, and the diagnosis and treatment plan can be dynamically adjusted according to the changes in the physiological parameters, making the treatment more personalized and accurate.

[0064] In the embodiment of the present application, the analysis model may also be applied to other aspects. For example, the method further includes:

[0065] S124, collect the patient's external environment, integrate the external environment with the patient's medical record data, and form a complete patient file.

[0066] Among them, the patient's external environmental information can be collected through questionnaires, mobile applications, Internet of Things devices, etc., including living environment, working environment, climate conditions, etc.; living environment: such as indoor air quality, noise level, light intensity, etc.; working environment: such as air quality, stress level, work intensity, etc. in the workplace; climate conditions: such as temperature, humidity, air pressure, etc.

[0067] The collected external environmental data is then integrated with the existing medical record data to form a complete patient file, which can ensure that all relevant information is in a unified data set, making it easier for doctors to fully understand the patient's health status.

[0068] S125, retrieve the pre-trained analysis model, input the patient's file into the analysis model to obtain the parameters of the impact of the external environment on the patient's health.

[0069] Among them, by selecting characteristics related to the external environment, such as the air quality index of the living environment, the stress level of the working environment, the temperature and humidity of the climatic conditions, etc., and inputting the integrated patient file data into the analysis model, the impact parameters of the external environment on the patient's health can be obtained, such as the possibility and risk level of environmental factors on the development of the patient's disease; through the analysis model, accurate impact parameters can be provided to help doctors more accurately judge the degree of impact of the external environment on the patient's health.

[0070] S126, matching corresponding association rules based on the influencing parameters, and judging whether the impact of the external environment on the patient's disease requires adjustment of the target diagnosis and treatment plan based on matching the corresponding association rules.

[0071] Among them, the existing association rule library is used to find rules that match the current influencing parameters, and rules related to external environmental influencing parameters are extracted from the rule library, such as "high humidity + high temperature -> increased risk of heart attack"; if the matched rules show that the external environment has a significant impact on the patient's disease, the diagnosis and treatment plan is adjusted according to these rules, such as adding protective measures, adjusting medication, or increasing the frequency of treatment. By matching the new rules, the diagnosis and treatment plan is adjusted in a timely manner to ensure that the treatment plan can respond to the patient's health changes in a timely manner

[0072] By executing steps S124 to S126, it is possible to collect and integrate the patient's external environment data, and evaluate the impact of the external environment on the patient's health based on these data, and then adjust the diagnosis and treatment plan according to the influencing parameters. This not only improves the scientificity and effectiveness of the diagnosis and treatment plan, but also enhances communication between doctors and patients, and improves patients' treatment compliance and satisfaction.

[0073] During the treatment of the patient, the patient's emotional changes also need to be taken into account. For this purpose, the system includes a natural language processing unit, and the method also includes:

[0074] S127, obtaining the patient's input natural language, and inputting the input natural speech into a natural language processing unit to obtain the patient's consultation content.

[0075] Among them, natural language input from patients, such as consultation in voice or text form, is collected through mobile applications, websites or other interactive interfaces; Voice input: patients can speak their consultation content through voice input devices (such as the microphone on a smartphone); Text input: patients can also enter consultation content in text form through a keyboard or other input devices.

[0076] The input natural language is then sent to the natural language processing (NLP) unit for processing; speech-to-text: for speech input, speech recognition is first performed to convert the speech into text; text parsing: the text is parsed to identify the patient's consultation content, including symptom descriptions, health problems, etc. Through natural language processing technology, the patient's consultation content is accurately parsed to ensure that the patient's intentions and needs can be correctly understood.

[0077] S128, query the TCM knowledge graph based on the consultation content to obtain the corresponding accurate health information.

[0078] It should be pointed out here that the TCM knowledge graph contains relevant information such as symptoms, physical constitution types, treatment methods, etc. of various diseases. Therefore, according to the patient's consultation content, relevant and accurate health information such as causes, treatment methods, preventive measures, etc. can be found in the knowledge graph, thereby ensuring that the information provided is highly matched with the patient's consultation content to improve the relevance and practicality of the information.

[0079] S129, generating corresponding health advice based on the patient's accurate health information, and sending the health advice to the patient based on an interactive interface.

[0080] Among them, health advice may include dietary advice, exercise advice, treatment methods, etc.; interaction can be carried out through mobile applications, websites or other forms of user interfaces to ensure that patients can receive health advice in a timely manner and can provide further consultation or feedback through the interactive interface.

[0081] By executing steps S127 to S129, the patient's consultation content can be accurately parsed through natural language processing technology to ensure that the patient's intentions and needs can be correctly understood; personalized health advice is generated based on the patient's health information to make the advice more in line with the patient's actual situation, which can improve the treatment effect; health advice is sent to the patient through an interactive interface so that the patient can obtain professional advice in a timely manner, which can improve treatment compliance.

[0082] Finally, patients need to be reminded to take medication on time, so the method also includes:

[0083] S111, obtaining the prescription data issued by the doctor and the patient's schedule.

[0084] This includes information such as drug name, dosage, frequency of medication, and time of medication; the schedule includes working hours, rest time, daily activities, etc.

[0085] S112, determining a corresponding reminder schedule based on the prescription data and the schedule data.

[0086] Among them, matching the medication time with the patient's schedule ensures that the reminder time does not conflict with the patient's other important activities, so as to reasonably arrange the reminder time and ensure that the patient can take the medication at the appropriate time.

[0087] S113, reminding the patient based on the reminder schedule and recording each medication situation of the patient, each medication situation including medication time and dosage information.

[0088] Among them, according to the set schedule, the patient is reminded to take the medicine through a mobile application or smart wearable device. For example, the patient can be reminded through mobile phone notifications, smart watch vibrations, etc. If the patient does not take the medicine at the reminded time, multiple reminders can be set until the patient confirms to take the medicine.

[0089] Then, each time the patient takes the medicine is recorded. The patient can confirm taking the medicine through the application. The application automatically records the time and dosage information of the medicine, and then stores the medicine record in the cloud server or local database for subsequent viewing and analysis.

[0090] First, by setting a reasonable reminder schedule, ensure that patients will not miss the medication time and improve medication compliance; second, by recording each medication, ensure that the doctor can accurately understand the patient's medication status, which is helpful for subsequent treatment adjustments; finally, by recording and tracking medication status, ensure that patients take medication on time and in the right amount, thereby improving treatment outcomes.

[0091] The present application embodiment discloses a method for generating a personalized diagnosis and treatment plan of traditional Chinese medicine, referring to Figure 2 , the devices include but are not limited to:

[0092] The TCM knowledge graph building module 200 obtains TCM-related medical record data from multiple sources, analyzes the medical record data to obtain potential association rule data, and uses the association rule data to build a corresponding TCM knowledge graph;

[0093] The diagnosis and treatment recommendation data generation module 210 obtains the patient's health data and generates corresponding diagnosis and treatment recommendation data based on the TCM knowledge graph and the health data, wherein the health data includes the patient's symptoms and constitution;

[0094] The target diagnosis and treatment plan determination module 220 sends the health data and the corresponding diagnosis and treatment recommendation data to different user terminals, obtains the diagnosis and treatment feedback data of each user terminal, optimizes the diagnosis and treatment recommendation data based on all the diagnosis and treatment feedback data and uses it to determine the corresponding target diagnosis and treatment plan.

[0095] Optionally, the device includes but is not limited to:

[0096] The conversion module preprocesses the medical record data, obtains the most relevant categorical features and converts the categorical features into numerical representations;

[0097] The association rule data acquisition module calls the pre-trained analysis model and inputs the categorical features converted into numerical representation into the analysis model to obtain the corresponding association rule data.

[0098] Optionally, the device includes but is not limited to:

[0099] A physiological parameter data acquisition module is used to obtain the patient's physiological parameter data, upload the physiological parameter data to the cloud server, and synchronize the physiological parameter data with the existing medical record data;

[0100] A physiological parameter change determination module, which evaluates the patient's health status based on the physiological parameter data and is used to determine the corresponding physiological parameter changes;

[0101] The matching module is used to match the physiological parameter changes with the existing association rule data. If new rule data is matched, the target diagnosis and treatment plan is adjusted based on the matched new rule data.

[0102] Optionally, the device includes but is not limited to:

[0103] The external environment collection module is used to collect the patient's external environment, integrate the external environment with the patient's medical record data, and form a complete patient file; the external environment includes living environment, working environment, and climate conditions;

[0104] The influencing parameter acquisition module calls the pre-trained analysis model and inputs the patient's files into the analysis model to obtain the influencing parameters of the external environment on the patient's health;

[0105] The judgment module matches the corresponding association rules based on the influencing parameters, and is used to judge whether the impact of the external environment on the patient's disease requires adjustment of the target diagnosis and treatment plan based on the matching of the corresponding association rules.

[0106] Optionally, a natural language processing unit is included, and the device includes but is not limited to:

[0107] A consultation content acquisition module acquires the patient's input natural language and inputs the input natural speech into a natural language processing unit to acquire the patient's consultation content;

[0108] The module for obtaining accurate health information queries the TCM knowledge graph based on the consultation content to obtain the corresponding accurate health information;

[0109] The health advice generation module is used to generate corresponding health advice based on the patient's accurate health information, and send the health advice to the patient based on the interactive interface.

[0110] Optionally, the device includes but is not limited to:

[0111] Schedule acquisition module, used to obtain the prescription data issued by the doctor and the patient's schedule;

[0112] A reminder schedule determination module, for determining a corresponding reminder schedule based on the prescription data and the schedule data;

[0113] The module for recording each medication intake reminds the patient based on the reminder schedule and is used to record each medication intake of the patient, including medication time and dosage information.

[0114] An embodiment of the present application also discloses a method for generating a personalized TCM diagnosis and treatment plan, including a processor, in which a program of any one of the above-mentioned methods for generating a personalized TCM diagnosis and treatment plan is running.

[0115] The embodiment of the present application also discloses a storage medium storing a program of the method for generating a personalized TCM diagnosis and treatment plan as described in any one of the above.

[0116] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for generating a personalized diagnosis and treatment plan of traditional Chinese medicine, characterized in that: include: Acquire medical record data related to traditional Chinese medicine from multiple sources, analyze the medical record data to obtain potential association rule data, and establish a corresponding traditional Chinese medicine knowledge graph based on the association rule data; Acquire the patient's health data, and generate corresponding diagnosis and treatment recommendation data based on the TCM knowledge graph and the health data, wherein the health data includes the patient's symptoms and constitution; The health data and the corresponding diagnosis and treatment recommendation data are sent to different user terminals, the diagnosis and treatment feedback data of each user terminal is obtained, and the diagnosis and treatment recommendation data is optimized based on all the diagnosis and treatment feedback data to determine the corresponding target diagnosis and treatment plan.

2. The method for generating a personalized TCM diagnosis and treatment plan according to claim 1, characterized in that: In the process of analyzing the medical record data to obtain potential association rule data, the method further includes: Preprocessing the medical record data to obtain the most relevant categorical features and converting the categorical features into numerical representations; Retrieve the pre-trained analysis model, input the categorical features converted into numerical representation into the analysis model, and obtain the corresponding association rule data.

3. The method for generating a personalized TCM diagnosis and treatment plan according to claim 1, characterized in that: The method also includes: Acquire the patient's physiological parameter data, upload the physiological parameter data to a cloud server, and synchronize the physiological parameter data with existing medical record data; Assessing the patient's health status based on the physiological parameter data and determining corresponding physiological parameter changes; The physiological parameter changes are matched with the existing association rule data. If new rule data is matched, the target diagnosis and treatment plan is adjusted based on the matched new rule data.

4. The method for generating a personalized TCM diagnosis and treatment plan according to claim 1, characterized in that: The method also includes: Collect the patient's external environment, integrate the external environment with the patient's medical record data to form a complete patient file; the external environment includes living environment, working environment, and climate conditions; Retrieving a pre-trained analysis model, and inputting the patient profile into the analysis model to obtain parameters of the impact of the external environment on the patient's health; Based on matching the influencing parameters with corresponding association rules, it is determined whether the impact of the external environment on the patient's disease requires adjustment of the target diagnosis and treatment plan.

5. The method for generating a personalized TCM diagnosis and treatment plan according to claim 1, characterized in that: Including a natural language processing unit, the method also includes: Acquire the patient's input natural language, and input the input natural language into a natural language processing unit to acquire the patient's consultation content; Based on the consultation content, query the TCM knowledge graph to obtain corresponding accurate health information; Generate corresponding health advice based on the patient's accurate health information, and send the health advice to the patient based on the interactive interface.

6. The method for generating a personalized TCM diagnosis and treatment plan according to claim 1, characterized in that: The method also includes: Access physician prescription data and patient schedules; determining a corresponding reminder schedule based on the prescription data and the schedule data; The patient is reminded based on the reminder schedule and each medication situation of the patient is recorded, and each medication situation includes medication time and dosage information.

7. A device for generating personalized diagnosis and treatment plans of traditional Chinese medicine, characterized in that: include: A TCM knowledge graph building module obtains TCM-related medical record data from multiple sources, analyzes the medical record data to obtain potential association rule data, and uses the association rule data to build a corresponding TCM knowledge graph; A diagnosis and treatment recommendation data generation module is used to obtain the patient's health data and generate corresponding diagnosis and treatment recommendation data based on the TCM knowledge graph and the health data, wherein the health data includes the patient's symptoms and constitution; The target diagnosis and treatment plan determination module sends the health data and the corresponding diagnosis and treatment recommendation data to different user terminals, obtains the diagnosis and treatment feedback data of each user terminal, optimizes the diagnosis and treatment recommendation data based on all the diagnosis and treatment feedback data and uses it to determine the corresponding target diagnosis and treatment plan.

8. A method for generating personalized diagnosis and treatment plans in traditional Chinese medicine, characterized in that: It includes a processor, in which runs a program of the method for generating a personalized Chinese medicine diagnosis and treatment plan as described in any one of claims 1 to 6.

9. A storage medium, characterized in that: A program for generating a personalized TCM diagnosis and treatment plan as described in any one of claims 1 to 6 is stored.

Images