Chronic pain-oriented traditional Chinese medicine meridian physiotherapy scheme intelligent recommendation system

Abstract

The invention provides a chronic pain-oriented traditional Chinese medicine meridian physiotherapy scheme intelligent recommendation system. The chronic pain-oriented traditional Chinese medicine meridian physiotherapy scheme intelligent recommendation system comprises a multi-modal data acquisition module, a knowledge graph construction module, an intelligent analysis module and a physiotherapy scheme recommendation module, the multi-modal data acquisition module is used for acquiring and preprocessing multi-modal data of a patient; the knowledge graph construction module is used for constructing an acupoint searching knowledge graph and a human body link relation graph according to traditional Chinese medicine meridian physiotherapy experience data; the intelligent analysis module is used for generating a preliminary associated acupuncture point set; the physiotherapy scheme recommendation module is used for generating a final personalized traditional Chinese medicine meridian physiotherapy scheme; according to the invention, high-precision and personalized traditional Chinese medicine meridian physiotherapy scheme intelligent recommendation can be realized; in addition, while personalized inquiry is realized, the inquiry efficiency is improved, the burden of doctors is reduced, data can be acquired without wearing fixing equipment, the operation is simple, the popularization is easy, and non-professional personnel can also autonomously carry out pain inquiry and rehabilitation management.

Description

Technical Field

[0001] The present invention relates to the field of deep learning and TCM-assisted diagnosis and treatment technology, and more specifically, to an intelligent recommendation system for TCM meridian therapy plans for chronic pain. Background Art

[0002] According to the "China Pain Medicine Development Report (2020)", the number of chronic pain patients in my country has reached 300 million, and continues to grow at a rate of 10 to 20 million per year. Chronic pain can be effectively relieved through physical therapy methods such as moxibustion or electrical stimulation of traditional Chinese medicine acupoints. The precise recommendation of high-precision and personalized Chinese medicine meridian physical therapy plans will help improve the effect of Chinese medicine meridian physical therapy. In the field of chronic pain management, traditional Chinese medicine consultation methods represented by acupuncture and massage mainly rely on the experience and skills of physicians. Take the existing Bai's skin needle therapy as an example. This is a pain treatment method based on Chinese medicine theory. It determines the type and degree of pain of patients through comprehensive symptom consultation and myofascial trigger point positioning. The feature of this Chinese medicine physical therapy plan is that it can quickly determine the location of pain by combining the physician's meticulous consultation and palpation, and provide personalized physical therapy plans based on the acupuncture experience summarized by Bai. However, the existing myofascial trigger point positioning method mainly relies on the physician's consultation and palpation, which not only requires high experience and skills of the physician, but also takes a lot of time, and it is difficult to meet the growing needs of the vast number of pain patients. In addition, differences in pain sensitivity or subjective description errors among patients during palpation may affect diagnostic accuracy.

[0003] With the development of science and technology, a variety of rehabilitation and physiotherapy products using digital health monitoring devices have appeared on the market. For example, some products integrate wearable devices and are installed in fixed positions on the human body. They can monitor the patient's physiological parameters in real time and provide pain management suggestions through data analysis. The function of these technologies is to assist physicians in diagnosis and treatment through objective physiological data.

[0004] Existing chronic pain management technologies, whether traditional Chinese medicine or modern scientific methods, have certain limitations. The former relies too much on the physician's personal experience, techniques and the patient's subjective statements, and the implementation of consultation plans based on individual differences is inefficient; while the latter, although providing objective data, needs to be worn regularly in a fixed position, affecting daily life, and the data collection and analysis process often lacks personalized and in-depth disease analysis. Therefore, it is urgent to combine patient condition information and physician knowledge base to develop an intelligent consultation and recommendation system to improve consultation efficiency and accuracy. Summary of the invention

[0005] In order to overcome the defects of the traditional methods in the above-mentioned prior art, such as excessive reliance on manual experience, strong subjectivity, low consultation efficiency, the need to wear digital devices regularly, and the lack of personalized and in-depth symptom analysis, the present invention provides an intelligent recommendation system for Chinese medicine meridian therapy plans for chronic pain, which improves consultation efficiency and reduces the burden on doctors while realizing personalized consultation. There is no need to wear fixed equipment to collect data, and the operation is simple and easy to promote. Non-professionals can also conduct independent pain consultation and rehabilitation management.

[0006] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0007] An intelligent recommendation system for TCM meridian therapy programs for chronic pain, including: a multimodal data acquisition module, a knowledge graph construction module, an intelligent analysis module and a therapy program recommendation module;

[0008] The multimodal data acquisition module is connected to the intelligent analysis module and the physical therapy plan recommendation module in sequence; the knowledge graph construction module is connected to the physical therapy plan recommendation module;

[0009] The multimodal data acquisition module is used to collect and pre-process the multimodal data of chronic pain patients, wherein the multimodal data includes at least: medical history information, pain location, pain type and personalized action examination feedback data;

[0010] The knowledge graph construction module is used to construct acupoint-finding knowledge graph and human body link relationship graph according to preset TCM meridian therapy experience data;

[0011] The intelligent analysis module is preset with a multimodal attention network, which is used to perform feature extraction, feature fusion and preliminary prediction of acupoints on the preprocessed multimodal data to generate a preliminary associated acupoint set;

[0012] The therapy plan recommendation module is used to obtain a general therapy plan based on the acupuncture point search knowledge graph, and input the general therapy plan, the preliminary associated acupuncture point set and the human body link relationship diagram into a preset optimization calibration network, and finally generate a personalized Chinese medicine meridian therapy plan to complete intelligent recommendation.

[0013] Preferably, the multimodal data is obtained according to the patient's complaint, and the medical record information at least includes: pain area complaint information, accompanying pain area complaint information, pain intensity complaint information, pain time complaint information, pain history complaint information, treatment records and drug use;

[0014] The pain site includes: at least one of the head, neck, shoulder blade, chest, back, waist, pelvis and hip, leg, knee, ankle, foot, elbow, wrist or finger;

[0015] The pain types include: dull pain or sharp pain, wherein dull pain includes at least soreness, distending pain and dull pain, and sharp pain includes at least tearing pain, cutting pain, stabbing pain, burning pain and colic;

[0016] Based on the pain area selected by the patient, the patient completes the movement examination in the horizontal, coronal and sagittal planes according to the preset movement prompts, and performs a VAS score on each movement. The VAS score is used as the patient's personalized movement examination feedback data.

[0017] Preferably, the preprocessing includes: information encoding the multimodal data, the information encoding includes mapping and standardizing the multimodal data according to a predefined data model;

[0018] The preprocessing of the multimodal data after information encoding is completed by removing duplicate data, filling missing values, correcting format errors and processing outliers.

[0019] Preferably, in the knowledge graph construction module, the preset TCM meridian therapy experience data is imported into the graph database to form an acupoint-finding knowledge graph;

[0020] In the knowledge graph construction module, based on the preset TCM meridian therapy experience data and according to the strength characteristics of the human body link association, an adjacency matrix diagram containing at least 90 mutual strength relationships between diagnosis and treatment points is constructed to obtain a human body link relationship diagram; in the human body link relationship diagram, the nodes of the diagram represent different acupuncture points, and the edges represent the direct association relationship between the acupuncture points.

[0021] Preferably, the preset TCM meridian therapy experience data are specifically medical record data related to TCM meridian therapy obtained from multiple sources.

[0022] Preferably, in the intelligent analysis module, the structure of the multimodal attention network includes: an embedding layer, a multi-head self-attention layer, a mapping layer, a mutual attention layer and a first multi-layer perceptron layer connected in sequence;

[0023] The embedding layer is used to extract key features from the preprocessed multimodal data, map discrete variables in the preprocessed multimodal data to a continuous vector space, and obtain a multimodal embedding vector;

[0024] The multi-head self-attention layer is used to perform adaptive feature weighting on the multimodal embedding vector;

[0025] The mapping layer is used to project the multimodal embedding vector after the multi-head self-attention layer to a higher-dimensional vector space to obtain a multimodal high-dimensional vector;

[0026] The mutual attention layer performs feature fusion on the multimodal high-dimensional vector based on the mutual attention mechanism, captures the mutual dependence between different modalities by calculating the similarity weights between each modality, and generates fusion features after weighting;

[0027] The first multi-layer perceptron layer is used to make a preliminary probability prediction of acupoints according to the fusion features, and to group acupoints with the top several predicted probabilities into a preliminary associated acupoint set for output.

[0028] Preferably, in the physical therapy plan recommendation module, the optimization calibration network includes: a graph attention layer and a second multi-layer perceptron layer connected in sequence;

[0029] The general physiotherapy scheme, the set of preliminary associated acupuncture points, and the human body link relationship graph are input into the graph attention layer, and the graph attention layer is used to use the human body link relationship graph to perform relationship modeling and semantic enhancement on the general physiotherapy scheme and the set of preliminary associated acupuncture points, and calculate the deep nonlinear features of the physiotherapy scheme containing the human body link relationship;

[0030] The second multi-layer perceptron layer is used to optimize and calibrate deep nonlinear features, capture the implicit combination patterns of acupoints, output the final acupoint prediction results, and save them as personalized Chinese medicine meridian therapy plans to complete intelligent recommendations.

[0031] Preferably, the system further comprises: a feedback update module; the feedback update module is respectively connected with the knowledge graph construction module, the intelligent analysis module and the physical therapy plan recommendation module;

[0032] The feedback update module is used to update the cave-finding knowledge graph and fine-tune the multimodal attention network and the optimization calibration network.

[0033] Preferably, chronic pain patients are treated according to a personalized TCM meridian therapy program, and the efficacy data is fed back to the feedback update module;

[0034] The preset loss function is calculated based on the therapeutic effect data, the acupuncture knowledge graph is updated according to the preset loss function, and the multimodal attention network and the optimization calibration network are fine-tuned.

[0035] Preferably, the preset loss function is specifically:

[0036] Loss=minΔRI(p)

[0037] Among them, Loss is the preset loss function value; ΔRI(p) is the recovery index obtained based on the efficacy data.

[0038] Compared with the prior art, the technical solution of the present invention has the following beneficial effects:

[0039] The present invention provides a TCM meridian therapy intelligent recommendation system for chronic pain, comprising: a multimodal data acquisition module, a knowledge graph construction module, an intelligent analysis module and a therapy recommendation module; the multimodal data acquisition module is used to collect multimodal data of chronic pain patients and perform preprocessing; the knowledge graph construction module is used to construct an acupuncture point search knowledge graph and a human body link relationship diagram according to preset TCM meridian therapy experience data; a multimodal attention network is preset in the intelligent analysis module, and the multimodal attention network is used to perform feature extraction, feature fusion and preliminary prediction of acupuncture points on the preprocessed multimodal data to generate a set of preliminary associated acupuncture points; an optimization calibration network is preset in the therapy recommendation module, which is used to generate a personalized TCM meridian therapy plan by using a general therapy plan given by the acupuncture point search knowledge graph, a preliminary associated acupuncture point set calculated by a model and a human body link relationship diagram, and complete intelligent recommendation;

[0040] By combining multimodal data and attention-based neural networks, the present invention can more accurately identify the location and type of pain and provide personalized TCM meridian therapy plans. The recommendation accuracy of this system is comparable to that of professional doctors' diagnoses, making the treatment more targeted. At the same time, this system reduces the communication time between doctors and patients in traditional consultations through automated consultation and motion inspection processes, reduces the burden on doctors, and patients can also get treatment advice faster, reducing waiting time, thereby effectively improving consultation efficiency. In addition, based on the constructed knowledge graph, this system can simulate the doctor's consultation experience and provide professional treatment advice. There is no need to wear fixed equipment to collect data. It is simple to operate and easy to promote. This means that in some cases, ordinary people can also use the system for self-treatment or auxiliary treatment, reducing dependence on professional doctors. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is a structural diagram of an intelligent recommendation system for a TCM meridian therapy program for chronic pain provided in Example 1.

[0042] Figure 2 This is a structural diagram of an intelligent recommendation system for a TCM meridian therapy program for chronic pain provided in Example 2.

[0043] Figure 3 This is a workflow diagram of an intelligent recommendation system for a TCM meridian therapy program for chronic pain provided in Example 2.

[0044] Figure 4 This is a schematic diagram of the system model pre-training provided in Example 2.

[0045] Figure 5 This is a schematic diagram of the human body movement inspection provided in Example 2.

[0046] Figure 6 Schematic diagram of the multi-head self-attention layer provided in Example 2.

[0047] Figure 7 This is a schematic diagram of the alignment of the patient complaint data provided in Example 2.

[0048] Figure 8 This is a schematic diagram of the cave-finding knowledge graph provided in Example 2.

[0049] Fig. 9 This is a schematic diagram of the human body link relationship provided in Example 2.

[0050] Fig.10 This is a schematic diagram of the optimization calibration network structure and reasoning process provided in Example 2.

[0051] Fig.11 Schematic diagram of updating the knowledge graph and fine-tuning the model parameters based on the feedback provided in Example 2.

[0052] Fig.12 This is a comparison chart of the gender and age group statistics (number of people) of the experimental group and the control group provided in Example 3.

[0053] Fig.13 This is a comparison chart of the pain location statistics (number of people) of the experimental group and the control group patients provided in Example 3.

[0054] Fig.14 This is a schematic diagram of the intelligent Chinese medicine meridian therapy instrument provided in Example 3. DETAILED DESCRIPTION

[0055] The drawings are for illustrative purposes only and should not be construed as limiting the present patent;

[0056] In order to better illustrate the present embodiment, some parts in the drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product;

[0057] It is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.

[0058] The technical solution of the present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0059] Example 1

[0060] like Figure 1 As shown, this embodiment provides a TCM meridian therapy program intelligent recommendation system for chronic pain, including: a multimodal data acquisition module, a knowledge graph construction module, an intelligent analysis module and a therapy program recommendation module;

[0061] The multimodal data acquisition module is connected to the intelligent analysis module and the physical therapy plan recommendation module in sequence; the knowledge graph construction module is connected to the physical therapy plan recommendation module;

[0062] The multimodal data acquisition module is used to collect and pre-process the multimodal data of chronic pain patients, wherein the multimodal data includes at least: medical history information, pain location, pain type and personalized action examination feedback data;

[0063] The knowledge graph construction module is used to construct acupoint-finding knowledge graph and human body link relationship graph according to preset TCM meridian therapy experience data;

[0064] The intelligent analysis module is preset with a multimodal attention network, which is used to perform feature extraction, feature fusion and preliminary prediction of acupoints on the preprocessed multimodal data to generate a preliminary associated acupoint set;

[0065] The therapy plan recommendation module is used to obtain a general therapy plan based on the acupuncture point search knowledge graph, and input the general therapy plan, the preliminary associated acupuncture point set and the human body link relationship diagram into a preset optimization calibration network, and finally generate a personalized Chinese medicine meridian therapy plan to complete intelligent recommendation.

[0066] In the specific implementation process, this system constructs acupuncture point knowledge graph based on traditional Chinese medicine meridian therapy experience data, and at the same time converts the human body link relationship into a mathematical language that can be understood by the network to form a human body link reasoning rule. The system implements the knowledge graph and human body link reasoning rule established above, combines the patient's motion examination, the main complaint medical record information and the associated acupuncture point set calculated by the model, and finally forms a personalized treatment plan;

[0067] The system as a whole is centered on the fusion analysis of multimodal data. Through multimodal feature extraction and fusion, it accurately analyzes the patient's pain characteristics, and combines the knowledge graph and human body association link graph to optimize and calibrate the personalized consultation plan. The detailed steps are as follows:

[0068] The multimodal data collection module is used to collect multimodal data such as the patient's main complaint, movement examination, pain level and pain coronal plane;

[0069] 1) Chief complaint information: The patient enters the chief complaint into the electronic medical record, which includes the main pain area, associated pain area, pain intensity, pain duration, previous pain history, etc., to initially establish the patient's electronic medical record;

[0070] 2) Movement test: assess pain and disability by asking patients to perform specific movements and use a visual analogue scale (VAS) to quantify pain intensity;

[0071] VAS uses a straight line (usually 10 cm or 100 mm in length) to indicate the degree of pain, with one end of the line representing "no pain" and the other end representing "the most severe pain"; patients mark the corresponding position on the straight line according to the degree of pain they feel; medical staff assess the degree of pain based on the position of the patient's mark. The result of the VAS score can be a continuous value, so it can reflect the changes in pain more carefully; VAS scores usually divide pain into 10 levels, with 0 points indicating no pain, 1-3 points indicating mild pain, 4-6 points indicating moderate pain, and 7-10 points indicating severe pain; this score is used to quantify the changes in pain before and after treatment, intuitively evaluate the treatment effect of the intelligent Chinese medicine physiotherapy instrument, and verify the accuracy of the system-generated solution;

[0072] Based on the clinical experience and knowledge of professional physicians, the above information is converted into model input, which is divided into the following steps:

[0073] Preprocessing: Digitally encode the patient's chief complaint information, movement test results, pain level, pain distribution and other multimodal data; for example, the pain site can be encoded as different numbers, and the pain level can be quantified according to the VAS score; after encoding, input into the multimodal attention network in the intelligent analysis module;

[0074] Feature extraction: Use a multimodal attention network to extract key features from the encoded information; for example, extract abnormal values ​​of joint range of motion from action checks, and extract the main area of ​​pain from pain distribution;

[0075] Feature weighting: Using the multi-head self-attention mechanism, the network can adaptively increase its attention to key information, such as joint examination in joint pain;

[0076] Feature fusion: Based on the mutual attention mechanism, different pain disease information encoding vectors are fused;

[0077] Preliminary prediction: Project and reduce the dimensionality of the fused features through a multi-layer perceptron, and output a unique set of preliminary associated acupuncture points that match the current patient's condition;

[0078] The knowledge graph construction module is used to build a knowledge graph based on the consultation experience of professional doctors, and the pain location, pain nature, and movement test results are linked to possible treatment plans. For example, if the patient complains of low back pain and the pain is distributed on the coronal plane, the knowledge graph can search for a general treatment plan that meets the needs of patients with low back pain and pain distribution on the coronal plane. At the same time, in this module, the human body link association diagram is obtained based on Bai's experience summary.

[0079] The unique set of preliminary associated acupoints that are consistent with the current patient's condition output by the intelligent analysis module (the acupoints associated with the patient's condition in this treatment) is combined with the general physiotherapy plan (without personalized differences) searched by the acupoint search knowledge graph and the human body link association relationship diagram to generate a personalized treatment plan; in this embodiment, the graph attention network is used to optimize and correct the acupoint features and finally output a personalized physiotherapy plan to ensure that the treatment plan is consistent with the patient's specific physical condition;

[0080] This system provides a more accurate and personalized treatment plan. It improves the efficiency of consultation and reduces the burden on doctors while realizing personalized consultation. There is no need to wear fixed equipment to collect data during the motion inspection stage. The whole process is simple to operate and easy to promote. Non-professionals can also conduct independent pain consultation and rehabilitation management.

[0081] Example 2

[0082] like Figure 2 As shown, this embodiment provides a TCM meridian therapy program intelligent recommendation system for chronic pain, including: a multimodal data acquisition module, a knowledge graph construction module, an intelligent analysis module, a therapy program recommendation module and a feedback update module;

[0083] The multimodal data acquisition module is connected to the intelligent analysis module and the physical therapy plan recommendation module in sequence; the knowledge graph construction module is connected to the physical therapy plan recommendation module;

[0084] The multimodal data acquisition module is used to collect and pre-process the multimodal data of chronic pain patients, wherein the multimodal data includes at least: medical history information, pain location, pain type and personalized action examination feedback data;

[0085] The knowledge graph construction module is used to construct acupoint-finding knowledge graph and human body link relationship graph according to preset TCM meridian therapy experience data;

[0086] The intelligent analysis module is preset with a multimodal attention network, which is used to perform feature extraction, feature fusion and preliminary prediction of acupoints on the preprocessed multimodal data to generate a preliminary associated acupoint set;

[0087] The physiotherapy plan recommendation module is used to obtain a general physiotherapy plan based on the acupuncture point search knowledge map, and input the general physiotherapy plan, the preliminary associated acupuncture point set and the human body link relationship diagram into a preset optimization calibration network, and finally generate a personalized Chinese medicine meridian physiotherapy plan to complete intelligent recommendation;

[0088] The feedback update module is used to update the cave-finding knowledge graph and fine-tune the multimodal attention network and the optimization calibration network;

[0089] In this embodiment, chronic pain patients are treated according to a personalized TCM meridian therapy program, and the efficacy data is fed back to the feedback update module;

[0090] Calculate the preset loss function based on the efficacy data, update the acupuncture knowledge graph based on the preset loss function, and fine-tune the multimodal attention network and the optimization calibration network;

[0091] The preset loss function is specifically:

[0092] Loss=minΔRI(p)

[0093] Among them, Loss is the preset loss function value; ΔRI(p) is the rehabilitation index obtained based on the efficacy data;

[0094] The multimodal data is obtained according to the patient's complaint, and the medical record information at least includes: pain area complaint information, accompanying pain area complaint information, pain intensity complaint information, pain time complaint information, pain history complaint information, treatment records and drug use;

[0095] The pain site includes: at least one of the head, neck, shoulder blade, chest, back, waist, pelvis and hip, leg, knee, ankle, foot, elbow, wrist or finger;

[0096] The pain types include: dull pain or sharp pain, wherein dull pain includes at least soreness, distending pain and dull pain, and sharp pain includes at least tearing pain, cutting pain, stabbing pain, burning pain and colic;

[0097] Based on the pain area selected by the patient, the patient completes the movement check in the horizontal plane, coronal plane and sagittal plane according to the preset movement prompts, and performs a VAS score for each movement, and the VAS score is used as the patient's personalized movement check feedback data;

[0098] The preprocessing includes: information encoding the multimodal data, wherein the information encoding includes mapping and standardizing the multimodal data according to a predefined data model;

[0099] The multimodal data after information encoding is preprocessed by removing duplicate data, filling missing values, correcting format errors and processing outliers;

[0100] In the knowledge graph construction module, the preset TCM meridian therapy experience data is imported into the graph database to form a knowledge graph for acupuncture point search;

[0101] In the knowledge graph construction module, based on the preset TCM meridian therapy experience data and the strength characteristics of the human body link association, an adjacency matrix diagram containing at least 90 strong and weak relationships between diagnosis and treatment points is constructed to obtain a human body link relationship diagram; in the human body link relationship diagram, the nodes of the diagram represent different acupuncture points, and the edges represent the direct association relationship between acupuncture points;

[0102] The preset TCM meridian therapy experience data is specifically medical record data related to TCM meridian therapy obtained from multiple sources; in this embodiment, medical record data related to TCM meridian therapy is obtained from two sources: the hospital online system and the doctor's offline interview; the TCM meridian therapy experience data in this embodiment is specifically related to medical record data of Bai's skin acupuncture therapy;

[0103] In the intelligent analysis module, the structure of the multimodal attention network includes: an embedding layer, a multi-head self-attention layer, a mapping layer, a mutual attention layer and a first multi-layer perceptron layer connected in sequence;

[0104] The embedding layer is used to extract key features from the preprocessed multimodal data, map discrete variables in the preprocessed multimodal data to a continuous vector space, and obtain a multimodal embedding vector;

[0105] The multi-head self-attention layer is used to perform adaptive feature weighting on the multimodal embedding vector;

[0106] The mapping layer is used to project the multimodal embedding vector after the multi-head self-attention layer to a higher-dimensional vector space to obtain a multimodal high-dimensional vector;

[0107] The mutual attention layer performs feature fusion on the multimodal high-dimensional vector based on the mutual attention mechanism, captures the mutual dependence between different modalities by calculating the similarity weights between each modality, and generates fusion features after weighting;

[0108] The first multi-layer perceptron layer is used to make a preliminary probability prediction of acupoints according to the fusion features, and to form a preliminary associated acupoint set from a number of acupoints ranked top in the prediction probability for output;

[0109] In the physical therapy plan recommendation module, the optimization calibration network includes: a graph attention layer and a second multi-layer perceptron layer connected in sequence;

[0110] The general physiotherapy scheme, the set of preliminary associated acupuncture points, and the human body link relationship graph are input into the graph attention layer, and the graph attention layer is used to use the human body link relationship graph to perform relationship modeling and semantic enhancement on the general physiotherapy scheme and the set of preliminary associated acupuncture points, and calculate the deep nonlinear features of the physiotherapy scheme containing the human body link relationship;

[0111] The second multi-layer perceptron layer is used to optimize and calibrate deep nonlinear features, capture the implicit combination patterns of acupoints, output the final acupoint prediction results, and save them as personalized Chinese medicine meridian therapy plans to complete intelligent recommendations.

[0112] In the specific implementation process, Figure 3 As shown, this system constructs acupuncture point knowledge graph based on the experience data of traditional Chinese medicine meridian therapy (this embodiment uses the experience of Bai's therapy, which achieves the effect of relieving pain and regulating meridian qi and blood by applying weak electrical signals to specific acupuncture points on the skin surface. It is suitable for a variety of chronic pain problems, such as neuralgia, stomachache, biliary colic, etc.), and at the same time converts the experience data into mathematical language understandable by the network to form human body link reasoning rules based on Bai's therapy experience, so that the system can autonomously learn the reasoning relationship of acupuncture point treatment points based on the knowledge graph established above, and finally form a personalized treatment plan by combining the patient's action examination and the main complaint medical record information;

[0113] Before making a formal recommendation, Figure 4 As shown, the neural network model in the system needs to be pre-trained, and the process is: according to a large number of treatment cases of doctors, the model in the system is iteratively trained, and the difference between the manually determined physical therapy plan and the personalized Chinese medicine meridian physical therapy plan generated by the system is calculated according to the similarity loss function, and the loss function uses the cross entropy loss; during the training stage, the system ensures that after learning a large number of cases, the recommendation system can achieve physical therapy plan recommendations that are basically consistent with those of doctors;

[0114] The system as a whole is centered on the fusion analysis of multimodal data. Through multimodal feature extraction and data fusion, it accurately analyzes the patient's pain characteristics, and combines knowledge graphs and graph neural networks to optimize and calibrate personalized consultation plans. The detailed steps are as follows:

[0115] First, the multimodal data collection module is used to collect multimodal data of patients with chronic pain, including medical history information, pain location, pain type, and personalized action examination feedback data;

[0116] In this embodiment, multimodal data is constructed based on the patient's main complaint, and the medical record information at least includes: pain area main complaint information, accompanying pain area main complaint information, pain intensity main complaint information, pain time main complaint information, pain history main complaint information, treatment records and drug use; the recommendation system can comprehensively understand the patient's health status and individual differences in the consultation plan from this information, so as to formulate a personalized treatment plan;

[0117] The pain location refers to the distribution and manifestation of pain on different planes of the body. In this embodiment, the human body is divided into 14 main sections, including: head, neck, shoulder blade, chest, back, waist, pelvis and hip, leg, knee, ankle, foot, elbow, wrist and finger. Knowing the pain location helps the recommendation system locate the source of pain and recommend corresponding treatment plans according to the source.

[0118] Pain types include: dull pain or sharp pain, where dull pain includes at least soreness, distending pain and dull pain, and sharp pain includes at least tearing pain, cutting pain, stabbing pain, burning pain and colic. The recommendation system helps to select a consultation plan that meets the differences in different pain types by understanding the pain type.

[0119] Based on the pain area selected by the patient, the system automatically recommends motion examination plans in the horizontal, coronal, and sagittal planes, and the patient follows the motion prompts (such as Figure 5 The system completes the motion examination in the horizontal, coronal and sagittal planes, and performs VAS scoring for each motion, and uses the VAS score as the patient's personalized motion examination feedback data; through comprehensive analysis of the motion examination data in the three planes, the system can accurately locate the pain area and its impact on specific movements, quantify the degree of motion limitation of the patient, and formulate a personalized treatment plan based on this;

[0120] Then, the multimodal data is preprocessed, including: information encoding of the multimodal data, which includes mapping and standardizing the multimodal data according to a predefined data model; then, the multimodal data after information encoding is removed from duplicate data, filled with missing values, corrected format errors, and processed outliers to complete the preprocessing;

[0121] The design of the embedding layer is mainly to convert discrete pain symptom information into a low-dimensional continuous vector representation and solve the consistency problem in data format; the embedding layer captures the semantic relationship between pain symptom information by mapping these discrete variables into a continuous vector space; the structure of the embedding layer can be regarded as a lookup table, which maps each discrete category to a vector of fixed dimension; its core is a trainable weight matrix, each row in the weight matrix represents the embedding vector of a category, and the specific formula is as follows:

[0122] e i =W[x i ],i∈[0,N]

[0123] Wherein, N=4 represents the total number of pain disease information (i.e., the total number of modal types of multimodal data), x i Represents each pain condition information, e i represents the vector encoded by the embedding layer, and W represents the weight matrix;

[0124] Then the vector encoded by the embedding layer is input into the multimodal attention network in the intelligent analysis module;

[0125] In the previous step, the pain symptom information is separately encoded into a feature vector through the embedding layer. The data itself contains a lot of useless components and does not selectively pay attention to the data of the current modality. Therefore, the multimodal attention layer uses a multi-head self-attention mechanism to adaptively weight its own modal data, enhance the signal-to-noise ratio of data features, and increase attention to the feature information that has a significant effect on the pain acupoints. The use of a multi-head design allows each attention mechanism to optimize the different feature parts of each modal data, thereby balancing the deviations that may be caused by the same attention mechanism, allowing the modal data to focus on multi-angle features. The specific layer structure is as follows: Figure 6 As shown;

[0126] In the multimodal attention layer, the input is the encoding vector of each modality. First, the feature vector is multiplied with the weight matrix Wq, Wk, and Wv to obtain the query vector, key vector, and value vector. Their respective meanings are: query vector: represents the "query" initiated for the current information; key vector: indicates that there are corresponding keys in the input feature vector, and each key represents its related features; value vector: represents the actual data or features associated with each input, and the model finally uses these values ​​to generate output;

[0127] Then, the correlation score between the query vector and the key vector is calculated as the weighting coefficient. After these scores are passed through the activation function to obtain the attention weight score, they are then Hadamard-producted with the value vector to obtain the pain vector weighted by these weights, so that the current modal data can be focused on the pain input-related features related to the current query. This mechanism makes the attention mechanism very effective in capturing important features and can improve the model's ability to understand complex disease information, thereby providing more reliable data support for accurate diagnosis and the design of personalized treatment plans.

[0128] Then, the mutual attention layer is used to fuse the chief complaint data. Its main function is to align and fuse the multi-modal chief complaint information, solve the differences in modal characteristics and distribution, and ensure that the output features are efficiently represented in a unified space. Its structure is as follows: Figure 7As shown; the mutual attention layer performs feature fusion on the multimodal high-dimensional vector based on the mutual attention mechanism, and captures the interdependence between different modalities by calculating the similarity weights between each modality, and generates weighted fusion features; specifically, the input multimodal data includes the patient's chief complaint information (such as pain area, accompanying symptoms, pain intensity, pain time, and action examination feedback data) and case information (such as pain history, treatment records, and drug use); these input data are first preprocessed and encoded to form multiple high-dimensional vectors, and then, through the mutual attention mechanism, the model can interact between different modalities, pay attention to and adjust the influence of each modality, and finally generate fusion features; these fusion features integrate the comprehensive information of the patient's chief complaint information and medical record information;

[0129] The characteristics of pathological information features are that the data presents discrete distribution and the feature dimension is low. In order to enhance the learning ability of the model, in this layer, the pathological information features are first projected to a high-dimensional space through the mapping layer; then, the multimodal pathological information is further fused through the mutual attention network, and the association between different data features is established to capture the mutual influence and interaction between them; the core idea of ​​the mutual attention mechanism is to guide the feature extraction of another modality by paying attention to the important information in one modality, thereby playing a vital role in multimodal fusion tasks or cross-modal learning tasks; finally, the high-order features extracted from different modal data are further nonlinearly combined and extracted using multi-layer perceptrons and nonlinear activation functions, and the multi-layer perceptron is used to assign the corresponding probability of meeting the treatment plan to the 90 consultation points of the human body constructed by professional physicians’ experience, and the acupuncture points with probability values ​​greater than the threshold are output to obtain a set of preliminary associated acupuncture points; this set does not integrate the human body link association strength and weakness relationship information designed by professional physicians’ experience, and the subsequent network needs to be further adjusted according to expert experience;

[0130] Then, the knowledge graph construction module is used to build a knowledge graph for acupuncture points based on the consultation experience of professional doctors, linking the pain location, pain nature, and movement test results with possible treatment plans. For example, if the patient complains of low back pain and the pain is distributed on the coronal plane, the knowledge graph can point to a specific basic treatment plan for the low back.

[0131] Specifically, in the knowledge graph construction module, the preset TCM meridian therapy experience data is imported into the graph database to form a knowledge graph for acupuncture points, including nodes such as pain, intensity, location, treatment plan, and their relationships. Figure 8As shown in the figure, according to the graph, a basic treatment plan related to the current condition without personalized differences can be found; in addition, in the knowledge graph construction module, based on the human link inference rules of Bai's physical therapy experience, according to the strength and weakness characteristics of the human link association, an adjacency matrix diagram containing the strength and weakness relationships between at least 90 diagnosis and treatment points is constructed, as shown in Fig. 9 As shown, the nodes of the graph represent different acupuncture points, and the edges represent the direct associations between acupuncture points. Following the acupuncture point constraints of Bai's therapy (each truncation has 2-3 diagnosis and treatment points in the horizontal plane, coronal plane and sagittal plane; the distal points are the wrist and ankle, with a total of 12 diagnosis and treatment points), the acupuncture point search logic relationship of Bai's therapy is obtained. This module converts the experience of Bai's therapy into a mathematical language that can be understood by the network, forming knowledge rules.

[0132] Finally, the therapy plan recommendation module uses the associated acupuncture point set inferred by the intelligent analysis module, combined with the basic treatment plan and human link association diagram obtained by searching the knowledge graph constructed by the clinical experience of professional physicians, to calculate and generate a personalized treatment plan; in this embodiment, the graph attention network is used to optimize and correct the preliminary treatment plan to ensure that the treatment plan meets the patient's specific physical condition, such as Fig.10 As shown in the figure, the associated acupoint feature points and the general physiotherapy plan obtained by the knowledge graph search are input into the graph attention layer together. The graph attention layer is used to use the human body link relationship graph to model and semantically enhance the relationship between the general physiotherapy plan and the preliminary associated acupoints, and calculate the deep nonlinear features of the physiotherapy plan containing the human body link relationship. According to the three elements of the self-attention mechanism, the graph attention also contains three elements: Q, K, and V. Q is the feature vector of the central node, K is the feature vector of all neighboring nodes, and V is the new feature vector of the central node after the aggregation operation.

[0133] The role of optimization and calibration is to calibrate and optimize the reasoning results in combination with the actual experience of the physician when generating the final treatment plan. In the physiotherapy plan recommendation module, the graph attention layer and the multi-layer perceptron work together to complete the optimization and calibration of the treatment acupuncture points. First, the preliminary treatment plan is adjusted using the above-mentioned graph information and the graph attention layer. By introducing graph information and the graph attention network to capture the relationship and feature information between acupuncture points, the model can pay more attention to important neighbor nodes, thereby improving the model's ability to provide personalized treatment plans, and aggregating the feature information of neighbor nodes to obtain the feature information of the current node, making feature transfer more efficient, and better capturing the relationship between nodes and changes in feature information, thereby improving the generalization ability of the model. Then, through the multi-layer perceptron, the output of the graph attention layer is subjected to deep nonlinear feature extraction to further capture the implicit pattern of acupuncture point combination and optimize treatment decisions. By filtering invalid features, multi-layer mapping and feature calibration, the multi-layer perceptron outputs the final set of treatment acupuncture points. Overall, the graph attention layer is responsible for "relationship modeling and semantic enhancement", and the multi-layer perceptron is responsible for "feature optimization and personalized decision-making". The combination of the two ensures that the plan is both scientific and accurate and meets personalized needs.

[0134] After a series of network architectures, the network can generate a personalized treatment plan based on the patient's main complaint information and the professional physician's experience in traditional Chinese medicine. This plan not only integrates the physician's experience to establish the relationship between the human meridian structure and the consultation points, but also uses the personalized plan given by the professional physician consultation system as supervision to ensure that the network can provide a physical therapy plan that meets the patient's needs.

[0135] To further optimize the solution, this embodiment designs a feedback update mechanism. After the patient receives treatment, the system collects efficacy data (such as pain relief, improvement of movement restrictions, etc.), dynamically updates the Bai's meridian acupoint experience knowledge map, and continuously improves the accuracy of the acupoint search network model and the quality of the personalized treatment plan;

[0136] Specifically, the learning process of the model to recommend Bai's skin acupuncture consultation technology mainly consists of two parts: forward reasoning and feedback update;

[0137] Based on multimodal information input, the model gradually generates a forward reasoning process for a personalized Bai's skin acupuncture consultation plan. First, the patient's chief complaint data (such as medical history information, pain location, pain type, and movement examination data) is input into the network; then the input information is encoded using the embedding layer to convert discrete pain symptom information into a low-dimensional continuous vector representation, and a multimodal attention network is used to fuse a variety of different pain symptom information encoding vectors to capture the semantic relationship between pain symptom information; then based on the learned pain features and combined with the medical knowledge graph of Bai's skin acupuncture, the model can generate a basic treatment plan, and use graph information and graph attention network to adjust the basic treatment plan, thereby improving the model's ability to provide personalized treatment plans; finally, the network can generate a personalized treatment plan that integrates the patient's chief complaint information and the professional physician's Chinese medicine experience. At this point, the model completes the forward reasoning process and also learns the fusion relationship of different modal features and the deep association between symptoms and acupoints from the multimodal input data and the Bai's experience acupoint knowledge graph;

[0138] Feedback update is the core mechanism for this model to learn real-life consultation techniques and gradually improve (e.g. Fig.11 As shown in the figure); after the model generates a consultation plan, the patient receives treatment according to the recommended acupoints and records the treatment effect through efficacy evaluation methods; these efficacy data, such as the degree of pain relief and recovery after treatment, will be input into the system as feedback information for further optimization of the model; after the feedback data enters the model, the calibration results are first deeply analyzed through the graph attention mechanism to extract more accurate feature information from the Bai's empirical acupoint knowledge graph; at the same time, the model further adjusts the parameters in each module so that the model can more accurately align the relationship between the patient's symptoms and acupoints; through this dynamic update process, the system gradually learns how to better deal with complex or special cases and improves its ability to handle diverse patient needs; in addition, feedback information is also used to update the Bai's empirical knowledge graph; the system will re-evaluate the applicability of acupoints based on the actual feedback of the treatment effect, strengthen the record of efficient acupoints, and mark the points with poor efficacy and reduce their recommendation priority; through the dynamic adjustment of the knowledge graph, the model can gradually form a more personalized and targeted consultation path;

[0139] Through forward reasoning and feedback updates, the system can combine the patient's initial symptom information and feedback data to generate an optimized treatment plan based on the patient's personalized symptom information and Bai's TCM experience, while continuously improving its own knowledge graph representation to enhance the understanding of the deep connection between symptoms and acupoints. The two build a closed-loop system, and as patient samples accumulate, the model continues to learn from new cases and real-time treatment data, which can not only improve the accuracy and personalization of the consultation plan, but also optimize its own knowledge representation and decision-making logic through continuous learning, forming a more dynamic and intelligent consultation recommendation system.

[0140] This system provides a more accurate and personalized treatment plan. It improves the efficiency of consultation and reduces the burden on doctors while realizing personalized consultation. There is no need to wear fixed equipment to collect data during the motion inspection stage. The whole process is simple to operate and easy to promote. Non-professionals can also conduct independent pain consultation and rehabilitation management.

[0141] Example 3

[0142] This embodiment provides a verification experiment to verify the effectiveness of the recommendation system described in Embodiment 1 or 2.

[0143] In the specific implementation process, this experiment recruited 128 chronic pain patients for consultation, of which the experimental group consisted of 68 patients, who were consulted using the recommendation system provided in Example 1 or 2; the control group consisted of 60 patients, who were personally consulted by professional physicians; the statistical information of the patients' gender, age group, and pain location was as follows: Fig.12 and Fig.13 As shown in the figure, it can be seen that there is no statistically significant difference in gender, age group and pain location between the experimental group and the control group. The degree of pain relief was calculated by VAS scores before and after treatment, and this was used as efficacy data to verify the accuracy and effectiveness of the consultation effect.

[0144] Equipment Introduction:

[0145] The core equipment of this experiment is the intelligent Chinese medicine meridian therapy instrument (such as Fig.14 As shown), it has built-in Bai's experience knowledge graph and multi-modal consultation solution recommendation network, integrated chronic pain management consultation system, and supports multi-point electrical stimulation treatment; the device adopts a non-invasive design, using electrodes to replace traditional acupuncture stimulation, and can accurately stimulate 10 independent treatment points. Each point provides 40 levels of current adjustment, covering multiple treatment modes such as sparse and dense waves, intermittent waves and continuous waves; during the treatment process, the device can dynamically monitor the patient's physiological reactions and generate feedback data to provide support for subsequent optimization of consultation solutions; the device is used by professional physicians, and in the following comparative experiments, the same treatment device is used. The difference is that the experimental group uses the built-in chronic pain management consultation system to recommend treatment plans, while the control group is given a treatment plan by a professional physician based on his own experience;

[0146] Operation process:

[0147] The patient first fills in personal information and medical records, including pain location, pain type, duration and VAS score (visual analogue scale); VAS score is an internationally used pain intensity quantification tool. Patients subjectively express their pain level by marking a straight line from "no pain" (0 points) to "severe pain" (10 points); 0 points means no pain, 1-3 points means mild pain, 4-6 points means moderate pain, and 7-10 points means severe pain; this score is used to quantify the changes in pain before and after treatment, intuitively evaluate the treatment effect of the intelligent Chinese medicine physiotherapy instrument, and verify the accuracy of the system-generated solution;

[0148] Patients in the experimental group were required to undergo movement checks and pain induction assessments. The intelligent TCM meridian therapy instrument accurately located the treatment points based on the data input by the patients and the consultation plan generated by the system, and implemented electrical stimulation treatment by applying electrodes. During the treatment, the instrument adjusted the treatment parameters in real time through multi-gear adjustment and multi-channel control to ensure personalized consultation effects. After the treatment, the patients filled out the consultation records again to evaluate the pain relief, and combined the treatment data recorded by the instrument for effect analysis. For the patients in the control group, professional physicians personally diagnosed and treated them according to the consultation results. After the treatment, the patients filled out the consultation records again to evaluate the pain relief.

[0149] Statistical analysis of the data after diagnosis and physical therapy of patients in the experimental group and the control group:

[0150] The results showed that among the patients who were diagnosed and treated with the intelligent TCM meridian therapy device, 85.29% of them achieved a 40% to 100% pain relief, while 80% of the patients who were personally consulted by professional physicians achieved a 40% to 100% relief. Among them, 29.41% of the patients who were consulted with the device achieved a 70% to 100% relief, while the proportion of patients consulted by professional physicians was 18.33%, indicating that the effect of the consultation system designed by this patent is better than that of traditional physician consultation. In addition, the vast majority of patients reported that the pain area was significantly reduced, the range of motion was increased, and the treatment process was comfortable and easy to accept.

[0151] The statistical results are shown in Table 1:

[0152] Table 1 Comparison of the degree of relief from TCM physiotherapy after diagnosis between the experimental group and the control group

[0153]

[0154] Experimental results and discussion:

[0155] The experimental results (Table 1) show that the consultation plan generated by the intelligent Chinese medicine meridian therapy instrument based on the recommendation system in Example 1 or 2 is slightly better than the plan formulated by professional physicians in person in terms of efficacy, and the patient's pain relief and functional recovery effects are both as expected; the verification results prove that the recommendation system in Example 1 or 2 can effectively replace traditional doctor consultations, has a wide range of promotion and application value, can provide safe and efficient treatment plans for patients with chronic pain, and significantly reduce the workload of physicians.

[0156] The same or similar reference numerals correspond to the same or similar components;

[0157] The terms used in the drawings to describe positional relationships are only used for illustrative purposes and should not be construed as limiting this patent;

[0158] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the embodiments here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. An intelligent recommendation system for TCM meridian therapy for chronic pain, characterized in that: include: Multimodal data collection module, knowledge graph construction module, intelligent analysis module and physical therapy plan recommendation module; The multimodal data acquisition module is connected to the intelligent analysis module and the physical therapy plan recommendation module in sequence; the knowledge graph construction module is connected to the physical therapy plan recommendation module; The multimodal data acquisition module is used to collect and pre-process the multimodal data of chronic pain patients, wherein the multimodal data includes at least: medical history information, pain location, pain type and personalized action examination feedback data; The knowledge graph construction module is used to construct acupoint-finding knowledge graph and human body link relationship graph according to preset TCM meridian therapy experience data; The intelligent analysis module is preset with a multimodal attention network, which is used to perform feature extraction, feature fusion and preliminary prediction of acupoints on the preprocessed multimodal data to generate a preliminary associated acupoint set; The therapy plan recommendation module is used to obtain a general therapy plan based on the acupuncture point search knowledge graph, and input the general therapy plan, the preliminary associated acupuncture point set and the human body link relationship diagram into a preset optimization calibration network, and finally generate a personalized Chinese medicine meridian therapy plan to complete intelligent recommendation.

2. According to claim 1, a TCM meridian therapy intelligent recommendation system for chronic pain, characterized in that: The multimodal data is obtained according to the patient's complaint, and the medical record information at least includes: pain area complaint information, accompanying pain area complaint information, pain intensity complaint information, pain time complaint information, pain history complaint information, treatment records and drug use; The pain site includes: at least one of the head, neck, shoulder blade, chest, back, waist, pelvis and hip, leg, knee, ankle, foot, elbow, wrist or finger; The pain types include: dull pain or sharp pain, wherein dull pain includes at least soreness, distending pain and dull pain, and sharp pain includes at least tearing pain, cutting pain, stabbing pain, burning pain and colic; Based on the pain area selected by the patient, the patient completes the movement examination in the horizontal, coronal and sagittal planes according to the preset movement prompts, and performs a VAS score on each movement. The VAS score is used as the patient's personalized movement examination feedback data.

3. According to claim 1, a TCM meridian therapy intelligent recommendation system for chronic pain, characterized in that: The preprocessing includes: information encoding the multimodal data, wherein the information encoding includes mapping and standardizing the multimodal data according to a predefined data model; The preprocessing of the multimodal data after information encoding is completed by removing duplicate data, filling missing values, correcting format errors and processing outliers.

4. The intelligent recommendation system for TCM meridian therapy for chronic pain according to claim 1, characterized in that: In the knowledge graph construction module, the preset TCM meridian therapy experience data is imported into the graph database to form a knowledge graph for acupuncture point search; In the knowledge graph construction module, based on the preset TCM meridian therapy experience data and according to the strength characteristics of the human body link association, an adjacency matrix diagram containing at least 90 mutual strength relationships between diagnosis and treatment points is constructed to obtain a human body link relationship diagram; in the human body link relationship diagram, the nodes of the diagram represent different acupuncture points, and the edges represent the direct association relationship between the acupuncture points.

5. The intelligent recommendation system for TCM meridian therapy for chronic pain according to claim 4, characterized in that: The preset TCM meridian therapy experience data specifically refers to medical record data related to TCM meridian therapy obtained from multiple sources.

6. The intelligent recommendation system for TCM meridian therapy for chronic pain according to claim 1, characterized in that: In the intelligent analysis module, the structure of the multimodal attention network includes: an embedding layer, a multi-head self-attention layer, a mapping layer, a mutual attention layer and a first multi-layer perceptron layer connected in sequence; The embedding layer is used to extract key features from the preprocessed multimodal data, map discrete variables in the preprocessed multimodal data to a continuous vector space, and obtain a multimodal embedding vector; The multi-head self-attention layer is used to perform adaptive feature weighting on the multimodal embedding vector; The mapping layer is used to project the multimodal embedding vector after the multi-head self-attention layer to a higher-dimensional vector space to obtain a multimodal high-dimensional vector; The mutual attention layer performs feature fusion on the multimodal high-dimensional vector based on the mutual attention mechanism, captures the mutual dependence between different modalities by calculating the similarity weights between each modality, and generates fusion features after weighting; The first multi-layer perceptron layer is used to make a preliminary probability prediction of acupoints according to the fusion features, and to group acupoints with the top several predicted probabilities into a preliminary associated acupoint set for output.

7. The intelligent recommendation system for TCM meridian therapy for chronic pain according to claim 1, characterized in that: In the physical therapy plan recommendation module, the optimization calibration network includes: a graph attention layer and a second multi-layer perceptron layer connected in sequence; The general physiotherapy scheme, the set of preliminary associated acupuncture points, and the human body link relationship graph are input into the graph attention layer, and the graph attention layer is used to use the human body link relationship graph to perform relationship modeling and semantic enhancement on the general physiotherapy scheme and the set of preliminary associated acupuncture points, and calculate the deep nonlinear features of the physiotherapy scheme containing the human body link relationship; The second multi-layer perceptron layer is used to optimize and calibrate deep nonlinear features, capture the implicit combination patterns of acupoints, output the final acupoint prediction results, and save them as personalized Chinese medicine meridian therapy plans to complete intelligent recommendations.

8. An intelligent recommendation system for TCM meridian therapy for chronic pain according to any one of claims 1 to 7, characterized in that: The system further includes: a feedback update module; the feedback update module is respectively connected to the knowledge graph construction module, the intelligent analysis module and the physical therapy plan recommendation module; The feedback update module is used to update the cave-finding knowledge graph and fine-tune the multimodal attention network and the optimization calibration network.

9. The intelligent recommendation system for TCM meridian therapy for chronic pain according to claim 8, characterized in that: Chronic pain patients receive treatment based on personalized TCM meridian therapy plans, and feedback efficacy data to the feedback update module; The preset loss function is calculated based on the therapeutic effect data, the acupuncture point search knowledge graph is updated based on the preset loss function, and the multimodal attention network and the optimization calibration network are fine-tuned.

10. The intelligent recommendation system for TCM meridian therapy for chronic pain according to claim 9, characterized in that: The preset loss function is specifically: Loss=minΔRI(p) Among them, Loss is the preset loss function value; ΔRI(p) is the recovery index obtained based on the efficacy data.

Images