Moxibustion application scheme prediction method and system based on big data and storage medium

Abstract

The invention relates to the technical field of data prediction, in particular to a big data-based moxibustion application scheme prediction method and system and a storage medium, which are used for acquiring body information of a patient, identifying basic body conditions of the patient based on body conditions of the patient, historical disease diagnosis reasons and past medical history, and predicting a moxibustion application scheme of the patient. On the basis, different predicted moxibustion application schemes are correspondingly matched in a moxibustion application scheme big database through the moxibustion application scheme big database established in advance, then the predicted moxibustion application schemes selected in advance are implemented in stages, the body information of the patient is obtained again before implementation of each stage, and the body information of the patient is determined according to changes of the body conditions of the patient. According to the method, whether the corresponding moxibustion application scheme is prepared again or not is selected, so that the predicted moxibustion application scheme suitable for the patient is dialectically found, the predicted moxibustion application scheme is effectively verified, and the treatment effect of moxibustion treatment is improved.

Description

Technical Field

[0001] The present invention relates to the field of data prediction technology, and more specifically, to a moxibustion scheme prediction method, system and storage medium based on big data. Background Art

[0002] Moxibustion, also known as moxibustion therapy or moxibustion therapy, is a therapeutic method that uses moxa sticks or cones made from mugwort leaves to stimulate acupuncture points or specific areas of the body. The heat generated by the moxa stimulates the flow of qi in the meridians, thereby regulating the body's physiological and biochemical disorders, thereby preventing and treating disease. Moxibustion's mechanism of action is similar to that of acupuncture, and they have complementary therapeutic effects. It offers numerous advantages, including ease of use, low cost, and significant effectiveness.

[0003] Traditional moxibustion relies on manual operation, and the implementation plan of moxibustion is heavily dependent on the experience level of medical staff. For patients with different symptoms, the moxibustion implementation plan is also different, which leads to moxibustion effects varying from person to person.

[0004] In order to further standardize the moxibustion implementation plan and provide moxibustion implementation plan intelligently, and get rid of the problem of uneven implementation level of traditional moxibustion, the moxibustion implementation plan is predicted through artificial intelligence big data, and accurate moxibustion plans can be quickly obtained for different symptoms of patients. For example, patent No. 202310842915.6, the patent name is moxibustion plan prediction method, device, electronic device and medium based on big data, which discloses the following: finding at least two historical moxibustion plans corresponding to information similar to the symptom description or diagnosed disease in the medical consultation record of the target user; determining the predicted moxibustion points and predicted moxibustion order based on the historical moxibustion effects corresponding to the at least two historical moxibustion plans, the historical moxibustion points and the moxibustion point order included in the at least two historical moxibustion plans; determining the average moxibustion time corresponding to the historical moxibustion points matching the predicted moxibustion points as the predicted moxibustion time of the predicted moxibustion points; determining that the predicted moxibustion points, the predicted moxibustion order and the predicted moxibustion time of the predicted moxibustion points constitute a moxibustion prediction plan.

[0005] However, due to the different physical constitutions of patients and different conditions of patients with different constitutions, the corresponding moxibustion prediction plans are not the same, and it is difficult for most patients to achieve ideal therapeutic effects through a single implementation of the moxibustion prediction plan. Summary of the Invention

[0006] In view of the above-mentioned deficiencies in the prior art, the purpose of the present invention is to provide a moxibustion plan prediction method, system and storage medium based on big data, which dialectically finds a predicted moxibustion plan suitable for the patient, thereby achieving effective verification of the predicted moxibustion plan and achieving the purpose of improving the therapeutic effect of moxibustion treatment.

[0007] The above technical objectives of the present invention are achieved through the following technical solutions: A method for predicting moxibustion schemes based on big data, comprising the following implementation steps: S1, obtain the patient's physical information and identify the patient's basic physical condition based on the patient's physical condition, historical disease diagnosis reasons and past medical history; S2: Prepare a corresponding predicted moxibustion plan. A large database of moxibustion plans is established in advance. According to the patient's basic physical condition, different predicted moxibustion plans are matched in the database. The predicted moxibustion plans include the moxibustion acupoints and the order of the moxibustion acupoints; S3, staged moxibustion implementation, is implemented in stages according to the previously selected predicted moxibustion plan, and the patient's physical information is obtained again before the implementation of each stage. According to the changes in the patient's physical condition, it is decided whether to re-equip the corresponding moxibustion plan.

[0008] Preferably, the patient's physical information includes the patient's tongue image captured by video and the patient's pulse image collected by wearable devices. Before matching and predicting the moxibustion plan, the tongue image and pulse image are input into a pre-trained classification model, and the tongue image type code and pulse image type code are output. The patient's cause of illness is identified through the patient's tongue image type code, pulse type code, historical disease diagnosis reasons and past medical history analysis, and the moxibustion plan is matched and predicted in the moxibustion plan database according to the patient's cause of illness.

[0009] Preferably, the moxibustion method and moxibustion time are matched according to the patient's physical condition. The moxibustion method selection includes direct moxibustion, moxibustion through an object and suspended moxibustion. Different moxibustion method selections correspond to different moxibustion times. The patient's physical condition includes the patient's age and TCM constitution type.

[0010] Preferably, the predicted moxibustion program includes several first-stage trial moxibustion stages of implementing the moxibustion program for the patient for the first time and several subsequent second-stage recovery moxibustion stages implemented based on the first-stage trial moxibustion stages.

[0011] Preferably, the basis for re-arranging the corresponding moxibustion treatment plan is the patient feedback after the first stage of trial moxibustion, and the patient feedback includes: (a) The change in the total score of the TCM Symptom Score Form filled out by the patient; (b) Changes in physiological indicators based on tongue and pulse patterns; When the total score change is less than 30% or the physiological indicators deteriorate, the re-equipment plan is triggered.

[0012] Preferably, the type sources of the moxibustion scheme big database include classic Chinese medicine knowledge books, modern clinical data and historical patient moxibustion schemes, and a knowledge graph is constructed based on the data from the type sources, wherein the nodes of the knowledge graph include acupoint entities and syndrome entities, and the relationship edges of the knowledge graph include main efficacy and contraindications, and the moxibustion scheme is predicted based on the corresponding matching of the patient's physical information.

[0013] On the one hand, a moxibustion scheme prediction system based on big data is provided, including An information acquisition module is used to obtain patient identity information and patient physical information; The matching module identifies the patient's physical information and matches the appropriate predicted moxibustion plan in the established moxibustion plan database; Implementation module, which implements the predicted moxibustion plan in stages; The efficacy evaluation module uses the "TCM Symptom Scoring Form" filled out by the patient and the changes in physiological indicators based on tongue and pulse conditions; The decision-making module triggers the pairing module to rematch the plan when the improvement rate after the completion of the first stage of trial moxibustion is less than 30%; when the improvement rate after the completion of the first stage of trial moxibustion is greater than or equal to 30%, the implementation module is triggered to implement the second stage of recovery moxibustion.

[0014] On the one hand, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the moxibustion scheme prediction method based on big data as described above is implemented.

[0015] In summary, the present invention has the beneficial effects of: obtaining the patient's physical information, identifying the patient's basic physical condition based on the patient's physical condition, historical disease diagnosis reasons and past medical history, and on this basis, through the pre-established moxibustion plan database, matching different predicted moxibustion plans in the moxibustion plan database, and then implementing the previously selected predicted moxibustion plan in stages, and obtaining the patient's physical information again before the implementation of each stage, and choosing whether to re-equip the corresponding moxibustion plan according to changes in the patient's physical condition, thereby dialectically finding a predicted moxibustion plan suitable for the patient, thereby achieving effective verification of the predicted moxibustion plan and improving the therapeutic effect of moxibustion treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 Schematic diagram of the steps of generating a moxibustion plan prediction method according to an embodiment of the present invention; Figure 2 4 is a structural block diagram of a moxibustion scheme prediction system according to an embodiment of the present invention.

[0017] Figure numerals: 1. Information acquisition module; 2. Matching module; 3. Implementation module; 4. Efficacy evaluation module; 5. Decision-making module. DETAILED DESCRIPTION

[0018] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0019] It should be noted that when a component is referred to as being “fixed to” or “disposed on” another component, it can be directly on the other component or indirectly on the other component. When a component is referred to as being “connected to” another component, it can be directly or indirectly connected to the other component.

[0020] It should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the present invention.

[0021] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature identified as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0022] For a moxibustion plan prediction method based on big data, see Figure 1 , including the following implementation steps: S1, obtain the patient's physical information and identify the patient's basic physical condition based on the patient's physical condition, historical disease diagnosis reasons and past medical history; S2: Prepare a corresponding predicted moxibustion plan. A large database of moxibustion plans is established in advance. According to the patient's basic physical condition, different predicted moxibustion plans are matched in the database. The predicted moxibustion plans include the moxibustion acupoints and the order of the moxibustion acupoints; S3, staged moxibustion implementation, is implemented in stages according to the previously selected predicted moxibustion plan, and the patient's physical information is obtained again before the implementation of each stage. According to the changes in the patient's physical condition, it is decided whether to re-equip the corresponding moxibustion plan.

[0023] When implementing this embodiment, the patient's physical information is first obtained, and the patient's basic physical condition is identified based on the patient's physical condition, historical diagnosis reasons of symptoms, and past medical history. On this basis, through the pre-established moxibustion plan database, different predicted moxibustion plans are matched in the moxibustion plan database, and then the previously selected predicted moxibustion plan is implemented in stages. Before the implementation of each stage, the patient's physical information is obtained again. According to the changes in the patient's physical condition, it is decided whether to re-equip the corresponding moxibustion plan, so as to dialectically find the predicted moxibustion plan suitable for the patient, thereby achieving effective verification of the predicted moxibustion plan and improving the therapeutic effect of moxibustion treatment.

[0024] The historical diagnosis reasons include Western medicine disease diagnosis, using the ICD-11 international standard coding, and Traditional Chinese Medicine syndrome classification, referring to the "Classification and Code of Traditional Chinese Medicine Diseases and Syndromes" GB / T 15657-2021. Both must be provided at the same time. If there are corresponding records of the historical diagnosis reasons and past medical history, they should be provided; otherwise, they do not need to be provided.

[0025] Based on the fact that the mechanism of action of moxibustion is based on the meridian system and combined with modern experimental research, it is believed that the mechanism of action of moxibustion is related to the following five aspects: 1. Local irritation Moxibustion's localized warming stimulation enhances blood and lymphatic circulation, boosting the metabolic capacity of skin tissue and effectively dissipating pathological products such as inflammation, adhesions, exudates, and hematomas. Localized warming stimulation can also induce the diffusion of inhibitory substances in the cerebral cortex, reducing the excitability of the nervous system, thereby achieving a calming and analgesic effect without any toxic side effects. Warmth also promotes the absorption of medications, fully unleashing the medicinal properties of moxa wool itself, other herbs added to the moxa stick, and spacers. Furthermore, moxibustion also produces near-infrared radiation. This near-infrared radiation provides essential energy for bodily functions, and the energy emitted by moxibustion can be controlled by the human body. During moxibustion treatment, near-infrared radiation possesses strong penetrating power, enabling energy to be transmitted through the meridians to distal locations, ultimately reaching the affected area. Stimulating acupuncture points can also stimulate the body's own immune system, restoring normal physiological functions.

[0026] 2. Meridian Regulation Meridian theory is the basic theory of moxibustion therapy. The stimulation of acupoints will eventually regulate the internal organs and limbs of the human body through the meridian system, so that the overall function of the human body remains in good operation.

[0027] (1) First, meridian acupoints are sensitive to drugs. The so-called sensitivity means that when moxibustion is performed, acupoints are more effective than general body surface points. If the moxibustion point deviates from the acupoint, the sensation will not be transmitted, and the treatment and health care effect will be greatly reduced.

[0028] (2) Secondly, the effects of meridians and acupoints on drugs can be amplified. The meridians are definitely not a simple route for circulation on the body surface, but a multi-level, multi-functional, and multi-form regulatory system that connects the internal organs of the human body and the skin surface. When moxibustion is applied to acupoints, it affects the physiological functions of other levels through the meridian system, forming a multi-level circulation induction. The levels stimulate and cooperate with each other, and the effects are superimposed, resulting in a physiological amplification effect. In clinical practice, for some of the same diseases, if taken with Chinese medicine, it takes several prescriptions of Chinese medicine to be effective, but moxibustion at the corresponding acupoints often works in one treatment.

[0029] (3) Finally, meridian acupoints also have the function of storing medicinal properties. For example, when treating chronic bronchitis and asthma, we often adopt the method of treating winter diseases in summer, that is, moxibustion treatment once a day during the dog days of summer, each time for several hours. If we analyze it from a general perspective, this method is relatively short in duration and the amount of medicine used is very small, so the intensity is far from enough. However, it can achieve good therapeutic effects. This is because acupoints have the function of storing medicinal properties - the physical and chemical effects of the medicine can remain in the acupoints for a long time or be slowly released throughout the body, thereby exerting the role of overall regulation and health care.

[0030] 3. Immune function regulation Human immunity refers to the body's resistance to pathogens or toxins. This is also known in Western medicine as the production of antibodies by white blood cells to enhance immune function and phagocytize foreign bacteria, thereby providing a defensive defense. Moxibustion precisely enhances human immunity. Many of the therapeutic benefits of moxibustion are achieved by regulating immune function. This regulation exhibits a bidirectional nature, increasing low immune levels and reducing high immune levels. This regulatory effect is particularly evident in the use of moxibustion to treat existing illnesses. Staphylococcus aureus is a common pathogenic bacterium that is easily carried by humans and animals. It can grow in healthy individuals in areas such as the nose, throat, and hands, and is also prone to colonization in wounds. Increased numbers of Staphylococcus aureus can produce toxins that harm human health. Moxibustion can increase the number of white blood cells and their average migration rate, enhancing their ability to attack S. aureus. Moxibustion can also promote immune cell recirculation and migration into lymphoid tissues by enhancing peripheral circulation, thereby enhancing the induction of local immune responses and strengthening the phagocytic function of macrophages.

[0031] 4. Pharmacological Action There are also many kinds of drugs used in moxibustion therapy. In addition to the pure moxa sticks made with moxa wool alone, there are also medicated moxa sticks with various drugs added. Among the drugs used in moxa sticks, moxa is indispensable. Without moxa, moxibustion does not exist.

[0032] Most of the drugs used in moxibustion therapy are spicy and aromatic. The volatile oils and pungent compounds they contain can stimulate epidermal cells, increasing cell membrane permeability and facilitating drug absorption, thereby fully utilizing the drug's efficacy. At the same time, the openings of skin glands in the epidermis dilate due to pungent and warm stimulation, allowing some large molecular weight and fat-soluble drugs to enter the body through these glandular openings, facilitating the drug's efficacy.

[0033] 5. Comprehensive Effect Moxibustion's primary effect on the human body is a comprehensive one, resulting from the interplay, complementation, and synergy of various factors. Moxibustion's therapeutic approach is comprehensive. Any type of moxibustion involves selecting appropriate acupoints, applying the appropriate medication, and applying the warmth of moxa to the affected area. This series of steps forms an organically connected whole, not a single, isolated step. Missing any one of these steps will negate the therapeutic effect. The therapeutic effects are also comprehensive. The warmth of the moxa and the pharmacological effects of the medications are concentrated on the acupoints. Stimulating these points stimulates meridian qi, thereby mobilizing the regulating functions of the meridians and enhancing immune function. These interactions complement each other and work as a whole. The therapeutic effects are also integrated with the body's reactivity. The use of moxibustion as a therapeutic method on the human body must leverage the body's internal reactivity.

[0034] From this we can see that moxibustion therapy in traditional Chinese medicine is a multi-faceted combination of traditional Chinese medicine conditioning using mugwort and other medicines, local stimulation, meridian regulation, and immune function regulation.

[0035] For this reason, moxibustion therapy in traditional Chinese medicine cannot be separated from syndrome differentiation and treatment. To this end, moxibustion is implemented in stages. According to the previously selected predictive moxibustion plan, it is implemented in stages, and the patient's physical information is obtained again before the implementation of each stage. According to the changes in the patient's physical condition, it is decided whether to re-equip the corresponding moxibustion plan until the predictive moxibustion plan is implemented for the corresponding patient.

[0036] Specifically, the patient's physical information includes the patient's tongue image captured by video and the patient's pulse image collected by wearable devices. Before matching and predicting the moxibustion plan, the tongue image and pulse image are input into a pre-trained classification model, and the tongue image type code and pulse image type code are output. The patient's cause of illness is identified through the patient's tongue image type code, pulse type code, historical disease diagnosis reasons and past medical history analysis, and the moxibustion plan is matched and predicted in the moxibustion plan database according to the patient's cause of illness.

[0037] Under a standard D65 light source, a camera module captures tongue images. After tongue image recognition, an electronic wristband is used to capture pulse information. A pre-trained classification model outputs tongue and pulse type codes. For example, there are eight tongue types (1 = pale tongue, 2 = red tongue, 3 = crimson tongue, etc.), and six pulse types (1 = string pulse, 2 = slippery pulse, 3 = deep pulse, etc.). The model architecture uses 1D-CNN. Identify the cause of the patient's illness by combining historical diagnosis of symptoms and analysis of past medical history.

[0038] Construction of etiology rule base:

[0039] At the same time, the moxibustion method and time are matched according to the patient's physical condition. The moxibustion method selection includes direct moxibustion, moxibustion through objects and hanging moxibustion. Different moxibustion method selections correspond to different moxibustion times. The patient's physical condition includes the patient's age and TCM constitution type.

[0040] Constitution types in Traditional Chinese Medicine include balanced constitution, qi deficiency constitution, yang deficiency constitution, yin deficiency constitution, phlegm-damp constitution, damp-heat constitution, blood stasis constitution, qi stagnation constitution, and special constitution. Taking into account the different physical conditions of patients and their different tolerance to pharmacology and moxibustion treatment intensity, different moxibustion methods are selectively matched to further improve the patient's moxibustion experience and safety.

[0041] Specifically, the predicted moxibustion plan includes a first stage of trial moxibustion phase in which the moxibustion plan is implemented for the patient for the first time for several times and a second stage of recovery moxibustion phase in which the moxibustion plan is implemented several times subsequently based on the first stage of trial moxibustion phase.

[0042] The predicted moxibustion program is mainly divided into a first stage trial moxibustion stage and a second stage recovery moxibustion stage. The moxibustion program is implemented on patients during the first stage trial moxibustion stage. Due to different patients and their poor physical conditions, the first stage trial moxibustion stage and the second stage recovery moxibustion stage can be implemented in multiple times.

[0043] For patients in good physical condition, the first stage of trial moxibustion and the second stage of recovery moxibustion are mainly adopted. The first stage of trial moxibustion is used to further observe the patients after moxibustion, and then the second stage of recovery moxibustion is implemented.

[0044] Specifically, the basis for re-arranging the corresponding moxibustion treatment plan is based on the subsequent patient feedback during the first phase of the trial moxibustion phase, and the patient feedback includes: (a) The change in the total score of the TCM Symptom Score Form filled out by the patient; (b) Changes in physiological indicators based on tongue and pulse patterns; When the total score change is less than 30% or the physiological indicators deteriorate, the re-equipment plan is triggered.

[0045] Traditional Chinese Medicine Symptom Score Table (for moxibustion efficacy)

[0046] Total score calculation rules: Total score = ∑(all symptom scores) (full score = 3 points × number of symptoms) Example: If 5 symptoms are evaluated with a full score of 15; the initial score is 10, and it drops to 4 after moxibustion, then the improvement rate = (10-4) / 10=60%.

[0047] Efficacy assessment: Markedly effective: total score reduction rate ≥ 50%; effective: total score reduction rate 30% ≤ <50%; ineffective: total score reduction rate <30%.

[0048] Specifically, the types of sources of the moxibustion scheme database include classic Chinese medicine knowledge books, modern clinical data, and historical patient moxibustion schemes. The data based on the type sources are constructed into a knowledge graph, wherein the nodes of the knowledge graph include acupoint entities and syndrome entities, and the relationship edges of the knowledge graph include main efficacy and contraindications, and the moxibustion scheme is predicted based on the corresponding matching of the patient's physical information.

[0049] Data was collected from three sources: classical TCM texts, modern clinical data, and historical patient moxibustion protocols. Classic TCM texts, including ancient texts such as the Yellow Emperor's Classic of Internal Medicine and the Acupuncture and Moxibustion Classic, were extracted using manual excerpting or optical character recognition technology to extract textual information such as acupoint names, primary symptoms, and moxibustion methods. Modern clinical data was collected from the hospital's electronic medical record system and TCM clinical research reports, covering structured and semi-structured data such as basic patient information, diagnoses, and moxibustion treatment records. Historical patient moxibustion protocols were obtained by collating hospital-archived paper medical records and patient follow-up records, forming the original dataset.

[0050] Data is annotated to prepare for the subsequent construction of the knowledge graph. During the annotation process, key information such as acupoint entities, syndrome entities, main treatment effects, and contraindications are clarified. For example, in modern clinical data, the syndrome entity corresponding to the patient's symptoms and the acupoint entity selected by the doctor are annotated, and the main treatment effects of the acupoint and contraindications for the patient are also recorded.

[0051] Based on the labeled data, define the nodes and edges of the knowledge graph. Acupoint names and TCM syndrome types are used as nodes. The therapeutic associations between acupoints and syndrome types are defined as "Main Indications and Efficacy" edges. Indications that acupoints are inappropriate for specific syndromes or patient conditions are defined as "Contraindications" edges. For example, the "Zusanli" acupoint node is connected to the "Spleen and Stomach Deficiency Syndrome" syndrome node via a "Main Indications and Efficacy" edge. If a patient has stomach heat syndrome, a "Contraindications" edge exists between "Zusanli" and the patient's condition.

[0052] Utilize graph databases or knowledge graph building tools to structure and visualize nodes and edges. Use graph embedding algorithms to learn vector representations of nodes and relationships and explore potential relationships between nodes.

[0053] In addition, based on the above-mentioned moxibustion scheme prediction method based on big data, a moxibustion scheme prediction system based on big data is provided. Figure 2 ,include: Information acquisition module 1, used to obtain patient identity information and patient physical information; Matching module 2, based on the patient's physical information identification, matches the appropriate predicted moxibustion plan in the established moxibustion plan database; Implementing module 3, the predicted moxibustion plan was implemented in stages; Therapeutic effect evaluation module 4 is based on the "TCM Symptom Scoring Form" filled out by the patient and the changes in physiological indicators based on tongue and pulse conditions; Decision module 5, when the improvement rate after the completion of the first stage of trial moxibustion is less than 30%, triggers the matching module 2 to re-match the plan; when the improvement rate after the completion of the first stage of trial moxibustion is greater than or equal to 30%, triggers the matching implementation module 3 to implement the second stage of recovery moxibustion.

[0054] Based on the above-mentioned big data-based moxibustion plan prediction system, the beneficial effects of the corresponding method embodiments are achieved, which will not be repeated here.

[0055] It should be noted that in the embodiments of this application Figure 2 The division of modules in the moxibustion scheme prediction system based on big data shown is schematic and is only a logical function division. In actual implementation, there may be other division methods. In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or it can be a separate physical existence, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. It can also be implemented in the form of a combination of software and hardware.

[0056] It should be noted that in the embodiments of the present application, if the above-mentioned method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer storage medium. Based on this understanding, the technical solution of the embodiments of the present application, or the part that contributes to the relevant technology, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling an electronic device to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk.

[0057] An embodiment of the present application provides a computer device, which may be a server. The computer device includes a processor, a memory, and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the above-mentioned method is implemented.

[0058] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method provided in the above embodiment are implemented.

[0059] An embodiment of the present application provides a computer program product containing instructions, which, when executed on a computer, enables the computer to execute the steps of the method provided in the above method embodiment.

[0060] Those skilled in the art will appreciate that, in one embodiment, the moxibustion plan prediction system based on big data provided in this application can be implemented in the form of a computer program that can be run on a computer device. The memory of the computer device can store the various program modules that constitute the above-mentioned device. The computer program composed of the various program modules causes the processor to execute the steps of the method of each embodiment of the present application described in this specification.

[0061] The above embodiments are merely explanations of the present invention and are not limitations of the present invention. After reading this specification, those skilled in the art may make non-creative modifications to the embodiments as needed. However, as long as they are within the scope of the claims of the present invention, they are protected by patent law.

Claims

1. A moxibustion plan prediction method based on big data, characterized by: Including the following Implementation steps: S1, obtain the patient's physical information and identify the patient's basic physical condition based on the patient's physical condition, historical disease diagnosis reasons and past medical history; S2: Prepare a corresponding predicted moxibustion plan. A large database of moxibustion plans is established in advance. According to the patient's basic physical condition, different predicted moxibustion plans are matched in the database. The predicted moxibustion plans include the moxibustion acupoints and the order of the moxibustion acupoints; S3, staged moxibustion implementation, is implemented in stages according to the previously selected predicted moxibustion plan, and the patient's physical information is obtained again before the implementation of each stage. According to the changes in the patient's physical condition, it is decided whether to re-equip the corresponding moxibustion plan.

2. The method for predicting moxibustion schemes based on big data according to claim 1, wherein: The patient's physical information includes the patient's tongue image captured by video and the patient's pulse image collected by wearable devices. Before matching and predicting the moxibustion plan, the tongue image and pulse image are input into a pre-trained classification model, and the tongue image type code and pulse image type code are output. The patient's cause of illness is identified through the patient's tongue image type code, pulse type code, historical disease diagnosis reasons and past medical history analysis, and the moxibustion plan is matched and predicted in the moxibustion plan database according to the patient's cause of illness.

3. The method for predicting moxibustion schemes based on big data according to claim 2, wherein: At the same time, the moxibustion method and time are matched according to the patient's physical condition. The moxibustion method selection includes direct moxibustion, moxibustion through objects and hanging moxibustion. Different moxibustion method selections correspond to different moxibustion times. The patient's physical condition includes the patient's age and TCM constitution type.

4. The method for predicting moxibustion schemes based on big data according to claim 1, wherein: The predicted moxibustion program includes a first-stage trial moxibustion phase in which the moxibustion program is implemented for the patient for the first time for several times and a second-stage recovery moxibustion phase in which the program is subsequently implemented for several times based on the first-stage trial moxibustion phase.

5. The method for predicting moxibustion schemes based on big data according to claim 4, characterized in that: The basis for re-designing the corresponding moxibustion treatment plan is the follow-up patient feedback after the first phase of the trial moxibustion, which includes: (a) The change in the total score of the TCM Symptom Score Form filled out by the patient; (b) Changes in physiological indicators based on tongue and pulse patterns; When the total score change is less than 30% or the physiological indicators deteriorate, the re-equipment plan is triggered.

6. The method for predicting moxibustion schemes based on big data according to claim 1, wherein: The types of sources of the moxibustion scheme big database include classic Chinese medicine knowledge books, modern clinical data and historical patients' moxibustion schemes. The data based on the type sources are constructed into a knowledge graph, wherein the nodes of the knowledge graph include acupoint entities and syndrome entities, and the relationship edges of the knowledge graph include main efficacy and contraindications, and the moxibustion scheme is predicted based on the corresponding matching of the patient's physical information.

7. A moxibustion plan prediction system based on big data, characterized by: include An information acquisition module is used to obtain patient identity information and patient physical information; The matching module identifies the patient's physical information and matches the appropriate predicted moxibustion plan in the established moxibustion plan database; Implementation module, which implements the predicted moxibustion plan in stages; The efficacy evaluation module uses the "TCM Symptom Scoring Form" filled out by the patient and the changes in physiological indicators based on tongue and pulse conditions; The decision-making module triggers the matching module to rematch the plan when the improvement rate after the completion of the first stage of trial moxibustion is less than 30%; when the improvement rate after the completion of the first stage of trial moxibustion is greater than or equal to 30%, the matching implementation module is triggered to implement the second stage of recovery moxibustion.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the moxibustion scheme prediction method based on big data as described in any one of claims 1 to 6 is implemented.

Images