Traditional Chinese medicine AI auxiliary inquiry method, storage medium, electronic equipment and product

Abstract

The invention relates to the technical field of intelligent auxiliary diagnosis and treatment, and particularly provides a traditional Chinese medicine AI auxiliary inquiry method, a storage medium, electronic equipment and a product, and the method can comprise the following steps: based on feature information of a target object, recommending a personalized question to the target object, the feature information comprises tongue condition information, face information, pulse condition information or palm information; the personalized question is used for reflecting symptom information of the target object; obtaining an answer to the personalized question; based on the answer, a diagnosis prediction result of the target object is generated, and the diagnosis prediction result comprises disease prediction information and diagnosis and treatment auxiliary suggestions. Some embodiments of the application can provide high-precision auxiliary diagnosis prediction suggestions for the traditional Chinese medicine or the target object, and the reliability is high.

Description

Technical Field

[0001] This application relates to the field of intelligent diagnosis and treatment technologies, and more particularly, to a method, storage medium, electronic device, and product for AI-assisted traditional Chinese medicine (TCM) interrogation. Background Art

[0002] With the continuous development of artificial intelligence (AI) technology, it has been widely applied to various fields. Currently, in the field of TCM-assisted diagnosis, usually after a doctor performs the operations of inspection, auscultation and olfaction, interrogation, and palpation on a patient, based on the patient's self-reported information and previous medical record information, it is determined what diseases the patient has, and then a corresponding TCM prescription is issued for the patient. However, due to the complexity of TCM theoretical knowledge, relying solely on the experience of TCM doctors to diagnose patients, the accuracy of the diagnosis results cannot be guaranteed.

[0003] Therefore, how to provide a technical solution for a method of AI-assisted TCM interrogation with higher accuracy has become a technical problem that urgently needs to be solved. Summary of the Invention

[0004] Some embodiments of this application aim to provide a method, storage medium, electronic device, and product for AI-assisted TCM interrogation. Through the technical solutions of the embodiments of this application, intelligent interrogation of a target object can be achieved, providing reliable and accurate auxiliary diagnostic reference suggestions for TCM doctors and the target object.

[0005] In a first aspect, some embodiments of this application provide a method for AI-assisted TCM interrogation, including: recommending personalized questions to the target object based on the feature information of the target object, where the feature information includes: tongue image information, facial information, pulse condition information, or palm information; the personalized questions are used to reflect the symptom information of the target object; obtaining the answers to the personalized questions; and generating a diagnostic prediction result for the target object based on the answers, where the diagnostic prediction result includes: disease prediction information and treatment assistance suggestions.

[0006] Some embodiments of this application recommend corresponding personalized questions to the target object based on the feature information of the target object, and then generate a diagnostic prediction result for the target object based on the answers selected by the target object for the personalized questions. The diagnostic prediction result realizes intelligent preliminary interrogation of the target object, can provide reliable and accurate auxiliary reference opinions for doctors, indirectly improve the interrogation efficiency of doctors, and relieve the interrogation pressure.

[0007] In some embodiments, there are N personalized questions, where N is a positive integer. Recommending personalized questions to the target object based on the characteristic information of the target object includes: generating and recommending a first personalized question corresponding to the characteristic information; or, selecting and recommending a first personalized question matching the characteristic information from a question bank for consultation; obtaining an i-th answer to the i-th personalized question, where i ∈ [1, N); generating and recommending an (i + 1)-th personalized question corresponding to the characteristic information and / or historical answers; or, selecting and recommending an (i + 1)-th personalized question corresponding to the characteristic information and / or historical answers from the question bank for consultation; where the historical answers include at least one of the first i answers.

[0008] In some embodiments of the present application, multiple corresponding personalized questions can be generated or found from a question bank through the characteristic information of the target object and / or subsequent historical answers, improving the recommendation accuracy of personalized questions, so as to timely learn about the actual symptom information of the target object and provide data support for the accuracy of subsequent diagnosis and prediction results.

[0009] In some embodiments, before recommending personalized questions to the target object based on the characteristic information of the target object, the method further includes: obtaining a characteristic image of the target object collected by a tongue, face, pulse, and palm acquisition device, where the characteristic image includes: a tongue image, a face image, a pulse image, and a palm image; analyzing the characteristic image to obtain the characteristic information.

[0010] In some embodiments of the present application, a characteristic image of the target object is collected by a tongue, face, pulse, and palm acquisition device, and then the characteristic image is analyzed to obtain the characteristic information, so as to obtain the accurate basic situation of the target object and provide support for subsequent recommendation of accurate personalized questions.

[0011] In some embodiments, analyzing the characteristic image to obtain the characteristic information includes: respectively inputting the tongue image, the face image, the pulse image, and the palm image into a characteristic analysis model to obtain the tongue information, the face information, the pulse information, and the palm information.

[0012] In some embodiments of the present application, by respectively inputting the tongue image, the face image, the pulse image, and the palm image into a characteristic analysis model to obtain characteristic information, accurate analysis of the characteristic data of the target object is realized.

[0013] In some embodiments, generating the diagnostic prediction result of the target object based on the answer includes: obtaining some disease information among the syndrome types information and the disease prediction information corresponding to the answer; and determining the diagnosis and treatment assistance suggestions and other disease information in the disease prediction information except the some disease information based on the syndrome types information.

[0014] In some embodiments of the present application, after obtaining the syndrome types information and some disease information corresponding to the answer, the diagnosis and treatment assistance suggestions and other disease information can be determined based on the syndrome types information, so as to realize the intelligent interrogation prediction of the target object and provide reliable auxiliary information for doctors during the interrogation process.

[0015] In some embodiments, determining the diagnosis and treatment assistance suggestions and other disease information in the disease prediction information except the some disease information based on the syndrome types information includes: looking up the diagnosis and treatment assistance suggestions and the other disease information matching the syndrome types information in the syndrome type comparison table.

[0016] In some embodiments of the present application, by looking up the diagnosis and treatment assistance suggestions and other disease information matching the syndrome types information in the syndrome type comparison table, the information search efficiency and accuracy are improved.

[0017] In some embodiments, the diagnosis and treatment assistance suggestions include: drug prescriptions and medical orders related to the disease prediction information; and the symptom information includes: main symptoms, secondary symptoms or accompanying symptoms.

[0018] In a second aspect, some embodiments of the present application provide a traditional Chinese medicine AI-assisted interrogation device, including: a recommendation module, configured to recommend personalized questions to the target object based on the feature information of the target object, where the feature information includes: tongue image information, facial information, pulse condition information or palm information; the personalized questions are used to reflect the symptom information of the target object; a response module, configured to obtain the answers to the personalized questions; and a prediction module, configured to generate the diagnostic prediction result of the target object based on the answers, where the diagnostic prediction result includes: disease prediction information and diagnosis and treatment assistance suggestions.

[0019] In a third aspect, some embodiments of the present application provide a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the method described in any embodiment of the first aspect can be implemented.

[0020] In a fourth aspect, some embodiments of the present application provide an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where when the processor executes the program, the method described in any embodiment of the first aspect can be implemented.

[0021] Fifth aspect, some embodiments of the present application provide a computer program product, the computer program product includes a computer program, wherein, when the computer program is executed by a processor, it can implement the method described in any embodiment of the first aspect. Description of the Drawings

[0022] To more clearly illustrate the technical solutions of some embodiments of the present application, the following will briefly introduce the drawings required to be used in some embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0023] Figure 1 System diagram of a traditional Chinese medicine AI-assisted interrogation provided for some embodiments of the present application;

[0024] Figure 2 One of the method flowcharts of traditional Chinese medicine AI-assisted interrogation provided for some embodiments of the present application;

[0025] Figure 3 Another method flowchart of traditional Chinese medicine AI-assisted interrogation provided for some embodiments of the present application;

[0026] Figure 4 Block diagram of the composition of a device for traditional Chinese medicine AI-assisted interrogation provided for some embodiments of the present application;

[0027] Figure 5 Schematic diagram of an electronic device provided for some embodiments of the present application. Detailed Embodiments

[0028] Next, the technical solutions in some embodiments of the present application will be described in conjunction with the drawings in some embodiments of the present application.

[0029] It should be noted that: similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of the present application, terms such as "first", "second", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0030] In the related art, if a patient wants to know their own condition, the doctor needs to conduct a basic inquiry on the patient at the front end. Only after obtaining the patient's basic symptoms and condition information can an AI inquiry system generate a relevant disease report. However, with the popularization of traditional Chinese medicine knowledge, the pressure of traditional Chinese medicine inquiry has gradually increased, and traditional Chinese medicine knowledge is relatively complex. Relying on offline inquiries can only rely on the doctor's own experience. On the one hand, this results in low efficiency of traditional Chinese medicine inquiry, and on the other hand, the accuracy of the results of traditional Chinese medicine inquiry cannot be guaranteed.

[0031] In view of this, some embodiments of the present application provide a method for traditional Chinese medicine AI-assisted inquiry. This method can recommend personalized questions suitable for the target object based on the characteristic information of the target object; through the answers selected by the target object for the personalized questions, a diagnostic prediction result for the target object is generated. The diagnostic prediction result contains disease prediction information and treatment assistance suggestions. The embodiments of the present application can achieve intelligent inquiry with high efficiency; and on the one hand, it can enable the target object to promptly learn about their own situation, and on the other hand, it can provide reliable and accurate auxiliary inquiry basis and suggestions for traditional Chinese medicine, reduce the inquiry pressure of traditional Chinese medicine, and improve the medical experience of the target object.

[0032] The following will Figure 1 exemplarily elaborate on the overall composition structure of the traditional Chinese medicine AI-assisted inquiry system provided by some embodiments of the present application.

[0033] As Figure 1 shown, some embodiments of the present application provide a traditional Chinese medicine AI-assisted inquiry system, which can include: a tongue, face, pulse, and palm acquisition device 100 and a terminal 200. Among them, the tongue, face, pulse, and palm acquisition device 100 can acquire the characteristic image of the target object and send it to the terminal 200. After receiving the characteristic image, the terminal 200 obtains its corresponding characteristic information; then, based on this characteristic information, personalized questions are recommended and displayed to the target object. The target object can operate on the terminal 200 to select the answers to the personalized questions; finally, the terminal 200 can generate a diagnostic prediction result based on the answers.

[0034] In some embodiments of the present application, the terminal 200 can use an AI big data model pre-deployed internally to process the characteristic image to obtain the characteristic information; or the terminal 200 can send the characteristic image to the server, and use the AI big data model deployed internally in the server to process the characteristic image and then return the characteristic information to the terminal 200. Specifically, the AI big data model can be deployed according to the actual application scenario, and the embodiments of the present application do not make specific limitations here. Among them, the AI big data model contains multiple AI sub-models, which can realize the characteristic analysis and processing of the four parts of the tongue, face, pulse, and palm. The multiple AI sub-models can be obtained by training existing models in the application scenario of traditional Chinese medicine inquiry.

[0035] In some embodiments of the present application, the terminal 200 can be a mobile terminal or a non-portable computer terminal, and the embodiments of the present application do not make specific limitations here.

[0036] The following Figure 2 exemplarily elaborates the implementation process of traditional Chinese medicine AI-assisted interrogation performed by the terminal 200 provided in some embodiments of the present application.

[0037] Please refer to the Figure 2 , Figure 2 which is a flowchart of a method for traditional Chinese medicine AI-assisted interrogation provided in some embodiments of the present application. The method for traditional Chinese medicine AI-assisted interrogation may include:

[0038] S210, based on the feature information of the target object, recommend personalized questions to the target object, where the feature information includes: tongue image information, facial information, pulse condition information, or palm information; the personalized questions are used to reflect the symptom information of the target object. The symptom information includes: main symptoms, secondary symptoms, or accompanying symptoms.

[0039] For example, in some embodiments of the present application, based on the feature information of one or more parts of the tongue image, face, pulse condition, and palm of the target object (i.e., the patient or the interrogated person), recommend personalized questions (simply referred to as questions) that match the target object's own situation to the target object and display them to the target object. Among them, the personalized questions can be one or more, and these personalized questions can reflect the symptom information currently existing in the target object. The symptom information can include at least one of main symptoms, secondary symptoms, and accompanying symptoms. It can be understood that different target objects have different constitutions, resulting in differences in their feature information, and thus there are differences in the personalized questions recommended among different target objects.

[0040] In other application scenarios, in addition to the feature information of the target object, the basic information (such as height, weight, current symptoms, etc.) filled in by the target object himself / herself before interrogation, the information of previous medical record reports, and other relevant contents can also be combined, and appropriate personalized questions can be recommended for the target object through comprehensive consideration.

[0041] It should be noted that when there are multiple personalized questions, all the personalized questions can be recommended at one time based on the feature information. Or, after determining the first personalized question based on the characteristic information, when recommending subsequent personalized questions, at least based on the answer to the previous personalized question, the next personalized question can be recommended in sequence until the target object completes all the personalized questions.

[0042] In some embodiments of the present application, before performing S210, the method for TCM AI-assisted medical interrogation may further include: obtaining a feature image of the target object collected by a tongue, face, pulse, and palm acquisition device, where the feature image includes: a tongue image, a face image, a pulse image, and a palm image; analyzing the feature image to obtain the feature information.

[0043] For example, in some embodiments of the present application, an integrated tongue, face, pulse, and palm acquisition device or a split-type tongue, face, pulse, and palm acquisition device can guide the target object to perform operations to separately collect images of its four parts, obtaining a tongue image, a face image, a pulse image, and a palm image. Then, by separately identifying or analyzing the tongue image, the face image, the pulse image, and the palm image, tongue information, face information, pulse information, and palm information are obtained.

[0044] In some embodiments of the present application, analyzing the feature image to obtain the feature information includes: separately inputting the tongue image, the face image, the pulse image, and the palm image into a feature analysis model to obtain the tongue information, the face information, the pulse information, and the palm information.

[0045] For example, in some embodiments of the present application, different part AI models (i.e., AI sub-models) are called to separately identify the tongue image, the face image, the pulse image, and the palm image to obtain tongue information, face information, pulse information, and palm information.

[0046] It should be understood that different recognition rules are set in different AI models. For example, for the AI model for identifying tongue images, tongue surface detection rules are deployed inside it. For example, the tongue quality includes classifications such as pale white, light red, red and descending, cyanotic and purple, etc. Through the method of feature point detection, which categories of tongue quality exist can be marked and expressed in the form of text description in the output tongue information. Correspondingly, corresponding recognition rules are also set inside the AI models corresponding to the face, pulse, and palm. Specific recognition rules can be flexibly set according to the following feature information to be detected.

[0047] For example, tongue image information may include, but is not limited to, information about the tongue that can be used for diagnosis, such as tongue coating, tongue body, tongue shape, and sublingual area. Facial information can be obtained by performing image recognition on the user's facial image. Facial information includes, but is not limited to, information about the face that can be used for diagnosis, such as facial complexion, acne, and spots. Pulse condition information can be obtained by collecting data through the pulse sensor of the tongue surface pulse palm collection device. Pulse condition information includes, but is not limited to, cun pulse information, guan pulse information, and chi pulse information that can be used for diagnosis. Palm information can be obtained by performing image recognition on the user's palm. Palm information includes, but is not limited to, information about the palm that can be used for diagnosis, such as palm shape and palm color. It can be understood that the specific information included in the tongue image information, facial information, pulse condition information, and palm information can be flexibly set and recognized according to the actual application scenario, and the embodiments of the present application are not limited thereto.

[0048] S220. Obtain the answer to the personalized question.

[0049] For example, in some embodiments of the present application, the target object can select or input the answer corresponding to the personalized question on the terminal 200; or reply to the answer to each personalized question by means of voice reply, etc. The embodiments of the present application are not limited thereto.

[0050] In some embodiments of the present application, when there are N personalized questions, where N is a positive integer, S210 may include: generating and recommending the first personalized question corresponding to the feature information; or selecting and recommending the first personalized question that matches the feature information from the interrogation question bank. Obtain the i-th answer to the i-th personalized question, where i ∈ [1, N); generate and recommend the (i + 1)-th personalized question corresponding to the feature information and / or historical answers; or select and recommend the (i + 1)-th personalized question corresponding to the feature information and / or historical answers from the interrogation question bank; where the historical answers include at least one of the previous i answers.

[0051] For example, in some embodiments of the present application, when recommending multiple personalized questions to a target object, such as N questions, there is an association among the N personalized questions. Specifically, when recommending the first personalized question (referred to as the first question), one way is to generate and recommend the corresponding question through feature information, and some words or content in the first personalized question may contain some information in the feature information; another way is to match and recommend the first question corresponding to the feature information from the interrogation question bank. For example, the first question is determined by semantic matching, or similarity matching is used to confirm which question description in the feature information is hit more, and then the first question suitable for the target object is matched. In addition, the question bank can also be set with questions matched by different feature information, and the first question is directly determined through the mapping relationship between the feature information and the questions, etc.

[0052] After the first question is recommended, at this time i = 1. After the target object selects or enters the first answer to the first question on the terminal 200, when recommending the second question, the current answer includes the first answer. The second question can be determined based on the answer to the first question (as a specific example of the historical answer, or referred to as the first answer), or based on the feature information and the answer to the first question, or based on the feature information. At this time, i = 2; after the target object answers the second question, the second answer to the second question is obtained.

[0053] When recommending the third question, the current answer includes the first answer and the second answer. The third question can be determined based on the second answer (as a specific example of the historical answer), or based on the first answer and the second answer (as a specific example of the historical answer), or based on the feature information, the first answer and the second answer, etc. At this time, i = 3. Among them, when determining and recommending the questions after the first question, the question can be directly generated according to the above basis; or matched from the interrogation question bank according to the above basis. It should be understood that the determination method of the personalized questions can also adopt other methods in addition to the above situations, and the embodiments of the present application are not limited thereto.

[0054] Through the above method, after the target object answers all the personalized questions, the answers corresponding to all the questions are obtained, providing rich data support for subsequent interrogation.

[0055] S230. Generate a diagnostic prediction result of the target object based on the answer, where the diagnostic prediction result includes: disease prediction information and medical treatment assistance suggestions. The medical treatment assistance suggestions include: a drug prescription and medical advice related to the disease prediction information.

[0056] For example, in some embodiments of the present application, the diagnostic prediction result of the target object can be generated based on the answers to all personalized questions. Or, in some other embodiments, the corresponding diagnostic prediction result can also be generated based on the answers and the tongue surface, pulse, and palm information of the target object (as a specific example of the feature information). Among them, the disease prediction information can be the diseases that the current target object may have or the diseases that may occur in the future. The diagnosis and treatment assistance suggestions can be some reference information such as drug prescriptions and doctor's orders for the target object and traditional Chinese medicine practitioners to refer to. It should be understood that the diagnostic prediction result can only provide auxiliary reference opinions for the target object and traditional Chinese medicine practitioners to assist traditional Chinese medicine practitioners in obtaining some situations of the target object and cannot be used as a direct diagnostic result.

[0057] In some embodiments of the present application, S230 may include: obtaining some disease information of the syndrome type information and the disease prediction information existing in the target object corresponding to the answer; based on the syndrome type information, determining the diagnosis and treatment assistance suggestions and other disease information in the disease prediction information except the part of the disease information.

[0058] For example, in some embodiments of the present application, the answers given by the target object to the personalized questions can be matched to the syndrome type information and the main disease information of the target object (as a specific example of some disease information). After that, the diagnosis and treatment assistance suggestions and other possible disease information of the target object can be determined through the syndrome type information.

[0059] Among them, the traditional Chinese medicine syndrome type (i.e., the syndrome type information mentioned above, abbreviated as syndrome type) is an important basis for traditional Chinese medicine to diagnose diseases. It refers to the generalization of the pathological attributes at a certain stage in the development of the disease. Traditional Chinese medicine divides the human body into yin, yang, qi, and blood, and the causes of diseases include wind, cold, summer heat, dampness, dryness, heat, phlegm, and deficiency and excess. The syndrome type is the different disease states of the human body caused by different causes leading to different changes in yin, yang, qi, and blood.

[0060] In some embodiments of the present application, S230 may include: searching in the syndrome type comparison table for the diagnosis and treatment assistance suggestions and the other disease information that match the syndrome type information.

[0061] For example, in some embodiments of the present application, in order to realize intelligent interrogation, a syndrome type comparison table is pre-organized according to a large amount of traditional Chinese medicine knowledge and stored in the terminal 200. The syndrome type comparison table includes: the disease names, drug prescription suggestions, reference prescriptions, reference doctor's orders, and other relevant diagnosis and treatment assistance suggestions corresponding to different syndrome types. Through the syndrome type comparison table, the diagnosis and treatment assistance suggestions and disease information corresponding to the syndrome type information of the target object can be quickly found. Moreover, the syndrome type comparison table can be continuously updated according to the actual situation to be applicable to more intelligent interrogation scenarios.

[0062] The following combines the appendix Figure 3Exemplarily illustrate the specific process of traditional Chinese medicine AI-assisted interrogation provided by some embodiments of the present application.

[0063] Please refer to the appendix Figure 3 , Figure 3 which is a flowchart of a method for traditional Chinese medicine AI-assisted interrogation provided by some embodiments of the present application.

[0064] The above process will be exemplarily described below.

[0065] S310. Obtain the characteristic image of the target object collected by the tongue, face, pulse, and palm collection device.

[0066] S320. Analyze the characteristic image to obtain characteristic information.

[0067] S330. Let i = 1, and recommend the first personalized question corresponding to the characteristic information to the target object.

[0068] For example, the number of personalized questions is N.

[0069] S340. In response to the operation instruction of the target object, obtain the answer to the ith personalized question.

[0070] S350. Determine whether i is not less than N. If so, execute S370; otherwise, execute S360.

[0071] S360. Based on the answer to the ith personalized question, let i = i + 1, recommend the ith personalized question, and return to S340.

[0072] S370. Obtain N answers to N personalized questions.

[0073] S380. Obtain the syndrome type information and partial disease information corresponding to the N answers.

[0074] S390. Search in the syndrome type comparison table for the diagnosis and treatment assistance suggestions and other disease information that match the syndrome type information.

[0075] It can be understood that the specific implementation process of S310 to S390 can refer to the method embodiments provided above. To avoid repetition, the detailed description is appropriately omitted here. Through the above-mentioned some embodiments of the present application, it can be seen that the method for traditional Chinese medicine AI-assisted interrogation provided by the present application can enable the target object to timely learn about their own condition and can predict it more accurately, bringing a great shock to the user; moreover, based on the tongue, face, pulse, and palm information, to predict the situation of the target object, self-service interrogation can be realized, providing auxiliary suggestions for doctors.

[0076] Please refer to Figure 4 , Figure 4The block diagram of the composition of the device for TCM AI-assisted consultation provided by some embodiments of the present application is shown. It should be understood that the device for TCM AI-assisted consultation corresponds to the above method embodiment and can execute each step involved in the above method embodiment. The specific functions of the device for TCM AI-assisted consultation can be found in the description above. To avoid repetition, the detailed description is appropriately omitted here.

[0077] Figure 4 The device for TCM AI-assisted consultation includes at least one software function module that can be stored in a memory in the form of software or firmware or solidified in the device for TCM AI-assisted consultation, and the device for TCM AI-assisted consultation includes: a recommendation module 410, used to recommend personalized questions to the target object based on the characteristic information of the target object, wherein the characteristic information includes: tongue information, facial information, pulse information or palm information; the personalized questions are used to reflect the symptom information of the target object; a response module 420, used to obtain answers to the personalized questions; a prediction module 430, used to generate a diagnosis prediction result of the target object based on the answer, wherein the diagnosis prediction result includes: disease prediction information and auxiliary diagnosis and treatment suggestions.

[0078] In some embodiments of the present application, the personalized questions include N, where N is a positive integer, and the recommendation module 410 is used to generate and recommend a first personalized question corresponding to the feature information; or, select and recommend the first personalized question matching the feature information from a medical question bank; obtain the i-th answer to the i-th personalized question, i∈[1,N); generate and recommend the i+1-th personalized question corresponding to the feature information and / or historical answers; or, select and recommend the i+1-th personalized question corresponding to the feature information and / or historical answers from the medical question bank; wherein the historical answers include: at least one of the first i answers.

[0079] In some embodiments of the present application, before the recommendation module 410, the device for TCM AI-assisted medical consultation also includes a collection module (not shown in the figure), which is used to: obtain the characteristic image of the target object collected by the tongue, face, pulse and palm collection device, wherein the characteristic image includes: tongue image, facial image, pulse image and palm image; analyze the characteristic image to obtain the characteristic information.

[0080] In some embodiments of the present application, an acquisition module (not shown in the figure) is used to, including: inputting the tongue image, the facial image, the pulse image and the palm image into a feature analysis model respectively to obtain the tongue information, the facial information, the pulse information and the palm information.

[0081] In some embodiments of the present application, the prediction module 430 is configured to obtain partial disease information among the syndrome type information and the disease prediction information corresponding to the answer; and determine the diagnosis and treatment assistance suggestions and other disease information in the disease prediction information except the partial disease information based on the syndrome type information.

[0082] In some embodiments of the present application, the prediction module 430 is configured to look up the diagnosis and treatment assistance suggestions and the other disease information that match the syndrome type information from a syndrome type comparison table.

[0083] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the above-described device can refer to the corresponding process in the foregoing method, and will not be elaborated herein.

[0084] Some embodiments of the present application further provide a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the operations corresponding to any embodiment of the method provided in the above embodiments can be implemented.

[0085] Some embodiments of the present application further provide a computer program product, which includes a computer program. When the computer program is executed by a processor, the operations corresponding to any embodiment of the method provided in the above embodiments can be implemented.

[0086] As Figure 5 shown, some embodiments of the present application provide an electronic device 500, which includes: a memory 510, a processor 520, and a computer program stored on the memory 510 and executable on the processor 520. When the processor 520 reads the program from the memory 510 through a bus 530 and executes the program, the method of any of the above embodiments can be implemented.

[0087] The processor 520 can process digital signals and can include various computing architectures. For example, a complex instruction set computer architecture, a reduced instruction set computer architecture, or an architecture that implements a combination of multiple instruction sets. In some examples, the processor 520 can be a microprocessor.

[0088] The memory 510 can be used to store instructions executed by the processor 520 or data related to the execution of the instructions. These instructions and / or data can include code for implementing some or all of the functions of one or more modules described in the embodiments of the present application. The processor 520 of the present disclosure embodiment can be used to execute the instructions in the memory 510 to implement the method shown above. The memory 510 includes a dynamic random access memory, a static random access memory, a flash memory, an optical memory, or other memories well known to those skilled in the art.

[0089] The above are only embodiments of the present application and are not intended to limit the protection scope of the present application. For those skilled in the art, various modifications and changes can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application. It should be noted that similar reference numerals and letters indicate similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0090] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or replacements, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claimed rights.

[0091] It should be noted that in this text, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising a..." does not exclude the existence of additional identical elements in the process, method, article or device comprising the element.

Claims

1. A method for AI-assisted consultation in traditional Chinese medicine, characterized in that: include: Based on the characteristic information of the target object, recommend personalized questions to the target object, wherein the characteristic information includes: tongue information, facial information, pulse information or palm information; the personalized questions are used to reflect the symptom information of the target object; Obtaining answers to the personalized questions; Based on the answer, a diagnosis prediction result of the target object is generated, wherein the diagnosis prediction result includes: disease prediction information and auxiliary diagnosis and treatment suggestions.

2. The method according to claim 1, characterized in that The personalized questions include N, where N is a positive integer. The recommending personalized questions to the target object based on the feature information of the target object includes: Generate and recommend a first personalized question corresponding to the characteristic information; or select and recommend the first personalized question matching the characteristic information from a question bank; Get the i-th answer to the i-th personalized question, i∈[1,N); Generate and recommend the i+1th personalized question corresponding to the feature information and / or historical answers; or select and recommend the i+1th personalized question corresponding to the feature information and / or historical answers from the medical question bank; wherein the historical answers include: at least one of the first i answers.

3. The method according to claim 1 or 2, characterized in that Before recommending personalized questions to the target object based on the feature information of the target object, the method further includes: Acquire the characteristic image of the target object collected by the tongue, face, pulse and palm collection device, wherein the characteristic image includes: tongue image, face image, pulse image and palm image; The characteristic image is analyzed to obtain the characteristic information.

4. The method according to claim 3, characterized in that The step of analyzing the characteristic image to obtain the characteristic information includes: The tongue image, the facial image, the pulse image and the palm image are respectively input into a feature analysis model to obtain the tongue image information, the facial information, the pulse information and the palm information.

5. The method according to any one of claims 1 to 2 and 4, characterized in that: Generating a diagnosis prediction result of the target object based on the answer includes: Acquire the syndrome type information of the target object corresponding to the answer and part of the disease information in the disease prediction information; Based on the syndrome type information, determine the auxiliary diagnosis and treatment suggestions and other disease information in the disease prediction information except the partial disease information.

6. The method according to claim 5, characterized in that The determining, based on the syndrome type information, the auxiliary diagnosis and treatment suggestions and other disease information in the disease prediction information except for the partial disease information includes: The auxiliary diagnosis and treatment suggestions and the other disease information that match the syndrome information are searched in the syndrome comparison table.

7. The method according to any one of claims 1 to 2, 4 and 6, characterized in that: The diagnosis and treatment assistance suggestions include: drug prescriptions and medical advice related to the disease prediction information; the symptom information includes: main symptoms, secondary symptoms or concomitant symptoms.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program executes the method according to any one of claims 1 to 7 when executed by a processor.

9. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the computer program executes the method according to any one of claims 1 to 7 when being run by the processor.

10. A computer program product, characterized in that The computer program product comprises a computer program, wherein the computer program executes the method according to any one of claims 1 to 7 when executed by a processor.

Images