User diagnosis and treatment information processing method, program product, equipment and storage medium

Abstract

The embodiment of the invention provides a user diagnosis and treatment information processing method, a program product, equipment and a storage medium. The method comprises the following steps: acquiring traditional Chinese medicine diagnosis and treatment information of a user and disease information of the user; the traditional Chinese medicine diagnosis and treatment information of the user comprises tongue diagnosis information, face diagnosis information, pulse diagnosis information and palm diagnosis information; the user disease information comprises user disease information and user symptom information; inputting the traditional Chinese medicine diagnosis and treatment information of the user into a trained information processing model to obtain output user prediction information; the user prediction information comprises a prediction syndrome element, a prediction symptom and a prediction cause of the user; matching a prediction syndrome type set hit by the disease information of the user from a syndrome type library; syndrome types corresponding to the diseases and symptoms corresponding to the syndrome types are recorded in the syndrome type library; determining user syndrome information from the prediction syndrome set by using the user prediction information; and the target prescription is matched from the prescription library based on the user disease information and the user syndrome type information, so that the traditional Chinese medicine auxiliary diagnosis and treatment accuracy based on artificial intelligence is improved.

Description

Technical Field

[0001] This application relates to the technical field of traditional Chinese medicine assisted diagnosis and treatment, and more specifically, to a method for processing user diagnosis and treatment information, a program product, a device, and a storage medium. Background Art

[0002] With the rapid development of information technology, the combination of traditional Chinese medicine diagnosis and treatment with information technology can provide auxiliary suggestions for doctors' diagnosis, thereby reducing the workload of doctors. The AI (Artificial Intelligence) system combines modern technology with traditional Chinese medicine theory, and through advanced sensing technology, artificial intelligence, and big data analysis, etc., provides auxiliary support for traditional Chinese medicine assisted diagnosis and treatment and prescription recommendation. However, in related technologies, the accuracy of traditional Chinese medicine assisted diagnosis and treatment through artificial intelligence needs to be improved. Summary of the Invention

[0003] The purpose of the embodiments of this application is to provide a method for processing user diagnosis and treatment information, a program product, a device, and a storage medium, so as to improve the accuracy of traditional Chinese medicine assisted diagnosis and treatment based on artificial intelligence.

[0004] The first aspect of the embodiments of this application provides a method for processing user diagnosis and treatment information, and the method includes:

[0005] Obtain user traditional Chinese medicine diagnosis and treatment information and user disease information; wherein, the user traditional Chinese medicine diagnosis and treatment information includes one or more of tongue diagnosis information, face diagnosis information, pulse diagnosis information, and palm diagnosis information; the user disease information includes user disease information and user symptom information;

[0006] Input the user traditional Chinese medicine diagnosis and treatment information into a trained information processing model to obtain user prediction information output by the information processing model; the user prediction information includes one or more of predicted syndrome elements, predicted symptoms, and predicted etiologies of the user;

[0007] Match a set of predicted syndrome types hit by the user disease information from a preset syndrome type library; wherein, the syndrome type library records the syndrome types corresponding to diseases and the symptoms corresponding to the syndrome types;

[0008] Use the user prediction information to determine user syndrome type information from the set of predicted syndrome types;

[0009] Based on the user disease information and the user syndrome type information, match a target prescription from a preset prescription library.

[0010] In the above implementation process, the trained information processing model is used to output user prediction information based on the user's tongue surface pulse and palm diagnosis information, so as to determine the user's basic physical condition and general disease condition, match the corresponding set of predicted syndromes based on the user's disease information, and then use the user prediction information to more accurately screen out the user syndrome information that conforms to the user's physical condition and general disease condition from the set of predicted syndromes. Finally, the target prescription is matched based on the accurately predicted user syndrome information, so that the target prescription can better match the treatment indications of the user's clinical manifestations, thereby improving the accuracy of traditional Chinese medicine assisted diagnosis and treatment based on artificial intelligence.

[0011] Further, the syndrome database records multi-level symptoms corresponding to each syndrome, and the multi-level symptoms include any combination of main symptoms, secondary symptoms, accompanying symptoms, and other symptoms. The weights of the main symptoms, the secondary symptoms, the accompanying symptoms, and the other symptoms decrease in turn. Matching the set of predicted syndromes hit by the user's disease information from the preset syndrome database includes:

[0012] Determine multiple candidate syndromes corresponding to the user's disease information from the syndrome database;

[0013] For each level of symptoms corresponding to each candidate syndrome, determine the number of hits of the user's symptom information hitting each level of symptoms corresponding to the candidate syndrome;

[0014] For each candidate syndrome, based on the number of hits of each level of symptoms under the candidate syndrome and the weight corresponding to each level of symptoms, determine the hit score of the candidate syndrome;

[0015] Based on the hit scores of multiple candidate syndromes, determine the set of predicted syndromes hit by the user's disease information.

[0016] In the above implementation process, the symptoms of the syndrome are divided into multiple levels, and different weights are assigned to each level of symptoms. By counting the number of hits of the user's symptom information on the multi-level symptoms under each candidate syndrome and performing weighted processing on the number of hits to obtain the hit score of each candidate syndrome, and finally using the hit score to match the set of predicted syndromes, so as to predict the syndrome that the user is prone to suffer from from the perspective of the user's physical symptoms.

[0017] Further, the user's symptom information includes multiple mutually exclusive symptoms, and the method further includes:

[0018] Determine the first symptom that matches the user's prediction information and the second symptom that does not match the user's prediction information from the multiple mutually exclusive symptoms;

[0019] Perform a target operation, where the target operation includes: increasing the weight corresponding to the first symptom, decreasing the weight corresponding to the second symptom, and deleting one or more of the second symptoms from the user symptom information.

[0020] In the above implementation process, by using user prediction information to divide multiple mutually exclusive symptoms of the user into a first symptom and a second symptom, the ability to identify interference items is given, so that the influence of interference items on syndrome type prediction can be excluded, and the robustness of syndrome type prediction is improved.

[0021] Further, the determining the user syndrome type information from the predicted syndrome type set by using the user prediction information includes:

[0022] Based on the user prediction information, determine the syndrome element attributes that conform to the user's constitution, and determine the user syndrome type information that conforms to the syndrome element attributes from the predicted syndrome type set.

[0023] In the above implementation process, based on the user prediction information, determine the syndrome element attributes that conform to the user's constitution, so as to determine the user syndrome type information that conforms to the syndrome element attributes from the predicted syndrome type set. In this way, the obtained user syndrome type information is more matched with the user's traditional Chinese medicine diagnosis and treatment information, and the accuracy of syndrome differentiation can be improved.

[0024] Further, the user symptom information includes user concomitant symptom information, and the method further includes:

[0025] Input the target prescription, the user's traditional Chinese medicine diagnosis and treatment information, and the user's concomitant symptom information into a trained prescription adjustment model;

[0026] Obtain a first prescription after the prescription adjustment model adjusts the target prescription based on the user's traditional Chinese medicine diagnosis and treatment information and the user's concomitant symptom information.

[0027] In the above implementation process, use the prescription adjustment model to learn the prescription adjustment rules and characteristics, input the target prescription, the user's traditional Chinese medicine diagnosis and treatment information, and the user's concomitant symptom information into the trained prescription adjustment model, so as to generate a customized first prescription for the user. The first prescription can better match the treatment indications of the user's clinical manifestations. Thus, the problem of "one prescription for all people" with fixed content in the related art is solved.

[0028] Further, the user symptom information includes user concomitant symptom information, and the method further includes:

[0029] According to a pre-established first mapping relationship between diseases, syndrome types, concomitant symptoms, and additional herbs, determine a first traditional Chinese medicine corresponding to the user's disease information, the user's syndrome type information, and the user's concomitant symptom information, and increase the dose of the first traditional Chinese medicine in the target prescription;

[0030] According to the pre-established second mapping relationship between diseases, syndrome types, accompanying symptoms and drug reduction, determine the second traditional Chinese medicine corresponding to the user's disease information, the user's syndrome type information and the user's accompanying symptom information, and delete the second traditional Chinese medicine or reduce the dosage of the second traditional Chinese medicine in the target prescription;

[0031] According to the pre-established third mapping relationship between traditional Chinese medicine diagnosis and treatment information and syndrome elements, determine the target syndrome element corresponding to the user's traditional Chinese medicine diagnosis and treatment information, determine the third traditional Chinese medicine matching the target syndrome element from the preset traditional Chinese medicine set, and adjust the dosage of the third traditional Chinese medicine in the target prescription to obtain the first prescription.

[0032] In the above implementation process, using the user's accompanying symptom information as one of the adjustment reference information for the target prescription, and mapping the user's traditional Chinese medicine diagnosis and treatment information to the target syndrome element, and using the target syndrome element as one of the adjustment reference information for the target prescription, can more pertinently provide personalized prescriptions more suitable for different users' physical conditions, can pertinently improve the user's accompanying symptoms, and break the limitation of the same prescription for all people.

[0033] Further, the method further includes:

[0034] Adjust the first prescription according to the user information to obtain a second prescription; the user information includes one or more of the user's allergic drug use information, age information, and gender information;

[0035] Output the second prescription to the doctor, obtain the third prescription obtained after the doctor reviews the second prescription, and output the third prescription.

[0036] In the above implementation process, using the user information to adjust the first prescription, and then obtaining the second prescription after being reviewed by medical staff, and finally forming the third prescription. Adjusting the prescription from different dimensions can ensure the accurate and safe use of the prescription.

[0037] The second aspect of the embodiments of the present application provides a computer program product, the computer program product includes a computer program, and when the computer program is executed by a processor, it implements any method in the first aspect.

[0038] The third aspect of the embodiments of the present application provides an electronic device, the electronic device includes:

[0039] A processor;

[0040] A memory for storing executable instructions of the processor;

[0041] Wherein, when the processor calls the executable instructions, it implements the operations of any method in the first aspect.

[0042] A fourth aspect of the embodiments of the present application provides a computer-readable storage medium, on which computer instructions are stored, and when the computer instructions are executed by a processor, the steps of any of the methods in the first aspect are implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required to be used in the embodiments of the present application. It should be understood that the following drawings only show some 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.

[0044] Figure 1 FIG. is a schematic flowchart of a method for processing user diagnosis and treatment information provided by an embodiment of the present application;

[0045] Figures 2 - 4 FIG. is a schematic flowchart of another method for processing user diagnosis and treatment information provided by an embodiment of the present application;

[0046] Figure 5 FIG. is a hardware structure diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] The following will describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application.

[0048] 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. At the same time, in the description of the present application, the terms "first", "second", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0049] To solve the related problems mentioned above, the present application provides a method for processing user diagnosis and treatment information. Among them, all the steps included in this method are implemented by an electronic device with computing capabilities such as a computer. The computer processes the user diagnosis and treatment information by executing all the steps of this method to obtain one or more intermediate processing results. And the final result output by the computer is used as reference information for the doctor's reference. Specifically, the method includes steps 110-step 150 as Figure 1 shown.

[0050] Step 110: Obtain the user's traditional Chinese medicine diagnosis and treatment information and the user's disease information.

[0051] Among them, the user's traditional Chinese medicine diagnosis and treatment information includes one or more of tongue diagnosis information, face diagnosis information, pulse diagnosis information, and palm diagnosis information. The tongue diagnosis information can be obtained, for example, by performing image recognition on the user's tongue image. The tongue diagnosis information includes, for example, but is not limited to, information on the tongue coating, tongue body, and tongue bottom that can be used for diagnosis. The face diagnosis information can be obtained, for example, by performing image recognition on the user's face image. The face diagnosis information includes, for example, but is not limited to, information on the facial complexion, acne, and spots that can be used for diagnosis. The pulse diagnosis information can be obtained, for example, from the collected data of a pulse sensor. The pulse diagnosis information includes, for example, but is not limited to, pulse information such as cun pulse information, guan pulse information, and chi pulse information that can be used for diagnosis. The palm diagnosis information can be obtained, for example, by performing image recognition on the user's palm. The palm diagnosis information includes, for example, but is not limited to, information on the palm shape and palm color that can be used for diagnosis.

[0052] The user's disease information includes the user's disease type and the user's symptom information. The user's disease information refers to the type of disease the user has contracted. The user's disease information can be input and obtained after being diagnosed by a doctor.

[0053] The user's symptom information refers to the symptoms the user shows or feels on the body, such as, for example, but not limited to, headache, diarrhea, constipation, insomnia, and so on. In some embodiments, the user's symptom information at least includes the user's main symptom information and the user's secondary symptom information. In addition to the user's main symptom information and the user's secondary symptom information, the user's symptom information can also include the user's accompanying symptom information and / or the user's other symptom information.

[0054] Among them, the user's main symptom information is the manifestation data of the user's main symptoms. The main symptom is the primary symptom, which refers to the symptom that is decisive for the diagnosis of a certain disease among the many symptoms shown when a disease occurs. It includes the main symptoms and signs when the user seeks medical treatment, and is the symptom that best reflects the cause, pathology, and nature of the disease. It is the main contradiction and also the key factor in clinical syndrome differentiation. Each disease has specific main symptoms. The user's main symptom information can be checked by the user or the doctor, and includes at least one item and at most three items.

[0055] The user's secondary symptom information is the manifestation data of the user's secondary symptoms. The secondary symptom is the secondary symptom, which is a symptom closely related to the main symptom, and its reflected pathogenesis is the same as that of the main symptom, and can also be called the concurrent symptom. The user's secondary symptom information can be checked by the user or the doctor, and includes at least one item, and there is no limit on the maximum number.

[0056] The user's accompanying symptom information refers to the manifestation data of the user's accompanying symptoms. In a symptom group (symptoms and signs), the pathogenesis reflected by the accompanying symptoms is secondarily related, or even opposite, to the pathological cold-heat nature of the "main symptom" and "secondary symptom", and can also be called the complication syndrome and the complex syndrome. The user's accompanying symptom information can be checked by the user or the physician, and there is no limit to the quantity. According to the actual situation, it can be not selected or multiple items can be selected.

[0057] The user's other symptom information is filled in by the user's chief complaint, and the symptom information described by the user is obtained through information extraction technology and semantic recognition technology. There is no limit to the quantity of the user's other symptom information. According to the actual situation, it can be not filled in or multiple items can be filled in.

[0058] It should be noted that the user's traditional Chinese medicine diagnosis and treatment information is different from the user's symptom information. The so-called symptoms usually refer to the symptoms that bring uncomfortable experiences to the user. When the user has these symptoms, they will go to see a doctor. However, the user's traditional Chinese medicine diagnosis and treatment information such as the tongue surface, pulse, palm, etc. are not obvious physical symptoms, and may not even attract the user's attention. For example, the user will not go to see a doctor because the palm color is relatively red. However, from the perspective of traditional Chinese medicine, the diagnosis and treatment information such as the tongue surface, pulse, palm, etc. often implies disease information, which indicates the disease the user suffers from and the course of the disease development. The user's traditional Chinese medicine diagnosis and treatment information such as the tongue surface, pulse, palm, etc. and the user's symptom information are both the clinical manifestations of the user. It is of great significance to use the user's clinical manifestation information as one of the reference information for syndrome type and prescription matching.

[0059] Step 120: Input the user's traditional Chinese medicine diagnosis and treatment information into the trained information processing model to obtain the user prediction information output by the information processing model; the user prediction information includes one or more of the user's predicted syndrome elements, predicted symptoms, and predicted etiologies.

[0060] Among them, the so-called syndrome element refers to the element of the syndrome, including the disease location syndrome element and the disease nature syndrome element. And the syndrome type is composed of syndrome elements. Specifically, the syndrome type can be composed of the disease location syndrome element and the disease nature syndrome element. For example, the syndrome type of "syndrome of spleen and kidney yang deficiency" is composed of the disease location syndrome element "spleen", the disease location syndrome element "kidney", and the disease nature syndrome element "yang deficiency". In addition, the syndrome type can also be composed of multiple disease nature syndrome elements. For example, the syndrome type of "syndrome of deficiency of both qi and blood" is composed of the disease nature syndrome element "qi deficiency" and the disease nature syndrome element "blood deficiency".

[0061] The so-called syndrome type refers to the syndromes that are relatively common, typical, with standardized or established syndrome names in clinical practice. Regarding the relationship between diseases and syndrome types, one disease can be divided into multiple syndrome types, and the symptoms and treatment methods of different syndrome types under the same disease are different. And the same syndrome type can correspond to multiple diseases. For example, the syndrome type of "syndrome of spleen yang deficiency" can correspond to multiple diseases such as diarrhea, constipation, vomiting, etc.

[0062] Exemplarily, there may be multiple information processing models. The information processing models may correspond one by one to each type of TCM diagnosis information of users. Thus, step 120 may include one or more of the following:

[0063] Input the tongue diagnosis information of the user into the trained tongue diagnosis information processing model to obtain the user prediction information output by the tongue diagnosis information processing model based on the tongue diagnosis information; input the face diagnosis information of the user into the trained face diagnosis information processing model to obtain the user prediction information output by the face diagnosis information processing model based on the face diagnosis information; input the pulse diagnosis information of the user into the trained pulse diagnosis information processing model to obtain the user prediction information output by the pulse diagnosis information processing model based on the pulse diagnosis information; input the palm diagnosis information of the user into the trained palm diagnosis information processing model to obtain the user prediction information output by the palm diagnosis information processing model based on the palm diagnosis information.

[0064] For example, if the tongue diagnosis information of the user is "the tongue body is light red, the tongue shape is normal with teeth marks on the tongue", then the user prediction information output by the tongue diagnosis information processing model based on the tongue diagnosis information may include "the user has spleen deficiency or internal retention of dampness (predicted syndrome element), and may have a series of pathological phenomena and diseases (predicted symptoms) caused by the impairment of the spleen qi, including syndromes such as spleen qi deficiency, spleen yang deficiency, middle qi sinking, and failure of the spleen to control blood (predicted syndrome types), mostly caused by dietary disorders, excessive work and rest, or prolonged illness and weakness (predicted etiology).

[0065] Another example, if the tongue diagnosis information of the user is "the tongue coating is yellow and greasy, and the veins under the tongue are red in color", then the user prediction information output by the tongue diagnosis information processing model based on the tongue diagnosis information may include "the user has damp-heat, phlegm-heat or food retention (predicted syndrome element), and the specific manifestation may be due to overeating, excessive diet, or the inability of the diet to be digested normally, accumulating and stagnating in the gastrointestinal tract, resulting in the syndrome of abnormal ascending and descending of the spleen and stomach (predicted etiology).".

[0066] Another example, if the face diagnosis information of the user is "the face is relatively dark", then the user prediction information output by the face diagnosis information processing model based on the face diagnosis information may include "the user mainly has kidney deficiency syndrome, cold syndrome, phlegm retention, and blood stasis (predicted syndrome element and predicted syndrome type). Black belongs to the kidney, and a dark face (withered and haggard) is mostly caused by the decline of kidney yang, the internal exuberance of yin cold, and the blood losing warmth. Dark circles around the eyes also belong to a dark face (predicted etiology).

[0067] Another example, if the pulse diagnosis information of the user is "the pulse can be felt lightly and becomes slightly weaker but not empty when pressed heavily", then the user prediction information output by the pulse diagnosis information processing model based on the pulse diagnosis information may include "the syndrome manifested by insufficient vital qi and decline of zang-fu organ functions (predicted etiology). In contrast to the excess syndrome. Common symptoms include dull complexion, mental fatigue, shortness of breath and weak voice, spontaneous sweating and night sweating, dizziness and blurred vision, palpitation and insomnia, reduced appetite, etc. (predicted symptoms).".

[0068] Among them, the information processing model can be a deep convolutional neural network model, such as a ResNet50 (Residual Networks) model. Each information processing model can be supervised trained using traditional Chinese medicine diagnosis and treatment information carrying patient syndrome element labels, symptom labels, and / or etiology labels. In addition, since in the sample data for supervised training, the amount of positive sample data (such as normal tongue shape, normal tongue coating, normal palm, normal pulse condition) is much larger than the amount of negative sample data (such as prickly tongue, blood stasis under the tongue, dark face, jaundiced face, and other abnormal data), in order to prevent the information processing model from misjudging the user's traditional Chinese medicine diagnosis and treatment information that can indicate diseases as abnormal dirty data for processing, during the supervised training process, the training weight of the negative sample data can be increased, so that the information processing model can learn the hidden features in the negative sample data.

[0069] Step 130: Match the set of predicted syndromes hit by the user's disease information from a preset syndrome type library. Among them, the syndrome type library records the syndromes corresponding to diseases and the symptoms corresponding to the syndromes.

[0070] Exemplarily, a syndrome type library can be established in advance by a team of traditional Chinese medicine experts. The syndrome type library records multiple diseases, as well as one or more syndromes corresponding to each disease, and one or more symptoms corresponding to various syndromes under each disease. Generally speaking, the relationship between a disease and a syndrome can be one-to-one or one-to-many, and a certain syndrome under a certain disease can include one or more symptoms.

[0071] The established syndrome type library can be stored in a computer or a server, so that when the computer executes the steps of this method, it can call the syndrome type library from the local or from the server, so as to determine the set of predicted syndromes hit by the user's disease information. The set of predicted syndromes includes one or more predicted syndromes.

[0072] Step 140: Determine the user's syndrome type information from the set of predicted syndromes using the user's prediction information.

[0073] Exemplarily, if the set of predicted syndromes includes one predicted syndrome, then the user's prediction information can be used to verify whether the predicted syndrome is correct.

[0074] Exemplarily, if the set of predicted syndromes includes multiple predicted syndromes, then the user's prediction information can be used to determine the user's syndrome type information that more conforms to the user's constitution from the multiple predicted syndromes.

[0075] Step 150: Based on the user's disease information and the user's syndrome type information, match the target prescription from a preset prescription library.

[0076] Exemplarily, a prescription library can be pre-established by a team of traditional Chinese medicine experts. As an example, the prescription library records the mapping relationships between diseases, syndromes, and prescriptions. The mapping relationships between diseases, syndromes, and prescriptions can be one-to-one or many-to-many. Thus, based on the user's disease information and syndrome information, the corresponding target prescription can be matched from the prescription library.

[0077] As another example, the prescription library records the mapping relationships between diseases, syndromes, treatment methods, and prescriptions. Among them, a certain syndrome under a certain disease can correspond to one or more treatment methods, and each treatment method can correspond to multiple prescriptions. Thus, based on the user's disease information and syndrome information, multiple candidate treatment methods can be matched from the prescription library. Subsequently, the target treatment method can be determined from the multiple candidate treatment methods. For example, the commonly used treatment method can be determined as the target treatment method from the multiple candidate treatment methods. Or, since the user prediction information above characterizes the general condition of the user's illness, the target treatment method that meets the treatment indications of the user can be determined from the multiple candidate treatment methods based on the user prediction information.

[0078] Subsequently, if the target treatment method corresponds to one prescription, the prescription can be directly determined as the target prescription. If the target treatment method corresponds to multiple prescriptions, the commonly used prescription can be determined as the target prescription from the multiple prescriptions. Or, the target prescription that meets the treatment indications of the user can be determined from the multiple prescriptions based on the user prediction information.

[0079] It can be seen that a user diagnosis and treatment information processing method provided by the present application uses a trained information processing model to output user prediction information based on the user's tongue, face, pulse, and palm diagnosis information, thereby determining the user's basic physical condition and general condition of the illness, and matching the corresponding predicted syndrome set based on the user's disease information. Then, the user syndrome information that meets the user's physical condition and general condition of the illness is more accurately screened from the predicted syndrome set using the user prediction information. Finally, the target prescription is matched based on the accurately predicted user syndrome information, so that the target prescription can better match the treatment indications of the user's clinical manifestations, thereby improving the accuracy of traditional Chinese medicine assisted diagnosis and treatment based on artificial intelligence.

[0080] The following provides a detailed introduction to step 110-step 150.

[0081] Regarding the syndrome library, the syndrome library records multi-level symptoms of each syndrome. The multi-level symptoms include, but are not limited to, any combination of main symptoms, secondary symptoms, accompanying symptoms, and other symptoms. It can be understood that each syndrome under a disease corresponds to at least main symptoms and secondary symptoms, and may also correspond to accompanying symptoms and / or other symptoms. For example, syndrome a under disease A 1 corresponds to main symptom b 1 and main symptom b 2 secondary symptom c 1 and secondary symptom c2 Syndrome type a under disease A 2 Corresponding to main symptom b 2 , secondary symptom c 3 , concomitant symptom d 1 , and other symptom e 1 Syndrome type a under disease A 3 Corresponding to main symptom b 3 , main symptom b 4、 Secondary symptom c 3 , concomitant symptom d 2 , and concomitant symptom d 3 . In addition, among multi-level symptoms, the weights corresponding to the main symptom, secondary symptom, concomitant symptom, and other symptom decrease in turn. That is, the weight of the main symptom is the highest, followed by the weight of the secondary symptom, then the weight of the concomitant symptom, and the weight of the other symptom is the smallest. For example, the weight of the main symptom can be set to 5, the weight of the secondary symptom can be set to 3, the weight of the concomitant symptom can be set to 1, and the weight of the other symptom can be set to 0.5.

[0082] Based on this, the set of predicted syndrome types obtained by matching the user's disease information from the syndrome type library in step 130 above may specifically include steps 131 - 134 as shown in Figure 2 Figure 131 - Figure 134.

[0083] Step 131: Determine multiple candidate syndrome types corresponding to the user's disease information from the syndrome type library.

[0084] Exemplarily, since the syndrome type library records the syndrome types corresponding to each disease, the syndrome types corresponding to the user's disease information can be matched in the syndrome type library, and all the matched syndrome types are the candidate syndrome types.

[0085] Step 132: For each level of symptoms corresponding to each candidate syndrome type, determine the number of hits of the user's symptom information on each level of symptoms corresponding to the candidate syndrome type.

[0086] As described above, the syndrome type library also records the multi-level symptoms corresponding to various syndrome types under each disease. The user's symptom information records multiple symptoms of the user, including at least the user's main symptom information and the user's secondary symptom information, and may also include the user's concomitant symptom information and / or the user's other symptom information. Thus, the number of times the user's symptom information hits each level of symptoms in each candidate syndrome type can be counted. Continuing with the above example, the user's symptom information includes 2 pieces of user's main symptom information, 4 pieces of user's secondary symptom information, and 3 pieces of user's concomitant symptom information. For candidate syndrome type a 1 , the user's symptom information hits two main symptoms and two secondary symptoms of candidate syndrome type a 1 . Thus, it can be determined that the user's symptom information for candidate syndrome type a 1The hit count for the main symptoms is 2, and the hit count for the secondary symptoms is 2. For candidate syndrome type a 2 , the user's symptom information hits one main symptom, one secondary symptom, and one accompanying symptom of candidate syndrome type a 2 . Thus, it can be determined that for candidate syndrome type a 2 , the hit count for the main symptoms is 1, the hit count for the secondary symptoms is 1, and the hit count for the accompanying symptoms is 1, and so on.

[0087] Step 133: For each of the candidate syndrome types, based on the hit count of each level of symptoms under the candidate syndrome type and the weight corresponding to each level of symptoms, determine the hit score of the candidate syndrome type.

[0088] Exemplarily, for each candidate syndrome type, after obtaining the hit count of the user's symptom information for each level of symptoms, the weighted sum can be performed based on the hit count of each level of symptoms and the corresponding weight to obtain the hit score of the candidate syndrome type. Thus, the calculation formula for the hit score can be expressed as:

[0089]

[0090] where score is the hit score. m is the number of levels into which the symptoms corresponding to the candidate syndrome type are divided. For example, if the symptoms are divided into 3 levels: main symptoms, secondary symptoms, and accompanying symptoms, then m takes the value of 3. Another example, if the symptoms are divided into 2 levels: main symptoms and secondary symptoms, then m takes 2. w i is the weight corresponding to the i-th level of symptoms. n i is the hit count of the user's symptom information for the i-th level of symptoms.

[0091] As an example, considering that the number of multi-level symptoms corresponding to each syndrome type may be different. As in the above example, syndrome type a 1 corresponds to a total of 4 symptoms, while syndrome type a 3 corresponds to a total of 5 symptoms. Therefore, for each candidate syndrome type, the hit score of the candidate syndrome type can be determined based on the hit count of each level of symptoms under the candidate syndrome type, the weight corresponding to each level of symptoms, and the number of symptoms corresponding to the candidate syndrome type. For example, after performing the weighted sum of the hit count of each level of symptoms under a certain candidate syndrome type and the corresponding weight, the ratio of the weighted sum result to the number of symptoms corresponding to the candidate syndrome type can be determined as the hit score. Thus, the calculation formula for the hit score can be expressed as:

[0092]

[0093] where score is the hit score. S is the number of symptoms corresponding to the candidate symptoms. m is the number of levels into which the symptoms corresponding to the candidate syndrome type are divided. w iis the weight corresponding to the symptoms at the i-th level. n i is the number of hits of the user's symptom information at the symptoms of the i-th level.

[0094] Step 134: Determine the set of predicted syndromes hit by the user's disease information based on the hit scores of the multiple candidate syndromes.

[0095] Exemplarily, after obtaining the hit scores of the multiple candidate syndromes, the set of predicted syndromes hit by the user's disease information can be determined. The set of predicted syndromes may include one or more predicted syndromes.

[0096] As an example, if there is one candidate syndrome with the highest hit score, or there is one candidate syndrome with a hit score higher than the preset score threshold, the set of predicted syndromes includes one predicted syndrome, and it can be determined that this predicted syndrome is the user's syndrome information.

[0097] As another example, if there are multiple candidate syndromes with the highest hit scores, or there are multiple candidate syndromes with hit scores higher than the score threshold, the set of predicted syndromes includes multiple predicted syndromes.

[0098] It can be seen that in this embodiment, the symptoms of the syndrome are divided into multiple levels, and different weights are assigned to the symptoms of each level. By counting the number of hits of the user's symptom information on the multi-level symptoms under each candidate syndrome, and performing weighted processing on the number of hits to obtain the hit score of each candidate syndrome, and finally using the hit score to match the set of predicted syndromes, so as to predict the syndrome that the user is prone to suffer from from the perspective of the user's physical symptoms.

[0099] In Figure 2 On the basis of the embodiment, in some scenarios, the user's symptom information may include multiple mutually exclusive symptoms. For example, the user's secondary symptom information includes "constipation", but the user's accompanying symptom information includes "diarrhea". At this time, the user's secondary symptom information is mutually exclusive with the user's accompanying symptom information. There are various reasons for the user's symptom information to include multiple mutually exclusive symptoms. For example, the user may have misselected the symptoms. Another example is that the user may have the physical symptom of "constipation" most of the time, but suddenly had the symptom of "diarrhea" one day, which will also cause the user's symptom information to include multiple mutually exclusive symptoms.

[0100] The multiple mutually exclusive symptoms will affect the correct identification of the syndrome, and then affect the matching accuracy of the prescription. In order to exclude the interference information in the user's symptom information, in some embodiments, before counting the number of hits of the user's symptom information on the symptoms of each level, the steps also include: determining the first symptom that matches the user's prediction information and the second symptom that does not match the user's prediction information from the multiple mutually exclusive symptoms.

[0101] It can be understood that the information processing model can predict the syndrome elements, physical symptoms and possible causes that a user may exhibit based on the user's traditional Chinese medicine diagnosis and treatment information, so as to know the user's basic physical condition and general condition of the illness. By using one or more of the predicted syndrome elements, predicted symptoms and predicted causes, it is possible to infer the symptoms that the user is unlikely to have. Therefore, the first symptom matching the user's prediction information refers to the symptom with a high occurrence probability among a plurality of mutually exclusive symptoms; the second symptom not matching the user's prediction information refers to the symptom with a low occurrence probability among a plurality of mutually exclusive symptoms. Based on the user's prediction information, the probability of the user having the first symptom is higher than that of having the second symptom.

[0102] As an example, the process of distinguishing the first symptom from the second symptom can be performed by an AI system. For example, the user's traditional Chinese medicine diagnosis and treatment information and the user's disease information can be input into the AI system, or the user's prediction information and the user's disease information can be input into the AI system. The AI system can automatically determine a plurality of mutually exclusive symptoms from the user's symptom information, and use the user's traditional Chinese medicine diagnosis and treatment information or the user's prediction information to distinguish the first symptom from the second symptom among the plurality of mutually exclusive symptoms.

[0103] Subsequently, one or more of the following target operations can be performed on the plurality of mutually exclusive symptoms:

[0104] Target operation 1: Increase the weight of the first symptom. Since the user is more likely to exhibit the first symptom, the weight of the first symptom in the calculation of the hit score is increased.

[0105] Target operation 2: Reduce the weight of the second symptom. Since the user is unlikely to have the second symptom, it means that the second symptom is an interference item in the user's symptom information. In order to reduce the influence of the interference item on the syndrome differentiation result, the weight of the second symptom in the calculation of the hit score can be selected to be reduced.

[0106] Target operation 3: Delete the second symptom from the user's symptom information. Similarly, since it is determined that the second symptom is an interference item in the user's symptom information, the second symptom can be selected to be deleted, so as to exclude the influence of the second symptom on the syndrome differentiation result.

[0107] It can be seen that in this embodiment, the user's prediction information is used to divide the user's plurality of mutually exclusive symptoms into the first symptom and the second symptom, endowing the ability to identify interference items, so as to exclude the influence of interference items on the syndrome type prediction and improve the robustness of the syndrome type prediction.

[0108] On the basis of any of the above embodiments, regarding determining the user's syndrome type information by using the user's prediction information in step 140, it can specifically include the steps:

[0109] Determine the syndrome element attributes that conform to the user's physique based on the user prediction information, and determine the user syndrome type information that conforms to the syndrome element attributes from the set of predicted syndrome types.

[0110] Exemplarily, when the set of predicted syndrome types includes multiple predicted syndrome types, the user's physique can be determined by analyzing the user prediction information, or in other words, the syndrome element attributes that the user's physique tends to can be determined. Subsequently, the predicted syndrome type that conforms to the syndrome element attributes is determined from the set of predicted syndrome types as the user syndrome type information. As an example, the screening process of the user syndrome type information can be executed by an AI system. For example, the set of predicted syndrome types and the user prediction information, or the user's traditional Chinese medicine diagnosis and treatment information, can be input into the AI system. The AI system can determine the syndrome element attributes that conform to the user's physique based on the user prediction information or by analyzing the user's traditional Chinese medicine diagnosis and treatment information, so as to determine the user syndrome type information that conforms to the syndrome element attributes from the set of predicted syndrome types. In this way, the obtained user syndrome type information is more matched with the user's traditional Chinese medicine diagnosis and treatment information, and the accuracy of syndrome differentiation can be improved.

[0111] In addition to screening the user syndrome type information from the set of predicted syndrome types using the user prediction information, in some embodiments, the user syndrome type information can also be determined from the set of predicted syndrome types based on the user's past diagnosis and treatment information. As an example, the past diagnosis and treatment information includes the user's historical syndrome type information. In this way, the user syndrome type information that conforms to the historical syndrome type information can be determined from the set of predicted syndrome types. As another example, the past diagnosis and treatment information can include the user's historical syndrome type information and the efficacy feedback information after treatment for the historical syndrome type. Based on the efficacy feedback information, it can be determined whether the user's past syndrome differentiation is accurate. If the efficacy feedback information indicates that the user's condition has improved, it means that the past syndrome differentiation is accurate and the historical syndrome type information is accurate, and the user syndrome type information that conforms to the historical syndrome type information can be determined from the set of predicted syndrome types. On the contrary, if the efficacy feedback information indicates that the user's condition has not improved or has worsened, it means that the past syndrome differentiation may be inaccurate and the historical syndrome type information may be inaccurate. At this time, the predicted syndrome types that conform to the historical syndrome type information can be excluded from the set of predicted syndrome types, and then the user syndrome type information can be determined.

[0112] In addition to screening the user's syndrome information from the predicted syndrome set by using the user prediction information, in some embodiments, the user's syndrome information can also be screened from the predicted syndrome set based on one or more reference information among the current season, the user's age, and the user's gender. As an example, the reference information includes the current season. Thus, the predicted syndromes with high incidence in the current season can be determined from the predicted syndrome set as the user's syndrome information. As an example, the reference information includes the user's age. Thus, the predicted syndromes with high incidence at the user's age can be determined from the predicted syndrome set as the user's syndrome information. As another example, the reference information includes the user's gender. Thus, the predicted syndromes with high incidence of the user's gender can be determined from the predicted syndrome set as the user's syndrome information.

[0113] According to some embodiments of the present application, as described above, the user's symptom information at least includes the user's main symptom information and the user's secondary symptom information. That is, in some cases, only using the user's main symptom information and the user's secondary symptom information can also match the user's syndrome information, and then match the target prescription. However, the obtained target prescription may not be able to target the treatment of the user's accompanying symptoms. In order to make the prescription more in line with the treatment indications of the user's clinical manifestations, in this embodiment, the user's symptom information includes the user's accompanying symptom information. Based on this, the method may further include steps 310-step 320 as Figure 3 shown.

[0114] Step 310: Input the target prescription, the user's traditional Chinese medicine diagnosis and treatment information, and the user's accompanying symptom information into the trained prescription adjustment model.

[0115] Step 320: Obtain the first prescription after the target prescription is adjusted by the prescription adjustment model based on the user's traditional Chinese medicine diagnosis and treatment information and the user's accompanying symptom information.

[0116] Exemplarily, the prescription adjustment model can be obtained through supervised training. Each piece of training data of the prescription adjustment model can include a historical prescription, historical traditional Chinese medicine diagnosis and treatment information, historical accompanying symptom information, and a historical prescription. Among them, the historical prescription is the prescription obtained after the historical prescription is adjusted according to the historical traditional Chinese medicine diagnosis and treatment information and the historical accompanying symptom information. The prescription adjustment model can learn the rules and features between the traditional Chinese medicine diagnosis and treatment information, the accompanying symptom information, and the prescription adjustment through the above training data. Therefore, the trained prescription adjustment model can adjust the target prescription by using the input user's traditional Chinese medicine diagnosis and treatment information and the user's accompanying symptom information based on the learned prescription adjustment rules and features, and output the adjusted first prescription.

[0117] It can be seen that in this embodiment, the prescription adjustment model is used to learn the prescription adjustment rules and features. The target prescription, the user's traditional Chinese medicine diagnosis and treatment information, and the user's accompanying symptom information are input into the trained prescription adjustment model, so as to generate a customized first prescription for the user. The first prescription can better match the treatment indications of the user's clinical manifestations. Thus, the problem of "one prescription for all people with fixed content" in the related art is solved.

[0118] In addition, in addition to using the prescription adjustment model to adjust the target prescription to obtain the first prescription, in some embodiments, the target prescription can also be adjusted based on a pre-established mapping relationship. Specifically, it includes any one or more of step S1, step S2, and step S3.

[0119] Step S1: According to the first mapping relationship between diseases, syndromes, accompanying symptoms, and added herbs established in advance, determine the first traditional Chinese medicine corresponding to the user's disease information, the user's syndrome information, and the user's accompanying symptom information, and increase the dose of the first traditional Chinese medicine in the target prescription.

[0120] Exemplarily, a traditional Chinese medicine library can be established in advance by a team of traditional Chinese medicine experts. The traditional Chinese medicine library records the first mapping relationship among diseases, syndromes, accompanying symptoms, and added herbs. The added herbs refer to the added traditional Chinese medicine. Among them, the first mapping relationship between diseases, syndromes, accompanying symptoms, and added herbs can be a one-to-one mapping relationship, or a one-to-one-to-many mapping relationship. The traditional Chinese medicine library can be stored in a computer or a server, so that when the computer executes the steps of this method, the corresponding first mapping relationship can be called from the local or from the server. In this way, by inputting the user's disease information, the user's syndrome information, and the user's accompanying symptom information, the corresponding added herbs can be mapped from the first mapping relationship in the traditional Chinese medicine library, and the mapped added herbs are the first traditional Chinese medicine. The first traditional Chinese medicine can include one or more flavors.

[0121] After determining the first traditional Chinese medicine, the dose of the first traditional Chinese medicine in the target prescription can be increased. Among them, if the first traditional Chinese medicine is not included in the target prescription, then increasing the dose of the first traditional Chinese medicine can be adding the first traditional Chinese medicine. For example, adding the first traditional Chinese medicine according to the conventional dose in the target prescription, and the first prescription is obtained after adjustment. Among them, the doses increased for different first traditional Chinese medicines in the target prescription can be different.

[0122] Step S2: According to the second mapping relationship between diseases, syndromes, accompanying symptoms, and subtracted herbs established in advance, determine the second traditional Chinese medicine corresponding to the user's disease information, the user's syndrome information, and the user's accompanying symptom information, and delete the second traditional Chinese medicine or reduce the dose of the second traditional Chinese medicine in the target prescription.

[0123] Exemplarily, in addition to recording the first mapping relationship, the traditional Chinese medicine library also records a second mapping relationship between diseases, syndromes, accompanying symptoms, and the reduction of traditional Chinese medicine. The reduction of traditional Chinese medicine refers to the deletion of traditional Chinese medicine. Among them, the second mapping relationship between diseases, syndromes, accompanying symptoms, and the reduction of traditional Chinese medicine can be a one-to-one mapping relationship, or a one-to-many mapping relationship. In this way, by inputting the user's disease information, user syndrome information, and user accompanying symptom information, the corresponding reduction of traditional Chinese medicine can be mapped from the second mapping relationship in the traditional Chinese medicine library, and the mapped reduction of traditional Chinese medicine is the second traditional Chinese medicine.

[0124] The second traditional Chinese medicine can include one or more flavors.

[0125] After determining the second traditional Chinese medicine, the second traditional Chinese medicine can be deleted from the target prescription, or the dose of the second traditional Chinese medicine can be reduced, and the first prescription is obtained after adjustment. Among them, the doses reduced for different second traditional Chinese medicines in the target prescription can be different.

[0126] In addition, if the user's accompanying symptom information includes multiple items, that is, the user has multiple accompanying symptoms, then for each accompanying symptom, the target prescription can be adjusted by performing the above-mentioned step S1 and / or step S2 to obtain the first prescription.

[0127] Step S3: According to the third mapping relationship established in advance between traditional Chinese medicine diagnosis and treatment information and syndrome elements, determine the target syndrome element corresponding to the user's traditional Chinese medicine diagnosis and treatment information, determine the third traditional Chinese medicine matching the target syndrome element from the preset traditional Chinese medicine set, and adjust the dose of the third traditional Chinese medicine in the target prescription to obtain the first prescription.

[0128] Exemplarily, a syndrome element library can be established in advance by a team of traditional Chinese medicine experts. The syndrome element library records the third mapping relationship between traditional Chinese medicine diagnosis and treatment information and syndrome elements, including but not limited to the mapping relationship between tongue diagnosis information and syndrome elements, the mapping relationship between face diagnosis information and syndrome elements, the mapping relationship between pulse diagnosis information and syndrome elements, and the mapping relationship between palm diagnosis information and syndrome elements.

[0129] In addition, the relationship between traditional Chinese medicine diagnosis and treatment information and syndrome elements can be a one-to-one relationship. For example, the tongue diagnosis information "yellow and greasy tongue coating" corresponds to the syndrome element "damp-heat". The relationship between diagnosis information and syndrome elements can also be a one-to-many relationship. For example, the pulse diagnosis information "thin and deep on the right chi position" corresponds to the syndrome elements "qi deficiency" and "yin deficiency".

[0130] The syndrome element library can be stored in a computer or server, so that when the computer executes the steps of this method, the corresponding third mapping relationship can be called from the local or from the server. In this way, by inputting the patient's traditional Chinese medicine diagnosis and treatment information, the corresponding syndrome element can be mapped from the third mapping relationship in the syndrome element library, and the mapped syndrome element is the target syndrome element. The target syndrome element can include one or more.

[0131] Among them, if there are multiple target syndrome elements, the target formula can be adjusted for each target syndrome element by performing step S3. Alternatively, some target syndrome elements can be selected from all the target syndrome elements to adjust the target formula. Specifically, since different traditional Chinese medicine diagnosis and treatment information may correspond to the same target syndrome element or different target syndrome elements, the target syndrome elements of a certain user may be repeated. At this time, the occurrence times of each target syndrome element can be counted, and the preset number of target syndrome elements can be determined in order from high to low according to the occurrence times, and the target formula can be adjusted by performing step S3.

[0132] Exemplarily, a traditional Chinese medicine set can be established in advance by a team of traditional Chinese medicine experts. Among them, there can be multiple traditional Chinese medicine sets. As an example, the traditional Chinese medicine sets can correspond to diseases one by one, that is, each disease corresponds to a traditional Chinese medicine set. Then, when performing step S3, first determine the traditional Chinese medicine set corresponding to the user's disease information, and then determine the third traditional Chinese medicine that matches the target syndrome element from this traditional Chinese medicine set.

[0133] As an example, the traditional Chinese medicine sets can correspond to diseases and syndrome types, that is, each sub - type of syndrome under a certain disease corresponds to a traditional Chinese medicine set. Then, when performing step S3, first determine the traditional Chinese medicine set corresponding to the user's disease information and the user's syndrome type information, and then determine the third traditional Chinese medicine that matches the target syndrome element from this traditional Chinese medicine set. The third traditional Chinese medicine can include one or more flavors.

[0134] After determining the third traditional Chinese medicine, the dose of the third traditional Chinese medicine in the target formula can be adjusted. Among them, if the third traditional Chinese medicine is not included in the target formula, then adjusting the dose of the third traditional Chinese medicine can be adding the third traditional Chinese medicine. For example, adding the third traditional Chinese medicine to the target formula according to the conventional dose. If the target formula includes the third traditional Chinese medicine, then adjusting the dose of the third traditional Chinese medicine can be increasing the dose of the third traditional Chinese medicine in the target formula, and the first prescription is obtained after adjustment. Among them, the increased doses of different third traditional Chinese medicines in the target formula can be different.

[0135] It can be understood that even if different user individuals have the same disease and the same syndrome type, their manifestations in clinical manifestations, especially in accompanying symptoms and traditional Chinese medicine diagnosis and treatment information such as tongue, pulse, palm, etc. may not be the same. Therefore, in this embodiment, the user's accompanying symptom information is used as one of the adjustment reference information for the target formula, and the user's traditional Chinese medicine diagnosis and treatment information is mapped to the target syndrome element, and the target syndrome element is used as one of the adjustment reference information for the target formula, which can more pertinently provide personalized prescriptions more suitable for their physical conditions for different users, can pertinently improve the accompanying symptoms of users, and breaks the limitation of the same prescription for thousands of people.

[0136] On the basis of any of the above embodiments, after obtaining the first prescription, the method further includes as Figure 4Steps 410 - 420 as shown

[0137] Step 410: Adjust the first prescription according to user information to obtain a second prescription; the user information includes one or more of the user's allergy medication information, age information, and gender information.

[0138] As an example, to ensure medication safety, the first prescription can be adjusted based on the user's allergy medication information, and the allergy medications in the first prescription for the user can be deleted to obtain the second prescription.

[0139] As an example, since users of different age groups need to consider the dosage of medications. For example, in pediatric and geriatric medications, the dosages of some medications need to be reduced or increased. Therefore, the dosages of some medications in the first prescription can be adjusted based on the user's age information to obtain the second prescription.

[0140] As another example, different genders of users also need to consider medications. Therefore, some medications in the first prescription can be adjusted based on the user's gender information to obtain the second prescription.

[0141] Step 420: Output the second prescription to the physician, obtain a third prescription after the physician reviews the second prescription, and output the third prescription.

[0142] Exemplarily, the obtained second prescription is output to the physician, and the physician can review the second prescription based on traditional Chinese medicine taboos such as the eighteen incompatible medicaments and the nineteen medicaments with mutual restraint. After completing the review, the physician can choose to adopt the second prescription, modify the second prescription, or delete the second prescription. If the physician chooses to adopt the second prescription, then the second prescription is the third prescription, and the third prescription can be output to the user. If the physician chooses to modify the second prescription, then the third prescription can be obtained after modification and output to the user. If the physician chooses to delete the second prescription, the physician can prescribe a new prescription for the user according to the actual situation.

[0143] It can be seen that in this embodiment, the first prescription is adjusted using user information, and then the second prescription obtained after being reviewed by medical staff is finally formed into the third prescription. Adjusting the prescription from different dimensions can ensure the accuracy and safe use of the prescription.

[0144] It should be noted that the formulas, prescriptions, syndrome type information, etc. generated in any embodiment of this application are all output to the physician. The physician can choose to adopt or refer to the output information to assist in syndrome differentiation and diagnosis and treatment. Or the physician can also choose not to adopt or refer to the output information. In addition, the output formulas and prescriptions are different from treatment plans. These formulas and prescriptions play a role in improving and conditioning the patient's constitution or delaying the progression of the disease. They should not be directly used as a means of treating diseases, nor should they replace the physician's treatment plan.

[0145] Based on the user diagnosis and treatment information processing method described in any of the above embodiments, the present application further provides a computer program product, which includes one or more computer programs or instructions. The computer program or instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. When the computer program is executed by a processor, it implements the user diagnosis and treatment information processing method described in any of the above embodiments.

[0146] Based on the user diagnosis and treatment information processing method described in any of the above embodiments, the present application further provides a Figure 5 structural schematic diagram of an electronic device as shown. As Figure 5 , at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory. Of course, it may also include other hardware required for other services. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to implement the user diagnosis and treatment information processing method described in any of the above embodiments.

[0147] The present application further provides a computer storage medium storing a computer program, which can be used to execute the user diagnosis and treatment information processing method described in any of the above embodiments when the computer program is executed by a processor.

[0148] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of devices, methods, and computer program products according to multiple embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0149] In addition, in each embodiment of the present application, the various functional modules can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part.

[0150] If the above-mentioned functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0151] The above are only the embodiments of this application and are not used to limit the protection scope of this application. For those skilled in the art, this application can have various changes and modifications. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of this application shall be included in the protection scope of this application. It should be noted that similar reference numerals and letters represent 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.

[0152] As mentioned above, this is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by this application, and all should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

[0153] It should be noted that in this article, 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 variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including 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 limitations, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the said element.

Claims

1. A method for processing user diagnosis and treatment information, characterized in that: The method comprises: Obtaining user TCM diagnosis and treatment information and user symptom information; wherein the user TCM diagnosis and treatment information includes one or more of tongue diagnosis information, face diagnosis information, pulse diagnosis information and palm diagnosis information; the user symptom information includes user disease information and user symptom information; Inputting the user's TCM diagnosis and treatment information into the trained information processing model to obtain the user prediction information output by the information processing model; the user prediction information includes one or more of the user's predicted syndrome factors, predicted symptoms and predicted causes of disease; Matching a predicted syndrome set that matches the user's symptom information from a preset syndrome library; wherein the syndrome library records syndromes corresponding to diseases and symptoms corresponding to the syndromes; Determining user syndrome type information from the predicted syndrome type set using the user predicted information; Based on the user's disease information and the user's syndrome type information, a target prescription is matched from a preset prescription library.

2. The method according to claim 1, characterized in that: The syndrome database records the multi-level symptoms corresponding to each syndrome, and the multi-level symptoms include any number of main symptoms, secondary symptoms, concomitant symptoms and other symptoms, and the weights of the main symptoms, the secondary symptoms, the concomitant symptoms and the other symptoms are decreased respectively; The step of matching the predicted syndrome type set hit by the user's symptom information from a preset syndrome type library includes: Determining a plurality of candidate syndrome types corresponding to the user's disease information from the syndrome type library; For each level of symptoms corresponding to each candidate syndrome type, determining the number of hits of the user symptom information on each level of symptoms corresponding to the candidate syndrome type; For each of the candidate syndromes, based on the hit number of each level of symptoms under the candidate syndrome and the weight corresponding to each level of symptoms, determine the hit score of the candidate syndrome; A predicted syndrome set that the user's symptom information hits is determined based on the hit scores of the plurality of candidate syndromes.

3. The method according to claim 2, characterized in that The user symptom information includes a plurality of mutually exclusive symptoms, and the method further includes: determining, from the mutually exclusive plurality of symptoms, a first symptom that matches the user prediction information and a second symptom that does not match the user prediction information; Execute a target operation, wherein the target operation includes one or more of increasing a weight corresponding to the first symptom, decreasing a weight corresponding to the second symptom, and deleting the second symptom from the user symptom information.

4. The method according to any one of claims 1 to 3, characterized in that: The using the user prediction information to determine the user syndrome type information from the predicted syndrome type set includes: Based on the user prediction information, a syndrome attribute that matches the user's constitution is determined, and user syndrome type information that matches the syndrome attribute is determined from the predicted syndrome type set.

5. The method according to claim 1, characterized in that The user symptom information includes user accompanying symptom information, and the method further includes: Inputting the target prescription, the user's TCM diagnosis and treatment information, and the user's accompanying symptom information into a trained prescription adjustment model; A first prescription is obtained after the prescription adjustment model adjusts the target prescription based on the user's traditional Chinese medicine diagnosis and treatment information and the user's accompanying symptom information.

6. The method according to claim 1, characterized in that The user symptom information includes user accompanying symptom information, and the method further includes: According to a pre-established first mapping relationship between diseases, syndrome types, associated symptoms and increased medicines, determining a first traditional Chinese medicine corresponding to the user's disease information, the user's syndrome type information and the user's associated symptom information, and increasing the dosage of the first traditional Chinese medicine in the target prescription; Determine, according to a pre-established second mapping relationship between diseases, syndrome types, associated symptoms and drug reduction, a second Chinese medicine corresponding to the user's disease information, the user's syndrome type information and the user's associated symptom information, and delete the second Chinese medicine from the target prescription or reduce the dosage of the second Chinese medicine; According to a pre-established third mapping relationship between TCM diagnosis and treatment information and syndrome factors, the target syndrome factor corresponding to the user's TCM diagnosis and treatment information is determined, a third TCM matching the target syndrome factor is determined from a preset set of TCMs, and the dosage of the third TCM in the target prescription is adjusted to obtain a first prescription.

7. The method according to claim 5 or 6, characterized in that: The method further comprises: The first prescription is adjusted according to user information to obtain a second prescription; the user information includes one or more of the user's allergy medication information, age information, and gender information; The second prescription is output to the physician, a third prescription obtained after the physician reviews the second prescription is obtained, and the third prescription is output.

8. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

9. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing processor-executable instructions; Wherein, when the processor calls the executable instructions, the operation of any method described in claims 1-7 is implemented.

10. A computer-readable storage medium, characterized in that: Computer instructions are stored thereon, and when the computer instructions are executed by a processor, the steps of any method described in claims 1-7 are implemented.

Images