Traditional Chinese medicine diagnosis and treatment prescription recommendation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a traditional Chinese medicine diagnosis and treatment prescription recommendation method and device, electronic equipment and a storage medium, and relates to the technical field of data processing, and the method comprises the steps: obtaining the disease information of a patient to be diagnosed and treated, obtaining at least one recommendation case and a corresponding recommendation index from a pre-constructed expert experience case library according to the disease information, generating a recommendation case selection interface according to the at least one recommendation case and the corresponding recommendation index, responding to a selection operation of the user on the recommendation case selection interface, and generating a prescription interface according to a prescription in the target recommendation case selected by the user, so that the user can make a prescription for the patient to be diagnosed and treated according to the prescription displayed on the prescription interface. The recommendation cases and the recommendation index of each recommendation case are screened out from the expert experience case library according to the disease information, so that the situation that the accuracy and efficiency of traditional Chinese medicine diagnosis and treatment are low due to less diagnosis and treatment experience of the user is avoided, and the accuracy and efficiency of traditional Chinese medicine diagnosis and treatment are improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, electronic device and storage medium for recommending prescriptions for traditional Chinese medicine diagnosis and treatment. Background Art

[0002] In the field of traditional Chinese medicine, diagnosis and treatment experience often depends on personal clinical practice and long-term accumulation. Since everyone's understanding of diseases and treatment methods may be different, it is difficult to systematically and standardizedly impart rich diagnosis and treatment experience. These diagnosis and treatment experiences are often passed down orally between teachers and apprentices, but the limitations of this method in expanding influence and ensuring quality are becoming increasingly prominent. On the one hand, this method makes it difficult to form a broad and systematic knowledge base; on the other hand, the speed at which new Chinese medicine practitioners acquire diagnosis and treatment experience is limited by the experience and ability of their mentors, resulting in low accuracy and efficiency in Chinese medicine diagnosis and treatment. Summary of the invention

[0003] The purpose of the present invention is to provide a method, device, electronic device and storage medium for recommending prescriptions for traditional Chinese medicine diagnosis and treatment, so as to solve the problems of low accuracy and efficiency of traditional Chinese medicine diagnosis and treatment.

[0004] In a first aspect, the present invention provides a method for recommending prescriptions for TCM diagnosis and treatment, the method comprising:

[0005] Obtain information about the symptoms of patients to be diagnosed and treated;

[0006] Obtaining at least one recommended case and a corresponding recommendation index from a pre-constructed expert experience case library according to the symptom information; the expert experience case library is obtained by analyzing an expert diagnosis and treatment experience database;

[0007] Generating a recommended case selection interface according to at least one of the recommended cases and the corresponding recommendation index;

[0008] In response to the user's selection operation on the recommended case selection interface, a prescription interface is generated according to the prescription in the target recommended case selected by the user, so that the user can prescribe a prescription for the patient to be treated according to the prescription displayed on the prescription interface.

[0009] In an optional embodiment, the expert experience case library includes a plurality of diagnosis and treatment cases, and obtaining at least one recommended case and a corresponding recommendation index from the pre-built expert experience case library according to the symptom information includes:

[0010] Processing the disease information to obtain target disease characteristics;

[0011] The recommended case is determined according to the similarity value between the target disease feature and the diseases of the plurality of diagnosis and treatment cases, and the corresponding recommendation index is obtained according to the similarity value corresponding to the recommended case.

[0012] In an optional implementation manner, the processing the disease information to obtain target disease characteristics includes:

[0013] Extract features from the disease information to obtain the target disease features.

[0014] In an optional embodiment, the method further comprises:

[0015] Acquiring usage feedback information; the usage feedback information is feedback information after the user uses the target recommended case;

[0016] The expert experience case library is optimized according to the usage feedback information.

[0017] In an optional implementation manner, the expert experience case library is constructed by the following steps:

[0018] Obtaining the expert diagnosis and treatment experience database;

[0019] Preprocessing the expert diagnosis and treatment experience database to obtain a preprocessed experience database;

[0020] Analyze the pre-processed experience database through a data mining algorithm to obtain multiple syndrome differentiation and medication rules; each syndrome differentiation and medication rule is a prescription for a corresponding disease;

[0021] According to the plurality of syndrome differentiation and medication rules, a plurality of diagnosis and treatment cases are obtained;

[0022] Based on the multiple diagnosis and treatment cases, the expert experience case library is obtained.

[0023] In an optional embodiment, the preprocessing of the expert diagnosis and treatment experience database to obtain the preprocessed experience database includes:

[0024] Deduplication processing is performed on multiple expert diagnosis and treatment experience data in the expert diagnosis and treatment database;

[0025] Performing outlier detection on the plurality of expert diagnosis and treatment experience data after deduplication processing, and deleting the expert diagnosis and treatment experience data with outliers;

[0026] After deleting the expert diagnosis and treatment experience data with abnormal values, each of the remaining expert diagnosis and treatment experience data is processed in a unified manner to obtain the pre-processing experience database.

[0027] In an optional implementation, the unification processing of each of the remaining expert diagnosis and treatment experience data to obtain the pre-processing experience database includes:

[0028] The symptom description information, diagnosis information, and medication information included in each of the remaining expert diagnosis and treatment experience data are uniformly processed to obtain the pre-processing experience database.

[0029] In a second aspect, the present invention provides a device for recommending prescriptions for traditional Chinese medicine diagnosis and treatment, the device comprising:

[0030] A symptom information acquisition module is used to obtain symptom information of the patient to be diagnosed and treated;

[0031] A recommended case acquisition module, used to obtain at least one recommended case and a corresponding recommendation index from a pre-built expert experience case library according to the symptom information; the expert experience case library is obtained by analyzing the expert diagnosis and treatment experience database;

[0032] A recommended case selection interface generation module, used to generate a recommended case selection interface according to at least one of the recommended cases and the corresponding recommendation index;

[0033] The prescription interface generation module is used to respond to the user's selection operation on the recommended case selection interface and generate a prescription interface based on the prescription in the target recommended case selected by the user, so that the user can prescribe for the patient to be treated according to the prescription displayed on the prescription interface.

[0034] In a third aspect, the present invention provides an electronic device comprising a processor and a memory, wherein the memory stores a computer program executable by the processor, and the computer program executable by the processor is used to implement the method for recommending prescriptions for TCM diagnosis and treatment as described in any of the aforementioned embodiments.

[0035] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for recommending prescriptions for TCM diagnosis and treatment as described in any one of the aforementioned embodiments.

[0036] The method, device, electronic device and storage medium for recommending TCM diagnosis and treatment prescriptions provided by the embodiments of the present invention include: obtaining symptom information of a patient to be diagnosed and treated, obtaining at least one recommended case and a corresponding recommendation index from a pre-constructed expert experience case library based on the symptom information, the expert experience case library is obtained by analyzing the expert diagnosis and treatment experience database, generating a recommended case selection interface based on at least one recommended case and the corresponding recommendation index, responding to a user's selection operation on the recommended case selection interface, generating a prescription interface based on the prescription in the target recommended case selected by the user, so that the user can prescribe for the patient to be diagnosed and treated based on the prescription displayed on the prescription interface. By screening out recommended cases and the recommendation index of each recommended case from the expert experience case library based on symptom information, the situation in which the accuracy and efficiency of TCM diagnosis and treatment are low due to the user's lack of diagnosis and treatment experience is avoided, thereby improving the accuracy and efficiency of TCM diagnosis and treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0038] Figure 1 A schematic diagram of a process of a method for recommending prescriptions for TCM diagnosis and treatment provided by an embodiment of the present invention is shown;

[0039] Figure 2 A schematic diagram showing a recommended case selection interface provided by an embodiment of the present invention is shown;

[0040] Figure 3 A schematic diagram of a prescription interface provided by an embodiment of the present invention is shown;

[0041] Figure 4 Another schematic diagram of a process of recommending a prescription for TCM diagnosis and treatment provided by an embodiment of the present invention is shown;

[0042] Figure 5 Another schematic diagram of a process of recommending a prescription for TCM diagnosis and treatment provided by an embodiment of the present invention is shown;

[0043] Figure 6 A module block diagram of a device for recommending prescriptions for TCM diagnosis and treatment provided by an embodiment of the present invention is shown;

[0044] Figure 7 A block diagram of an electronic device provided by an embodiment of the present invention is shown.

[0045] Icons: 100 - electronic device; 110 - memory; 120 - processor; 130 - communication module; 200 - TCM diagnosis and treatment prescription recommendation device; 210 - symptom information acquisition module; 220 - recommended case acquisition module; 230 - recommended case selection interface generation module; 240 - prescription interface generation module. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0047] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] It should be noted that relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0049] See also Figure 1 , Figure 1 A schematic diagram of a process flow of a method for recommending TCM diagnosis and treatment prescriptions provided by an embodiment of the present invention is shown. The method for recommending TCM diagnosis and treatment prescriptions can be applied to electronic devices. The specific process of this embodiment is described below using electronic devices as an example. Figure 1 The process shown is described in detail, and the TCM diagnosis and treatment prescription recommendation method may specifically include the following steps:

[0050] Step 110: Obtain the disease information of the patient to be diagnosed.

[0051] In some embodiments, an expert experience sharing platform may be run in the electronic device, and a user may input the symptom information of a patient to be diagnosed and treated in the expert experience sharing platform, and the expert experience sharing platform may obtain the symptom information of the patient to be diagnosed and treated.

[0052] Among them, the disease information of the patient to be diagnosed includes the symptom information of the patient to be diagnosed, the name of the disease suffered by the patient to be diagnosed and the syndrome information. It should be noted that the symptom information is the direct manifestation of the disease suffered by the patient to be diagnosed; the syndrome information reflects the nature and development law of the disease suffered by the patient to be diagnosed, and is the basis of traditional Chinese medicine treatment. Users can collect the symptom and sign information of the patient to be diagnosed through methods such as observation, smell, questioning and palpation, and then conduct syndrome differentiation according to the theory of traditional Chinese medicine to determine the syndrome.

[0053] Step 120: Obtain at least one recommended case and a corresponding recommendation index from a pre-built expert experience case library according to the symptom information.

[0054] Among them, the expert experience case library is obtained by analyzing the expert diagnosis and treatment experience database.

[0055] In some embodiments, the electronic device can be communicatively connected to the server, an expert experience collection platform can be run in the electronic device, the expert experience collection platform can analyze the expert diagnosis and treatment experience database, obtain an expert experience case library, and send the expert experience case library to the server, and the expert experience sharing platform can obtain at least one recommended case and a corresponding recommendation index from the expert experience case library pre-built in the server based on the disease information.

[0056] The electronic device running the expert experience collection platform and the electronic device running the expert experience sharing platform may be the same electronic device; the electronic device running the expert experience collection platform and the electronic device running the expert experience sharing platform may also be different electronic devices.

[0057] Step 130: Generate a recommended case selection interface based on at least one recommended case and a corresponding recommendation index.

[0058] like Figure 2 As shown, the recommended case selection interface includes at least one selection control 231, and the selection control corresponds to the recommended case one by one. Each selection control 231 displays the corresponding recommended case and the recommendation index of the recommended case. The user can perform a selection operation on the selection control 231 corresponding to the selected recommended case. The selection operation can be a click and a keyboard input (shortcut key), etc.

[0059] Step 140: In response to the user's selection operation on the recommended case selection interface, a prescription interface is generated according to the prescription in the target recommended case selected by the user, so that the user can prescribe a prescription for the patient to be treated according to the prescription displayed on the prescription interface.

[0060] In some embodiments, the prescription interface may also display detailed information of the target recommended case so that the user can learn the target recommended case. The detailed information may include the effect of the drug after use during the diagnosis and treatment process and detailed symptom information.

[0061] In some embodiments, the prescription in the target recommendation case includes multiple drugs and the dosage of each drug. The user can adjust the drugs and the dosage in the prescription interface to prescribe for the patient to be treated.

[0062] like Figure 3 As shown, the prescription interface displays the multiple drugs included in the prescription of the target recommended case and the dosage of each drug. The prescription interface includes a delete control 232 for deleting the corresponding drug, a dose adjustment control 233 for adjusting the dosage of the corresponding drug, and a prescription control 234. The user can adjust the prescription through the delete control 232 and the dose adjustment control 233, and after the adjustment is completed, prescribe for the patient to be treated through the prescription control 234.

[0063] The method for recommending prescriptions for TCM diagnosis and treatment provided in the embodiment of the present invention obtains the symptom information of the patient to be diagnosed and treated, obtains at least one recommended case and a corresponding recommendation index from a pre-constructed expert experience case library based on the symptom information, and the expert experience case library is obtained by analyzing the expert diagnosis and treatment experience database. A recommended case selection interface is generated based on the at least one recommended case and the corresponding recommendation index, and a prescription interface is generated based on the prescription in the target recommended case selected by the user in response to the user's selection operation on the recommended case selection interface, so that the user can prescribe for the patient to be diagnosed and treated based on the prescription displayed on the prescription interface. By screening the recommended cases and the recommendation index of each recommended case from the expert experience case library based on the symptom information, the situation in which the accuracy and efficiency of TCM diagnosis and treatment are low due to the user's lack of diagnosis and treatment experience is avoided, thereby improving the accuracy and efficiency of TCM diagnosis and treatment.

[0064] In order to improve the accuracy of the recommended cases, the expert experience case library includes multiple diagnosis and treatment cases, such as Figure 4 As shown, step 120 specifically further includes the following steps:

[0065] Step 121: Process the symptom information to obtain target symptom characteristics.

[0066] In some embodiments, the expert experience sharing platform may convert the disease information into structured data through a text classification algorithm, wherein the text classification algorithm may include natural language processing (Natural Language Processing, NLP) and a preset keyword matching algorithm.

[0067] It should be noted that structured data has a clear format and definition, and can be quickly read and processed by the expert experience sharing platform, thereby improving the efficiency of the expert experience sharing platform in finding recommended cases.

[0068] In some embodiments, the expert experience sharing platform can extract features from disease information to obtain target disease features.

[0069] Step 122: Determine a recommended case based on the similarity values ​​between the target symptom characteristics and the symptoms of multiple diagnosis and treatment cases, and obtain a corresponding recommendation index based on the similarity values ​​corresponding to the recommended cases.

[0070] In some embodiments, the expert experience sharing platform can calculate the similarity values ​​between the target disease characteristics and the diseases of multiple diagnosis and treatment cases through a similarity algorithm, determine the recommended cases based on the similarity values ​​between the target disease characteristics and the diseases of multiple diagnosis and treatment cases, and obtain the corresponding recommendation index based on the similarity values ​​corresponding to the recommended cases.

[0071] As an implementation method, a preset similarity value is stored in the expert experience sharing platform, and the diagnosis and treatment cases with a similarity value greater than the preset similarity value are determined as recommended cases. For example, if the preset similarity value is 90%, the similarity value between the target symptom feature and the symptom of diagnosis and treatment case 1 is 0.8, and the similarity value between the target symptom feature and the symptom of diagnosis and treatment case 2 is 0.92, then diagnosis and treatment case 2 is determined as a recommended case.

[0072] As another implementation, the expert experience sharing platform stores a preset number of recommended cases. The expert experience sharing platform can sort the multiple diagnosis and treatment cases in descending order according to the similarity values ​​between the target symptom characteristics and the symptoms of the multiple diagnosis and treatment cases, obtain a diagnosis and treatment case sequence, and determine the diagnosis cases with the preset number of recommended cases starting from the first one in the diagnosis and treatment case sequence as recommended cases. For example, the similarity value between the target symptom characteristics and the symptoms of diagnosis and treatment case 1 is 0.8, the similarity value between the target symptom characteristics and the symptoms of diagnosis and treatment case 2 is 0.92, the similarity value between the target symptom characteristics and the symptoms of diagnosis and treatment case 3 is 0.7, and the similarity value between the target symptom characteristics and the symptoms of diagnosis and treatment case 4 is 0.98. According to the similarity values ​​between the target symptom characteristics and the symptoms of the multiple diagnosis and treatment cases, the multiple diagnosis and treatment cases are sorted in descending order, and the diagnosis and treatment case sequence obtained is diagnosis and treatment case 4, diagnosis and treatment case 2, diagnosis and treatment case 1, and diagnosis and treatment case 3. The preset number of recommended cases is 2, and diagnosis and treatment case 4 and diagnosis and treatment case 2 are determined as recommended cases.

[0073] In some implementations, the expert experience sharing platform may obtain a corresponding recommendation index according to a similarity value corresponding to the recommended case.

[0074] As an implementation method, the expert experience sharing platform can convert the similarity value corresponding to the recommended case into a percentage as a recommendation index. For example, if the similarity value of the recommended case is 0.8, the recommendation index of the recommended case is 80%.

[0075] As another implementation, the expert experience sharing platform stores the weighted coefficients of the similarity value and the weighted coefficients of the practicality index. The expert experience sharing platform can perform a practicality analysis on each recommended case to obtain the practicality index of each recommended case, and perform weighted calculations based on the weighted coefficients of the similarity value, the weighted coefficients of the practicality index, the similarity value corresponding to the recommended case, and the practicality index to obtain the recommendation index of the recommended case. For example, if the weighted coefficient of the similarity value is 60%, the weighted coefficient of the practicality index is 40%, the similarity value corresponding to the recommended case is 0.8, and the practicality index corresponding to the recommended case is 0.9, then the recommendation index of the recommended case is 0.84.

[0076] (60%*0.8+40%*0.9=0.84).

[0077] In order to make the expert experience case library more complete and continuously update and optimize the expert experience case library with feedback from actual applications, the above-mentioned method for recommending prescriptions for TCM diagnosis and treatment also includes the following steps: obtaining usage feedback information; using the feedback information to provide feedback information after the user uses the target recommended case; and optimizing the expert experience case library based on the usage feedback information.

[0078] In some embodiments, there is a feedback interface in the expert experience sharing platform, and users can view detailed information of the target recommended case in the feedback interface. Users can also enter usage feedback information to evaluate the effectiveness and practicality of the target recommended case in the feedback interface. The expert experience sharing platform can analyze multiple usage feedback information to obtain analysis results, optimize the expert experience case library according to the analysis results, modify or delete diagnosis and treatment cases with low evaluation and poor practicality, and improve diagnosis and treatment cases with high evaluation and good practicality.

[0079] In some implementations, the expert experience sharing platform uses feedback information to count key indicators such as the score, rate of favorable comments, and reasons for unfavorable comments of multiple target recommendation cases, and identifies changes in user preferences and needs to obtain analysis results.

[0080] In some implementations, for controversial usage feedback information, experts in the field may be invited to review it to obtain more authoritative opinions, and the expert experience case library may be optimized based on the experts' opinions.

[0081] like Figure 5 As shown in Figure 1, the expert experience case library is constructed through the following steps:

[0082] Step 310: Obtain expert diagnosis and treatment experience database.

[0083] Among them, the expert diagnosis and treatment experience database includes multiple expert diagnosis and treatment experience data, which include the patient's symptom information, diagnostic information, medication information, treatment strategies, and changes in the patient's condition during the expert's diagnosis and treatment process.

[0084] In some embodiments, the user can input the expert diagnosis and treatment experience data into the expert experience collection platform, and the expert experience collection platform can obtain multiple expert diagnosis and treatment experience data, and construct an expert diagnosis and treatment experience database based on the multiple expert diagnosis and treatment experience data.

[0085] Step 320: pre-process the expert diagnosis and treatment experience database to obtain a pre-processed experience database.

[0086] In some embodiments, deduplication processing is performed on multiple expert diagnosis and treatment experience data in the expert diagnosis and treatment database; outlier detection is performed on the multiple expert diagnosis and treatment experience data after deduplication processing, and the expert diagnosis and treatment experience data with outliers are deleted; after the expert diagnosis and treatment experience data with outliers are deleted, each remaining expert diagnosis and treatment experience data is unified to obtain a preprocessed experience database.

[0087] In some embodiments, the expert experience collection platform can set a preset dosage range for each drug based on the Chinese Pharmacopoeia standards and expert experience. The expert experience collection platform detects the dosage of each drug in the multiple expert diagnosis and treatment experience data after deduplication based on the preset dosage range of all drugs. If the test result fails, it is determined that the dosage of the drug in the expert diagnosis and treatment experience data is an abnormal value. The expert experience collection platform can also check the compatibility relationship between drugs in multiple expert diagnosis and treatment experience data. If there is an adverse reaction between drugs at a specific dose or there is a contraindication for compatibility between drugs, the drug used in the expert diagnosis and treatment experience data is determined to be an abnormal value.

[0088] In some embodiments, the expert experience collection platform may first check the expert diagnosis and treatment experience data with abnormal values ​​to see if there are any input errors. If there are any input errors, the corresponding expert diagnosis and treatment experience data will be corrected; if the expert diagnosis and treatment experience data with abnormal values ​​can be corrected to normal values, the expert diagnosis and treatment experience data will be corrected; if the expert diagnosis and treatment experience data with abnormal values ​​neither have input errors nor can be corrected to normal values, the expert diagnosis and treatment experience data with abnormal values ​​will be deleted.

[0089] In some embodiments, the symptom description information, diagnosis information, and medication information included in each remaining expert diagnosis and treatment experience data are uniformly processed to obtain a pre-processing experience database.

[0090] In some embodiments, the expert experience collection platform can uniformly process the symptom description information and diagnosis information included in each remaining expert diagnosis and treatment experience data, and unify the symptom description information and diagnosis information into professional medical terms.

[0091] For example, the symptom description information of expert diagnosis and treatment experience data 1 may be chest pain, and the diagnosis information of expert diagnosis and treatment experience data 1 may be heart disease; the symptom description information of expert diagnosis and treatment experience data 2 may be heart pressure, and the diagnosis information of expert diagnosis and treatment experience data 2 may be heart failure; the symptom description information of expert diagnosis and treatment experience data 1 (chest pain) and the symptom description information of expert diagnosis and treatment experience data 2 (heart pressure) are uniformly processed as angina pectoris, and the diagnosis information of expert diagnosis and treatment experience data 1 (heart disease) and the diagnosis information of expert diagnosis and treatment experience data 2 (heart failure) are uniformly processed as heart failure.

[0092] In some embodiments, the medication information includes the drug and the dosage. The expert experience collection platform can encode the drug and unify the unit of the dosage. For example, the drug in the expert diagnosis and treatment experience data 1 is licorice and the dosage is 0.1g, the drug in the expert diagnosis and treatment experience data 2 is licorice tablets and the dosage is 0.2g, and the drug in the expert diagnosis and treatment experience data 3 is roasted licorice and the dosage is 0.2G. Licorice, licorice tablets and roasted licorice are all unified drugs. Licorice, licorice tablets and roasted licorice are all coded as 001, and g, gram and G are unified as grams.

[0093] Step 330: Analyze the preprocessed experience database through a data mining algorithm to obtain multiple syndrome differentiation and medication rules; each syndrome differentiation and medication rule is a prescription for a corresponding disease.

[0094] Among them, data mining algorithms can include association rule learning algorithms, clustering analysis algorithms, machine learning models, and graph mining algorithms.

[0095] In some embodiments, analyzing the pre-treatment experience database through an association rule learning algorithm can reveal the synergistic effect or side effect between drugs; analyzing the pre-treatment experience database through a cluster analysis algorithm can obtain the difference in the response of patients with different diseases to drugs; analyzing the pre-treatment experience database through a machine learning model can predict the efficacy of drugs, the patient's response to drugs, the risk of adverse drug events, etc.; analyzing the pre-treatment experience database through a graph mining algorithm can be used to analyze the interaction relationship between drugs and discover potential drug combination effects or side effects. Specifically, the association rule learning algorithm can be Apriori and FP-growth; cluster analysis can include K-means, hierarchical clustering, etc.; machine learning models can include decision trees, random forests, neural networks, etc.; graph mining algorithms can include community detection, path finding, etc.

[0096] As an implementation method, one of the above-mentioned data mining algorithms is selected to analyze the preprocessed experience database to obtain multiple syndrome differentiation and medication rules.

[0097] As another implementation, multiple syndrome differentiation and medication rules are obtained by combining a plurality of the above data mining algorithms to analyze the preprocessed experience database.

[0098] Step 340: Obtain multiple diagnosis and treatment cases based on multiple syndrome differentiation and medication rules.

[0099] In some embodiments, the expert experience collection platform can perform structured processing on multiple syndrome differentiation and medication rules, and convert the multiple syndrome differentiation and medication rules into process form models to obtain multiple diagnostic cases. For example, if the patient exhibits XX symptoms, the tongue pattern is XX, and the pulse pattern is XX, then the diagnosis is considered to be XX syndrome type, and the use of XX drug combination is recommended.

[0100] It is understandable that structuring multiple rules of syndrome differentiation and medication can organize information clearly, making complex TCM theories easier to understand and remember, and can be easily processed, retrieved and analyzed by electronic equipment. Converting multiple rules of syndrome differentiation and medication into process form models can improve the efficiency of subsequent search for recommended cases.

[0101] Step 350: Obtain an expert experience case library based on multiple diagnosis and treatment cases.

[0102] The method for recommending prescriptions for TCM diagnosis and treatment provided by the embodiment of the present invention realizes the sharing of expert experience in treatment by building an expert experience case library, which helps to improve the accuracy and efficiency of TCM diagnosis and treatment and promote the development of TCM. At the same time, it can also provide rich practical experience resources for TCM teaching and scientific research, and promote the innovation and development of TCM.

[0103] In order to execute the corresponding steps in the above embodiments and various possible methods, a method for implementing a TCM diagnosis and treatment prescription recommendation device is given below. Figure 6 , FIG. is a functional module diagram of a TCM diagnosis and treatment prescription recommendation device provided by an embodiment of the present invention. It should be noted that the basic principle and technical effects of the TCM diagnosis and treatment prescription recommendation device provided by this embodiment are the same as those of the above-mentioned embodiments. For the sake of brief description, for parts not mentioned in this embodiment, please refer to the corresponding contents in the above-mentioned embodiments. The TCM diagnosis and treatment prescription recommendation device 200 includes: a symptom information acquisition module 210, a recommended case acquisition module 220, a recommended case selection interface generation module 230 and a prescription interface generation module 240, wherein:

[0104] The symptom information obtaining module 210 is used to obtain symptom information of the patient to be diagnosed and treated.

[0105] The recommended case acquisition module 220 is used to obtain at least one recommended case and a corresponding recommendation index from a pre-constructed expert experience case library according to the symptom information; the expert experience case library is obtained by analyzing the expert diagnosis and treatment experience database.

[0106] The recommended case selection interface generation module 230 is used to generate a recommended case selection interface according to at least one recommended case and a corresponding recommendation index.

[0107] The prescription interface generation module 240 is used to respond to the user's selection operation on the recommended case selection interface and generate a prescription interface based on the prescription in the target recommended case selected by the user, so that the user can prescribe for the patient to be treated according to the prescription displayed on the prescription interface.

[0108] Furthermore, the expert experience case library includes multiple diagnosis and treatment cases, and the recommended case acquisition module 220 is specifically used to process the symptom information to obtain the target symptom characteristics; determine the recommended case based on the similarity value between the target symptom characteristics and the symptoms of multiple diagnosis and treatment cases, and obtain the corresponding recommendation index based on the similarity value corresponding to the recommended case.

[0109] Furthermore, the recommended case obtaining module 220 is specifically used to extract features from the symptom information to obtain target symptom features.

[0110] Furthermore, the TCM diagnosis and treatment prescription recommendation device 200 also includes an expert experience case library optimization module, wherein:

[0111] The expert experience case library optimization module is used to obtain usage feedback information; use the feedback information to provide feedback information after the user uses the target case recommendation; and optimize the expert experience case library based on the usage feedback information.

[0112] Furthermore, the TCM diagnosis and treatment prescription recommendation device 200 also includes an expert experience case library construction module, wherein:

[0113] The expert experience case library construction module is used to obtain the expert diagnosis and treatment experience database; pre-process the expert diagnosis and treatment experience database to obtain the pre-processed experience database; analyze the pre-processed experience database through a data mining algorithm to obtain multiple syndrome differentiation and medication rules; each syndrome differentiation and medication rule is a prescription for the corresponding disease; based on the multiple syndrome differentiation and medication rules, multiple diagnosis and treatment cases are obtained; based on the multiple diagnosis and treatment cases, an expert experience case library is obtained.

[0114] Furthermore, the expert experience case library construction module is specifically used to deduplicate multiple expert diagnosis and treatment experience data in the expert diagnosis and treatment database; perform outlier detection on the multiple expert diagnosis and treatment experience data after deduplication, and delete the expert diagnosis and treatment experience data with outliers; after deleting the expert diagnosis and treatment experience data with outliers, perform unified processing on each remaining expert diagnosis and treatment experience data to obtain a preprocessed experience database.

[0115] Furthermore, the expert experience case library construction module is specifically used to unify the symptom description information, diagnosis information, and medication information included in each remaining expert diagnosis and treatment experience data to obtain a pre-processed experience database.

[0116] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0117] In several embodiments provided by the present invention, the coupling between modules may be electrical, mechanical or other forms of coupling.

[0118] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of software functional modules.

[0119] Please refer to Figure 7 , is a block diagram of an electronic device 100 provided in an embodiment of the present invention. The electronic device 100 includes a memory 110, a processor 120, and a communication module 130. The memory 110, the processor 120, and the communication module 130 are electrically connected to each other directly or indirectly to achieve data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines.

[0120] The memory 110 is used to store programs or data. The memory 110 may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc.

[0121] The processor 120 is used to read / write data or programs stored in the memory and execute corresponding functions. For example, when the computer program stored in the memory 110 is executed by the processor 120, the TCM diagnosis and treatment prescription recommendation method disclosed in the above embodiments can be implemented.

[0122] The communication module 130 is used to establish a communication connection between the electronic device 100 and a server through a network, and to send and receive data through the network.

[0123] It should be understood that Figure 7 The structure shown is only a schematic diagram of the structure of the electronic device. The electronic device may also include Figure 7 More or fewer components may be shown. Figure 7 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0124] An embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored. When the computer program can be executed by a processor, the method for recommending prescriptions for traditional Chinese medicine diagnosis and treatment described in the above method embodiment is implemented.

[0125] The computer-readable storage medium may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk, or a ROM. Optionally, the computer-readable storage medium includes a non-transitory computer-readable storage medium. The computer-readable storage medium has storage space for program codes that execute any of the method steps in the above method. These program codes can be read from or written to one or more computer program products. The program code can be compressed, for example, in an appropriate form.

[0126] In several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and a module, a program segment or a part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0127] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0128] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for recommending prescriptions for TCM diagnosis and treatment, characterized in that: The method comprises: Obtain information about the symptoms of patients to be diagnosed and treated; Obtaining at least one recommended case and a corresponding recommendation index from a pre-constructed expert experience case library according to the symptom information; the expert experience case library is obtained by analyzing an expert diagnosis and treatment experience database; Generating a recommended case selection interface according to at least one of the recommended cases and the corresponding recommendation index; In response to the user's selection operation on the recommended case selection interface, a prescription interface is generated according to the prescription in the target recommended case selected by the user, so that the user can prescribe a prescription for the patient to be treated according to the prescription displayed on the prescription interface.

2. The method according to claim 1, characterized in that The expert experience case library includes a plurality of diagnosis and treatment cases, and obtaining at least one recommended case and a corresponding recommendation index from the pre-built expert experience case library according to the symptom information includes: Processing the disease information to obtain target disease characteristics; The recommended case is determined according to the similarity value between the target disease feature and the diseases of the plurality of diagnosis and treatment cases, and the corresponding recommendation index is obtained according to the similarity value corresponding to the recommended case.

3. The method according to claim 2, characterized in that The step of processing the disease information to obtain target disease characteristics includes: Extract features from the disease information to obtain the target disease features.

4. The method according to claim 1, characterized in that The method further comprises: Acquiring usage feedback information; the usage feedback information is feedback information after the user uses the target recommended case; The expert experience case library is optimized according to the usage feedback information.

5. The method according to claim 1, characterized in that The expert experience case library is constructed by the following steps: Obtaining the expert diagnosis and treatment experience database; Preprocessing the expert diagnosis and treatment experience database to obtain a preprocessed experience database; Analyze the pre-processed experience database through a data mining algorithm to obtain multiple syndrome differentiation and medication rules; each syndrome differentiation and medication rule is a prescription for a corresponding disease; According to the plurality of syndrome differentiation and medication rules, a plurality of diagnosis and treatment cases are obtained; Based on the multiple diagnosis and treatment cases, the expert experience case library is obtained.

6. The method according to claim 5, characterized in that The preprocessing of the expert diagnosis and treatment experience database to obtain the preprocessed experience database includes: Deduplication processing is performed on multiple expert diagnosis and treatment experience data in the expert diagnosis and treatment database; Performing outlier detection on the plurality of expert diagnosis and treatment experience data after deduplication processing, and deleting the expert diagnosis and treatment experience data with outliers; After deleting the expert diagnosis and treatment experience data with abnormal values, each of the remaining expert diagnosis and treatment experience data is processed in a unified manner to obtain the pre-processing experience database.

7. The method according to claim 6, characterized in that The unification processing of each of the remaining expert diagnosis and treatment experience data to obtain the pre-processing experience database includes: The symptom description information, diagnosis information, and medication information included in each of the remaining expert diagnosis and treatment experience data are uniformly processed to obtain the pre-processing experience database.

8. A device for recommending prescriptions for traditional Chinese medicine diagnosis and treatment, characterized in that: The device comprises: A symptom information acquisition module is used to obtain symptom information of the patient to be diagnosed and treated; A recommended case acquisition module, used to obtain at least one recommended case and a corresponding recommendation index from a pre-built expert experience case library according to the symptom information; the expert experience case library is obtained by analyzing the expert diagnosis and treatment experience database; A recommended case selection interface generation module, used to generate a recommended case selection interface according to at least one of the recommended cases and the corresponding recommendation index; The prescription interface generation module is used to respond to the user's selection operation on the recommended case selection interface and generate a prescription interface based on the prescription in the target recommended case selected by the user, so that the user can prescribe for the patient to be treated according to the prescription displayed on the prescription interface.

9. An electronic device, characterized in that: It includes a processor and a memory, wherein the memory stores a computer program that can be executed by the processor, and the computer program executable by the processor is used to implement the method for recommending prescriptions for traditional Chinese medicine diagnosis and treatment as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for recommending prescriptions for TCM diagnosis and treatment as described in any one of claims 1 to 7 is implemented.

Images