Method and device for recommending prescription based on tongue picture information, medium, equipment and product

Abstract

The invention relates to the technical field of image processing, and particularly provides a method and device for recommending a prescription based on tongue picture information, a medium, equipment and a product, and the method can comprise the steps: carrying out the feature extraction of a tongue picture image of a target object, and obtaining the key features of the tongue picture; performing permutation and combination on all features in the tongue picture key features to obtain multiple groups of tongue picture features; wherein each group of tongue picture characteristics of the plurality of groups of tongue picture characteristics comprises a normal tongue picture characteristic type and a special tongue picture characteristic type; based on a medicine rule base, recommended medicine prescriptions corresponding to each group of tongue picture characteristics are generated, the medicine rule base contains medicine information corresponding to different tongue picture characteristics, the recommended medicine prescriptions comprise medicine names and dosage ratios, and the recommended medicine prescriptions are used for providing auxiliary suggestions for doctors to make personalized prescriptions. According to some embodiments of the invention, intelligent extraction can be realized, and reliable reference suggestions are provided for doctors.

Description

Technical Field

[0001] The present application relates to the technical field of image processing. Specifically, it relates to a method, device, medium, equipment and product for recommending prescriptions based on tongue image information. Background Art

[0002] With the popularization and development of intelligent medicine and digital traditional Chinese medicine, the development of traditional Chinese medicine has shifted to a data-driven model. Traditional tongue diagnosis basically relies entirely on doctors' manual observation. Doctors observe the state of the user's tongue and then, after face-to-face consultation, prescribe corresponding prescriptions for the user. However, traditional Chinese medicine involves a lot of complex knowledge, and the characteristics of various Chinese herbal medicines are also different. The way of face-to-face consultation in traditional Chinese medicine cannot meet the needs of a large number of users and takes a long time; moreover, relying solely on the way of manual diagnosis has low intelligence, lacks personalized processing, and the diagnosis process is time-consuming and vulnerable to subjective factors.

[0003] Therefore, how to provide a technical solution for a method of recommending prescriptions based on tongue image information with relatively high reliability has become a technical problem that urgently needs to be solved. Summary of the Invention

[0004] Some embodiments of the present application aim to provide a method, device, medium, equipment and product for recommending prescriptions based on tongue image information. Through the technical solutions of the embodiments of the present application, appropriate drug prescription suggestions can be recommended for the target object based on tongue image information, which can provide reliable auxiliary suggestions for doctors and realize intelligent services.

[0005] In a first aspect, some embodiments of the present application provide a method for recommending prescriptions based on tongue image information, including: extracting features from the tongue image of the target object to obtain key tongue features; performing permutation and combination on all the features in the key tongue features to obtain multiple groups of tongue features; wherein each group of tongue features in the multiple groups of tongue features includes a normal tongue feature type and a special tongue feature type; generating a recommended drug prescription corresponding to each group of tongue features based on a medical rule library, wherein the medical rule library contains drug information corresponding to different tongue features, and the recommended drug prescription includes: drug name and dosage ratio, and the recommended drug prescription is used to provide auxiliary suggestions for doctors to prescribe personalized prescriptions.

[0006] In some embodiments of the present application, multiple groups of tongue image features are obtained by permuting and combining the key tongue image features of the extracted target object, and each group of tongue image features in the multiple groups of tongue image features is analyzed in combination with a medical rule base to generate a corresponding recommended drug prescription. In some embodiments of the present application, through the automatic extraction, combination, and analysis of the tongue image of the target object, a recommended drug prescription with relatively high reliability and reference value is provided for doctors, and at the same time, an intelligent consultation service for the target object is realized, enabling the target object to better understand their own situation; this intelligent consultation service can improve the consultation efficiency, reduce the influence caused by subjective factors, and provide objective and reliable reference suggestions for the target object and doctors.

[0007] In some embodiments, the feature extraction of the tongue image of the target object to obtain the key tongue image features includes: identifying the tongue image to obtain the key regions corresponding to different parts of the tongue; wherein, the parts include: the tongue surface and the tongue bottom; matching the key regions according to the tongue image analysis rules to obtain the key tongue image features, where the key tongue image features include the relevant features of the tongue texture, tongue shape, and tongue coating of the tongue surface and the tongue bottom.

[0008] In some embodiments of the present application, the key tongue image features are accurately extracted after the tongue image is identified and located, with relatively high efficiency.

[0009] In some embodiments, the permutation and combination of all the features in the key tongue image features to obtain multiple groups of tongue image features includes: dividing all the features in the key tongue image features into the normal tongue image feature type and the characteristic tongue image feature type; using the tongue image permutation and combination algorithm to perform permutation and combination on the normal tongue image feature type and the characteristic tongue image feature type to obtain the multiple groups of tongue image features.

[0010] In some embodiments of the present application, multiple groups of tongue image features are obtained by classifying and then permuting and combining the key tongue image features, realizing the random combination of the key tongue image features and providing effective data support for subsequent prescription recommendation.

[0011] In some embodiments, generating a recommended drug prescription corresponding to each group of tongue image features based on the medical rule base includes: retrieving the physical constitution information corresponding to each group of tongue image features from the medical rule base; determining the recommended drug prescription through the physical constitution information.

[0012] In some embodiments of the present application, the physical constitution information of the target object is determined through the medical rule base and the tongue image features, and then the recommended drug prescription is determined, which can improve the accuracy of prescription recommendation.

[0013] In some embodiments, generating a recommended drug prescription corresponding to each group of tongue image features based on the medical rule base includes: retrieving a drug combination corresponding to each group of tongue image features from the medical rule base; and integrating the drug combinations corresponding to each group of tongue image features to obtain the recommended drug prescription.

[0014] In some embodiments of the present application, by first matching the drug combination corresponding to each group of tongue image features and then integrating to obtain the final recommended drug prescription, the efficiency and accuracy of prescription recommendation can be improved.

[0015] In some embodiments, after generating the recommended drug prescription corresponding to each group of tongue image features based on the medical rule base, the method further includes: in response to an operation instruction of the doctor, obtaining prescription modification content corresponding to the recommended drug prescription; and generating a personalized prescription file corresponding to the prescription modification content, where the personalized prescription file includes: drug types, drug doses, usage methods, and precautions.

[0016] In some embodiments of the present application, after obtaining the prescription modification content by responding to the doctor's operation instruction, a personalized prescription file is automatically generated, realizing the efficient integration of prescription content, facilitating the target object to view, and enhancing the intelligent service experience of the target object.

[0017] In a second aspect, some embodiments of the present application provide a device for recommending a prescription based on tongue image information, including: an extraction module, configured to extract features from a tongue image of a target object to obtain key tongue image features; a combination module, configured to perform permutation and combination on all the features in the key tongue image features to obtain multiple groups of tongue image features, where each group of tongue image features in the multiple groups of tongue image features includes a normal tongue image feature type and a special tongue image feature type; and a recommendation module, configured to generate a recommended drug prescription corresponding to each group of tongue image features based on a medical rule base, where the medical rule base contains drug information corresponding to different tongue image features, and the recommended drug prescription includes: drug names and dosage ratios, and the recommended drug prescription is used to provide auxiliary suggestions for a doctor to issue a personalized prescription.

[0018] In a third aspect, some embodiments of the present application provide a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the method described in any embodiment of the first aspect can be implemented.

[0019] In a fourth aspect, some embodiments of the present application provide an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where when the processor executes the program, the method described in any embodiment of the first aspect can be implemented.

[0020] Fifth aspect, some embodiments of the present application provide a computer program product, the computer program product includes a computer program, wherein, when the computer program is executed by a processor, the method described in any one of the embodiments of the first aspect can be implemented. Description of the Drawings

[0021] In order to more clearly illustrate the technical solutions of some embodiments of the present application, the accompanying drawings required for use in some embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0022] Figure 1 System diagram for recommending prescriptions based on tongue image information provided by some embodiments of the present application;

[0023] Figure 2 One of the method flowcharts for recommending prescriptions based on tongue image information provided by some embodiments of the present application;

[0024] Figure 3 Another method flowchart for recommending prescriptions based on tongue image information provided by some embodiments of the present application;

[0025] Figure 4 Block diagram of the device for recommending prescriptions based on tongue image information provided by some embodiments of the present application;

[0026] Figure 5 Schematic diagram of an electronic device provided by some embodiments of the present application. Detailed Embodiments

[0027] Next, the technical solutions in some embodiments of the present application will be described in conjunction with the accompanying drawings in some embodiments of the present application.

[0028] It should be noted that: similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of the present application, terms such as "first", "second", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0029] In the solutions of the prior art, traditional tongue diagnosis relies on doctors' manual observation and usually gives prescription suggestions after face-to-face consultations. In this way, doctors need to conduct face-to-face consultations and observations, which takes a long time and cannot quickly handle a large number of patients. Moreover, tongue analysis depends on doctors' experience, and different doctors may give different diagnostic opinions and prescription suggestions. From the above related technologies, it can be seen that the current intelligence level of traditional Chinese medicine based on tongue diagnosis is low, lacking personalized processing, and the diagnosis process is time-consuming and vulnerable to subjective factors, and cannot provide self-help consultation services for patients.

[0030] In view of this, some embodiments of the present application provide a method for recommending prescriptions based on tongue image information. After extracting the features of the tongue image of the target object, this method performs permutations and combinations on the extracted key tongue features to obtain multiple groups of tongue features; then, in combination with the medical rule base, it determines the recommended drug prescriptions corresponding to each group of tongue features. The recommended drug prescriptions can provide auxiliary references for doctors during consultations, avoiding the influence of subjective factors, being objective and reliable; moreover, the entire process does not require manual participation, realizing intelligent consultation, enabling the target object to know their own situation, improving the consultation efficiency, and saving time costs.

[0031] The following Figure 1 exemplarily elaborates the overall composition structure of the system for recommending prescriptions based on tongue image information provided by some embodiments of the present application.

[0032] As Figure 1 shown, some embodiments of the present application provide a system for recommending prescriptions based on tongue image information. The system for recommending prescriptions based on tongue image information may include: a terminal 100 and a processing server 200. Among them, the acquisition device (such as a camera device) connected to the terminal 100 can provide voice or text guidance to the target object, so that the target object is in the acquisition position, realizing the accurate acquisition of the tongue image of the target object. The terminal 100 can send the tongue image to the processing server 200, and the processing server 200 can perform feature extraction, feature permutation and combination, and analysis on the tongue image to generate a recommended drug prescription. The entire process does not require manual participation and has a high degree of intelligence.

[0033] In some other embodiments of the present application, if the terminal 100 has functions related to feature extraction, feature permutation and combination, and analysis of the tongue image by the processing server 200, the processing server 200 may not be set at this time; specifically, it can be set according to the actual application scenario, and the embodiments of the present application do not make specific limitations here.

[0034] In some embodiments of the present application, the terminal 100 can be a mobile terminal or a non-portable computer terminal; the acquisition device can be a camera device dedicated to acquiring tongue images or other types of acquisition terminals. The embodiments of the present application do not make specific limitations here.

[0035] The following will exemplarily elaborate on the implementation process of recommending prescriptions based on tongue image information executed by the processing server 200 provided by some embodiments of the present application in conjunction with the attached Figure 2 drawings.

[0036] Please refer to the attached Figure 2 drawings Figure 2 which is a flowchart of a method for recommending prescriptions based on tongue image information provided by some embodiments of the present application. The method for recommending prescriptions based on tongue image information may include:

[0037] S210, extract features from the tongue image of the target object to obtain the key tongue image features.

[0038] For example, in some embodiments of the present application, the device side (i.e., the acquisition device) may acquire the tongue image of a patient (a specific example of the target object), where the tongue image includes the tongue surface image and the tongue bottom image. Then, deep learning technology is used to analyze the tongue image to extract the key tongue image features.

[0039] In some embodiments of the present application, S210 may include: identifying the tongue image to obtain the key regions corresponding to different parts of the tongue image; where the parts include: the tongue surface and the tongue bottom; matching the key regions according to the tongue image analysis rules to obtain the key tongue image features, where the key tongue image features include the relevant features of the tongue texture, tongue shape, and tongue coating of the tongue surface and the tongue bottom.

[0040] For example, in some embodiments of the present application, a deep learning algorithm is called to analyze and locate the tongue surface image and the tongue bottom image of the patient respectively. Specifically, the tongue surface and tongue bottom parts in the tongue image are located and masked to identify the key analysis parts, and the key analysis parts include: tongue shape, tongue coating, and tongue texture. Analyze the key analysis parts according to the tongue image analysis rules to obtain the key tongue image features. The tongue image analysis rules include: tongue image color classification, tongue image texture analysis, color space conversion, tongue coating region segmentation, tongue shape analysis, tongue image edge detection, etc. Through the tongue image analysis rules, accurate identification and classification of the tongue bottom image and the tongue surface image can be achieved, and the key tongue image features can be determined.

[0041] S220, perform permutations and combinations on all the features in the key tongue image features to obtain multiple groups of tongue image features; where each group of tongue image features in the multiple groups of tongue image features includes a normal tongue image feature type and a special tongue image feature type.

[0042] For example, in some embodiments of the present application, each of the key tongue image features of the patient is arranged and combined through an AI tongue image arrangement and combination algorithm to generate a combination list that includes all possible normal tongue image feature types and special tongue image feature types (as a specific example of multiple groups of tongue image features). This AI tongue image arrangement and combination algorithm not only considers single tongue image features but also generates multiple combination schemes based on the cooperation of different tongue images (i.e., normal and special tongue images).

[0043] Specifically, in an actual scenario, the tongue image features include: normal tongue image feature types (abbreviated as normal tongue images) and special tongue image feature types (abbreviated as special tongue images). Among them, the normal tongue image feature types include normal tongue substance, normal tongue shape, and normal tongue coating; the special tongue image feature types include special tongue substance, special tongue shape, and special tongue coating. For example, the colors of normal tongue substance are: light red, light white, red and crimson, cyanotic and purple, or light and dull, etc.; normal tongue shapes include: normal, swollen tongue, or thin tongue, etc.; normal tongue coatings include: thin white coating, thin white and slippery coating, thin white and dry coating, white and greasy coating, white and dry coating, thin yellow coating, yellow and greasy coating, yellow and dry coating, purulent and putrid coating, or gray and black and moist coating, etc. The colors of special tongue substance include: dark red, light white, etc.; special tongue shapes include: prickled tongue, scalloped tongue, or fissured tongue, etc.; special tongue coatings include: exfoliated coating in the front, exfoliated coating in the middle, exfoliated coating at the root, map-like exfoliated coating, geographic tongue, or mirror-like tongue, etc.

[0044] In some embodiments of the present application, S220 may include: classifying all the features in the key tongue image features into the normal tongue image feature types and the special tongue image feature types; using the tongue image arrangement and combination algorithm to arrange and combine the normal tongue image feature types and the special tongue image feature types to obtain the multiple groups of tongue image features.

[0045] For example, in some embodiments of the present application, according to the tongue image classification rules, the key tongue image features of the patient are classified into two categories: normal tongue images and special tongue images. That is, all the features in the key tongue image features of the patient are divided into two categories according to the relevant content of the above-listed normal tongue images and special tongue images (as a specific example of the tongue image classification rules). One category is the normal tongue images existing in the patient, and the other category is the special tongue images existing in the patient. Through the AI tongue image arrangement and combination algorithm, all the normal composition results + special tongue image composition results of the information collected from the current patient are obtained to get multiple groups of tongue image features. That is to say, each group of tongue image features in the multiple groups of tongue image features contains both normal and special types of tongue images. Each tongue image feature in the key tongue image features is combined, and finally a possible combination list (i.e., multiple groups of tongue image features) is generated, which includes the tongue image features corresponding to each combination. Each group of tongue image features is a theoretically possible tongue image result and represents different constitutions or pathological states. For example, in a group of tongue image features, the tongue shape on the tongue surface is scalloped tongue, the tongue coating is white and greasy coating, and the tongue substance is light red.

[0046] Through the above permutations and combinations, a comprehensive combination list that combines "normal tongue images" and "special tongue images" can be formed. This list includes the tongue image features of the patient and all possible combination types.

[0047] It should be understood that the classification methods and contents of normal tongue images and special tongue images can be adjusted according to the actual application scenarios, and the embodiments of the present application are not limited thereto.

[0048] S230, based on the medical rule base, generate a recommended drug prescription corresponding to each group of tongue image features, where the medical rule base contains drug information corresponding to different tongue image features, and the recommended drug prescription includes: drug name and dosage ratio, and the recommended drug prescription is used to provide auxiliary suggestions for doctors to issue personalized prescriptions.

[0049] For example, in some embodiments of the present application, the medical rule base is pre-constructed, and its content includes various different tongue image features, as well as the physique information and symptomatic medicinal materials corresponding to a single tongue image feature or a combination of multiple tongue image features. Through each group of tongue image features of the patient, a recommended drug prescription that suits their situation can be determined in the medical rule base.

[0050] In some embodiments of the present application, S230 may include: retrieving the physique information corresponding to each group of tongue image features from the medical rule base; and determining the recommended drug prescription based on the physique information.

[0051] For example, in some embodiments of the present application, through the characteristic key information in each group of tongue image features, the physique information or pathological conditions corresponding to this characteristic key information can be retrieved from the medical rule base. For example, a certain specific combination of tongue image features may indicate problems such as internal heat toxin, dampness, or yin deficiency and excessive fire in the body. Through the physique information or pathological information, the corresponding recommended drug prescription can be matched from the medical rule base.

[0052] Subsequently, the AI algorithm deployed within the system can also perform comprehensive analysis by combining past prescriptions with key tongue image features or each group of tongue image features. The system will automatically give a medication addition or subtraction plan, that is, add or subtract medications in the recommended drug prescription to obtain a more reliable recommended drug prescription. For example: If a combination of tongue image features includes "cracked tongue" and "punctate tongue", it indicates heat toxin in the body and may require adding heat-clearing and detoxifying medications such as Coptis chinensis, honeysuckle, forsythia, etc., and the system will recommend this content. If a tongue image combination includes "toothed tongue" and "damp tongue coating", it represents spleen deficiency with water dampness, and the system may recommend adding medications for strengthening the spleen and resolving dampness such as Atractylodes macrocephala and Poria cocos. If the combination includes "thin white tongue coating" and "red tongue", it may indicate yang deficiency or excessive fire, and the system will recommend medications for warming and tonifying yang qi or clearing heat. Based on the content recommended by the system, the recommended drug prescription can be processed by adding or subtracting medications to obtain the final recommended drug prescription for doctors' reference.

[0053] It can be understood that after matching the recommended drug prescription from the medical rule library, it can also be comprehensively determined based on the medications recommended by the system automatically according to the key tongue image features or each group of tongue image features. That is, if such medications recommended by the system are not in the recommended drug prescription, they can be added, and if it is detected that such medications are added repeatedly, they can be automatically deleted to achieve automatic update and correction of the recommended drug prescription.

[0054] It should be noted that in actual application scenarios, the recommended drug prescription can be determined only by relying on the medical rule library, or it can be determined by combining the medical rule library and the system's automatic recommendation. The embodiments of the present application are not limited to this.

[0055] In some other embodiments of the present application, S230 may include: retrieving the drug combinations corresponding to each group of tongue image features from the medical rule library; integrating the drug combinations corresponding to each group of tongue image features to obtain the recommended drug prescription.

[0056] For example, in some other embodiments of the present application, there may be drug combinations corresponding to different tongue image feature combinations in the medical rule library. After obtaining the drug combinations corresponding to each group of tongue image features, and then integrating them, the recommended drug prescription applicable to the target object is determined. The integration method is not limited to addition or subtraction of drug dosages.

[0057] After obtaining the recommended drug prescription as described above, it can be used for doctors' reference. Doctors can adjust and optimize it according to the patient's specific condition, other clinical examination results, medical history, etc.; or the system further adjusts the drug ratio according to different physical constitution information (such as deficiency-cold, excess-heat, damp stagnation, etc.). If certain medications do not match the patient's physical constitution, experts can also decide whether to increase or decrease certain medicinal materials according to the changes in the tongue image. Finally, the doctor inputs the prescription modification content on the terminal 100.

[0058] In some embodiments of the present application, after executing S230, the method for recommending a prescription based on tongue image information may further include: in response to the operation instruction of the doctor, obtaining the prescription modification content corresponding to the recommended drug prescription; generating the personalized prescription file corresponding to the prescription modification content, where the personalized prescription file includes: drug type, drug dosage, usage method, and precautions.

[0059] For example, in some embodiments of the present application, after the terminal 100 obtains the latest prescription modification content, it may automatically generate a personalized prescription file according to the latest prescription modification content. The personalized prescription file contains explanatory content related to the usage and dosage of the drug for the patient to view. The personalized prescription file can also be subsequently recognized by the processing server 200, and according to the latest collected tongue surface image of the patient, the content in the personalized prescription file can be dynamically adjusted to give adjustment suggestions that conform to the current situation of the patient. For example, through the latest tongue surface image of the patient, it can be seen that a certain special tongue image has returned to normal. At this time, the drug dosage corresponding to this feature can be reduced according to the rules. It should be understood that the reduced prescription file is not used as a direct diagnosis basis. It is only for the patient and the doctor to understand the current situation, and the system only gives objective suggestions.

[0060] The following Figure 3 Exemplarily elaborates the specific process of the method for recommending a prescription based on tongue image information provided by some embodiments of the present application.

[0061] Please refer to the Figure 3 , Figure 3 which is a flowchart of a method for recommending a prescription based on tongue image information provided by some embodiments of the present application.

[0062] The above process is exemplarily elaborated below.

[0063] S310, obtain the tongue surface image of the patient.

[0064] S320, use the feature extraction algorithm to identify and analyze the tongue surface image to obtain the key tongue image features.

[0065] Among them, the feature extraction algorithm contains the tongue image analysis rules described above.

[0066] S330, classify all the features in the key tongue image features into normal tongue image feature types and characteristic tongue image feature types.

[0067] S340, use the tongue image permutation and combination algorithm to perform permutation and combination on the normal tongue image feature types and characteristic tongue image feature types to obtain multiple groups of tongue image features.

[0068] S350, generate a recommended drug prescription corresponding to each group of tongue image features based on a medical rule base.

[0069] S360, in response to a doctor's operation instruction, obtain prescription modification content corresponding to the recommended drug prescription.

[0070] S370, generate a personalized prescription file corresponding to the prescription modification content.

[0071] It can be understood that the specific implementation processes of S310 to S370 can refer to the method embodiments provided above. To avoid repetition, the detailed description is appropriately omitted here.

[0072] From some embodiments of the present application described above, it can be seen that throughout the process of the present application, through the automatic recognition and analysis of tongue image, the system can capture the subtle changes of the patient's tongue image in an efficient and accurate manner, avoiding the deviation of manual judgment. At the same time, using AI technology can process a large amount of data, which is more efficient and stable than manual inspection. Especially in the process of large-scale diagnosis and treatment, it avoids the errors caused by doctor fatigue or experience differences, and improves the accuracy and consistency of the consultation suggestions. By combining tongue image features and considering the cross-influence of different features, complete auxiliary information is provided for experts. Moreover, the AI algorithm in the system can provide professional suggestions on adding or subtracting medicinal materials, helping doctors formulate more appropriate prescriptions according to the specific pathological conditions of patients, thereby improving the treatment effect.

[0073] Please refer to Figure 4 , Figure 4 which shows a block diagram of the composition of a prescription recommendation device based on tongue image information provided by some embodiments of the present application. It should be understood that this prescription recommendation device based on tongue image information corresponds to the above method embodiments and can execute each step involved in the above method embodiments. The specific functions of this prescription recommendation device based on tongue image information can be seen in the above description. To avoid repetition, the detailed description is appropriately omitted here.

[0074] Figure 4The device for recommending prescriptions based on tongue image information includes at least one software function module that can be stored in a memory in the form of software or firmware or solidified in the device for recommending prescriptions based on tongue image information. The device for recommending prescriptions based on tongue image information includes: an extraction module 410, which is used to extract features from the tongue image of the target object and obtain key features of the tongue image; a combination module 420, which is used to arrange and combine all features in the key features of the tongue image to obtain multiple groups of tongue image features; wherein each group of tongue image features in the multiple groups of tongue image features includes a normal tongue image feature type and a special tongue image feature type; a recommendation module 430, which is used to generate a recommended drug prescription corresponding to each group of tongue image features based on a medical rule library, wherein the medical rule library contains drug information corresponding to different tongue image features, and the recommended drug prescription includes: drug name and drug dosage ratio, and the recommended drug prescription is used to provide auxiliary suggestions for doctors to prescribe personalized prescriptions.

[0075] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the device described above can refer to the corresponding process in the aforementioned method, and will not be described in detail here.

[0076] Some embodiments of the present application further provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, can implement the operations of the method corresponding to any of the above methods provided in the above embodiments.

[0077] Some embodiments of the present application further provide a computer program product, which includes a computer program, wherein when the computer program is executed by a processor, it can implement the operations corresponding to any of the above methods provided in the above embodiments.

[0078] like Figure 5 As shown, some embodiments of the present application provide an electronic device 500, which includes: a memory 510, a processor 520, and a computer program stored in the memory 510 and executable on the processor 520, wherein the processor 520 can implement a method as described in any of the above embodiments when reading the program from the memory 510 through a bus 530 and executing the program.

[0079] Processor 520 can process digital signals and can include various computing structures, such as complex instruction set computer structure, reduced instruction set computer structure, or a structure that implements a combination of multiple instruction sets. In some examples, processor 520 can be a microprocessor.

[0080] The memory 510 can be used to store instructions executed by the processor 520 or data related to the instruction execution process. These instructions and / or data may include code for implementing some or all of the functions of one or more modules described in the embodiments of the present application. The processor 520 of the embodiments of the present disclosure can be used to execute the instructions in the memory 510 to implement the method shown above. The memory 510 includes dynamic random access memory, static random access memory, flash memory, optical memory, or other memories well known to those skilled in the art.

[0081] The above are only the embodiments of the present application and are not intended to limit the protection scope of the present application. For those skilled in the art, the present application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application. It should be noted that similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0082] As mentioned above, this is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, and all should be covered by the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

[0083] 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 variation thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising a..." does not exclude the existence of additional identical elements in the process, method, article or device comprising the element.

Claims

1. A method for recommending prescriptions based on tongue image information, characterized in that: include: Extract features from the tongue image of the target object to obtain key features of the tongue image; Arrange and combine all the features in the tongue image key features to obtain multiple groups of tongue image features; wherein each group of tongue image features in the multiple groups of tongue image features includes a normal tongue image feature type and a special tongue image feature type; Based on the medical rule base, a recommended drug prescription corresponding to each group of tongue image features is generated, wherein the medical rule base contains drug information corresponding to different tongue image features, and the recommended drug prescription includes: drug name and dosage ratio, and the recommended drug prescription is used to provide auxiliary suggestions for doctors to prescribe personalized prescriptions.

2. The method according to claim 1, characterized in that The step of extracting features from the tongue image of the target object to obtain key features of the tongue image includes: Identify the tongue image to obtain key areas corresponding to different parts of the tongue image; wherein the parts include: tongue surface and tongue bottom; The key areas are matched according to the tongue image analysis rules to obtain the key features of the tongue image, wherein the key features of the tongue image include the relevant features of the tongue quality, tongue shape and tongue coating of the tongue surface and the tongue base.

3. The method according to claim 1 or 2, characterized in that All the features in the tongue image key features are arranged and combined to obtain multiple groups of tongue image features, including: Dividing all the features of the tongue image key features into the normal tongue image feature type and the characteristic tongue image feature type; The tongue image permutation and combination algorithm is used to permutate and combine the normal tongue image feature type and the characteristic tongue image feature type to obtain the multiple groups of tongue image features.

4. The method according to claim 1 or 2, characterized in that: The method of generating a recommended drug prescription corresponding to each group of tongue image characteristics based on the medical rule base includes: Retrieving the constitution information corresponding to each group of tongue image characteristics from the medical rule library; The recommended drug prescription is determined based on the physical condition information.

5. The method according to claim 1 or 2, characterized in that: The method of generating a recommended drug prescription corresponding to each group of tongue image characteristics based on the medical rule base includes: Retrieving a drug combination corresponding to each group of tongue image features from the medical rule library; The drug combinations corresponding to each group of tongue image characteristics are integrated to obtain the recommended drug prescription.

6. The method according to claim 1 or 2, characterized in that: After generating a recommended drug prescription corresponding to each group of tongue image features based on the medical rule base, the method further includes: In response to the doctor's operation instruction, obtaining prescription modification content corresponding to the recommended drug prescription; Generate a personalized prescription file corresponding to the prescription modification content, wherein the personalized prescription file includes: drug type, drug dosage, usage method and precautions.

7. A device for recommending prescriptions based on tongue image information, characterized in that: include: An extraction module is used to extract features from the tongue image of the target object and obtain key features of the tongue image; A combination module, used for arranging and combining all the features in the tongue image key features to obtain multiple groups of tongue image features; wherein each group of tongue image features in the multiple groups of tongue image features includes a normal tongue image feature type and a special tongue image feature type; The recommendation module is used to generate a recommended drug prescription corresponding to each group of tongue image features based on a medical rule base, wherein the medical rule base contains drug information corresponding to different tongue image features, and the recommended drug prescription includes: drug name and dosage ratio, and the recommended drug prescription is used to provide auxiliary suggestions for doctors to prescribe personalized prescriptions.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program executes the method according to any one of claims 1 to 6 when executed by a processor.

9. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the computer program executes the method according to any one of claims 1 to 6 when being run by the processor.

10. A computer program product, characterized in that The computer program product comprises a computer program, wherein the computer program executes the method according to any one of claims 1 to 6 when executed by a processor.

Images