Therapeutic regimen detection method executed by electronic device

Abstract

The invention provides a treatment scheme detection method executed by electronic equipment. The treatment scheme detection method can be applied to the technical field of artificial intelligence and medical treatment. The method comprises the following steps: in response to a received treatment scheme about a to-be-treated disease of a target user input in a medical inquiry interface, detecting a drug taking mode of the treatment scheme according to actual priorities and recommendation priorities of respective actual drug taking modes of a plurality of treatment drugs in the treatment scheme, obtaining a taking mode detection result; according to the dose deviation degree of the plurality of treatment drugs, detecting the respective doses of the plurality of treatment components in the plurality of treatment drugs to obtain a dose detection result; and determining a target detection result of the treatment scheme according to the taking mode detection result and the dose detection result. By means of the method, multi-level and high-precision detection of the medicine taking mode, the medicine dosage and the therapeutic ingredient dosage can be achieved, the therapeutic scheme detection precision is improved, and the labor cost is reduced.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of artificial intelligence and medical technology, in particular to a treatment plan detection method performed by an electronic device. BACKGROUND

[0002] With the wide application of outpatient medical insurance services, users can not only obtain prescription drugs through the outpatient department of a hospital, but also obtain prescription drugs online. However, the authenticity and rationality of prescription management have become a major problem in medical and health reform. At present, in order to verify the authenticity and rationality of the prescription, the prescription issued by the doctor is usually manually checked to determine whether the drugs in the prescription are reasonable.

[0003] However, manual checking of the prescription results in a large amount of human cost, and the checking efficiency is low for a large number of prescriptions, and the detection accuracy of the prescription is low. SUMMARY

[0004] Therefore, the present disclosure provides a treatment plan detection method, device, electronic device, medium and program product performed by an electronic device.

[0005] According to a first aspect of the present disclosure, a treatment plan detection method performed by an electronic device is provided, comprising:

[0006] In response to receiving a treatment plan for a target user's to-be-treated disease input in a medical consultation interface, detecting the drug taking mode of the treatment plan according to the actual priority and the recommended priority of the actual drug taking mode of each of the plurality of treatment drugs in the treatment plan, obtaining a drug taking mode detection result, and the recommended priority is the priority corresponding to the recommended drug taking mode of the treatment drug in the database;

[0007] According to the dose deviation degree of the plurality of treatment drugs, detecting the dose of each of the plurality of treatment components in the plurality of treatment drugs to obtain a dose detection result, and the dose deviation degree is determined according to the body weight adjustment coefficient of the target user, the recommended dose of the treatment drug in the database and the actual dose of the treatment drug in the treatment plan;

[0008] According to the drug taking mode detection result and the dose detection result, determining the target detection result of the treatment plan.

[0009] The second aspect of the present disclosure provides a treatment plan detection device performed by an electronic device, comprising:

[0010] The taking mode detection module is configured to, in response to receiving the treatment plan for the target user's to-be-treated disease input in the medical consultation interface, detect the taking mode of the treatment plan according to actual priorities and recommended priorities of actual taking modes of the plurality of treatment drugs in the treatment plan, and obtain a taking mode detection result, wherein the recommended priority is a priority corresponding to a recommended taking mode of the treatment drug in the database;

[0011] The dose detection module is configured to detect the dose of each of the plurality of therapeutic components in the plurality of treatment drugs according to a dose deviation degree of the plurality of treatment drugs, and obtain a dose detection result, wherein the dose deviation degree is determined according to the body weight adjustment coefficient of the target user, the recommended dose of the treatment drug in the database, and the actual dose of the treatment drug in the treatment plan.

[0012] The detection result determination module is configured to determine a target detection result of the treatment plan according to the taking mode detection result and the dose detection result.

[0013] The third aspect of the present disclosure provides an electronic device, comprising: one or more processors; a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the method.

[0014] The fourth aspect of the present disclosure also provides a computer-readable storage medium having a computer program or instructions stored thereon, wherein the computer program or instructions are executed by a processor to implement the steps of the method.

[0015] The fifth aspect of the present disclosure also provides a computer program product comprising a computer program or instructions, wherein the computer program or instructions are executed by a processor to implement the steps of the method.

[0016] According to the embodiments of the present disclosure, by detecting the taking mode of the treatment plan according to actual priorities and recommended priorities of actual taking modes of the plurality of treatment drugs in the treatment plan, a taking mode error of the treatment drug can be avoided. Since the dose deviation degree is determined according to the body weight adjustment coefficient of the target user, the recommended dose of the treatment drug in the database, and the actual dose of the treatment drug in the treatment plan, the dose deviation degree of the treatment drug for the target user can be accurately determined, and whether the dose of the treatment drug is correct can also be indirectly detected. Meanwhile, by detecting the dose of each of the plurality of therapeutic components in the plurality of treatment drugs according to the dose deviation degree of the plurality of treatment drugs, the dose detection of the plurality of therapeutic components in the treatment drug can be realized. According to the taking mode detection result and the dose detection result, the target detection result of the treatment plan is determined, the multi-level and high-precision detection of the taking mode of the treatment drug, the dose of the treatment drug, and the dose of the therapeutic component is realized, the precision of the treatment plan detection is improved, and the labor cost is reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The above contents and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0018] Figure 1 Schematically illustrates an application scenario diagram of a treatment regimen detection method, apparatus, device, medium, and program product executed by an electronic device according to an embodiment of the present disclosure;

[0019] Figure 2 Schematically shows a flow chart of a treatment plan detection method executed by an electronic device according to an embodiment of the present disclosure;

[0020] Figure 3 The process of component conflict detection according to an embodiment of the present disclosure is schematically shown;

[0021] Figure 4 The process of detecting a treatment plan according to an embodiment of the present disclosure is schematically shown;

[0022] Figure 5 The process of authenticating a user according to an embodiment of the present disclosure is schematically shown; and

[0023] Figure 6 The structure block diagram of the treatment plan detection device executed by an electronic device according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0024] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present disclosure. In the detailed description below, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0025] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise," "include," etc. used herein indicate the presence of the features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0026] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0027] In the case of using expressions similar to "at least one of A, B, and C, etc.", it is generally intended to include any of them alone, any combination of two or more of them, and the like.

[0028] In the technical solutions of the present disclosure, the user information (including but not limited to user personal information, user image information, user health information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved are information and data authorized by the user or authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of related data comply with relevant laws, regulations and standards, necessary security measures are taken, do not violate public order and good customs, and provide corresponding operation portal for user to choose authorization or refusal.

[0029] With the wide application of outpatient medical insurance services, users can not only obtain prescription drugs through the outpatient department of a hospital, but also obtain prescription drugs through online methods. However, the authenticity and rationality of prescription management have become a major problem in medical and health reform. At present, in order to verify the authenticity and rationality of the prescription, the prescription issued by the doctor is usually manually checked to determine whether the medicine in the prescription is reasonable. However, manual checking of the prescription leads to a large amount of human cost, and the checking efficiency is low for a large number of prescriptions, and the detection accuracy of the prescription is low.

[0030] Therefore, the embodiment of the present disclosure provides a treatment scheme detection method executed by an electronic device, which can be applied to the fields of artificial intelligence and medical technology. The method comprises: in response to receiving a treatment scheme for a target user's to-be-treated disease input in a medical consultation interface, detecting the medicine taking mode of the treatment scheme according to the actual priority and the recommended priority of the actual medicine taking mode of each of a plurality of treatment medicines in the treatment scheme, to obtain a taking mode detection result; detecting the dose of each of a plurality of treatment components in the plurality of treatment medicines according to the dose deviation degree of the plurality of treatment medicines, to obtain a dose detection result; and determining a target detection result of the treatment scheme according to the taking mode detection result and the dose detection result.

[0031] Figure 1 An application scenario diagram of a treatment scheme detection method, device, equipment, medium and program product executed by an electronic device according to an embodiment of the present disclosure is schematically shown.

[0032] As Figure 1As shown, the application scenario 100 according to this embodiment can include an identity authentication system 101, a medical inquiry system 102, and a medical insurance verification system 103. The identity authentication system 101 can authenticate the consistency of user identity and insured account information. The user and the doctor can communicate in the medical inquiry system 102, for example, voice inquiry, video inquiry, text inquiry, etc. The doctor can give a treatment plan according to the user-provided information of the disease to be treated. The treatment plan can include various treatment drugs. At the same time, the medical inquiry system 102 can detect the treatment plan. The medical insurance verification system 103 can verify the reimbursable drugs in the treatment plan and perform reimbursement settlement.

[0033] It should be understood that Figure 1 The number of terminal devices in the system is only illustrative. According to the needs of implementation, there can be any number of terminal devices.

[0034] Figure 2 An illustrative flowchart of a treatment plan detection method performed by an electronic device according to an embodiment of the present disclosure is shown.

[0035] As Figure 2 shown, the treatment plan detection method performed by an electronic device of this embodiment includes operation S210 to operation S230.

[0036] In operation S210, in response to receiving a treatment plan for a disease to be treated of a target user input in a medical inquiry interface, the drug taking mode of the treatment plan is detected according to the actual priority and the recommended priority of the actual drug taking mode of each of the plurality of treatment drugs in the treatment plan, to obtain a taking mode detection result.

[0037] According to an embodiment of the present disclosure, the medical inquiry interface can include an input box for user input related to the disease to be treated, an input box for the doctor to input the treatment plan, and a function button with voice call, video inquiry, etc.

[0038] According to an embodiment of the present disclosure, the target user can be a patient, and the treatment plan for the disease to be treated can be a treatment plan input by a doctor in a medical inquiry interface.

[0039] According to an embodiment of the present disclosure, the drug taking mode can be oral taking, external use, etc. Each drug taking mode has a risk, and a plurality of priorities are divided according to the risk. For example, the higher the risk, the higher the priority.

[0040] According to an embodiment of the present disclosure, the recommended drug taking mode can be the taking mode of the treatment drug in the database in the treatment plan input by the doctor in the medical inquiry interface, and the recommended drug taking mode can be used as the standard mode of drug taking.

[0041] According to an embodiment of the present disclosure, the actual priority can be a priority corresponding to an actual medicine taking manner of a treatment medicine in a treatment scheme input by a doctor in a medical consultation interface.

[0042] According to an embodiment of the present disclosure, the recommended priority is a priority corresponding to a recommended medicine taking manner of a treatment medicine in a database. In an embodiment of the present disclosure, the treatment scheme can be a prescription, the medical consultation interface is used for voice, video and the like interaction between a target user and a doctor, and the doctor inputs the prescription to the medical consultation interface after prescribing the prescription, and detects the prescription to ensure that the disease type, medicine dose, medicine service manner and the like of the prescription are normal, so as to avoid misprescription.

[0043] According to an embodiment of the present disclosure, the taking manner detection result can represent a difference between the actual medicine taking manner and the recommended medicine taking manner. If the difference is equivalent to a difference threshold value that is larger than a preset difference threshold value, the taking manner detection fails. If the difference is equivalent to a difference threshold value that is smaller than the preset difference threshold value, the taking manner detection passes.

[0044] The taking manner detection result can include whether the actual medicine taking manner and the recommended medicine taking manner are different, whether the priority of the actual medicine taking manner and the recommended medicine taking manner meets a priority condition, whether a cumulative difference value of the actual medicine taking manners of the plurality of treatment medicines reaches a preset difference value, and the like.

[0045] The priority condition can be that the actual medicine taking manner is lower than the recommended medicine taking manner, so that the risk of the actual medicine taking manner is smaller.

[0046] The cumulative difference value can be calculated by calculating the similarity of the actual medicine service manner of the plurality of treatment medicines and the respective recommended medicine taking manner in the priority, and adding the similarity to obtain the cumulative difference value. The cumulative difference value lower than the preset difference value can be a detection result representing that the taking manner detection passes; and the cumulative difference value higher than the preset difference value can be a detection result representing that the taking manner detection fails.

[0047] In an embodiment of the present disclosure, before obtaining the information of the user, the consent or authorization of the user can be obtained. For example, before operation S210, a request for obtaining the information of the user can be sent to the user. In the case that the user agrees or authorizes to obtain the information of the user, the operation S210 is performed.

[0048] In operation S220, according to the dose deviation degree of the plurality of treatment medicines, the dose of each of the plurality of treatment components in the plurality of treatment medicines is detected to obtain a dose detection result.

[0049] According to an embodiment of the present disclosure, the dose deviation degree is determined according to a body weight adjustment coefficient of the target user, a recommended dose of the therapeutic drug in the database, and an actual dose of the therapeutic drug in the treatment plan.

[0050] According to an embodiment of the present disclosure, the recommended dose of the therapeutic drug can be a standard dose of the drug.

[0051] According to an embodiment of the present disclosure, the dose deviation degree characterizes a deviation between a dose of the drug in the treatment plan and a dose of the therapeutic drug required by the target user, which is related to the body weight of the target user.

[0052] The dose deviation degree can be a dose deviation degree of a total dose of a therapeutic component in the treatment plan or a total dose of a therapeutic drug. For example, the dose deviation degree can be calculated by the following formula:

[0053] Dose deviation degree = |actual dose - recommended dose| / (recommended dose x body weight adjustment coefficient) (1)

[0054] The body weight adjustment coefficient can be determined by the type of the therapeutic drug used, the actual body weight of the target user, and the ideal body weight of the target user.

[0055] The actual dose can be a total dose of a therapeutic component in multiple therapeutic drugs, and the recommended dose can be a recommended total dose of a therapeutic component determined according to the body weight and age of the user.

[0056] In the case of the therapeutic drug being a chemotherapy drug, the body weight adjustment coefficient can be calculated by the following formula:

[0057] Body weight adjustment coefficient = actual body weight / ideal body weight (2)

[0058] and interval standardization is performed on the body weight adjustment coefficient. For example, the value range of the body weight adjustment coefficient is controlled to be [0.8, 1.2], and when the calculated body weight adjustment coefficient is less than 0.8, 0.8 is taken as the body weight adjustment coefficient; when the calculated body weight adjustment coefficient is greater than 1.2, 1.2 is taken as the body weight adjustment coefficient. According to an embodiment of the present disclosure, the dose detection result can include a dose deviation degree of a single therapeutic drug in the treatment plan or a dose deviation degree of a therapeutic component in multiple therapeutic drugs, and if the dose deviation degree is relatively large with respect to a preset deviation degree, the dose detection fails; if the dose deviation degree is relatively small with respect to the preset deviation degree, the dose detection passes.

[0059] In operation S230, the target detection result of the treatment plan is determined according to the administration mode detection result and the dose detection result.

[0060] In the embodiments of the present disclosure, the target detection result can be a comprehensive evaluation of the taking mode and the dose of the comprehensive treatment medicine, and the taking mode detection result and the dose detection result can be weighted and summed to obtain the target detection result.

[0061] According to the embodiments of the present disclosure, by detecting the taking mode of the medicine in the treatment scheme according to the actual priority and the recommended priority of the actual taking mode of each of the multiple treatment medicines in the treatment scheme, the taking mode detection result of the medicine is obtained, which can avoid the error of the taking mode of the medicine. Since the dose deviation degree is determined according to the body weight adjustment coefficient of the target user, the recommended dose of the treatment medicine in the database, and the actual dose of the treatment medicine in the treatment scheme, the dose deviation degree of the medicine for the target user is accurately determined, and the dose of the medicine is indirectly detected. At the same time, according to the dose deviation degree of the multiple treatment medicines, the dose of each of the multiple treatment components in the multiple treatment medicines is detected to obtain the dose detection result, so that the dose detection of the multiple treatment components of the medicine is realized. According to the taking mode detection result and the dose detection result, the target detection result of the treatment scheme is determined, the multi-level and high-precision detection of the taking mode of the medicine, the dose of the medicine, and the dose of the treatment component is realized, the precision of the detection of the treatment scheme is improved, and the labor cost is reduced.

[0062] According to the embodiments of the present disclosure, in response to receiving the treatment scheme of the target user's to-be-treated disease in the medical inquiry interface, the taking mode of the medicine in the treatment scheme is detected according to the actual priority and the recommended priority of the actual taking mode of each of the multiple treatment medicines in the treatment scheme, including: in response to receiving the treatment scheme, the component conflict detection of the multiple treatment components in the multiple treatment medicines is performed by using the preset component conflict information to obtain the component conflict detection result of the treatment scheme. The preset component conflict information includes the conflict relationship between the multiple preset components. When the component conflict detection result indicates that the component conflict detection of the treatment scheme is passed, the taking mode of the medicine in the treatment scheme is detected according to the actual priority and the recommended priority to obtain the taking mode detection result.

[0063] In the embodiments of the present disclosure, the preset component conflict information can be a component conflict matrix, which can be constructed in advance through previous cases and related medical and food science knowledge.

[0064] In the embodiments of the present disclosure, the element consistent with the treatment medicine component in the treatment scheme is searched from the component conflict matrix to obtain the component conflict detection result. When the component conflict detection result is passed, the taking mode detection of the medicine is performed.

[0065] According to an embodiment of the present disclosure, the component conflict detection before the drug taking mode detection by using the component conflict matrix can effectively avoid unreasonable prescriptions directly, save the time and manpower of manual component conflict detection, and improve the detection efficiency of the prescriptions.

[0066] According to an embodiment of the present disclosure, the component conflict detection of the plurality of therapeutic components in the plurality of therapeutic drugs by using the preset component conflict information obtains the component conflict detection result of the treatment scheme, including: matching the plurality of therapeutic components in the plurality of therapeutic drugs with the plurality of preset components having the conflict relationship in the preset conflict information to obtain a matching result; in the case that the matching result represents that the plurality of therapeutic components have the conflict relationship, determining the conflict level between the plurality of therapeutic components; and determining the component conflict detection result according to the conflict level between the plurality of therapeutic components and the component dynamic factor of each of the plurality of therapeutic components. According to an embodiment of the present disclosure, the component dynamic factor is determined according to the preset basic weight and the adjustment weight of the therapeutic component, and the adjustment weight is determined according to the body state information of the target user.

[0067] In an embodiment of the present disclosure, the conflict level generated by the conflict between the therapeutic component i and the therapeutic component j in the component conflict matrix can be represented as x ij For example, the conflict level can be divided into 3 levels, 0 represents no conflict, 1 represents mild conflict, and 2 represents severe conflict. Taking coumarin and ibuprofen as an example, the therapeutic component i = coumarin, the therapeutic component j = ibuprofen, and the conflict level x ij = 2 is obtained from the component conflict matrix, that is, there is a severe conflict between coumarin and ibuprofen.

[0068] In an embodiment of the present disclosure, the component dynamic factor can be a risk parameter for quantifying the conflict between the therapeutic components to the health damage of the target user, and can be calculated by the following formula:

[0069] severity_factor = fixed_factor + patient_factor (3)

[0070] Wherein, severity_factor is the component dynamic factor, fixed_factor is the basic weight, and patient_factor is the adjustment weight. The basic weight can be preset in advance to form a conflict weight table, and the component dynamic factor can be directly obtained from the database during calculation. The adjustment weight can be calculated according to the state of the target user. For example, the basic weight of coumarin and ibuprofen corresponds to 1.5; if the target user has liver dysfunction, the adjustment weight increment is +0.5, if the target user has kidney dysfunction, the adjustment weight increment is +0.5, if the target user is > 65 years old, the adjustment weight increment is +0.3, and if the target user is pregnant, the adjustment weight increment is +1.0.

[0071] According to an embodiment of the present disclosure, by determining the conflict level and the component dynamic factor, the risk degree of the health damage of the target user caused by the conflict between the treatment components can be determined, and the risk of medication according to the physical state of the target user can be determined, thereby avoiding the problem that the risk of medication is not accurately calculated due to the difference in the state of the target user, improving the accuracy of prescription detection, reducing labor costs, and improving detection efficiency.

[0072] According to an embodiment of the present disclosure, the method further comprises: in the case where the conflict level meets a preset level condition, displaying a prompt interface with the drug component conflict information.

[0073] In an embodiment of the present disclosure, for example, the preset level condition can be set as a severe conflict level. Taking coumarin and ibuprofen as an example, the conflict level can be obtained from the component conflict matrix, which is a severe conflict. Therefore, in the case where the treatment scheme contains both coumarin and ibuprofen, the component conflict detection is not passed, and the doctor re-enters the treatment scheme in the medical inquiry interface.

[0074] For example, the conflict level x ij =0 or 1 obtained from the component conflict matrix does not meet the preset level condition, and the next step can be performed.

[0075] According to an embodiment of the present disclosure, the treatment components with severe conflict will cause serious damage to health. By setting the preset level condition, the treatment components with severe conflict can be directly screened, without considering the state of the target user, thereby reducing the calculation load and improving the detection efficiency.

[0076] According to an embodiment of the present disclosure, the component conflict detection result is determined according to the conflict level between the plurality of treatment components and the component dynamic factor of each of the plurality of treatment components, comprising: determining the component risk value of each of the plurality of treatment components according to the conflict level between the plurality of treatment components and the component dynamic factor of each of the plurality of treatment components, and determining the cumulative component risk value of the plurality of treatment components in the treatment scheme; in the case where the cumulative component risk value is greater than or equal to a preset component risk threshold, displaying a prompt interface with the drug component conflict information; in the case where the cumulative component risk value is less than the preset component risk threshold, obtaining a component conflict detection result representing that the component conflict detection of the treatment scheme is passed.

[0077] In an embodiment of the present disclosure, the component risk value can be calculated by the following formula:

[0078] weighted_risk=x ij ×(1+severity_factor)(4)

[0079] Wherein, weighted_risk is the component risk value. Taking coumarin and ibuprofen as an example, if the target patient has liver dysfunction, then x ij = 2, severity_factor = 1.5 + 0.5 = 2.0, weighted_risk = 2 x (1 + 2.0) = 6.0.

[0080] In an embodiment of the present disclosure, it can also be checked whether there is a severe contraindication component in the treatment component. In the case where the component risk value is greater than or equal to the contraindication threshold, the treatment component combination information corresponding to the component risk value is added to the severe contraindication list. For example, the contraindication threshold can be set to 3, or it can be adjusted according to the actual situation. In the case where the treatment component combination exists in the severe contraindication list, the doctor is asked to re-input the treatment plan in the medical inquiry interface.

[0081] In an embodiment of the present disclosure, the cumulative component risk value can be understood as a whole prescription risk evaluation function The component risk value of each group of treatment components in the treatment plan is calculated and accumulated to obtain For example, the preset component risk threshold can be set to 5. In the case where the cumulative component risk value is greater than or equal to 5, a prompt interface with drug component conflict information is displayed, and the doctor is asked to re-input the treatment plan in the medical inquiry interface; in the case where the cumulative component risk value is less than 5, the component conflict detection passes.

[0082] According to an embodiment of the present disclosure, by comparing the cumulative component risk value and the preset component risk threshold, the drug safety of the target user can be guaranteed by quantifying the drug risk, the rationality and authenticity of the prescription can be guaranteed, and the treatment plan detection accuracy can be improved.

[0083] Figure 3 The process of component conflict detection according to an embodiment of the present disclosure is schematically shown.

[0084] As shown in Figure 3 , in operation S310, a plurality of treatment components in a plurality of treatment drugs are matched with a plurality of preset components having a conflict relationship in the preset conflict information, and a matching result is obtained.

[0085] In operation S320, in the case where the matching result represents that the plurality of treatment components have a conflict relationship, the conflict level between the plurality of treatment components is determined.

[0086] In operation S330, it is judged whether the conflict level meets the preset conflict level condition.

[0087] In a case where the conflict level does not satisfy the preset conflict level condition, operation S340 is performed to determine a component risk value of each of the plurality of therapeutic components according to the conflict level between the plurality of therapeutic components and the component dynamic factor of each of the plurality of therapeutic components, and to determine an accumulated component risk value of the plurality of therapeutic components in the treatment scheme.

[0088] In a case where the conflict level satisfies the preset conflict level condition, operation S360 is performed to display a prompt interface with the drug component conflict information.

[0089] After operation S340, operation S350 is performed to determine whether the accumulated component risk value is less than a preset component risk value threshold.

[0090] In a case where the accumulated component risk value is less than the preset component risk value threshold, operation S370 is performed to obtain a component conflict detection result representing that the component conflict detection of the treatment scheme is passed.

[0091] In a case where the accumulated component risk value is greater than or equal to the preset component risk value threshold, operation S360 is performed to display a prompt interface with the drug component conflict information.

[0092] According to embodiments of the present disclosure, the component conflict detection can adapt to the state of the target user, so that the accumulated component risk value is closer to the medication risk in a case where the target user takes medication according to the treatment scheme, and the detection accuracy of the treatment scheme is improved.

[0093] According to embodiments of the present disclosure, the medication taking manner of the treatment scheme is detected according to the actual priority and the recommended priority to obtain a taking manner detection result, including: determining an actual quantitative value corresponding to the actual priority and a recommended quantitative value corresponding to the recommended priority from a mapping relationship between the priority and the quantitative value; determining a target value satisfying a preset condition from a difference between the actual quantitative value and the recommended quantitative value and a preset value; accumulating the target values corresponding to the plurality of therapeutic drugs to obtain an accumulated taking manner risk value; and in a case where the accumulated taking manner risk value satisfies a preset taking manner condition, obtaining a taking manner detection result representing that the medication taking manner of the treatment scheme is passed.

[0094] In embodiments of the present disclosure, the priority can be a medication risk level brought by the medication taking manner. For example, the priority quantitative value of oral administration can be set as level 2, the priority of external use can be set as level 1, and the priority of other taking manners can be set as level 0, and then the priority order of different taking manners is oral administration (priority 2) > external use (priority 1) > other (priority 0).

[0095] In the embodiments of the present disclosure, the actual priority can be the priority of the medicine taking mode in the treatment plan, the recommended priority can be the priority of the medicine taking mode obtained according to the previous medical records and medical knowledge, and the preset value can be 0. The target value can be calculated by the following formula:

[0096] Target value = max(0, priority actual -priority theory ) (5)

[0097] Wherein, priority actual represents the actual quantitative value, and priority theory represents the recommended quantitative value.

[0098] According to the embodiments of the present disclosure, the preset condition can be the larger value between the difference between the actual quantitative value and the recommended quantitative value and the preset value. For example, the preset value is 0, the difference between the actual quantitative value and the recommended quantitative value can be 2, and the target value is 2.

[0099] In the embodiments of the present disclosure, for example, the preset taking mode condition can be set as the cumulative taking mode risk value equaling to 0, and the cumulative taking mode risk value can be calculated by the following formula:

[0100] (6)

[0101] Wherein, is the cumulative taking mode risk value, represents the total number of medicines. For example, when , it indicates that the taking mode detection is passed, otherwise it indicates that the taking mode detection is failed, and the doctor re-enters the treatment plan in the medical inquiry interface.

[0102] In the embodiments of the present disclosure, the taking mode of the medicine in the prescription is read, the dosage form of the corresponding medicine is obtained from the database, and the cumulative taking mode risk value of the medicine in the prescription is calculated. When the cumulative taking mode risk value meets the preset taking mode condition, the taking mode detection of the medicine in the prescription is passed.

[0103] According to the embodiments of the present disclosure, the taking mode is detected by using the priority, which can scientifically measure the influence of the taking mode on the medicine risk, improve the accuracy of the taking mode detection, and further improve the accuracy of the treatment plan detection.

[0104] According to an embodiment of the present disclosure, the doses of the plurality of therapeutic ingredients in the plurality of therapeutic drugs are detected according to the plurality of dose deviation degrees, to obtain dose detection results, including: in a case where the plurality of dose deviation degrees are greater than a preset deviation degree, displaying a prompt interface with a dose error; in a case where the plurality of dose deviation degrees are less than the preset deviation degree, determining the cumulative doses of the plurality of therapeutic ingredients according to the contents of the plurality of therapeutic ingredients in the plurality of therapeutic drugs; and detecting the taking dose of the treatment scheme according to the cumulative doses of the plurality of therapeutic ingredients, the safe cumulative amount and the half-life of the therapeutic drug, to obtain taking dose detection results.

[0105] In an embodiment of the present disclosure, for example, the preset deviation degree can be set to 0.5, and in a case where at least one dose deviation degree is greater than 0.5, the last layer is returned to reissue a prescription. In a case where the dose deviation degrees of the therapeutic drugs are all less than or equal to 0.5, the cumulative doses of the plurality of therapeutic ingredients are determined.

[0106] In an embodiment of the present disclosure, in a case where the plurality of dose deviation degrees are all less than the preset deviation degree, a preset confirmation deviation degree can also be set. In a case where the plurality of dose deviation degrees are all less than or equal to the preset confirmation deviation degree, the cumulative doses of the plurality of therapeutic ingredients are determined, and in a case where the plurality of dose deviation degrees are greater than the preset confirmation deviation degree, a dose deviation degree confirmation prompt interface is displayed.

[0107] For example, the preset confirmation deviation degree can be set to 0.3, in a case where the dose deviation degree is less than or equal to 0.3, the cumulative doses of the plurality of therapeutic ingredients are determined, in a case where 0.3 < dose deviation degree ≤ 0.5, dose deviation degree confirmation information is sent to a doctor or a drugstore salesperson, after the dose deviation degree information is confirmed to be correct, the cumulative doses of the plurality of therapeutic ingredients are determined, otherwise the doctor is required to re-input the treatment scheme in a medical inquiry interface.

[0108] In an embodiment of the present disclosure, detecting the taking dose of the treatment scheme according to the cumulative doses of the plurality of therapeutic ingredients, the safe cumulative amount and the half-life of the therapeutic drug, to obtain taking dose detection results, includes: calculating a dose risk index according to the cumulative doses of the plurality of therapeutic ingredients, the safe cumulative amount and the half-life of the therapeutic drug; in a case where the dose risk index meets a preset dose risk condition, obtaining a taking dose detection result indicating that the taking dose detection of the treatment scheme passes; and in a case where the dose risk index does not meet the preset dose risk condition, displaying a prompt interface with a dose error.

[0109] In an embodiment of the present disclosure, the dose risk index can be calculated by the following formula:

[0110]

[0111] in, represents the dose risk index.

[0112] For example, a pre-set dose risk condition could be , in the calculated In the case of , the dosage test is passed; in the calculated In this case, ask the doctor to re-enter the treatment plan in the medical consultation interface.

[0113] In an embodiment of the present disclosure, before performing the dose deviation calculation, it is also possible to determine whether the target user is an adult or a child. If the target user is an adult, the dose of the drug in the prescription is compared with the maximum dose in the corresponding drug instructions. If the dose of the drug in the prescription is less than or equal to the maximum dose in the instructions, the dose deviation calculation is performed; if the dose of the drug in the prescription is greater than the maximum dose in the instructions, the doctor is asked to re-enter the treatment plan in the medical consultation interface. If the target user is a child, the target user's weight / height is calculated, and the maximum allowable dose corresponding to the target user in the instructions is determined based on the obtained results. The dose of the drug in the prescription is compared with the maximum allowable dosage. If the dose of the drug in the prescription is less than or equal to the maximum allowable dosage, the dose deviation calculation is performed; if the dose of the drug in the prescription is greater than the maximum allowable dosage, the doctor is asked to re-enter the treatment plan in the medical consultation interface.

[0114] According to the disclosed embodiments, the dosage deviation is determined based on the target user's weight adjustment factor, the recommended dosage of the therapeutic drug in the database, and the actual dosage of the therapeutic drug in the treatment plan. This allows for accurate determination of the dosage deviation for the target user and also indirectly detects whether the drug dosage is incorrect. Determining the dosage detection result based on the dosage deviation allows for dosage detection of multiple therapeutic components of a therapeutic drug.

[0115] According to an embodiment of the present disclosure, the method further includes: when the dosage detection result indicates that the dosage detection of the treatment plan has passed, the applicability of multiple therapeutic drugs is detected based on the symptom information of the target user for the preset disease, to obtain the applicability detection result of the treatment plan for the target user.

[0116] In the embodiments of the present disclosure, the preset condition includes a special state of the target user and a disease suffered by the target user, such as pregnancy, allergy, heart disease, etc. The suitability of the plurality of therapeutic drugs to the target user is detected according to the condition information of the target user for the preset condition, and the suitability detection result of the treatment scheme to the target user includes: calculating a suitability risk index according to the special state of the target user and the disease suffered by the target user; in the case that the suitability risk index meets a preset suitability risk condition, obtaining a suitability detection result indicating that the suitability detection of the treatment scheme is passed; in the case that the suitability risk index does not meet the preset suitability risk condition, displaying a prompt interface with suitability error.

[0117] For example, the suitability risk condition can be set as that the suitability risk index is 1, and the suitability risk index The suitability risk index can be calculated in the following manner: if the drug contraindication contains the special state of the target user, ; the target user's allergy history ∩ drug component ≠ ∅, then ; the target user's disease ∩ drug contraindication disease ≠ ∅, then ; otherwise In the case of , the doctor is required to re-input the treatment scheme in the medical inquiry interface; in the case of , the suitability detection is passed.

[0118] According to the embodiments of the present disclosure, the suitability detection can detect whether the treatment scheme is suitable for the target user according to the special state and the disease of the target user, and the accuracy and rationality of the treatment scheme detection are improved by considering the state of the target user.

[0119] According to the embodiments of the present disclosure, the target detection result of the treatment scheme is determined according to the taking mode detection result and the dose detection result, and includes: weighted sum of the taking mode detection result, the component conflict detection result, the dose detection result and the suitability detection result to obtain the target detection result of the treatment scheme.

[0120] In the embodiments of the present disclosure, the weighted sum of the taking mode detection result, the component conflict detection result, the dose detection result and the suitability detection result to obtain the target detection result of the treatment scheme includes: weighted sum of the cumulative component risk value , the cumulative taking mode risk value , the dose risk index and the suitability risk index to obtain a total risk value; and grading processing the total risk value to obtain the target detection result of the treatment scheme.

[0121] For example, the total risk value can be calculated based on the following formula:

[0122] Total risk value = 0.4 x + 0.3 x + 0.2 x + 0.1 x (8)

[0123] For example, the total risk value can be divided into 3 levels, if the total risk value ranges in [0, 1], it is low risk, the treatment plan detection passes; ranges in (1, 3] is medium risk, send total risk confirmation prompt information, confirm after detection pass; if the total risk value is greater than 3, it is high risk, return to reissue a prescription.

[0124] According to the embodiments of the present disclosure, the total risk value is calculated to confirm the target detection result, to realize multi-level and high-precision detection of drug taking mode, drug dose and treatment component dose, improve the precision and efficiency of treatment plan detection, and reduce the labor cost.

[0125] Figure 4 The process of detecting the treatment plan according to the embodiments of the present disclosure is schematically shown.

[0126] As shown in FIG. 4, in action A401, it is judged whether the component conflict detection passes. If yes, action A402 is executed; if no, action A407 is executed. Figure 4

[0127] In action A402, it is judged whether the drug taking mode detection passes. If yes, action A403 is executed; if no, action A407 is executed.

[0128] In action A403, it is judged whether the dose deviation degree is greater than the preset deviation degree. If yes, action A407 is executed; if no, action A404 is executed.

[0129] In action A404, it is judged whether the dose deviation degree is greater than the preset confirmation deviation degree.

[0130] In action A405, a confirmation interface of whether the dose detection passes is sent to the user. If the user confirms, action A406 is executed; if the user does not confirm, action A407 is executed.

[0131] In action A406, it is judged whether the applicability detection passes. If yes, action A408 is executed; if no, action A407 is executed.

[0132] In action A407, an interface of re-entering the treatment plan is sent to the user.

[0133] In action A408, the target detection result representing that the treatment plan passes is obtained.

[0134] ​According to an embodiment of the present disclosure, the method further comprises: in response to receiving the verification image of the target user, obtaining a registration image of the target user from a database; determining a time decay value according to a verification time of the verification image, a registration time of the registration image, and a yearly decay rate; determining a target time decay value that satisfies a time decay condition from the time decay value and a preset time decay threshold; determining a similarity threshold according to the target time decay value and a time adjustment coefficient; and in a case where a similarity between the verification image and the registration image is greater than the similarity threshold, displaying a medical inquiry interface to the target user, so as to facilitate the target user to input a to-be-treated condition in the medical inquiry interface.

[0135] In an embodiment of the present disclosure, the time decay value can be calculated by the following formula:

[0136] decay_factor = 1 - decay_year (9)

[0137] wherein decay_factor is the time decay value, and decay_year is the yearly decay rate, which can be calculated according to the verification time and the registration time of the registration image, for example, the yearly decay rate is 1.5%.

[0138] In an embodiment of the present disclosure, in a case where the calculated time decay value is greater than the preset time decay threshold, the target time decay value is the calculated time decay value; and in a case where the calculated time decay value is less than or equal to the preset time decay threshold, the target time decay value is the preset time decay threshold. For example, the preset time decay threshold can be set to 0.7, or can be adjusted according to actual conditions.

[0139] In an embodiment of the present disclosure, the similarity threshold can be calculated by the following formula:

[0140] dynamic_threshold = base_threshold x max(0.7, decay_factor) (10)

[0141] wherein dynamic_threshold is the similarity threshold, base_threshold is a base threshold, and max(0.7, decay_factor) is the target time decay value. For example, the base threshold can be set to 0.85.

[0142] In an embodiment of the present disclosure, the similarity can be calculated by the following formula:

[0143]

[0144] Wherein, the similarity is the similarity, V1 represents the facial feature vector of the target user at present, and V2 represents the feature vector of the registered image of the target user stored in the database.

[0145] In the embodiment of the present disclosure, the target user uploads the real-time photographed face verification image through an encrypted channel, uses the feature extraction model to perform feature extraction on the verification image, and obtains the facial feature vector of the target user. The facial feature vector of the user is compared with the feature vector of the registered image stored in the database, and the similarity is calculated to obtain the identity authentication result. In the case of identity authentication, the medical diagnosis interface is displayed to the target user. If the identity authentication is not passed, the specific error information of the target user is prompted and the login is refused.

[0146] For example, the feature extraction model can be a convolutional neural network. The similarity can be calculated using cosine similarity or Euclidean distance.

[0147] Figure 5 The process of identity authentication of the user according to the embodiment of the present disclosure is schematically shown.

[0148] As shown in Figure 5 In action A501, the identity authentication process is started. In action A502, the scene category is judged, and if the scene is offline diagnosis, action A503 is executed to judge whether the social security card is valid. In the case of no in the judgment result of action A503, action A515 is jumped to, prompting that the social security card is invalid; in the case of yes in the judgment result of action A503, action A507 is executed to photograph the face image of the user. After action A507, action A508 is executed to judge whether the user passes the random action instruction.

[0149] If the scene is online diagnosis, action A504 is executed to let the user input the account password. In action A505, it is judged whether the account password is correct, if not, action A520 is executed to prompt that the account or password is incorrect; if correct, action A506 is executed to judge whether the medical insurance bureau verification is successful. If the judgment result of action A506 is no, action A519 is executed to prompt that the medical insurance verification fails; if the judgment result of action A506 is yes, action A508 is executed to judge whether the user passes the random action instruction.

[0150] If the judgment result of action A508 is no, action A518 is executed to prompt that the liveness detection fails; if the judgment result of action A508 is yes, action A509 is executed to judge whether the user passes the photoplethysmography (PPG) blood detection.

[0151] If the determination result of action A509 is no, action A518 is performed to prompt that the living body detection fails; if the determination result of action A509 is yes, action A510 is performed to acquire the registration time and the annual attenuation rate of the registration image, action A511 is performed to determine the target time attenuation value, action A512 is performed to determine the similarity threshold, action A513 is performed to perform the user facial feature comparison, and action A514 is performed to determine whether the similarity is greater than the similarity threshold.

[0152] If the determination result of action A514 is no, action A517 is performed to prompt that the facial feature comparison fails; if the determination result of action A514 is yes, action A516 is performed to display the medical diagnosis interface.

[0153] According to embodiments of the present disclosure, the target user facial feature comparison by considering the time attenuation factor can explicitly indicate the difference between the target user face and the registration image caused by the change of the target user face over time, and improve the accuracy of the facial comparison.

[0154] According to embodiments of the present disclosure, before the treatment scheme for the target user is determined in response to receiving the input in the medical diagnosis interface, the embodiments further comprise determining a target doctor for treating the target user from a plurality of candidate doctors according to the information of the to-be-treated disease, the geographical location of the target user, the treatment task amount and the historical treatment evaluation information of each of the plurality of candidate doctors.

[0155] In embodiments of the present disclosure, the doctor adaptation degree is calculated according to the information of the to-be-treated disease, the geographical location of the target user, the treatment task amount and the historical treatment evaluation information of each of the plurality of candidate doctors, and the target doctor for treating the target user is determined from the plurality of candidate doctors according to the candidate doctor adaptation degree.

[0156] For example, the doctor adaptation degree is calculated by using a weighted scoring model, and the formula is as follows:

[0157] Doctor adaptation degree = professional matching degree × W1 + reception load × W2 + geographical location × W3 + historical treatment evaluation information × W4.

[0158] The information of the to-be-treated disease represents the professional matching degree of the doctor and the target user, and the treatment task amount represents the reception load of the doctor.

[0159] Professional matching degree = number of common diseases / number of required diseases of the target user (12)

[0160] Reception load = 1 - (current number of receptions / maximum reception capacity) (13)

[0161] Historical treatment evaluation information = W5 × satisfaction score in the last 3 months + W6 × median score

[0162] Geographical location is scored by distance: 5km (1.0), 5-10km (0.8), 10-20km (0.5), and over 20km (0.2).

[0163] In embodiments of the present disclosure, for example, , , When the doctor's reception load exceeds 80% of the capacity, the weight W2 is automatically halved, and other weights are increased.

[0164] According to embodiments of the present disclosure, by calculating the doctor's fitness, a suitable doctor can be selected for the target user for diagnosis, and the professional fitness can select a doctor who is good at diagnosing the target user's symptoms, thereby improving the feasibility and rationality of the treatment plan.

[0165] In embodiments of the present disclosure, the electronic device can further include a risk detection system. For example, the treatment plan is uploaded to the risk detection system after being detected by the medical inquiry system. The risk detection system can automatically collect prescription information, target user identity information, target user medical history and medication record information, and target user medical insurance reimbursement record information. For example, the target user information can include a unique identifier, a card number, etc. The prescription information can include the drug name, the dosage, the usage, and the time of prescribing. The target user medical history and medication record information can include past medical history, allergy history, surgery history, historical medication record, and medication frequency. The target user medical insurance reimbursement record information can include reimbursed drugs, reimbursement amount, etc.

[0166] In embodiments of the present disclosure, the risk detection system can further use a risk prediction model to analyze the prescription in multiple dimensions using big data analysis and machine learning algorithms to obtain a risk prediction result. The risk prediction result can include risk type, risk assessment level, and risk probability. For example, the prediction process can be as follows:

[0167] 1) Construct a data pipeline to extract prescription data from the database for analysis in real time or periodically.

[0168] 2) Use the k-means clustering (K-Means) algorithm or the density-based clustering algorithm (DBSCAN) to construct a patient classification model to group patients with similar medication patterns. For example, patients who frequently use antibiotics are grouped together to analyze the rationality of their medication.

[0169] 3) Use the Random Forest algorithm or the gradient boosting decision tree-based ensemble learning (XGBoost) algorithm to construct a prescription classification model, and use patient information to train the prescription classification model to determine whether the prescription is reasonable. The patient information includes: patient age range, drug category, medication frequency, medical history, etc.

[0170] 4) Use Isolation Forest or LOF (Local Outlier Factor) algorithm to build risk prediction model and detect abnormal prescriptions. For example, detect the behavior of frequently prescribing high-priced drugs or off-label use of drugs.

[0171] 5) Train risk prediction model based on historical data to predict the risk level of prescriptions (such as low risk, medium risk, high risk).

[0172] In embodiments of the present disclosure, according to historical data and expert experience, risk thresholds and rules can be set, and when the detected results exceed the thresholds or do not meet the rules, potential risk points are determined. For example, if a patient frequently prescribes high-priced anticancer drugs in a short period of time, and there is no corresponding cancer diagnosis record, the system will issue a risk warning. Risk thresholds can be determined based on high-priced drug usage frequency, off-label use of drugs, and drug interactions, for example:

[0173] 1) High-priced drug usage frequency: such as more than 3 times per month.

[0174] 2) Off-label use of drugs: such as antibiotics for non-bacterial infections.

[0175] 3) Drug interactions: such as simultaneous use of two contraindicated drugs. Such as frequent prescription of high-priced drugs, off-label use of drugs, etc.

[0176] In embodiments of the present disclosure, when an abnormal situation is detected, if an anomaly is found, the system records relevant information and generates a risk warning report and feeds back to the relevant regulatory department; if no anomaly is found, the process continues. The risk warning report includes detailed risk information, such as prescription details, patient information, risk type, risk assessment level, etc., so that the regulatory department can quickly understand the situation and take appropriate measures.

[0177] In embodiments of the present disclosure, the prescriptions that pass the risk detection without abnormalities are uploaded to the medical insurance bureau reimbursement system through an encrypted channel. For example, the encrypted channel uses Secure Sockets Layer and Transport Layer Security (SSL / TLS) protocol for encrypted transmission to ensure the security of data during network transmission. At the same time, the system will digitally sign the uploaded prescription data to ensure the integrity of the data and the reliability of the source.

[0178] In an embodiment of the present disclosure, the prescription data is symmetrically encrypted to generate an encrypted data packet. The symmetric key is encrypted using an asymmetric encryption algorithm to ensure that only the medical insurance bureau reimbursement system can decrypt the data. A digital signature is generated using a private key-based encryption algorithm to verify the authenticity and integrity of the prescription. For example, a hash value of the prescription data is generated using a hash algorithm, and the hash value is signed using the private key of the medical insurance bureau to generate a unique digital signature. The encrypted data packet and the digital signature are uploaded to the medical insurance bureau reimbursement system together. For example, a prescription double-signature mechanism (prescribing physician + pharmacy responsible person) is implemented for special drugs such as immunoglobulin.

[0179] In an embodiment of the present disclosure, the target user enters the medical insurance verification system through the identity authentication system and the medical inquiry system to conduct a detailed audit of the prescription, including the reimbursement range of the drug, the rationality of the diagnosis and treatment project, the accuracy of the cost calculation, etc., and each item of the prescription is audited item by item to check whether the drug is in the medical insurance reimbursement directory, whether the diagnosis and treatment project conforms to the medical insurance policy, and whether the cost calculation is accurate. If the verification is passed, the reimbursement settlement process is entered; otherwise, an error message is returned.

[0180] In an embodiment of the present disclosure, the medical insurance verification system decrypts and verifies the encrypted prescription and starts an intelligent verification program. For example, the decryption process can be: using the private key of the medical insurance bureau to decrypt the symmetric key, using the symmetric key to decrypt the prescription data, using the public key of the medical insurance bureau to decrypt the digital signature, obtaining the hash value, recalculating the hash value of the decrypted prescription data, and comparing it with the decrypted hash value. If they are consistent, the verification is passed, ensuring that the prescription data has not been tampered with, and the decrypted prescription data is input into the intelligent verification program for detailed audit, including the reimbursement range of the drug, the rationality of the diagnosis and treatment project, the accuracy of the cost calculation, etc.

[0181] In an embodiment of the present disclosure, the intelligent verification program can conduct in-depth audit of the prescription content according to the medical insurance policy rule library. For example, the audit process is as follows:

[0182] (1) Rule library construction: based on the medical insurance policy, a dynamically updated rule library is constructed, including: drug reimbursement range, diagnosis and treatment project rationality, cost calculation accuracy, and the rule library supports real-time updating to adapt to changes in the medical insurance policy.

[0183] (2) Audit process: each item of the prescription is audited item by item to check whether the drug is in the medical insurance reimbursement directory, whether the diagnosis and treatment project conforms to the medical insurance policy, and whether the cost calculation is accurate. For ambiguous or uncertain cases, the system automatically performs secondary verification, such as data comparison with the hospital medical record system, to ensure the accuracy of the audit result

[0184] (3) Record the key operations and results in the audit process in the blockchain to ensure data tamper-proofing and traceability.

[0185] (4) If the preliminary verification is passed, the system automatically triggers the medical insurance identity authentication process, verifies the patient's medical insurance information, and sends the following information to the medical insurance bureau official verification interface: medical insurance card number or identity card number, prescription number. The medical insurance bureau interface returns the verification result, which can include: insurance state (such as normal / abnormal), medical insurance account balance, reimbursement ratio. If the verification is passed, enter the reimbursement settlement process; otherwise, return error information.

[0186] (5) After the audit is passed, the system automatically processes the reimbursement settlement, and the reimbursement amount is paid into the patient's designated account. The reimbursement settlement process uses an automated financial system and interfaces with the bank to achieve fast and accurate fund transfer. For example, the settlement process can be as follows:

[0187] 1) Cost calculation: calculate the patient's reimbursement amount according to the medical insurance policy and reimbursement ratio;

[0188] 2) Fund transfer: call the bank interface to pay the reimbursement amount into the patient's designated account, and use HTTPS protocol to ensure the security of the fund transfer process.

[0189] 3) Blockchain record: record the details of the reimbursement settlement in the blockchain, including: reimbursement amount, transfer time, patient account information.

[0190] (6) The system will generate detailed reimbursement records (such as prescription details, audit results, reimbursement amount, transfer information, etc.) and vouchers, and store the hash values of the reimbursement records and vouchers in the blockchain to ensure data tamper-proofing. Patients and regulatory authorities can query reimbursement records through the blockchain, and patients can download electronic reimbursement vouchers through the platform for subsequent queries or reimbursement proof.

[0191] In embodiments of the present disclosure, a regulatory system is also included, which can supervise the identity authentication system, medical consultation system, risk detection system and medical insurance verification system. For example, a closed-loop supervision mechanism is used to monitor each link in real time. The monitoring system uses real-time data acquisition technology, such as sensors, log records, etc., to monitor the operation behavior, data flow, etc. of the system in real time. At the same time, data analysis tools are used to analyze the collected data in real time, and abnormal situations are discovered in time. For example, the supervision process can be as follows:

[0192] 1) Data Collection: Collect the following data in real-time using sensors (e.g. server performance monitoring sensors) and logging tools: system operational behavior (e.g. user login, prescription upload, reimbursement settlement), data flow path (e.g. the transmission path of prescriptions from hospitals to medical insurance bureaus), system performance indicators (e.g. response time, CPU / memory usage).

[0193] 2) Real-time Analysis: Use a stream processing framework to analyze the collected data in real-time, apply anomaly detection algorithms such as Isolation Forest, LOF (Local Outlier Factor) to identify abnormal behavior: for example, detect a large number of reimbursement requests or unusually high reimbursement amounts in a short period of time, use clustering algorithms (e.g. K-Means) to group operational behavior and identify abnormal patterns.

[0194] 3) Visualization Monitoring: Use data analysis and visualization platforms to build real-time monitoring dashboards to display key indicators and abnormal situations. Support custom alarm rules, such as triggering an alarm when CPU usage exceeds 80%.

[0195] In embodiments of the present disclosure, once a violation behavior (e.g. false reimbursement, violation of prescription issuance, etc.) is found, a pre-warning mechanism is triggered immediately. For example:

[0196] 1) Violation behavior detection: Use a rule engine to define violation behavior rules. For example, false reimbursement rule: the same patient reimburses the same drug multiple times in the same time period. Violation of prescription issuance rule: a doctor issues a drug that is beyond his / her scope of practice. Use machine learning models (e.g. XGBoost) to train on historical violation behaviors to predict potential violation behaviors.

[0197] 2) Pre-warning notification: Send pre-warning information through various means (SMS, email, system pop-up).

[0198] 3) Preliminary analysis: The system automatically generates a violation behavior analysis report, including: violation type (e.g. false reimbursement, violation of prescription issuance), relevant evidence (e.g. prescription details, operation log), risk level (e.g. low risk, medium risk, high risk).

[0199] For example, after the relevant departments receive the pre-warning, they start the investigation and handling procedures, conduct in-depth investigation on the violation behavior and handle it according to the law. During the investigation process, the system provides comprehensive data analysis support to help investigators quickly locate the problem. The handling procedure will take appropriate measures according to the severity of the violation behavior, such as warning, fine, suspension of medical insurance service qualification, etc., and record the handling results in the system.

[0200] In embodiments of the present disclosure, the processing results can be fed back to each participant, including the patient, the pharmacy, the hospital, the medical insurance bureau, and the health commission, through the information sharing platform. The information sharing platform adopts a unified data format and interface standard to ensure that each party can accurately receive and understand the processing results. At the same time, the platform provides a feedback channel to facilitate each party to provide opinions and suggestions on the processing results. According to the feedback results, the system continuously improves and optimizes the regulatory measures to improve the overall regulatory effectiveness. The system regularly analyzes and summarizes the regulatory data (uses clustering algorithms (such as DBSCAN) to identify high-frequency violations, and uses regression analysis (such as linear regression) to evaluate the effectiveness of regulatory measures), finds out the problems and deficiencies in the regulatory process, and then makes targeted improvements and optimizations. For example, adjusting the parameters of the risk detection algorithm, optimizing the audit process, and strengthening the monitoring of key links.

[0201] Figure 6 A structural block diagram of a treatment scheme detection apparatus executed by an electronic device according to an embodiment of the present disclosure is schematically shown.

[0202] As shown in Figure 6 the treatment scheme detection apparatus 600 executed by an electronic device of this embodiment includes a taking manner detection module 610, a dosage detection module 620, and a detection result determination module 630.

[0203] The taking manner detection module 610 is configured to, in response to receiving a treatment scheme for a target user's to-be-treated disease input in a medical consultation interface, detect the taking manner of the treatment scheme according to actual priority and recommended priority of actual drug taking manners of each of the plurality of treatment drugs in the treatment scheme, to obtain a taking manner detection result, the recommended priority being a priority corresponding to a recommended drug taking manner of the treatment drug in the database. In an embodiment, the taking manner detection module 610 can be configured to perform the operation S210 described above, and details are not repeated here.

[0204] The dosage detection module 620 is configured to detect the dosage of each of the plurality of treatment components in the plurality of treatment drugs according to a dosage deviation degree of the plurality of treatment drugs, to obtain a dosage detection result, the dosage deviation degree being determined according to a body weight adjustment coefficient of the target user, a recommended dosage of the treatment drug in the database, and an actual dosage of the treatment drug in the treatment scheme. In an embodiment, the dosage detection module 620 can be configured to perform the operation S220 described above, and details are not repeated here.

[0205] The detection result determination module 630 is configured to determine a target detection result of the treatment scheme according to the taking manner detection result and the dosage detection result. In an embodiment, the detection result determination module 630 can be configured to perform the operation S230 described above, and details are not repeated here.

[0206] According to the embodiment of the present disclosure, the dose deviation degree of the medicine is determined according to the weight adjustment coefficient of the target user, the recommended dose of the therapeutic medicine and the actual dose of the therapeutic medicine in the treatment plan, the medicine taking mode is detected according to the priority of the medicine, and the dose of the therapeutic component is detected according to the dose deviation degree of the therapeutic medicine, so that the dose deviation degree of the medicine for the target user can be accurately determined, and whether the dose of the medicine is wrong can be indirectly detected. The medicine taking mode detection can avoid the error of the taking mode of the therapeutic medicine, and the rationality and authenticity of the treatment plan are detected in multiple aspects, so as to realize the multi-level and high-precision detection of the medicine taking mode, the medicine dose and the dose of the therapeutic component, improve the precision and efficiency of the treatment plan detection, and reduce the labor cost.

[0207] According to the embodiment of the present disclosure, the taking mode detection module 610 includes a component conflict detection sub-module and a medicine taking mode detection sub-module. The component conflict detection sub-module is configured to, in response to receiving the treatment plan, perform component conflict detection on the plurality of therapeutic components in the plurality of therapeutic medicines by using preset component conflict information, to obtain a component conflict detection result of the treatment plan, and the preset component conflict information includes conflict relationships between a plurality of preset components. The medicine taking mode detection sub-module is configured to, when the component conflict detection result indicates that the component conflict detection of the treatment plan is passed, detect the medicine taking mode of the treatment plan according to the actual priority and the recommended priority, to obtain a taking mode detection result.

[0208] According to the embodiment of the present disclosure, the component conflict detection sub-module includes a component matching unit, a conflict level determination unit and a conflict detection result determination unit. The component matching unit is configured to match the plurality of therapeutic components in the plurality of therapeutic medicines with the plurality of preset components having conflict relationships in the preset conflict information, to obtain a matching result. The conflict level determination unit is configured to, when the matching result indicates that the plurality of therapeutic components have conflict relationships, determine a conflict level between the plurality of therapeutic components. The conflict detection result determination unit is configured to determine the component conflict detection result according to the conflict level between the plurality of therapeutic components and the component dynamic factor of each of the plurality of therapeutic components, and the component dynamic factor is determined according to the preset basic weight and the adjustment weight of the therapeutic component, and the adjustment weight is determined according to the body state information of the target user.

[0209] According to the embodiment of the present disclosure, the component conflict detection sub-module further includes a component conflict information unit. The component conflict information display unit is configured to, when the conflict level meets a preset level condition, display a prompt interface with medicine component conflict information.

[0210] According to an embodiment of the present disclosure, the conflict detection result determination unit comprises a component risk value determination subunit, a component conflict information display subunit, and a component conflict detection result determination subunit. The component risk value determination subunit is configured to determine a component risk value of each of the plurality of therapeutic components according to the conflict level between the plurality of therapeutic components and the component dynamic factor of each of the plurality of therapeutic components, and determine a cumulative component risk value of the plurality of therapeutic components in the treatment scheme. The component conflict information display subunit is configured to display a prompt interface with the drug component conflict information in a case where the cumulative component risk value is greater than or equal to a preset component risk threshold. The component conflict detection result determination subunit is configured to obtain a component conflict detection result indicating that the component conflict detection of the treatment scheme is passed in a case where the cumulative component risk value is less than the preset component risk threshold.

[0211] According to an embodiment of the present disclosure, the drug taking mode detection sub-module comprises a quantization value determination unit, a target value determination unit, a target value accumulation unit, and a taking mode detection result determination unit. The quantization value determination unit is configured to determine an actual quantization value corresponding to the actual priority and a recommended quantization value corresponding to the recommended priority from a mapping relationship between the priority and the quantization value. The target value determination unit is configured to determine a target value satisfying a preset condition from a difference between the actual quantization value and the recommended quantization value and a preset value. The target value accumulation unit is configured to accumulate the target values corresponding to the plurality of therapeutic drugs to obtain a cumulative taking mode risk value. The taking mode detection result determination unit is configured to obtain a taking mode detection result indicating that the drug taking mode detection of the treatment scheme is passed in a case where the cumulative taking mode risk value satisfies a preset taking mode condition.

[0212] According to an embodiment of the present disclosure, the dose detection module 620 comprises a dose prompt sub-module, a cumulative dose determination sub-module, and a dose detection sub-module. The dose prompt sub-module is configured to display a prompt interface with a dose error in a case where there is a preset deviation degree in the plurality of dose deviation degrees. The cumulative dose determination sub-module is configured to determine a cumulative dose of each of the plurality of therapeutic components according to the content of the plurality of therapeutic components in the plurality of therapeutic drugs in a case where the plurality of dose deviation degrees are all less than the preset deviation degree. The dose detection sub-module is configured to detect the taking dose of the treatment scheme according to the cumulative dose of each of the plurality of therapeutic components, the safe cumulative amount, and the half-life of the therapeutic drug, and obtain a taking dose detection result.

[0213] According to an embodiment of the present disclosure, the taking mode detection module 610 comprises a suitability detection sub-module. The suitability detection sub-module is configured to detect the suitability of the plurality of therapeutic drugs according to the disease information of the target user for the preset disease in a case where the taking dose detection result indicates that the taking dose detection of the treatment scheme is passed, and obtain a suitability detection result of the treatment scheme for the target user.

[0214] According to an embodiment of the present disclosure, the detection result determination module 630 comprises a weighted sum sub-module. The weighted sum sub-module is configured to perform weighted sum on the taking manner detection result, the ingredient conflict detection result, the dosage detection result and the applicability detection result to obtain the target detection result of the treatment scheme.

[0215] According to an embodiment of the present disclosure, the treatment scheme detection apparatus 600 executed by the electronic device further comprises an image acquisition module, a time attenuation value determination module, a target time attenuation value determination module, a similarity threshold value determination module and an interface display module. The image acquisition module is configured to acquire the registered image of the target user from the database in response to receiving the verification image of the target user. The time attenuation value determination module is configured to determine the time attenuation value according to the verification time of the verification image, the registration time of the registered image and the annual attenuation rate. The target time attenuation value determination module is configured to determine the target time attenuation value satisfying the time attenuation condition from the time attenuation value and the preset time attenuation threshold value. The similarity threshold value determination module is configured to determine the similarity threshold value according to the target time attenuation value and the time adjustment coefficient. The interface display module is configured to display the medical inquiry interface to the target user in the case that the similarity between the verification image and the registered image is greater than the similarity threshold value, so as to facilitate the target user to input the to-be-treated disease in the medical inquiry interface.

[0216] According to an embodiment of the present disclosure, any one or more of the taking manner detection module 610, the dosage detection module 620 and the detection result determination module 630 can be combined in one module, or any one of them can be split into multiple modules. Alternatively, at least part of the function of one or more of these modules can be combined with at least part of the function of other modules, and implemented in one module. According to an embodiment of the present disclosure, at least one of the taking manner detection module 610, the dosage detection module 620 and the detection result determination module 630 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on substrate, a system on package, an application specific integrated circuit (ASIC), or any other reasonable way of integrating or packaging a circuit, etc. hardware or firmware, or in any one of software, hardware and firmware implementation or in any appropriate combination of any of them. Alternatively, at least one of the taking manner detection module 610, the dosage detection module 620 and the detection result determination module 630 can be at least partially implemented as a computer program module which can perform corresponding functions when executed.

[0217] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the above-mentioned module, program segment, or a part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession 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 or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0218] Those skilled in the art will appreciate that the features described in the various embodiments of the present disclosure may be combined and / or coupled in various ways, even if such combinations or couplings are not explicitly described in the present disclosure. In particular, the features described in the various embodiments of the present disclosure may be combined and / or coupled in various ways without departing from the spirit and teachings of the present disclosure. All such combinations and / or couplings fall within the scope of the present disclosure.

[0219] The above describes the embodiments of the present disclosure. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although each embodiment has been described separately above, this does not mean that the measures in each embodiment cannot be advantageously used in combination. Without departing from the scope of the present disclosure, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A treatment plan detection method performed by an electronic device, characterized in that: The method comprises: In response to receiving a treatment plan for a target user's condition input on a medical consultation interface, detecting the drug administration method of the treatment plan based on actual priorities and recommended priorities of respective actual drug administration methods of a plurality of therapeutic drugs in the treatment plan, and obtaining an administration method detection result, wherein the recommended priority is the priority corresponding to the recommended drug administration method of the therapeutic drug in a database; detecting the dosages of the plurality of therapeutic ingredients in the plurality of therapeutic drugs according to dosage deviations of the plurality of therapeutic drugs to obtain dosage detection results, wherein the dosage deviations are determined based on a weight adjustment factor of the target user, a recommended dosage of the therapeutic drug in the database, and an actual dosage of the therapeutic drug in the treatment plan; The target detection result of the treatment plan is determined based on the administration method detection result and the dosage detection result.

2. The method according to claim 1, characterized in that In response to receiving a treatment plan for a target user's condition to be treated input on a medical consultation interface, detecting a drug administration method of the treatment plan based on actual drug administration methods of each of a plurality of therapeutic drugs in the treatment plan and an actual priority and a recommended priority, including: In response to receiving the treatment plan, performing a component conflict detection on a plurality of the therapeutic components in the plurality of therapeutic drugs using preset component conflict information to obtain a component conflict detection result of the treatment plan, wherein the preset component conflict information includes conflict relationships between the plurality of preset components; When the component conflict detection result indicates that the component conflict detection of the treatment plan has passed, the drug administration method of the treatment plan is detected according to the actual priority and the recommended priority to obtain the administration method detection result.

3. The method according to claim 2, characterized in that The method of performing component conflict detection on a plurality of the therapeutic components in the plurality of therapeutic drugs using the preset component conflict information to obtain the component conflict detection result of the treatment plan includes: Matching the plurality of therapeutic ingredients in the plurality of therapeutic drugs with the plurality of preset ingredients having the conflict relationship in the preset conflict information to obtain a matching result; If the matching result indicates that the multiple therapeutic components have a conflict relationship, determining the conflict levels between the multiple therapeutic components; The component conflict detection result is determined based on the conflict levels between the multiple treatment components and the component dynamic factors of each of the multiple treatment components. The component dynamic factors are determined based on the preset basic weights and adjustment weights of the treatment components, and the adjustment weights are determined based on the physical condition information of the target user.

4. The method according to claim 3, characterized in that The method further comprises: When the conflict level meets the preset level conditions, a prompt interface with drug ingredient conflict information is displayed.

5. The method according to claim 3, characterized in that Determining the component conflict detection result according to the conflict levels between the multiple therapeutic components and the component dynamic factors of the multiple therapeutic components includes: determining a component risk value for each of the plurality of therapeutic components based on the conflict levels between the plurality of therapeutic components and the component dynamic factors for each of the plurality of therapeutic components, and determining a cumulative component risk value for the plurality of therapeutic components in the treatment regimen; When the cumulative component risk value is greater than or equal to a preset component risk threshold, a prompt interface with drug component conflict information is displayed; When the cumulative component risk value is less than the preset component risk threshold, the component conflict detection result is obtained, indicating that the component conflict detection of the treatment plan has passed.

6. The method according to claim 2, characterized in that The detecting of the drug administration method of the treatment plan according to the actual priority and the recommended priority to obtain the administration method detection result includes: Determining, from a mapping relationship between priorities and quantization values, an actual quantization value corresponding to the actual priority and a recommended quantization value corresponding to the recommended priority; Determining a target value that meets a preset condition from a difference between the actual quantized value and the recommended quantized value and a preset value; Accumulating the target values ​​corresponding to the plurality of therapeutic drugs to obtain a cumulative risk value of the administration mode; When the cumulative administration method risk value meets the preset administration method condition, the administration method detection result is obtained, indicating that the drug administration method detection of the treatment plan has passed.

7. The method according to claim 1, characterized in that The step of detecting the dosage of each of the plurality of therapeutic components in the plurality of therapeutic drugs based on the dosage deviation of the plurality of therapeutic drugs to obtain dosage detection results includes: When there is a dosage error prompt interface when there is a dosage error among the plurality of dosage deviations that is greater than a preset deviation; When the dose deviations of the plurality of therapeutic components are all less than the preset deviation, determining the cumulative doses of the plurality of therapeutic components according to the contents of the plurality of therapeutic components in the plurality of therapeutic drugs; The dosage of the treatment plan is tested based on the cumulative dosage, safe cumulative amount and half-life of the therapeutic drugs of each of the multiple therapeutic components to obtain the dosage test results.

8. The method according to claim 2, characterized in that The method further comprises: When the dosage detection result indicates that the dosage detection of the treatment plan has passed, the applicability of the plurality of therapeutic drugs is detected according to the symptom information of the target user for the preset symptom to obtain the applicability detection result of the treatment plan for the target user.

9. The method according to claim 8, characterized in that Determining the target detection result of the treatment plan based on the administration method detection result and the dosage detection result includes: A weighted sum is performed on the administration method detection result, the component conflict detection result, the dosage detection result, and the applicability detection result to obtain a target detection result of the treatment plan.

10. The method according to claim 1, characterized in that The method further comprises: In response to receiving the verification image of the target user, obtaining a registration image of the target user from the database; determining a time decay value according to the verification time of the verification image, the registration time of the registration image, and the annual decay rate; Determining a target time decay value that meets a time decay condition from the time decay value and a preset time decay threshold; determining a similarity threshold according to the target time decay value and the time adjustment coefficient; When the similarity between the verification image and the registration image is greater than the similarity threshold, the medical consultation interface is displayed to the target user, so that the target user can input the disease to be treated on the medical consultation interface.

Images