Precise matching method and system for patient treatment scheme based on quantification rule

Abstract

The invention provides an accurate matching method and system for a patient treatment scheme based on a quantification rule, and belongs to the technical field of digital therapy. Based on the type of the obtained intervention means, configuring a quantification rule to obtain a plurality of sub intervention means, including determining a patient index and setting basic information of the quantification rule and an intervention effective quantification condition according to the patient index; obtaining index data of the patient; matching the sub-intervention means based on the obtained index data of the patient, traversing all the sub-intervention means, and returning the quantification rule and the sub-intervention means including the quantification rule when the index of the patient meets the effective condition of the quantification rule; and generating a task message from the matched sub intervention means, and pushing the task message to a mobile terminal of the patient. According to the accurate matching method and system, a more targeted accurate treatment scheme can be matched for each patient according to the actual index condition of the patient, and the treatment effect is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of digital therapeutics, and in particular, to a precise matching method and system for a patient treatment plan based on quantization rules. Background Art

[0002] Digital Therapeutics (DTx) is a subset of digital health and is an evidence-based treatment intervention driven by high-quality software programs for preventing, managing, or treating medical disorders or diseases. It can be broadly defined as a treatment method that uses digital technology and Internet-based health technology to stimulate patients' behavior change. Digital therapeutics can break through the limitations of traditional drug treatment and present treatment and management plans in the form of application software through digital means to achieve intervention and treatment. The application software can be used remotely, is simple, convenient, and has good interactivity, and can effectively improve the treatment rate of related diseases. Whether it is for Alzheimer's disease, insomnia, anxiety, depression, autism, or attention deficit hyperactivity disorder, digital therapeutics can enable patients to carry out a large number of active interventions and trainings at home. Compared with traditional therapies, digital therapeutics can significantly reduce the economic burden on patients and reduce the time required for patients to visit doctors, thus providing a more cost-effective treatment.

[0003] However, current digital therapeutics generally adopt a general treatment plan and cannot meet the personalized treatment needs of each patient. On the one hand, the general treatment plan cannot fully consider the disease state, physiological characteristics, and treatment responses of each patient, lacking pertinence in treatment, thus affecting the treatment effect. On the other hand, the treatment plans of digital therapeutics often involve multiple treatment means, different doses and frequencies, etc., which increases the difficulty for medical staff to make reasonable configurations, resulting in uncertainties and errors in the formulation and implementation of the treatment plan, affecting the accuracy and effectiveness of the treatment, and patients cannot obtain good treatment effects. Summary of the Invention

[0004] In view of the above problems, in order to enable the treatment plan to be more precisely matched with the actual situation of patients, reduce the complexity and difficulty of the treatment process, reduce unnecessary interventions that may exist in the treatment process, and ensure the treatment effect of patients, the present invention provides a precise matching method and system for a patient treatment plan based on quantization rules, which improves the existing digital therapeutics and can automatically match targeted intervention means through the patient's own index data.

[0005] In a first aspect, the present invention provides a precise matching method for a patient treatment plan based on quantization rules, and the method includes:

[0006] Obtain the type of intervention means;

[0007] Based on the type of intervention means obtained, configure quantification rules to obtain multiple sub-intervention means. For each type of intervention means, multiple quantification rules are configured. Each sub-intervention means corresponds to a type of intervention means and a quantification rule, including determining patient indicators and setting the basic information of the quantification rule and the intervention effective quantification conditions based on the patient indicators.

[0008] Obtain the indicator data of the patient.

[0009] Based on the obtained indicator data of the patient, perform matching of sub-intervention means. Traverse all sub-intervention means. When the patient indicators meet the effective conditions of the quantification rule, return the current quantification rule and the sub-intervention means including the current quantification rule.

[0010] Generate a task message for the matched sub-intervention means and push it to the patient's mobile terminal.

[0011] As a further improvement of the present invention, before performing the matching of sub-intervention means based on the obtained indicator data of the patient, the mobile terminal of the patient receives the prescription solution formulated by the doctor, and after obtaining the message of the patient's mobile terminal confirming the prescription solution, trigger the matching of sub-intervention means based on the obtained indicator data of the patient.

[0012] The start timing of the matching of intervention means according to the patient indicators of the present invention is determined by the patient through the mobile terminal. Only after the patient receives the prescription solution formulated by the doctor for him / her and confirms the prescription solution on the mobile terminal will the matching and screening of the treatment plan be started, which reflects the initiative of the patient and is a guarantee of the patient's rights and interests.

[0013] As a further improvement of the present invention, the quantification rule includes a stop intervention condition. When performing the matching of sub-intervention means based on the obtained indicator data of the patient, first judge the stop intervention condition. When the stop intervention condition is not met, then perform the quantification rule matching of the intervention effective quantification condition.

[0014] As a further improvement of the present invention, before performing the matching of sub-intervention means based on the obtained indicator data of the patient, perform the conversion of the data structure of the intervention effective condition.

[0015] As a further improvement of the present invention, the basic information of the quantification rule includes naming, the longest usage days, and the intervention frequency.

[0016] As a further improvement of the present invention, the types of intervention means include one or several of drug intervention, video intervention, video intervention, audio intervention, and popular science intervention.

[0017] As a further improvement of the present invention, the mobile terminal includes one or several of a mobile phone, a tablet computer, and a smart wearable device.

[0018] In a second aspect, the present invention provides a precise matching system for a patient treatment plan based on quantization rules, and the system includes:

[0019] An intervention means type acquisition module, configured to configure the type of intervention means and obtain at least one intervention means type as the to-be-pushed intervention means type;

[0020] A quantization rule configuration module, configured to perform quantization rule configuration on the to-be-pushed intervention means type obtained by the intervention means type acquisition module, including:

[0021] A patient index determination unit, configured to determine the patient indexes required in the quantization rules;

[0022] And a quantization condition setting unit, configured to set the intervention effective quantization conditions of the quantization rules for the patient indexes determined by the patient index determination unit;

[0023] A patient index data acquisition module, configured to collect the current index data of the patient, and the indexes are the patient indexes already determined in the patient index determination unit;

[0024] A quantization rule matching module, configured to match the current patient index data obtained by the patient index data acquisition module with the quantization rules configured in the quantization rule configuration module, and obtain the quantization rules that meet the intervention effective quantization conditions and the intervention means including the quantization rules;

[0025] A task information generation module, configured to generate a task message based on the intervention means successfully matched by the quantization rule matching module and push it;

[0026] A mobile terminal, configured to receive the task information pushed by the task information generation module and perform intervention treatment on the patient.

[0027] As a further improvement of the present invention, it further includes a prescription setting module. A doctor customizes a digital therapy prescription solution for a patient in the prescription setting module and sends it to the mobile terminal. After the patient confirms the prescription solution formulated by the doctor through the prescription setting module on the mobile terminal, the quantization rule matching module is triggered to perform quantization rule matching.

[0028] As a further improvement of the present invention, it further includes a data structure conversion module, configured to convert the data formed in the quantization condition setting unit.

[0029] The present invention provides a precise matching method and system for a patient treatment plan based on quantization rules, which automatically matches the most targeted intervention means in all quantization rules according to the own indicators of each patient for treatment. There is no need for a doctor to configure a treatment plan for the patient based on personal experience. While improving the formulation efficiency of the treatment plan, it can more specifically intervene and treat the patient, significantly improving the treatment effect of digital therapy; the solution of the present invention reduces the unnecessary interventions and side effects existing in the treatment process, thereby also improving the treatment satisfaction of the patient. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 is a schematic flowchart of the precise matching method for a patient treatment plan based on quantization rules in Embodiment 1.

[0031] Figure 2 is another schematic diagram of the precise matching method for a patient treatment plan based on quantization rules in Embodiment 1.

[0032] Figure 3 is a schematic diagram of the precise matching system for a patient treatment plan based on quantization rules in Embodiment 2.

[0033] Description of reference numerals: 1. Intervention means type acquisition module; 2. Quantization rule configuration module; 3. Patient index data acquisition module; 4. Quantization rule matching module; 5. Task information generation module; 6. Mobile terminal. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0034] The following combines specific embodiments and the attached Figures 1 - 3 to make a detailed description of the invention, so that those skilled in the art can more fully understand the purpose, features and effects of the present invention.

[0035] Unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as commonly understood by those skilled in the art to which the present invention belongs. When the definition of a term in this specification conflicts with the meaning commonly understood by those skilled in the art to which the present invention belongs, the definition in this document shall prevail.

[0036] The present invention provides a precise matching method and system for a patient treatment plan based on quantization rules, which makes improvements in view of the problems of lack of pertinence and insufficient precision of the treatment plan in existing digital therapies, and improves the treatment effect of patients.

[0037] Embodiment 1

[0038] As a specific embodiment of the present invention, this embodiment provides a precise matching method for a patient treatment plan based on quantization rules. Referring to Figure 1 、 Figure 2 , including:

[0039] S100. Obtain the type of intervention means to be pushed

[0040] Configure the types of intervention means for digital therapy. There are at least 5 types of intervention means, including drug intervention, food intervention, video intervention, audio intervention, and science popularization intervention.

[0041] Among them, drug intervention is carried out by having the patient take medicine, food intervention is carried out by having the patient have a reasonable diet, video intervention is carried out by having the patient watch videos, audio intervention is carried out by having the patient listen to audio, and science popularization intervention is carried out by popularizing knowledge to the patient.

[0042] Based on the configured types of intervention means, obtain and determine at least one type of intervention means as the type of intervention means to be pushed.

[0043] S200. Configure quantization rules based on the type of intervention means to be pushed

[0044] Configure quantization rules based on the type of intervention means obtained in S100. Multiple quantization rules can be configured for one type of intervention means to be pushed, but ultimately only one quantization rule is selected.

[0045] The quantization rules include naming, the longest usage days, intervention frequency, intervention time points, and quantization conditions. For example, the naming of one quantization rule is mild, the longest usage days is 180 days, the intervention frequency of pushing the intervention every day is 3 times, and the intervention time points are 19:00, 20:00, and 21:00 respectively, that is, an intervention treatment is carried out once at 19:00, 20:00, and 21:00 every day within 180 days.

[0046] Multiple quantization rules are configured for each type of intervention means, forming multiple sub-intervention means containing different quantization rules. The multiple sub-intervention means constitute a sub-intervention means configuration library, that is, each sub-intervention means corresponds to one type of intervention means and one quantization rule.

[0047] In this embodiment, since at least one quantization rule is configured for the same type of intervention means to be pushed, different quantization rules are distinguished by naming. The purpose of configuring the longest usage days is to prevent the sub-intervention means containing the type of intervention means to be pushed from being infinitely generated tasks and pushed to the patient. For example, if the type of intervention means to be pushed of the sub-intervention means is drug intervention and the configured longest usage days is 10 days, then the sub-intervention means will no longer be pushed on the 11th day. The intervention frequency determines the degree of intervention on the patient and controls the number of times the selected sub-intervention means is pushed to the patient. The intervention time points are to determine the specific time points when the selected sub-intervention means is pushed to the patient.

[0048] In this embodiment, the quantitative condition is to determine whether to push the sub-intervention means by setting certain conditions. Only when the patient's indicators meet the quantitative conditions will the quantitative rule take effect, and the sub-intervention means configured with the quantitative rule will be pushed to the patient for intervention treatment. By setting the quantitative conditions for the intervention to take effect, the quantitative rules corresponding to the patient and patients with different indicators and the intervention means containing the quantitative rules can be automatically determined, and then the intervention means containing the quantitative rules will be generated and pushed to the corresponding patient after generating task information, and the patient will be intervened and different intensities of intervention will be performed on patients with different indicators, such as the increase or decrease of the frequency of intervention or the amount.

[0049] The settings of quantification conditions include:

[0050] S201. Determine patient indicators and set quantitative conditions based on the indicators

[0051] A patient indicator is selected, and a target value and an operator of the patient indicator are determined, and the patient indicator is saved in a database when all sub-intervention means of digital therapy are released. The database may be a PostgreSQL database. Patient indicators are indicators used to describe patient characteristics.

[0052] Specifically, in the computer, the setting example of the indicator is as follows:

[0053] "{\"combinator\":\"and\",\"conditions\":[{\"combinator\":\"and\",\"conditions\":[{\"fieldName\":\"Whether the pressure yesterday was excessive. Value\",\"operator\":\"EQ\",\"field\":\"indicator.excessive_pressure.value\",\"value\":[[\"Yes\"]],\"type\":\"STRING\"}]}]}"

[0054] In this example, the indicator is "whether the pressure yesterday was too high". Among them, combinator is a logical symbol, including and, or, the purpose is to combine two conditions. In the above example, and is the value of the logical symbol, indicating that condition 1 and condition 2 are met at the same time;

[0055] Operator is an operator, including greater than, less than, and equal to. In the above example, EQ is the value of the operator, which means equal to. The purpose is to compare the patient's index value with the target value and finally determine whether the condition is met;

[0056] The "field" is the index coding field, whose purpose is to bind the index and the quantization rule. "indicator.excessive_pressure.value" represents the value of the index coding; "value" is the target value, whose purpose is to compare with the value of the patient's index.

[0057] The meaning represented by the above example is: the condition is satisfied when the value of the index "Whether the pressure was excessive yesterday" is equal to "Yes". Among them, the data type of the index is "STRING". When the value collected according to the patient's own index "Whether the pressure was excessive yesterday" is equal to "Yes", it means that the index data of the patient meets this quantization condition, and the quantization rule containing this quantization condition is triggered.

[0058] The setting of the quantization condition includes the setting of the quantization condition for the intervention to take effect and the setting of the condition to stop the intervention.

[0059] In this embodiment, JSON structure data is used to set the quantization condition. JSON structure data has the advantages of being easy to read and write, and having strong readability, which is convenient for developers to view and edit during development and debugging.

[0060] S202. Data structure conversion

[0061] The JSON structure data in S201 is converted into Groovy script data and then stored, which is convenient for the script execution engine provided by JDK to execute the Groovy script data.

[0062] Specifically, the data in JSON structure is concatenated and replaced through strings, and after being converted according to the agreed rules, it is saved in the database.

[0063] Specifically, referring to the example in S201 above, the following method is used for the conversion of the data structure:

[0064] "combinator" represents a variable, "and" represents a variable. The value "and" of "combinator" is converted into the "&&" symbol in the Groovy script, representing "and". "condition" represents a condition group, and after being converted into the Groovy script, it represents the parentheses in the condition "()&&()". This is a nested structure, indicating that the condition group can have infinitely many layers, but the finally generated Groovy script has only one return result, that is, the result after the logical operation of the condition group.

[0065] Operator represents the operator. The value of the operator is set by EQ. In the Groovy script, EQ is displayed as EQ. Conditions.textCondition() can be understood as an equal sign. Field represents the attribute. Indicator.excessive_pressure.value is the value of the attribute, which corresponds to indicator.excessive_pressure.value in the Groovy script. It exists as a variable in the script. When the script is run, the value of this indicator of the patient will be obtained through this variable. Type represents the data type. The textCondition part in the Groovy script is set by type, indicating that the data is of text type. If it is number type data, numberCondition is generated. Obj is fixed and is used to represent the receiving parameters of the Groovy script.

[0066] The above solution can realize the function of converting JSON structure data into Groovy script data, so that the nested structure of the conditional group can be correctly represented in the Groovy script and used in the script through variables and properties. Such a conversion solution can realize the seamless conversion of JSON data structure to Groovy script, and also facilitate the subsequent logical operation and result judgment of the conditional group.

[0067] Groovy is a dynamic scripting language based on the JVM. Its syntax is concise and easy to understand, making the converted script data easier to read and maintain, and improving the readability and maintainability of the code.

[0068] The converted data format is as follows:

[0069] "triggerCondition":......&&(Conditions.textCondition(obj.get('indicator.excessive_pressure.value',null)as String,'EQ',[\"有\"]))

[0070] In this example, Conditions is a custom Java class. Since Groovy is also a language that runs in the JVM environment, Java methods can be used conveniently. The converted script data can interoperate with other Java applications, improving the reusability and sharing of data.

[0071] In this embodiment, JSON structure data is converted into Groovy script data, making data management and use simpler.

[0072] S300. Determine and push intervention task information

[0073] Based on the patient's current indicator data, generate task information for the sub - intervention means containing the quantification rules matching the patient's indicators in S200 and send it to the patient for intervention treatment.

[0074] In this embodiment, the patient can use a smart mobile terminal to receive the generated task information. The mobile terminal can be a mobile phone, a tablet computer, or a smart wearable device such as a smart watch. For example, the patient can operate after downloading the corresponding digital therapy APP software program on the mobile phone side and receive the generated task information through the APP software program on the mobile phone side.

[0075] When the value of the patient's indicator meets the quantification condition for stopping intervention in the quantification rule, no intervention treatment is carried out.

[0076] Specifically, it includes:

[0077] S301. Obtain and store patient indicator data

[0078] Based on the patient's indicators determined in S201, collect the corresponding indicator data of the patient, obtain the current actual values of all indicators, and then save the data in the patient's meta - database.

[0079] The collection of patient indicators can be in the form of a questionnaire survey or can be collected using a data collection terminal. This embodiment does not limit this.

[0080] S302. Quantification rule matching

[0081] According to the patient's current indicator data obtained in S301, query all sub - intervention means in the sub - intervention means configuration library. The self - intervention means are stored in the PostgreSQL database. Traverse all quantification rules. If the patient's indicator data meets the quantification condition for starting intervention, the matching is successful and return the quantification rule and the sub - intervention means containing this quantification rule. The judgment principle is: If the patient's indicator meets the matching condition of the configured quantification rule, it is determined that the matching is successful; otherwise, it is determined that the matching fails.

[0082] Generate task information for the matched sub - intervention means and send it to the patient's mobile terminal. Further, send the task information to the patient's mobile phone APP.

[0083] Further, before S302, the patient receives the prescription solution formulated by the doctor on the mobile terminal. After confirming that the prescription treatment plan is correct on the mobile terminal, the patient activates the digital therapy through the mobile terminal, and at the same time, the mobile terminal sends information to trigger the quantification rule matching.

[0084] In this embodiment, after the patient activates the digital therapy through the mobile terminal, a RabbitMq message body is sent to trigger the matching of quantization rules.

[0085] An example of the RabbitMq message body is as follows:

[0086] {"messageId":"d903aed4625047478797e06ebaee7caa","data":{"dtxId":25,"memberId":92,"instId":19},"createTime":"1687677917272"}

[0087] Among them, dtxId is the id of the digital therapy confirmed by the patient, memberId represents the unique identifier of the patient, and InstId represents the prescription instance of the patient.

[0088] After that, according to the memberId, the patient's index data information is queried through the patient's meta-database for quantization rule matching.

[0089] Furthermore, when performing quantization rule matching, first judge the stop intervention condition. When the stop intervention condition is not met, then perform the quantization rule matching for starting the intervention.

[0090] Specifically, obtain the groovy script for the stop intervention condition, and use the current patient index information and the groovy script text as input parameters to pass to the groove script and hand it over to the groovy execution engine to obtain the script execution result (true or false). If it is true, it means that the stop intervention condition is met. If it is false, it means that the stop intervention condition is not met.

[0091] By using the current patient index information and the Groovy script text as input parameters to pass to the Groovy script and hand it over to the groovy execution engine, it is possible to make a conditional judgment according to the actual situation of the patient. When it is judged that the stop intervention condition is met, there is no need to perform the quantization rule matching for the intervention. Otherwise, perform the quantization rule matching for the intervention.

[0092] Furthermore, a RabbitMq message body is generated based on the matched sub-intervention means, and its data definition is as follows:

[0093] {"createTime":"1694277000549","data":{"baselineTime":1694277000549,"businessId":30,"dt xId":825,"quantization":{"genType":2,"id":79},"type":"SK","userId":3204},"messageId":"c9c2feb130a341a8af7582e56936fff9"}

[0094] Among them, dtxId represents the matching digital therapy id, that is, the id of the sub-intervention means. Quantization includes the generated type and the matched quantization rule id. Type represents the type of the intervention means, and userId represents the patient id. All the intervention means associated with the digital therapy and their quantization rules can be queried from the Postgres database through dtxId, that is, all sub-intervention means can be queried from the database through dtxId.

[0095] Based on the generated RabbitMq message body, query the longest usage days, intervention frequency, and intervention time point of the quantization rule of the matched sub-intervention means in the sub-intervention means configuration library according to the dtxId of the matched digital therapy and the id of the matched quantization rule. The intervention time point is the execution time point of the task.

[0096] After querying the longest usage days, intervention frequency, and intervention time point of the sub-intervention means, generate a cron expression according to the intervention time point and intervention frequency, and calculate the final intervention time point when the quantization rule is valid according to the longest usage days. Then, judge the start time point of the cron expression based on the cron expression. After reaching the start time point of the cron expression, send a task carrying the task id and generate task information based on the matched sub-intervention means based on this task. The sub-intervention means information can be queried according to the task id. Finally, push this task information to the patient's intelligent mobile terminal, such as the patient's mobile phone.

[0097] By querying the longest usage days, intervention frequency, and intervention time point of the sub-intervention means, personalized intervention tasks can be customized to ensure that the correct intervention is provided to the patient at the correct time point, improving the intervention effect.

[0098] By generating a cron expression, automatic scheduling of intervention tasks can be realized, and the task execution time can be accurately arranged according to the intervention frequency and intervention time point, improving the automation degree and execution efficiency.

[0099] The precise matching method of the patient treatment plan based on quantization rules in this embodiment configures multiple quantization rules for each type of intervention method, increasing the selection range of intervention methods. Instead of simply adopting the general digital therapy treatment plan, it enables the automatic provision of a more targeted treatment plan for each patient according to the actual index situation of the patient, ensuring the treatment effect and quality of the patient.

[0100] Embodiment 2

[0101] As a specific embodiment of the present invention, this embodiment provides a precise matching system for the patient treatment plan based on quantization rules. Referring to Figure 3 , it includes an intervention method type acquisition module 1, a quantization rule configuration module 2, a patient index data acquisition module 3, a quantization rule matching module 4, a task information generation module 5, and a mobile terminal 6.

[0102] The intervention method type acquisition module 1 is used to configure the types of intervention methods, and obtain at least one intervention method type as the to-be-pushed intervention method type according to the configured intervention method types. The types of intervention methods include drug intervention, video intervention, video intervention, audio intervention, and science popularization intervention.

[0103] The quantization rule configuration module 2 is used to configure quantization rules for the to-be-pushed intervention method types obtained by the intervention method type acquisition module 1 and save the configuration results in the database. Multiple quantization rules are configured for each to-be-pushed intervention type. The quantization rules include basic information and intervention effective quantization conditions.

[0104] The quantization rule configuration module 2 includes:

[0105] A patient index determination unit, which is used to determine the patient indexes required in the quantization rules;

[0106] And a quantization condition setting unit, which sets the intervention effective quantization conditions of the quantization rules for the patient indexes determined by the patient index determination unit.

[0107] The patient index data acquisition module 3 is used to collect the current index data of the patient, and the indexes are the patient indexes that have been determined in the patient index determination unit.

[0108] The quantization rule matching module 4 is used to match the patient current index data obtained by the patient index data acquisition module 3 with the quantization rules configured in the quantization rule configuration module 2, and obtain the quantization rules that meet the intervention effective quantization conditions and the intervention methods including these quantization rules.

[0109] The task information generation module 5 is used to generate a task message based on the intervention method successfully matched by the quantization rule matching module 4 and push it.

[0110] A mobile terminal 6, which is used to receive the task information pushed by the task information generation module 5 to perform intervention treatment on patients.

[0111] In another specific embodiment of the present invention, the precise matching system for the patient treatment plan based on quantization rules further includes a prescription setting module. The doctor customizes a digital therapy prescription solution for the patient in the prescription setting module and sends it to the mobile terminal 6. After the patient confirms the prescription solution formulated by the doctor through the prescription setting module on the mobile terminal 6, the quantization rule matching module 4 is triggered to perform quantization rule matching.

[0112] Specifically, the patient enables quantization rule matching by sending a RabbitMq message body from the mobile terminal 6 to the quantization rule matching module 4. The message body instance is as follows:

[0113] {"messageId":"d903aed4625047478797e06ebaee7caa","data":{"dtxId":25,"memberId":92,"instId":19},"createTime":"1687677917272"}

[0114] Among them, dtxId represents the id of the digital therapy confirmed by the patient, memberId represents the unique patient identifier of the patient in the system, and InstId represents the prescription instance of the patient.

[0115] In another specific embodiment of the present invention, the precise matching system for the patient treatment plan based on quantization rules further includes a data structure conversion module, which is used to convert the JSON structure data formed in the quantization condition setting unit into Groovy script data, making it easier to process and utilize the data.

[0116] In another specific embodiment of the present invention, the precise matching system for the patient treatment plan based on quantization rules further includes a timed task scheduling module. The quantization rule matching module 4 sends the intervention means information to the task information generation module 5 by sending a RabbitMq message body. After receiving the RabbitMq message body sent by the quantization rule matching module 4, the task information generation module 5 determines the task start time and sends it to the timed task scheduling module for execution. After the timed task scheduling module determines that the start time has arrived, it notifies the task information generation module 5 to push the task information. The timed task scheduling module in this embodiment is the XXL-JOB timed task scheduling module.

[0117] Specifically, the quantization rule matching module 4 sends the matched intervention means information to the task information generation module 5 through a RabbitMq message body. Its data definition is as follows:

[0118] {"createTime":"1694277000549","data":{"baselineTime":1694277000549,"businessId":30,"dt xId":825,"quantization":{"genType":2,"id":79},"type":"SK","userId":3204},"messageId":"c9c2feb130a341a8af7582e56936fff9"}

[0119] Among them, dtxId represents the matching digital therapy id, that is, the id of the intervention means, quantization includes the generated type and the matched quantization rule id, type represents the type of the intervention means, and userId represents the user id. All the intervention means associated with the digital therapy and the quantization rules of these intervention means can be queried from the database through dtxId.

[0120] After receiving the RabbitMq message body, the task information generation module 5 queries the longest usage days, intervention frequency, and intervention time points of the quantization rules of the matched intervention means according to the dtxId of the matched digital therapy and the id of the matched quantization rule, generates a cron expression according to the intervention time point and intervention frequency, and calculates the final intervention time point when the quantization rule is valid according to the longest usage days, and sends it to the XXL-JOB timed task scheduling module for execution.

[0121] The timed task scheduling module reads and processes the cron expression, judges whether it reaches the start time point of the cron expression. After reaching the start time point of the cron expression, it sends the task carrying the task id to the task information generation module 5. The intervention means information can be queried according to the task id. Finally, the task information generation module 5 generates the task information and sends it to the patient's intelligent mobile terminal 6.

[0122] The accurate matching method and system of the patient treatment plan based on the quantization rule of the present invention can automatically match the most suitable intervention means from multiple intervention treatment plans according to the patient's indicators to intervene in the patient, without the need for medical staff to configure according to personal experience, simplifies the process of formulating and implementing the treatment plan while improving the pertinence, and reduces the difficulty of treatment; moreover, since the treatment plan can be adjusted according to the actual indicator situation of the patient, the accuracy and effectiveness of the treatment are guaranteed, the treatment effect is maximally improved, the interference of some unnecessary human factors is reduced, and the satisfaction of the patient is also improved.

[0123] The precise matching system for patient treatment plans based on quantization rules can collect and analyze the actual indicator data and treatment outcomes of patients, providing valuable data and explanations for medical research. Through data-driven research, treatment plans can be continuously optimized and improved, promoting the development and application of digital therapeutics.

[0124] As described above, it is only the preferred embodiment of the present invention, and it is not limited to the present invention in any other form. Any modification or equivalent change made according to the technical essence of the present invention still falls within the scope claimed by the present invention.

Claims

1. A precise matching method for a patient treatment plan based on quantization rules, characterized in that, The method includes: Obtaining the type of intervention means; Based on the obtained type of intervention means, configuring quantization rules to obtain multiple sub-intervention means. For each type of intervention means, multiple quantization rules are configured. Each sub-intervention means corresponds to one type of intervention means and one quantization rule, including determining patient indicators and setting the basic information of the quantization rule and the intervention effectiveness quantization condition based on the patient indicators; Obtaining the indicator data of the patient; Based on the obtained indicator data of the patient, perform matching of sub-intervention means. Traverse all sub-intervention means. When the patient indicators meet the effectiveness condition of the quantization rule, return the current quantization rule and the sub-intervention means including the current quantization rule; Generate a task message for the matched sub-intervention means and push it to the patient's mobile terminal.

2. The precise matching method for a patient treatment plan based on quantization rules according to claim 1, wherein Before performing the matching of sub-intervention means based on the obtained indicator data of the patient, the patient's mobile terminal receives the prescription solution formulated by the doctor, and after obtaining the confirmation message of the prescription solution by the patient's mobile terminal, trigger the matching of sub-intervention means based on the obtained indicator data of the patient.

3. The precise matching method for a patient treatment plan based on quantization rules according to any one of claims 1-2, characterized in that, The quantization rule includes a stop intervention condition. When performing the matching of sub-intervention means based on the obtained indicator data of the patient, first judge the stop intervention condition. When the stop intervention condition is not met, then perform the quantization rule matching of the intervention effectiveness quantization condition.

4. The precise matching method for a patient treatment plan based on quantization rules according to any one of claims 1-2, characterized in that, Before performing the matching of sub-intervention means based on the obtained indicator data of the patient, perform the conversion of the intervention effectiveness condition data structure.

5. The precise matching method for a patient treatment plan based on quantization rules according to claim 1, characterized in that, The basic information of the quantization rule includes naming, the longest usage days, and the intervention frequency.

6. The precise matching method for a patient treatment plan based on quantization rules according to claim 1, characterized in that The types of intervention means include one or several of drug intervention, video intervention, video intervention, audio intervention, and popular science intervention.

7. The precise matching method for a patient treatment plan based on quantization rules according to claim 1, characterized in that, The mobile terminal includes one or several of a mobile phone, a tablet computer, and a smart wearable device.

8. A precise matching system for a patient treatment plan based on quantization rules, characterized in that, The system includes: An intervention means type acquisition module, configured to configure the type of intervention means and obtain at least one type of intervention means as the to-be-pushed intervention means type; A quantization rule configuration module, configured to perform quantization rule configuration on the to-be-pushed intervention means type obtained by the intervention means type acquisition module, including: A patient indicator determination unit, configured to determine the patient indicators required in the quantization rule; And a quantization condition setting unit, configured to set the intervention effectiveness quantization condition of the quantization rule for the patient indicators determined by the patient indicator determination unit; A patient indicator data acquisition module, configured to collect the current indicator data of the patient, and the indicator is the patient indicator already determined in the patient indicator determination unit; A quantization rule matching module, configured to match the current indicator data of the patient obtained by the patient indicator data acquisition module with the quantization rules configured in the quantization rule configuration module, and obtain the quantization rules that meet the intervention effectiveness quantization condition and the intervention means including the quantization rules; A task information generation module, configured to generate a task message for the intervention means successfully matched by the quantization rule matching module and push it; A mobile terminal, which is used to receive the task information pushed by the task information generation module to perform intervention treatment on patients.

9. The precise matching system for patient treatment plans based on quantization rules according to claim 8, wherein It further includes a prescription setting module. A doctor customizes a digital therapy prescription solution for a patient in the prescription setting module and sends it to the mobile terminal. After the patient confirms the prescription solution formulated by the doctor through the prescription setting module on the mobile terminal, the quantization rule matching module is triggered to perform quantization rule matching.

10. The precise matching system for a patient treatment plan based on quantization rules according to claim 8, characterized in that, It further includes a data structure conversion module, which is used to convert the data formed in the quantization condition setting unit.

Images