Intervention task planning system, device and method

Abstract

The invention provides an intervention task planning system, device and method, and belongs to the technical field of digital therapy, and the method comprises the steps: enabling the system to carry out the matching of patient index data with a plurality of pre-configured group treatment templates containing intervention metadata, and enabling the matched group treatment templates to serve as first planning data; according to the patient index data and the intervention metadata, generating second planning data based on AIGC; obtaining evaluation results of the first planning data and the second planning data to determine intervention planning data; determining an intervention task based on intervention metadata in the intervention planning data; the device comprises a first planning data acquisition module, a second planning data acquisition module and an intervention task determination module. By evaluating the first planning data generated by simulating the left brain and the second planning data generated by simulating the right brain, the intervention planning data more suitable for the illness state of the patient is determined to plan the final intervention task, and the treatment effect of the patient is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of digital therapeutics, and particularly to an intervention task planning system, device and method. Background Art

[0002] Digital Therapeutics (DTx) is a subset of digital health and is an evidence-based therapeutic 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] The left-right brain theory holds that the human brain is divided into two hemispheres, the left brain and the right brain, and each hemisphere has different functions and abilities. The left brain is mainly responsible for tasks such as language, logical reasoning, analysis and mathematics. It is considered the "expert brain" and has strong capabilities in dealing with details, sequences and logical problems. The left brain tends to use symbols, symbol systems and language to express thoughts and is good at linear thinking and sequential processing. This makes the left brain perform excellently in academic fields, scientific research and logical reasoning.

[0004] The right brain is mainly responsible for tasks such as spatial perception, image processing, emotion and intuition. It is considered the "wisdom brain" and has strong capabilities in dealing with wholes, patterns and creative problems. The right brain tends to perform comprehensive thinking and non-linear processing, and can recognize, understand and express non-verbal information, such as images, music and emotions. The right brain has outstanding performance in art, music, creative thinking and solving complex problems.

[0005] In the formulation of digital therapeutics treatment plans, it often tends to follow the left-brain theory, that is, experts formulate treatment plans for patients based on clinical experience according to the patient's condition and set intervention tasks for execution. For example, CN115762812A discloses a digital diagnosis and treatment method for stroke patients, which specifically includes obtaining the health status information and daily life information uploaded by stroke patients; and a digital therapeutics prescription issued by in-hospital doctors based on the health status information and daily life information uploaded by the stroke patients.

[0006] Although the digital therapy treatment plan formulated by the above-mentioned "expert brain" can achieve a certain degree of treatment effect on patients, due to the lack of participation of the "intelligent brain", the formulated treatment plan completely depends on the "expert brain" plan, resulting in a situation where it cannot be well adapted to the actual condition of the patient, leading to insufficient matching degree of the treatment plan and insufficient accuracy of treatment. Summary of the Invention

[0007] In view of the above problems, in order to formulate a more accurate planning plan for patients and determine intervention tasks, the present invention provides an intervention task planning system, device and method, which obtains a digital therapy planning plan suitable for patients based on the left and right brain theory, and treats patients more pertinently, thereby improving the treatment effect.

[0008] In a first aspect, the present invention provides an intervention task planning system, which includes a processor and a memory. A computer executable program is stored on the memory, and the processor executes the computer executable program to implement:

[0009] Match the patient index data with multiple group treatment templates pre-configured with intervention metadata, and use the matched group treatment template as the first planning data;

[0010] Generate second planning data based on AIGC according to the patient index data and intervention metadata;

[0011] Obtain the evaluation results of the first planning data and the second planning data to determine the intervention planning data;

[0012] Determine the intervention task based on the intervention metadata in the intervention planning data.

[0013] Further, before performing the matching of the patient index data with multiple group treatment templates pre-configured with intervention metadata and using the matched group treatment template as the first planning data, pre-configure the group treatment template, including basic information configuration and inclusion condition configuration;

[0014] The matching of the patient index data with multiple group treatment templates pre-configured with intervention metadata includes matching the patient index data with the inclusion conditions. When the patient index data meets the inclusion conditions, it means that the matching is successful, and the matched group treatment template is used as the first planning data.

[0015] Further, the matching of the patient index data with multiple group treatment templates pre-configured with intervention metadata and using the matched group treatment template as the first planning data includes:

[0016] When multiple group treatment templates are matched, sort the multiple group treatment templates according to the matching degree, and determine the first planning data according to the sorting result.

[0017] Further, generating the second planning data based on AIGC according to the patient index data and intervention metadata includes obtaining the patient index data, treatment goals, intervention metadata, and the mutual relationship between the intervention metadata, and AIGC generates the second planning data according to the obtained patient index data, treatment goals, intervention metadata, and the mutual relationship between the intervention metadata.

[0018] Further, obtaining the evaluation results of the first planning data and the second planning data to determine the intervention planning data includes:

[0019] Evaluate the intervention metadata in the first planning data and the second planning data respectively, and determine the intervention planning data according to the evaluation results.

[0020] Further, obtaining the evaluation results of the first planning data and the second planning data to determine the intervention planning data includes:

[0021] Assign scores to all the intervention metadata in the digital therapy respectively, and configure the interaction rules between different intervention metadata to obtain the scores of all combinations of intervention metadata;

[0022] Compare the scores of the combinations of intervention metadata in the first planning data and the second planning data, and determine the intervention planning data according to the scores.

[0023] Further, when using the patient index data to match with multiple pre-configured group treatment templates containing intervention metadata and the matching of the group treatment template fails, combine all the intervention metadata in the multiple group treatment templates to obtain the general planning data;

[0024] Evaluate the second planning data and the general planning data, and determine the intervention planning data according to the returned evaluation results.

[0025] In a second aspect, the present invention provides an intervention task planning device, and the device includes:

[0026] A first planning data acquisition module, configured to use the patient index data to match with multiple pre-configured group treatment templates containing intervention metadata, and use the matched group treatment template as the first planning data;

[0027] A second planning data acquisition module, configured to generate the second planning data based on AIGC according to the patient index data and the intervention metadata;

[0028] An intervention task determination module, configured to evaluate the first planning data and the second planning data, and determine an intervention task according to the evaluation result.

[0029] Further, the apparatus further includes a general planning data acquisition module, configured to combine the intervention metadata in all group treatment templates to obtain the general planning data of the digital therapy when the group treatment template cannot be matched according to the first planning data acquisition module;

[0030] The intervention task determination module evaluates the second planning data and the general planning data, and determines an intervention task according to the evaluation result.

[0031] In a third aspect, the present invention provides an intervention task planning and distribution method, the method including:

[0032] Matching the patient index data with multiple pre-configured group treatment templates including intervention metadata, and using the matched group treatment template as the first planning data;

[0033] Generating second planning data based on AIGC according to the patient index data and the intervention metadata;

[0034] Obtaining the evaluation result of the first planning data and the second planning data to determine the intervention planning data;

[0035] Determining an intervention task based on the intervention metadata in the intervention planning data;

[0036] Distributing the intervention task.

[0037] The intervention task planning system, apparatus and method provided by the present invention have at least the following beneficial effects:

[0038] 1. According to the patient's index data, on the one hand, it is matched with the pre-configured group treatment template to obtain the first planning data applicable to the patient's intervention from multiple group treatment templates, and on the other hand, the second planning data applicable to the patient's intervention is obtained by using the AIGC model generation method. The first planning data is an "expert-type" plan generated by simulating the left brain of a person, and the second planning data is a "wise-type" plan generated by simulating the right brain of a person. The most suitable intervention planning data for the patient is determined from the planning plans generated by simulating the left and right brains, and the intervention task for the patient is planned based on the intervention planning data, so that the formulated intervention task can better adapt to the patient's condition and the treatment effect is guaranteed;

[0039] 2. By assigning scores to different intervention metadata and obtaining the scores of different intervention metadata combinations according to the calculation interaction rules, it is possible to more intuitively and accurately determine the advantages and disadvantages of different planning plans, so as to reasonably determine the planning plan corresponding to the patient's condition for the intervention task planning. Brief Description of the Drawings

[0040] Figure 1 It is a schematic diagram of the implementation process of the intervention task planning system according to the first embodiment of the present invention.

[0041] Figure 2 It is a schematic diagram of the configuration of an example group therapy template of the intervention task planning system according to the first embodiment of the present invention.

[0042] Figure 3 It is a schematic diagram of the configuration of an example intervention means of the intervention task planning system according to the first embodiment of the present invention.

[0043] Figure 4 It is a schematic diagram of the structural relationship between an example group therapy template and an intervention means of the intervention task planning system according to the first embodiment of the present invention.

[0044] Figure 5 It is a schematic diagram of the storage structure of the treatment plan of the intervention task planning system according to the first embodiment of the present invention.

[0045] Figure 6 It is a schematic diagram of the score configuration of the intervention means of the intervention task planning system according to the first embodiment of the present invention.

[0046] Figure 7 It is a schematic diagram of the interaction rules of the intervention task planning system according to the first embodiment of the present invention.

[0047] Figure 8 It is a schematic diagram of the structure of the intervention task planning device according to the second embodiment of the present invention.

[0048] Description of the reference numerals: 10, the first planning data acquisition module; 20, the second planning data acquisition module; 30, the general planning data acquisition module; 40, the intervention task determination module. Detailed Embodiments

[0049] The following will describe the invention in detail with specific embodiments and attached Figure 1-8 drawings, so that those skilled in the art can more fully understand the purpose, features and effects of the present invention.

[0050] 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 the present invention conflicts with the meaning commonly understood by those skilled in the art, the definition described herein shall prevail.

[0051] The present invention improves the existing digital therapy by providing an intervention task planning system, device and method to improve the symptom targeting of intervention task formulation.

[0052] Embodiment 1

[0053] As a specific embodiment of the present invention, this embodiment provides an intervention task planning system, including:

[0054] One or more processors for processing computer programs, including computer programs stored in a memory or stored on a memory to display graphical information of a GUI on an external input / output device;

[0055] One or more memories for storing computer programs executed by the processor;

[0056] Component connection interfaces;

[0057] And a bus connecting each component,

[0058] The processor executes the computer program on the memory to implement the following steps.

[0059] Refer to Figure 1 , the specific steps are as follows:

[0060] S100. Obtain a pre-configured group treatment template and determine the first planning data according to patient indicators

[0061] Multiple group treatment templates for the patient's condition are pre-configured for digital therapy, and each group treatment template corresponds to a patient disease intervention treatment plan for digital therapy. Under one digital therapy, multiple group treatment templates may be included, and different group treatment templates can be used as intervention treatment plans for patients with different degrees of diseases.

[0062] Specifically, refer to Figure 2 , each group treatment template includes basic information configuration S101 and enrollment condition configuration S102.

[0063] S101. Configure the basic information of the group treatment template

[0064] As Figure 2 shown, the basic information includes template name, target name, intervention means, label, treatment days, presence or absence of an action model, task generation method, the task generation method includes quantization rules and intelligent recommendation and the task generation method is a single selection, and during the group treatment template configuration stage, the task generation method defaults to quantization rules and intelligent recommendation cannot be selected.

[0065] When configuring the group treatment template, the template name is determined by custom input or selection, the target name, intervention means, and label are determined by selection from a drop-down list, where the target is a single selection, the intervention means is a multiple selection, the label is a multiple selection, and the intervention means can only select the intervention means associated with the selected target.

[0066] AsFigure 2 As shown, in an example of a group treatment template for treating spinal C curvature, the template name is "C curvature treatment", the target name is "spine", the intervention means include "C curvature training - mild" and "C curvature training - increased dosage", the label is "mild", the treatment days are set to 100 days, the incorrect action model selection is "yes", and the task generation method is "quantification rule".

[0067] In a group treatment template, it includes at least one intervention means, and the at least one intervention means forms an intervention means combination, that is, a group treatment template includes an intervention means combination, and an intervention means combination includes at least one intervention means. The intervention means is the data source of the intervention task in the digital therapy treatment plan, indicating that the intervention task of treating the patient is performed by using the intervention means. In the above example, the intervention means gives two intervention means, namely "C curvature training - mild" and "C curvature training - increased dosage", and the two intervention means form an intervention means combination, indicating that when using this treatment template as the treatment plan of digital therapy, in the intervention task of intervening in the treatment of the spine, the intervention means combination is used to treat the spine.

[0068] In this embodiment, the types of intervention means include video intervention, audio intervention, food intervention, drug intervention, questionnaire intervention. Among them, as Figure 3 shown, the two intervention means, namely "C curvature training - mild" and "C curvature training - increased dosage" in the example, both belong to the video intervention type.

[0069] In this embodiment, referring to Figure 3 、 Figure 4 , the configuration information of the intervention means includes means id, means name, means classification, sub - classification, creation time, update time, where the creation time and update time are used to record the first generation time and the last modification time of the intervention means in the group treatment template. The intervention means are pre - configured and saved in the data structure in the group treatment template as Figure 4 shown. In this embodiment, the information of the intervention means can be described by intervention metadata, that is, the intervention metadata includes the description data of the intervention means.

[0070] Figure 4 In it, 1054 is the id of the digital therapy group treatment template, and 463 and 464 are the ids of the intervention means. The data structure indicates that in the digital therapy group treatment template with id 1054, two intervention means with means ids 463 and 464 are configured.

[0071] Preferably, in this embodiment, the data format of the label stored in the group treatment template is String type.

[0072] The number of treatment days indicates the number of days during which the intervention tasks are continuously executed when the described group treatment template is adopted as the treatment plan.

[0073] S102. Configure the inclusion criteria for the group treatment template

[0074] The inclusion criteria can match the conditions of the group treatment template, specifically referring to the matching conditions between the patient's indicator data and the group treatment template. When the patient's indicator data meets the inclusion criteria, it means that the group treatment template matches the patient's indicator data, and it is recommended to adopt the group treatment template as the digital therapy treatment plan for the patient, and execute the intervention tasks according to the group treatment template; when the patient's indicator data does not meet the inclusion criteria, it means that the group treatment template does not match the patient's indicator data, and it is not recommended to use the group treatment template as the digital therapy treatment plan for the patient.

[0075] Specifically, the indicators are used to describe the parts or substances related to the health status of the patient's disease manifestations. For example, for diabetes, the indicators of concern include blood sugar and blood lipids; for scoliosis, the indicators of concern include the type of scoliosis and the scoliosis angle (Cobb angle).

[0076] In this embodiment, the inclusion criteria include indicator options, comparison operators, and target values. Refer to Figure 2 , the indicator is the value of the scoliosis type, the comparison operator is "contains", and the target values are C and S, indicating that when the value of the patient's corresponding indicator scoliosis type contains C and S, it can match the group treatment template, and it is recommended to adopt the group treatment template as the digital therapy treatment plan for the patient with spinal C curve.

[0077] In the configuration of the inclusion criteria for the cobb angle indicator, the stored data format is as follows:

[0078] {"combinator":"and","conditions":[{"combinator":"and","conditions":[{"fieldName":"cobb angle.value","operator":"GT","field":"indicator.cobb.value","value":

[15] ,"type":"NUMBER"}]}]}

[0079] Among them, combinator represents the symbol connecting two conditions, and the optional values are and and or; conditions represents the list of conditions, which is an array and also contains combinator and conditions, meaning that the conditions can be infinitely nested; fieldName represents the name of the indicator; field represents the indicator code; indicator.cobb.value represents the value of the indicator code; value represents the target value; type represents the data type of the indicator; operator represents the comparison operator.

[0080] Preferably, the data types of the indicators include NUMBER, STRING, DATETIME, LIST, BOOL; the comparison operators include LT (less than), LE (less than or equal to), EQ (equal to), NE (not equal to), GE (greater than or equal to), GT (greater than), BETWEEN (between XX and YY).

[0081] The meaning of the inclusion criteria expressed by the above structure is: when the value of the cobb angle of the indicator is greater than 15, this population treatment template is matched.

[0082] The above structure is a JSON data structure. Using the above data structure, inclusion criteria for different indicators can be constructed.

[0083] Defining the data structure in JOSN format ensures the simplicity and readability of the code, facilitating quick reading and writing. And since JOSN is a format that is independent of programming languages and operating systems, data conversion can be achieved between different platforms and languages. Additionally, JSON supports nested structures and can be used to represent complex data relationships.

[0084] According to S101 and S102, configure multiple population treatment templates and save the population treatment templates in the database.

[0085] S103. Match the population treatment template according to the patient's indicator data

[0086] Furthermore, convert the inclusion criteria data in JSON format into a Groovy script that can run in the JVM environment. The above inclusion criteria data for the cobb angle of the indicator is converted to the following script data:

[0087]

[0088] In the above data, "import com.cwdata.dtx.engine.Conditions" means importing a class Conditions, which can be used in subsequent code. Conditions has the ability to handle comparators for different data types. The code "Conditions.numberCondition" represents the numberCondition method under the Conditions class, which is used to handle comparison operations for numeric types. The code configuration of this method is based on the data type "NUMBER" in the JSON data. If the data type in the JSON data is "STRING", the method in the Conditions class is the textCondition method. "GT" and "

[15] " are the comparator and the target value respectively.

[0089] The Map<String,Object> obj is a formal parameter of the func method. When the script runs, the patient's indicator data is passed into the script in the form of a Map. The numberCondition performs operations based on the target value, comparator, and the passed-in patient's indicator data and returns the result. The type of the returned result is BOOL. When the returned result is true, it means the patient's indicator data conforms to the group treatment template, and this group treatment template is used as the intervention treatment plan for the patient's disease. When the returned result is false, it means the patient's indicator data does not conform to this group treatment template, and then the matching of the next group treatment template is carried out.

[0090] After the traversal and matching process, the group treatment templates that match the patient's indicator data are obtained. The number of the matched group treatment templates can be multiple or none. When the number of matched group treatment templates is 0, it means no suitable group treatment template is obtained for intervening in the treatment of the patient.

[0091] In this embodiment, the enrollment condition data in JSON format is converted into a Groovy script that can run in the JVM environment. On the one hand, since Groovy is a scripting language based on the Java platform, it can conveniently call Java libraries. On the other hand, it is also because Groovy is easy to maintain and reuse, supporting object-oriented and procedural programming.

[0092] Before performing S103, the patient's indicator data is collected and stored in the database.

[0093] S104. Obtain the treatment preference and determine the first planning data based on the matching degree between the treatment preference and the matched group treatment template

[0094] By Figure 2It can be known that tags are configured in the basic information of each group treatment template. In this embodiment, each group treatment template can be configured with multiple tag groups, and each tag group is configured with multiple tags, that is, each group treatment template can include several tags. Only one tag can be selected from each tag group as the tag of the group treatment template.

[0095] Each group treatment template includes multiple tag groups, and only one tag can be selected from each tag group, enabling flexible combination between different tags and tag groups. For a specific group treatment template, one tag from the tag group where it is located can be selected in each tag group, or one tag from the tag group where it is located can be selected only in some tag groups, meeting complex treatment requirements.

[0096] Treatment preferences are obtained according to the tags to ensure the consistency between treatment preferences and tags. Since treatment preferences correspond to the tags of the group treatment template, correspondingly, multiple treatment preferences form a treatment preference group. When determining, one treatment preference from one treatment preference group can be selected, or one treatment preference from each treatment preference group can be selected from multiple treatment preference groups.

[0097] In this embodiment, when calculating the matching degree between the treatment preference and the tags of the matched group treatment template, the number of tags that are the same as the tags in the matched group treatment among the obtained treatment preferences is a, and the number of tags configured in all group treatment templates is b. The matching degree k is calculated by the following method:

[0098]

[0099] Since different treatment preferences are selected, there may be multiple matched tags. The more the number of matched tags, the higher the matching degree score, indicating that the group treatment template is more suitable for the patient.

[0100] The group treatment templates matched according to the patient's index data are sorted according to the matching degree, and the group treatment template with the maximum matching degree value is used as the first planning data for the patient's disease.

[0101] If multiple successfully matched group treatment templates are obtained, the first planning data can be determined according to the results of the matching degree, and finally a unique recommended "expert-type" treatment plan can be obtained.

[0102] S103 and S104 can be carried out simultaneously. After the doctor selects the treatment preference according to the patient's index data, during the process of generating the treatment plan, the matching of the patient's index data with the group treatment template is synchronously carried out, and the matching degree between the treatment preference and the tags of the matched group treatment template is calculated to obtain several group treatment templates with different matching degree values. The group treatment template with the maximum matching degree value is used as the first planning data for the patient's disease.

[0103] In another embodiment, the calculation of the matching degree may not be performed, and all the group treatment templates that are matched are used as the first planning data.

[0104] S100 mainly simulates the left brain of a human, and obtains a treatment plan containing the patient's disease intervention tasks through the "expert brain".

[0105] S200. Generate second planning data based on AIGC according to patient indicators and intervention means

[0106] Obtain basic data on patient indicator data and the doctor's judgment of the patient's condition, such as treatment preferences, treatment goals, intervention means, and the interaction relationship between intervention means. According to the indicator data and the basic data, generate second planning data suitable for the patient's intervention treatment based on the AIGC model. The intervention means may be all the intervention means in the pre-configured group treatment templates under this digital therapy, as well as the intervention means that are under this digital therapy but not configured in the group treatment templates. In S100, a digital therapy may include multiple group treatment templates. The intervention means pre-configured in the group treatment templates all come from the digital therapy to which they belong, that is, the number of intervention means in the digital therapy to which they belong is greater than or equal to the number of intervention means in the group treatment templates. It is possible that some of the intervention means in the digital therapy to which they belong are not configured into the group treatment templates. Therefore, the intervention means obtained in S200 include all the intervention means under the digital therapy to which they belong.

[0107] The AIGC model may be Chat-GPT, Wenxin Yiyan, and in this embodiment, Chat-GPT is used for illustration.

[0108] In an example, the Prompt parameters given to Chat-GPT are:

[0109] String promptTemp = "You are an experienced clinician in ${therapyArea}. You are required to calculate the best list of means based on the patient's current indicator status and treatment goals. Format your answer as a compactly written JSON object. Example: [{\"reason\":\"The patient has high blood sugar. Empagliflozin tablets can effectively lower blood sugar. At the same time, aerobic exercise can help control BMI, and daily walks can increase daily physical activity. Disease video introductions can help improve the patient's understanding of the disease, and medication popular science introductions can help improve the patient's understanding of the medication. At the same time, this combination can avoid conflicts between means, so it is one of the best means combinations.\",\"meansList\":[{\"name\":\"Metformin\",\"purpose\":\"Adjust blood sugar\",\"score\":\"85\"},{\"name\":\"Aerobic exercise\",\"purpose\":\"Adjust

[0110] BMI\",\"score\":\"70\"}]}]\n" +

[0111] "\n" +

[0112] "Requirements:\n" +

[0113] "1. Try to meet all the patient's indicator treatment goals as much as possible\n" +

[0114] "2. Prioritize means with the highest score under the treatment purpose\n" +

[0115] "3. The higher the overall score, the better\n" +

[0116] "4. Some means cannot be used simultaneously. Refer to the means conflict list\n" +

[0117] "5. Some means have a synergistic effect when used simultaneously\n" +

[0118] "6. Some means have an antagonistic effect when used simultaneously\n" +

[0119] "\n" +

[0120] "The patient's current indicator status is:\n" +

[0121] "${patientKeyIndicatorValueList}\n" +

[0122] "\n" +

[0123] "The patient's treatment goal is: ${interventionPurpose}\n" +

[0124] "\n" +

[0125] "${targetPointMeansList}\n" +

[0126] "\n" +

[0127] "List of means conflicts:\n" +

[0128] "${conflictMeansList}\n" +

[0129] "\n" +

[0130] "Calculating the list of the best ${candidatePlanCount} means, the result is: ";

[0131] Among them, patientKeyIndicatorValueList represents the indicator status of the patient, interventionPurpose represents the treatment goal, conflictMeansList represents the list of intervention means conflicts, candidatePlanCount represents the number of results to be returned, and therapyArea represents the treatment area of the digital therapy. The treatment area can be diabetes, hypertension, glioblastoma, coronary heart disease, obesity, respiratory diseases, neurological diseases, orthopedic diseases. In this embodiment, one treatment area corresponds to at least one digital therapy, and different digital therapies may act on the same treatment area.

[0132] meansList is the list of intervention means obtained by Chat-GPT, and name exactly matches the name of the intervention means configured in the digital therapy.

[0133] Through the above method, a unified template processed by Chat-GPT is obtained.

[0134] Before execution, it is necessary to replace the variables in ${} with the associated data of the current patient. For example, it is necessary to replace ${therapyArea} with the value of the field of the treatment area of the digital therapy queried by the DtxId of the group treatment template of the digital therapy, and replace ${patientKeyIndicatorValueList} with the real indicator data of the patient. The replacement of data uses the String.replace method.

[0135] During execution, Chat-GPT processes according to the indicator data of the patient and the treatment area of the digital therapy and returns the result. The returned result is encapsulated in the following format:

[0136] [{

[0137] "name": xxx, / / Name of the means

[0138] "purpose": xxx, / / Function of the means

[0139] "score": xxx / / Score of the means

[0140] }]

[0141] Among them, the score of the means is the score pre-configured for the corresponding intervention means. Further, the score of the means is the score pre-configured for the intervention means under different targets.

[0142] After that, the above-formatted data is saved in the database to obtain the second planning data for the intervention treatment of the patient. S200 is used to simulate the right brain of a person, and through the "intelligent brain", a treatment plan containing the disease intervention tasks of the patient is obtained.

[0143] S300. Obtain general planning data

[0144] In S100, when matching the group treatment template according to the patient index data, if no group treatment template is matched, all the intervention means under this digital therapy are combined into an intervention treatment plan as the general planning data and recommended to the patient for intervention treatment.

[0145] S300 is also used to simulate the left brain of a person, and through the "expert brain", a treatment plan containing the disease intervention tasks of the patient is obtained.

[0146] The storage structure of different treatment plans in the database is as Figure 5 shown.

[0147] Among them, the type field represents the source of the treatment plan. For example, 1 means the treatment plan is generated by AIGC, 2 means it comes from the matched group treatment template, and 0 means it comes from the general planning data. The treatment plan includes specific targets and intervention means.

[0148] S400. Determine the intervention task

[0149] If a group treatment template can be matched according to the patient index data in S100, the intervention planning data is determined after comparing the first planning data and the second planning data of S100 and S200; if a group treatment template cannot be matched according to the patient index data in S200, the intervention planning data is determined by comparing the second planning data of S200 and the general planning data of S300.

[0150] When determining the intervention task, it is judged based on the scores of the intervention means in different plans. The plan with the highest score is used as the final intervention planning data, and the intervention task is planned with the intervention means in the intervention planning data.

[0151] Specifically, if the score of the intervention means in the first planning data is high, the intervention task is determined according to the intervention means in the first planning data; if the score of the intervention means in the second planning data is high, the intervention task is determined according to the intervention means in the second planning data; if the score of the intervention means in the general planning data is high, the intervention task is determined according to the intervention means in the general planning data.

[0152] When configuring the intervention means for the target point in S100, the score of the intervention means under the target point is configured at the same time, such as Figure 6 shown, indicating that the scores of the two intervention means "C-curve training - mild" and "C-curve training - increased dosage" for the spinal target point are 80 points and 90 points respectively. The specific storage format is as follows:

[0153] [{"dtxId":xxx,"targetPoint":xx,"meanList":[{"name":"C-curve training - increased dosage","score":80,"type":"video"}]}]

[0154] Since a group treatment template can configure multiple intervention means at the same time, and there are interactions between different intervention means, the interaction rules between the pre-configured intervention means are as follows Figure 7 shown.

[0155] Specifically, the interaction of the intervention means represents the mutual influence between the intervention means, including antagonism, synergy, repetition, and prohibition. In the interaction rules, antagonism means that when two intervention means appear at the same time, the score of the intervention means will be reduced by 10%; synergy means that when two intervention means appear at the same time, the score of the intervention means will be increased by 10%; repetition means that two intervention means are used overlapped: the score of the intervention means is 0; prohibition means that the digital therapy does not recommend using this intervention means, and the score of the intervention means is 0.

[0156] The calculation steps of the intervention means score of the treatment plan are as follows:

[0157] Query all target points configured by the digital therapy;

[0158] Form a data structure by combining the target point and the score of the intervention means under the target point;

[0159] Take the Cartesian product of the data structure to obtain all combinations of the scores of the intervention means under different target points;

[0160] Traverse each combination and obtain the score of the intervention means of each combination according to the interaction rules.

[0161] Compare the scores of the combinations of intervention means obtained under different planning data, and determine the final intervention task according to the planning data where the combination of intervention means with the highest score is located.

[0162] Since the intervention means scoring is the score assignment under the target point, the scores of all combinations of intervention means obtained are also the scores for this target point. When making score judgments, all intervention combinations are for the same target point.

[0163] By comparing the treatment plan obtained by configuring the group treatment template and simulating the human left brain with the planning data generated by the AIGC model simulating the human right brain, the most suitable plan for the patient is obtained from the planning data obtained through different paths, and then the intervention task is planned for the patient.

[0164] The intervention task planning system of the present invention can formulate a more reasonable digital therapy treatment plan based on the left and right brain theory, plan a more targeted intervention task for the patient for implementing the intervention treatment, thereby improving the treatment effect of the patient.

[0165] Example Two

[0166] As a specific embodiment of the present invention, this embodiment provides an intervention task planning and distribution method, including:

[0167] Match the patient index data with multiple pre-configured group treatment templates containing intervention metadata, and use the matched group treatment template as the first planning data;

[0168] Generate second planning data based on AIGC according to the patient index data and intervention metadata;

[0169] Obtain the evaluation results of the first planning data and the second planning data to determine the intervention planning data;

[0170] Determine the intervention task based on the intervention metadata in the intervention planning data;

[0171] Distribute the intervention task.

[0172] The intervention task planning and distribution method of the present invention is used to implement the steps of the intervention task planning in Example One and distribute the intervention task after completing the intervention task planning, providing a more reasonable intervention plan for the patient to adapt to the actual physical state of the patient, so as to be used for guiding the patient's intervention treatment.

[0173] Example Three

[0174] As a specific embodiment of the present invention, this embodiment provides an intervention task planning device, referring to Figure 8 , the intervention task planning device includes:

[0175] The first planning data acquisition module is used to match the patient index data with multiple group treatment templates including intervention means pre-configured, and use the matched group treatment template as the first planning data for digital therapy intervention treatment;

[0176] The second planning data acquisition module is used to generate the second planning data for digital therapy intervention treatment based on AIGC according to the patient index data and intervention means;

[0177] The general planning data acquisition module is used to combine the intervention means in all group treatment templates to obtain the general planning data for digital therapy intervention treatment when no group treatment template can be matched by the first planning data acquisition module;

[0178] The intervention task determination module is used to evaluate the first planning data and the second planning data or the second planning data and the third planning data, and determine the intervention task according to the evaluation result.

[0179] In this embodiment, the first planning data acquisition module can simulate the left brain of a person to obtain the "expert type" first planning data, and the second planning data acquisition module can simulate the right brain of a person to obtain the "intelligent type" second planning data. When the first planning data cannot be obtained through the first planning data acquisition module, the general planning data acquisition module works to obtain the general planning data of the "expert type" that simulates the left brain of a person. Finally, the intervention task determination module evaluates the treatment plans obtained by simulating the left and right brains to obtain intervention planning data more suitable for the patient's condition, and plans the intervention task according to the intervention planning data.

[0180] The above is only a preferred embodiment of the present invention, and it is not any other form of limitation to the present invention. Any modification or equivalent change made according to the technical essence of the present invention still belongs to the scope of protection required by the present invention.

Claims

1. An intervention task planning system, characterized in that, The system includes a processor and a memory, and a computer-executable program is stored on the memory. The processor executes the computer-executable program to implement: Matching the patient indicator data with multiple group treatment templates pre-configured with intervention metadata, and taking the matched group treatment template as the first planning data; Generating second planning data based on AIGC according to the patient indicator data and the intervention metadata; Obtaining evaluation results of the first planning data and the second planning data to determine the intervention planning data; Planning intervention tasks based on the intervention metadata in the intervention planning data.

2. The intervention task planning system according to claim 1, wherein Before performing the matching of the patient indicator data with multiple group treatment templates pre-configured with intervention metadata and taking the matched group treatment template as the first planning data, the group treatment templates are pre-configured, including basic information configuration and enrollment condition configuration; The matching of the patient indicator data with multiple group treatment templates pre-configured with intervention metadata includes matching the patient indicator data with the enrollment conditions. When the patient indicator data meets the enrollment conditions, it indicates a successful match, and the matched group treatment template is taken as the first planning data.

3. The intervention task planning system according to claim 1 or 2, characterized in that, The matching of the patient indicator data with multiple group treatment templates pre-configured with intervention metadata and taking the matched group treatment template as the first planning data includes: When multiple group treatment templates are matched, the multiple group treatment templates are sorted according to the matching degree, and the first planning data is determined according to the sorting result.

4. The intervention task planning system according to claim 1, characterized in that, The generating of the second planning data based on AIGC according to the patient indicator data and the intervention metadata includes obtaining the patient indicator data, treatment goals, intervention metadata, and the mutual relationship between the intervention metadata. AIGC generates the second planning data according to the obtained patient indicator data, treatment goals, intervention metadata, and the mutual relationship between the intervention metadata.

5. The intervention task planning system according to claim 1, wherein Obtaining evaluation results of the first planning data and the second planning data to determine the intervention planning data includes: Evaluating the intervention metadata in the first planning data and the second planning data respectively, and determining the intervention planning data according to the evaluation results.

6. The intervention task planning system according to claim 5, wherein Obtaining evaluation results of the first planning data and the second planning data to determine the intervention planning data includes: Assigning scores to all the intervention metadata in the digital therapy respectively, and configuring the interaction rules between different intervention metadata to obtain the scores of all combinations of intervention metadata; Comparing the scores of the combinations of intervention metadata in the first planning data and the second planning data, and determining the intervention planning data according to the scores.

7. The intervention task planning system according to claim 1 or 2, characterized in that, When the matching of the patient indicator data with multiple group treatment templates pre-configured with intervention metadata fails, all combinations of the intervention metadata in the multiple group treatment templates are obtained to obtain the general planning data; Evaluating the second planning data and the general planning data, and determining the intervention planning data according to the returned evaluation results.

8. An intervention task planning device, characterized in that, The device includes: The first planning data acquisition module is used to match the patient index data with multiple group treatment templates containing intervention metadata that are pre-configured, and use the matched group treatment template as the first planning data; The second planning data acquisition module is used to generate second planning data based on AIGC according to the patient index data and the intervention metadata; The intervention task determination module is used to evaluate the first planning data and the second planning data, and determine the intervention task according to the evaluation result.

9. An intervention task planning and distribution method, the method comprising: Matching the patient index data with multiple group treatment templates containing intervention metadata that are pre-configured, and using the matched group treatment template as the first planning data; Generating second planning data based on AIGC according to the patient index data and the intervention metadata; Obtaining the evaluation results of the first planning data and the second planning data to determine the intervention planning data; Determining the intervention task based on the intervention metadata in the intervention planning data; Distributing the intervention task.

Images