WO2023207793A1

WO2023207793A1 - Human-computer interaction method for health decision making, device, and system

Info

Publication number: WO2023207793A1
Application number: PCT/CN2023/089807
Authority: WO
Inventors: 吴运良
Original assignee: 吴运良
Priority date: 2022-04-26
Filing date: 2023-04-21
Publication date: 2023-11-02
Also published as: CN114743669A

Abstract

The present invention relates to a human-computer interaction method for health decision making, comprising the following steps: a computer obtains user basic data in real time, generates preliminary diagnosis data according to the user basic data, and uploads the preliminary diagnosis data to a server; a doctor logs on to a human-computer interface, obtains at least one group of user basic data and preliminary diagnosis data from the server by means of the human-computer interface for processing, generates corresponding user whole person health data, and returns the corresponding user whole person health data to the computer; the computer generates a preliminary intervention scheme according to the user whole person health data, determines whether the user whole person health data is unbalanced, and uploads the preliminary intervention scheme to the server when the user whole person health data is unbalanced; the doctor obtains a preliminary intervention scheme corresponding to a user by means of the human-computer interface for confirmation, generates a final intervention scheme after confirmation, and returns the final intervention scheme to the computer; the computer matches an intervention measure according to the final intervention scheme and submits same to the user; the user evaluates the implemented final intervention scheme and the effect of the intervention measure and generates an evaluation result.

Description

Human-computer interaction methods, devices and systems for health decision-making

Technical field

The invention relates to a human-computer interaction method, equipment, storage medium and system for health decision-making, and belongs to the technical field of human-computer interaction in medical and health systems.

Background technique

The application of data information technology in the health field has always received much attention, and it has become a consensus to use informatization to drive innovation and development in this field. Responding to challenges such as chronic non-communicable diseases, more and more attention is paid to population health, and active health intervention technology has become a cutting-edge direction in the medical and health field in the context of information technology. On the one hand, through the combination of Internet + and the big health industry, the health industry based on computers, communications, cloud computing, big data and other technologies is showing a rapid development trend, driving health services to develop in the direction of digitalization, networking, and intelligence. Among them, how digital information technology represented by artificial intelligence can be deeply applied in the field of medicine and health and how to empower health and medical big data are technical issues that need to be solved urgently. On the other hand, with the development of society, the task of medicine is not only to prevent and treat diseases, but more importantly, to improve people's quality of life. However, doctors are a scarce resource in society. Computer artificial intelligence systems must be used to improve doctor efficiency and user initiative. to address current health challenges. Third, in the digital age, how individual users participate in healthcare decisions and how to become more intelligent are also issues to be solved in the medical and health field. Medical services are complex and uncertain. Digital information technologies such as the Internet and artificial intelligence cannot unconditionally replace doctors' face-to-face data collection and diagnostic decision-making, and cannot comprehensively solve the problem. Therefore, doctors' manual processing cannot be replaced, and human-machine collaboration has become inevitable. In the next period, human-machine collaborative work will be the development trend of the future society. The development of human-machine collaborative intelligent systems for medical care will enable the close and deep integration of human-computer interaction and artificial intelligence.

Technical solutions

In order to solve the problems existing in the above-mentioned prior art, the present invention proposes a human-computer interaction method for health decision-making, which is user-centered, predicts preliminary diagnosis data based on the user's basic data, and combines the preliminary diagnosis with the doctor's The data improves the user's whole-person health data. The computer and the doctor collaboratively process the user's whole-person health data, generate an intervention plan and match the intervention measures to the user. The user selects the intervention measures and feeds back the treatment evaluation to the computer, forming a closed loop. system.

The technical solution of the present invention is as follows:

On the one hand, the present invention provides a human-computer interaction method for health decision-making, which is characterized by including the following steps:

The computer obtains the user's basic data in real time, and generates preliminary diagnostic data based on the user's basic data and sends it to the server;

The doctor logs in to the human-machine interface, obtains at least one set of user basic data and preliminary diagnosis data from the server through the human-machine interface, processes it, generates corresponding user whole-person health data and returns it to the computer;

The computer generates a preliminary intervention plan based on the user's whole-person health data, and determines whether the user's whole-person health data is imbalanced. When the user's whole-person health data is imbalanced, the preliminary intervention plan is sent to the server;

The doctor logs in to the human-machine interface, obtains the preliminary intervention plan corresponding to the user from the server through the human-machine interface, and confirms it, and after confirmation, generates the final intervention plan and returns it to the computer;

The computer matches the intervention measures based on the final intervention plan and submits it to the user;

The final intervention plan implemented by the user and the effect of the intervention measures are evaluated, and the evaluation results are generated and submitted to the computer. The computer incorporates the evaluation results into the user's basic data.

As a preferred embodiment, in the step of the doctor logging into the human-machine interface and obtaining at least a set of user basic data and preliminary diagnosis data from the server through the human-machine interface for processing, the processing process is specifically: according to the user basic data Correct, amend and improve preliminary diagnostic data.

As a preferred implementation, the steps for the computer to generate a preliminary intervention plan based on the user's overall health data are specifically:

Training multidisciplinary diagnostic models based on neural networks;

Predict the user's health problems through a multidisciplinary diagnostic model based on the user's whole-person health data;

Establish an intervention plan database, write corresponding intervention plans for different health problems and put them into the intervention plan database. The intervention plan contains a number of sequential nodes, and each node has an optional intervention sub-program written corresponding to it, and each node is programmed with an optional intervention sub-program. Intervention sub-programs add program characteristics and interventions available for that intervention sub-program;

The intervention plan is matched from the intervention plan database based on the user's health problem, and each node of the intervention plan is matched according to the user's basic data and plan characteristics, and the intervention sub-plan with a high matching degree is selected to generate the preliminary intervention plan.

As a preferred embodiment, when the doctor logs into the human-machine interface, the preliminary intervention plan corresponding to the user is obtained from the server through the human-machine interface for confirmation, and after confirmation, the final intervention plan is generated and returned to the computer, which specifically includes:

If the doctor confirms the adoption of the preliminary intervention plan, the preliminary intervention plan will be returned to the computer as the final intervention plan;

If the doctor needs to re-judge, the computer will return to re-acquire the user's basic data and generate preliminary diagnostic data, submit it to the doctor for reprocessing, update the user's overall health data and submit it to the doctor;

The doctor confirms or modifies the intervention sub-plan at any node in the preliminary intervention plan based on the user's whole-person health data, and generates the final intervention plan and returns it to the computer after all nodes are confirmed or modified.

As a preferred implementation, the computer matches the intervention measures according to the final intervention plan and submits them to the user. The steps are specifically:

Establishing an intervention measure information database, the intervention measure information database includes multiple sub-intervention measure databases, each sub-intervention measure database corresponding to different types of intervention measures respectively;

Collect the intervention measures, classify and label the intervention measures, where the labeling is specifically to add the characteristic information of the corresponding intervention measures; put the labeled intervention measures into the corresponding type of sub-intervention measure database according to the classification;

According to the final intervention plan, the types of intervention measures available in the intervention sub-program of each node are obtained, and the intervention measures are automatically matched from the sub-intervention measure database of the corresponding type;

Submit the matched intervention measures and corresponding feature information to the user.

As a preferred embodiment, the evaluation results include the user's effectiveness evaluation and suitability evaluation of the intervention plan and the effectiveness evaluation and suitability evaluation of the intervention measures;

The computer adds rating labels to the corresponding intervention programs and intervention measures based on the user's evaluation results of the effects of the intervention programs and intervention measures, and incorporates the intervention programs and corresponding rating labels, as well as the intervention measures and corresponding rating labels into the user's basic data;

The intervention plan and corresponding scoring labels, as well as the intervention measures and corresponding scoring labels, are used to provide a basis for judgment in the subsequent process of computer-generated preliminary intervention plans and matching intervention measures.

In a second aspect, the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, any embodiment of the present invention is implemented. The human-computer interaction method for health decision-making.

In a third aspect, the present invention provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the human-computer interaction method for health decision-making as described in any embodiment of the present invention is implemented.

In a fourth aspect, the present invention provides a human-computer interaction system for health decision-making, including a computer and a server communicatively connected to the computer, and also includes:

The basic data acquisition module is used to obtain the user's basic data in real time in the computer, and generate preliminary diagnostic data based on the user's basic data and send it to the server;

The preliminary diagnosis module is used for doctors to log in to the human-machine interface, obtain at least one set of user basic data and preliminary diagnosis data from the server through the human-machine interface, process it, generate corresponding user whole-person health data and return it to the computer;

The preliminary plan generation module is used to generate a preliminary intervention plan based on the user's whole-person health data in the computer, and determine whether the user's whole-person health data is imbalanced. When the user's whole-person health data is imbalanced, the preliminary intervention plan is sent to the server;

The plan confirmation module is used for doctors to log in to the human-machine interface, obtain the preliminary intervention plan corresponding to the user from the server through the human-machine interface for confirmation, and generate the final intervention plan after confirmation and return it to the computer;

The measure matching module is used to match intervention measures according to the final intervention plan in the computer and submit it to the user;

The evaluation module is used to evaluate the final intervention plan implemented by the user and the effect of the intervention measures, generate evaluation results and submit them to the computer, and the computer will incorporate the evaluation results into the user's basic data.

In the fifth aspect, the present invention provides a life-cycle health management service system, including a collaborative management module and a human-computer interaction system for health decision-making according to any embodiment of the present invention;

The collaborative management module obtains data from the human-computer interaction system for health decision-making and provides services to users based on the obtained data.

beneficial effects

The invention has the following beneficial effects:

The invention is a human-computer interaction method for health decision-making, which is user-centered, predicts preliminary diagnosis data based on the user's basic data, and completes the user's whole-person health data through the doctor's combination with the preliminary diagnosis data. Through the computer and the doctor The user's whole-person health data is collaboratively processed, an intervention plan is generated and the matching intervention measures are provided to the user. The user selects the intervention measures and feeds back the treatment evaluation to the computer, forming a closed-loop system.

The present invention is a human-computer interaction method for health decision-making. It uses a multi-disciplinary diagnostic model based on machine learning to replace humans to a certain extent and closely integrate humans and machines. It can carry out early diagnosis and preventive treatment, and achieve precise prevention and precise treatment of diseases. .

The present invention is a human-computer interaction method for health decision-making. It processes and outputs new basic data in real time. It continuously iterates so that people and intervention implementation gradually form a balance and remain in a dynamic matching and intervention state. Based on data and doctor collaboration, it provides Full-process health management outside of emergency care gives users the decision-making power for medical health intervention; it makes medical system intervention a time-point or staged special form of intervention, and users know the intervention plan and the necessity, value and effectiveness of the intervention measures in advance. and prognostic effects.

Description of drawings

Figure 1 is a flow chart of a human-computer interaction method for health decision-making in an embodiment of the present invention;

Figure 2 is an example diagram of a human-computer interaction system for health decision-making in an embodiment of the present invention;

Figure 3 is an example diagram of a life cycle health management service system in an embodiment of the present invention.

Embodiments of the invention

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts fall within the scope of protection of the present invention.

It should be understood that the step numbers used in the text are only for convenience of description and are not intended to limit the execution order of the steps.

It should be understood that the terminology used in the description of the present invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a", "an" and "the" are intended to include the plural forms unless the context clearly dictates otherwise.

The terms "comprises" and "comprising" indicate the presence of described features, integers, steps, operations, elements and/or components but do not exclude the presence of one or more other features, integers, steps, operations, elements, components and/or The existence or addition to its collection.

The term "and/or" refers to any and all possible combinations of one or more of the associated listed items and includes such combinations.

Embodiment 1: Referring to Figure 1, a human-computer interaction method for health decision-making includes the following steps:

S1: Acquisition and processing of user health data, details are as follows:

S101: The computer obtains the user's basic data in real time, and generates preliminary diagnosis data based on the user's basic data and sends it to the server. The preliminary diagnosis data generated in this step is used to assist the doctor in diagnosis. Data acquisition can be multi-dimensional, such as collecting panoramic data from users’ daily life information, environmental information, wearable devices, physical examinations, diagnosis and treatment, etc.;

S102: The doctor logs in to the human-machine interface, optionally obtains at least a set of user basic data and preliminary diagnosis data from the server through the human-machine interface for processing, and corrects and confirms the preliminary diagnosis data based on the user basic data.

S103: Cyclically receive later daily health care data, health imbalance data and post-intervention user evaluation results, and loop steps S101 and S102 to dynamically output the corresponding user whole-person health data and return it to the computer.

S2: Generate intervention plan, details are as follows:

S201: The computer generates a preliminary intervention plan based on the user's whole-person health data, and determines whether the user's whole-person health data is imbalanced. When the user's whole-person health data is imbalanced, the preliminary intervention plan is sent to the server. The method for determining whether the user's whole-person health data is imbalanced includes receiving corresponding values of the user's perceived symptoms, wearable device data, doctor observation data and monitoring data that deviate to a threshold, and abnormal data that will be generated by computer correlation inference predictions;

S202: The doctor logs in to the human-machine interface and obtains the preliminary intervention plan corresponding to the user from the server through the human-machine interface for confirmation. The doctor's confirmation process proceeds to step S203. If the doctor needs to re-collect user data for judgment, then return to step S102.

S203: Generate the final intervention plan and return it to the computer.

S3: The computer matches the intervention measures according to the final intervention plan and submits it to the user.

S4: The user evaluates the final intervention plan and intervention measures implemented, generates evaluation results and submits them to the computer, and the computer incorporates the evaluation results into the user's basic data.

Through the above steps S1 to S4, multiple rounds of cyclic interactions are performed until the overall data of the user's health status or imbalance status is formed, as well as the corresponding preferred intervention measures. The preferred intervention measures are output for use in the user's daily health care, medical and health institutions, and elderly care institutions. and other real-time health interventions.

Among them, the user's whole-person health data refers to the data expression of the whole-person health elements using the person as a whole system, including the carbon-based space (genes, molecules, body temperature, age, shape, etc.) of the user's human body based on the cell tissue system, the person (at least Including users, doctors) thinking humanistic social environment cognition (psychology, perception, diagnosis, decision-making, etc.), natural and man-made engineering equipment intervention factors (implementation of gradual intervention including monitoring), establish a full-time dynamic health digital portrait or further form a digital Twins constitute the basic model of the digital life system. Through iteration, the best balance of the three is achieved with the goal of increasing the self-organizing power of the human body. The user's proactive perception is included in the decision-making elements; the individual is regarded as a whole, and through big data integration The results are analyzed to make a systematic diagnosis, and then the doctor combines his or her own clinical experience to further analyze the patient's psychological, social, environmental, subjective wishes and other influencing factors to make intervention recommendations and formulate optional intervention plans. Therefore, the user-centered approach integrates medical teams to provide non-disease-based general medical services, which solves the blindness of individual selection of service institutions and the limitations of individual institutions or single-disciplinary department services, embodies the overall concept of the system, and avoids " If you have a headache, treat the head; if you have a foot pain, treat the feet.” It demonstrates the individualized pursuit of combining traditional Chinese and Western medicine and giving full play to their respective advantages, dialectical treatment, individualized treatment, and treatment of co-morbidities, forming a mechanism and model for collaboration and interaction among clinical teams of Chinese and Western medicine.

Users, decision-making systems (people, computers), and natural systems (monitoring and intervention equipment, etc.) are connected to each other through regional servers (health information systems) to establish continuous and deterministic relationships, so that individual (group) health, intervention measures, and policies form a closed relationship. Multi-party integration and joint decision-making maximize individual-based group benefits.

As a preferred implementation of this embodiment, in step S201, the computer generates a preliminary intervention plan based on the user's whole person health data. The specific steps are:

Training multidisciplinary diagnostic models based on neural networks;

This embodiment uses a multidisciplinary diagnostic model based on machine learning (including modern medicine, traditional and complementary medicine (including traditional Chinese medicine), and knowledge systems related to promoting physical and mental health) to replace humans to a certain extent and closely integrate humans and machines, where humans at least include Users, medical and health workers. Use multidisciplinary diagnostic models to obtain regional population data from regional servers, and use epidemiological analysis methods to conduct early diagnosis and preventive treatment to achieve precise prevention and precise disease treatment.

When a certain element of individual health data changes, such as the occurrence of symptoms, physical signs, age, environment, psychology and other dynamic factors from multiple sources, the artificial intelligence system immediately analyzes and processes it to form real-time updated individual health data. In other words, the consumer Changes in data mean that individuals trigger service requests to the decision-making system. Similarly, when a certain queue parameter of a regional population changes, the artificial intelligence system immediately processes it and integrates biological big data, clinical big data and health medical big data through data queue analysis to achieve regionalization, individualization and precision of disease prevention and treatment.

As a preferred implementation of this embodiment, in step S202, the doctor logs in to the human-machine interface, obtains the preliminary intervention plan corresponding to the user from the server through the human-machine interface for confirmation, and generates the final intervention plan after confirmation and returns to the computer steps, including:

As a preferred implementation of this embodiment, in step S3, the computer matches the intervention measures according to the final intervention plan and submits them to the user. The steps are specifically:

As a preferred implementation of this embodiment, in step S4, the evaluation results include the user's effectiveness evaluation and suitability evaluation of the intervention plan and the effectiveness evaluation and suitability evaluation of the intervention measures.

This embodiment forms a data-based health decision-making method around the user, processes and outputs new basic data in real time, and continuously iterates so that the human body and intervention implementation gradually form a balance and continue to be in a state of dynamic matching and intervention. Based on data and doctor collaboration, it provides Full-process health management except emergency first aid, giving users the decision-making power for medical health intervention; making medical system intervention a special form of time-point or staged intervention, and users knowing the intervention plan and the necessity and value of taking intervention measures in advance effectiveness and prognosis.

Embodiment 2: This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, any implementation of the present invention is implemented. Human-computer interaction method for health decision-making as described in the example.

Embodiment 3: This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the human-computer interaction method for health decision-making as described in any embodiment of the present invention is implemented. .

Embodiment 4: Referring to Figure 2, this embodiment provides a human-computer interaction system for health decision-making, including a computer and a server communicatively connected to the computer, and also includes:

The basic data acquisition module is used to obtain the user's basic data in real time in the computer, and generate preliminary diagnosis data based on the user's basic data and send it to the server; the basic data acquisition module implements the function of step S101 in Embodiment 1, which will not be described in detail here. ;

The preliminary diagnosis module is used for doctors to log in to the human-machine interface, obtain at least a set of user basic data and preliminary diagnosis data from the server through the human-machine interface, process it, generate corresponding user whole-person health data and return it to the computer; the preliminary diagnosis module implements The function of step S102 in Embodiment 1 will not be described again;

The preliminary plan generation module is used to generate a preliminary intervention plan based on the user's whole-person health data in the computer, and determine whether the user's whole-person health data is imbalanced. When the user's whole-person health data is imbalanced, the preliminary intervention plan is sent to the server; the preliminary plan The generation module implements the function of step S201 in Embodiment 1, which will not be described again;

The plan confirmation module is used for doctors to log in to the human-machine interface, obtain the preliminary intervention plan corresponding to the user from the server through the human-machine interface for confirmation, and generate the final intervention plan after confirmation and return it to the computer; the plan confirmation module is implemented as in the embodiment The function of step S202 will not be described again here;

The measure matching module is used to match intervention measures according to the final intervention plan in the computer and submit it to the user; the measure matching module implements the function of step S3 in Embodiment 1, which will not be described again here;

The evaluation module is used to evaluate the final intervention plan implemented by the user and the effect of the intervention measures, generate evaluation results and submit them to the computer, and the computer incorporates the evaluation results into the user's basic data; the measure matching module implements the function of step S4 in Embodiment 1. This will not be described again.

Embodiment 5: Referring to Figure 3, this embodiment provides a life cycle health management service system, including a collaborative management module and a human-computer interaction system for health decision-making as described in the above Embodiment 4;

The above are only examples of the present invention, and do not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the description and drawings of the present invention, or directly or indirectly applied to other related technologies fields are equally included in the scope of patent protection of the present invention.

Claims

A human-computer interaction method for health decision-making, characterized by including the following steps:

The computer obtains the user's basic data in real time, and generates preliminary diagnostic data based on the user's basic data and sends it to the server;

The doctor logs in to the human-machine interface, obtains at least one set of user basic data and preliminary diagnosis data from the server through the human-machine interface, processes it, generates corresponding user whole-person health data and returns it to the computer;

The computer generates a preliminary intervention plan based on the user's whole-person health data, and determines whether the user's whole-person health data is imbalanced. When the user's whole-person health data is imbalanced, the preliminary intervention plan is sent to the server;

The doctor logs in to the human-machine interface, obtains the preliminary intervention plan corresponding to the user from the server through the human-machine interface, and confirms it, and after confirmation, generates the final intervention plan and returns it to the computer;

The computer matches the intervention measures based on the final intervention plan and submits it to the user;

The final intervention plan implemented by the user and the effect of the intervention measures are evaluated, and the evaluation results are generated and submitted to the computer. The computer incorporates the evaluation results into the user's basic data.
A human-computer interaction method for health decision-making according to claim 1, characterized in that when the doctor logs in to the human-machine interface, at least one set of user basic data and preliminary diagnosis are obtained from the server through the human-machine interface. In the step of data processing, the processing process specifically includes: correcting, modifying and improving the preliminary diagnosis data based on the user's basic data.
A human-computer interaction method for health decision-making according to claim 1, characterized in that the steps of the computer generating a preliminary intervention plan based on the user's whole person health data are specifically:

Training multidisciplinary diagnostic models based on neural networks;

Predict the user's health problems through a multidisciplinary diagnostic model based on the user's whole-person health data;

Establish an intervention plan database, write corresponding intervention plans for different health problems and put them into the intervention plan database. The intervention plan contains a number of sequential nodes, and each node has an optional intervention sub-program written corresponding to it, and each node is programmed with an optional intervention sub-program. Intervention sub-programs add program characteristics and interventions available for that intervention sub-program;

The intervention plan is matched from the intervention plan database based on the user's health problem, and each node of the intervention plan is matched according to the user's basic data and plan characteristics, and the intervention sub-plan with a high matching degree is selected to generate the preliminary intervention plan.
A human-computer interaction method for health decision-making according to claim 3, characterized in that when the doctor logs into the human-machine interface, the preliminary intervention plan corresponding to the user is obtained from the server through the human-machine interface for confirmation. , and after confirmation, the final intervention plan is generated and returned to the computer steps, including:

If the doctor confirms the adoption of the preliminary intervention plan, the preliminary intervention plan will be returned to the computer as the final intervention plan;

If the doctor needs to re-judge, the computer will return to re-acquire the user's basic data and generate preliminary diagnostic data, submit it to the doctor for reprocessing, update the user's overall health data and submit it to the doctor;

The doctor confirms or modifies the intervention sub-plan at any node in the preliminary intervention plan based on the user's whole-person health data, and generates the final intervention plan and returns it to the computer after all nodes are confirmed or modified.
A human-computer interaction method for health decision-making according to claim 4, characterized in that the steps of the computer matching intervention measures according to the final intervention plan and submitting them to the user are specifically:

Establishing an intervention measure information database, the intervention measure information database includes multiple sub-intervention measure databases, each sub-intervention measure database corresponding to different types of intervention measures respectively;

Collect the intervention measures, classify and label the intervention measures, where the labeling is specifically to add the characteristic information of the corresponding intervention measures; put the labeled intervention measures into the corresponding type of sub-intervention measure database according to the classification;

According to the final intervention plan, the types of intervention measures available for each node's intervention sub-program are obtained, and the intervention measures are automatically matched from the sub-intervention measure database of the corresponding type; the matched intervention measures and corresponding feature information are submitted to the user.
A human-computer interaction method for health decision-making according to claim 1, characterized in that:

The evaluation results include the user's effectiveness evaluation and suitability evaluation of the intervention plan and the effectiveness evaluation and suitability evaluation of the intervention measures;

The computer adds rating labels to the corresponding intervention programs and intervention measures based on the user's evaluation results of the effects of the intervention programs and intervention measures, and incorporates the intervention programs and corresponding rating labels, as well as the intervention measures and corresponding rating labels into the user's basic data; using The intervention plan and corresponding scoring labels, as well as the intervention measures and corresponding scoring labels, provide a basis for judgment in the subsequent computer-generated preliminary intervention plan and matching intervention measures.
An electronic device, including a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that when the processor executes the program, the method for health as claimed in claim 1 is implemented. Human-computer interaction methods for decision-making.
A human-computer interaction system for health decision-making, including a computer and a server communicatively connected to the computer, and is characterized in that it also includes:

The basic data acquisition module is used to obtain the user's basic data in real time in the computer, and generate preliminary diagnostic data based on the user's basic data and send it to the server;

The preliminary diagnosis module is used for doctors to log in to the human-machine interface, obtain at least one set of user basic data and preliminary diagnosis data from the server through the human-machine interface, process it, generate corresponding user whole-person health data and return it to the computer;

The preliminary plan generation module is used to generate a preliminary intervention plan based on the user's whole-person health data in the computer, and determine whether the user's whole-person health data is imbalanced. When the user's whole-person health data is imbalanced, the preliminary intervention plan is sent to the server;

The plan confirmation module is used for doctors to log in to the human-machine interface, obtain the preliminary intervention plan corresponding to the user from the server through the human-machine interface for confirmation, and generate the final intervention plan after confirmation and return it to the computer;

The measure matching module is used to match intervention measures according to the final intervention plan in the computer and submit it to the user;

The evaluation module is used to evaluate the final intervention plan implemented by the user and the effect of the intervention measures, generate evaluation results and submit them to the computer, and the computer will incorporate the evaluation results into the user's basic data.
A life-cycle health management service system characterized by:

Comprising a collaborative management module and a human-computer interaction system for health decision-making as claimed in claim 8;

The collaborative management module obtains data from the human-computer interaction system for health decision-making and provides services to users based on the obtained data.