A decision making method, system, electronic device and storage medium

Abstract

The present invention discloses a decision-making method, system, electronic device and storage medium, and relates to the field of computer technology. The method comprises: obtaining real-time feedback data provided by a target user for a preset problem through an interactive platform; generating an initial decision for solving the preset problem according to the real-time feedback data and historical feedback data of the target user; optimizing the initial decision, generating a final decision for solving the preset problem, and providing it to the target user. The present invention can obtain real-time feedback data provided by the target user for the preset problem through an interactive platform, and then automatically analyze the feedback data and existing feedback data of each target user, so as to generate an initial decision such as a health management plan and a learning plan for each target user's preset problem in a more targeted and accurate manner, and then further improve the success rate of solving the preset problem by optimizing the initial decision.

Description

Background Art

[0002] Currently, the medical management of patients with rare diseases faces multiple challenges, including lack of personalized treatment plans, poor communication between doctors and patients, and scarce expert resources. The existing medical system is often unable to effectively integrate the multi-dimensional data of patients, resulting in a lack of pertinence and flexibility in the health management plans provided. Summary of the invention

[0003] The technical problem to be solved by the present invention is to address the deficiencies of the prior art and specifically provide a decision making method, system, electronic device and storage medium, as follows:

[0004] 1) In the first aspect, the present invention provides a decision making method, and the specific technical solution is as follows:

[0005] Obtain real-time feedback data from target users on preset questions through the interactive platform;

[0006] Generate initial decisions for solving preset problems based on real-time feedback data and historical feedback data from target users;

[0007] The initial decision is optimized to generate a final decision to solve the preset problem and provide it to the target users.

[0008] The beneficial effects of a decision making method provided by the present invention are as follows:

[0009] Through the interactive platform, we can obtain real-time feedback data provided by target users in response to preset questions, and then automatically analyze the feedback data and existing feedback data of each target user, so as to generate initial decisions for each target user's preset questions in a more targeted and accurate manner, such as health management plans and learning plans, and then further improve the success rate of solving preset problems by optimizing the initial decisions.

[0010] Based on the above solution, a decision making method of the present invention can also be improved as follows.

[0011] Furthermore, it also includes:

[0012] When the target user is executing the final decision, the execution feedback questionnaire corresponding to the final decision is pushed to the target user at a regular interval, the target user's response to the execution feedback questionnaire is received and data processing is performed to obtain the target user's self-assessment data when executing the final decision.

[0013] The beneficial effect of adopting the above further solution is that during the process of the target user executing the final decision, the execution effect of the final decision can be continuously evaluated in real time through evaluation data.

[0014] Furthermore, it also includes:

[0015] The final decision is revised based on the target user's self-assessment data when executing the final decision.

[0016] The beneficial effect of adopting the above further solution is: by correcting the final decision, the corrected final decision is made more suitable for the target user, thereby further improving the success rate of solving the preset problem.

[0017] Furthermore, the real-time feedback data includes at least one of voice data, text data and images.

[0018] Furthermore, the feedback data is encrypted and the encrypted feedback data is stored.

[0019] The beneficial effect of adopting the above further solution is that the security of the user's feedback data can be guaranteed to the greatest extent through data encryption.

[0020] 2) In the second aspect, the present invention also provides a decision making system, and the specific technical solution is as follows:

[0021] It includes a data acquisition module, an initial decision generation module and a final decision generation module;

[0022] The data acquisition module is used to: obtain real-time feedback data provided by target users for preset questions through the interactive platform;

[0023] The initial decision generation module is used to: generate an initial decision for solving a preset problem based on the real-time feedback data and historical feedback data of the target user;

[0024] The final decision generation module is used to optimize the initial decision, generate the final decision for solving the preset problem, and provide it to the target user.

[0025] Based on the above solution, a decision making system of the present invention can also be improved as follows.

[0026] Furthermore, the data acquisition module is also used to:

[0027] When the target user is executing the final decision, the execution feedback questionnaire corresponding to the final decision is pushed to the target user at a regular interval, the target user's response to the execution feedback questionnaire is received and data processing is performed to obtain the target user's self-assessment data when executing the final decision.

[0028] Furthermore, it also includes a final decision correction module, which is used to correct the final decision based on the self-assessment data of the target user when executing the final decision.

[0029] Furthermore, the real-time feedback data includes at least one of voice data, text data and images.

[0030] Furthermore, it also includes a data encryption module and a data storage module. The data encryption storage module is used to encrypt the feedback data, and the data storage module is used to store the encrypted feedback data.

[0031] 3) In a third aspect, the present invention further provides an electronic device, comprising a processor, the processor being coupled to a memory, the memory storing at least one computer program, the at least one computer program being loaded and executed by the processor so that the electronic device implements any one of the above-mentioned decision-making methods.

[0032] 4) In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, any one of the above-mentioned decision-making methods is implemented.

[0033] It should be noted that the beneficial effects achieved by the technical solutions of the second to fourth aspects of the present invention and the corresponding possible implementation methods can be found in the above-mentioned technical effects of the first aspect and its corresponding possible implementation methods, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments of the present invention:

[0035] Figure 1 A flowchart of a decision making method according to an embodiment of the present invention;

[0036] Figure 2 A schematic diagram of the structure of a decision making system according to an embodiment of the present invention;

[0037] Figure 3 The figure is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0038] The principles and features of the present invention are described below. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0039] The technical solution of the present invention and how the technical solution of the present invention solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present invention will be described below in conjunction with the accompanying drawings.

[0040] like Figure 1 As shown, a decision making method according to an embodiment of the present invention comprises the following steps:

[0041] S1. Obtain real-time feedback data provided by target users on preset questions through the interactive platform;

[0042] The real-time feedback data includes at least one of voice data, text data and images.

[0043] Among them, the interactive platform is divided into a management end and a user end. The management end can be an executable program in exe format, which can be installed on a computer device. The management end can also be an APP program, which can be installed on the manager's smartphone or tablet computer. The user end can be an APP program, which is easy to install on the target user's smartphone or tablet computer, so that each target user can provide feedback data on preset questions in real time.

[0044] The target user may be any preset user, and the preset user is: a user registered on the interactive platform.

[0045] On the display interface of the user end, there are click boxes for voice mode, text mode and image mode. The target user selects voice mode, text mode or image mode by clicking to provide data feedback for preset questions.

[0046] Among them, the preset questions can be "how to match diet", "how to manage health", "how to treat" or "how to predict each user's learning progress and future learning needs to provide personalized learning suggestions", etc. The preset questions can be set according to the actual situation, and the interactive platform provides different prompts for different preset questions, so that the target user can fill in the content according to the prompts. Specifically:

[0047] 1) For example, when the preset question is "How to match diet", the interactive platform pops up an input box for inputting at least one of physiological parameters, current diet, exercise status and medication status, and displays click boxes in voice, text and image modes, so that the target user can input data in different ways. When the target user has questions, he can call and view the prompt content, where physiological parameters include blood sugar value, blood pressure value, heart rate value, height and weight, etc.

[0048] 2) For example, when the preset question is "How to manage health", the interactive platform pops up an input box for entering at least one of physiological parameters, current diet, exercise status, symptoms, and past medical history, and displays click boxes in voice, text, and image modes, so that the target user can input data in different ways. When the target user has questions, he or she can call and view the prompt content.

[0049] 3) For example, when the preset question is "How to treat", the interactive platform pops up an input box for entering at least one of physiological parameters, disease name, current diet, exercise status, medication status, physical condition and previous medical history, and displays click boxes in voice, text and image modes, so that the target user can input data in different ways. When the target user has questions, he can call and view the prompt content.

[0050] 4) When the preset question is "How to predict each user's learning progress and future learning needs to provide personalized learning suggestions", the interactive platform pops up an input box for entering course completion status, test scores, and learning time, and displays click boxes in voice, text, and image modes, so that the target user can input data in different ways. When the target user has questions, he or she can call and view the prompt content.

[0051] S2. Generate an initial decision for solving the preset problem based on the real-time feedback data and historical feedback data of the target users;

[0052] Among them, for different preset problems, corresponding decision models are pre-trained, specifically:

[0053] 1) When the preset question may be "how to match diet", historical feedback data of multiple preset users are collected in advance, and a reference diet matching plan of the historical feedback data of each preset user is set (the reference diet matching plan is a diet matching plan determined after discussion by multiple diet experts), and a first sample set is constructed. The first sample set is used to train the first preset deep learning model to obtain a corresponding decision model, which is recorded as the first decision model.

[0054] Among them, the first preset deep learning model can be a convolutional neural network or a long short-term memory neural network, etc., which can be set according to actual conditions.

[0055] 2) When the preset question may be “how to conduct health management”, historical feedback data of multiple preset users are collected in advance, and a reference health management plan for the historical feedback data of each preset user is set (the reference health management plan is a health management plan determined after discussion by multiple experts), and a second sample set is constructed. The second preset deep learning model is trained using the second sample set to obtain a corresponding decision model, which is recorded as the second decision model.

[0056] Among them, the second preset deep learning model can be a convolutional neural network or a long short-term memory neural network, etc., which can be set according to actual conditions.

[0057] 3) When the preset question may be “how to treat”, historical feedback data of multiple preset users are collected in advance, and a reference treatment plan for the historical feedback data of each preset user is set (the reference treatment plan is a treatment plan determined after discussion by multiple experts), and a third sample set is constructed. The third preset deep learning model is trained using the third sample set to obtain a corresponding decision model, which is recorded as the third decision model.

[0058] Among them, the third preset deep learning model can be a convolutional neural network or a long short-term memory neural network, etc., which can be set according to actual conditions.

[0059] 4) When the preset question may be “how to predict each user’s learning progress and future learning needs in order to provide personalized learning suggestions”, historical feedback data of multiple preset users are collected in advance, and a reference learning suggestion plan for the historical feedback data of each preset user is set (the reference learning suggestion plan is a learning suggestion plan determined after discussion by multiple experts), and a fourth sample set is constructed. Based on the fourth sample set, the fourth preset deep learning model is trained to obtain a corresponding decision model, which is recorded as the fourth decision model.

[0060] Among them, the fourth preset deep learning model can be a convolutional neural network or a long short-term memory neural network, etc., which can be set according to actual conditions.

[0061] Based on the real-time and historical feedback data of target users, generate initial decisions for solving preset problems, including:

[0062] S20, dividing the historical feedback data of each preset user collected in advance into two parts in chronological order, inputting the first part of the historical feedback data of any preset user into the decision model to obtain a first initial decision, inputting the second part of the historical feedback data of the preset user into the decision model to obtain a second initial decision, inputting the historical feedback data of the preset user into the decision model to obtain a third initial decision, calculating the similarity between the first part of the historical feedback data of the preset user and the second part of the historical feedback data of the preset user, recorded as the first similarity, calculating the similarity between the first initial decision of the preset user and the second initial decision, recorded as the second similarity, and calculating the The proportion of the front part of the historical feedback data of the preset user in the historical feedback data of the preset user is used as the similarity between the front part of the historical feedback data of the preset user and the historical feedback data of the preset user, which is recorded as the third similarity, until the first similarity, second similarity and third similarity corresponding to multiple preset users are obtained, and the functional relationship between the first similarity and the second similarity is fitted, which is recorded as the first functional relationship, and the functional relationship between the first similarity and the third similarity is fitted, which is recorded as the second functional relationship. According to the first functional relationship and the second functional relationship, the functional relationship between the second similarity and the third similarity is fitted, which is recorded as the third functional relationship.

[0063] S21, input the real-time feedback data of the target user into the decision model, generate a first initial decision for solving the preset problem, and for the sake of distinction, record the first initial decision as the first target initial decision; input the historical feedback data of the target user into the decision model, generate a second initial decision for solving the preset problem, and for the sake of distinction, record the second initial decision as the second target initial decision; calculate the similarity between the real-time feedback data of the target user and the historical feedback data of the target user, and for the sake of distinction, record the similarity as the first target similarity; calculate the similarity between the first target initial decision and the second target initial decision, and for the sake of distinction, record the similarity as the second target similarity;

[0064] S22. Calculate the expected value of the second target similarity corresponding to the first target initial decision by using the first functional relationship, calculate and determine whether the deviation between the second target similarity and the expected value of the second target similarity exceeds a first preset deviation threshold, and obtain a first judgment result. When the first judgment result is no, determine the first target initial decision as the initial decision for solving the preset problem, wherein the first preset deviation threshold can be set according to actual conditions.

[0065] S23. When the first judgment result is yes, the proportion of the target user's real-time feedback data in the real-time feedback data and the historical feedback data is calculated as the third target similarity, and the expected value of the third target similarity corresponding to the second target initial decision is calculated using the third functional relationship, and it is determined whether the deviation between the expected value of the third target similarity and the third target similarity exceeds the second preset deviation similarity threshold, to obtain a second judgment result. When the second judgment result is no, it means that the second target similarity and the third target similarity conform to the third functional relationship, and a deviation has occurred in the first target initial decision. At this time, the interactive platform issues a reminder to remind the target user to confirm whether the filled-in data is correct. When the target user confirms that the filled-in data is correct, the manager's correction to the first target initial decision is received, and the corrected first target initial decision is used as the initial decision for solving the preset problem.

[0066] S24. When the second judgment result is yes, the amount of historical feedback data input to the decision model is reduced in a sliding window manner, the third target similarity is regenerated, and return to S23 to determine whether there is a situation that makes the second judgment result yes, and obtain the third judgment result, wherein the size of the sliding window used can be set according to the actual situation. For example, each time it slides, a group of data in the historical feedback data is reduced.

[0067] S25. When the third judgment result is yes, it means that the second target similarity and the third target similarity still conform to the third functional relationship, and the first target initial decision has deviated. At this time, the interactive platform issues a reminder to remind the target user to confirm whether the filled-in data is correct. When the target user confirms that the filled-in data is correct, the manager will receive the correction of the first target initial decision, and the corrected first target initial decision will be used as the initial decision for solving the preset problem.

[0068] S26. When the third judgment result is no, it means that the second target similarity and the third target similarity do not always conform to the third functional relationship. Since the first judgment result is yes, it means that there is a problem with the first target initial decision or the second target initial decision. In a sliding window manner and in chronological order, before the real-time feedback data, part of the historical feedback data is spliced, and then the first target initial decision is regenerated, and then the execution of S22 is returned. When the first judgment result is yes for the first time, the first target initial decision generated this time is used as the initial decision for solving the preset problem. When the first judgment result is not yes, a reminder is issued to receive the manager's correction of the first target initial decision, and the corrected first target initial decision is used as the initial decision for solving the preset problem, and a reminder is issued to the user to optimize the decision model, the first functional relationship, the second functional relationship and the third functional relationship.

[0069] The size of the sliding window used may be set according to actual conditions. For example, each time a sliding window is slid, a group of data in the historical feedback data is spliced.

[0070] Among them, when the preset question may be "How to match diet", the initial decision is: the initial diet matching plan; when the preset question may be "How to manage health", the initial decision is: the initial health management plan; when the preset question may be "How to treat", the initial decision is: the initial treatment plan; when the preset question may be "How to predict each user's learning progress and future learning needs to provide personalized learning suggestions", the initial decision is: the initial learning suggestion plan.

[0071] Through S20 to S26, the success rate of the initial decision in solving the preset problem can be guaranteed to the greatest extent, and the complexity of subsequent optimization of the initial decision can also be reduced.

[0072] S3. Optimize the initial decision, generate the final decision to solve the preset problem, and provide it to the target users.

[0073] Among them, after obtaining the initial diet matching plan, the initial health management plan, the initial treatment plan or the initial learning suggestion plan, the implementation effect of the initial diet matching plan, the initial health management plan, the initial treatment plan or the initial learning suggestion plan is estimated through discussion by multiple experts, and the initial diet matching plan, the initial health management plan, the initial treatment plan or the initial learning suggestion plan is optimized according to the estimated results to generate the final diet matching plan, the final health management plan, the final treatment plan or the final learning suggestion plan.

[0074] In another embodiment, after obtaining an initial diet pairing plan, an initial health management plan, an initial treatment plan or an initial learning suggestion plan, an estimation is made of the execution effect of the initial diet pairing plan, the initial health management plan, the initial treatment plan or the initial learning suggestion plan through artificial intelligence, and the initial diet pairing plan, the initial health management plan, the initial treatment plan or the initial learning suggestion plan is optimized according to the estimation result to generate a final diet pairing plan, a final health management plan, a final treatment plan or a final learning suggestion plan.

[0075] Optionally, in the above technical solution, it also includes:

[0076] S4. When the target user is executing the final decision, the execution feedback questionnaire corresponding to the final decision is pushed to the target user at a regular interval, the target user's response to the execution feedback questionnaire is received and data is processed to obtain the target user's self-assessment data when executing the final decision.

[0077] Optionally, in the above technical solution, it also includes:

[0078] S5. Modify the final decision based on the target user’s self-assessment data when executing the final decision.

[0079] Among them, a trained deep learning network is used to predict the self-assessment data of the target user after a preset period of time, which can be 1 week or 1 month, etc., to obtain the evaluation data of the target user, and a first portrait of the user is established based on the predicted self-assessment data. A second portrait of the user is established based on the real evaluation data of the target user, and the similarity between the first portrait and the second portrait is calculated. When the similarity is less than a third similarity threshold, the user is asked to confirm whether to strictly execute the final decision. When the user confirms to strictly execute the final decision, the process data of the target user when executing the final decision is received, and combined with the target user's evaluation data on the final decision, the final decision is corrected by expert argumentation and other means.

[0080] When the user confirms that the final decision is not strictly implemented, the predicted self-assessment data is provided to the target user to motivate the target user to strictly implement the final decision.

[0081] Optionally, in the above technical solution, it also includes:

[0082] The feedback data is encrypted and stored. By encrypting the data, the security of the user's feedback data can be guaranteed to the greatest extent.

[0083] The invention is illustrated by the following examples.

[0084] Embodiment 1:

[0085] In Example 1, the preset question is "How to treat a rare disease", which specifically includes the following steps:

[0086] 1) Data collection and integration: Specifically, by distributing rare disease questionnaires to rare disease patients, we obtain feedback data from rare disease patients. The feedback data includes: lifestyle, etc., and integrate multi-dimensional information such as genomic data, clinical records, and lifestyle of rare disease patients.

[0087] 2) Generation of personalized treatment plans (i.e. final decision): Using machine learning algorithms, personalized treatment plans are generated based on the data of patients with rare diseases. The target problem determined is: how to treat rare diseases. The decision feature data includes: genomic data, clinical records, lifestyle and other multi-dimensional information of patients with rare diseases.

[0088] 3) Regular diagnosis and treatment and follow-up: Set regular follow-up time, and doctors and patients will conduct online or offline diagnosis and treatment.

[0089] 4) Doctor-patient interaction platform: Establish a doctor-patient interaction platform where patients can consult doctors at any time and upload changes in symptoms.

[0090] 5) Expert consultation mechanism: In complex cases, after the preliminary plan is automatically generated, experts are invited to consult and the plan is optimized based on the doctor’s experience (the final decision is optimized).

[0091] 6) Patient Education and Support: Provide educational resources on disease management and treatment to help patients better understand their condition.

[0092] When the rare disease is Alkire's disease, it specifically includes:

[0093] 1) Data collection: Collect genomic data, dietary habits, and symptom records (feedback data) of patients with Alkire's disease.

[0094] 2) Personalized diet and treatment plan (final decision): Based on data analysis, a personalized low-tyrosine and low-phenylalanine diet plan is generated.

[0095] 3) Regular diagnosis and treatment: Set regular follow-up time, and doctors will conduct regular online or offline diagnosis and treatment with Alkire disease patients to evaluate changes in the condition.

[0096] 4) Doctor-patient interaction platform: Establish a doctor-patient interaction platform, where Alkire's disease patients can consult doctors at any time and upload symptom changes. Alkire's disease doctors can adjust treatment plans based on feedback.

[0097] 5) Expert consultation: In complex cases, after the preliminary treatment plan is automatically generated, experts in related fields are invited to consult and the treatment plan is optimized based on the doctors’ experience.

[0098] 6) Patient Education: Provide educational resources on disease management and diet to help patients understand their condition.

[0099] 7) Results: The symptoms of Alkire's disease patients were effectively controlled and their quality of life was significantly improved.

[0100] When the rare disease is Gaucher Disease, it specifically includes:

[0101] 1) Health data integration: Integrate clinical data, genetic testing, and family medical history of Gaucher disease patients.

[0102] 2) Enzyme replacement therapy plan: Develop a personalized enzyme replacement therapy plan (final decision) based on the patient's specific situation.

[0103] 3) Regular diagnosis and treatment: Set up regular follow-up visits for doctors to diagnose and treat Gaucher disease patients and monitor disease progression.

[0104] 4) Doctor-patient interaction platform: Gaucher disease patients can report symptom changes at any time through the platform, and doctors can adjust treatment plans based on real-time data.

[0105] 5) Expert consultation: During the treatment process, experts can be invited to consult based on the patient's condition, and the treatment strategy can be optimized based on the doctor's experience (to optimize the final decision).

[0106] 6) Support network: Establish a patient communication platform to promote information sharing and support.

[0107] 7) Results: The health status and quality of life of patients with Gaucher disease improved.

[0108] When the rare disease is Huntington's Disease, it specifically includes:

[0109] 1) Genetic testing and evaluation: Genetic testing is performed to assess the risk and symptom development of Huntington's disease patients.

[0110] 2) Personalized psychological support program (final decision): Provide personalized psychological support and counseling services to Huntington's disease patients and their families.

[0111] 3) Regular diagnosis and treatment: Set up regular follow-up visits for doctors to diagnose and treat Huntington's disease patients and assess mental health and cognitive function.

[0112] 4) Doctor-patient interaction platform: Huntington's disease patients can communicate with their doctors at any time and report changes in symptoms. Doctors can adjust psychological support plans based on feedback.

[0113] 5) Expert consultation: In complex situations, the system can invite experts for consultation and optimize treatment recommendations based on the doctor’s experience (optimizing the final decision).

[0114] 6) Lifestyle adjustment: Develop a personalized lifestyle management plan, including diet and exercise recommendations.

[0115] 7) Results: The quality of life and mental health of Huntington's disease patients were significantly improved.

[0116] In this embodiment, the technology of generating personalized medical plans, intelligent risk intervention and doctor-patient interaction system for patients with rare diseases is used. The system combines multiple technical means such as big data analysis, artificial intelligence, machine learning and medical informatics to improve the diagnosis and treatment efficiency and quality of life of patients with rare diseases, and has the following technical effects:

[0117] 1) Personalized medicine: Generate personalized treatment plans based on the specific data of patients with rare diseases to improve treatment outcomes.

[0118] 2) Enhance doctor-patient interaction: Through the doctor-patient interaction platform, patients with rare diseases can communicate with doctors at any time to improve their satisfaction with treatment.

[0119] 3) Efficient expert consultation: The system can quickly invite experts for consultation to ensure that patients with rare diseases receive the best treatment advice.

[0120] 4) Automatic learning and optimization: The system has the ability to learn automatically and can continuously optimize treatment plans and improve management effectiveness based on feedback from patients with rare diseases.

[0121] Embodiment 2:

[0122] With the popularity of wearable devices, medical institutions hope to use these devices to collect patients' health data for real-time monitoring and intervention. On this basis, an intelligent health monitoring method is provided, including the following steps:

[0123] 1) Data collection: Collect patients’ real-time health data (feedback data) through wearable devices and upload them to the cloud.

[0124] 2) Data processing: Clean and integrate data and use algorithms to identify outliers.

[0125] 3) Abnormality detection: Establish threshold models, monitor physiological indicators in real time, and identify potential health risks.

[0126] 4) Feedback mechanism: When an abnormality is detected, the system automatically sends alerts to patients and doctors and provides corresponding health advice (final decision).

[0127] The method in Example 2 can monitor the patient's physiological indicators (such as heart rate, blood pressure, blood oxygen saturation, etc.) in real time, identify abnormal conditions through data analysis, and promptly remind the patient and the medical team. Through historical data analysis, personalized health advice can be provided.

[0128] Embodiment 3:

[0129] At present, more and more patients hope to obtain medical consultation and services through telemedicine. On this basis, a telemedicine consultation platform is provided, which can achieve the following functions:

[0130] 1) Support video calls, text chat and other functions.

[0131] 2) Data collection: Collect the patient's medical history, symptoms, and relevant examination results (feedback data) during the consultation process.

[0132] 3) Intelligent assistance: Use natural language processing technology to analyze the symptoms described by the patient, assist doctors in making a preliminary diagnosis, and obtain a treatment plan (final decision).

[0133] 4) Feedback and optimization: Based on patient feedback and treatment results, continuously optimize the platform's functions and doctors' treatment plans (optimize the final decision).

[0134] Telemedicine consultation platforms facilitate online communication between patients and doctors, collect patients’ health information, help doctors make more accurate diagnoses, and optimize doctors’ diagnosis and treatment plans through data analysis.

[0135] Embodiment 4:

[0136] Medical institutions hope to evaluate the efficacy and side effects of drugs by monitoring the reactions of patients during medication. The present invention also provides the following technical solutions:

[0137] 1) Data collection: Collect patient feedback and physiological data (feedback data) through questionnaires, electronic medical records, and health monitoring devices.

[0138] 2) Data analysis: Apply statistical analysis and machine learning models to evaluate the efficacy and side effects of drugs.

[0139] 3) Personalized recommendations: Based on the analysis results, provide personalized medication recommendations and adjustment plans (final decisions) to doctors and patients.

[0140] 4) Continuous monitoring: Establish a long-term monitoring mechanism to track patients’ medication responses and health changes.

[0141] Medical institutions can collect feedback and changes in physiological indicators from patients after taking medication, and use data analysis to evaluate the efficacy and safety of the drugs, and then provide personalized medication recommendations and optimize treatment plans (optimize the final decision).

[0142] Embodiment 5:

[0143] At present, mental health issues are increasingly receiving attention, and medical institutions hope to help patients manage their mental health through data analysis. The present invention also provides the following technical solutions:

[0144] 1) Data collection: Collect patients’ mental health data (feedback data) through questionnaires, online assessment tools, and wearable devices.

[0145] 2) Data Analysis: Apply machine learning models to analyze data and identify potential mental health risks.

[0146] 3) Personalized intervention: Based on the analysis results, provide patients with personalized psychological counseling and intervention suggestions (final decision).

[0147] 4) Feedback mechanism: Regularly collect patient feedback, evaluate intervention effectiveness, and optimize management strategies (optimize final decisions).

[0148] Medical institutions can collect patients' mental health data (e.g., emotional state, stress level, etc.), use data analysis to identify mental health risks, and provide personalized intervention plans. Optimize mental health management strategies through continuous monitoring and feedback.

[0149] Embodiment 6:

[0150] An online learning platform hopes to predict each user's learning progress and future learning needs through the user's historical learning data and real-time interaction data, so as to provide personalized learning suggestions. The present invention also provides the following technical solutions:

[0151] 1) Data collection (feedback data collection):

[0152] ①Historical data: collect users’ learning records on the platform, including course participation, grades, learning time, etc.

[0153] ② Real-time data: Real-time data is obtained through user behavior monitoring (such as the length of time watching videos, the frequency of participating in discussions, the timeliness of homework submission, etc.).

[0154] 2) Data processing and analysis:

[0155] ①Use data cleaning techniques to process the collected data and remove noise and outliers.

[0156] ② Apply machine learning algorithms (such as regression analysis, decision trees, random forests, etc.) to analyze users’ learning behaviors and predict future learning trends (such as expected time to complete the course, possible grades, etc.).

[0157] 3) Model training and prediction:

[0158] ① Divide historical data into training sets and test sets, use the training set to train the model, and verify the accuracy of the model on the test set.

[0159] ② Generate personalized learning prediction reports for each user, providing suggestions and improvement measures (final decision).

[0160] 4) Result comparison and feedback:

[0161] After the user completes the course, collect the actual learning results (such as final grade, course completion time, etc.). Compare the predicted results with the actual results, analyze the accuracy of the prediction, and identify the deficiencies of the model.

[0162] 5) Algorithm optimization:

[0163] According to the results of comparative analysis, adjust and optimize the parameters of the machine learning model, or try other algorithms (such as deep learning, ensemble learning, etc.). Update the model regularly to adapt to changes in user behavior and ensure the accuracy and personalization of predictions.

[0164] Through the above implementation steps, the online learning platform can achieve the following goals:

[0165] 1) Improve users’ learning experience and satisfaction.

[0166] 2) Realize personalized learning recommendations to help users better plan their learning paths.

[0167] 3) Continuously optimize the prediction algorithm and improve prediction accuracy, thereby improving the overall effectiveness of the platform.

[0168] In the above embodiments, although the steps are numbered S1, S2, etc., these are only specific embodiments given by the present invention. Those skilled in the art may adjust the execution order of S1, S2, etc. according to actual conditions, which is also within the protection scope of the present invention. It can be understood that in some embodiments, some or all of the above embodiments may be included.

[0169] like Figure 2 As shown, a decision making system 200 according to an embodiment of the present invention includes a data acquisition module 201, an initial decision making module 202 and a final decision making module 203;

[0170] The data acquisition module 201 is used to: acquire real-time feedback data provided by target users for preset questions through the interactive platform;

[0171] The initial decision generating module 202 is used to generate an initial decision for solving a preset problem according to the real-time feedback data and historical feedback data of the target user;

[0172] The final decision generation module 203 is used to optimize the initial decision, generate a final decision for solving a preset problem, and provide it to the target user.

[0173] Optionally, in the above technical solution, the data acquisition module 201 is further used for:

[0174] When the target user is executing the final decision, the execution feedback questionnaire corresponding to the final decision is pushed to the target user at a regular interval, the target user's response to the execution feedback questionnaire is received and data processing is performed to obtain the target user's self-assessment data when executing the final decision.

[0175] Optionally, the above technical solution further includes a final decision correction module, which is used to correct the final decision according to the self-assessment data of the target user when executing the final decision.

[0176] Optionally, in the above technical solution, the real-time feedback data includes at least one of voice data, text data and images.

[0177] It should be noted that the beneficial effects of a decision-making system 200 provided in the above embodiment are the same as the beneficial effects of the above decision-making method, which will not be described in detail here. In addition, when the system provided in the above embodiment realizes its functions, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the system can be divided into different functional modules according to actual conditions to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be described in detail here.

[0178] Among them, the decision-making system of the present invention can be a computer program (including program code) running in a computer device. For example, the decision-making system of the present invention is an application software that can be used to execute the corresponding steps in the decision-making method of the present invention.

[0179] In some embodiments, the decision-making system of the present invention can be implemented in a combination of software and hardware. As an example, the decision-making system of the present invention can be a processor in the form of a hardware decoding processor, which is programmed to execute the decision-making method of the present invention. For example, the processor in the form of a hardware decoding processor can adopt one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs) or other electronic components.

[0180] The modules involved in the embodiments of the present invention may be implemented in software or hardware. The name of a module does not limit the module itself in some cases.

[0181] An electronic device according to an embodiment of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, any one of the above-mentioned decision-making methods is implemented. That is to say, an electronic device according to an embodiment of the present invention may include but is not limited to: a processor and a memory; a memory for storing a computer program; a processor for executing a decision-making method shown in any embodiment of the present invention by calling a computer program.

[0182] In an alternative embodiment, an electronic device is provided, such as Figure 3 As shown, Figure 3 The electronic device 4000 shown includes: a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, such as through a bus 4002. Optionally, the electronic device 4000 may also include a transceiver 4004, which may be used for data interaction between the electronic device and other electronic devices, such as data transmission and / or data reception. It should be noted that in actual applications, the transceiver 4004 is not limited to one, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present invention.

[0183] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of the present invention. Processor 4001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0184] The bus 4002 may include a path to transmit information between the above components. The bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 4002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 In the figure, only one thick line is used to represent the bus 4002, but this does not mean that there is only one bus or one type of bus.

[0185] The memory 4003 can be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to this.

[0186] The memory 4003 is used to store the application code (computer program) for executing the solution of the present invention, and the execution is controlled by the processor 4001. The processor 4001 is used to execute the application code stored in the memory 4003 to implement the content shown in the above method embodiment.

[0187] Among them, the electronic device can also be a terminal device, and the terminal device can be any device that can install applications, including at least one of a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, a smart TV, and a smart car device.

[0188] It should be noted that Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0189] A computer-readable storage medium according to an embodiment of the present invention stores a computer program, and when the computer program is executed by a processor, any one of the above-mentioned decision-making methods is implemented.

[0190] Optionally, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0191] In an exemplary embodiment, a computer program product or a computer program is also provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device performs any of the above-mentioned decision-making methods.

[0192] Computer program code for performing the operations of the present invention may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0193] It should be understood that the flow charts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the module, the program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0194] The computer-readable storage medium provided by the embodiment of the present invention may be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or component.

[0195] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method shown in the above embodiment.

[0196] The above description is only a preferred embodiment of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the disclosure scope involved in the present invention is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present invention (but not limited to) by each other.

[0197] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects and represent the definition of a specific order or sequence. The order of use of similar objects can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than the order shown or described.

[0198] Those skilled in the art know that the present invention can be implemented as a system, method or computer program product. Therefore, the present invention can be specifically implemented in the following forms, namely: it can be complete hardware, it can be complete software (including firmware, resident software, microcode, etc.), or it can be a combination of hardware and software, which is generally referred to as "circuit", "module" or "system" herein. In addition, in some embodiments, the present invention can also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable medium contains computer-readable program code.

[0199] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A decision making method, characterized in that: include: Obtain real-time feedback data from target users on preset questions through the interactive platform; Generating an initial decision for solving the preset problem according to the real-time feedback data and historical feedback data of the target user; The initial decision is optimized to generate a final decision for solving the preset problem, and the final decision is provided to the target user.

2. A decision making method according to claim 1, characterized in that: Also includes: When the target user is executing the final decision, the execution feedback questionnaire corresponding to the final decision is pushed to the target user at a regular interval, the target user's reply to the execution feedback questionnaire is received and data processing is performed to obtain the target user's self-assessment data when executing the final decision.

3. A decision making method according to claim 2, characterized in that: Also includes: The final decision is modified according to the self-assessment data of the target user when executing the final decision.

4. A decision making method according to any one of claims 1 to 3, characterized in that: The real-time feedback data includes at least one of voice data, text data and images.

5. A decision making system, characterized in that: It includes a data acquisition module, an initial decision generation module and a final decision generation module; The data acquisition module is used to: obtain real-time feedback data provided by target users for preset questions through the interactive platform; The initial decision generating module is used to: generate an initial decision for solving the preset problem according to the real-time feedback data and historical feedback data of the target user; The final decision generation module is used to optimize the initial decision, generate a final decision for solving the preset problem, and provide it to the target user.

6. A decision making system according to claim 5, characterized in that: The data acquisition module is also used for: When the target user is executing the final decision, the execution feedback questionnaire corresponding to the final decision is pushed to the target user at a regular interval, the target user's reply to the execution feedback questionnaire is received and data processing is performed to obtain the target user's self-assessment data when executing the final decision.

7. A decision making system according to claim 6, characterized in that: It also includes a final decision correction module, which is used to correct the final decision according to the self-assessment data of the target user when executing the final decision.

8. A decision making system according to any one of claims 5 to 7, characterized in that: The real-time feedback data includes at least one of voice data, text data and images.

9. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements a decision making method as claimed in any one of claims 1 to 4 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, a decision-making method according to any one of claims 1 to 4 is implemented.

Images