Physical examination service data processing method and device

Abstract

The embodiment of the invention discloses a physical examination service data processing method and device. The specific implementation mode of the method comprises the steps that abnormal indexes in a physical examination result are input into a pre-trained medical knowledge model, and post-examination suggestion information is output for diagnosis reference of a doctor; generating total examination suggestion information according to modification operation of a doctor on the post-examination suggestion information; performing health state evaluation according to each index in the physical examination result to obtain health state information; inputting the user questionnaire information into a disease risk model, and predicting disease risk information; generating at least one of inquiry service link information and recommended commodity link information according to the abnormal index; and generating a physical examination report based on the total examination suggestion information, the health state information, the disease risk information and the link information. According to the embodiment, the efficiency of generating the physical examination report can be improved, and accurate chronic disease management service, medical service and marketing recommendation after physical examination are provided.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of medical technology, and more particularly to a method and apparatus for processing physical examination service data. Background Art

[0002] Existing post-examination services offered by medical examination institutions only generate medical reports (mostly outputting electronic reports or providing interpretations of these reports), lacking a systematic post-examination service system based on health status. Therefore, for users lacking medical knowledge, it is difficult to accurately and quickly manage and utilize subsequent medical examination service data based on medical reports. Summary of the Invention

[0003] The embodiments of the present disclosure provide a method and apparatus for processing physical examination service data.

[0004] In the first aspect, an embodiment of the present disclosure provides a method for processing physical examination service data, including: inputting abnormal indicators in the physical examination results into a pre-trained medical knowledge model, and outputting post-examination recommendation information for the doctor's diagnosis reference; generating general examination recommendation information based on the doctor's modification operation on the post-examination recommendation information; performing a health status assessment based on various indicators in the physical examination results to obtain health status information; inputting user questionnaire information into a disease risk model to predict disease risk information; generating at least one of consultation service link information and recommended product link information based on the abnormal indicators; and generating a physical examination report based on the general examination recommendation information, the health status information, the disease risk information and the link information.

[0005] In some embodiments, the method also includes: calculating the loss value of the medical knowledge model based on the difference between the post-examination recommendation information output by the medical knowledge model and the content modified by the doctor; repeating the following training steps until the loss value is less than a predetermined threshold: adjusting the network parameters of the medical knowledge model according to the loss value; inputting the abnormal indicators into the adjusted medical knowledge model to obtain new post-examination recommendation information; calculating the loss value of the medical knowledge model based on the difference between the new post-examination recommendation information and the content modified by the doctor.

[0006] In some embodiments, generating at least one of consultation service link information and recommended product link information based on the abnormal indicator includes: generating link information for re-examination item appointment based on the positive indicator in the physical examination result.

[0007] In some embodiments, generating at least one of consultation service link information and recommended product link information based on the abnormal indicator includes: generating offline outpatient appointment link information based on the abnormal indicator.

[0008] In some embodiments, the method further includes: establishing a connection with a doctor terminal of a corresponding department of an Internet hospital based on the abnormal indicator; extracting condition-related information from the physical examination results and sending it to the doctor terminal.

[0009] In some embodiments, the method further includes: extracting key information from the online consultation session and generating a medical record.

[0010] In some embodiments, generating at least one of consultation service link information and recommended product link information based on the abnormal indicator includes: calculating the purchase quantity of the recommended product based on the abnormal indicator; and generating the recommended product link information based on the purchase quantity.

[0011] In some embodiments, the method also includes: querying the chronic disease management plan corresponding to the disease risk information from a preset knowledge base; regularly notifying the user to undergo a physical examination to obtain the user's health status according to the chronic disease management plan; generating health questionnaire information based on the user's health status, and inputting the health questionnaire information into a disease risk model to predict disease risk information.

[0012] In the second aspect, an embodiment of the present disclosure provides a physical examination service data processing device, including: a diagnosis unit, configured to input abnormal indicators in the physical examination results into a pre-trained medical knowledge model, and output post-examination recommendation information for the doctor's diagnosis reference; a correction unit, configured to generate general examination recommendation information based on the doctor's modification operation on the post-examination recommendation information; an evaluation unit, configured to perform health status evaluation based on various indicators in the physical examination results to obtain health status information; a prediction unit, configured to input user questionnaire information into a disease risk model to predict disease risk information; a recommendation unit, configured to generate at least one of consultation service link information and recommended product link information based on the abnormal indicators; a generation unit, configured to generate a physical examination report based on the general examination recommendation information, the health status information, the disease risk information and the link information.

[0013] In some embodiments, the device also includes a training unit configured to: calculate the loss value of the medical knowledge model based on the difference between the post-examination recommendation information output by the medical knowledge model and the content modified by the doctor; repeat the following training steps until the loss value is less than a predetermined threshold: adjust the network parameters of the medical knowledge model according to the loss value; input the abnormal indicators into the adjusted medical knowledge model to obtain new post-examination recommendation information; calculate the loss value of the medical knowledge model based on the difference between the new post-examination recommendation information and the content modified by the doctor.

[0014] In some embodiments, the recommendation unit is further configured to generate link information for re-examination item appointment based on the positive indicators in the physical examination results.

[0015] In some embodiments, the recommendation unit is further configured to generate link information for offline outpatient appointments based on the abnormal indicators.

[0016] In some embodiments, the recommendation unit is further configured to: establish a connection with a doctor terminal of a corresponding department of the Internet hospital based on the abnormal indicators; extract disease-related information from the physical examination results and send it to the doctor terminal.

[0017] In some embodiments, the online service unit is further configured to extract key information from the online consultation session and generate a medical record.

[0018] In some embodiments, the recommendation unit is further configured to: calculate the purchase quantity of the recommended product based on the abnormality indicator; and generate recommended product link information based on the purchase quantity.

[0019] In some embodiments, the device also includes a chronic disease management unit, which is configured to: query the chronic disease management plan corresponding to the disease risk information from a preset knowledge base; regularly notify the user to undergo a physical examination to obtain the user's health status according to the chronic disease management plan; generate health questionnaire information based on the user's health status, and input the health questionnaire information into the disease risk model to predict disease risk information.

[0020] In a third aspect, an embodiment of the present disclosure provides an electronic device comprising: one or more processors; a storage device on which one or more computer programs are stored, wherein when the one or more computer programs are executed by the one or more processors, the one or more processors implement a method as described in any one of the first aspects.

[0021] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method as described in any one of the first aspects is implemented.

[0022] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Other features, objects and advantages of the present disclosure will become more apparent from a reading of the detailed description of non-limiting embodiments made with reference to the following drawings:

[0024] Figure 1a 、 1b is an exemplary system architecture diagram in which an embodiment of the present disclosure may be applied;

[0025] Figure 2 is a flow chart of an embodiment of a method for processing physical examination service data according to the present disclosure;

[0026] Figure 3 is a schematic diagram of an application scenario of the physical examination service data processing method according to the present disclosure;

[0027] Figure 4 is a structural diagram of an embodiment of a physical examination service data processing device according to the present disclosure;

[0028] Figure 5 It is a schematic diagram of the structure of a computer system of an electronic device suitable for implementing the embodiments of the present disclosure. DETAILED DESCRIPTION

[0029] The present disclosure will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are intended only to illustrate the relevant invention and are not intended to limit the invention. It should also be noted that, for ease of description, only portions relevant to the relevant invention are shown in the accompanying drawings.

[0030] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0031] The process of post-physical examination services is as follows Figure 1a As shown: 1) Collect user health data; 2) Build a health archive (basic information, behavioral psychology, health history, health examinations, medical and health records, etc.); 3) Train disease screening models; 4) Build a disease screening model library; 5) Output chronic disease management plans based on disease risk assessment results; 6) Provide health management recommendations (diet, sports camps, nutrition, sleep, medication guidance, etc.); 7) Improve health status.

[0032] The experience service provided by this application achieves the following goals: 1) Provide professional chronic disease management services (personalized chronic disease management plans, health services with full disease tracking, and scientific and accurate disease risk management); 2) Provide efficient telemedicine services (accurate visual health portraits, efficient doctor-patient links, and accurate specialist and disease services); 3) Provide accurate marketing recommendations (accurate population recommendations, customized insurance services, and comprehensive pharmaceutical marketing coverage).

[0033] The structure of the post-inspection service system using the experience service method of this application is as follows: Figure 1b The post-examination service system is a complex multi-terminal information system, involving intelligent algorithms, physical examination center systems, physical examination software systems, post-examination service systems, management systems, health record systems, and doctor report interpretation systems.

[0034] 1. Intelligent algorithm: intelligent post-examination recommendations (building a comprehensive knowledge base based on disease entry content).

[0035] 1) Doctor feedback: Based on the physical examination indicators, output doctor diagnosis feedback and build the entry database.

[0036] Solution Design: Build multiple medical knowledge bases, including "doctor feedback - diagnostic recommendations - interpretation techniques," and associate these knowledge bases with "positive indicators - abnormal results" (managed by doctors). The goal is to cover all "high-frequency positive indicators" in the knowledge base and implement them, building a comprehensive knowledge base based on disease terms.

[0037] Technology implementation: Call the GPT-4 interface: [Input parameter]: entry content; [Output parameter]: output the integrated content corresponding to the entry; completed through GPT-4's prompts and few-shot capabilities. First, through some QA tests, let GPT-4 generate cases on typical problems, including a small number of cases obtained from doctors. Then design complex prompts to allow GPT-4 to understand the task, give examples, and constrain the output content. After constraining the output, perform regular expression filtering to find the specific content of 6 high-frequency contents from a large text response).

[0038] For example: [Input] Fatty liver; [Output] Preliminary diagnosis, treatment recommendations, lifestyle guidance, positive data, emergency prevention, medical consultation guidance, review cycle, etc. If no content is found, the display will be empty.

[0039] [Preliminary diagnosis] Fatty liver is a disease characterized by fatty degeneration of hepatic parenchymal cells.

[0040]

Treatment recommendations

[0041] Lifestyle Guidance: It is recommended to adopt a healthy diet, reduce fat and sugar intake, increase the intake of vegetables, fruits and whole grains. Increase aerobic exercise, such as walking, cycling or swimming, three times a week for a total of more than 150 minutes.

[0042] [Emergency Prevention] If you experience jaundice or your liver function exceeds 2 times the normal value, please seek medical attention.

[0043] [Guidelines for consultation] If you experience fatigue, upper abdominal distension, loss of appetite, etc., please consult a gastroenterologist.

[0044] [Review cycle] It is recommended to perform liver function tests and liver ultrasound tests every 6 months to 1 year.

[0045] 2) Diagnostic recommendations: Through continuous summarization and accumulation into the diagnostic recommendation knowledge base, such as HPV positive and uterine fibroids

[0046] HPV positive: We recommend that you seek medical attention from a gynecologist and, if necessary, receive immunotherapy, antiviral therapy, and treatment for gynecological-related diseases (such as cervicitis). Follow up on changes in HPV status and retest for HPV every three months.

[0047] Uterine fibroids: We recommend visiting a gynecologist for further examination and treatment if necessary. Regular follow-up examinations are recommended. If you experience any compression symptoms, such as increased menstruation, vaginal bleeding, rapid tumor growth, abdominal pain, or frequent urination, consult a doctor promptly.

[0048] 3) Interpretation techniques: Through continuous summarization and accumulation into the diagnostic interpretation knowledge base, such as blood pressure.

[0049] [Blood Pressure Below Critical Limit] A blood pressure value below 90 / 60 mmHg is considered hypotension. Your blood pressure is *** mmHg, just below the critical limit. Low blood pressure is related to gender, age, weight, and genetics. Long-term, chronic hypotension can be asymptomatic, but may also cause dizziness, chest tightness, fatigue, and palpitations. If you experience these symptoms, you should improve your nutrition, eat more high-protein foods, and drink plenty of fluids to replenish blood volume. Be careful when changing position (especially squatting and standing) and after meals to avoid falls and injuries caused by hypotension. Check your blood pressure monthly.

[0050] 2. Physical Examination Center: Users enter the center for guided examination and undergo specialized examinations. After the examination, users are supported to view the physical examination report.

[0051] 3. Physical software system: After the physical examination, the doctor refers to the intelligent AI general inspection to generate general inspection recommendations, and finally generates an electronic report. The electronic report is pushed to the user for review and pushed to the health record for storage.

[0052] 4. Post-inspection service: display the general inspection conclusion, health status score, inspection results, comprehensive review suggestions, health suggestions, abnormal indicators, general inspection suggestions, etc.

[0053] 5. Health records: store health status (past medical examination reports, risk assessment data, health management data)

[0054] 6. Management side: Configure health service conversion (including department services, abnormal words, inspection items, recommended products)

[0055] 7. Doctor side: Doctors refer to the AI ​​intelligent general inspection suggestions and interpret the report (including physical examination data review, general inspection suggestions, attention to abnormal indicators, writing general inspection conclusions, generating a comprehensive physical examination report, and pushing it to the user side).

[0056] Continue to refer Figure 2, shows a process 200 of an embodiment of a method for processing physical examination service data according to the present disclosure. The method for processing physical examination service data includes the following steps:

[0057] Step 201: Input abnormal indicators in the physical examination results into a pre-trained medical knowledge model, and output post-examination recommendation information for the doctor's diagnosis reference.

[0058] In this embodiment, each indicator in the physical examination results is marked with a normal range, and indicators outside the normal range are considered abnormal. The medical knowledge model is a neural network model with human-computer interaction capabilities, such as GPT-4. Multiple medical knowledge bases are pre-built, including a "Physical Examination High-Frequency Disease Term Library" and a "Physical Examination Interpretation Knowledge Base." The medical knowledge model retrieves relevant knowledge from these medical knowledge bases to generate post-examination recommendations. Post-examination recommendations may include: preliminary diagnosis, treatment recommendations, lifestyle guidance, positive data, emergency prevention, consultation instructions, and follow-up intervals.

[0059] The "Prompt" in GPT-4 is a detailed and structured input information that allows GPT-4 to accurately understand the user's needs and generate high-quality responses for specific tasks or applications.

[0060] A prompt is a user's instruction or question to an AI. It serves as the bridge between the user and the AI. Just as a user's question or topic serves as the introductory element to a conversation with another person, a prompt similarly serves as the introductory element to a conversation with the AI.

[0061] "Few-shot" learning typically involves providing a few input-output pairs as examples in a prompt, then presenting a new input and asking the model to generate the corresponding output. These input-output pairs help the model understand the requirements of the task. This approach is inspired by the human learning ability, which often requires only a few examples to grasp new concepts or tasks.

[0062] Implementation steps:

[0063] 1. Clarify the task: Clarify what task GPT-4 should complete;

[0064] 2. Provide contextual keywords: Provide relevant keywords and examples to provide GPT-4 with a detailed map;

[0065] 3. Set the expected output and audience: Let GPT-4 know what conditions its answer needs to meet;

[0066] 4. Provide example questions: This can help the model gain a more comprehensive understanding of the scope of the task;

[0067] 5. One-click operation: copy and paste this information into GPT-4 and then view the output;

[0068] 6. Continuous Optimization: Based on the output results, continuously adjust them to meet the needs. Adjust the experimental content. For example, if the output content does not meet the expectations, you need to modify the experimental parameters, change the input parameters, or control the search conditions.

[0069] For example, [input] fatty liver; [output] preliminary diagnosis, treatment recommendations, lifestyle guidance, positive data, emergency prevention, medical consultation guidance, review cycle, etc. If no content is found, the display will be empty.

[0070] Step 202: Generate general examination recommendation information based on the doctor's modification operation on the post-examination recommendation information.

[0071] In this embodiment, the doctor needs to review the post-examination recommendation information generated by the medical knowledge model. If there is any incorrect content, it needs to be edited and modified. Only the doctor's modified content can be used as the general examination recommendation information.

[0072] Step 203: perform health status assessment based on various indicators in the physical examination results to obtain health status information.

[0073] In this embodiment, the health status is comprehensively evaluated based on the comprehensiveness of the physical examination items and any abnormal conditions found, and can be divided into three levels: excellent, good, and needs improvement.

[0074] [Excellent] The physical examination was basically normal, with no serious indicators. You can continue to maintain good living habits and have regular physical examinations.

[0075] [Good] There are a few abnormal indicators in this physical examination, which require immediate intervention and treatment, and adjustment of related lifestyle habits.

[0076] [To be improved] This physical examination showed multiple abnormal or serious indicators, which have an impact on the body system. Please follow the doctor's advice immediately and improve the abnormal indicators by adjusting your lifestyle habits.

[0077] Step 204: Input the user questionnaire information into the disease risk model to predict disease risk information.

[0078] In this embodiment, the disease risk model is a risk mapping table. Corresponding disease risk information can be found based on the user's completed health information questionnaire. For details on the disease risk model, please refer to the glossary below. The questionnaire may include: personal information (e.g., height, weight), health information (e.g., family medical history), lifestyle information (e.g., sleep duration, exercise habits), etc.

[0079] Step 205: Generate at least one of consultation service link information and recommended product link information based on the abnormality indicator.

[0080] In this embodiment, consultation services may include offline outpatient appointments, positive test re-examination appointments, and online internet consultations. The physical examination service system of this application provides a medical advice interface to provide consultation services. Simply click on the corresponding link to access the medical advice interface. It can also recommend products based on the user's physical condition, such as calcium supplements and massagers. A purchase link is generated for each recommended product, and the purchase can be made by simply clicking on the link.

[0081] Step 206: Generate a physical examination report based on the general examination recommendation information, health status information, disease risk information and link information.

[0082] In this embodiment, the physical examination report includes not only the physical examination results, but also lists the general examination recommendation information, health status information, disease risk information and link information. The generated electronic physical examination report can be pushed to the user terminal for the user to download.

[0083] The method provided by the above-mentioned embodiments of the present disclosure opens up the doctor-side system link, allowing doctors to output comprehensive medical advice and physical examination reports at one time, and using intelligent algorithms and knowledge bases to improve doctor efficiency. The content of the physical examination report is innovatively designed to construct content such as the general examination conclusion, examination results, comprehensive advice, and disease risk prediction. Through the doctor's general examination advice, an integrated service link based on abnormal indicators is constructed. A link is realized from positive abnormality -) online consultation -) online diagnosis -) improvement during the rehabilitation period -) long-term improvement.

[0084] In some optional implementations of this embodiment, the method further includes: calculating a loss value for the medical knowledge model based on the difference between the post-examination recommendation information output by the medical knowledge model and the doctor's revised content; repeating the following training steps until the loss value is less than a predetermined threshold: adjusting the network parameters of the medical knowledge model based on the loss value; inputting the abnormality indicator into the adjusted medical knowledge model to obtain new post-examination recommendation information; and calculating the loss value for the medical knowledge model based on the difference between the new post-examination recommendation information and the doctor's revised content. The doctor's revised content expands the comprehensive knowledge base based on the disease entry content, constructing multiple medical knowledge bases such as "doctor feedback-diagnosis advice-interpretation dialogue." This is equivalent to adding training samples to the medical knowledge model. The doctor's revised content is used as a supervisory label, and supervised training is performed by calculating a loss value based on the difference between the post-examination recommendation information output by the original model and the doctor's revised content. The loss value can be calculated based on the similarity between the two text segments, with the higher the similarity, the smaller the loss value. If the loss value does not converge to the predetermined threshold, the network parameters of the medical knowledge model are adjusted. The above training steps are repeated until the loss value is less than the predetermined threshold, resulting in a trained model. By retraining the medical knowledge model based on the newly added training samples, a medical knowledge model with better performance can be obtained.

[0085] In some optional implementations of this embodiment, the method further includes archiving and storing the physical examination results, the health status information, and the disease risk information, thereby providing users with cloud storage and viewing of health information, and helping users manage their health data more conveniently and scientifically.

[0086] In some optional implementations of this embodiment, generating at least one of a consultation service link and a recommended product link based on the abnormal indicator includes generating a link for re-examination appointments based on a positive indicator in the physical examination result. This link is output through the medical advice interface, and a user clicks on it to access the doctor-recommended re-examination items for the positive indicators, allowing the user to directly place an order for the re-examination and schedule the appointment.

[0087] In some optional implementations of this embodiment, generating at least one of a consultation service link and a recommended product link based on the abnormality indicator includes generating an offline clinic appointment link based on the abnormality indicator. This link is output through the medical advice interface. When a user clicks on the link, a clinic plus sign and doctor service pricing are displayed according to the configured content, allowing the user to directly schedule an appointment. The user can automatically locate first- and second-level departments and doctors.

[0088] In some optional implementations of this embodiment, the generation of at least one of consultation service link information and recommended product link information based on the abnormal indicators includes: establishing a connection with the doctor terminal of the corresponding department of the Internet hospital based on the abnormal indicators; extracting the condition-related information from the physical examination results and sending it to the doctor terminal. Output from the medical advice interface and match the consultation link by department ID. Connect to the Internet medical fast consultation capability, provide chief complaint information (condition / symptoms / patient duration / drugs taken, etc.), patient files (name / gender / age / triage department / physical examination report, etc.), users can directly ask questions (chief complaint → patient → triage card → bill of lading card → waiting for consultation → IM → end of consultation).

[0089] Chief complaint: Hello, I was diagnosed with *** and *** problems during my recent physical examination. Doctor, please help me answer them.

[0090] Department: Obtained from the doctor's interpretation interface.

[0091] Patient information: patientID (patient ID, subject to the interface requirements of Internet medical care).

[0092] Report: Report ID (subject to the interface requirements of Internet medical care).

[0093] Use the physical examination report ID + department ID for splicing to directly locate the first and second level departments, thereby improving triage efficiency.

[0094] In some optional implementations of this embodiment, the method further includes extracting key information from the online consultation session to generate a medical record. This helps doctors automatically generate medical records by extracting key information (such as user information, abnormal indicators, disease names, etc.) during the consultation session and performing OCR text recognition, thereby improving doctor service efficiency.

[0095] In some optional implementations of this embodiment, generating at least one of consultation service link information and recommended product link information based on the abnormality indicator includes: calculating the purchase quantity of the recommended product based on the abnormality indicator; and generating the recommended product link information based on the purchase quantity. Output is from the medical advice interface, and configuration information is obtained by associating the physical object name ID. Business operations configure related physical goods and category rankings, and users can directly purchase and place orders by clicking on the product link information without the user having to calculate the purchase quantity themselves. The purchase quantity is calculated based on the user's abnormality indicator. The worse the indicator, the longer the conditioning period and the more health products required.

[0096] In some optional implementations of this embodiment, the method further includes: querying a chronic disease management plan corresponding to the disease risk information from a preset knowledge base; regularly notifying the user to undergo a physical examination according to the chronic disease management plan to obtain the user's health status and generate health questionnaire information based on the user's health status, and inputting the health questionnaire information into a disease risk model to predict disease risk information. For example, regular reminders can be made to make appointments for physical examinations, and changes in abnormal indicators can be recorded. If they deteriorate, prompt medical treatment can be sought in a timely manner. Health questionnaire information for abnormal indicators after changes can also be generated based on the user's health status, and then disease risk information can be predicted through a disease risk model. Tracking and management of chronic diseases can be achieved.

[0097] Continue to see Figure 3 , Figure 3 This is a schematic diagram of an application scenario of the physical examination service data processing method according to this embodiment. Figure 3 In the application scenario, the physical examination report with abnormal indicators is listed and the instructions for using the physical examination report are given. The contents of the physical examination report mainly include:

[0098] 1. Health status: Displays health status by big data classification (needs improvement, good, excellent).

[0099] Use the physical examination report ID to obtain health status classification and health score comparison values ​​for different groups. Health status is a comprehensive evaluation based on the comprehensiveness of the physical examination items and any abnormalities found, and is divided into three levels. Health status is based on the current physical examination report and sets various status targets (inspection items and abnormal indicator data ratios) according to specified rules. Dynamic adjustments can be made based on operational goals.

[0100] [Excellent] The physical examination was basically normal, with no serious indicators. You can continue to maintain good living habits and have regular physical examinations.

[0101] [Good] There are a few abnormal indicators in this physical examination, which require immediate intervention and treatment, and adjustment of related lifestyle habits.

[0102] [To be improved] This physical examination showed multiple abnormal or serious indicators, which have an impact on the body system. Please follow the doctor's advice immediately and improve the abnormal indicators by adjusting your lifestyle habits.

[0103] [Percentage of peers] Calculate the proportion of health values ​​among the total sample size of peers.

[0104] [Report Comparison] If there is a previous physical examination, the increase and decrease in the number of normal and abnormal indicators will be recorded.

[0105] [Report List] Full report of the physical examination person, hepatitis B report, and extension report. Click to view details.

[0106] [Abnormal Tips] This physical examination has [***] abnormalities. Pay special attention to abnormal indicators such as [***, ***]. (*** is taken from the abnormal indicator data and indicator names in the physical examination report)

[0107] [Normal reminder] This physical examination included [***] items in total, and no abnormalities were found. Please continue to maintain good living habits and have regular annual physical examinations.

[0108] 2. General inspection conclusion: including the comprehensive review opinion of the general inspection on the doctor's side.

[0109] [General Examination Conclusion] Displays the structured data of the general examination conclusion of the doctor's physical examination report (indicator name + indicator result + doctor's suggestion). The data comes from the physical examination indicator knowledge base built in the doctor's general examination system.

[0110] [Health Status] Based on the current physical examination report, various status targets (inspection items and abnormal indicator data ratio) are set according to specified rules, and can be dynamically adjusted according to operational goals.

[0111] 3. Inspection results: including abnormal indicators and all indicators.

[0112] [Abnormal Indicators]: The number of abnormal indicators. It is divided into the following categories: 1) Numerical range (normal range is marked in the legend); 2) Percentage (the indicator needs to be configured to the corresponding type); 3) Positive and negative (the default normal range is negative, and the value outside the range is positive); 4) Text

[0113] [All indicators] Organize information by department and sub-item of the physical examination, display the number of department abnormalities, and display the department summary (abnormalities are displayed in red). If it is blank, it will not be displayed.

[0114] 4. Comprehensive recommendations: including offline medical treatment, online consultation, positive re-examination, physical recommendations, and health management.

[0115] [Offline Medical Treatment] Output from the medical advice interface, displayed according to the configuration content, and the outpatient plus sign shows the doctor's service price. Users can directly make an outpatient appointment. Can automatically locate the first and second level departments and doctors.

[0116] [Online Consultation] Output from the medical advice interface and match consultation links by department ID. Connected to the rapid consultation capabilities of online medical services, it provides chief complaint information (condition / symptoms / patient duration / medications taken, etc.) and patient profile (name / gender / age / triage department / physical examination report, etc.). Users can directly consult (chief complaint → patient → triage card → bill of lading card → waiting for consultation → IM → end consultation).

[0117] Chief complaint: Hello, I was diagnosed with *** and *** problems during my recent physical examination. Doctor, please help me answer them.

[0118] Department: Obtained from the doctor's interpretation interface.

[0119] Patient information: patientID (patient ID, subject to the interface requirements of Internet medical care).

[0120] Report: Report ID (subject to the interface requirements of Internet medical care).

[0121] Use the physical examination report ID + department ID for splicing to directly locate the first and second level departments, thereby improving triage efficiency.

[0122] [Positive re-examination] Output from the medical advice interface and call the positive indicator re-examination items recommended by the doctor. Users can directly complete the re-examination order and appointment.

[0123] [Physical Product Recommendations] Output from the medical recommendation interface and associate configuration information by physical product name ID. Business operations configure related physical products and category rankings. Users can click on a product to directly purchase it.

[0124] [Special Note] Service / product recommendations will be made in combination with abnormal indicators in the current physical examination report. If the physical examination report shows high blood pressure and high blood lipids, the comprehensive recommendations are as follows: 1) Push the outpatient plus sign of the related department to make an appointment; 2) If the physical examination report shows high uric acid, then the re-examination items of routine urine and blood tests will be listed in the positive re-examination, and re-examination discounts will be supported; 3) For hypertension and hyperlipidemia, the patient information and indicator status will be used as the main complaint to request Internet medical AI intelligent triage, and the corresponding cardiology online consultation will be brought out to efficiently complete the division of departments and intelligent allocation of doctors; 4) For irregular heartbeat, cardiovascular and other nourishing health products can be recommended.

[0125] 5. Risk prediction: Risk prediction is divided into unassessed and assessed states.

[0126] [Solution Design] Listen for event messages generated by reports, query the questionnaire result ID based on the report ID, and use big data to perform disease risk model analysis. This automatically analyzes the user's disease risk while issuing a physical examination report. The analysis results display the risk level, assessment details, disease risk list, and the risk level of each disease.

[0127] [Not Evaluated] Demonstrate disease screening benefits, comprehensive screening, and specialized examinations. Supplement lifestyle habits and medical history to predict high-risk diseases.

[0128] [Assessed] displays the disease risk level assessment and comprehensive improvement suggestions. [0-50] [50-100] [100 and above] correspond to low, medium, and high, respectively.

[0129] [Risk Results] Displays comprehensive risk level, risk score, corresponding population distribution, and risk assessment time

[0130] [Risk Level] All, high risk, medium risk, low risk, cannot be assessed.

[0131] [Risk Distribution] Displays the risk level information of peers and calculates the risk of peers based on risk values.

[0132]

Disease Risk

[0133]

Improvement Suggestions

[0134] Further references Figure 4 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a physical examination service data processing device. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0135] like Figure 4 As shown, the physical examination service data processing device 400 of this embodiment includes: a diagnosis unit 401, a correction unit 402, an evaluation unit 403, a prediction unit 404, a recommendation unit 405, and a generation unit 406. The diagnosis unit 401 is configured to input abnormal indicators in the physical examination results into a pre-trained medical knowledge model and output post-examination recommendation information for the doctor's diagnosis reference; the correction unit 402 is configured to generate general examination recommendation information based on the doctor's modification operation on the post-examination recommendation information; the evaluation unit 403 is configured to perform health status assessment based on various indicators in the physical examination results to obtain health status information; the prediction unit 404 is configured to input user questionnaire information into a disease risk model to predict disease risk information; the recommendation unit 405 is configured to generate at least one of consultation service link information and recommended product link information based on the abnormal indicators; and the generation unit 406 is configured to generate a physical examination report based on the general examination recommendation information, the health status information, the disease risk information, and the link information.

[0136] In this embodiment, the specific processing of the diagnosis unit 401, the correction unit 402, the evaluation unit 403, the prediction unit 404, the recommendation unit 405, and the generation unit 406 of the physical examination service data processing device 400 can be referred to. Figure 2 This corresponds to steps 201-206 in the embodiment.

[0137] In some optional implementations of this embodiment, the device also includes a training unit, configured to: calculate the loss value of the medical knowledge model based on the difference between the post-examination recommendation information output by the medical knowledge model and the content modified by the doctor; repeat the following training steps until the loss value is less than a predetermined threshold: adjust the network parameters of the medical knowledge model according to the loss value; input the abnormal indicators into the adjusted medical knowledge model to obtain new post-examination recommendation information; calculate the loss value of the medical knowledge model based on the difference between the new post-examination recommendation information and the content modified by the doctor.

[0138] In some optional implementations of this embodiment, the recommendation unit is further configured to generate link information for re-examination item reservation based on the positive indicators in the physical examination results.

[0139] In some optional implementations of this embodiment, the recommendation unit is further configured to generate link information for offline outpatient appointments based on the abnormality indicator.

[0140] In some optional implementations of this embodiment, the recommendation unit is further configured to: establish a connection with the doctor terminal of the corresponding department of the Internet hospital based on the abnormal indicators; extract disease-related information from the physical examination results and send it to the doctor terminal.

[0141] In some optional implementations of this embodiment, the recommendation unit is further configured to extract key information from the online consultation session and generate a medical record.

[0142] In some optional implementations of this embodiment, the recommendation unit is further configured to: calculate the purchase quantity of the recommended product based on the abnormality indicator; and generate recommended product link information based on the purchase quantity.

[0143] In some optional implementations of this embodiment, the device also includes a chronic disease management unit, which is configured to: query the chronic disease management plan corresponding to the disease risk information from a preset knowledge base; regularly notify the user to undergo a physical examination to obtain the user's health status according to the chronic disease management plan; generate health questionnaire information based on the user's health status, and input the health questionnaire information into the disease risk model to predict disease risk information.

[0144] Glossary

[0145] 1. Disease risk model:

[0146]

[0147] 2. Physical examination high-frequency disease term library (using GPT4, taking fatty liver and obesity as examples):

[0148]

[0149]

[0150] 3. Physical Examination Interpretation Knowledge Base (General Examination Examples):

[0151]

[0152] It should be noted that the collection, collection, updating, analysis, processing, use, transmission, and storage of user personal information involved in the technical solutions disclosed herein all comply with relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken with respect to user personal information to prevent unauthorized access to user personal information data and to safeguard the security of user personal information, network security, and national security.

[0153] According to an embodiment of the present disclosure, the present disclosure further provides an electronic device and a readable storage medium.

[0154] An electronic device comprises: one or more processors; a storage device storing one or more computer programs, wherein when the one or more computer programs are executed by the one or more processors, the one or more processors implement the method described in process 200.

[0155] A computer-readable medium stores a computer program thereon, wherein the computer program implements the method described in process 200 when executed by a processor.

[0156] Figure 5 A schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0157] like Figure 5As shown, the device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. Various programs and data required for the operation of the device 500 can also be stored in the RAM 503. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0158] Various components in device 500 are connected to I / O interface 505, including: an input unit 506, such as a keyboard, mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a magnetic disk, optical disk, etc.; and a communication unit 509, such as a network card, modem, wireless communication transceiver, etc. The communication unit 509 allows device 500 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0159] The computing unit 501 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as the road zone planning method. For example, in some embodiments, the road zone planning method can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as the storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the road zone planning method described above can be performed. Alternatively, in other embodiments, the computing unit 501 can be configured to perform the road zone planning method by any other suitable means (e.g., by means of firmware).

[0160] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0161] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0162] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, 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 of the foregoing.

[0163] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0164] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0165] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact via a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a server in a distributed system or a server integrated with blockchain. The server may also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology. The server may be a server in a distributed system or a server integrated with blockchain. The server may also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology.

[0166] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0167] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for processing physical examination service data, comprising: Abnormal indicators in the physical examination results are input into the pre-trained medical knowledge model, and post-examination recommendation information is output for the doctor's diagnosis reference; Generate general examination recommendation information based on the doctor's modification operation on the post-examination recommendation information; Conduct health status assessment based on various indicators in the physical examination results to obtain health status information; Input user questionnaire information into the disease risk model to predict disease risk information; generating at least one of consultation service link information and recommended product link information according to the abnormality indicator; A physical examination report is generated based on the general examination recommendation information, the health status information, the disease risk information and the link information.

2. The method according to claim 1, wherein The method further comprises: The loss value of the medical knowledge model is calculated based on the difference between the post-examination recommendation information output by the medical knowledge model and the content modified by the doctor; the following training steps are repeated until the loss value is less than a predetermined threshold: the network parameters of the medical knowledge model are adjusted according to the loss value; the abnormal indicators are input into the adjusted medical knowledge model to obtain new post-examination recommendation information; the loss value of the medical knowledge model is calculated based on the difference between the new post-examination recommendation information and the content modified by the doctor.

3. The method according to claim 1, wherein Generating at least one of the consultation service link information and the recommended product link information according to the abnormality indicator includes: Based on the positive indicators in the physical examination results, link information for re-examination item reservation is generated.

4. The method according to claim 1, wherein Generating at least one of the consultation service link information and the recommended product link information according to the abnormality indicator includes: Generate offline outpatient appointment link information based on the abnormal indicators.

5. The method according to claim 1, wherein Generating at least one of the consultation service link information and the recommended product link information according to the abnormality indicator includes: Establishing a connection with a doctor terminal of a corresponding department of the Internet hospital based on the abnormal indicator; The disease-related information is extracted from the physical examination results and sent to the doctor terminal.

6. The method according to claim 5, wherein: The method further comprises: Extract key information from online consultation conversations and generate medical records.

7. The method according to claim 1, wherein Generating at least one of the consultation service link information and the recommended product link information according to the abnormality indicator includes: Calculate the purchase quantity of the recommended product based on the abnormal indicator; Generate recommended product link information based on the purchase quantity.

8. The method according to claim 1, wherein The method further comprises: Querying the chronic disease management plan corresponding to the disease risk information from a preset knowledge base; Notify the user to undergo a physical examination regularly according to the chronic disease management plan to obtain the user's health status; Health questionnaire information is generated according to the health status of the user, and the health questionnaire information is input into a disease risk model to predict disease risk information.

9. A physical examination service data processing device, comprising: The diagnosis unit is configured to input abnormal indicators in the physical examination results into a pre-trained medical knowledge model and output post-examination recommendation information for the doctor's diagnosis reference; a correction unit configured to generate general examination recommendation information according to the doctor's modification operation on the post-examination recommendation information; An evaluation unit is configured to evaluate the health status based on various indicators in the physical examination results to obtain health status information; a prediction unit configured to input the user questionnaire information into a disease risk model to predict disease risk information; a recommendation unit configured to generate at least one of consultation service link information and recommended product link information according to the abnormality indicator; A generating unit is configured to generate a physical examination report based on the general examination recommendation information, the health status information, the disease risk information and the link information.

10. An electronic device comprising: one or more processors; a storage device having one or more computer programs stored thereon, When the one or more computer programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 8.

11. A computer-readable medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images