Intelligent pre-examination triage method and system based on digital human

Abstract

The invention belongs to the technical field of online medical treatment, and particularly relates to an intelligent pre-examination triage method and system based on a digital person, and the method comprises the steps: obtaining the information of a patient seeing a doctor based on the digital person; processing the obtained doctor-seeing patient information to obtain doctor-seeing patient key information; carrying out deep classification analysis on the obtained key information of the doctor-seeing patient, and judging the disease of the doctor-seeing patient; predicting the disease of the doctor-seeing patient in real time according to the obtained judgment result of the disease of the doctor-seeing patient; and based on the real-time prediction result of the disease of the patient seeing the doctor, performing recommendation of a doctor-seeing department, and completing intelligent pre-examination triage. According to the invention, based on a digital human technology in which a virtual medical assistant and a machine learning algorithm are arranged, while rapid and accurate pre-examination triage is realized through human-computer interaction, humanized and emotional support is provided for a doctor-seeing patient, questions are answered and puzzled for the doctor-seeing patient, and the experience feeling of the doctor-seeing patient is improved.

Description

Technical Field

[0001] The present invention belongs to the field of online medical technology, and specifically relates to an intelligent pre-examination and triage method and system based on digital humans. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] When patients visit a hospital for treatment, they must undergo pre-examination and triage registration based on their condition to improve efficiency. However, during this process, patients may be assigned to the wrong department due to unclear descriptions of their condition, resulting in inefficient treatment and delayed treatment. Therefore, pre-examination and triage is a crucial aspect of daily hospital operations. Convenient and efficient patient care can significantly enhance the patient experience.

[0004] According to the inventors' understanding, existing pre-examination and triage generally adopts manual triage or self-service consultation by patients based on the platform. Manual triage requires a lot of manpower, and the differences in hospital levels and medical staff levels will affect the accuracy of manual triage; when patients conduct self-service consultations based on the platform, they provide their own symptoms and information through the online platform, and the online platform provides preliminary medical advice to the patients to achieve pre-examination and triage. However, self-service consultation requires the use of a certain intelligent algorithm model, and the algorithm used in the online platform directly affects the accuracy and efficiency of pre-examination and triage. At the same time, existing online platforms have the defects of long pre-examination and triage time, poor effect in handling complex diseases, focusing on triage rather than on providing initial solutions to patients' doubts, and lacking humanization and emotional support. Summary of the Invention

[0005] In order to solve the above problems, the present invention proposes an intelligent pre-examination and triage method and system based on digital humans. Based on the digital human technology with a built-in virtual medical assistant and machine learning algorithm, it realizes rapid and accurate pre-examination and triage through human-computer interaction, while providing humanized and emotional support to patients, answering their questions and solving their doubts, and improving their experience.

[0006] According to some embodiments, the first solution of the present invention provides an intelligent pre-examination and triage method based on digital humans, which adopts the following technical solutions:

[0007] An intelligent pre-examination and triage method based on digital humans, comprising:

[0008] Obtaining patient information based on digital humans;

[0009] Process the acquired patient information to obtain key patient information;

[0010] Conduct in-depth classification analysis on the key information of the patients to determine their symptoms;

[0011] According to the obtained judgment results of the patient's symptoms, the patient's disease is predicted in real time;

[0012] Recommendations to treatment departments are made based on the real-time prediction results of patients’ diseases, completing intelligent pre-examination and triage.

[0013] As a further technical limitation, through the human-computer interaction between the patient and the digital human, the patient's speech information is extracted, and the key information of the patient's speech information is analyzed through the digital human's voice recognition.

[0014] As a further technical limitation, the key information of the patient obtained includes at least the patient's symptoms, medical history, medical treatment records and historical medical records.

[0015] As a further technical limitation, the patient's disease category is identified based on the key information of the patient obtained, and combined with the feedback from medical staff, new patient data and diagnosis results are collected, the disease category identification is updated, and the judgment of the patient's disease is completed.

[0016] As a further technical limitation, in the process of real-time prediction of the patient's disease, the patient's speech information is obtained through human-computer interaction between the patient and the digital human, the patient's key information is obtained based on the digital human's voice recognition and analysis, and the patient's symptoms are obtained through classification and analysis of the patient's key information; the patient's disease category is identified based on the obtained patient's symptoms, and the severity of the disease is evaluated; combined with the feedback from medical staff, the patient's disease category identification is continuously optimized and updated to complete the real-time prediction of the patient's disease.

[0017] As a further technical limitation, based on the real-time prediction results of the patient's disease, combined with the medical knowledge base containing the correlation between different diseases and corresponding departments, the real-time prediction results of the patient's disease are analyzed by using a recommendation model of a machine learning recommendation algorithm to obtain matching relevant treatment departments; by analyzing the case data, historical treatment records and real-time feedback from medical staff in the medical knowledge base, the recommendation model is optimized, and the treatment department is recommended to the patient, completing intelligent pre-examination and triage.

[0018] According to some embodiments, the second solution of the present invention provides an intelligent pre-examination and triage system based on digital humans, which adopts the following technical solutions:

[0019] An intelligent pre-examination and triage system based on digital humans, comprising:

[0020] An acquisition module configured to acquire patient information based on a digital human;

[0021] An extraction module is configured to process the acquired patient information to obtain key patient information;

[0022] A judgment module is configured to perform in-depth classification analysis on the key information of the patient and judge the condition of the patient;

[0023] A prediction module is configured to predict the disease of the patient in real time based on the obtained judgment result of the patient's disease;

[0024] The triage module is configured to recommend the treatment department based on the real-time prediction results of the patient's disease, and complete intelligent pre-examination triage.

[0025] According to some embodiments, a third solution of the present invention provides a computer-readable storage medium, which adopts the following technical solution:

[0026] A computer-readable storage medium stores a program, which, when executed by a processor, implements the steps of the intelligent pre-examination and triage method based on digital humans as described in the first solution of the present invention.

[0027] According to some embodiments, a fourth solution of the present invention provides an electronic device, which adopts the following technical solution:

[0028] An electronic device comprises a memory, a processor and a program stored in the memory and running on the processor. When the processor executes the program, the steps of the intelligent pre-examination and triage method based on digital human as described in the first solution of the present invention are implemented.

[0029] According to some embodiments, a fifth solution of the present invention provides a computer program product, which adopts the following technical solution:

[0030] A computer program product includes software code, wherein the program in the software code executes the steps of the intelligent pre-examination and triage method based on digital human as described in the first solution of the present invention.

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] The present invention uses digital human technology to collect and analyze large amounts of medical data to provide more accurate, reliable and efficient triage suggestions, shorten consultation time, and help patients receive appropriate diagnosis and treatment as early as possible; based on human-computer interactive questions and answers, it can better answer patients' initial questions and help them understand their own symptoms, save time for communication between doctors and patients, reduce medical pressure, rationally allocate medical resources, improve the consultation environment, improve hospital operating efficiency, and reduce costs; use good digital human images to interact with patients, communicate with patients in a friendly and understandable manner, provide clear explanations and suggestions, and offer emotional support, thereby improving the overall experience of patients; digital humans can convey health knowledge to patients in simple and easy-to-understand language, provide prevention and health care advice, and help improve their awareness of their own health. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The drawings constituting a part of the specification of this embodiment are used to provide a further understanding of this embodiment. The schematic embodiments and descriptions of this embodiment are used to explain this embodiment and do not constitute an improper limitation on this embodiment.

[0034] Figure 1 This is a flow chart of the intelligent pre-examination and triage method based on digital human in the first embodiment of the present invention;

[0035] Figure 2 This is a structural block diagram of the intelligent pre-examination and triage system based on digital human in the second embodiment of the present invention. DETAILED DESCRIPTION

[0036] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0037] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present application belongs.

[0038] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.

[0039] In the absence of conflict, the embodiments of the present invention and the features thereof may be combined with each other.

[0040] Example 1

[0041] The first embodiment of the present invention introduces an intelligent pre-examination and triage method based on digital humans.

[0042] like Figure 1 The intelligent pre-examination and triage method based on digital human shown in the figure includes:

[0043] Obtaining patient information based on digital humans;

[0044] Process the acquired patient information to obtain key patient information;

[0045] Conduct in-depth classification analysis on the key information of the patients to determine their symptoms;

[0046] According to the obtained judgment results of the patient's symptoms, the patient's disease is predicted in real time;

[0047] Recommendations to treatment departments are made based on the real-time prediction results of patients’ diseases, completing intelligent pre-examination and triage.

[0048] As one or more implementation methods, in the process of obtaining patient information, a virtual medical assistant is used in combination with the human-computer interaction interface of a digital human. The digital human simulates medical staff to interact with the patient (for example, voice communication, inputting information on the screen, etc.) and collects the patient's medical information to ensure the accuracy, completeness and consistency of the patient information obtained by the digital human.

[0049] It should be noted that in the process of obtaining patient information based on digital humans, medical information such as medical records of patients from other hospitals that have reached cooperation and information sharing with the patient's current hospital and medical records in stores can be obtained. However, it is impossible to obtain various medical information from hospitals that have not reached cooperation and information sharing with the patient's current hospital.

[0050] As one or more implementation methods, natural language processing and speech recognition technology are used to process the obtained patient information. The specific process includes the following steps: converting the patient's voice input into text through speech recognition technology; then using the word segmentation algorithm in natural language processing technology to segment the text and decompose the sentences into independent words or phrases; using named entity recognition technology to identify medical-related entities from the segmented text, such as symptoms, medical history, drug names, etc.; on this basis, using part-of-speech tagging and syntactic analysis technology to parse the sentence structure and extract key information; through a pre-trained medical knowledge base and keyword matching algorithm, the extracted key information is verified to ensure the accuracy of the keywords, thereby obtaining the key information of the patient; to ensure accurate analysis of the patient's words and effective extraction of key information.

[0051] In this embodiment, the obtained key information of the patient includes at least the patient's symptoms, medical history, medical treatment records and historical medical records.

[0052] As one or more implementation methods, advanced machine learning algorithms such as deep learning models, support vector machines, random forests, clustering, and ensemble learning are used, and deep learning algorithms (convolutional neural networks, recurrent neural networks, etc.) and machine learning models (support vector machines, decision trees, random forests, etc.) are used to perform feature extraction and classification analysis on the processed data. The patient's data is predicted in real time through the trained model, that is, information such as the human body system to which the disease belongs, the cause, severity, stage, infectiousness, and mode of transmission are given.

[0053] To improve triage accuracy, the system continuously optimizes and learns through positive and negative feedback from physicians on disease predictions, model evaluation, and hyperparameter adjustment. The specific process is as follows: First, the system collects a large amount of patient data, including symptoms, medical history, and test results, to train an initial disease prediction model. When a patient uses the system for pre-examination triage, the system predicts the disease based on the model and recommends a medical department. Physicians verify the predictions after the consultation and provide positive and negative feedback. The system records and categorizes this feedback, with positive feedback strengthening the model's predictive capabilities and negative feedback triggering further training. The system regularly evaluates model metrics such as precision, recall, and F1 score, and automatically adjusts the model's hyperparameters based on the evaluation results, selecting the optimal parameter combination through methods such as grid search, random search, or Bayesian optimization. After collecting a certain amount of feedback data, the system periodically retrains the model, continuously updating the model parameters using the latest patient data and physician feedback to improve its accuracy. During retraining, the system employs cross-validation techniques to ensure the model's generalization ability to new data. After a consultation, doctors provide detailed feedback through the system interface, including reasons for correct diagnoses and misdiagnoses. This feedback is categorized and stored for use in training and adjusting the model, as well as error analysis to identify weaknesses. Furthermore, the system's medical knowledge base is continuously updated based on doctor feedback and new medical research, ensuring that predictions remain consistent with the latest medical advances. Through these steps, the system continuously learns and optimizes, improving the accuracy of disease prediction and triage, providing medical staff with a more scientific basis for preliminary diagnoses and ensuring that patients receive timely and accurate diagnosis and treatment.

[0054] In one or more implementation modes, based on a medical knowledge base, the system uses a trained model to make real-time predictions on patient data, identify possible disease categories, and evaluate their severity, etiology, infectiousness, and other characteristics.

[0055] As one or more implementation methods, based on the medical knowledge base, the system uses machine learning recommendation algorithms such as association rules, collaborative filtering, matrix decomposition, clustering, knowledge graphs, etc. to analyze the patient's disease prediction results, match the most relevant treatment department, and complete intelligent pre-examination and triage.

[0056] It should be noted that the digital human used in this embodiment utilizes access control, identity authentication and authorization, data anonymization, data decryption, and encryption technologies to ensure the privacy and security of patient data. The specific process is as follows: First, the system implements a strict access control policy, allowing only authorized users to access patient data and recording and monitoring each access request. The identity authentication process uses multi-factor authentication (password, facial recognition, etc.) to ensure that only legitimate users can access the system. This protects patients' personal information from unauthorized access. Second, data is encrypted using the Advanced Encryption Standard during storage and transmission to ensure data security at all stages. Third, to further protect privacy, the system anonymizes the data, replacing or removing personal identifying information (such as name and ID number), while ensuring that the data remains usable for analysis and processing. In addition, data decryption technology is applied to sensitive data to ensure that even if the data is intercepted, unauthorized personnel cannot interpret it. Fifth, the system also conducts regular security audits and vulnerability scans to promptly identify and remediate potential security issues. All of these measures combine to form a multi-layered security protection system, ensuring that patient information remains highly confidential throughout the entire processing process.

[0057] It should be noted that this embodiment can provide rich user education and health management information, so that patients can fully understand their own health status; the system uses the SMS service provider to send text messages, and automatically sends reminder text messages to patients according to a preset schedule to implement regular health reminders, promote patients to actively participate in health management, and realize the medical concept of prevention first.

[0058] This embodiment uses digital human technology to collect and analyze large amounts of medical data to provide more accurate, reliable, and efficient triage recommendations, shorten consultation time, and help patients receive appropriate diagnosis and treatment as early as possible; based on human-computer interactive question-and-answer sessions, it can better answer patients' initial questions and help them understand their symptoms, saving time for doctor-patient communication, alleviating medical pressure, rationally allocating medical resources, improving the consultation environment, increasing hospital operating efficiency, and reducing costs; using a good digital human image to interact with patients, the digital human communicates with patients in a friendly and understandable manner, providing clear explanations and suggestions, and offering emotional support, thereby improving the overall patient experience; the digital human can convey health knowledge to patients in simple and easy-to-understand language, provide preventive and health care advice, and help improve their awareness of their own health.

[0059] Example 2

[0060] The second embodiment of the present invention introduces an intelligent pre-examination and triage system based on digital humans.

[0061] like Figure 2 The intelligent pre-examination and triage system based on digital human shown in the figure includes:

[0062] An acquisition module configured to acquire patient information based on a digital human;

[0063] An extraction module is configured to process the acquired patient information to obtain key patient information;

[0064] A judgment module is configured to perform in-depth classification analysis on the key information of the patient and judge the condition of the patient;

[0065] A prediction module is configured to predict the disease of the patient in real time based on the obtained judgment result of the patient's disease;

[0066] The triage module is configured to recommend the treatment department based on the real-time prediction results of the patient's disease, and complete intelligent pre-examination triage.

[0067] The detailed steps are the same as those of the intelligent pre-examination and triage method based on digital humans provided in Example 1, and will not be repeated here.

[0068] Example 3

[0069] A third embodiment of the present invention provides a computer-readable storage medium.

[0070] A computer-readable storage medium stores a program, which, when executed by a processor, implements the steps of the intelligent pre-examination and triage method based on digital humans as described in the first embodiment of the present invention.

[0071] The detailed steps are the same as those of the intelligent pre-examination and triage method based on digital humans provided in Example 1, and will not be repeated here.

[0072] Example 4

[0073] A fourth embodiment of the present invention provides an electronic device.

[0074] An electronic device includes a memory, a processor, and a program stored in the memory and running on the processor. When the processor executes the program, the steps of the intelligent pre-examination and triage method based on digital human as described in Example 1 of the present invention are implemented.

[0075] The detailed steps are the same as those of the intelligent pre-examination and triage method based on digital humans provided in Example 1, and will not be repeated here.

[0076] Example 5

[0077] A fifth embodiment of the present invention provides a computer program product.

[0078] A computer program product includes software code, wherein the program in the software code executes the steps of the intelligent pre-examination and triage method based on digital human as described in the first embodiment of the present invention.

[0079] The detailed steps are the same as those of the intelligent pre-examination and triage method based on digital humans provided in Example 1, and will not be repeated here.

[0080] The above description is merely a preferred embodiment of this embodiment and is not intended to limit this embodiment. Those skilled in the art will readily appreciate that this embodiment may be modified and varied in various ways. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of this embodiment shall be within the scope of protection of this embodiment.

Claims

1. An intelligent pre-examination and triage method based on digital human, characterized in that: include: Obtaining patient information based on digital humans; Process the acquired patient information to obtain key patient information; Conduct in-depth classification analysis on the key information of the patients to determine their symptoms; According to the obtained judgment results of the patient's symptoms, the patient's disease is predicted in real time; Recommendations to treatment departments are made based on the real-time prediction results of patients’ diseases, completing intelligent pre-examination and triage.

2. The intelligent pre-examination and triage method based on digital human as described in claim 1, characterized in that: Through human-computer interaction between the patient and the digital human, the patient's speech information is extracted, and the key words of the patient's speech information are analyzed through the digital human's voice recognition to obtain the patient's key information.

3. The intelligent pre-examination and triage method based on digital human as described in claim 1, characterized in that: The key information of the patient obtained includes at least the patient's symptoms, medical history, medical treatment records and historical medical records.

4. The intelligent pre-examination and triage method based on digital human as described in claim 1, characterized in that: Based on the key information of the patients obtained, the disease categories of the patients are identified. Combined with the feedback from medical staff, new patient data and diagnosis results are collected, the disease category identification is updated, and the judgment of the disease of the patients is completed.

5. The intelligent pre-examination and triage method based on digital human as described in claim 1, characterized in that: In the process of real-time prediction of patients' diseases, the patient's speech information is obtained through human-computer interaction between the patient and the digital human, and the patient's key information is obtained based on the digital human's speech recognition and analysis. The patient's symptoms are obtained through classification analysis of the patient's key information; the patient's disease category is identified based on the obtained patient's symptoms, and the severity of the disease is assessed; the patient's disease category identification is continuously optimized and updated in combination with the feedback from medical staff to complete the real-time prediction of the patient's disease.

6. The intelligent pre-examination and triage method based on digital human as described in claim 1, characterized in that: Based on the real-time prediction results of the patients' diseases, combined with the medical knowledge base containing the correlation between different diseases and corresponding departments, the recommendation model of the machine learning recommendation algorithm is used to analyze the real-time prediction results of the patients' diseases and obtain matching relevant treatment departments; by analyzing the case data, historical treatment records and real-time feedback from medical staff in the medical knowledge base, the recommendation model is optimized, and treatment departments are recommended to patients, completing intelligent pre-examination and triage.

7. An intelligent pre-examination and triage system based on digital human, characterized by: include: An acquisition module configured to acquire patient information based on a digital human; An extraction module is configured to process the acquired patient information to obtain key patient information; A judgment module is configured to perform in-depth classification analysis on the key information of the patient and judge the condition of the patient; A prediction module is configured to predict the disease of the patient in real time based on the obtained judgment result of the patient's disease; The triage module is configured to recommend the treatment department based on the real-time prediction results of the patient's disease, and complete intelligent pre-examination triage.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the intelligent pre-examination and triage method based on digital human as described in any one of claims 1 to 6 are implemented.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the program, the steps of the intelligent pre-examination and triage method based on digital human as described in any one of claims 1 to 6 are implemented.

10. A computer program product comprising software code, characterized in that The program in the software code executes the steps of the intelligent pre-examination and triage method based on digital human according to any one of claims 1 to 6.

Images