Disease consultation system based on big data

Abstract

The invention relates to the technical field of data analysis, in particular to a disease consultation system based on big data. The system comprises a consultation request health data acquisition module, a disease health association map construction module, a consultation disease department navigation analysis module and a user disease consultation application agreement module. The method comprises the following steps: acquiring a user consultation request of a disease patient, and acquiring corresponding personal disease health data, patient historical health data and public medical health data; performing user current health state association analysis and disease health association map construction on the personal disease health data to generate a consultation patient user personal disease health association map, and performing consultation disease department navigation analysis and disease consultation application at the same time; and acquiring patient consultation queuing data and online inquiry active data to perform re-queuing consultation application and disease consultation processing so as to complete a disease consultation result of a corresponding consultation patient user. According to the invention, the efficiency and accuracy of disease consultation service can be significantly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a disease consultation system based on big data. Background Art

[0002] In recent years, disease consultation methods based on big data have gradually emerged. By collecting and analyzing a large amount of patient data, disease information, diagnosis and treatment plans, and related medical literature, big data technology can provide patients with more accurate and personalized health consultation services. Big data technology can efficiently integrate data from different channels (such as electronic medical records, health monitoring equipment, medical literature, etc.), and through data mining and analysis, it can discover potential disease risks and early warning signs, providing strong support for disease consultation and the formulation of personalized treatment plans.

[0003] In addition, a Chinese patent with publication number CN117133448A proposes a gynecological disease consultation system based on big data, including a gynecological disease consultation platform, in which an information registration module, a database module, a publicity and display module, an information inquiry module, a doctor-patient selection module and a medical diagnosis module are provided; the information registration module is used to register the identity of users using the platform; the database module is used to store the data information and medical information of users in the platform; the publicity and display module is used to display knowledge of gynecological diseases; the information inquiry module is used to obtain the basic information of the patient and generate medical guide information; the doctor-patient selection module is used for the patient to select the corresponding doctor according to the medical guide information to generate an inquiry application for detailed inquiry; the medical diagnosis module is used to set up a joint diagnosis group, and the doctors in the joint diagnosis group generate a diagnosis book to complete the disease consultation for the corresponding patient; the beneficial effect of the present invention is to reduce the misdiagnosis rate of doctors in the platform to a certain extent.

[0004] Although the technical solution proposed in the above patent can effectively reduce the misdiagnosis rate of doctors' disease consultation, it also generates medical guide information based on the patient's basic situation. At the same time, although big data technology can provide fast consulting services, its results are often based on the output of statistical models or machine learning models, but lack of in-depth integration with actual historical health and public health, and no rearrangement of queues based on consultation activity, resulting in differences between some consulting suggestions and actual medical operations, thereby affecting patients' waiting time and trust. Summary of the invention

[0005] Based on this, it is necessary for the present invention to provide a disease consultation system based on big data to solve at least one of the above technical problems.

[0006] To achieve the above purpose, a disease consultation system based on big data includes the following modules:

[0007] The consultation request health data acquisition module is used to obtain the consultation request of the disease patient user, and based on the consultation request of the disease patient user, obtain the personal disease health data uploaded by the consulting patient user on the disease consultation platform and the patient historical health data and public medical health data corresponding to the consultation background database;

[0008] The disease-health association map construction module is used to perform an association analysis of the personal disease-health data with the user's current health status based on the patient's historical health data and public medical health data, so as to generate a disease association relationship between the patient's past medical history and public medical conditions and the current health status of the consulting patient user; based on the patient's past medical history and the disease association relationship between the public medical conditions and the current health status of the consulting patient user, a disease-health association map is constructed for the personal disease-health data, so as to generate a personal disease-health association map for the consulting patient user;

[0009] The consultation disease department navigation analysis module is used to perform consultation disease department navigation analysis on the basic situation of the consultation patient user based on the consultation patient user's personal disease health association map, so as to generate the consultation patient user's personal disease health department guidance information;

[0010] The user disease consultation application consent module is used for consulting patient users to select the corresponding department doctor to apply for disease consultation according to the corresponding personal disease health department medical guide information, and obtain the corresponding patient consultation queue data and online inquiry active data of the department doctor, and re-queue the consultation application according to the patient consultation queue data and online inquiry active data to generate a department doctor consent consultation application request; according to the department doctor's consent consultation application request, the corresponding department doctor is selected to perform disease consultation processing on the basic situation of the consulting patient user to complete the disease consultation result of the corresponding consulting patient user.

[0011] Furthermore, the consultation request health data acquisition module includes the following functions:

[0012] Obtain consultation requests from disease patients;

[0013] Obtain corresponding disease consultation patient user needs and consultation information input by consulting patient users through disease patient user consultation requests, and perform deep semantic analysis on the consultation information input by consulting patient users to obtain patient user consultation topic content classification;

[0014] Prioritize and sort disease patient user consultation requests based on disease consultation patient user needs and patient user consultation topic content classification to generate a patient user consultation request priority sequence;

[0015] According to the consultation request queuing sequence corresponding to the patient user's consultation request priority sequence, the personal disease health data uploaded by the corresponding consulting patient user on the disease consultation platform and the patient historical health data corresponding to the consultation background database are obtained;

[0016] Based on the patient user consultation subject content classification corresponding to the consultation request queuing sequence, the latest public medical information in the consultation background database is matched with the subject content to obtain public medical health data.

[0017] Furthermore, the disease-health association map construction module includes the following functions:

[0018] Conduct statistical analysis on the patient's historical health data to obtain the patient's medical history data;

[0019] Conduct statistical analysis of disease epidemic trends on public medical health data to obtain the epidemic trends of similar public medical diseases;

[0020] Conduct current health status evaluation and analysis on the personal disease health data corresponding to the consulting patient user to obtain the current disease health status of the consulting patient user;

[0021] Based on the patient's past medical history data and the prevalence of similar diseases in public medicine, the patient's current disease health status is analyzed to generate a disease association relationship between the patient's past medical history and public conditions and the patient's current health status;

[0022] Based on the patient's past medical history and the disease association relationship between the public condition and the current health status of the consulting patient user, a disease-health association map is constructed for the personal disease-health data to generate a personal disease-health association map for the consulting patient user.

[0023] Furthermore, the analysis of the current health status of the consulting patient user based on the consulting patient user's past medical history data and the prevalence of similar diseases in public medicine includes:

[0024] Performing a past medical history incidence analysis on the past medical history data of the consulting patient user to obtain the past medical history incidence of the consulting patient user;

[0025] Based on the past medical history incidence rate of the consulting patient user, the hidden risk assessment analysis of the current disease health status of the consulting patient user is performed to obtain the hidden risk factors of the user's current disease health history;

[0026] Perform time-series synchronous prediction on the epidemic situation of similar public medical diseases and the current disease health status of consulting patient users to generate the corresponding epidemic situation of public medical diseases and the current disease status of consulting patient users in the same time period; predict the patient disease evolution rate of the corresponding current disease status of consulting patient users based on the corresponding epidemic situation of public medical diseases in the same time period to obtain the corresponding predicted rate of consulting patient disease evolution under the public disease epidemic situation;

[0027] Based on the user's current disease health history implicit risk factors and the corresponding predicted rate of disease evolution of the consulting patient under the public disease epidemic situation, the disease health risk association calculation formula is used to quantitatively calculate the disease risk association of the consulting patient's current disease health status, so as to obtain the disease risk association between the patient's previous medical history and the public condition and the user's current health status;

[0028] The disease risk association between the patient's past medical history and public conditions and the user's current health status is compared and judged according to a preset disease risk association threshold. If the disease risk association is greater than or equal to the preset disease risk association threshold, the disease risk association between the patient's past medical history and public conditions and the user's current health status is determined as an explicit association relationship; if the disease risk association is less than the preset disease risk association threshold, the disease risk association between the patient's past medical history and public conditions and the user's current health status is determined as an implicit association relationship; and association connections are made based on the explicit association relationship and the implicit association relationship to generate a disease association relationship between the patient's past medical history and public conditions and the current health status of the consulting patient user.

[0029] Furthermore, the disease health risk association calculation formula is specifically as follows:

[0030]

[0031] In the formula, G L is the disease risk correlation between the patient's past medical history and public condition and the user's current health status, T is the integral time range parameter, t is the time variable parameter, and D h (t) is the patient’s medical history health record at time t, m is the number of health problems in the patient’s medical history, h j (t) is the known health risk score of the jth health problem at time t, θ j is the weight coefficient corresponding to the jth health problem, α1 is the risk impact weight of previous medical history, F a (t) is the public disease health risk factor at time t, I(t) is the number of people infected with the public disease at time t, N is the total population, R0 is the basic reproduction number, f pis the predicted rate of disease evolution of consulting patients corresponding to the epidemic situation of public diseases, α2 is the impact weight of public disease health risk, D c is the metric value corresponding to the patient's current disease health status, β is the attenuation coefficient of the patient's current disease health status, n is the total number of the user's current disease health past hidden risk factors, i is the item index of the user's current disease health past hidden risk factors, S i is the hidden risk factor of the current disease and health history of the i-th user, γ i is the weight coefficient corresponding to the hidden risk factor of the current disease and health history of the i-th user, and η is the correction coefficient of the disease risk correlation.

[0032] Furthermore, the consultation disease category navigation analysis module includes the following functions:

[0033] Produce a disease and health profile for the basic conditions of the consulting patient user to obtain a disease and health profile for the consulting patient user;

[0034] Conduct disease and health assessment analysis on the disease and health portrait of the consulting patient user to generate a disease and health assessment report for the consulting patient user;

[0035] Based on the consulting patient user's disease health assessment report, a health problem mapping analysis is performed on the disease health status corresponding to the consulting patient user's disease health profile to generate the consulting patient user's disease health problems;

[0036] Based on the personal disease and health association map of the consulting patient user, the consulting patient user's disease and health problems are analyzed for the disease and health category attribution, and the disease and health problem category attribution corresponding to the consulting patient user is obtained;

[0037] According to the department affiliation of the disease and health problems corresponding to the consulting patient users, a department navigation suggestion analysis is performed to generate personal disease and health department guide information corresponding to the consulting patient users.

[0038] Further, the analysis of the disease category of the consulting patient user's disease and health problems based on the consulting patient user's personal disease and health association map includes:

[0039] Perform health problem semantic embedding analysis on the patient's disease and health problems to generate a user's disease and health problem semantic embedding vector;

[0040] Based on the semantic embedding vector of the user's disease and health problem, the disease and health urgency assessment analysis is performed on the consulting patient's disease and health problem to obtain the urgency of the consulting patient's disease and health problem;

[0041] Conduct personal health goal analysis on the disease and health problems of consulting patient users to obtain personal disease and health goals of consulting patient users;

[0042] Based on the consulting patient user's personal disease-health association map, the consulting patient user's personal disease-health goals are analyzed for potential disease-related hazards, and the consulting patient user's personal disease-related hazards are obtained;

[0043] Based on the urgency of the consulting patient's disease and health problems and the potential associated hazards of the consulting patient's personal diseases, the corresponding consulting patient's disease and health problems are analyzed to obtain the corresponding disease and health problem category of the consulting patient.

[0044] Furthermore, the user disease consultation application consent module includes the following functions:

[0045] The consulting patient user selects the corresponding department doctor to apply for disease consultation based on the corresponding personal disease health department medical guide information, so as to generate a patient user disease health matching doctor consultation application;

[0046] According to the patient user's disease health matching doctor consultation application, obtain the patient consultation queue data and online inquiry activity data corresponding to the department doctor, where the online inquiry activity data includes the inquiry response speed and online inquiry activity of the department doctor;

[0047] According to the patient consultation queue data and online inquiry activity data, a re-queue consultation application is made to the next department doctor corresponding to the personal disease and health department medical guide information to generate a consultation application consent request from the department doctor;

[0048] According to the department doctor's consent to the consultation application request, the corresponding department doctor is selected to conduct disease consultation on the basic situation of the consulting patient user to complete the disease consultation result of the corresponding consulting patient user.

[0049] Furthermore, the requeuing consultation application for the next department doctor corresponding to the personal disease and health department medical guide information according to the patient consultation queue data and the online inquiry activity data includes:

[0050] Obtain the corresponding available time of consulting doctors and the total number of consulting doctors in line through the patient consultation queue data, and perform queue time prediction analysis based on the available time of consulting doctors and the total number of consulting doctors in line to obtain the consultation queue time of doctors in the current department;

[0051] Based on the total number of consultation doctors’ queues, the current consultation queue time of doctors in the department, and the online inquiry activity data, the consultation queue activity load of the department doctors corresponding to the personal disease and health department medical guide information is quantitatively calculated to obtain the patient consultation doctor queue activity load index;

[0052] The patient consultation doctor queue active load index is compared and judged according to the preset queue active load threshold to generate a department doctor's consent consultation application request.

[0053] Furthermore, the specific process of the comparison and judgment is as follows:

[0054] If the patient's consultation doctor queue activity load index is greater than or equal to the preset queue activity load threshold, the patient needs to queue again to apply for the next department doctor corresponding to the personal disease and health department medical guide information; if the patient's consultation doctor queue activity load index is less than the preset queue activity load threshold, the patient will continue to queue for the current corresponding department doctor until the corresponding department doctor agrees to the consultation application when the time comes, thereby generating a request for the department doctor to agree to the consultation application.

[0055] Beneficial effects of the present invention:

[0056] The disease consultation system based on big data proposed in the present invention is generally composed of a consultation request health data acquisition module, a disease health association map construction module, a consultation disease category navigation analysis module, and a user disease consultation application consent module. Compared with the prior art, the beneficial effect of the present application is that the platform receives the patient's consultation request, obtains the personal disease health data uploaded by the patient, and retrieves the patient's historical health data and related public medical health data in the background database. This process can effectively associate the patient's individual disease health information with a wide range of public medical health to form a comprehensive and detailed patient health file. In this way, the platform can not only fully understand the patient's current health status, but also can further accurately analyze the potential health risks faced by the patient based on his past medical history and public health data. The health data uploaded by the patient includes physical examination reports, imaging data, laboratory test results, etc. The acquisition of this information provides necessary data support for the subsequent processing process, and the public medical health data includes epidemiological survey data, disease occurrence trends, the incidence patterns of common diseases, etc., which can provide doctors with a broader disease knowledge background and provide strong support for consultation on individual diseases. Secondly, by analyzing the association between personal disease health data and the user's current health status based on the patient's historical health data and public medical health data, the key to this step is to combine the patient's historical health data with public medical data, associate them through data analysis tools, and generate a disease association map, which not only helps to build a comprehensive understanding of the patient's current health status, but also can discover the potential connection between his disease and other related diseases. Through this process, the platform can combine the patient's past medical history, family history, lifestyle and other information with epidemiological trends, common disease risks and other factors in public health data for association analysis. For example, if the patient has a history of hypertension, and public health data show that hypertension is often accompanied by diabetes, cardiovascular disease, etc., it will indicate the risk of related diseases and mark the possibility of these diseases in personal health data. This association analysis not only helps doctors fully understand the patient's health status, but also assists in formulating personalized department disease consultation plans. The generation of disease-health association maps can also intuitively display the multi-dimensional information of the patient's health, which is convenient for doctors to refer to when consulting and making decisions. This comprehensive analysis can enhance their understanding of their own disease health and enhance patients' awareness of actively managing their health.Then, by conducting consultation disease department navigation analysis on the basic information of the consulting patient user based on the consulting patient user's personal disease-health association map, the implementation of this function has greatly improved the efficiency and accuracy of patients seeking medical treatment. Traditional medical consultation usually faces the problem that patients are not clear about which department they should choose for treatment, especially when the patient's disease involves multiple organs or complex health problems, the choice of department becomes particularly difficult. Through the disease-health association map, the platform can accurately analyze the patient's health problems and related departments, and generate personalized department guidance information. For example, if the patient shows a potential association between cardiovascular disease and diabetes in the analysis, the platform will recommend that the patient choose a doctor in the cardiology and endocrinology departments for further consultation. This not only improves the patient's medical experience, avoids the trouble of repeated registration and multiple referrals, but also helps patients obtain professional disease assessments and suggestions in the shortest time. This step can also improve the doctor's work efficiency, so that they can understand the patient's health background more quickly and reduce time waste. Finally, consulting patients select corresponding department doctors for disease consultation applications based on corresponding personal disease and health department medical guide information, and reasonably re-queue based on queuing data and online inquiry activity data. This process not only improves the matching degree between patients and doctors, but also effectively optimizes the consultation queuing process and reduces patient waiting time. By comprehensively considering the needs of patients and the workload of doctors, the platform can flexibly schedule to ensure that patients get the required medical services as quickly as possible. In addition, based on online inquiry activity data, the platform can analyze which doctors have more active inquiries and faster processing speeds, thereby helping patients choose the most suitable doctors for consultation. This systematic queuing mechanism The system can improve the efficiency of resource utilization and avoid the situation where some doctors cannot receive more patients due to long queues. At the same time, it also ensures that patients can get timely disease consultation and help within a reasonable time. After the doctor agrees to consult, the patient's consultation will enter the formal disease consultation and advice stage. The doctor can make detailed plans or suggestions based on the data from the previous analysis, thereby providing patients with higher quality and more accurate medical services. This process effectively improves the management of medical resources and patient experience, and promotes the overall efficiency of medical services. Through the in-depth integration of historical health and public health, it can reduce the difference between consultation advice and actual medical operations, thereby enhancing patients' trust. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0058] Figure 1 This is a module diagram of a disease consultation system based on big data of the present invention;

[0059] Figure 2 for Figure 1 Functional flow diagram of the health data acquisition module in the consultation request;

[0060] Figure 3 for Figure 1 Schematic diagram of the functional flow of the disease-health association map construction module. DETAILED DESCRIPTION

[0061] The technical system of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0062] To achieve this, please refer to Figures 1 to 3 The present invention provides a disease consultation system based on big data, the system comprising the following modules:

[0063] The consultation request health data acquisition module is used to obtain the consultation request of the disease patient user, and based on the consultation request of the disease patient user, obtain the personal disease health data uploaded by the consulting patient user on the disease consultation platform and the patient historical health data and public medical health data corresponding to the consultation background database;

[0064] The disease-health association map construction module is used to perform an association analysis of the personal disease-health data with the user's current health status based on the patient's historical health data and public medical health data, so as to generate a disease association relationship between the patient's past medical history and public medical conditions and the current health status of the consulting patient user; based on the patient's past medical history and the disease association relationship between the public medical conditions and the current health status of the consulting patient user, a disease-health association map is constructed for the personal disease-health data, so as to generate a personal disease-health association map for the consulting patient user;

[0065] The consultation disease department navigation analysis module is used to perform consultation disease department navigation analysis on the basic situation of the consultation patient user based on the consultation patient user's personal disease health association map, so as to generate the consultation patient user's personal disease health department guidance information;

[0066] The user disease consultation application consent module is used for consulting patient users to select the corresponding department doctor to apply for disease consultation according to the corresponding personal disease health department medical guide information, and obtain the corresponding patient consultation queue data and online inquiry active data of the department doctor, and re-queue the consultation application according to the patient consultation queue data and online inquiry active data to generate a department doctor consent consultation application request; according to the department doctor's consent consultation application request, the corresponding department doctor is selected to perform disease consultation processing on the basic situation of the consulting patient user to complete the disease consultation result of the corresponding consulting patient user.

[0067] In the embodiment of the present invention, please refer to Figure 1 FIG. 1 is a schematic diagram of a module of a disease consultation system based on big data of the present invention. In this example, the disease consultation system based on big data includes the following modules:

[0068] S1: A consultation request health data acquisition module, which is used to obtain consultation requests from disease patient users, and based on the consultation requests from disease patient users, obtain the corresponding personal disease health data uploaded by the consulting patient users on the disease consultation platform, as well as the patient historical health data and public medical health data corresponding to the consultation background database;

[0069] In an embodiment of the present invention, a consultation request from a patient user is received through a disease consultation platform, and the patient user submits his or her own questions through an online consultation interface. The questions may include descriptions of symptoms, inquiries about drugs, or understanding of the condition, etc. At this time, the system needs to record each user request and assign a unique identifier to each request. The information submitted by the patient is transmitted to the background through the front-end input box. The background performs basic language recognition and processing on the text input by the patient through natural language processing (NLP) technology, and converts it into a machine-understandable format, thereby obtaining a consultation request from a patient user. When a patient submits a consultation request to the disease consultation platform, the patient's consultation content will be received, the patient's questions or symptom descriptions will be recorded, and the patient's identity and account information will be identified. According to the patient's account, the personal health data uploaded on the disease platform will be automatically associated, including physical examination reports, diagnosis results, drug use records, and related medical images. At the same time, the platform will automatically extract the patient's historical health data from the consultation background database, such as previous disease records, hospitalization records, surgical history, allergy history, etc. In addition, disease-related information in the public medical health database will be called, covering medical literature, clinical guidelines, scientific research data, etc., and finally the corresponding patient historical health data and public medical health data will be obtained.

[0070] S2: A disease-health association map construction module, which is used to perform an association analysis of the personal disease-health data with the user's current health status based on the patient's historical health data and public medical health data, so as to generate a disease association relationship between the patient's past medical history and the public medical condition and the current health status of the consulting patient user; based on the patient's past medical history and the disease association relationship between the public medical condition and the current health status of the consulting patient user, a disease-health association map is constructed for the personal disease-health data, so as to generate a personal disease-health association map for the consulting patient user;

[0071] In an embodiment of the present invention, by integrating the patient's historical health data with public medical health data, the patient's personal health data is first analyzed to identify potential disease risks related to the current health status. Specifically, by using a big data analysis algorithm, such as an association rule algorithm in machine learning, the patient's past medical history and public medical knowledge are combined to evaluate the association between the patient's current health status and known disease patterns, thereby generating a disease association between the patient's past medical history and public conditions and the current health status of the consulting patient user. At the same time, based on these analyses, a "disease association map" of the patient is established, showing the disease association between the patient's past medical history and his current health status, indicating potential health problems. In addition, the public condition database will be combined to identify the current popular disease trends, causes and other information, and further perform a multi-dimensional association analysis on the patient's health status. A disease-health association map is generated through an algorithm, which shows the multi-level association between the patient's health status, historical medical history, public disease information and potential diseases, and finally generates a personal disease-health association map for the consulting patient user.

[0072] S3: a consultation disease department navigation analysis module, which is used to perform consultation disease department navigation analysis on the basic situation of the consultation patient user based on the consultation patient user's personal disease health association map, so as to generate the consultation patient user's personal disease health department guidance information;

[0073] In an embodiment of the present invention, an in-depth analysis of the patient's basic situation is conducted based on the patient's health status analysis results and the disease-health association map. Combined with the patient's main symptoms, disease risks, and historical medical history, a navigation analysis of the disease department is automatically generated. According to the patient's symptoms, medical history and disease association map, the medical departments involved are recommended, and the patient is provided with corresponding disease department guidance information. For example, if the patient has a history of cardiovascular disease, the system will automatically guide him to contact the cardiology department; if the patient has digestive system problems, the system will guide the patient to the gastroenterology department. This process involves the application of an intelligent recommendation algorithm. By comparing historical health data with public medical data, it ensures that the patient can obtain the most relevant department recommendation. The guidance information includes the name of the relevant department, the profile of the attending physician, the diagnosis and treatment characteristics of the department, the department appointment process, etc., to help patients more conveniently choose a suitable department for consultation on the platform, and finally generate personal disease health department guidance information corresponding to the consulting patient user.

[0074] S4: User disease consultation application consent module, used for consulting patient users to select the corresponding department doctor to apply for disease consultation according to the corresponding personal disease health department medical guide information, and obtain the corresponding patient consultation queue data and online inquiry active data of the department doctor, and re-queue the consultation application according to the patient consultation queue data and online inquiry active data to generate a department doctor consent consultation application request; according to the department doctor's consent consultation application request, select the corresponding department doctor to perform disease consultation processing on the basic situation of the consulting patient user, so as to complete the disease consultation result of the corresponding consulting patient user.

[0075] In an embodiment of the present invention, after obtaining the medical guide information of personal disease and health departments, the consulting patient user selects the doctor of the corresponding department according to his own needs to apply for consultation. After the patient submits the consultation application, the system will automatically obtain the queuing data of the department and the doctor's online inquiry activity, and judge whether the patient can get consultation directly by analyzing the doctor's current queuing situation, available appointment time, online consultation status and other information. If there are a large number of people queuing in the current department, the system will re-optimize the queuing strategy, make reasonable adjustments based on the doctor's available time and the patient's needs, and provide the patient with real-time estimated queuing time. At the same time, it will also analyze the doctor's response efficiency based on the online inquiry activity data, and prioritize the patient's application. If the doctor confirms that he can see the patient, the system will generate an application request for the department doctor to agree to the consultation, and update the patient's consultation queuing status on the platform, and send a reminder to the patient. At this time, the consultation process between the patient and the doctor has been successfully established, and the doctor will provide detailed disease consultation based on the basic information provided by the patient, such as disease symptoms, previous medical history and other information.

[0076] Further, as an embodiment of the present invention, refer to Figure 2As shown, Figure 1 The functional flow diagram of the consultation request health data acquisition module in this embodiment includes the following functions:

[0077] S11: Obtain consultation requests from disease patients;

[0078] In an embodiment of the present invention, a consultation request from a patient user is received through a disease consultation platform, and the patient user submits his or her own questions through an online consultation interface. The questions may include a description of symptoms, an inquiry about medication, or an understanding of the condition, etc. At this time, the system needs to record each user request and assign a unique identifier to each request. The information submitted by the patient is transmitted to the background through the front-end input box. The background performs basic language recognition and processing on the text input by the patient through natural language processing (NLP) technology, and converts it into a machine-understandable format. According to the system architecture design, the patient request will be automatically uploaded to the background server, and connected to the database through an adapter, and finally the disease patient user consultation request is obtained.

[0079] S12: Obtain corresponding disease consultation patient user needs and consultation information input by the consulting patient user through the disease patient user consultation request, and perform deep semantic analysis on the consultation information input by the consulting patient user to obtain the patient user consultation topic content classification;

[0080] In an embodiment of the present invention, the corresponding disease consultation patient user needs and the consultation information input by the consulting patient user are obtained from the corresponding consultation request, and semantic analysis is performed based on the patient user's consultation information. The natural language understanding technology (NLU) is used to perform in-depth analysis on the text input by the user to identify the core elements of the consultation content. In specific operations, the pre-built medical knowledge base is used to classify the patient input based on lexical, syntactic, and semantic analysis. For example, if the user asks "I have been coughing for two weeks, with phlegm and frequent coughing", it will be identified that the patient has a respiratory-related disease. Through deep semantic analysis, the user's input is mapped to a predefined subject classification, such as "respiratory diseases" or "infectious diseases". The patient's health needs are also extracted based on the user's question structure and keywords, and it is determined whether the patient needs to know the symptoms of the disease, decision-making plans, or disease prevention information. The patient's needs are classified through hierarchical analysis and marked as corresponding subject content, and finally the patient user consultation subject content classification is obtained.

[0081] S13: Prioritizing and sorting disease patient user consultation requests based on disease consultation patient user needs and patient user consultation topic content classification to generate a patient user consultation request priority sequence;

[0082] In an embodiment of the present invention, the urgency and priority of the consultation request are further determined by classifying the needs of the disease consultation patients and the consultation content obtained according to the aforementioned steps. Specifically, each patient consultation request is scored by a preset priority model, and the priority model performs weighted scoring according to the following factors: the severity of the patient's symptoms, the urgency of the problem, historical disease records (such as chronic diseases or high-risk diseases), and the user's health data. For example, if the user asks about the symptoms of an acute heart attack, the priority of such questions will be automatically set to a higher level; while for consultations on common cold symptoms, the priority is lower. In the background, according to these scoring rules, a weighted sorting algorithm (such as score-based sorting or priority queue) is used to generate a priority sequence of patient consultation requests to ensure that urgent and high-priority requests can be responded to in a timely manner, and ultimately a priority sequence of patient user consultation requests is generated.

[0083] S14: Obtain the personal disease health data uploaded by the corresponding consulting patient user on the disease consultation platform and the patient historical health data corresponding to the consultation background database according to the corresponding consultation request queuing sequence in the patient user consultation request priority sequence;

[0084] In an embodiment of the present invention, each consultation request in the queue is processed in sequence according to the priority sequence of the patient's consultation request. When processing each request, relevant health data is extracted from the patient's personal file. These data include but are not limited to the patient's historical medical history, previous medical records, physical examination results and other health monitoring data. By connecting with the health data storage system, the health data uploaded by the patient is automatically identified and relevant information is obtained. In addition, the patient's historical health data is retrieved from the electronic health record (EHR) database of the hospital or clinic to supplement the patient's health background information. The acquisition of this information helps the disease consultation platform to provide more personalized consulting services based on the patient's past medical history, ensuring that the doctor or artificial intelligence system's answer can take into account the patient's special health status, and ultimately obtain the user's corresponding uploaded personal disease health data and the patient's historical health data corresponding to the consultation background database.

[0085] S15: Based on the patient user consultation subject content classification corresponding to the consultation request queuing sequence, the latest public medical information in the consultation background database is matched with the subject content to obtain public medical health data.

[0086] In an embodiment of the present invention, by classifying the subject content in the patient's consultation request, the latest public medical information related to the patient's needs is automatically extracted from the consultation background database. The background database contains medical data extracted from medical literature, academic papers, medical guidelines and the latest public health information. Through keyword matching and semantic analysis technology, combined with the patient's consultation topic, the data most relevant to the user's consultation is screened out from these public medical information and returned to the platform. For example, if the patient asks about the subject content of "allergic rhinitis", the latest clinical research results, research guidelines and drug recommendations will be found in the background database based on the keyword "allergic rhinitis", and this information will be pushed to the corresponding consulting department doctors. The matching process of the system is based on classification models and information retrieval algorithms to ensure that the medical information provided is accurate, relevant and timely, thereby helping patients obtain the most valuable medical advice and ultimately obtain public medical health data.

[0087] Further, as an embodiment of the present invention, refer to Figure 3 As shown, Figure 1 The functional flow diagram of the disease-health association map construction module in this embodiment includes the following functions:

[0088] S21: Performing medical history statistical analysis on the patient's historical health data to obtain medical history data of the consulting patient user;

[0089] In an embodiment of the present invention, by collecting the patient's historical health data, including but not limited to the patient's previous medical history, treatment records, medication, surgical history, allergy history and other medical information, these data are usually obtained through an electronic health record (EHR) system or a medical history record form submitted by the patient, and then the collected raw data is cleaned using data preprocessing technology to remove missing, duplicate or invalid data. For example, the patient's previous medical history information needs to be standardized to unify the disease coding formats used by different medical institutions to ensure data consistency and comparability. Through statistical analysis methods, such as frequency analysis and trend analysis, the patient's previous medical history data is deeply mined to identify the patient's high-incidence disease types and the time pattern of disease occurrence, and generate the patient's previous medical history data, including detailed information such as the number of illnesses, disease types, and decision-making effects, and finally obtain the consulting patient user's previous medical history data.

[0090] S22: Conduct statistical analysis on the epidemic situation of public medical health data to obtain the epidemic situation of similar public medical diseases;

[0091] In an embodiment of the present invention, public medical health data is obtained from a wide range of disease monitoring systems, public health data reports, and global or regional epidemiological studies. First, public health data including disease incidence, mortality, geographic distribution, demographic characteristics, etc. are collected, and these data are processed using data mining technology, including data cleaning, outlier detection, and missing data completion. Then, statistical methods such as time series analysis, cluster analysis, and regression analysis are applied to study the epidemic trends of different diseases. For example, for specific diseases (such as influenza, diabetes, hypertension, etc.), the changes in their epidemic situation in different regions and time periods are analyzed, so as to derive key characteristics such as seasonal fluctuations and geographical differences of the disease. Through data visualization technology, charts and reports of the epidemic situation are generated to show the distribution pattern and changing trend of the disease, thereby obtaining the epidemic situation of diseases similar to the patient's historical medical history, and finally obtaining the epidemic situation of similar public medicine diseases.

[0092] S23: Performing a current health status evaluation and analysis on the personal disease health data corresponding to the consulting patient user to obtain the current disease health status of the consulting patient user;

[0093] In an embodiment of the present invention, by consulting the patient's current health status, it is necessary to first collect the patient's real-time health data, including the patient's latest diagnosis results, laboratory test data, imaging examination reports, symptoms and signs information, etc. These data can be obtained through an electronic medical record system, smart health devices (such as wearable devices, blood glucose meters, blood pressure monitors, etc.) or health monitoring data uploaded by the patient himself, and then based on professional medical knowledge, a machine learning algorithm (such as a decision tree, a support vector machine, etc.) is used to evaluate the patient's current health data. The algorithm model is used to evaluate whether the patient's physiological indicators (such as blood glucose, blood pressure, heart rate, etc.) are within the normal range. Combined with the patient's main symptoms, a comprehensive analysis is performed. For patients with a history of chronic diseases, the difference between the patient's health data and the standard diagnostic criteria is analyzed to determine the current disease control situation, and the patient's disease development trend is evaluated, and finally the consulting patient user's current disease health status is obtained.

[0094] S24: performing a correlation analysis of the current disease health status of the consulting patient user based on the previous medical history data of the consulting patient user and the epidemic situation of similar diseases in public medicine, so as to generate a disease correlation relationship between the patient's previous medical history and the public condition and the current health status of the consulting patient user;

[0095] In an embodiment of the present invention, the patient's past medical history data is associated with the disease epidemic situation in public medical health data, and the association rule mining technology in machine learning (such as Apriori algorithm, FP-growth algorithm) is used to compare the patient's past disease type, treatment method and the possibility of disease recurrence with the epidemic pattern of similar diseases in public data. Specifically, when the patient has a history of hypertension, the epidemic situation analysis is used to evaluate the current prevalence of hypertension in the patient's area, such as whether there is a high incidence period or epidemic situation of hypertension in the area. Combined with the patient's current health status, an association model is established to determine which external public epidemic factors will affect the patient's disease status, such as seasonal changes, environmental pollution and other factors. Through data analysis, a correlation map between the patient's past medical history, the public disease epidemic situation and the patient's current health status is generated, revealing potential health risks and related factors of disease development, and finally generating a disease association relationship between the patient's past medical history and the public condition and the current health status of the consulting patient user.

[0096] S25: Construct a disease-health association map for personal disease-health data based on the patient's past medical history and the disease association relationship between the public condition and the current health status of the consulting patient user, so as to generate a personal disease-health association map for the consulting patient user.

[0097] In an embodiment of the present invention, a disease-health association map is constructed based on the results of the association analysis of the patient's past medical history, the epidemic situation in public medical data, and the patient's current health status. The map displays the patient's various health data, disease risks, the relationship between diseases, and potential health threats in the form of a graph structure. In specific operations, a graph database (such as Neo4j, etc.) is used to construct a patient's health data model, and the patient's past medical history, the epidemic situation of public diseases, and the current health status are used as nodes of the graph. The nodes are connected by edges to represent the association between different diseases, health status, public health information, etc. The map is further optimized through graph algorithms (such as shortest path algorithms, clustering algorithms, etc.) to mine key nodes and risk factors in the patient's health data. These association graphs can not only help doctors understand the patient's health status more intuitively, but also reflect the changes in the patient's health status in a timely manner through dynamic updates, and provide a scientific basis for future health management and intervention. The generated disease-health association map can be used as a reference for medical professionals, or presented to patients through visualization technology to help patients better understand their health status and potential disease risks, and finally generate a personal disease-health association map for consulting patient users.

[0098] Furthermore, the analysis of the current health status of the consulting patient user based on the consulting patient user's past medical history data and the prevalence of similar diseases in public medicine includes:

[0099] Performing a past medical history incidence analysis on the past medical history data of the consulting patient user to obtain the past medical history incidence of the consulting patient user;

[0100] In an embodiment of the present invention, the patient's medical history data is extracted from the patient's electronic health record or medical database. These data may include the patient's chronic diseases, past diseases, surgical history, family medical history, etc. In order to conduct morbidity analysis, big data processing tools such as Hadoop and Spark are used to clean and preprocess the data, remove outliers and missing values, and standardize the data format. Then, the morbidity of the patient's medical history data is calculated through statistical analysis methods such as chi-square test, regression analysis or survival analysis. Specifically, the incidence of each disease can be calculated according to different disease types, and further compared with the overall incidence of the population, so as to obtain the individual's medical history incidence, and finally obtain the medical history incidence of the consulting patient user.

[0101] Preferably, based on the past medical history incidence rate of the consulting patient user, the medical history health implicit risk assessment analysis is performed on the current disease health status of the consulting patient user to obtain the user's current disease health past implicit risk factors;

[0102] In an embodiment of the present invention, a hidden health risk assessment is performed by combining the previously obtained past medical history incidence rate with the patient's current health status. First, the patient's current disease information (such as physical examination report, clinical diagnosis, laboratory results, etc.) is used to identify the corresponding health risk factors, and then the patient's past medical history incidence rate and the current disease status are correlated and analyzed. A machine learning algorithm, such as decision tree, random forest, support vector machine (SVM), etc., is used to build a prediction model based on historical data. The model is used to evaluate the hidden risk factors of the patient's current disease, that is, the potential risk factors of the current disease are inferred based on the incidence rate of the past medical history, and the hidden risk factors of the patient's current health status are obtained, such as the potential recurrence risk of chronic diseases or the impact of genetic factors on the current disease, and finally the user's current disease health hidden risk factors are obtained.

[0103] Preferably, the epidemic situation of similar public medical diseases and the current disease health status of consulting patient users are predicted in a time-series synchronization manner to generate the corresponding epidemic situation of public medical diseases and the current disease status of consulting patient users in the same time period; based on the corresponding epidemic situation of public medical diseases in the same time period, the patient disease evolution rate is predicted for the corresponding current disease status of consulting patient users to obtain the corresponding predicted rate of consulting patient disease evolution under the public disease epidemic situation;

[0104] In an embodiment of the present invention, by making a time-series synchronous prediction of the epidemic situation of public medical diseases and the current health status of patients, firstly, epidemiological data in the field of public health are collected, including epidemic reports, disease epidemic trends, geographical distribution, etc., and time series analysis methods such as ARIMA model, long short-term memory network (LSTM), etc. are used to predict the epidemic situation of public diseases. At the same time, according to the current health status of patients, dynamic monitoring data such as real-time health monitoring equipment and self-reported symptoms of patients are used to track changes in the health status of patients, and a time series model is used for synchronous prediction, thereby generating the corresponding epidemic situation of public medical diseases in the same time period and the current disease status of consulting patient users. At the same time, based on the time-series synchronous prediction results of the previous step, the evolution rate of the patient's disease status under the public disease epidemic situation is analyzed. First, by establishing a mathematical model (such as the SIR model, the Logistic regression model, etc.), the evolution process of the patient's current disease under different epidemic situations is simulated. The evolution rate can be obtained by calculating the gradient or growth rate of the disease state change. For example, if the patient is in a high-risk epidemic state, the model can predict the speed of the patient's condition worsening through the disease evolution pattern in the historical data. The input variables of the model include the patient's current health status, the public disease epidemic situation and other relevant environmental factors. Through this prediction, the possible evolution path and time frame of the patient's disease under different public epidemic situations can be foreseen, and finally the corresponding consultation patient disease evolution prediction rate under the public disease epidemic situation is obtained.

[0105] Preferably, based on the user's current disease health past hidden risk factors and the corresponding predicted rate of disease evolution of the consulting patient under the public disease epidemic situation, the disease health risk association calculation formula is used to perform a quantitative calculation of the disease risk association of the consulting patient user's current disease health status, so as to obtain the disease risk association between the patient's previous medical history and the public condition and the user's current health status;

[0106] In an embodiment of the present invention, a suitable disease-health risk association calculation formula is constructed by combining time variable parameters, patient's past medical history health records, past medical history risk impact weights, public disease health risk factors, corresponding predicted disease evolution rates of consulting patients under public disease epidemic situations, public disease health risk impact weights, patient's current disease health status measurement, patient's current disease health status attenuation coefficient, user's current disease health past latent risk factors, corresponding weight coefficients and related parameters to perform disease risk association quantitative calculation on the consulting patient user's current disease health status to quantify the correlation of disease risks. The risk association calculation formula takes into account multiple factors, such as the weight of latent risk factors, the impact of public disease epidemic situations on the patient's health status, and the stability of the patient's current disease status, and finally obtains the disease risk correlation between the patient's past medical history and the public condition and the user's current health status.

[0107] Preferably, the disease risk association between the patient's past medical history and public conditions and the user's current health status is compared and judged according to a preset disease risk association threshold. If the disease risk association is greater than or equal to the preset disease risk association threshold, the disease risk association between the patient's past medical history and public conditions and the user's current health status is determined as an explicit association relationship; if the disease risk association is less than the preset disease risk association threshold, the disease risk association between the patient's past medical history and public conditions and the user's current health status is determined as an implicit association relationship; and an association connection is performed based on the explicit association relationship and the implicit association relationship to generate a disease association relationship between the patient's past medical history and public conditions and the current health status of the consulting patient user.

[0108] In an embodiment of the present invention, a disease risk association threshold is preset, which is used to determine whether the patient's disease risk association degree reaches an explicit or implicit association relationship. If the calculated disease risk association degree is greater than or equal to the threshold, it is considered that there is an explicit association relationship between the patient's past medical history and public conditions and the patient's current health status, otherwise it is an implicit association relationship. This process can be implemented through a comparison judgment function (such as a simple comparison operator or a more complex logistic regression model). Then, the results of the explicit and implicit association relationships are processed and connected separately to form a complete disease association relationship map. The explicit association relationship can be used to provide direct consulting advice or risk management solutions, while the implicit association relationship provides a deeper analysis basis for potential disease risks. Through data association analysis, the disease association relationship between the patient's past medical history and public conditions and the current health status of the consulting patient user is ultimately generated.

[0109] Furthermore, the disease health risk association calculation formula is specifically as follows:

[0110]

[0111] In the formula, G L is the disease risk correlation between the patient's past medical history and public condition and the user's current health status, T is the integral time range parameter, t is the time variable parameter, and D h (t) is the patient’s medical history health record at time t, m is the number of health problems in the patient’s medical history, h j (t) is the known health risk score of the jth health problem at time t, θ j is the weight coefficient corresponding to the jth health problem, α1 is the risk impact weight of previous medical history, F a (t) is the public disease health risk factor at time t, I(t) is the number of people infected with the public disease at time t, N is the total population, R0 is the basic reproduction number, f p is the predicted rate of disease evolution of consulting patients corresponding to the epidemic situation of public diseases, α2 is the impact weight of public disease health risk, D c is the metric value corresponding to the patient's current disease health status, β is the attenuation coefficient of the patient's current disease health status, n is the total number of the user's current disease health past hidden risk factors, i is the item index of the user's current disease health past hidden risk factors, S i is the hidden risk factor of the current disease and health history of the i-th user, γ i is the weight coefficient corresponding to the hidden risk factor of the current disease and health history of the i-th user, and η is the correction coefficient of the disease risk correlation.

[0112] The present invention obtains a disease-health risk association calculation formula by using a specific mathematical model and verifying it, which is used to perform quantitative calculation of the disease risk association of the current disease health status of the consulting patient user. The disease-health risk association calculation formula predicts the disease risk by combining the patient's past medical history and current health status, so that it can reflect the patient's health trend in multiple dimensions. Past medical history data reflects the patient's past disease experience, which is important for predicting future health risks. For patients with chronic diseases or recurrent diseases, the impact of past medical history is particularly important, and the current health status can reflect the patient's current health status. By evaluating the patient's current disease status, it helps doctors to understand changes in the disease in a timely manner. This comprehensive assessment based on historical and current health conditions avoids relying solely on one aspect of information and can more accurately predict the patient's health risks. The formula makes dynamic predictions by introducing public disease health risk factors and the patient disease evolution rate under the public disease epidemic situation. This reflects the impact of public health conditions (such as epidemic outbreaks) on individual health in different time and social environments. By introducing public disease health risk factors, risk assessment can be adjusted in time according to changes in the public health environment (such as epidemic outbreaks, seasonal epidemics, etc.). By introducing the patient disease evolution rate, it can be adjusted according to the public health situation to ensure that the patient's disease evolution prediction takes into account changes in the external environment. This method can dynamically predict the evolution of the disease and make risk assessment more accurate in combination with changes in the public health environment. The multiple weight coefficients and attenuation coefficients in the formula allow the impact of different factors to be adjusted according to actual conditions. The corresponding weight coefficients are used to measure the impact of past medical history and public disease health risk factors on the current disease status, ensuring the relative importance of different historical and environmental factors on risk assessment. The attenuation coefficient is used to adjust the impact of the current health status on risk assessment. Over time, the impact of the patient's current disease may decay, so the attenuation coefficient is needed to quantify this impact. The weight coefficient reflects the specific impact of the user's current disease health history hidden risk factors. These factors come from the patient's individual specific health risks and can accurately assess certain potential health threats. The use of these weight coefficients and attenuation coefficients allows the model to flexibly adapt to individual differences, medical history and environmental changes of different patients, thereby improving the accuracy of the assessment. In summary, this formula fully considers the disease risk correlation G between the patient's past medical history and public conditions on the user's current health status L , integration time range parameter T, time variable parameter t, patient's medical history health record D at time t h (t), the number of health problems in the past medical history m, the known health risk score h of the jth health problem at time t j (t), the weight coefficient θ corresponding to the jth health problem j, the risk impact weight of past medical history α1, the public disease health risk factor F at time t a (t), the number of people infected with the public disease at time t I(t), the total population N, the basic reproduction number R0, and the predicted rate of disease evolution of the consulting patients corresponding to the public disease epidemic situation f p , the public disease health risk impact weight α2, the metric value D corresponding to the patient's current disease health status c , the attenuation coefficient of the patient's current disease health status β, the total number of the user's current disease health past hidden risk factors n, the item index i of the user's current disease health past hidden risk factors, the i-th user's current disease health past hidden risk factor S i , the weight coefficient γ corresponding to the hidden risk factor of the current disease and health history of the i-th user i , the correction coefficient η of the disease risk association, where, by combining the number of health problems in the past medical history m, the known health risk score h of the jth health problem at time t j (t), the weight coefficient θ corresponding to the jth health problem j and the time variable parameter t constitute a patient's medical history health record D at time t h (t) It also forms a public disease health risk factor F at time t by combining the number of public disease infections I(t) at time t, the total population N, the basic reproduction number R0 and the time variable parameter t a (t) The disease risk correlation G between the patient's past medical history and public condition and the user's current health status L The correlation between the above parameters constitutes a functional relationship This formula can realize the quantitative calculation process of the disease risk association of the consulting patient user's current disease health status. At the same time, by introducing the correction coefficient η of the disease risk association, it can be adjusted according to the errors occurring in the calculation process, thereby improving the accuracy and applicability of the disease health risk association calculation formula.

[0113] Furthermore, the consultation disease category navigation analysis module includes the following functions:

[0114] Produce a disease and health profile for the basic conditions of the consulting patient user to obtain a disease and health profile for the consulting patient user;

[0115] In an embodiment of the present invention, by collecting the patient's basic health information, including but not limited to age, gender, height, weight, past medical history, family genetic history, living habits (such as diet, exercise, sleep quality, etc.), recent physical examination results and other data, big data technology is used to build the patient's health database, and data preprocessing and cleaning are performed based on this information to ensure the accuracy and completeness of the data. By analyzing the patient's physical examination results and medical history, the health status of the patient is classified and predicted using a machine learning algorithm to generate a preliminary health portrait. The health portrait integrates the patient's various indicators and forms a high-dimensional health information vector through feature extraction. By analyzing the correlation between various indicators, a disease health portrait of the patient is constructed, including disease risks, types of susceptible diseases, and current health status, and finally a disease health portrait of the consulting patient user is obtained.

[0116] Preferably, a disease health assessment analysis is performed on the disease health portrait of the consulting patient user to generate a disease health assessment report for the consulting patient user;

[0117] In an embodiment of the present invention, a multi-dimensional data analysis technology is used to conduct an in-depth assessment of the patient's disease health portrait. First, a health assessment model is used to perform indicator analysis based on the data in the patient's health portrait. For each patient, his or her portrait will be mapped to a preset health assessment standard. These standards include disease risk, chronic disease warning, lifestyle impact, etc. Different health factors are prioritized through a weighted algorithm to assess the patient's overall health status. Based on the assessment results, a detailed disease health assessment report is generated. The report will specifically list the patient's health risk points, such as the possibility of certain diseases, existing health problems, and suggestions for improving lifestyle habits. This report is presented in a data visualization manner, so that patients can clearly understand their health status and ultimately generate a disease health assessment report for consulting patient users.

[0118] Preferably, based on the consulting patient user's disease health assessment report, a health problem mapping analysis is performed on the disease health status corresponding to the consulting patient user's disease health portrait to generate the consulting patient user's disease health problem;

[0119] In an embodiment of the present invention, by using an intelligent health problem mapping system for further analysis based on a previously generated disease health assessment report, the system will automatically identify potential health problems mentioned in the report and match them with the patient's health portrait. For example, if the assessment report indicates that the patient is at risk of diabetes, the system will add the health problem of "potential risk of diabetes" to the patient's health portrait. Further mapping analysis will perform a multi-dimensional comparison of the patient's specific health data (such as blood sugar levels, BMI, family history, etc.), associate the recommendations in the health assessment with the patient's actual situation, and extract specific health problems. These problems may include potential chronic disease risks, early warning signs of acute diseases, health risks caused by lifestyle, etc., and generate a list of disease health problems, listing in detail the health matters that need attention, and finally generate a consultation on disease health problems for the patient user.

[0120] Preferably, based on the personal disease-health association map of the consulting patient user, the consulting patient user's disease-health problem is analyzed for the disease-category classification, and the disease-category classification of the corresponding disease-health problem of the consulting patient user is obtained;

[0121] In an embodiment of the present invention, the health problems are mapped to relevant disease departments by comparing the patient's disease and health problems with the corresponding medical classification system (such as ICD-10). For example, diabetes-related health problems will be classified into "endocrinology" or "diabetes"; cardiovascular problems will be classified into "cardiology" or "vascular surgery". This process uses the consulting patient user's personal disease-health association map and disease department classification standards obtained from previous analysis, combined with natural language processing technology, to accurately classify health problems. According to the patient's specific problems, it will automatically identify which departments are most relevant and provide a detailed report on department attribution. This process is automated through algorithms, and patients do not need to make complex choices. According to the correlation between their health portraits and problems, department recommendations related to health problems are quickly generated, and finally the disease and health problem department attribution corresponding to the consulting patient user is obtained.

[0122] Preferably, a department navigation suggestion analysis is performed based on the department affiliation of the disease and health problem corresponding to the consulting patient user to generate personal disease and health department guidance information corresponding to the consulting patient user.

[0123] In an embodiment of the present invention, professional department navigation suggestions are provided to patients based on the department classification results of the patient's disease and health problems. Specifically, suitable medical departments and experts are automatically recommended based on the department classification of the patient's health problems. For example, if the patient is at risk of cardiovascular disease, the system will recommend "cardiology" or "cardiovascular surgery" and list the specific doctors in each department and their areas of expertise. At the same time, the nearest hospital or clinic is provided based on the patient's geographical location to help the patient seek medical treatment conveniently. The suggestion analysis will include suggestions on the medical process, recommendations on medical time, decision-making plans for medical treatment, and precautions, etc. The patient will receive a detailed department guide information to ensure that he or she can more effectively choose the appropriate department for consultation, improve medical efficiency and consultation results, and ultimately generate personal disease and health department guide information corresponding to the consulting patient user.

[0124] Further, the analysis of the disease category of the consulting patient user's disease and health problems based on the consulting patient user's personal disease and health association map includes:

[0125] Perform health problem semantic embedding analysis on the patient's disease and health problems to generate a user's disease and health problem semantic embedding vector;

[0126] In an embodiment of the present invention, by collecting disease and health problem data raised by patient users, the integrity and accuracy of the data content are ensured, and natural language processing technology, especially text semantic analysis models based on deep learning (such as BERT, GPT, etc.), are used to pre-process the health problems raised by patients, including word segmentation, stop word removal, part-of-speech tagging and other operations. After these pre-processing, the text of each health problem is input into a pre-trained semantic embedding model, which can convert each health problem into a semantic embedding vector of fixed dimension. The semantic embedding vector can reflect the semantic characteristics of the problem and capture the potential information in the health problem. The model generates a high-dimensional dense vector by calculating the semantic relationship between words as the embedding representation of the health problem. The semantic embedding vectors of all health problems will form a multidimensional vector space, and finally generate the semantic embedding vector of the user's disease and health problem.

[0127] Preferably, based on the semantic embedding vector of the user's disease and health problem, a disease and health urgency assessment analysis is performed on the consulting patient's disease and health problem to obtain the urgency of the consulting patient's disease and health problem;

[0128] In an embodiment of the present invention, the urgency of each health problem is evaluated by establishing an emergency assessment model for disease and health problems based on the previously generated semantic embedding vector of the disease and health problem. Here, a machine learning model, such as a support vector machine (SVM), a decision tree or a neural network, is used to classify and evaluate health problems. In this process, it is first necessary to establish a training data set containing disease urgency annotations based on historical disease data and the judgment criteria of medical experts. The data set will be labeled according to dimensions such as the severity of the disease and the acuteness of the symptoms. The semantic embedding vector of the user's health problem is used as input, and the model is trained based on the labeled data to obtain an urgency assessment model. After training, the model can automatically evaluate the urgency of the input health problem based on its semantic vector, generate an urgency score or label, indicate the degree of urgency of the health problem, and finally obtain the urgency of the disease and health problem of the consulting patient user.

[0129] Preferably, personal health goal analysis is performed on the disease and health problems of the consulting patient user to obtain the personal disease and health goals of the consulting patient user;

[0130] In an embodiment of the present invention, personalized health goals are formulated based on analyzing the patient's health record, historical medical history, family medical history and the patient's current health status. By introducing big data analysis technology, the patient's health trend data is extracted by utilizing historical data, medical records, living habits and disease databases related to the patient in the patient's health record. These data are subjected to cluster analysis, association analysis and other methods to identify the patient's potential health problems and propose personalized health management goals based on the individual differences of the patient. For example, for diabetic patients, the health goal is to control blood sugar levels; for patients with cardiovascular disease, the health goal is to improve heart health. Through such analysis, the personal health goals obtained can cover multiple dimensions such as disease management, lifestyle improvement, regular check-ups, etc., to ensure the comprehensiveness and pertinence of the goals, and ultimately obtain the personal disease health goals of the consulting patient user.

[0131] Preferably, based on the consulting patient user's personal disease-health association map, a disease potential association hazard analysis is performed on the consulting patient user's personal disease-health goal to obtain the consulting patient user's personal disease potential association hazard;

[0132] In an embodiment of the present invention, by utilizing the previously generated personal disease-health association map of the patient, the correlation between the user's health goals and potential diseases is analyzed. At this time, the disease-health association map is established through data mining technology. The disease, symptoms, drugs, decision-making methods and other information are connected in the form of nodes in the map. Through big data analysis, the potential connection between the patient's current health goals and other diseases is discovered. For example, the patient's cardiovascular health goals have a direct or indirect relationship with other diseases such as diabetes and hypertension. In order to evaluate the potential harmfulness of the disease, graph analysis algorithms such as PageRank algorithm, graph convolutional network (GCN), etc. can be used. By calculating the nodes and edges in the health association graph, the potential degree of correlation and harmfulness between the diseases are analyzed. This analysis method can reveal the chain effect between certain diseases, predict the health risks that occur, and ultimately obtain the potential correlation harmfulness of the consulting patient's personal disease.

[0133] Preferably, based on the urgency of the consulting patient user's disease and health problem and the potential associated hazards of the consulting patient user's personal disease, the corresponding consulting patient user's disease and health problem is analyzed for the disease category, and the corresponding disease category of the consulting patient user is obtained.

[0134] In an embodiment of the present invention, based on previous analysis results and combined with medical expertise, the patient's health problems are classified into corresponding medical departments. Through urgency assessment and potential associated hazard analysis, the priority of the health problem is first determined. For example, some health problems need to be handled by the emergency department, while some non-urgent health problems can be classified into internal medicine or other specialties. At this time, a rule system can be constructed or a deep learning model can be applied to automatically classify health problems into different departments. For example, health problems of heart disease will be classified into the cardiovascular department, while diabetes-related problems will be classified into the endocrinology department. By training historical health problem data, the model can accurately determine the department category of the health problem based on the semantic features, urgency scores and associated hazards of the health problem. This analysis process can not only help patients quickly find the right department, but also improve the allocation efficiency of medical resources, avoid patients wasting time due to unclear departments, and finally obtain the department category of the disease health problem corresponding to the consulting patient user.

[0135] Furthermore, the user disease consultation application consent module includes the following functions:

[0136] The consulting patient user selects the corresponding department doctor to apply for disease consultation based on the corresponding personal disease health department medical guide information, so as to generate a patient user disease health matching doctor consultation application;

[0137] In an embodiment of the present invention, the consulting patient user first obtains the department information that matches his or her health status through the disease and health department guidance system. The guidance process is based on big data analysis of the patient user's personal health information, such as medical history, symptoms, diagnosis records, etc., and compares these data with the professional fields, disease types, previous diagnosis and treatment records, etc. of the doctors in each department. The patient user selects a suitable department through the system interface and submits a disease consultation application. The system will recommend a doctor who best matches the patient's needs based on the disease type, symptom manifestations, historical health data and the doctor's professional direction through an intelligent algorithm. After the patient completes the selection, a disease and health matching doctor consultation application will be generated, which will be sent to the relevant department doctor, and the department doctor will wait for the processing of the application, and finally a disease and health matching doctor consultation application will be generated for the patient user.

[0138] Preferably, according to the patient user's disease health matching doctor consultation application, the patient consultation queue data and online inquiry activity data corresponding to the department doctor are obtained, wherein the online inquiry activity data includes the inquiry response speed and online inquiry activity of the department doctor;

[0139] In an embodiment of the present invention, by accessing the backend database, the queuing data and online inquiry activity data of doctors in relevant departments are obtained. The queuing data includes information such as the number of patients to be processed by the current department doctor, the waiting time in the queue for each patient, and the estimated processing time. The online inquiry activity data includes the inquiry response speed, processing efficiency, and the doctor's activity in participating in online inquiries within a specific time period of the department doctor. These data can reflect the doctor's processing ability and response timeliness in online consultation. These data are compared with the disease type and severity in the patient's consultation application. If the queuing data indicates that the doctor is currently unable to respond in time, the doctor's activity and queuing time will be evaluated, and other doctors with faster response speeds and higher activity will be recommended to ensure that patients can obtain consultation services in a timely manner, and finally obtain patient consultation queuing data and online inquiry activity data.

[0140] Preferably, a requeuing consultation application is made to the next department doctor corresponding to the personal disease and health department medical guide information according to the patient consultation queue data and the online inquiry activity data, so as to generate a consultation application request for the department doctor to agree;

[0141] In an embodiment of the present invention, by judging whether the patient can successfully consult with the currently selected department doctor based on the previously acquired queuing data and online inquiry activity data, if the queuing time of the current department doctor is too long or the doctor's activity is low, the patient user will be automatically recommended to re-select a next department doctor with a shorter queuing time, faster response speed and higher activity based on the data analysis results. At this time, the patient's consultation application will be regenerated and submitted to the new doctor to ensure that the patient can get help as soon as possible. During the re-queuing process, the recommended doctor will be dynamically adjusted through continuous analysis of the patient's health data. Each recommendation will take into account the doctor's real-time availability to ensure that the patient's consultation needs are met, and a corresponding doctor consent consultation application request will be generated, and finally the department doctor will agree to the consultation application request.

[0142] Preferably, according to the department doctor's consent to the consultation application request, the corresponding department doctor is selected to perform disease consultation on the basic situation corresponding to the consulting patient user, so as to complete the disease consultation result of the corresponding consulting patient user.

[0143] In an embodiment of the present invention, when the department doctor receives the patient's consultation application, the patient's basic information will be displayed to the doctor, including the patient's medical history, symptoms, known test results and other important health data. After viewing this information, the doctor will make a disease consultation decision based on the patient's specific situation, and will provide an auxiliary decision-making tool to help the doctor quickly make a judgment on the patient's condition. The doctor can use the tool to obtain reference information on similar cases, view the epidemic trends of the disease or the latest treatment plans, etc. In addition, the doctor can also interact with the patient in real time online through the platform to further understand the patient's specific condition. With the support of the system, the doctor will be able to provide patients with personalized disease consultation services more efficiently and accurately, and ultimately obtain consultation results. After completing the consultation, a detailed consultation record will be generated and sent to the patient user to ensure that the patient can obtain the required health guidance and advice, and ultimately complete the disease consultation results for the corresponding consulting patient user.

[0144] Furthermore, the requeuing consultation application for the next department doctor corresponding to the personal disease and health department medical guide information according to the patient consultation queue data and the online inquiry activity data includes:

[0145] Obtain the corresponding available time of consulting doctors and the total number of consulting doctors in line through the patient consultation queue data, and perform queue time prediction analysis based on the available time of consulting doctors and the total number of consulting doctors in line to obtain the consultation queue time of doctors in the current department;

[0146] In an embodiment of the present invention, the system obtains the patient's consultation queue data, which includes key indicators such as the department doctor information of the patient's current queue, the accessible time of the doctors in each department, and the total number of people in the queue. Using this data, the system will analyze the accessible time of each doctor, calculate the number of patients the doctor can receive in a certain time period in the future, and deduce the doctor's queue time based on this. In specific operations, the patient queue data is first read from the database, and matched with the department doctor's work schedule (such as outpatient schedule, doctor's accessible time period), and the number of people in the queue for each doctor in different time periods is calculated. At the same time, based on the doctor's historical queue data, the average time of each doctor's consultation, and the current patient's consultation needs, the system will generate an estimated queue time. The queue time prediction result is a dynamic, real-time updated value, which is based on a comprehensive prediction of factors such as patient consultation needs, doctor's reception capacity, and the number of people in the queue, and finally the current department doctor's consultation queue time is obtained.

[0147] Preferably, based on the total number of consultation doctor queues, the current department doctor consultation queue length, and online inquiry activity data, the department doctor corresponding to the personal disease and health department medical guide information is quantitatively calculated to obtain the patient consultation doctor queue activity load index;

[0148] In the embodiment of the present invention, a suitable queuing active load calculation formula is formed by combining the total number of consulting doctors in the queue, the current department doctor consultation queue time, the online activity and inquiry response speed of the department doctors in the online inquiry activity data, and related parameters to perform a quantitative calculation of the consultation queue active load of the department doctors corresponding to the personal disease and health department medical guide information, so as to quantify the active load index of each department doctor, for example Among them, L a Active load index for patient consultation in doctor queue, P q is the total number of people queuing for consultation with doctors, τ z A is the waiting time for doctor consultation in the current department. a is the online activity of doctors in the department, V r This index not only reflects the doctor's work pressure, but also reflects whether the doctor can efficiently handle the patient's consultation requests within a certain period of time, and finally obtains the active load index of the patient consultation doctor queue.

[0149] Preferably, the patient consultation doctor queue activity load index is compared and judged according to a preset queue activity load threshold to generate a department doctor's consent request for the consultation application.

[0150] In an embodiment of the present invention, the queue activity load index of the consulting doctor currently selected by the patient is compared and judged according to a preset queue activity load threshold. First, the system compares the doctor's queue activity load index with the preset threshold. If it is greater than or equal to the threshold, it will be judged that the current doctor's queue pressure is too large, and the patient will be automatically prompted to queue again and choose the next doctor or a doctor in a related department for consultation. If the doctor selected by the patient is less than the preset threshold, it means that the current doctor's queue pressure is within a controllable range. The system will continue to reserve the patient's queue position until the queue reaches the doctor and the doctor agrees, and finally generate a request for the department doctor to agree to the consultation application.

[0151] Furthermore, the specific process of the comparison and judgment is as follows:

[0152] If the patient's consultation doctor queue activity load index is greater than or equal to the preset queue activity load threshold, the patient needs to queue again to apply for the next department doctor corresponding to the personal disease and health department medical guide information; if the patient's consultation doctor queue activity load index is less than the preset queue activity load threshold, the patient will continue to queue for the current corresponding department doctor until the corresponding department doctor agrees to the consultation application when the time comes, thereby generating a request for the department doctor to agree to the consultation application.

[0153] In an embodiment of the present invention, if the doctor's queue active load index is greater than or equal to the threshold, it will be judged that the current doctor's queue pressure is too large and the patient's waiting time is too long. At this time, the system will automatically prompt the patient to re-queue and select the next doctor or the doctor of the relevant department for consultation. In the specific operation, the patient will receive a prompt, the system will provide a list of candidate doctors, and recommend doctors with lower queue loads to queue again. At this time, the patient needs to select a suitable doctor to re-queue according to the new recommendation information. If the patient chooses to re-queue, a new queue request will be automatically generated for the patient and the patient's queue data will be updated. On the other hand, if the queue active load index of the doctor selected by the patient is less than the preset threshold, it means that the current doctor's queue pressure is within a controllable range. The system will continue to retain the patient's queue position until the queue reaches the doctor and the doctor agrees. At this time, the system will continue to monitor the doctor's queue status and automatically generate a department doctor's consent consultation application request when the patient's queue arrives, ensuring that the patient can communicate and consult with the doctor smoothly, and finally generate a department doctor's consent consultation application request.

[0154] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A disease consultation system based on big data, characterized in that: Includes the following modules: The consultation request health data acquisition module is used to obtain the consultation request of the disease patient user, and based on the consultation request of the disease patient user, obtain the personal disease health data uploaded by the consulting patient user on the disease consultation platform and the patient historical health data and public medical health data corresponding to the consultation background database; The disease-health association map construction module is used to analyze the association between personal disease-health data and the user's current health status based on the patient's historical health data and public medical health data, so as to generate the disease association relationship between the patient's past medical history and public conditions and the current health status of the consulting patient user; Based on the patient's past medical history and the disease association relationship between the public condition and the current health status of the consulting patient user, a disease-health association map is constructed for the personal disease-health data to generate a personal disease-health association map for the consulting patient user; The consultation disease department navigation analysis module is used to perform consultation disease department navigation analysis on the basic situation of the consultation patient user based on the consultation patient user's personal disease health association map, so as to generate the consultation patient user's personal disease health department guidance information; The user disease consultation application consent module is used for consulting patient users to select the corresponding department doctor to apply for disease consultation according to the corresponding personal disease health department medical guide information, and obtain the corresponding patient consultation queue data and online inquiry active data of the department doctor, and re-queue the consultation application according to the patient consultation queue data and online inquiry active data to generate a consultation application request for the department doctor to agree; According to the department doctor's consent to the consultation application request, the corresponding department doctor is selected to conduct disease consultation on the basic situation of the consulting patient user to complete the disease consultation result of the corresponding consulting patient user.

2. The disease consultation system based on big data according to claim 1 is characterized in that: The consultation request health data acquisition module includes the following functions: Obtain consultation requests from disease patients; Obtain corresponding disease consultation patient user needs and consultation information input by consulting patient users through disease patient user consultation requests, and perform deep semantic analysis on the consultation information input by consulting patient users to obtain patient user consultation topic content classification; Prioritize and sort disease patient user consultation requests based on disease consultation patient user needs and patient user consultation topic content classification to generate a patient user consultation request priority sequence; According to the consultation request queuing sequence corresponding to the patient user's consultation request priority sequence, the personal disease health data uploaded by the corresponding consulting patient user on the disease consultation platform and the patient historical health data corresponding to the consultation background database are obtained; Based on the patient user consultation subject content classification corresponding to the consultation request queuing sequence, the latest public medical information in the consultation background database is matched with the subject content to obtain public medical health data.

3. The disease consultation system based on big data according to claim 1 is characterized in that: The disease-health association map construction module includes the following functions: Conduct statistical analysis on the patient's historical health data to obtain the patient's medical history data; Conduct statistical analysis of disease epidemic trends on public medical health data to obtain the epidemic trends of similar public medical diseases; Conduct current health status evaluation and analysis on the personal disease health data corresponding to the consulting patient user to obtain the current disease health status of the consulting patient user; Based on the patient's past medical history data and the prevalence of similar diseases in public medicine, the patient's current disease health status is analyzed to generate a disease association relationship between the patient's past medical history and public conditions and the patient's current health status; Based on the patient's past medical history and the disease association relationship between the public condition and the current health status of the consulting patient user, a disease-health association map is constructed for the personal disease-health data to generate a personal disease-health association map for the consulting patient user.

4. The disease consultation system based on big data according to claim 3 is characterized in that: The analysis of the current health status of the consulting patient user based on the previous medical history data of the consulting patient user and the epidemic situation of similar diseases in public medicine includes: Performing a past medical history incidence analysis on the past medical history data of the consulting patient user to obtain the past medical history incidence of the consulting patient user; Based on the past medical history incidence rate of the consulting patient user, the hidden risk assessment analysis of the current disease health status of the consulting patient user is performed to obtain the hidden risk factors of the user's current disease health history; Perform time-series synchronous prediction on the epidemic situation of similar public medical diseases and the current disease health status of consulting patient users to generate the corresponding epidemic situation of public medical diseases and the current disease status of consulting patient users in the same time period; predict the patient disease evolution rate of the corresponding current disease status of consulting patient users based on the corresponding epidemic situation of public medical diseases in the same time period to obtain the corresponding predicted rate of consulting patient disease evolution under the public disease epidemic situation; Based on the user's current disease health history implicit risk factors and the corresponding predicted rate of disease evolution of the consulting patient under the public disease epidemic situation, the disease health risk association calculation formula is used to quantitatively calculate the disease risk association of the consulting patient's current disease health status, so as to obtain the disease risk association between the patient's previous medical history and the public condition and the user's current health status; The disease risk association between the patient's past medical history and public conditions and the user's current health status is compared and judged according to a preset disease risk association threshold. If the disease risk association is greater than or equal to the preset disease risk association threshold, the disease risk association between the patient's past medical history and public conditions and the user's current health status is determined as an explicit association relationship; if the disease risk association is less than the preset disease risk association threshold, the disease risk association between the patient's past medical history and public conditions and the user's current health status is determined as an implicit association relationship; and association connections are made based on the explicit association relationship and the implicit association relationship to generate a disease association relationship between the patient's past medical history and public conditions and the current health status of the consulting patient user.

5. The disease consultation system based on big data according to claim 4 is characterized in that: The disease health risk association calculation formula is specifically: In the formula, G L is the disease risk correlation between the patient's past medical history and public condition and the user's current health status, T is the integral time range parameter, t is the time variable parameter, and D h (t) is the patient’s medical history health record at time t, m is the number of health problems in the patient’s medical history, h j (t) is the known health risk score of the jth health problem at time t, θ j is the weight coefficient corresponding to the jth health problem, α1 is the risk impact weight of previous medical history, F a (t) is the public disease health risk factor at time t, I(t) is the number of people infected with the public disease at time t, N is the total population, R0 is the basic reproduction number, f p is the predicted rate of disease evolution of consulting patients corresponding to the epidemic situation of public diseases, α2 is the impact weight of public disease health risk, D c is the metric value corresponding to the patient's current disease health status, β is the attenuation coefficient of the patient's current disease health status, n is the total number of the user's current disease health past hidden risk factors, i is the item index of the user's current disease health past hidden risk factors, S i is the hidden risk factor of the current disease and health history of the i-th user, γ i is the weight coefficient corresponding to the hidden risk factor of the current disease and health history of the i-th user, and η is the correction coefficient of the disease risk correlation.

6. The disease consultation system based on big data according to claim 1 is characterized in that: The consulting disease category navigation analysis module includes the following functions: Produce a disease and health profile for the basic conditions of the consulting patient user to obtain a disease and health profile for the consulting patient user; Conduct disease and health assessment analysis on the disease and health portrait of the consulting patient user to generate a disease and health assessment report for the consulting patient user; Based on the consulting patient user's disease health assessment report, a health problem mapping analysis is performed on the disease health status corresponding to the consulting patient user's disease health profile to generate the consulting patient user's disease health problems; Based on the personal disease and health association map of the consulting patient user, the consulting patient user's disease and health problems are analyzed for the disease and health category attribution, and the disease and health problem category attribution corresponding to the consulting patient user is obtained; According to the department affiliation of the disease and health problems corresponding to the consulting patient users, a department navigation suggestion analysis is performed to generate personal disease and health department guide information corresponding to the consulting patient users.

7. The disease consultation system based on big data according to claim 6 is characterized in that: The analysis of the disease category of the consulting patient user's disease and health problems based on the consulting patient user's personal disease and health association map includes: Perform health problem semantic embedding analysis on the patient's disease and health problems to generate a user's disease and health problem semantic embedding vector; Based on the semantic embedding vector of the user's disease and health problem, the disease and health urgency assessment analysis is performed on the consulting patient's disease and health problem to obtain the urgency of the consulting patient's disease and health problem; Conduct personal health goal analysis on the disease and health problems of consulting patient users to obtain personal disease and health goals of consulting patient users; Based on the consulting patient user's personal disease-health association map, the consulting patient user's personal disease-health goals are analyzed for potential disease-related hazards, and the consulting patient user's personal disease-related hazards are obtained; Based on the urgency of the consulting patient's disease and health problems and the potential associated hazards of the consulting patient's personal diseases, the corresponding consulting patient's disease and health problems are analyzed to obtain the corresponding disease and health problem category of the consulting patient.

8. The disease consultation system based on big data according to claim 1 is characterized in that: The user disease consultation application consent module includes the following functions: The consulting patient user selects the corresponding department doctor to apply for disease consultation based on the corresponding personal disease health department medical guide information, so as to generate a patient user disease health matching doctor consultation application; According to the patient user's disease health matching doctor consultation application, obtain the patient consultation queue data and online inquiry activity data corresponding to the department doctor, where the online inquiry activity data includes the inquiry response speed and online inquiry activity of the department doctor; According to the patient consultation queue data and online inquiry activity data, a re-queue consultation application is made to the next department doctor corresponding to the personal disease and health department medical guide information to generate a consultation application consent request from the department doctor; According to the department doctor's consent to the consultation application request, the corresponding department doctor is selected to conduct disease consultation on the basic situation of the consulting patient user to complete the disease consultation result of the corresponding consulting patient user.

9. The disease consultation system based on big data according to claim 8, characterized in that: The requeuing consultation application for the next department doctor corresponding to the personal disease and health department medical guide information according to the patient consultation queue data and the online inquiry activity data includes: Obtain the corresponding available time of consulting doctors and the total number of consulting doctors in line through the patient consultation queue data, and perform queue time prediction analysis based on the available time of consulting doctors and the total number of consulting doctors in line to obtain the consultation queue time of doctors in the current department; Based on the total number of consultation doctors’ queues, the current consultation queue time of doctors in the department, and the online inquiry activity data, the consultation queue activity load of the department doctors corresponding to the personal disease and health department medical guide information is quantitatively calculated to obtain the patient consultation doctor queue activity load index; The patient consultation doctor queue active load index is compared and judged according to the preset queue active load threshold to generate a department doctor's consent consultation application request.

10. The disease consultation system based on big data according to claim 9, characterized in that: The specific process of the comparison and judgment is as follows: If the patient's consultation doctor queue activity load index is greater than or equal to the preset queue activity load threshold, the patient needs to queue again to apply for the next department doctor corresponding to the personal disease and health department medical guide information; if the patient's consultation doctor queue activity load index is less than the preset queue activity load threshold, the patient will continue to queue for the current corresponding department doctor until the corresponding department doctor agrees to the consultation application when the time comes, thereby generating a request for the department doctor to agree to the consultation application.

Images