A health warning method and system based on health labels

Abstract

The present invention relates to the technical field of health data processing, and specifically provides a health warning method and system based on health tags, wherein the method includes: obtaining a user's historical driving data; determining the user's occupation based on the user's historical driving data; determining the user's associated potential diseases based on the user's occupation; determining the user's driving habits based on the user's historical driving data; obtaining the user's physiological state information; determining the user's health tag based on the disease characteristics of the user's associated potential diseases, the user's driving habits and physiological state information; generating health status prompt information based on the user's health tag, which has the advantage of automatically supervising the driver's health status based on driving data.

Description

Technical Field

[0001] The present invention relates to the technical field of health data processing, and in particular to a health warning method and system based on health tags. Background Art

[0002] With the rapid development of the automobile manufacturing industry, cars have played an increasingly important role in daily life, but a large number of cars and complex roads are also accompanied by more frequent traffic accidents. According to statistics, more than 95% of traffic accidents are related to the driver's state and operation. The driver's health is closely related to driving safety. However, in the current fast-paced life, a large number of drivers are in a sub-healthy state, which further increases the probability of traffic accidents. In addition, long-term driving can easily lead to occupational diseases such as lumbar spondylosis, and mental and physical fatigue and irregular work and rest also affect the driver's physical health.

[0003] In recent years, big data has developed rapidly and has great significance in medicine. If the driver's health big data is collected through the Internet of Vehicles and used in the medical field, it will be of great significance to accurately diagnose the driver's health status and predict the driver's potential diseases.

[0004] Therefore, there is a need to provide a health warning method and system based on health labels, which can be used to automatically monitor the health status of drivers based on driving data. Summary of the invention

[0005] The present invention provides a health warning method based on health tags, including: obtaining a user's historical driving data; determining the user's occupation based on the user's historical driving data; determining the user's associated potential diseases based on the user's occupation; determining the user's driving habits based on the user's historical driving data; obtaining the user's physiological state information; determining the user's health tag based on the disease characteristics of the user's associated potential diseases, the user's driving habits and physiological state information; and generating health status prompt information based on the user's health tag.

[0006] Furthermore, based on the user's historical driving data, the user's occupation is determined, including: establishing driving profiles corresponding to multiple occupations, wherein the driving profiles include multiple driving tags; based on the user's historical driving data, determining the user's driving profile; for each occupation, determining the driving profile similarity between the driving profile corresponding to the occupation and the user's driving profile; based on the similarity of the driving profiles corresponding to each occupation, determining the user's occupation.

[0007] Furthermore, based on the user's historical driving data, determining the user's driving profile includes: based on the user's historical driving data, determining the user's destination discreteness label, driving time discreteness label, average driving time label and destination feature label, wherein the multiple driving labels include at least the destination discreteness label, driving time discreteness label, average driving time label and destination feature label.

[0008] Furthermore, determining the driving profile similarity between the driving profile corresponding to the occupation and the driving profile of the user includes: calculating the destination discreteness label of the user's driving profile and the destination discreteness label of the driving profile corresponding to the occupation, and calculating a first label difference; calculating the driving time discreteness label of the user's driving profile and the driving time discreteness label of the driving profile corresponding to the occupation, and calculating a second label difference; calculating the average driving time label of the user's driving profile and the average driving time label of the driving profile corresponding to the occupation, and calculating a third label difference; calculating the destination feature label of the user's driving profile and the destination feature label of the driving profile corresponding to the occupation, and calculating a fourth label difference; based on the first label difference, the second label difference, the third label difference and the fourth label difference, determining the driving profile similarity between the driving profile corresponding to the occupation and the driving profile of the user.

[0009] Furthermore, based on the user's occupation, the associated potential diseases of the user are determined, including: establishing a knowledge graph, wherein the knowledge graph includes three types of nodes, a first type of node is used to represent the occupation, a second type of node is used to represent the associated potential diseases, and a third type of node is used to represent the disease characteristics of the associated potential diseases; the associated potential diseases of the nodes representing the user's occupation in the knowledge graph are used as the associated potential diseases of the user.

[0010] Furthermore, based on the user's historical driving data, the user's driving habits are determined, including: based on the user's historical driving data, determining the user's driving action habits; based on the user's historical driving data, determining the user's vehicle control habits; based on the user's historical driving data, determining the user's driving fatigue information; based on the user's historical driving data, determining the user's reaction information.

[0011] Furthermore, based on the disease characteristics of the user's associated potential diseases, the user's driving habits and physiological state information, the health label of the user is determined, including: determining the driving habits corresponding to each associated potential disease of the user; for each associated potential disease of the user, determining the matching degree of the disease characteristics corresponding to the associated potential disease based on the user's physiological state information and the disease characteristics of the user's associated potential diseases; for each associated potential disease of the user, determining the matching degree of the driving habits corresponding to the associated potential disease based on the user's driving habits and the driving habits corresponding to the associated potential disease; for each associated potential disease of the user, determining the disease matching degree corresponding to the associated potential disease based on the disease characteristics matching degree and the driving habits matching degree corresponding to the associated potential disease; based on the disease matching degree corresponding to each of the associated potential diseases, the health label of the user is determined.

[0012] Furthermore, based on the driving habits of the user and the driving habits corresponding to the associated potential diseases, the matching degree of the driving habits corresponding to the associated potential diseases is determined, including: obtaining historical driving data of multiple sample users of each associated potential disease; for each of the sample users, determining the driving action habits, vehicle control habits, driving fatigue information and reaction information of the sample user based on the historical driving data of the sample user; for each of the associated potential diseases, determining the driving action habits, vehicle control habits, driving fatigue information and reaction information corresponding to the associated potential disease based on the driving action habits, vehicle control habits, driving fatigue information and reaction information of multiple sample users of the associated potential disease.

[0013] Furthermore, health status prompt information is generated based on the user's health tag, including: generating potential disease warning information and driving habit intervention information based on the user's health tag.

[0014] The present invention provides a health warning system based on health labels, comprising a data acquisition module for acquiring historical driving data of a user; an occupation analysis module for determining the occupation of the user based on the historical driving data of the user; a disease screening module for determining the associated potential diseases of the user based on the occupation of the user; a data analysis module for determining the driving habits of the user based on the historical driving data of the user; a state acquisition module for acquiring the physiological state information of the user; a label determination module for determining the health label of the user based on the disease characteristics of the associated potential diseases of the user, the driving habits and physiological state information of the user; and a health prompt module for generating health state prompt information based on the health label of the user.

[0015] Compared with the prior art, the health warning method and system based on health labels provided in this specification have at least the following beneficial effects:

[0016] 1. By analyzing the user's historical driving data, the user's occupation is determined more accurately, so as to find the associated potential diseases that the user is at risk of. On this basis, the user's historical driving data is further analyzed to determine the user's driving habits. Combined with the user's physiological status information, the user's health label representing the user's risk of various associated potential diseases is determined, and then health status prompt information is generated according to the user's health label, so as to realize automatic supervision of the driver's health status based on driving data, predict and remind the driver of potential risks, and provide data support for subsequent improvement of the driver's health status, prevention of traffic accidents caused by abnormal physical health conditions, automatic rescue when the driver suddenly falls ill, and improvement of the safety of the car;

[0017] 2. By analyzing the user's historical driving data, the destination dispersion label, driving time dispersion label, average driving time label and destination feature label are determined, and then the first label difference, the second label difference, the third label difference and the fourth label difference are calculated to determine the driving profile similarity between the driving profile corresponding to the occupation and the user's driving profile, so as to achieve relatively fast and accurate determination of the user's occupation;

[0018] 3. By establishing a knowledge graph, we can sort out the correlation between different occupations, different diseases and different disease characteristics, and provide more accurate and comprehensive data support for determining the user's associated potential diseases. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0020] Figure 1 is a flow chart of a health warning method based on health tags shown in an embodiment of the present application;

[0021] Figure 2 is a flow chart for determining the similarity of driving portraits shown in one embodiment of the present application;

[0022] Figure 3 is a schematic diagram of a knowledge graph shown in an embodiment of the present application;

[0023] Figure 4 It is a module diagram of a health warning system based on health tags shown in one embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly introduces the drawings required for describing the embodiments.

[0025] Figure 1 is a flow chart of a health warning method based on health tags shown in an embodiment of the present application. Figure 1 As shown, a health warning method based on health labels may include the following process.

[0026] Step 110, obtaining the user's historical driving data.

[0027] Historical driving data may include the start time, end time, driving destination, user images during driving, driving path, and operating parameters of the vehicle during driving (e.g., steering wheel control information, gear shifting information, etc.) of each driving record.

[0028] Step 120 , determining the user's occupation based on the user's historical driving data.

[0029] Specifically include:

[0030] Establish driving profiles corresponding to various occupations, where the driving profiles include multiple driving labels;

[0031] Determine the user's driving profile based on the user's historical driving data;

[0032] For each occupation, determine the driving profile similarity between the driving profile corresponding to the occupation and the driving profile of the user;

[0033] Based on the similarity of the driving profiles corresponding to each occupation, the user's occupation is determined. For example, the occupation with the greatest driving profile similarity is taken as the user's occupation.

[0034] In some embodiments, determining a user's driving profile based on the user's historical driving data includes:

[0035] Based on the user's historical driving data, the user's destination discreteness label, driving time discreteness label, average driving time label and destination feature label are determined, wherein the multiple driving labels at least include the destination discreteness label, the driving time discreteness label, the average driving time label and the destination feature label.

[0036] Specifically, the user's destination dispersion can be calculated based on the following formula:

[0037]

[0038] Among them, D (i,1)is the destination discreteness of the ith user, N is the total number of driving records in the ith user’s historical driving data, is the driving destination of the n1th driving record in the historical driving data of the ith user, is the driving destination of the n2th driving record in the historical driving data of the ith user, is the distance between the driving destination of the n1th driving record in the historical driving data of the i-th user and the driving destination of the n2th driving record in the historical driving data of the i-th user, M1 is a preset parameter, and M1>0.

[0039] The user's driving time dispersion can be calculated based on the following formula:

[0040]

[0041] Among them, D (i,2) is the driving time discreteness of the ith user, is the starting time of the n1th driving record in the historical driving data of the ith user, is the starting time of the n2th driving record in the historical driving data of the ith user, is the starting time difference between the starting time of the n1th driving record in the historical driving data of the i-th user and the starting time of the n2th driving record in the historical driving data of the i-th user, M2 is a preset parameter, and M2>0.

[0042] The average driving time of a user can be calculated based on the following formula:

[0043]

[0044] Among them, T (i,average) is the average driving time of the i-th user, is the driving duration of the n1th driving record in the historical driving data of the i-th user.

[0045] The user's destination feature tag can be determined in the following ways:

[0046] Preset the digital identifier corresponding to each type of destination, for example, the digital identifier corresponding to a school is 1, the digital identifier corresponding to a hospital is 2, and so on;

[0047] The destination of each driving record in the user's historical driving data is used to determine the arrival frequency corresponding to each type of destination, wherein the arrival frequency of the i-th type of destination = the total number of driving records with the i-th type of destination as the destination in the user's historical driving data / the total number of driving records;

[0048] Based on the arrival frequency corresponding to each type of destination, multiple target types are determined, wherein the target type may be a destination type whose corresponding arrival frequency is greater than a preset arrival frequency threshold, and the user's destination feature sequence is determined, wherein the destination feature sequence is composed of digital identifiers corresponding to the target types arranged from large to small according to the arrival frequency.

[0049] Figure 2 is a flow chart of determining the similarity of driving portraits shown in an embodiment of the present application, such as Figure 2 As shown, determining the driving profile similarity between the driving profile corresponding to the occupation and the driving profile of the user includes:

[0050] Calculate the destination discreteness label of the user's driving profile and the destination discreteness label of the driving profile corresponding to the occupation, and calculate the first label difference;

[0051] Calculate the driving time dispersion label of the user's driving profile and the driving time dispersion label of the driving profile corresponding to the occupation, and calculate the second label difference;

[0052] Calculate the average driving time label of the user's driving profile and the average driving time label of the driving profile corresponding to the occupation, and calculate the third label difference;

[0053] Calculate the destination feature label of the user's driving profile and the destination feature label of the driving profile corresponding to the occupation, and calculate the fourth label difference;

[0054] Based on the first label difference, the second label difference, the third label difference and the fourth label difference, the driving profile similarity between the driving profile corresponding to the occupation and the driving profile of the user is determined.

[0055] Specifically, the driving profile similarity can be calculated based on the following formula:

[0056] S (i，j) =a1×D ((i，j)，1) +a2×D ((i，j)，2) +a3×D ((i，j)，3) +a4×D ((i，j)，4)

[0057] Among them, S (i,j) is the driving profile similarity between the driving profile corresponding to the jth occupation and the driving profile of the i-th user, D ((i,j),1) is the first label difference between the driving profile corresponding to the jth occupation and the driving profile of the i-th user, D ((i,j),2) is the second label difference between the driving profile corresponding to the jth occupation and the driving profile of the i-th user, D ((i,j),3) is the third label difference between the driving profile corresponding to the jth occupation and the driving profile of the i-th user, D ((i,j),4)is the fourth label difference between the driving profile corresponding to the jth occupation and the driving profile of the i-th user, D (i,j),4) Based on the cosine similarity of the destination feature sequence of the driving profile corresponding to the j-th occupation and the destination feature sequence of the driving profile of the ith user, a1, a2, a3 and a4 are preset weights, a1, a2, a3 and a4 are all greater than 0 and a1+a2+a3+a4=1.

[0058] It can be understood that by analyzing the user's historical driving data, the destination discreteness label, driving time discreteness label, average driving time label and destination feature label are determined, and then the first label difference, the second label difference, the third label difference and the fourth label difference are calculated to determine the driving profile similarity between the driving profile corresponding to the occupation and the user's driving profile, thereby achieving relatively fast and accurate determination of the user's occupation.

[0059] Step 130, based on the user's occupation, determine the user's associated potential diseases.

[0060] Specifically include:

[0061] Build a knowledge graph, where Figure 3 is a schematic diagram of a knowledge graph shown in an embodiment of the present application, such as Figure 3 As shown in the figure, the knowledge graph includes three types of nodes. The first node is used to represent occupations, the second node is used to represent associated potential diseases, and the third node is used to represent the disease characteristics of associated potential diseases. For example, the associated potential diseases of online ride-hailing drivers include cervical spondylosis, gastric disease, frozen shoulder and lumbar disc herniation. Among them, the disease characteristics of cervical spondylosis include limb numbness, dizziness, nausea, vomiting and tinnitus, the disease characteristics of gastric disease include pain, bloating, nausea and loss of appetite, the disease characteristics of frozen shoulder include pain, movement disorder, muscle atrophy, tenderness and fear of cold, and the disease characteristics of lumbar disc herniation include low back pain, sciatica, lower abdominal pain and lower limb numbness.

[0062] The associated potential diseases of the nodes representing the user's occupation in the knowledge graph are taken as the associated potential diseases of the user. For example, if the user's occupation is determined to be an online car-hailing driver, cervical spondylosis, gastric disease, frozen shoulder and lumbar disc herniation associated with the online car-hailing driver occupation are taken as the associated potential diseases of the user.

[0063] It is understandable that by establishing a knowledge graph, the correlation between different occupations, different diseases and different disease characteristics can be sorted out, providing more accurate and comprehensive data support for determining the user's associated potential diseases.

[0064] Step 140 , determining the user's driving habits based on the user's historical driving data.

[0065] Specifically include:

[0066] Determine the user's driving behavior based on the user's historical driving data;

[0067] Determine the user's vehicle control habits based on the user's historical driving data;

[0068] Determine the user's driving fatigue information based on the user's historical driving data;

[0069] Based on the user's historical driving data, the user's responsiveness information is determined.

[0070] Specifically, the user's historical driving data can be analyzed through a machine learning model to determine the user's driving action habits, vehicle control habits, driving fatigue information and reaction information, wherein the machine learning model can be a convolutional neural network (CNN) model.

[0071] Step 150: Acquire the user's physiological status information.

[0072] The user's physiological status information may include at least body temperature, heart rate, blood pressure, etc.

[0073] A physiological status acquisition device may be provided on the vehicle to acquire the physiological status information of the user, or the physiological status information of the user may be acquired from an external data source (eg, a physical examination center, etc.).

[0074] Step 160 , determining the user's health tag based on the disease characteristics of the user's associated potential diseases, the user's driving habits and physiological state information.

[0075] Specifically include:

[0076] Determine the user's driving habits for each associated potential disease;

[0077] For each associated potential disease of the user, determining a disease feature matching degree corresponding to the associated potential disease based on the user's physiological state information and the disease feature of the associated potential disease of the user;

[0078] For each associated potential disease of the user, determining a matching degree of the driving habits corresponding to the associated potential disease based on the driving habits of the user and the driving habits corresponding to the associated potential disease;

[0079] For each associated potential disease of the user, based on the disease feature matching degree and driving habit matching degree corresponding to the associated potential disease, determine the disease matching degree corresponding to the associated potential disease. For example, the disease feature matching degree and driving habit matching degree corresponding to the associated potential disease may be weighted summed to determine the disease matching degree corresponding to the associated potential disease.

[0080] The user's health label is determined based on the disease matching degree corresponding to each associated potential disease.

[0081] The matching degree of driving habits corresponding to the associated potential disease can be determined through a machine learning model based on the user's driving action habits, vehicle control habits, driving fatigue information and reaction information and the driving action habits, vehicle control habits, driving fatigue information and reaction information corresponding to the associated potential diseases. The matching degree of disease characteristics corresponding to the associated potential disease can be determined through a machine learning model based on the user's physiological state information and the disease characteristics of the user's associated potential diseases.

[0082] The user's health tag can represent the user's risk of contracting each associated potential disease. It can be understood that the higher the disease matching degree corresponding to the associated potential disease, the greater the user's risk of contracting the associated potential disease.

[0083] In some embodiments, based on the user's driving habits and the driving habits corresponding to the associated potential disease, determining the matching degree of the driving habits corresponding to the associated potential disease includes:

[0084] Obtaining historical driving data of multiple sample users for each associated potential disease;

[0085] For each sample user, based on the sample user's historical driving data, determine the sample user's driving action habits, vehicle control habits, driving fatigue information, and responsiveness information;

[0086] For each associated potential disease, the driving action habits, vehicle control habits, driving fatigue information and responsiveness information corresponding to the associated potential disease are determined based on the driving action habits, vehicle control habits, driving fatigue information and responsiveness information of multiple sample users of the associated potential disease.

[0087] Specifically, the machine learning model can be used to determine the sample user's driving action habits, vehicle control habits, driving fatigue information and responsiveness information based on the sample user's historical driving data.

[0088] For any two sample users, the driving habit similarity of the two sample users is determined based on the driving action habits, vehicle control habits, driving fatigue information and reaction information of the two sample users. Based on the driving habit similarity of any two sample users, multiple sample users are clustered by the K-means clustering algorithm to determine multiple cluster clusters, and then the cluster cluster with the most sample users is determined as the target cluster cluster. The driving action habits, vehicle control habits, driving fatigue information and reaction information corresponding to the cluster center of the target cluster are used as the driving action habits, vehicle control habits, driving fatigue information and reaction information corresponding to the associated potential disease.

[0089] Step 170, generating health status prompt information based on the user's health tag.

[0090] Specifically, it generates potential disease warning information and driving habit intervention information based on the user's health tags. For example, it reminds the user to conduct further examinations for potential diseases with a higher risk of disease, and reminds the user to correct incorrect driving actions that increase the risk of disease.

[0091] In some embodiments, the health status prompt information may also include predictive information for prompting the user of the future development of the disease.

[0092] Figure 4 is a module diagram of a health warning system based on health tags shown in an embodiment of the present application, such as Figure 4 As shown, a health warning system based on health labels may include a data acquisition module, an occupational analysis module, a disease screening module, a data analysis module, a status acquisition module, a label determination module and a health prompt module.

[0093] The data acquisition module can be used to obtain the user's historical driving data.

[0094] The occupation analysis module can be used to determine the user's occupation based on the user's historical driving data.

[0095] The disease screening module can be used to determine the user's associated potential diseases based on the user's occupation.

[0096] The data analysis module can be used to determine the user's driving habits based on the user's historical driving data.

[0097] The state acquisition module can be used to obtain the user's physiological state information.

[0098] The label determination module can be used to determine the user's health label based on the disease characteristics of the user's associated potential diseases, the user's driving habits and physiological state information.

[0099] The health reminder module can be used to generate health status reminder information based on the user's health tags.

[0100] In some embodiments, a health warning system based on health labels can be used to execute a health warning method based on health labels. For more descriptions of a health warning system based on health labels, please refer to the relevant descriptions of a health warning method based on health labels, which will not be repeated here.

[0101] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A health warning method based on health labels, characterized in that: include: Get the user's historical driving data; Determining the occupation of the user based on the historical driving data of the user; Determining associated potential diseases of the user based on the user's occupation; Determining the user's driving habits based on the user's historical driving data; Acquiring physiological status information of the user; Determining a health tag of the user based on disease characteristics of the associated potential disease of the user, the driving habits and physiological status information of the user; Generate health status prompt information based on the user's health tag; Determining the occupation of the user based on the historical driving data of the user includes: Establishing driving profiles corresponding to multiple occupations, wherein the driving profiles include multiple driving labels; Determining a driving profile of the user based on the historical driving data of the user; For each occupation, determining the driving profile similarity between the driving profile corresponding to the occupation and the driving profile of the user; Determining the occupation of the user based on the similarity of the driving profiles corresponding to each occupation; and determining the driving profile of the user based on the historical driving data of the user, including: Based on the historical driving data of the user, determining the destination discreteness label, driving time discreteness label, average driving duration label and destination feature label of the user, wherein the multiple driving labels at least include the destination discreteness label, driving time discreteness label, average driving duration label and destination feature label; determining the driving profile similarity between the driving profile corresponding to the occupation and the driving profile of the user, including: Calculate the destination discreteness label of the driving profile of the user and the destination discreteness label of the driving profile corresponding to the occupation, and calculate a first label difference; Calculate the driving time dispersion label of the driving profile of the user and the driving time dispersion label of the driving profile corresponding to the occupation, and calculate the second label difference; Calculate the average driving time label of the driving profile of the user and the average driving time label of the driving profile corresponding to the occupation, and calculate a third label difference; Calculating the destination feature label of the driving profile of the user and the destination feature label of the driving profile corresponding to the occupation, and calculating a fourth label difference; Determining the driving profile similarity between the driving profile corresponding to the occupation and the driving profile of the user based on the first label difference, the second label difference, the third label difference, and the fourth label difference; determining the associated potential disease of the user based on the occupation of the user, including: Establishing a knowledge graph, wherein the knowledge graph includes three types of nodes, a first type of node is used to represent occupations, a second type of node is used to represent associated potential diseases, and a third type of node is used to represent disease characteristics of associated potential diseases; The associated potential disease of the node representing the occupation of the user in the knowledge graph is used as the associated potential disease of the user; and the driving habit of the user is determined based on the historical driving data of the user, including: Determining the user's driving behavior based on the user's historical driving data; determining the vehicle control habits of the user based on the historical driving data of the user; Determining driving fatigue information of the user based on historical driving data of the user; Determining the user's responsiveness information based on the user's historical driving data; determining the user's health tag based on the disease characteristics of the user's associated potential diseases, the user's driving habits and physiological state information, including: Determining driving habits corresponding to each associated potential disease of the user; For each associated potential disease of the user, determining a disease feature matching degree corresponding to the associated potential disease based on the physiological state information of the user and the disease feature of the associated potential disease of the user; For each associated potential disease of the user, determining a matching degree of the driving habits corresponding to the associated potential disease based on the driving habits of the user and the driving habits corresponding to the associated potential disease; For each associated potential disease of the user, determining a disease matching degree corresponding to the associated potential disease based on a disease feature matching degree and a driving habit matching degree corresponding to the associated potential disease; Determining the health label of the user based on the disease matching degree corresponding to each of the associated potential diseases; determining the driving habit matching degree corresponding to the associated potential diseases based on the driving habits of the user and the driving habits corresponding to the associated potential diseases, including: Obtaining historical driving data of a plurality of sample users each associated with the potential disease; For each of the sample users, based on the historical driving data of the sample user, determining the driving action habits, vehicle control habits, driving fatigue information and responsiveness information of the sample user; For each of the associated potential diseases, the driving action habits, vehicle control habits, driving fatigue information and reaction information corresponding to the associated potential disease are determined based on the driving action habits, vehicle control habits, driving fatigue information and reaction information of multiple sample users of the associated potential disease.

2. A health warning method based on health labels according to claim 1, characterized in that: Generating health status prompt information based on the health tag of the user includes: Potential disease warning information and driving habit intervention information are generated based on the user's health tag.

3. A health warning system based on health labels, characterized in that: A method for performing a health warning method based on a health label according to claim 1 or 2, comprising: A data acquisition module is used to obtain the user's historical driving data; An occupation analysis module, used to determine the occupation of the user based on the historical driving data of the user; A disease screening module, for determining associated potential diseases of the user based on the user's occupation; A data analysis module, configured to determine the user's driving habits based on the user's historical driving data; A state acquisition module, used to acquire the physiological state information of the user; A label determination module, used to determine the health label of the user based on the disease characteristics of the associated potential diseases of the user, the driving habits and physiological status information of the user; The health reminder module is used to generate health status reminder information based on the health tag of the user.

Images