Method and system for analyzing driving behavior of vehicle owner based on big data

Abstract

The invention provides a method and system for analyzing the driving behavior of a vehicle owner based on big data, and the method comprises the steps: collecting the vehicle data of the vehicle owner, and accessing the vehicle data to a vehicle network big data platform, thereby providing a data basis for the subsequent driving analysis; a data dimension rule is introduced, vehicle owner vehicle use data are classified, sorted and preprocessed, and effective vehicle owner vehicle use data are obtained; on the basis of the effective vehicle using data of the vehicle owner, the driving behavior score of the vehicle owner in each travel is calculated by using dimension index recognition and dimension score rules, and a driving behavior data report of the corresponding travel is generated for the vehicle owner according to the score; and pushing the driving behavior data report to a vehicle owner client APP in a periodic service pushing mode. According to the method, complex and diversified driving behaviors can be effectively and accurately classified and evaluated, so that the driving safety awareness of a vehicle owner is enhanced, the improvement of driving habits is promoted, and the vehicle maintenance efficiency is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of big data application in Internet of Vehicles, and in particular, relates to a method and system for analyzing driving behavior of vehicle owners based on big data. Background Art

[0002] According to statistics from the public security department, by the end of 2023, the number of motor vehicles in China will reach 435 million, and it is still growing at a rate of more than 20 million new registrations each year. With the continuous increase in the number of cars and the increasing traffic volume, traffic safety issues have become increasingly prominent and have become the focus of attention from all walks of life. At the same time, the quality of the owner's driving behavior has a direct impact on the owner's driving safety, the quality and life of auto parts, and energy consumption. In order to actively respond to this challenge, improve driving safety, reduce the occurrence of traffic accidents, and increase the service life of auto parts, regularly providing customized reports to car owners has become an innovative solution.

[0003] In the existing technology, driving behavior is limited by relatively limited technical means, lack of high-precision sensors and powerful data processing capabilities, and it is difficult to accurately obtain and analyze relevant data on driving behavior. At the same time, the high cost of data collection and storage also limits large-scale data applications. Furthermore, the standards and models for driving behavior analysis are not perfect, making it difficult to accurately evaluate and classify complex and diverse driving behaviors.

[0004] Therefore, there is an urgent need for a method or system that can regularly provide customized analysis reports of driving analysis to car owners, so that car owners can enhance their safety awareness and promote the improvement of driving habits, while also improving the efficiency of vehicle maintenance. This has a positive impact on individual car owners, enterprises and society, and helps to achieve safer, more efficient, environmentally friendly and intelligent transportation. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a method and system for analyzing the driving behavior of vehicle owners based on big data, so as to solve the problems in the prior art that it is difficult to accurately obtain and analyze relevant data on driving behavior, the data collection and storage costs are high, and the standards and models for driving behavior analysis are not perfect, making it difficult to accurately evaluate and classify complex and diverse driving behaviors.

[0006] The present invention is achieved through the following technical solutions:

[0007] In one aspect, an embodiment of the present invention provides a method for analyzing a vehicle owner's driving behavior based on big data, the method comprising:

[0008] Collect car owners' car usage data and connect it to the vehicle network big data platform to provide a data basis for subsequent driving analysis;

[0009] Introduce data dimension rules to classify and pre-process car owners' car usage data to obtain effective car owners' car usage data;

[0010] Based on the valid car owner's car usage data, the driving behavior score of each trip of the car owner is calculated by using dimension indicator identification and dimension scoring rules, and a driving behavior data report of the corresponding trip is generated for the car owner according to the score;

[0011] The driving behavior data report is pushed to the car owner's client APP through periodic service push.

[0012] In another aspect, an embodiment of the present invention provides a system for analyzing driving behavior of vehicle owners based on big data, the system comprising a data collection access module, a data report generation module and a data display module, wherein:

[0013] The data collection and access module is used to collect the car owner's car usage data and access it to the Internet of Vehicles big data platform to provide a data basis for subsequent driving analysis;

[0014] The data report generation module is used to process, classify and calculate the collected car owner's car usage data, analyze the calculation results, and generate a driving behavior data report for the corresponding trip for the car owner;

[0015] The data display module is used to receive the driving behavior data report and display the report to the car owner.

[0016] Furthermore, the data report generating module further includes a data processing unit, a data dimension classification unit, a data processing and calculation unit and a vehicle owner report generating unit, wherein:

[0017] The data processing unit is used to eliminate unreasonable vehicle usage data and conduct data research and access pre-research work;

[0018] The data dimension classification unit is used to introduce the car owner's car usage data into the data dimension rules to perform dimension classification;

[0019] The data processing and calculation unit is used to calculate the score of the vehicle owner's travel driving behavior by combining the data classified by the data dimension classification unit;

[0020] The vehicle owner report generating unit is used to generate a driving behavior data report according to the score.

[0021] Compared with the prior art, the present invention has the following advantages:

[0022] 1. The present invention uses multiple sensors and a data analysis platform as the basis for data access and capacity support, thus avoiding the problem of high data collection and storage costs. At the same time, it provides a unified planning configuration library, establishes a unified standard for all car owners' driving behavior report analysis, and solves the problem that the standards and models for driving behavior analysis are not perfect, and it is difficult to accurately evaluate and classify complex and diverse driving behaviors.

[0023] 2. The present invention adopts the "end-cloud-end" link to realize the data transmission from the vehicle to the cloud and then back to the car owner's mobile client, thus completing the closed loop of data analysis and utilization, bringing practical data application results to the car owner, which has a positive impact on the car owner, the enterprise and the society, and helps to realize safer, more efficient, environmentally friendly and intelligent transportation.

[0024] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0026] Figure 1 It is a flow chart of a method for analyzing the driving behavior of vehicle owners based on big data according to the present invention.

[0027] Figure 2 It is a dimensional score map of the driving behavior analysis report of the present invention.

[0028] Figure 3 This is a key frame prototype diagram of the driving behavior analysis report pushed to the owner's end APP of the present invention.

[0029] Figure 4 It is a structural diagram of a system for analyzing the driving behavior of vehicle owners based on big data according to the present invention. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0031] Embodiment 1:

[0032] See also Figure 1 , Figure 1 The present invention is a flow chart of a method for analyzing the driving behavior of a vehicle owner based on big data, the method comprising the following steps:

[0033] Step S1: Collect the car owner's car usage data and connect it to the vehicle network big data platform to provide a data basis for subsequent driving analysis;

[0034] Furthermore, the collection of car owner's car usage data adopts a variety of sensors and data analysis platforms as the capacity support for data collection and data access; the car owner's car usage data includes but is not limited to: vehicle speed, GPS status, GPS longitude, GPS latitude, driving mileage, driving time, lateral acceleration, longitudinal acceleration, steering wheel angle, steering wheel speed, seat belt status, DMS (in-cabin camera), ADAS (intelligent assisted driving), speeding alarm, collision alarm, emergency braking and other vehicle original data.

[0035] Step S2: Introduce data dimension rules, classify and sort the car owner's car usage data, and perform pre-processing operations to obtain valid car owner's car usage data;

[0036] For further information, please refer to Table 1: Detailed list of dimension indicator factors of dimension meter; the data dimension rules include five dimensions, namely driving intensity, driving safety, driving risk, driving stability and driving concentration, among which: "Driving intensity" mainly measures the intensity of the owner's driving behavior each time; "Driving safety" mainly measures whether the owner has bad driving behavior and safety hazards during driving; "Driving risk" mainly measures the owner's risk factor during driving; "Driving stability" mainly measures the owner's control and driving stability during driving; "Driving concentration" mainly measures the owner's concentration during driving.

[0037] Furthermore, the five dimensions include a total of 20 indicators, which facilitate the identification and calculation of car owners' car usage data. The specific indicators of each dimension are divided into:

[0038] The specific indicators of the driving intensity dimension are continuous driving time and single driving mileage; the specific indicators of the driving safety dimension are camera blockage time, distracted driving, looking left and right, forward collision warning and frequent lane changes; the specific indicators of the driving risk dimension are fatigue driving, late night driving, speeding, the proportion of time without seat belts and driving in rainy and snowy days; the specific indicators of the driving stability dimension are sudden acceleration, sudden deceleration, sharp turns, lane departure and frequent lane changes; the specific indicators of the driving concentration dimension are smoking, making phone calls and playing with mobile phones.

[0039] Table 1: Detailed table of dimension indicator factors

[0040]

[0041] Furthermore, the step of introducing the collected car owner's car usage data into the data dimension rules and performing classification and preprocessing operations on the car usage data also includes the following steps:

[0042] Step S201: classify the car owner's car usage data connected to the vehicle network big data platform into the data warehouse, and classify the data according to the data dimension rules;

[0043] Step S202: pre-process the classified data to remove unreasonable vehicle usage data.

[0044] Furthermore, the data preprocessing includes abnormal data identification, missing data processing, duplicate data elimination, data format standardization, data consistency check, erroneous data correction, etc.;

[0045] Furthermore, the elimination of unreasonable vehicle usage data is based on the itinerary, specifically: "engine / generator ignition (power on)", "GPS displacement>100m", "engine / generator shutdown (power off)" are used as the judgment of effective itinerary, and the data of the vehicle started but not actually driven is eliminated to ensure the accuracy of the vehicle usage data analysis.

[0046] Step S3: Based on the valid car owner's car usage data, the driving behavior score of each trip of the car owner is calculated by using the dimension indicator identification and dimension scoring rules, and a driving behavior data report of the corresponding trip is generated for the car owner according to the score;

[0047] Furthermore, the dimensional indicator recognition is based on the real-time data signals collected by the ECU, the in-cabin camera (DMS) signal, the intelligent assisted driving (ADAS) signal, etc., to identify the triggering time and number of twenty indicators in the five dimensions during the journey, and count the items that trigger the corresponding indicators, the time when the corresponding indicators are triggered, and the number of times the corresponding indicators are triggered.

[0048] Furthermore, the dimension scoring rules are specifically an indicator behavior scoring rule calculation table; the initial score is 100 points, and the points are deducted accordingly based on the number of times the corresponding indicators occur and the degree of risk until the end of the trip, and the driving behavior score for a single trip can be calculated.

[0049] Furthermore, the indicator behavior score rule calculation table is based on five dimensions for score normalization, as follows:

[0050] For the scoring method of the “driving intensity” dimension, please refer to Table 2: “Driving intensity” dimension score calculation table;

[0051] Table 2: Calculation table of scores for the “driving intensity” dimension

[0052]

[0053]

[0054] As can be seen from Table 2, in the indicator of continuous driving time: the driving time is in the range of (0, 60] minutes, the score is 100 points, the driving time is in the range of (60, 120] minutes, the score is 80 points, the driving time is in the range of (120, 180] minutes, the score is 60 points, the driving time is in the range of (180, 240] minutes, the score is 40 points, and the driving time is more than 240 minutes, the score is 0 point; in the indicator of single driving mileage: the driving mileage is in the range of (0, 60] kilometers, the score is 100 points, the driving mileage is in the range of (60, 120] kilometers, the score is 80 points, the driving mileage is in the range of (120, 180] kilometers, the score is 60 points, and the driving mileage is more than 180 kilometers, the score is 0 point.

[0055] For the scoring method of the “driving safety” dimension, please refer to Table 3: Score calculation table of the “driving safety” dimension;

[0056] Table 3: Score calculation table for the "driving safety" dimension

[0057]

[0058]

[0059] As can be seen from Table 3, in the indicator of camera occlusion duration: the occlusion duration is in the range of [0,5%], the score is 100 points, the occlusion duration is in the range of [5%,20%], the score is 80 points, the occlusion duration is in the range of (20%,40%], the score is 60 points, and the occlusion duration is greater than 40%, the score is 0 points; in the indicator of distracted driving times: the number of distractions is 0, the score is 100 points, the number of distractions is 1-2, the score is 80 points, the number of distractions is 3-6, the score is 60 points, and the number of distractions is greater than 40%. If the number of times the driver looks left and right is greater than 6 times, the score is 0; in the indicator of the number of times the driver looks left and right: if the number of times the driver looks left and right is 0 times, the score is 100 points, if the number of times the driver looks left and right is 1-2 times, the score is 80 points, if the number of times the driver looks left and right is 3-6 times, the score is 60 points, and if the number of times the driver looks left and right is greater than 6 times, the score is 0; in the indicator of the number of front collision alarms: if the number of alarms is 0 times, the score is 100 points, if the number of alarms is 1-2 times, the score is 80 points, if the number of alarms is 3-6 times, the score is 60 points, and if the number of alarms is greater than 6 times, the score is 0.

[0060] For the scoring method of the “Driving Risk” dimension, please refer to Table 4: Score calculation table of the “Driving Risk” dimension;

[0061] Table 4: Score calculation table for the "Driving Risk" dimension

[0062]

[0063]

[0064] As shown in Table 4, in the indicator of fatigue driving: if there is no fatigue driving, the score is 100 points, if there is fatigue driving, the score is 0 points; in the indicator of late night driving: if the driving time period is between 00:00 and 04:00, the score is 80 points, and in other time periods, the score is 100 points; in the indicator of speeding driving: if the number of speeding is 0, the score is 100 points, if the number of speeding is 1 to 2, the score is 80 points, if the number of speeding is 3 to 6, the score is 60 points, and if the number of speeding is 1 to 2, the score is 60 points. If the number of times is greater than 6 times, the score is 0. In the indicator of the duration of time without seat belts: if the duration is in the range of [0,5%], the score is 100 points; if the duration is in the range of [5%,20%], the score is 80 points; if the duration is in the range of (20%,40%], the score is 60 points; if the duration is greater than 40%, the score is 0. In the indicator of traveling in rainy and snowy days: if there is no such time, the score is 100 points; if there is such time, the score is 0.

[0065] For the scoring method of the “driving stability” dimension, please refer to Table 5: Score calculation table of the “driving stability” dimension;

[0066] Table 5: Score calculation table for the "driving stability" dimension

[0067]

[0068] As shown in Table 5, in the indicator of sudden acceleration: the number of sudden accelerations is 0, the score is 100 points, the number of sudden accelerations is 1-2, the score is 80 points, the number of sudden accelerations is 3-6, the score is 60 points, and the number of sudden accelerations is more than 6 times, the score is 0 point; in the indicator of sudden deceleration: the number of sudden decelerations is 0, the score is 100 points, the number of sudden decelerations is 1-2, the score is 80 points, the number of sudden decelerations is 3-6, the score is 60 points, and the number of sudden decelerations is more than 6 times, the score is 0 point; in the lane For the indicator of number of deviations: if the number of lane departures is 0, the score is 100 points; if the number of lane departures is 1 to 2, the score is 80 points; if the number of lane departures is 3 to 6, the score is 60 points; if the number of lane departures is more than 6, the score is 0 point; for the indicator of frequent lane changes: if the number of frequent lane changes is 0, the score is 100 points; if the number of frequent lane changes is 1 to 2, the score is 80 points; if the number of frequent lane changes is 3 to 6, the score is 60 points; if the number of frequent lane changes is more than 6, the score is 0 point.

[0069] For the scoring method of the “driving concentration” dimension, please refer to Table 6: Score calculation table of the “driving concentration” dimension;

[0070] Table 6: Score calculation table for the "Driving Concentration" dimension

[0071]

[0072] It can be seen from Table 6 that in the indicator of smoking: if there is no smoking, the score is 100 points, and if there is smoking, the score is 0 point; in the indicator of making phone calls (handheld): if there is no phone call behavior, the score is 100 points, and if there is a phone call behavior, the score is 0 point; in the indicator of playing with mobile phones: if there is no phone call, the score is 100 points, and if there is a phone call behavior, the score is 0 point.

[0073] Further, in step S3, based on the valid car owner's car use data, the driving behavior score of each trip of the car owner is calculated by using dimension indicator identification and dimension scoring rules, and a driving behavior data report of the corresponding trip is generated for the car owner according to the score, which specifically includes:

[0074] Step S301: taking each major dimension in a single trip as an independent score calculation unit, and calculating the average score of the corresponding dimension according to the score of each indicator in each dimension, as the percentage score of each dimension in the single trip;

[0075] Step S302: generating a dimension score map of the user's single trip driving behavior analysis report based on the percentage score of each dimension;

[0076] Step S303: According to the dimension score map, weight proportions are configured for each dimension score, and the final score of the driving behavior of a single trip is calculated;

[0077] Step S304: Generate a driving behavior data report for a single trip for the car owner based on the final score.

[0078] For further information, see Figure 2 , Figure 2 It is the dimension score spectrum of the driving behavior analysis report of the present invention. In this embodiment, if Zhang San has 3 sudden accelerations, 6 sudden decelerations, 1 sharp turn, 8 lane departures, and 0 frequent lane changes in one trip, then Zhang San’s score in the “driving stability” dimension is: (60+60+80+0+100) / 5=60 points; if the calculated result is less than 60 points, it is displayed as 60 points; if the calculated result contains multiple decimal places, it is rounded to two decimal places by default; Zhang San’s scores in other dimensions are calculated in the above manner, and the dimension score spectrum of the driving behavior analysis report is obtained by drawing ( Figure 2 ); Based on the graph ( Figure 2 ) The scores of each dimension are allocated and the weight ratio of each dimension is allocated to calculate the final score. Assuming that the weight of each of the five dimensions is 20%, the final score is: (60*20%) + (78.5*20%) + (90*20%) + (69.25*20%) + (88.5*20%) = 77.25 points; then generate a driving behavior data report for Zhang San based on the final score.

[0079] Furthermore, according to the dimension score map, the weight ratio of each dimension score is configured, which is specifically adjusted in the management system by means of weight thresholds, but it is necessary to follow that the sum of the weight thresholds of the five major dimensions is 100%; at the same time, it supports the revision of the rule base to add / delete / modify the indicator factors included in each dimension.

[0080] Furthermore, the driving behavior data report includes a comprehensive score, scores for each dimension, a driving behavior analysis report dimension score map, and driving suggestions.

[0081] Step S4: Push the driving behavior data report to the car owner client APP through periodic service push.

[0082] Furthermore, the periodic service push method can support the administrator to set the report generation cycle, report push frequency and time. Once the conditions for report generation and push are met, the owner's driving behavior analysis report is automatically generated and pushed to the owner.

[0083] Further, in this embodiment, please refer to Figure 3, Figure 3 This is the key frame prototype diagram of the driving behavior analysis report pushed to the car owner's APP of the present invention, which further explains the client mobile phone APP and the periodic service push method: after purchasing the car, the car owner will install the car owner APP to support the car owner to use the vehicle-related remote control functions. After the platform layer is connected and the data is accessed, and the car owner has the corresponding authentication, the car owner can receive the pushed car owner report according to the rules set by the system layer administrator.

[0084] The pushed owner report will be pushed to the owner's APP application through the mobile APP desktop message. The owner can click the message to link to the corresponding report page for review; of course, the owner can also actively open the mobile APP and click on the "Owner Report" entrance on the homepage to view all pushed report records and the corresponding report details page. In order to improve the actual user experience, on the APP side, the owner can be supported to "turn off" or "turn on" the desktop message reminder of the push report. Once the user "turns off" the operation, the desktop message will no longer remind the owner, avoiding the trouble of information overload for the owner.

[0085] Car owners can set the frequency of generating and pushing car owner reports. They can choose and set according to several options such as "trip", "day", "week", and "month". The set results will be automatically synchronized to the platform, and the platform will generate and push according to the logic set by the car owner by default.

[0086] Furthermore, if the report is pushed according to a cycle such as "day", "week", or "month", specifically, all single-trip driving behavior data reports within the corresponding period are pushed; for example: if it is pushed once a week, all single-trip driving behavior data reports within this week are pushed, and the car owner can click on the corresponding single-trip driving behavior data report to query one by one.

[0087] Embodiment 2:

[0088] See also Figure 4 , Figure 4 This is a structural diagram of a system for analyzing the driving behavior of vehicle owners based on big data in the present invention. The system includes a data acquisition access module, a data processing module and a data display module; specifically:

[0089] The data collection and access module is used to collect the car owner's car usage data and access it to the Internet of Vehicles big data platform to provide a data basis for subsequent driving analysis;

[0090] Furthermore, in the data acquisition access module, a variety of data sensors and data analysis platforms are used to ensure the integrity and reliability of data acquisition.

[0091] The data report generation module is used to process, classify and calculate the collected car owner's car usage data, analyze the calculation results, and generate a driving behavior data report for the corresponding trip for the car owner;

[0092] The data display module is used to receive the driving behavior data report and display the report to the car owner.

[0093] Furthermore, in the data display module, the specific display module is a client mobile phone APP, and the driving behavior data report is obtained through the client mobile phone APP. The car owner logs in to the mobile phone APP, binds the vehicle information, and can receive the corresponding driving behavior data report.

[0094] Furthermore, the data report generation module further includes a data processing unit, a data dimension classification unit, a data processing and calculation unit, and a vehicle owner report generation unit, wherein:

[0095] The data processing unit is used to eliminate unreasonable vehicle usage data and conduct data research and access pre-research work;

[0096] The data dimension classification unit is used to introduce the car owner's car usage data into the data dimension rules to perform dimension classification;

[0097] The data processing and calculation unit is used to calculate the score of the vehicle owner's travel driving behavior by combining the data classified by the data dimension classification unit;

[0098] The vehicle owner report generating unit is used to generate a driving behavior data report according to the score.

[0099] Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent substitutions for some of the technical features therein; and these modifications or substitutions do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for analyzing the driving behavior of a vehicle owner based on big data, characterized in that: Collect car owners' car usage data and connect it to the vehicle network big data platform to provide a data basis for subsequent driving analysis; Introduce data dimension rules to classify and pre-process car owners' car usage data to obtain effective car owners' car usage data; Based on the valid car owner's car usage data, the driving behavior score of each trip of the car owner is calculated by using dimension indicator identification and dimension scoring rules, and a driving behavior data report of the corresponding trip is generated for the car owner according to the score; The driving behavior data report is pushed to the car owner's client APP through periodic service push.

2. The method for analyzing the driving behavior of a vehicle owner based on big data according to claim 1, characterized in that: The owner's vehicle usage data is the vehicle's original data, including vehicle speed, GPS status, GPS longitude, GPS latitude, driving mileage, driving time, lateral acceleration, longitudinal acceleration, steering wheel angle, steering wheel speed, seat belt status, in-cabin camera, intelligent assisted driving, speeding alarm, collision alarm and emergency braking data.

3. The method for analyzing the driving behavior of vehicle owners based on big data as claimed in claim 1, characterized in that: The introduction of data dimension rules, classification and preprocessing of the car owner's car usage data also includes: Classify the car owner's car usage data connected to the Internet of Vehicles big data platform into the data warehouse and classify the data according to the data dimension rules; The classified data is preprocessed to eliminate unreasonable vehicle usage data.

4. The method for analyzing the driving behavior of vehicle owners based on big data as claimed in claim 3, characterized in that: The classified data is preprocessed, including abnormal data identification, missing data processing, duplicate data elimination, data format standardization, data consistency check and erroneous data correction; The unreasonable vehicle usage data is eliminated by, specifically: based on the vehicle usage trip, using engine / generator ignition, GPS displacement>100m and engine / generator shutdown as the judgment of effective trip, eliminating the data of the vehicle started but not actually driven, to ensure the accuracy of vehicle usage data analysis.

5. The method for analyzing the driving behavior of vehicle owners based on big data as claimed in claim 1, characterized in that: The data dimension rules include five dimensions, namely driving intensity, driving safety, driving risk, driving stability and driving concentration; The five dimensions include a total of 20 indicators, which are used to identify and calculate the car owner's car usage data. The specific indicators of each dimension are: The indicators of the driving intensity dimension are continuous driving time and single driving mileage; The indicators of the driving safety dimension are camera occlusion duration, distracted driving, looking left and right, forward collision warning and frequent lane changes; The indicators of the driving risk dimension are fatigue driving, late night driving, speeding, the proportion of time without seat belts fastened, and driving in rainy and snowy days; The indicators of the driving stability dimension are sudden acceleration, sudden deceleration, sharp turns, lane departure and frequent lane changes; The specific indicators of the driving concentration dimension are divided into smoking, making phone calls and playing with mobile phones.

6. The method for analyzing the driving behavior of vehicle owners based on big data as claimed in claim 5, characterized in that: The dimension indicator recognition is to identify the triggering time and frequency of twenty indicators in five dimensions during the journey based on the real-time data signal collected by the ECU, the in-cabin camera signal and the intelligent assisted driving signal, and to count the items that trigger the corresponding indicators, the time when the corresponding indicators are triggered and the frequency of the triggering of the corresponding indicators; The dimension scoring rules are an indicator behavior scoring rule calculation table, with an initial score of 100 points. Points are deducted accordingly based on the number of times the corresponding indicators occur and the degree of risk until the end of the trip, and then the driving behavior score for a single trip can be calculated.

7. The method for analyzing the driving behavior of a vehicle owner based on big data as claimed in claim 6, characterized in that: Based on the valid car owner's car use data, the driving behavior score of each trip of the car owner is calculated by using dimension indicator identification and dimension scoring rules, and a driving behavior data report of the corresponding trip is generated for the car owner according to the score, specifically including: Each major dimension in a single trip is taken as an independent score calculation unit. According to the score of each indicator in each dimension, the average score of the corresponding dimension is calculated as the percentage score of each dimension in a single trip. Based on the percentage score of each dimension, a dimension score map of the user's single trip driving behavior analysis report is generated; According to the dimension score map, the weight ratio of each dimension score is configured to calculate the final score of the driving behavior of a single trip; Based on the final score, a single-trip driving behavior data report is generated for the car owner.

8. The method for analyzing the driving behavior of vehicle owners based on big data as claimed in claim 7, characterized in that: According to the dimension score map, the weight proportion of each dimension score is configured, specifically, it is allocated in the management system by means of weight thresholds, and the sum of the weight thresholds of the five dimensions is 100%; The driving behavior data report includes a comprehensive score, scores for each dimension, a driving behavior analysis report dimension score map, and driving suggestions.

9. A system for analyzing the driving behavior of car owners based on big data, characterized in that: The system includes a data collection access module, a data report generation module and a data display module, wherein: The data collection and access module is used to collect the car owner's car usage data and access it to the Internet of Vehicles big data platform to provide a data basis for subsequent driving analysis; The data report generation module is used to process, classify and calculate the collected car owner's car usage data, analyze the calculation results, and generate a driving behavior data report for the corresponding trip for the car owner; The data display module is used to receive the driving behavior data report and display the report to the car owner.

10. The system for analyzing the driving behavior of vehicle owners based on big data as claimed in claim 9, characterized in that: The data report generation module further includes a data processing unit, a data dimension classification unit, a data processing and calculation unit, and a vehicle owner report generation unit, wherein: The data processing unit is used to eliminate unreasonable vehicle usage data and conduct data research and access pre-research work; The data dimension classification unit is used to introduce the car owner's car usage data into the data dimension rules to perform dimension classification; The data processing and calculation unit is used to calculate the score of the vehicle owner's travel driving behavior by combining the data classified by the data dimension classification unit; The vehicle owner report generating unit is used to generate a driving behavior data report according to the score.

Images