Travel scoring method and device based on driving behaviors, equipment and medium

Abstract

The invention relates to a travel scoring method and device based on driving behaviors, equipment and a medium. The method comprises the following steps: acquiring vehicle track information; determining vehicle feature information according to the vehicle track information; using an AI algorithm to obtain AI feature information conforming to a driving time period according to the driving time period of the vehicle track information; and determining a travel score through a scoring method according to the vehicle feature information and the AI feature information. According to the method, the vehicle feature information and the AI feature information are integrated to determine the travel score, through rich feature data and a scientific scoring method, the scoring accuracy is improved, the method can be used for evaluating the travel safety and efficiency, and the defects of insufficient precision and less feature data existing in an existing method are overcome.

Description

Technical Field

[0001] The present application relates to the field of big data, and in particular to a method, device, equipment and medium for trip scoring based on driving behavior. Background Art

[0002] Existing driving behavior assessment methods based on vehicle-mounted sensors and data analysis mostly use sensors such as accelerometers, gyroscopes, and GPS to capture vehicle motion data, and compare these motion data with pre-determined behavior patterns to assess the quality of driving behavior. However, these existing technologies have the following disadvantages:

[0003] 1. Insufficient precision: There is a lack of sufficient precision in evaluating driving behavior, resulting in inaccurate scoring results.

[0004] 2. Few feature data: Using common feature data, such as driving mileage, driving time, average speed, sudden acceleration, sudden deceleration, sharp turns and other common features, it is impossible to accurately analyze the driver's driving behavior, resulting in inaccurate scoring data. Summary of the invention

[0005] The embodiments of the present application provide a method, device, equipment and medium for trip scoring based on driving behavior, aiming to solve the defects of insufficient accuracy and little feature data.

[0006] In a first aspect, an embodiment of the present application provides a trip scoring method based on driving behavior, comprising:

[0007] Get vehicle trajectory information;

[0008] Determine vehicle characteristic information according to vehicle trajectory information;

[0009] Using AI algorithm to obtain AI feature information that matches the driving time period according to the driving time period of vehicle trajectory information;

[0010] The trip score is determined based on vehicle feature information and AI feature information through a scoring method.

[0011] In a second aspect, an embodiment of the present application further provides a trip scoring device based on driving behavior, which includes a unit for executing the above method.

[0012] In a third aspect, an embodiment of the present application further provides a computer device, which includes a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the above method when executing the computer program.

[0013] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program can implement the above method when executed by a processor.

[0014] The embodiments of the present application provide a method, device, equipment and medium for trip scoring based on driving behavior, which determines the trip score by integrating vehicle feature information and AI feature information, that is, taking into account simple processing results (vehicle feature information) and AI deep mining analysis results (AI feature information). Through rich feature data and scientific scoring methods, the accuracy of the score is improved, which can be used to evaluate the safety and efficiency of the trip, and overcome the defects of insufficient accuracy and less feature data in the existing methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0016] In order to more clearly illustrate the embodiments of the present application 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, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0017] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0018] Figure 1 A flowchart of a method for trip scoring based on driving behavior provided in an embodiment of the present application.

[0019] Figure 2 A module block diagram of a trip scoring device based on driving behavior provided in an embodiment of the present application.

[0020] Figure 3 A module block diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0022] The disclosure below provides many different embodiments or examples to realize the different structures of the present application. In order to simplify the disclosure of the present application, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present application. In addition, the present application can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0023] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0024] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0025] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0026] As used in this specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0027] In order to solve the technical problems of insufficient precision and little feature data in the prior art, the present application provides a trip scoring method based on driving behavior, which can solve the defects of insufficient precision and little feature data.

[0028] See also Figure 1 , Figure 1 A driving behavior-based trip scoring method provided in an embodiment of the present application includes:

[0029] S1: Obtain vehicle trajectory information;

[0030] S2: Determine vehicle feature information based on vehicle trajectory information;

[0031] S3: Using the AI ​​algorithm to obtain AI feature information that matches the driving time period according to the driving time period of the vehicle trajectory information;

[0032] S4: Determine the trip score based on the vehicle feature information and AI feature information through a scoring method.

[0033] Vehicle trajectory information can be obtained by the vehicle's active reporting or passive reporting, that is, the vehicle can report the vehicle trajectory information at a fixed time or when the reporting conditions are met, and the vehicle can also report passively after receiving a data request. The reported vehicle trajectory information can be stored in a real-time data source (Kafka). This method can be implemented on the Flink stream processing architecture. The Flink stream processing architecture has the advantages of high performance, low latency, and scalability, and is widely used in big data analysis and real-time computing. This method has the following advantages when implemented on the Flink stream processing architecture: (1) Real-time data processing: Flink provides high-throughput and low-latency stream processing capabilities, which can quickly process vehicle data. Using Flink's stream processing capabilities, the vehicle's location information and other related data can be received and processed in real time, thereby achieving real-time alarms and ensuring the timeliness and accuracy of data processing. (2) Data parallel processing: Flink supports distributed computing, which can divide data into multiple partitions for parallel processing to increase data processing speed. (3) Scalability and fault tolerance: Horizontal expansion and task parallelism can be used to cope with the processing needs of large-scale data streams, and Flink's fault-tolerant mechanism can be used to ensure the stability and reliability of the system. This method can also be implemented based on the Spark architecture.

[0034] The vehicle trajectory information may include driving mileage, driving time, average speed, sudden acceleration, sudden deceleration, sharp turns and other data. After the method obtains the vehicle trajectory information, the vehicle trajectory information can be pre-processed, such as performing data cleaning, data filtering, data conversion, data normalization and other operations to ensure the accuracy and consistency of the data.

[0035] The method determines the vehicle characteristic information based on the vehicle trajectory information. For example, the method can determine the vehicle characteristic information by statistically analyzing the vehicle trajectory information. For example, the method accumulates the number of sudden accelerations in each section of the vehicle trajectory information to obtain the total number of sudden accelerations. For example, the method accumulates the fatigue driving time in each section of the vehicle trajectory information to obtain the fatigue driving time. The vehicle characteristic information can reflect the current driving conditions, including the vehicle driving conditions, the driver's state, the driving environment, etc.

[0036] The method uses an AI algorithm to obtain AI feature information that conforms to the driving time period according to the driving time period of the vehicle trajectory information. The AI ​​algorithm may be an open source AI tool or an independently developed AI algorithm. The method may input the vehicle trajectory information into the AI ​​algorithm to obtain AI feature information recognized by the AI. The AI ​​feature information is mainly data obtained after deep mining and deep analysis of the vehicle trajectory information. The AI ​​feature information corresponds to the time period of the vehicle trajectory information, that is, it reflects the data mining and analysis results of the vehicle during the current driving time.

[0037] The method determines the trip score according to the vehicle feature information and the AI ​​feature information through a scoring method. The vehicle feature information and the AI ​​feature information may include one or more features, and the user may choose to use all or part of the features for scoring. The scoring method page may include one or more, and the user may choose one of the scoring methods for scoring, or may fuse the scoring results of multiple scoring methods to obtain the final scoring result. The scoring method may be only a formulated scoring rule, or a model created according to the scoring rule, or a learning model trained based on historical vehicle feature information, historical AI feature information, and historical trip scores. The method may also classify drivers according to driving behavior based on the scoring results.

[0038] This method combines vehicle feature information and AI feature information to determine the trip score, that is, it considers simple processing results (vehicle feature information) and AI deep mining analysis results (AI feature information). Through rich feature data and scientific scoring methods, it improves the accuracy of the score, and can be used to evaluate the safety and efficiency of the trip, overcoming the defects of insufficient precision and less feature data in existing methods.

[0039] In one embodiment of the present application, the vehicle characteristic information includes at least one of the number of sharp turn alarms per 100 kilometers, the number of sharp acceleration alarms per 100 kilometers, and the number of sharp deceleration alarms per 100 kilometers;

[0040] The number of sharp turn alarms per 100 kilometers is obtained based on the ratio of the number of sharp turns to the total distance of the journey; the number of sharp acceleration alarms per 100 kilometers is obtained based on the ratio of the number of sharp accelerations to the total distance of the journey; the number of sharp deceleration alarms per 100 kilometers is obtained based on the ratio of the number of sharp decelerations to the total distance of the journey;

[0041] The number of sharp turns, sharp accelerations, and sharp decelerations is obtained through statistics of vehicle trajectory information; the vehicle trajectory information includes the total distance of the trip.

[0042] The method obtains the number of sharp turn alarms per 100 kilometers, the number of rapid acceleration alarms per 100 kilometers, and the number of rapid deceleration alarms per 100 kilometers according to the vehicle trajectory information, wherein the number of sharp turn alarms per 100 kilometers reflects the number of sharp turns that the driver makes during the current trip and the number of alarms is triggered, wherein the triggering of the alarm can be determined by the degree of the sharp turn, for example, when the sharp turn and the turning angle reach a preset value, the number of sharp turns is recorded once. The number of rapid acceleration alarms per 100 kilometers reflects the number of sharp accelerations that the driver makes during the current trip and the number of alarms is triggered, wherein the triggering of the alarm can be determined by the speed of the rapid acceleration, for example, when the rapid acceleration and the acceleration reach a preset value, the number of rapid accelerations is recorded once. The number of rapid deceleration alarms per 100 kilometers reflects the number of sharp decelerations that the driver makes during the current trip and the number of alarms is triggered, wherein the triggering of the alarm can be determined by the speed of the rapid deceleration, for example, when the rapid deceleration and the deceleration reach a preset value, the number of rapid decelerations is recorded once. The method divides the number of sharp turns, the number of rapid accelerations, and the number of rapid decelerations by the total distance of the trip and multiplies by 100 to obtain the number of sharp turn alarms per 100 kilometers, the number of rapid acceleration alarms per 100 kilometers, and the number of rapid deceleration alarms per 100 kilometers. The method can select at least one of the number of sharp turn alarms per 100 kilometers, the number of sharp acceleration alarms per 100 kilometers, and the number of sharp deceleration alarms per 100 kilometers to perform a trip score.

[0043] In one embodiment of the present application, the vehicle characteristic information further includes at least one of a nighttime driving mileage ratio and a fatigue driving mileage ratio;

[0044] The nighttime mileage ratio is calculated based on the ratio of nighttime driving time to total driving time; the fatigue mileage ratio is calculated based on the ratio of fatigue driving time to total driving time;

[0045] Night driving time and fatigue driving time are obtained based on vehicle trajectory information; the total driving time is obtained based on the driving time period.

[0046] The method obtains the proportion of night driving mileage and the proportion of fatigue driving mileage according to the vehicle trajectory information. The proportion of night driving mileage reflects the driver's night driving in the current trip. The night driving time includes the sum of night driving time and late night driving time. Generally, the driving time in the time period of 18:00-23:00 can be recorded as night driving time, and the driving time in the time period of 23:00-6:00 can be recorded as late night driving time. The proportion of fatigue driving mileage reflects the driver's fatigue driving in the current trip. When the driver's continuous driving time exceeds 4 hours, it is determined to be fatigue driving. For example, the driver's continuous driving time is 5 hours, and the fatigue driving time is 5 hours. For example, the driver's continuous driving time is 3 hours, and the fatigue driving time is 0 hours. The total driving time is obtained by subtracting the start time from the end time in the driving time period. The method divides the night driving time and the fatigue driving time by the total trip time respectively to obtain the proportion of night driving mileage and the proportion of fatigue driving mileage. The method can select at least one of the proportion of night driving mileage and the proportion of fatigue driving mileage for trip scoring.

[0047] In one embodiment of the present application, the vehicle characteristic information also includes the percentage of bad weather mileage;

[0048] The percentage of bad weather mileage is obtained based on the ratio of bad weather time to total driving time;

[0049] The bad weather time is obtained by counting the driving time in bad weather in each city in the vehicle trajectory information; the total driving time is determined according to the driving time period.

[0050] This method obtains the proportion of bad weather mileage based on vehicle trajectory information. When counting the bad weather time, you can first obtain the weather data of each city from a weather website or a public database, and then analyze the weather data of the cities passed by each section of the entire journey. When the weather data of the city passed is bad weather, such as heavy rain, thunderstorm, heavy snow, heavy fog, etc., the time driven in the bad weather is accumulated into the bad weather time. When the journey is over, the bad weather mileage proportion is calculated based on the accumulated bad weather time. Specifically, the bad weather time is divided by the total driving time to obtain the bad weather mileage proportion. This method can select the bad weather mileage proportion for the journey score.

[0051] In one embodiment of the present application, the vehicle characteristic information also includes the mileage ratio of familiar road sections;

[0052] The familiar road mileage ratio is obtained based on the ratio of the familiar road mileage to the total trip distance;

[0053] The travel distance of the familiar road section is determined according to the sum of the mileage of all familiar road sections in the vehicle trajectory information; the vehicle trajectory information includes multiple road sections; the familiar road section includes road sections that are the same as the road sections in the historical vehicle trajectory information for a preset number of times; the vehicle trajectory information includes the total travel distance.

[0054] The method obtains the mileage proportion of familiar sections according to the vehicle trajectory information. When the mileage proportion of familiar sections is counted, the longitude and latitude of each section in the entire journey can be obtained first, wherein the sections can be divided according to the road names. For example, if the entire journey passes through 3 main roads, the entire journey can be divided into 3 sections, or it can be divided according to the main buildings or main areas passed in the journey. Then each section is compared with the sections in the user's historical vehicle trajectory information. When the longitude and latitude of the current section A matches the longitude and latitude of the two sections in the historical vehicle trajectory information within a specific time (for example, 3 months), it can be determined that the section A is a familiar section. Assuming that the entire journey is divided into 3 sections: section A, section B and section C, sections A and section B are familiar sections, and section C is not a familiar section, then the familiar section driving distance is the sum of the mileage of section A and the mileage of section B, and the familiar section mileage proportion is the sum of the mileage of section A and the mileage of section B divided by the total journey distance. This method can select the mileage ratio of familiar sections for trip scoring.

[0055] In one embodiment of the present application, the AI ​​feature information includes at least one of the following: the number of distraction alarms per 100 kilometers, the number of phone call alarms per 100 kilometers, the number of mobile phone playing alarms per 100 kilometers, the number of smoking alarms per 100 kilometers, the number of fatigue driving alarms per 100 kilometers, the number of close vehicle distance alarms per 100 kilometers, the number of frequent lane change alarms per 100 kilometers, the number of forward collision alarms per 100 kilometers, and the number of pedestrian collision alarms per 100 kilometers.

[0056] The number of distraction alarms per 100 kilometers reflects the driver's distraction during driving. For example, the vehicle trajectory information includes the collected driver image information. The AI ​​algorithm recognizes that the driver is not looking forward or lowering his head based on the driver's image information, which is recorded as one distraction alarm. The number of distraction alarms per 100 kilometers is calculated based on the number of distraction alarms recorded within 100 kilometers.

[0057] The number of alarm calls per 100 kilometers reflects the situation of the driver making phone calls while driving. For example, the AI ​​algorithm recognizes that the driver is making a phone call based on the driver's image information, which is recorded as one alarm call. The number of alarm calls per 100 kilometers is obtained based on the number of alarm calls recorded within 100 kilometers.

[0058] The number of mobile phone playing alarms per 100 kilometers reflects the situation of the driver playing with the mobile phone while driving. For example, the AI ​​algorithm identifies the situation of the driver playing with the mobile phone based on the driver's image information, which is recorded as one mobile phone playing alarm. The number of mobile phone playing alarms per 100 kilometers is obtained based on the number of mobile phone playing alarms recorded within 100 kilometers.

[0059] The number of smoking alarms per 100 kilometers reflects the situation of the driver smoking while driving. For example, the AI ​​algorithm recognizes that the driver is smoking based on the driver's image information, which is recorded as one smoking alarm. The number of smoking alarms per 100 kilometers is obtained based on the number of smoking alarms recorded within 100 kilometers.

[0060] The number of fatigue driving alarms per 100 kilometers reflects the driver's fatigue during driving. For example, the AI ​​algorithm identifies that the driver is squinting or yawning based on the driver's image information, which is recorded as one fatigue driving alarm. The number of fatigue driving alarms per 100 kilometers is obtained based on the number of fatigue driving alarms recorded within 100 kilometers.

[0061] The number of close distance alarms per 100 kilometers reflects the situation where the distance between vehicles is too close during driving. For example, the vehicle trajectory information includes the distance to the vehicle in front collected by the sensor on the vehicle body. The AI ​​algorithm identifies the situation of the vehicle distance being too close based on the distance to the vehicle in front and records it as one close distance alarm number. The number of close distance alarms per 100 kilometers is obtained based on the number of close distance alarms recorded within 100 kilometers.

[0062] The number of frequent lane change alarms per 100 kilometers reflects the situation in which the driver frequently changes lanes during driving. For example, the vehicle trajectory information includes the driving environment image collected by the camera on the vehicle body. The AI ​​algorithm recognizes each lane change based on the driving environment image. When it is recognized that more than a set value (for example, 3-5 times) of lane changes occur in a short period of time, it is recorded as a frequent lane change alarm. The number of frequent lane change alarms per 100 kilometers is obtained based on the number of frequent lane change alarms recorded within 100 kilometers.

[0063] The number of forward collision warnings per 100 kilometers reflects the situation in which the driver is about to collide with the object in front during driving. For example, when the AI ​​algorithm recognizes that the vehicle is about to collide with the object in front based on the driving environment image, it is recorded as one forward collision warning. The number of forward collision warnings per 100 kilometers is obtained based on the number of forward collision warnings recorded within 100 kilometers.

[0064] The number of pedestrian collision alarms per 100 kilometers reflects the situation in which the driver is about to collide with a pedestrian during driving. For example, when the AI ​​algorithm recognizes that the vehicle is about to collide with a pedestrian based on the driving environment image, it is recorded as one pedestrian collision alarm. The number of pedestrian collision alarms per 100 kilometers is obtained based on the number of pedestrian collision alarms recorded within 100 kilometers.

[0065] In one embodiment of the present application, the scoring method includes a nonlinear regression method, and scoring can also be performed by the following methods, specifically including:

[0066] A standard vehicle feature and a standard AI feature under normal driving are defined as a parent sequence, wherein the standard vehicle feature and the standard AI feature are obtained by statistics of a plurality of data samples under normal driving; the data samples include the vehicle trajectory information;

[0067] Respectively calculating the distance between the vehicle feature information and the corresponding standard vehicle feature, and the distance between the AI ​​feature information and the corresponding standard AI feature;

[0068] All distances are weighted to obtain the trip score.

[0069] The method can select several (500-1000) data samples under normal driving for statistics to obtain standard features. For example, the driving data of vehicles that have not violated traffic rules in the past year can be selected as data samples. Standard features include standard vehicle features determined according to data samples, and standard AI features determined according to data samples using AI algorithms. Then the method calculates the distances between the features respectively, where the distances include Euclidean distance, cosine similarity, and the like. For example, the distance between the number of sharp turn alarms per 100 kilometers and the standard number of sharp turn alarms per 100 kilometers is calculated, the distance between the proportion of nighttime driving mileage and the standard proportion of nighttime driving mileage is calculated, the distance between the number of phone calls per 100 kilometers and the standard number of phone calls per 100 kilometers is calculated, and the like. The method also sets a weight for each feature. After obtaining the distances of all features, all distances are weighted to obtain the trip score. The weights of different features can be different or the same, and the weights of different features reflect the degree of influence of the feature on the final trip score. The method makes the trip score obtained more comprehensive and accurate by performing weighted operations on different features.

[0070] See also Figure 2 , Figure 2 It is a schematic block diagram of a trip scoring device based on driving behavior provided in an embodiment of the present application. Corresponding to the above trip scoring method based on driving behavior, the present application also provides a trip scoring device based on driving behavior. The trip scoring device based on driving behavior includes a unit for executing the above trip scoring method based on driving behavior, and the trip scoring device based on driving behavior can be configured in a desktop computer, a tablet computer, a laptop, and other terminals. Specifically, the trip scoring device based on driving behavior includes a data acquisition unit 101, a vehicle feature extraction unit 102, an AI feature extraction unit 103 and a scoring unit 104.

[0071] Data collection unit 101: obtain vehicle trajectory information;

[0072] The vehicle feature extraction unit 102 determines the vehicle feature information according to the vehicle trajectory information;

[0073] AI feature extraction unit 103: using an AI algorithm to obtain AI feature information that matches the driving time period according to the driving time period of the vehicle trajectory information;

[0074] Scoring unit 104: Determines a trip score according to the vehicle feature information and the AI ​​feature information through a scoring method.

[0075] See also Figure 3 , Figure 3 The present application provides a computer device, including a processor 111, a communication interface 112, a memory 113 and a communication bus 114, wherein the processor 111, the communication interface 112 and the memory 113 communicate with each other through the communication bus 114.

[0076] Memory 113, used for storing computer programs;

[0077] In one embodiment of the present application, the processor 111 is used to execute the program stored in the memory 113 to implement the trip scoring method based on driving behavior provided by any of the above method embodiments, including:

[0078] Get vehicle trajectory information;

[0079] Determining vehicle characteristic information according to the vehicle trajectory information;

[0080] Using an AI algorithm to obtain AI feature information that matches the driving time period according to the driving time period of the vehicle trajectory information;

[0081] The trip score is determined according to the vehicle feature information and the AI ​​feature information through a scoring method.

[0082] It is understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a storage medium, which is a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.

[0083] Therefore, an embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the trip scoring method based on driving behavior provided in any of the aforementioned method embodiments are implemented.

[0084] The storage medium is a physical, non-transient storage medium, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which can store program codes. Computer-readable storage media can be non-volatile or volatile.

[0085] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0086] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0087] The steps in the method of the embodiment of the present application can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present application can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0088] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the various embodiments of the present application.

[0089] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0090] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

[0091] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A trip scoring method based on driving behavior, characterized in that: include: Get vehicle trajectory information; Determining vehicle characteristic information according to the vehicle trajectory information; Using an AI algorithm to obtain AI feature information that matches the driving time period according to the driving time period of the vehicle trajectory information; The trip score is determined according to the vehicle feature information and the AI ​​feature information through a scoring method.

2. The trip scoring method according to claim 1, characterized in that: The vehicle characteristic information includes at least one of the number of sharp turn alarms per 100 kilometers, the number of sharp acceleration alarms per 100 kilometers, and the number of sharp deceleration alarms per 100 kilometers; The number of sharp turn alarms per 100 kilometers is obtained according to the ratio of the number of sharp turns to the total distance of the journey; the number of sharp acceleration alarms per 100 kilometers is obtained according to the ratio of the number of sharp accelerations to the total distance of the journey; the number of sharp deceleration alarms per 100 kilometers is obtained according to the ratio of the number of sharp decelerations to the total distance of the journey; The number of sharp turns, the number of sharp accelerations, and the number of sharp decelerations are obtained by counting the vehicle trajectory information; the vehicle trajectory information includes the total travel distance.

3. The trip scoring method according to claim 1, characterized in that: The vehicle characteristic information also includes at least one of a nighttime driving mileage ratio and a fatigue driving mileage ratio; The nighttime driving mileage ratio is obtained according to the ratio of the nighttime driving time to the total driving time; the fatigue driving mileage ratio is obtained according to the ratio of the fatigue driving time to the total driving time; The night driving time and the fatigue driving time are obtained by counting the vehicle trajectory information; The total driving time is obtained according to the driving time period.

4. The trip scoring method according to claim 1, characterized in that: The vehicle characteristic information also includes the percentage of bad weather mileage; The bad weather mileage ratio is obtained based on the ratio of the bad weather time to the total driving time; The bad weather time is obtained by counting the driving time under bad weather in each city in the vehicle trajectory information; the total driving time is determined according to the driving time period.

5. The trip scoring method according to claim 1, characterized in that: The vehicle characteristic information also includes the mileage ratio of familiar road sections; The familiar road section mileage ratio is obtained according to the ratio of the familiar road section driving distance to the total journey distance; The familiar road section driving distance is determined based on the total mileage of all familiar road sections in the vehicle trajectory information; the vehicle trajectory information includes multiple road sections; the familiar road section includes a road section that has the same number of times as a road section in the historical vehicle trajectory information reaching a preset value; the vehicle trajectory information includes the total travel distance.

6. The trip scoring method according to claim 1, characterized in that: The AI ​​feature information includes at least one of the following: number of distraction alarms per 100 kilometers, number of phone call alarms per 100 kilometers, number of mobile phone playing alarms per 100 kilometers, number of smoking alarms per 100 kilometers, number of fatigue driving alarms per 100 kilometers, number of close vehicle distance alarms per 100 kilometers, number of frequent lane change alarms per 100 kilometers, number of forward collision alarms per 100 kilometers, and number of pedestrian collision alarms per 100 kilometers; Among them, the number of distraction alarms per 100 kilometers is determined according to the driver's distraction within 100 kilometers; the number of phone call alarms per 100 kilometers is determined according to the number of phone calls made by the driver within 100 kilometers; the number of mobile phone playing alarms per 100 kilometers is determined according to the driver's mobile phone playing within 100 kilometers; the number of smoking alarms per 100 kilometers is determined according to the driver's smoking within 100 kilometers; the number of fatigue driving alarms per 100 kilometers is determined according to the driver's fatigue within 100 kilometers; the number of close vehicle distance alarms per 100 kilometers is determined according to the close vehicle distance during the driver's driving; the number of frequent lane change alarms per 100 kilometers is determined according to the driver's frequent lane changes during the driver's driving; the number of forward collision alarms per 100 kilometers is determined according to the situation that the driver is about to collide with the object in front within 100 kilometers; the number of pedestrian collision alarms per 100 kilometers is determined according to the situation that the driver is about to collide with a pedestrian while driving within 100 kilometers.

7. The trip scoring method according to claim 1, characterized in that: The scoring method specifically includes: A standard vehicle feature and a standard AI feature under normal driving are defined as a parent sequence, wherein the standard vehicle feature and the standard AI feature are obtained by statistics of a plurality of data samples under normal driving; the data samples include the vehicle trajectory information; respectively calculating the distance between the vehicle feature information and the corresponding standard vehicle feature, and the distance between the AI ​​feature information and the corresponding standard AI feature; All distances are weighted to obtain the trip score.

8. A trip scoring device based on driving behavior, characterized in that: The method comprises a unit for executing the method according to any one of claims 1 to 7.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 can be implemented.

Images