A vehicle-mounted computing power sharing scheduling method based on user driving behavior analysis

Abstract

The application discloses a vehicle-mounted computing power sharing scheduling method based on user driving behavior analysis, and steps include: 1) based on user historical driving behavior data and current state of the vehicle, the priority of vehicle computing power sharing is evaluated; 2) the user end sends a computing power request to the cloud end; 3) based on the priority of vehicle computing power sharing, the cloud end schedules one or more vehicle ends with the highest priority, answers the computing power request, and uploads the answer result to the cloud end; 4) the cloud end summarizes the answer result and transmits to the user end. The application dynamically determines the time of starting vehicle computing power sharing by clustering and analyzing driving style data, does not depend on charging piles, and effectively utilizes idle computing power of the vehicle.

Description

Technical Field

[0001] This invention relates to the fields of edge computing and vehicle computing power sharing, specifically a vehicle computing power sharing scheduling method based on user driving behavior analysis. Background Technology

[0002] With the rapid development of vehicle-to-everything (V2X) technology, the processing power of in-vehicle computing devices has been significantly enhanced. Compared to cloud servers that operate 24 / 7, in-vehicle computing resources are typically only used for intelligent driving assistance systems when the vehicle is running. During periods when the vehicle is not in use, these computing resources are often underutilized, resulting in significant waste. Effectively mobilizing and utilizing this idle in-vehicle computing power can save resources and bring significant benefits to society and the economy. Existing vehicle computing power sharing methods acquire the vehicle's status information when it connects to a charging station and utilize the vehicle's idle state during off-peak electricity periods to execute pre-set computing tasks distributed from the cloud. This method releases the vehicle's computing resources during charging and enables collaborative computing among multiple vehicles when electricity costs are low, achieving efficient processing of computing tasks.

[0003] Existing technologies in the field of vehicle computing power sharing mainly rely on the availability of charging stations and fluctuations in electricity costs to schedule computing resources, which limits their application capabilities in environments without charging stations. Limited by the dependence on charging infrastructure, existing methods cannot effectively address the computing power needs of vehicles when charging station support is lacking, especially during peak hours when computing power strain needs to be avoided. To address these limitations, this invention proposes an innovative vehicle computing power sharing scheduling method and device. Through intelligent prediction and scheduling algorithms, it optimizes the allocation and utilization of vehicle computing resources when a vehicle is connected to or away from a charging station, ensuring the continuity and efficiency of computing power services, and maintaining service quality even under conditions of limited power resources. Therefore, developing a vehicle computing power sharing scheduling method, system, and device based on user driving behavior analysis is of great significance for improving the utilization rate of vehicle computing power and providing users with more flexible and reliable computing power sharing services. Summary of the Invention

[0004] The purpose of this invention is to provide a vehicle computing power sharing and scheduling method based on user driving behavior analysis, comprising the following steps:

[0005] 1) Construct a vehicle-side computing power sharing system, including the cloud and the vehicle; the cloud stores the historical driving behavior data of vehicle users and obtains the current vehicle status in real time;

[0006] 2) Evaluate the priority of vehicle computing power sharing based on the historical driving behavior data of vehicle users and the current status of the vehicle;

[0007] 3) The user sends a computing power request to the cloud;

[0008] 4) Based on the vehicle computing power sharing priority, the cloud schedules one or more vehicle-side computing powers with the highest priority to respond to computing power requests and upload the response results to the cloud;

[0009] 5) The cloud summarizes the response results and transmits them to the user terminal.

[0010] Furthermore, in step 1), the current vehicle status includes the current vehicle usage status λ1, the remaining vehicle battery power a, and the vehicle power connection status λ2; λ2 = 1 indicates that the vehicle is connected to power, and λ2 = 0 indicates that the vehicle is not connected to power.

[0011] Furthermore, in step 2), after the user sends a computing power request to the cloud, the cloud determines the response service type corresponding to the computing power request; the response service type includes continuous response service and one-time response service.

[0012] If the response service type is continuous response service, the cloud will allocate computing power with higher priority.

[0013] Continuous response service requires contextual information, so the cloud will allocate higher priority computing power to it to ensure service continuity.

[0014] Furthermore, in step 3), the rules for evaluating the priority of vehicle computing power sharing include:

[0015] The more battery power a vehicle has remaining or the more power it is connected to, the higher the priority of computing power startup.

[0016] The greater the probability that a vehicle will not be used in the next m time slots, the higher the priority of computing power activation.

[0017] The more conservative the driver's driving style, the higher the priority of computing power activation.

[0018] Furthermore, in step 3), the step of evaluating the priority of vehicle computing power sharing includes:

[0019] 3.1) Cluster analysis was performed on users' historical driving behavior data to obtain multiple driving style cluster centers;

[0020] 3.2) Based on the cluster center index of driving style, assign a driving style level s∈|K| to the vehicle; the higher the driving style level s, the greater the priority of vehicle computing power sharing;

[0021] 3.3) Based on the time-series data of driving style, calculate the probability p = n of the car owner using the vehicle in the future m time slot. m / n;n m n is the number of times the car owner has used the vehicle in history. m where n is the total number of days;

[0022] 3.4) Calculate the vehicle computing power sharing priority S = sa(2-λ1)(λ2+1)(1-p); the larger the value of S, the higher the vehicle's computing power activation priority.

[0023] Furthermore, in step 3.1), the method for clustering analysis of users' historical driving behavior data includes the K-Means method.

[0024] Furthermore, step 3.1), the step of clustering analysis on the user's historical driving behavior data, includes:

[0025] 3.1.1) Collect driving behavior data, denoted as x i ={x i1 ,x i2 ,...,x i5};x i1 ,x i2 ,...,x i5 These represent vehicle speed, accelerator pedal opening, following distance, acceleration, and braking frequency, respectively.

[0026] 3.1.2) Use the elbow rule to determine the value of K, and calculate the total sum of squares for different K values. Where N is the total number of data points, K is the number of clusters, and μ j It is the centroid of the j-th cluster, δ(y i ,μ j ) is an indicator function, if x i If it belongs to cluster i, the value is 1; otherwise, it is 0. ||x i -μ j || is data point x i With the center of mass μ j The Euclidean distance between them;

[0027] 3.1.3) Set the initial centroid Initialize the number of iterations t = 1;

[0028] 3.1.4) For each data point x i Assigned to the nearest centroid y i =argmin||x i -μ j || 2 ;

[0029] 3.1.5) Recalculate the centroid Among them, C j It is the set of all data points in the j-th cluster, |C j | is the number of data points in cluster j;

[0030] 3.1.6) Judgment Alternatively, check if t is greater than tmax. If not, let t = t + 1 and update the centroid. And return to step 3.1.4). If yes, end the iteration and select the K value with the slowest SSE descent rate as the optimal number of clusters; ∈ is the error threshold; tmax is the maximum number of iterations.

[0031] 3.1.7) Cluster the user's historical driving behavior data based on the cluster number K.

[0032] Furthermore, in step 3.1.3), the initial centroid is set by either randomly selecting K data points as the initial centroid, or by using the K-Means algorithm to initialize the centroid. D(x) is the cost function for choosing data x as the centroid.

[0033] Furthermore, in step 4), the cloud periodically schedules one or more vehicle-end computing powers with the highest priority, with a scheduling period of m time slots.

[0034] Furthermore, in step 4), after scheduling one or more vehicle-side computing powers with the highest priority in the cloud, the vehicle-side revenue is periodically settled.

[0035] The technical effects of this invention are undeniable. This invention proposes a method and device for sharing idle computing power on the vehicle side that integrates vehicle status and user behavior analysis. Through intelligent scheduling algorithms, it optimizes the allocation and use of computing power on the vehicle side, ensuring the efficiency and continuity of computing power services, and making full use of the vehicle's idle computing resources without interfering with the vehicle owner's normal use of the vehicle.

[0036] This invention uses cluster analysis of driving style data to dynamically determine the time for sharing vehicle startup computing power, without relying on charging piles, and effectively utilizes the vehicle's idle computing power.

[0037] In the vehicle-cloud-user system architecture, users can rent computing power according to their needs without worrying about the computing power provider, and car owners can rent out computing power according to their usage habits.

[0038] The cloud makes computing power scheduling decisions every m time slots, which can effectively sense changes in vehicle status in order to achieve load balancing. Attached Figure Description

[0039] Figure 1 System model diagram;

[0040] Figure 2 For business process diagrams;

[0041] Figure 3 This is a flowchart of the computing power sharing algorithm. Detailed Implementation

[0042] The present invention will be further described below with reference to embodiments, but it should not be construed that the scope of the present invention is limited to the following embodiments. Various substitutions and modifications made based on ordinary technical knowledge and common practices in the art without departing from the above-described technical concept of the present invention should be included within the scope of protection of the present invention.

[0043] Example 1:

[0044] See Figures 1 to 3 A method for sharing and scheduling onboard computing power based on user driving behavior analysis includes the following steps:

[0045] 1) Construct a vehicle-side computing power sharing system, including the cloud and the vehicle; the cloud stores the historical driving behavior data of vehicle users and obtains the current vehicle status in real time;

[0046] 2) Evaluate the priority of vehicle computing power sharing based on the historical driving behavior data of vehicle users and the current status of the vehicle;

[0047] 3) The user sends a computing power request to the cloud;

[0048] 4) Based on the vehicle computing power sharing priority, the cloud schedules one or more vehicle-side computing powers with the highest priority to respond to computing power requests and upload the response results to the cloud;

[0049] 5) The cloud summarizes the response results and transmits them to the user terminal.

[0050] In step 1), the current vehicle status includes the current vehicle usage status λ1, the remaining vehicle battery power a, and the vehicle power connection status λ2; λ2 = 1 indicates that the vehicle is connected to power, and λ2 = 0 indicates that the vehicle is not connected to power.

[0051] If the response service type is continuous response service, the cloud will allocate computing power with higher priority.

[0052] Continuous response service requires contextual information, so the cloud will allocate higher priority computing power to it to ensure service continuity.

[0053] In step 2), after the user sends a computing power request to the cloud, the cloud determines the response service type corresponding to the computing power request; the response service type includes continuous response service and one-time response service.

[0054] In step 3), the rules for evaluating the priority of vehicle computing power sharing include:

[0055] The more battery power a vehicle has remaining or the more power it is connected to, the higher the priority of computing power startup.

[0056] The greater the probability that a vehicle will not be used in the next m time slots, the higher the priority of computing power activation.

[0057] The more conservative the driver's driving style, the higher the priority of computing power activation.

[0058] Step 3) includes the following steps for evaluating the priority of vehicle computing power sharing:

[0059] 3.1) Cluster analysis was performed on users' historical driving behavior data to obtain multiple driving style cluster centers;

[0060] 3.2) Based on the cluster center index of driving style, assign a driving style level s∈|K| to the vehicle; the higher the driving style level s, the greater the priority of vehicle computing power sharing;

[0061] 3.3) Based on the time-series data of driving style, calculate the probability p = n of the car owner using the vehicle in the future m time slot. m / n;n m n is the number of times the car owner has used the vehicle in history. m where n is the total number of days;

[0062] 3.4) Calculate the vehicle computing power sharing priority S = sa(2-λ1)(λ2+1)(1-p); the larger the value of S, the higher the vehicle's computing power activation priority.

[0063] In step 3.1), the method for clustering analysis of users' historical driving behavior data includes the K-Means method.

[0064] Step 3.1) involves performing cluster analysis on users' historical driving behavior data, including:

[0065] 3.1.1) Collect driving behavior data, denoted as x i ={x i1 ,x i2 ,...,x i5};x i1 ,x i2 ,...,x i5 These represent vehicle speed, accelerator pedal opening, following distance, acceleration, and braking frequency, respectively.

[0066] 3.1.2) Use the elbow rule to determine the value of K, and calculate the total sum of squares for different K values. Where N is the total number of data points, K is the number of clusters, and μ j It is the centroid of the j-th cluster, δ(y i ,μ i ) is an indicator function, if x i If it belongs to cluster i, the value is 1; otherwise, it is 0. ||x i -μ j || is data point x i With the center of mass μ j The Euclidean distance between them;

[0067] 3.1.3) Set the initial centroid Initialize the number of iterations t = 1;

[0068] 3.1.4) For each data point x i Assigned to the nearest centroid y i =argmin||x i -μ j || 2 ;

[0069] 3.1.5) Recalculate the centroid Among them, C j It is the set of all data points in the j-th cluster, |C j | is the number of data points in cluster j;

[0070] 3.1.6) Judgment Alternatively, check if t is greater than tmax. If not, let t = t + 1 and update the centroid. And return to step 3.1.4). If yes, end the iteration and select the K value with the slowest SSE descent rate as the optimal number of clusters; ∈ is the error threshold; tmax is the maximum number of iterations.

[0071] 3.1.7) Cluster the user's historical driving behavior data based on the cluster number K.

[0072] In step 3.1.3), the initial centroids are set either by randomly selecting K data points as the initial centroids, or by using the K-Means algorithm to initialize the centroids. D(x) is the cost function for choosing data x as the centroid.

[0073] In step 4), the cloud periodically schedules one or more vehicle-side computing powers with the highest priority, with a scheduling period of m time slots.

[0074] In step 4), after scheduling one or more vehicle-side computing powers with the highest priority in the cloud, the vehicle-side revenue is periodically settled.

[0075] Example 2:

[0076] A method for sharing and scheduling on-board computing power based on user driving behavior analysis includes the following steps:

[0077] 1) Construct a vehicle-side computing power sharing system, including the cloud and the vehicle; the cloud stores the historical driving behavior data of vehicle users and obtains the current vehicle status in real time;

[0078] 2) Evaluate the priority of vehicle computing power sharing based on the historical driving behavior data of vehicle users and the current status of the vehicle;

[0079] 3) The user sends a computing power request to the cloud;

[0080] 4) Based on the vehicle computing power sharing priority, the cloud schedules one or more vehicle-side computing powers with the highest priority to respond to computing power requests and upload the response results to the cloud;

[0081] 5) The cloud summarizes the response results and transmits them to the user terminal.

[0082] Example 3:

[0083] A vehicle computing power sharing and scheduling method based on user driving behavior analysis, with the same technical content as in Embodiment 2, further wherein, in step 1), the current vehicle status includes the current vehicle usage status λ1, the remaining vehicle power a, and the vehicle power connection status λ2; λ2 = 1 indicates that the vehicle is connected to power, and λ2 = 0 indicates that the vehicle is not connected to power.

[0084] Example 4:

[0085] A method for sharing and scheduling vehicle computing power based on user driving behavior analysis, with technical content identical to any one of embodiments 2-3, further comprising the following step 2): After the user sends a computing power request to the cloud, the cloud determines the response service type corresponding to the computing power request; the response service type includes continuous response service and one-time response service. If the response service type is continuous response service, the cloud allocates computing power with higher priority.

[0086] Continuous response service requires contextual information, so the cloud will allocate higher priority computing power to it to ensure service continuity.

[0087] Example 5:

[0088] A method for sharing and scheduling vehicle computing power based on user driving behavior analysis, with technical content the same as any one of embodiments 2-4, further comprising the following rules for evaluating the priority of vehicle computing power sharing in step 3):

[0089] The more battery power a vehicle has remaining or the more power it is connected to, the higher the priority of computing power startup.

[0090] The greater the probability that a vehicle will not be used in the next m time slots, the higher the priority of computing power activation.

[0091] The more conservative the driver's driving style, the higher the priority of computing power activation.

[0092] Example 6:

[0093] A method for vehicle-mounted computing power sharing and scheduling based on user driving behavior analysis, with technical content identical to any one of embodiments 2-5, further comprising, in step 3), evaluating the priority of vehicle computing power sharing, including:

[0094] 3.1) Cluster analysis was performed on users' historical driving behavior data to obtain multiple driving style cluster centers;

[0095] 3.2) Based on the cluster center index of driving style, assign a driving style level s∈|K| to the vehicle; the higher the driving style level s, the greater the priority of vehicle computing power sharing;

[0096] 3.3) Based on the time-series data of driving style, calculate the probability p = n of the car owner using the vehicle in the future m time slot. m / n;n m n is the number of times the car owner has used the vehicle in history. m where n is the total number of days;

[0097] 3.4) Calculate the vehicle computing power sharing priority S = sa(2-λ1)(λ2+1)(1-p); the larger the value of S, the higher the vehicle's computing power activation priority.

[0098] Example 7:

[0099] A vehicle computing power sharing and scheduling method based on user driving behavior analysis, with the same technical content as any one of embodiments 2-6, further wherein, in step 3.1), the method for clustering analysis of user historical driving behavior data includes the K-Means method.

[0100] Example 8:

[0101] A method for sharing and scheduling vehicle computing power based on user driving behavior analysis, with technical content the same as any one of embodiments 2-7, further comprising the following steps in step 3.1): performing cluster analysis on user historical driving behavior data.

[0102] 3.1.1) Collect driving behavior data, denoted as x i ={x i1 ,x i2 ,...,x i5};x i1 ,x i2 ,...,x i5 These represent vehicle speed, accelerator pedal opening, following distance, acceleration, and braking frequency, respectively.

[0103] 3.1.2) Use the elbow rule to determine the value of K, and calculate the total sum of squares for different K values. Where N is the total number of data points, K is the number of clusters, and μ j It is the centroid of the j-th cluster, δ(y i,μ j ) is an indicator function, if x i If it belongs to cluster i, the value is 1; otherwise, it is 0. ||x i -μ j || is data point x i With the center of mass μ j The Euclidean distance between them;

[0104] 3.1.3) Set the initial centroid Initialize the number of iterations t = 1;

[0105] 3.1.4) For each data point x i Assigned to the nearest centroid y i =argmin||x i -μ j || 2 ;

[0106] 3.1.5) Recalculate the centroid Among them, C j It is the set of all data points in the j-th cluster, |C j | is the number of data points in cluster j;

[0107] 3.1.6) Judgment Alternatively, check if t is greater than tmax. If not, let t = t + 1 and update the centroid. And return to step 3.1.4). If yes, end the iteration and select the K value with the slowest SSE descent rate as the optimal number of clusters; ∈ is the error threshold; tmax is the maximum number of iterations.

[0108] 3.1.7) Cluster the user's historical driving behavior data based on the cluster number K.

[0109] Example 9:

[0110] A method for sharing and scheduling on-board computing power based on user driving behavior analysis, with technical content the same as any one of embodiments 2-8, further wherein, in step 3.1.3), the initial centroid is set by randomly selecting K data points as the initial centroid, or by using the K-Means algorithm to initialize the centroid. D(x) is the cost function for choosing data x as the centroid.

[0111] Example 10:

[0112] A vehicle computing power sharing and scheduling method based on user driving behavior analysis, with the same technical content as any one of embodiments 2-9, further wherein, in step 4), the cloud periodically schedules one or more vehicle-end computing powers with the highest priority, and the scheduling period is m time slots.

[0113] Example 11:

[0114] A method for sharing and scheduling vehicle computing power based on user driving behavior analysis, with the same technical content as any one of embodiments 2-10, further wherein, in step 4), after scheduling one or more vehicle-side computing powers with the highest priority in the cloud, the vehicle-side revenue is periodically settled.

[0115] Example 11:

[0116] A method for sharing and scheduling on-board computing power based on user driving behavior analysis, comprising the following steps:

[0117] 1) Model the vehicle-side computing power sharing system. The vehicle owner authorizes the sharing of vehicle computing power. The cloud obtains the user's historical driving behavior data and the current vehicle status: current vehicle usage status λ1, remaining vehicle battery power a, and whether the vehicle is connected to a power source λ2.

[0118] 2) Users send computing power requests to the cloud. The cloud assesses whether the user requires continuous service, such as AI dialogue, or context-insensitive tasks, such as one-off AI conversational services. The cloud will maintain the consistency of user sessions for critical AI model applications to ensure service continuity.

[0119] 3) The cloud dynamically determines the vehicle computing power sharing time. The cloud performs computing power scheduling every m time slots. The cloud evaluates the vehicle's computing power sharing priority. We assess the vehicle's remaining computing power based on its status and driving style. Specifically, the more battery power a vehicle has remaining or is connected to a power source, the higher its computing power activation priority; the higher the probability that the vehicle will not be used in the next m time slots, the higher its computing power activation priority; the more conservative the driver's driving style, meaning they will not frequently perform tasks requiring high computing power (such as high-speed driving or complex driving operations), the higher their computing power activation priority. The specific calculation steps for computing power activation priority are as follows:

[0120] 3.1) The K-Means algorithm is used to perform cluster analysis on driving behavior, and K is defined as the number of classification levels of driving style. The specific steps are as follows:

[0121] 3.1.1) Collect driving behavior data, denoted as x i = (vehicle speed, accelerator pedal opening, following distance, acceleration, and braking frequency), and determine these as characteristic indicators of driving style.

[0122] 3.1.2) Use the "elbow rule" to determine the K value, and calculate the total sum of squares (SSE) for different K values: Where N is the total number of data points, K is the number of clusters, and μ j It is the centroid of the j-th cluster, δ(y i ,μ j) is an indicator function, if x i If it belongs to cluster i, the value is 1; otherwise, it is 0. ||x i -μ j || is data point x i With the center of mass μ j The Euclidean distance between them.

[0123] 3.1.3) Randomly select K data points as the initial centroids, or use the K-Means algorithm to initialize the centroids: μ j =argmin j D(x). Where D(x) is the cost function for choosing data x as the centroid, which is usually proportional to the square of the distance to the nearest centroid.

[0124] 3.1.4) For each data point x i Assigned to the nearest centroid μ j y i =argmin||x i -μ j || 2 .

[0125] 3.1.5) Recalculate the centroids. For each cluster, recalculate the centroids. Among them, C j It is the set of all data points in the j-th cluster, |C j | represents the number of data points in cluster j.

[0126] 3.1.6) Repeat steps 3.1.4) and 3.1.5) until one of the following conditions is met:

[0127] (a) The change in the centroid is less than the preset threshold:

[0128] (b) Reach the preset number of iterations.

[0129] 3.1.7) Repeat steps 3.1.2) to 3.1.6) and select the K value with the slowest SSE decrease rate as the optimal number of clusters.

[0130] 3.1.8) Result Interpretation. Drivers are categorized into different style levels s, s∈|K|, based on the cluster center values, with priority given to the sequence (vehicle speed, accelerator pedal opening, following distance, acceleration, and braking frequency). A higher s indicates a more conservative driving style, meaning more remaining computational power for the vehicle.

[0131] 3.2) Based on driving style time-series data, in the future m time slots, refer to the owner's historical vehicle usage count n. m Given a total of n days, the probability of a car owner using the vehicle in the next m time slots is: p = nm / n.

[0132] 3.3) Further, the computing power activation priority of each vehicle in the future m time slot is obtained as: S=sa(2-λ1)(λ2+1)(1-p). The larger the value of S, the higher the computing power activation priority of the vehicle.

[0133] 4) After the car owner completes the computing power sharing, the vehicle automatically sends the shared time period data to the cloud. The cloud quickly calculates and updates the car owner's earnings, and settles them with the car owner periodically in a secure manner. The car owner can view detailed sharing records and earnings through a mobile application.

Claims

1. A method for sharing and scheduling on-board computing power based on user driving behavior analysis, characterized in that, Includes the following steps: Step 1) Construct a vehicle-side computing power sharing system, including the cloud and the vehicle; The system stores historical driving behavior data of vehicle users in the cloud and obtains the current vehicle status in real time. Step 2) Based on the historical driving behavior data of vehicle users and the current status of the vehicle, assess the priority of vehicle computing power sharing; Step 3) The user sends a computing power request to the cloud; Step 4) Based on the vehicle computing power sharing priority, the cloud schedules one or more vehicle-side computing powers with the highest priority to respond to computing power requests and upload the response results to the cloud; Step 5) The cloud summarizes the response results and transmits them to the user's terminal; In step 3), after the user sends a computing power request to the cloud, the cloud determines the response service type corresponding to the computing power request; the response service type includes continuous response service and one-time response service. If the response service type is continuous response service, the cloud will allocate computing power with higher priority. Step 3), the steps for evaluating the priority of vehicle computing power sharing include: Step 3.1) Perform cluster analysis on the user's historical driving behavior data to obtain multiple driving style cluster centers; Step 3.2) Assign a driving style level to the vehicle based on the driving style cluster center index. Vehicle-side driving style levels The higher the value, the greater the priority for vehicle computing power sharing; Step 3.3) Calculate the probability of the car owner using the vehicle in the future m time slot based on the driving style time series data. = ; Historical number of times the car owner has used the vehicle Total number of days; Step 3.4) Calculate the vehicle computing power sharing priority. ; The higher the value, the higher the vehicle's computing power activation priority; The remaining battery power of the vehicle; , This refers to the vehicle's power connection status and current usage status.

2. The vehicle-mounted computing power sharing and scheduling method based on user driving behavior analysis according to claim 1, characterized in that, In step 1), the current vehicle status includes the current vehicle usage status. Remaining battery power in the vehicle Vehicle power connection status quantity ; =1 indicates that the vehicle is connected to a power source. =0 indicates that the vehicle is not connected to a power source.

3. The vehicle-mounted computing power sharing and scheduling method based on user driving behavior analysis according to claim 1, characterized in that, In step 2), the rules for evaluating the priority of vehicle computing power sharing include: The more battery power a vehicle has remaining or the more power it is connected to, the higher the priority of computing power startup. Vehicles in the future The higher the probability that a time slot is not used, the higher the priority of computing power activation. The more conservative the driver's driving style, the higher the priority of computing power activation.

4. The vehicle-mounted computing power sharing and scheduling method based on user driving behavior analysis according to claim 1, characterized in that, In step 3.1), the method for clustering analysis of users' historical driving behavior data includes the K-Means method.

5. The vehicle-mounted computing power sharing and scheduling method based on user driving behavior analysis according to claim 1, characterized in that, Step 3.1), the steps for clustering analysis of users' historical driving behavior data include: Step 3.1.1) Collect driving behavior data, denoted as ; These represent vehicle speed, accelerator pedal opening, following distance, acceleration, and braking frequency, respectively. Step 3.1.2) Use the elbow rule to determine the value of K, and calculate the total sum of squares for different K values. ;in It is the total number of data points. It is the number of clusters. It is the first The centroid of each cluster, δ( ) is an indicator function, if Belongs to clustering The value is 1 if it is 1, otherwise it is 0. Data points With center of mass The Euclidean distance between them; Step 3.1.3) Set the initial centroid Initialize the number of iterations t=1; Step 3.1.4) Transfer each data point Assigned to the nearest centroid : ; Step 3.1.5) Recalculate the centroid ,in, It is the first The set of all data points in each cluster, | | is clustering The number of data points in the middle; Step 3.1.6) Judgment Alternatively, check if t is greater than tmax. If not, set t = t + 1 and update the centroid. = If the iteration ends and the iteration returns to step 3.1.4, then the K value with the slowest SSE descent rate is selected as the optimal number of clusters. tmax is the error threshold; tmax is the maximum number of iterations. Step 3.1.7) Cluster the user's historical driving behavior data based on the number of clusters K.

6. The vehicle-mounted computing power sharing and scheduling method based on user driving behavior analysis according to claim 5, characterized in that, In step 3.1.3), the initial centroid is set by randomly selecting... Use one data point as the initial centroid, or use the K-Means algorithm to initialize the centroid. ; Selecting data points The cost function as the centroid.

7. The vehicle-mounted computing power sharing and scheduling method based on user driving behavior analysis according to claim 1, characterized in that, In step 4), the cloud periodically schedules one or more vehicle-side computing resources with the highest priority, with a scheduling period of [missing information]. Each time slot.

8. The vehicle-mounted computing power sharing and scheduling method based on user driving behavior analysis according to claim 1, characterized in that: In step 4), after the cloud schedules one or more vehicle-side computing powers with the highest priority, the vehicle-side revenue is settled periodically.

Images