Intelligent automobile program updating method and system

Abstract

The invention discloses an intelligent automobile program updating method and system. The intelligent automobile program updating method comprises the steps that firstly, a planned travel preset by a user is obtained; and then predicting a network state prediction result and a driving state prediction result of the driving path in the planned travel at different time in the future, and determining a network state and a driving state of the intelligent vehicle at different time in the future in combination with the prediction time of the intelligent vehicle reaching different positions of the driving path. Finally, the network state and the driving state of the intelligent automobile at different moments in the future and the data volume and the updating duration of the to-be-updated program are synthesized, the most suitable transmission time window and the most suitable updating time window are selected, the data packet is received in time, the to-be-updated program is rapidly updated, the waiting time for applying the latest program is shortened, and the updating efficiency is improved. Therefore, the updated program can provide services for the user as soon as possible.

Description

Technical Field

[0001] This invention relates to the field of software update technology, and specifically to a method and system for updating software in intelligent vehicles. Background Technology

[0002] In recent years, the intelligence level of smart cars has developed rapidly. Manufacturers regularly update various programs configured in smart cars to provide users with a better driving experience. However, since program updates require the smart car's network bandwidth to transmit update data packets, this can affect the smart car's network services. Furthermore, updates can also disrupt the normal operation of the programs. Therefore, choosing appropriate transmission and update times to avoid impacting user experience and enhance overall user satisfaction is crucial. Summary of the Invention

[0003] To address the shortcomings of existing technologies, this invention proposes a method and system for updating intelligent vehicle programs, capable of selecting an appropriate time window to transmit update packages and update programs. The specific technical solution is as follows: In a first aspect, a method for updating a smart car's software is provided, wherein in a first implementable manner of the first aspect, the method includes: Obtain the pending updates and planned routes for smart cars; Predict the network and driving status of intelligent vehicles at different times in the future based on the planned itinerary; Based on the network status and driving status of the intelligent vehicle at different times in the future, as well as the data volume and update duration of the program to be updated, the transmission time window and update time window of the program to be updated are determined.

[0004] In conjunction with the first implementable method of the first aspect, in the second implementable method of the first aspect, obtaining the update program for the intelligent vehicle includes: Real-time acquisition of vehicle status and software update notifications for intelligent vehicles; The priority of each target update program in the program update notification is determined based on the vehicle status, and the target update program with the highest priority is selected as the program to be updated.

[0005] In conjunction with the first feasible approach of the first aspect, in the third feasible approach of the first aspect, the network status of the intelligent vehicle at different times in the future is predicted based on the planned trip, including: Based on traffic flow data and traffic environment data at different locations along the planned route, a pre-set traffic flow prediction model is used to predict the traffic flow distribution of the planned route at different future times. By combining traffic flow distribution and network coverage data for planned trips at different future times, the network status distribution of planned trips at different future times can be predicted. Based on the current driving status and traffic environment of the intelligent vehicle, the arrival time of the intelligent vehicle to different locations in the planned route is predicted by the trajectory prediction model. By matching the arrival time of intelligent vehicles at different locations with the network state distribution of planned journeys at different future times, the network state of intelligent vehicles at different future times can be determined.

[0006] In conjunction with the first possible implementation of the first aspect, in the fourth possible implementation of the first aspect, determining the transmission time window of the program to be updated includes: Based on the network status of intelligent vehicles at different times in the future, select the best time period for the intelligent vehicle's network status. Based on the network status corresponding to the optimal time period and the amount of data of the program to be updated, determine the transmission duration required to transmit the program to be updated; Determine whether the transmission duration is greater than the duration corresponding to the optimal time period; In response to the transmission duration not exceeding the duration corresponding to the optimal time period, the optimal time period is taken as the transmission time window; In response to the transmission duration being longer than the duration corresponding to the optimal time period, the optimal time period is discarded, and a new optimal time period with the best network condition is determined.

[0007] In conjunction with the first possible implementation of the first aspect, in the fifth possible implementation of the first aspect, determining the update time window of the program to be updated includes: Determine whether a shutdown is required for the update based on the update requirements of the program to be updated; In response to the requirement of not stopping, the update time window is determined based on the update duration corresponding to the program to be updated, with the end time of the transmission time window as the start time. In response to the need to park, the system can filter out the future parking times of the smart car by analyzing its driving status at different times in the future. Select the parking time period from all parking time periods whose parking duration exceeds the update duration and is closest to the transmission time window as the update time window.

[0008] In conjunction with the first possible implementation of the first aspect, in the sixth possible implementation of the first aspect, determining the transmission time window and the update time window of the program to be updated includes: Based on the network and driving status of the intelligent vehicle at different future times, as well as the data volume and update duration of the program to be updated, the particle swarm optimization algorithm is used to determine the optimal transmission time window and update time window.

[0009] In conjunction with the sixth feasible implementation of the first aspect, the seventh feasible implementation of the first aspect employs a particle swarm optimization algorithm to determine the optimal transmission time window and update time window, including: The objective function is to minimize the total time, which includes the interval between the start time of the transmission time window and the current time, the transmission time required to transmit the program to be updated, the interval between the transmission time window and the update time window, and the update time.

[0010] Secondly, a smart car program update system is provided, wherein in a first implementable manner of the second aspect, it includes: The acquisition module is configured to acquire the smart car's pending updates and planned routes; The prediction module is configured to predict the network status and driving status of the intelligent vehicle at different times in the future based on the planned route; The push module is configured to determine the transmission time window and update time window of the program to be updated by combining the network status and driving status of the intelligent vehicle at different times in the future, as well as the data volume and update duration of the program to be updated.

[0011] In conjunction with the first possible implementation of the second aspect, in the second possible implementation of the second aspect, the push module includes: The filtering unit is configured to filter the optimal time period for the best network status of the intelligent vehicle based on the network status of the intelligent vehicle at different times in the future. The computing unit is configured to determine the transmission duration required to transmit the program to be updated based on the network status corresponding to the optimal time period and the amount of data of the program to be updated. The determining unit is configured to determine whether the transmission duration is greater than the duration corresponding to the optimal time period; In response to the transmission duration not exceeding the duration corresponding to the optimal time period, the optimal time period is taken as the transmission time window; In response to the transmission duration being longer than the duration corresponding to the optimal time period, the optimal time period is discarded, and a new optimal time period with the best network condition is determined.

[0012] In conjunction with the first possible implementation of the second aspect, in the third possible implementation of the second aspect, the push module includes: The optimization unit is configured to combine the network status and driving status of the intelligent vehicle at different future times, as well as the data volume and update duration of the program to be updated, and use the particle swarm optimization algorithm to determine the optimal transmission time window and update time window.

[0013] Beneficial effects: The intelligent vehicle program update method and system of the present invention, upon receiving a program update notification, can predict the network and driving status of the intelligent vehicle at different times in the future based on the user's future planned trip. Then, combined with the data volume and update duration of the program to be updated, a transmission time window with the shortest interval between the notification reception and the transmission duration is selected from the future time range for transmitting the update package of the program to be updated. The update time window with the shortest interval between the transmission time window and the update time window that does not affect the operation of the intelligent vehicle is selected to update the program, thereby reducing the waiting time for applying the latest program so that the updated program can provide services to the user as soon as possible. Attached Figure Description

[0014] To more clearly illustrate the specific embodiments of the present invention, the accompanying drawings used in the specific embodiments will be briefly described below. In all the drawings, the elements or parts are not necessarily drawn to scale.

[0015] Figure 1 A flowchart of an intelligent vehicle program update method provided in an embodiment of the present invention; Figure 2 This is a system block diagram of an intelligent vehicle program update system provided in an embodiment of the present invention. Detailed Implementation

[0016] The embodiments of the technical solution of the present invention will now be described in detail with reference to the accompanying drawings. These embodiments are merely illustrative of the technical solution of the present invention and are therefore intended to limit the scope of protection of the present invention.

[0017] It should be understood that in this embodiment, the planned trip includes the driving route planned by the user, the driving route includes the path nodes that the intelligent vehicle needs to reach, the planned time to reach the path nodes, and the parking time at the path nodes.

[0018] Example 1 like Figure 1 The flowchart shown illustrates a method for updating a smart car's software, which includes: Step 1: Obtain the smart car's pending updates and planned routes; Step 2: Predict the network status and driving status of the intelligent vehicle at different times in the future based on the planned itinerary; Step 3: Based on the network status and driving status of the intelligent vehicle at different times in the future, as well as the data volume and update duration of the program to be updated, determine the transmission time window and update time window of the program to be updated.

[0019] Specifically, after receiving a program update notification from the system, the intelligent vehicle first identifies the program that needs updating and obtains the user-preset planned route. Then, based on the driving path in the planned route, it obtains the network status prediction results and driving status prediction results along the driving path at different future times. Combined with the predicted time for the intelligent vehicle to arrive at different locations on the driving path, it determines the network status and driving status of the intelligent vehicle at different future times.

[0020] Finally, by considering the network and driving status of the intelligent vehicle at different future times, as well as the size of the update data packets for the program to be updated, the transmission time window can be selected within a future timeframe with the shortest interval between the notification reception and the network conditions. This not only reduces the waiting time for receiving data packets but also reduces the data packet reception time, ensuring timely receipt of data packets for program updates. Simultaneously, based on the required update duration of the program to be updated and the driving status of the intelligent vehicle within a future timeframe, the update time window can be selected within a future timeframe with the shortest interval between the transmission time window and the update time window, without affecting the intelligent vehicle's driving, thus shortening the program update waiting time. In this way, by reducing the waiting time for receiving data packets and the reception time, as well as the program update waiting time, the program to be updated can be completed quickly upon receiving the program update notification, thereby reducing the waiting time for applying the latest program and enabling the updated program to provide services to users as soon as possible.

[0021] In this embodiment, optionally, obtaining the update program of the smart car includes: Real-time acquisition of vehicle status and software update notifications for intelligent vehicles; The priority of each target update program in the program update notification is determined based on the vehicle status, and the target update program with the highest priority is selected as the program to be updated.

[0022] Specifically, intelligent vehicles can receive real-time program update notifications and vehicle status updates via the network, such as the operational status of the battery management system and the stability of the voice interaction system. The program update notifications include multiple applications that can be updated, and the intelligent vehicle can determine the priority of each application based on the vehicle's status. For example, if the battery management system frequently reports errors, it should be updated with the highest priority. If the battery management system is functioning well, but the voice interaction system is malfunctioning, the voice interaction system should be updated with the highest priority, and the battery management system should be updated only after the voice interaction system update is complete.

[0023] In this embodiment, optionally, predicting the network status of the intelligent vehicle at different future times based on the planned trip includes: Step 2-1: Based on the traffic flow data and traffic environment data at different locations of the planned route, predict the traffic flow distribution of the planned route at different future times using a preset traffic flow prediction model; Step 2-2: Combining traffic flow distribution and network coverage data for planned trips at different future times, predict the network status distribution for planned trips at different future times; Steps 2-3: Based on the current driving status and traffic environment of the intelligent vehicle, predict the arrival time of the intelligent vehicle to different locations on the planned route using the trajectory prediction model; Steps 2-4: Match the arrival time of the intelligent vehicle at different locations with the network state distribution of the planned journey at different future times to determine the network state of the intelligent vehicle at different future times.

[0024] Specifically, firstly, current traffic flow data and traffic environment data along the travel route can be obtained from the road management platform. Traffic flow data includes vehicle speed and traffic volume, while traffic environment data includes weather and visibility. Using the obtained traffic flow data and traffic environment data as input, a pre-trained traffic flow prediction model is used to predict traffic flow data at different locations along the travel route at different future times, i.e., the traffic flow distribution for the planned trip at different future times. In this embodiment, the traffic flow prediction model can use a time series model such as ARIMA to predict traffic flow, or an LSTM neural network can be used to construct the traffic flow prediction model.

[0025] It should be understood that predicting traffic flow data using time series models or LSTM neural networks is a conventional technique in this field, and its specific methods and principles will not be elaborated here.

[0026] Then, by measuring the network coverage strength along the travel route, such as signal strength, signal-to-noise ratio, and channel occupancy, and by determining the traffic flow distribution along the travel route at different future times, we can determine the network status of different locations along the travel route at different future times, i.e., the network status distribution of the planned journey at different future times.

[0027] Then, based on the intelligent vehicle's current driving speed, acceleration, and traffic flow and traffic environment data along the current driving path, a pre-trained trajectory prediction model can be used to predict the arrival time and driving status of the intelligent vehicle at different locations along the driving path.

[0028] Finally, the arrival time of the intelligent vehicle at different locations along the driving path can be matched with the network state of the corresponding location at different future times to determine the network state of the intelligent vehicle at different future times.

[0029] In this embodiment, optionally, determining the transmission time window of the program to be updated includes: Based on the network status of intelligent vehicles at different times in the future, select the best time period for the intelligent vehicle's network status. Based on the network status corresponding to the optimal time period and the amount of data of the program to be updated, determine the transmission duration required to transmit the program to be updated; Determine whether the transmission duration is greater than the duration corresponding to the optimal time period; In response to the transmission duration not exceeding the duration corresponding to the optimal time period, the optimal time period is taken as the transmission time window; In response to the transmission duration being longer than the duration corresponding to the optimal time period, the optimal time period is discarded, and a new optimal time period with the best network condition is determined.

[0030] Specifically, firstly, based on the network status of the intelligent vehicle at different future times, an optimal time period with the best network and the shortest time interval from the current moment is initially selected. Network status includes network bandwidth and device distance. Then, based on the network status of the intelligent vehicle during the optimal time period and the data packet size of the program to be updated, the transmission delay, propagation delay, processing delay, and queuing delay of the data packets are calculated, thereby calculating the transmission time required to transmit the data packets. Afterward, the transmission time is compared with the duration of the optimal time period. If the transmission time is less than or equal to the duration of the optimal time period, the optimal time period can be used as the data packet transmission time window. Otherwise, the optimal time period needs to be reselected.

[0031] In this embodiment, optionally, determining the update time window of the program to be updated includes: Determine whether a shutdown is required for the update based on the update requirements of the program to be updated; In response to the requirement of not stopping, the update time window is determined based on the update duration corresponding to the program to be updated, with the end time of the transmission time window as the start time. In response to the need to park, the system can filter out the future parking times of the smart car by analyzing its driving status at different times in the future. Select the parking time period from all parking time periods whose parking duration exceeds the update duration and is closest to the transmission time window as the update time window.

[0032] Specifically, whether or not the vehicle needs to be stopped for an update can be determined based on the type of program being updated. For example, updating the battery management system will disrupt the vehicle's operation because the system will be unavailable during the update process. Therefore, it is best to perform the update while the vehicle is parked. However, for the voice interaction system, pausing its use for an update will only affect the user experience and will not affect the vehicle's normal operation. Therefore, the update can be performed while the vehicle is in normal driving condition.

[0033] If stopping to update the program is not required, the start time can be set to the end time of the transmission time window, the end time can be determined based on the update duration of the program to be updated, and the start and end times can be used as the update time window. In this way, the program update can be performed immediately after the data packet is received.

[0034] If a parking update is required, the parking time periods of the intelligent vehicle can be selected from the subsequent time range of the transmission time window based on the driving status of the intelligent vehicle at different times in the future. The parking duration of each parking time period is then compared with the update duration required for the update program. The parking time period with the shortest time interval between the parking duration and the endpoint time is selected as the update time window to shorten the waiting time for the update program.

[0035] Example 2 Example 2 is largely the same as Example 1, with the main difference being: determining the transmission time window and update time window of the program to be updated, including: Based on the network and driving status of the intelligent vehicle at different future times, as well as the data volume and update duration of the program to be updated, the particle swarm optimization algorithm is used to determine the optimal transmission time window and update time window.

[0036] Specifically, intelligent vehicles can quickly search for the most suitable transmission and update time windows using existing particle swarm optimization algorithms, based on the network conditions along the driving path at different future times. These network conditions include network channel bandwidth, signal-to-noise ratio, and loss factor. The network conditions also include the vehicle's driving status at different future times, the amount of data in the update packet to be updated, and the update time required.

[0037] In this embodiment, optionally, a particle swarm optimization algorithm is used to determine the optimal transmission time window and update time window, including: The objective function is to minimize the total time consumption. The total time consumption includes the interval between the start time and the current time of the transmission time window, the transmission time required to transmit the program to be updated, the interval between the transmission time window and the update time window, and the update time. The specific objective function is as follows: ; in, The interval between the start time of the transmission time window and the current time when the update notification is received is calculated as follows: ; This is the start time of the transmission time window. The current time when the update notification was received; The specific calculation formula for the transmission time required to transmit the program to be updated is as follows: ; The data size of the data packet. As the loss factor, The specific calculation formula for Shannon capacity is as follows: ; For channel bandwidth, This refers to the signal-to-noise ratio.

[0038] The specific calculation formulas for the interval between the transmission time window and the update time window, and the update duration, are as follows: ; To update the start time of the time window, This is the end time of the transmission time window.

[0039] To update the duration, , , These are weights corresponding to the respective durations, which are manually set based on experience.

[0040] Constraints can be set based on time windows, such as the transmission time window needing to be after the current time is received, and the start time of the update time window needing to be after the end time of the transmission time window. Furthermore, constraints can be adjusted based on the type of program to be updated. For example, when the program to be updated belongs to the battery management system, constraints for the parking status update program need to be added, limiting the selection period of the update time window.

[0041] After setting the objective function and constraints, the particle swarm can be initialized, and a time allocation scheme including a teleportation time window and an update time window can be randomly generated. Then, the particle swarm is iteratively optimized, calculating the objective function value for each particle and updating iteratively based on the objective function value until the set convergence condition is met, ultimately obtaining the most suitable teleportation time window and update time window. In this embodiment, the convergence condition can be set as the maximum number of iterations.

[0042] Example 3 like Figure 2 The diagram shown is a system block diagram of an intelligent vehicle program update system, which includes: The acquisition module is configured to acquire the smart car's pending updates and planned routes; The prediction module is configured to predict the network status and driving status of the intelligent vehicle at different times in the future based on the planned route; The push module is configured to determine the transmission time window and update time window of the program to be updated by combining the network status and driving status of the intelligent vehicle at different times in the future, as well as the data volume and update duration of the program to be updated.

[0043] Specifically, the update system includes an acquisition module, a prediction module, and a push module. The acquisition module identifies programs requiring updates through update notifications and retrieves the user's pre-set planned itinerary. The prediction module obtains network and driving status predictions along the planned route at different future times, and combines this with the predicted arrival times of the intelligent vehicle at different locations along the route to determine the intelligent vehicle's network and driving status at different future moments.

[0044] The push module can comprehensively consider the network and driving status of the smart car at different times in the future, as well as the size of the data packet of the program to be updated. Within the future time range, it selects the time window with the shortest interval between the notification and the receiving time and the best network status as the transmission time window, and the time window with the shortest interval between the transmission time window and the smart car's driving time as the update time window, and pushes it to the smart car user so that the user can choose the program update time period.

[0045] This not only reduces the waiting time for receiving data packets but also the data packet reception time, allowing for timely data packet reception and program updates. Simultaneously, it shortens the program update waiting time, enabling rapid updates upon receiving update notifications and reducing the waiting time for the latest application, thus providing services to users as quickly as possible.

[0046] In this embodiment, optionally, the push module includes: The filtering unit is configured to filter the optimal time period for the best network status of the intelligent vehicle based on the network status of the intelligent vehicle at different times in the future. The computing unit is configured to determine the transmission duration required to transmit the program to be updated based on the network status corresponding to the optimal time period and the amount of data of the program to be updated. The determining unit is configured to determine whether the transmission duration is greater than the duration corresponding to the optimal time period; In response to the transmission duration not exceeding the duration corresponding to the optimal time period, the optimal time period is taken as the transmission time window; In response to the transmission duration being longer than the duration corresponding to the optimal time period, the optimal time period is discarded, and a new optimal time period with the best network condition is determined.

[0047] Specifically, the push module includes a filtering unit, a calculation unit, and a determination unit. The filtering unit can initially filter for the optimal time period with the best network and the shortest time interval from the current moment, based on the network status of the intelligent vehicle at different future times. Network status includes network bandwidth and device distance. The calculation unit can calculate the data packet transmission delay, propagation delay, processing delay, and queuing delay based on the network status of the intelligent vehicle during the optimal time period and the data packet size of the program to be updated, and then calculate the transmission time required to transmit the data packet. The determination unit can compare the transmission time with the duration of the optimal time period. If the transmission time is less than or equal to the duration of the optimal time period, the optimal time period can be used as the data packet transmission time window. Otherwise, the optimal time period needs to be re-filtered.

[0048] Example 4 Example 4 is largely the same as Example 3, with the main difference being that the push module includes: The optimization unit is configured to combine the network status and driving status of the intelligent vehicle at different future times, as well as the data volume and update duration of the program to be updated, and use the particle swarm optimization algorithm to determine the optimal transmission time window and update time window.

[0049] Specifically, the push module includes an optimization unit. This unit can determine the optimal transmission and update time windows based on the network conditions along the driving path at different future times. These network conditions include channel bandwidth, signal-to-noise ratio, and loss factor. Additionally, it considers the intelligent vehicle's driving status at different future times, the data volume of the program data packet to be updated, and the update time required. With the goal of minimizing the time interval between update completion and update reception, the unit employs existing particle swarm optimization algorithms to quickly search for the most suitable transmission and update time windows.

[0050] It should be understood that the specific method of the particle swarm optimization algorithm used in the optimization unit is the same as the method steps described in Example 2, and will not be repeated here.

[0051] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and specification of the present invention.

Claims

1. A method for updating software in an intelligent vehicle, characterized in that, include: Obtain the pending updates and planned routes for smart cars; Predict the network and driving status of intelligent vehicles at different times in the future based on the planned itinerary; Based on the network status and driving status of the intelligent vehicle at different times in the future, as well as the data volume and update duration of the program to be updated, the transmission time window and update time window of the program to be updated are determined.

2. The intelligent vehicle program update method according to claim 1, characterized in that, Obtain the update software for your smart car, including: Real-time acquisition of vehicle status and software update notifications for intelligent vehicles; The priority of each target update program in the program update notification is determined based on the vehicle status, and the target update program with the highest priority is selected as the program to be updated.

3. The intelligent vehicle program update method according to claim 1, characterized in that, Based on the planned itinerary, predict the network status of intelligent vehicles at different times in the future, including: Based on traffic flow data and traffic environment data at different locations along the planned route, a pre-set traffic flow prediction model is used to predict the traffic flow distribution of the planned route at different future times. By combining traffic flow distribution and network coverage data for planned trips at different future times, the network status distribution of planned trips at different future times can be predicted. Based on the current driving status and traffic environment of the intelligent vehicle, the arrival time of the intelligent vehicle to different locations in the planned route is predicted by the trajectory prediction model. By matching the arrival time of intelligent vehicles at different locations with the network state distribution of planned journeys at different future times, the network state of intelligent vehicles at different future times can be determined.

4. The intelligent vehicle program update method according to claim 1, characterized in that, Determining the transmission time window of the program to be updated includes: Based on the network status of intelligent vehicles at different times in the future, select the best time period for the intelligent vehicle's network status. The required transmission time for transmitting the program to be updated is determined based on the network status corresponding to the optimal time period and the amount of data in the program to be updated. Determine whether the transmission duration is greater than the duration corresponding to the optimal time period; In response to the transmission duration not exceeding the duration corresponding to the optimal time period, the optimal time period is taken as the transmission time window; In response to the transmission duration being longer than the duration corresponding to the optimal time period, the optimal time period is discarded, and a new optimal time period with the best network condition is determined.

5. The intelligent vehicle program update method according to claim 1, characterized in that, Determining the update time window for the program to be updated includes: Determine whether a shutdown is required for the update based on the update requirements of the program to be updated; In response to the requirement of not stopping, the update time window is determined based on the update duration corresponding to the program to be updated, with the end time of the transmission time window as the start time. In response to the need to park, the system can filter out the future parking times of the smart car by analyzing its driving status at different times in the future. Select the parking time period from all parking time periods whose parking duration exceeds the update duration and is closest to the transmission time window as the update time window.

6. The intelligent vehicle program update method according to claim 1, characterized in that, Determining the transmission time window and update time window of the program to be updated includes: Based on the network and driving status of the intelligent vehicle at different future times, as well as the data volume and update duration of the program to be updated, the particle swarm optimization algorithm is used to determine the optimal transmission time window and update time window.

7. The intelligent vehicle program update method according to claim 6, characterized in that, The optimal transmission time window and update time window are determined using the particle swarm optimization algorithm, including: The objective function is to minimize the total time, which includes the interval between the start time of the transmission time window and the current time, the transmission time required to transmit the program to be updated, the interval between the transmission time window and the update time window, and the update time.

8. A smart car program update system, characterized in that, include: The acquisition module is configured to acquire the smart car's pending updates and planned routes; The prediction module is configured to predict the network status and driving status of the intelligent vehicle at different times in the future based on the planned route; The push module is configured to determine the transmission time window and update time window of the program to be updated by combining the network status and driving status of the intelligent vehicle at different times in the future, as well as the data volume and update duration of the program to be updated.

9. The intelligent vehicle program update system according to claim 8, characterized in that, The push module includes: The filtering unit is configured to filter the optimal time period when the network status of the intelligent vehicle is best at different times in the future. The computing unit is configured to determine the transmission duration required to transmit the program to be updated based on the network status corresponding to the optimal time period and the amount of data of the program to be updated. The determining unit is configured to determine whether the transmission duration is greater than the duration corresponding to the optimal time period; In response to the transmission duration not exceeding the duration corresponding to the optimal time period, the optimal time period is taken as the transmission time window; In response to the transmission duration being longer than the duration corresponding to the optimal time period, the optimal time period is discarded, and a new optimal time period with the best network condition is determined.

10. The intelligent vehicle program update system according to claim 8, characterized in that, The push module includes: The optimization unit is configured to combine the network status and driving status of the intelligent vehicle at different future times, as well as the data volume and update duration of the program to be updated, and use the particle swarm optimization algorithm to determine the optimal transmission time window and update time window.

Images