WO2022228024A1 - 一种车辆驾驶策略推荐方法及装置 - Google Patents

一种车辆驾驶策略推荐方法及装置 Download PDF

Info

Publication number
WO2022228024A1
WO2022228024A1 PCT/CN2022/084442 CN2022084442W WO2022228024A1 WO 2022228024 A1 WO2022228024 A1 WO 2022228024A1 CN 2022084442 W CN2022084442 W CN 2022084442W WO 2022228024 A1 WO2022228024 A1 WO 2022228024A1
Authority
WO
WIPO (PCT)
Prior art keywords
driving
recommended
strategy
driving strategy
strategies
Prior art date
Application number
PCT/CN2022/084442
Other languages
English (en)
French (fr)
Inventor
徐镜进
祁琪
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to EP22794496.4A priority Critical patent/EP4328765A1/en
Publication of WO2022228024A1 publication Critical patent/WO2022228024A1/zh
Priority to US18/494,519 priority patent/US20240070213A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/451—Execution arrangements for user interfaces
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/23—Updating
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/23—Updating
    • G06F16/2379—Updates performed during online database operations; commit processing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9538—Presentation of query results
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F8/00—Arrangements for software engineering
    • G06F8/60—Software deployment
    • G06F8/65—Updates

Definitions

  • the present application relates to the field of smart vehicles, and in particular, to a method and device for recommending vehicle driving strategies based on driving scenarios.
  • the traditional car is driven by the driver, but with the advancement of technology, the technology of artificial intelligence (AI) is also gradually improving.
  • AI artificial intelligence
  • self-driving cars are proposed based on AI, and self-driving cars are also known as the future car form.
  • current cars are still unable to achieve fully autonomous driving in any scenario, and can only achieve autonomous driving in some specific scenarios.
  • autonomous driving strategy can also be considered as a new feature of self-driving cars. For example, automatic parking strategy for parking scenarios, low-speed cruise strategy for traffic jam scenarios, etc.
  • the in-vehicle assisted driving system is a system mounted on a vehicle, and is usually updated by an automobile manufacturer or an in-vehicle system contractor through the cloud, for example, an over-the-air (OTA) update is used.
  • OTA over-the-air
  • new automatic driving strategies also called new functions
  • the automatic driving strategy library is also updated accordingly.
  • a text update description is currently provided for users to check the detailed update content.
  • the embodiment of the present application provides a method for recommending a driving strategy of a vehicle, which determines possible driving scenarios of the current vehicle by collecting external environment data and/or internal environment data of the vehicle. In order to match from the strategy library to be recommended according to the driving scene, determine the driving strategy to be recommended corresponding to the driving scene and recommend it to the user. By actively recommending the driving strategy to be recommended to the user, it can be ensured that after the driving strategy is updated, the user can know the new driving strategy and fully experience the new driving strategy. Avoid the situation where the user's perception of the text update content is low, resulting in the user's unawareness of the newly added driving strategy.
  • a method for recommending a vehicle driving strategy can be applied to a terminal device, and the method can include: collecting at least one piece of environmental information.
  • the environment information may include external environment data and/or internal environment data.
  • at least one driving scene is determined according to the collected at least one environment information.
  • at least one driving scene is matched with the strategy library to be recommended.
  • the to-be-recommended strategy library may include a correspondence between driving scenarios and to-be-recommended driving strategies.
  • the at least one driving strategy to be recommended may be displayed. So that the terminal device can execute one or more displayed driving strategies to be recommended according to the user instruction input by the user.
  • the present application determines the corresponding driving scene by collecting environmental information, and then matches the corresponding strategy to be recommended from the strategy library to be recommended in combination with the driving scene and displays it to the user, which can ensure that after the driving strategy is updated, the user can know the new driving strategy. Avoid the situation where the user's perception of the text update content is low, resulting in the user's unawareness of the newly added driving strategy.
  • the strategy to be recommended is executed through user instructions, the user can fully experience the newly added driving strategy.
  • the method may further include: acquiring an update data package.
  • the update data package may include a driving strategy to be recommended and a driving scenario corresponding to the driving strategy to be recommended. Then, the to-be-recommended driving strategy and the driving scene corresponding to the to-be-recommended driving strategy in the update data package are added to the to-be-recommended strategy library.
  • the driving strategy to be recommended may include priority information.
  • Displaying the at least one to-be-recommended driving strategy may include: displaying at least one to-be-recommended driving strategy with the highest priority according to the priority information.
  • the driving scenarios may include single driving scenarios and composite driving scenarios.
  • the priority corresponding to the driving strategy to be recommended in the composite driving scenario is higher than the priority of the driving strategy to be recommended corresponding to the single driving scenario.
  • executing one or more displayed driving strategies to be recommended according to user instructions may include: if there is an execution conflict among the plurality of driving strategies to be recommended, executing one of the plurality of driving strategies to be recommended according to user instructions Some driving strategies to be recommended. Among them, there is no execution conflict in the executed part of the driving strategies to be recommended.
  • the method may further include: removing the executed at least one driving strategy to be recommended from the strategy library to be recommended. Alternatively, add one to the execution times of the at least one to-be-recommended driving strategy executed. The initial value of the execution times of each driving strategy to be recommended may be set to zero. Then, the to-be-recommended driving strategies whose execution times are greater than or equal to the recommended times threshold are removed from the to-be-recommended strategy library.
  • the driving strategies executed by the user from the strategy library to be recommended it can be ensured that most of the recommended driving strategies are driving strategies that the user is not familiar with or even does not know, so that the user can fully experience the newly added driving strategies.
  • a vehicle driving strategy recommendation device is provided.
  • the device is a terminal device.
  • the device may include: a sensor for collecting at least one piece of environmental information, where the environmental information includes external environment data and/or internal environment data; is coupled to the memory, and reads and executes the instructions stored in the memory; when the processor runs, executes the instructions, so that the processor is used to determine at least one driving scene according to at least one environmental information; associate the at least one driving scene with the strategy to be recommended
  • the to-be-recommended strategy library includes the corresponding relationship between the driving scene and the to-be-recommended driving strategy; when at least one to-be-recommended driving strategy is matched, the control display will display the at least one to-be-recommended driving strategy for execution according to user instructions At least one driving strategy to be recommended.
  • the present application determines the corresponding driving scene by collecting environmental information, and then matches the corresponding strategy to be recommended from the strategy library to be recommended in combination with the driving scene and displays it to the user, so as to ensure that after the driving strategy is updated, the user can know the new driving strategy. Avoid the situation where the user's perception of the text update content is low, resulting in the user's unawareness of the newly added driving strategy.
  • the strategy to be recommended is executed through user instructions, the user can fully experience the newly added driving strategy.
  • the apparatus further includes: a receiver for acquiring an update data package, where the update data package includes the driving strategy to be recommended and the driving scene corresponding to the driving strategy to be recommended; the processor is further configured to: The recommended driving strategy and the driving scenarios corresponding to the driving strategy to be recommended are added to the strategy library to be recommended.
  • the terminal device can determine the driving scene and the driving strategy to be recommended according to the environmental information, so as to ensure that the new driving strategy after the update can be known to the user Even fully experience, to avoid users' low awareness of the text update content, resulting in the new driving strategy users do not know.
  • the driving strategy to be recommended includes priority information; the processor is further configured to: control the display to display at least one driving strategy to be recommended with the highest priority according to the priority information.
  • the driving scenarios include a single driving scenario and a composite driving scenario, and the priority of the composite driving scenario corresponding to the driving strategy to be recommended is higher than the priority of the single driving scenario corresponding to the driving strategy to be recommended.
  • the receiver is further configured to: receive a user instruction; the processor is further configured to: if there is an execution conflict among the multiple driving strategies to be recommended, execute part of the multiple driving strategies to be recommended according to the user instruction A recommended driving strategy, in which there is no execution conflict for the part of the to-be-recommended driving strategy to be executed.
  • the processor is further configured to: remove the executed at least one to-be-recommended driving strategy from the to-be-recommended strategy library; or, add one to the execution times of the executed at least one to-be-recommended driving strategy, wherein , the initial value of the execution times of each to-be-recommended driving strategy is zero; the to-be-recommended driving strategies whose execution times are greater than or equal to the recommended times threshold are removed from the to-be-recommended strategy library.
  • the processor is further configured to: remove the executed at least one to-be-recommended driving strategy from the to-be-recommended strategy library; or, add one to the execution times of the executed at least one to-be-recommended driving strategy, wherein , the initial value of the execution times of each to-be-recommended driving strategy is zero; the to-be-recommended driving strategies whose execution times are greater than or equal to the recommended times threshold are removed from the to-be-recommended strategy library.
  • a computer-readable storage medium where instructions are stored in the computer-readable storage medium, and when the instructions are executed on a terminal, the terminal is made to execute any one of the methods in the first aspect.
  • a computer device containing instructions, which, when run on a terminal, cause the terminal to perform any one of the methods in the first aspect.
  • a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of any one of the first aspects.
  • the present application discloses a method and device for recommending a driving strategy for a vehicle.
  • the possible driving scenarios of the current vehicle are determined by collecting the environmental information of the vehicle, and then the corresponding driving strategy to be recommended is determined based on the driving scenario and recommended to the user. It is ensured that after the driving strategy is updated, the user can know the newly added driving strategy, so as to avoid the situation that the user is unaware of the newly added driving strategy due to the low perception of the user to the content of the text update. At the same time, executing the driving strategy to be recommended enables the user to fully experience the newly added driving strategy.
  • FIG. 1 is a schematic diagram of an application scenario provided by an embodiment of the present application.
  • FIG. 2 is a schematic diagram of the architecture of a vehicle driving strategy recommendation system provided by an embodiment of the present application
  • FIG. 3 is a flowchart of a method for recommending a vehicle driving strategy according to an embodiment of the present application
  • FIG. 4 is a schematic diagram of an interface for displaying a driving strategy to be recommended according to an embodiment of the present application
  • 5A is a schematic diagram of another interface for displaying a driving strategy to be recommended according to an embodiment of the present application.
  • 5B is a schematic diagram of another interface for displaying a driving strategy to be recommended according to an embodiment of the present application.
  • 5C is a schematic diagram of yet another interface for displaying a driving strategy to be recommended according to an embodiment of the present application.
  • 5D is a schematic diagram of another interface for displaying a driving strategy to be recommended according to an embodiment of the present application.
  • FIG. 6 is a flowchart of another vehicle driving strategy recommendation method provided by an embodiment of the present application.
  • FIG. 7 is a schematic diagram of a vehicle driving strategy update provided by an embodiment of the present application.
  • FIG. 8 is a schematic structural diagram of a terminal device according to an embodiment of the present application.
  • Example 9 is a schematic diagram of an interface for displaying a driving strategy to be recommended in Example 1 provided by an embodiment of the present application.
  • FIG. 10 is a schematic diagram of a driving strategy for removing to-be-recommended provided by an embodiment of the present application
  • Example 11 is a schematic diagram of an interface displaying a driving strategy to be recommended in Example 2 provided by the embodiment of the present application;
  • FIG. 12 is a schematic diagram of a vehicle driving strategy recommendation device provided by an embodiment of the present application.
  • This application is mainly applied to vehicle driving scenarios.
  • the user may face different situations when driving a vehicle. For example, when driving, he may encounter some road sections where the speed is limited, or he may need to overtake, etc. , for another example, the user may prepare to park, or park on the side of the road to take a short rest.
  • the vehicle can provide corresponding driving strategies accordingly.
  • the user does not fully understand the driving strategies in the vehicle. For example, the user has just purchased the vehicle recently, and obviously does not understand all the driving strategies in the vehicle. Or when a new driving strategy is updated on the vehicle, the user is also in a state of ignorance or ignorance of the newly added driving strategy after the update.
  • the update content can be "Version XXXX.X, 1. Developer feedback optimization: add intelligent customer service, appeal, problem feedback and other functions, feedback entry: icon in the upper right corner; floating button in the lower right corner of the page; 2. Homepage optimization and revision, Added 'special recommendation', 'demo project', etc., making it more convenient to find services; 3. Report optimization: download and install reports, support viewing data according to the application version dimension; 4. Crash service: support XX system application crash analysis; 5. Remote Configuration service enhancement: support XX system application; 6. A/B test service enhancement: support XX system application; 7.
  • New XXX driving strategy usually the update description will describe the new content of this update through the above text. However, for users, it is often turned off. Even if I read the updated description of the text at the time. Since it doesn't really use the various new functions, users still forget to update the content after a period of time, or can't remember the newly added functions when the time is right. For example, an update added an Auto Park driving strategy, which can be activated via a specific button on the steering wheel. However, users may not remember the newly added automatic parking driving strategy when they actually park, and often use the previous way to park. For the newly added automatic parking driving strategy of the vehicle, it is still in a state of "don't know - don't use”.
  • the present application provides a method for recommending a driving strategy for a vehicle.
  • the terminal device determines the driving scene in which the current vehicle may be located by collecting the environmental information of the vehicle, and then determines the corresponding driving strategy to be recommended according to the driving scene.
  • the terminal device executes one or more displayed driving strategies to be recommended according to the user's instruction.
  • the above method ensures that after the driving strategy is updated, the user can know the newly added driving strategy, so as to avoid the situation where the user is unaware of the newly added driving strategy due to low awareness of the text update content.
  • executing the driving strategy to be recommended enables the user to fully experience the newly added driving strategy.
  • FIG. 2 is a schematic diagram of the architecture of a vehicle driving strategy recommendation system provided by an embodiment of the present application.
  • a sensor 001 and a terminal device 002 may be included in the system.
  • the sensor 001 may be various sensors mounted on a terminal device or a vehicle, and is used to collect environmental information, so that the terminal device can determine a driving scene according to the collected environmental information.
  • sensors may include image sensors, ultrasonic sensors, lidars, millimeter wave radars, pressure sensors, gyroscope sensors, barometric pressure sensors, magnetic sensors, acceleration sensors, distance sensors, temperature sensors, ambient light sensors, and the like. It can be understood that the sensor 001 may include any possible sensor, which is not limited in this application.
  • the terminal device 002 may be, for example, a smart car or a vehicle-mounted smart terminal or the like.
  • the terminal device 002 is equipped with an in-vehicle auxiliary driving system, wherein the in-vehicle auxiliary driving system may include a vehicle driving strategy library, and the vehicle driving strategy library includes at least one driving strategy. It can be understood that each driving strategy can be applied to different driving scenarios to control the vehicle to complete the corresponding operation.
  • the terminal device determines possible driving scenarios according to the environmental information acquired by the sensor 001 . Combined with the driving strategies in the vehicle driving strategy library, the driving strategies applicable to the current driving scenario are determined and recommended to the user. In one example, driving strategies may be recommended to the user through a display screen and/or a microphone.
  • the sensor 001 in FIG. 2 can be deployed on the terminal device 002, of course, some sensors 001 can also be deployed in a specific location and connected to the terminal device 002 in a wired or wireless manner.
  • the terminal device 002 is a smart car
  • the sensor 001 may be deployed on the smart car to collect environmental information inside and/or outside the car.
  • the terminal device may also be an in-vehicle intelligent terminal connected to the vehicle through a wired or wireless manner, such as including but not limited to mobile phones, smart TVs, smart speakers, wearable devices, tablet computers, desktop computers, handheld computers, and notebook computers.
  • ultra-mobile personal computer UMPC
  • netbook personal digital assistant
  • PDA personal digital assistant
  • laptop computer laptop
  • mobile computer augmented reality (AR) device
  • virtual reality virtual reality, VR
  • artificial intelligence artificial intelligence, AI
  • any terminal equipment or portable terminal equipment such as in-vehicle equipment.
  • FIG. 3 is a flowchart of a method for recommending a vehicle driving strategy provided by an embodiment of the present application.
  • the present application provides a vehicle driving strategy recommendation method.
  • the method can be applied to the system shown in FIG. 2 , and in some examples, can be applied to the terminal device 002 in FIG. 2 .
  • the method may include the following steps:
  • S301 Collect at least one piece of environmental information.
  • the terminal device 002 can collect at least one piece of environmental information through the sensor 001 .
  • the sensor may be any of the sensors mentioned in FIG. 2 above, and may collect environmental information of the terminal device 002 .
  • the environment information may include external environment data and/or internal environment data.
  • the external environment data may be data representing the external environment of the terminal device 002, such as vehicle interior temperature, ambient temperature, vehicle speed, vehicle flow, road signs, environment signs, vehicle positions, etc., some of the data may be collected and passed through
  • the determination by the processor after corresponding processing, such as road signs, environmental signs, etc., may be determined after the image is collected by the camera and after image recognition.
  • the internal environment data may be status data, parameter change data, operation logs, etc. representing the in-vehicle system running on the terminal device 002 .
  • the operation records generated by the user's hardware operation may be included.
  • a log is generated after the user performs a reversing operation, and the log is used to record the user's reversing operation at a certain time.
  • the terminal device 002 can perceive the external environment scene of the terminal device 002 through the external environment data, and/or can perceive the internal state scene of the terminal device 002 through the internal environment data.
  • S302 Determine at least one driving scene according to at least one piece of environmental information.
  • the corresponding driving scene can be determined according to the collected environmental information. For example, according to the external environment data and/or the internal environment data, and according to a preset rule, a driving scene that may correspond to the terminal device 002 is determined.
  • the driving scenarios may include external scenarios, terminal internal scenarios and/or composite driving scenarios.
  • the terminal device 002 may determine the external scene of the terminal device 002 according to the external environment data. For example, if the external environment data is the location information of the terminal device 002, it can be determined that the current driving scene of the terminal device 002 can be a location scene; or the external environment data is road sign information, then the current terminal device can be determined according to the road sign information.
  • the driving scene of 002 can be a road scene; or, if the external environment data is the temperature information of the terminal device 002, it can be determined according to the temperature information that the current driving scene of the terminal device 002 can be a temperature scene; or, the external environment data is traffic speed information, it can be determined according to the traffic speed information that the current driving scene of the terminal device 002 may be a driving scene or the like. It can be understood that the external environment data can also be any other possible data, and the external scene corresponding to the terminal device 002 is determined according to the external environment data. Of course, in some examples, comprehensive analysis can also be performed in combination with a plurality of external environment data to determine the external scene of the terminal device 002.
  • the driving scene of the terminal device 002 can be driving in combination with road sign information and location information. Scenes. Taking the road sign information as the parking space sign and the location information as the terminal device 002 in a parking lot as an example, it can be determined that the terminal device 002 may be located near the parking space.
  • some external environmental data can be raw data collected by sensors, such as location information, temperature information, etc.; other external environmental data can be obtained by analyzing the raw data collected by sensors, for example, the sensor is a camera, and the collected data can be image information, and perform image recognition on the image information, for example, speed limit signs, road signs, etc. can be recognized. So that the terminal device 002 determines the corresponding external scene according to the external environment data.
  • the terminal device 002 may also determine the terminal internal scene of the terminal device 002 according to the internal environment data. For example, it is assumed that the internal environment data records that the user operates the vehicle to perform a reversing operation, so the terminal device 002 can determine that the current driving scene of the terminal device 002 can be a reversing scene. For another example, assuming that the internal environment data records that the user steps on the accelerator to accelerate the vehicle, the terminal device 002 may determine that the current driving scene of the terminal device 002 may be an acceleration scene. Obviously, a comprehensive analysis can also be carried out in combination with multiple internal environment data to determine the terminal internal scene of the terminal device 002.
  • the driving scenario that can be comprehensively determined by the terminal device 002 may be an accelerated overtaking scenario.
  • the terminal device 002 may also combine the external environment data and the internal environment data to jointly determine the composite driving scenario of the driving scenario of the terminal device 002 .
  • a single driving scene represents a driving scene determined by a certain environmental information
  • a compound driving scene may represent a driving scene determined by a plurality of environmental information.
  • the analysis can be performed in combination with multiple external environment data and internal environment data, wherein the external environment data includes road sign information for parking space signs and location information for parking lots, and the internal environment data includes the reversing operation performed by the vehicle, then the terminal device 002 can determine that the driving scene can be a driving scene of entering a parking space from a parking lot.
  • the identification when determining the driving scene, may be performed according to a pre-stored correspondence table between the environment information and the driving scene. For example, as shown in Table 1.
  • Table 1 only provides some possible examples, and of course, it may also include the correspondence between more environmental information and driving scenarios.
  • the specific environmental information content and the corresponding driving scene can be arbitrarily adjusted or modified according to the actual situation, which is not limited in this application.
  • the corresponding relationship between a single driving scene and a composite driving scene can be preset.
  • the simultaneous appearance of two single driving scenes of "to be parked” and “reversing” can correspond to the "parking” Compound driving scenarios.
  • the compound driving scenario of "parking in place” can be directly determined.
  • three driving scenarios of "to be parked", “reversing” and “parking in place” can be determined at the same time.
  • the above process can determine at least one driving scene according to at least one piece of environmental information.
  • the terminal device 002 may perform matching in combination with the preset strategy library to be recommended to determine whether there is a driving strategy to be recommended corresponding to the driving scenario.
  • the to-be-recommended strategy library may include: a correspondence between driving scenarios and to-be-recommended driving strategies.
  • the to-be-recommended strategy library is pre-configured, and the to-be-recommended driving strategies included in the to-be-recommended strategy library are driving strategies that have never been used by the user, or driving strategies whose execution times are less than the recommended times threshold. It can be seen that the driving strategies in the strategy library to be recommended are all driving strategies that the user is not familiar with or understands.
  • a mapping table for representing the correspondence between driving scenarios and driving strategies to be recommended may be set in the strategy library to be recommended. So that the terminal device 002 can match the corresponding driving strategy to be recommended in the mapping table according to the driving scenario determined in S302. For example, the corresponding relationship between the driving scene and the driving strategy to be recommended can be shown in Table 2.
  • the driving strategy to be recommended corresponding to at least one driving scenario determined in S302 is matched through the corresponding relationship between the driving scenarios shown in Table 2 and the driving strategy to be recommended.
  • the to-be-recommended driving strategy may be "not currently available", indicating that there is currently no suitable to-be-recommended driving strategy for the current driving scenario.
  • the same driving scenario obviously does not correspond to multiple different driving strategies to be recommended.
  • Table 2 only provides some possible examples, and of course, it may also include the correspondence between more driving scenarios and driving strategies to be recommended.
  • the specific driving scene content and the corresponding driving strategy to be recommended can be arbitrarily adjusted or modified according to the actual situation, which is not limited in this application.
  • each to-be-recommended driving strategy in the to-be-recommended strategy library may correspond to a two-category neural network.
  • the environmental information collected in S301 is parameterized and input into the two-category neural network corresponding to each driving strategy to be recommended as an input layer.
  • For each two-category neural network it is determined according to the result of the output layer whether the activation condition of the driving strategy to be recommended corresponding to the neural network is met.
  • the collected environmental information is parameterized and input into the two-category neural network corresponding to the driving strategy to be recommended in A, and the output results are 65% "satisfied" and 35% "unsatisfied”.
  • the activation condition of the driving strategy to be recommended If it is set that satisfying the proportion of 60% is the activation condition of the strategy to be recommended, it can be determined that the activation condition of the driving strategy to be recommended is met. Alternatively, if the output result is "satisfied", and the output "satisfied" is set as the activation condition of the strategy to be recommended, it can also be directly determined that the activation condition of the driving strategy to be recommended is met.
  • the user may be notified of the determined at least one driving strategy to be recommended through the terminal device 002 .
  • it can be displayed through a display in the terminal device 002 , or a voice broadcast can be performed through a speaker in the terminal device 002 .
  • the driving strategy to be recommended and an option of whether to implement it may be displayed, so that the user can make a determination.
  • at least one driving strategy to be recommended it means that there is a driving strategy that the user is not familiar with and does not understand. For example, a driving strategy that the user has never used, or a driving strategy whose execution times are less than the recommended times threshold. Therefore, the determined driving strategy to be recommended can be recommended to the user, so that the user can choose whether to execute it.
  • priority information may be included in the driving strategy to be recommended.
  • display or voice broadcast may be performed according to the matched priority information of the to-be-recommended driving strategy.
  • the driving strategy to be recommended with the highest priority can be displayed according to the priority information; or the priority information can be sorted in descending order and displayed in the form of a list, or displayed in sequence.
  • the driving strategy to be recommended with the highest priority can be broadcast by voice according to the priority information; or according to the priority information in descending order of voice broadcast. It can be understood that, if there are multiple driving strategies to be recommended with the highest priority, the multiple driving strategies to be recommended with the highest priority can also be displayed or broadcasted by voice at the same time.
  • FIG. 4 shows a schematic diagram of an interface for displaying a driving strategy to be recommended. It can be seen that the interface is displayed by recommending a driving strategy to be recommended as an example.
  • the interface includes the content of the to-be-recommended driving strategy recommended to the user, and provides the user with options for selection. This example is applicable to the case where only one to-be-recommended driving strategy is matched, or only the highest-priority to-be-recommended driving strategy is recommended according to the priority information.
  • FIG. 5A shows another schematic diagram of an interface for displaying driving strategies to be recommended. For example, when a driving strategy to be recommended is recommended, it can be displayed on the display in a preset order.
  • the preset order is displayed in descending order, for example, according to the priority information of the driving strategy to be recommended. It can also be seen from FIG. 5A that, for each displayed driving strategy to be recommended, there may be an option corresponding to it for the user to select. It can be understood that, if the driving strategies to be recommended cannot be all displayed on one page, they can be displayed in multiple pages. So that users can switch the screen by sliding the screen or through physical buttons, voice, etc., and select the displayed driving strategy to be recommended.
  • priority information is included in the driving strategy to be recommended, it may be set that the priority of the driving strategy to be recommended in the composite driving scenario is higher than the priority of the driving strategy to be recommended in the single driving scenario.
  • the reason is that it can be considered that the composite driving scene may be closer to the real driving scene than the single driving scene.
  • matching the driving strategy to be recommended you can first match the composite driving scenario to the recommended driving strategy, and then match the single driving scenario to the recommended driving strategy. In one example, the matching can also be stopped when a compound driving scenario is matched to a driving strategy to be recommended.
  • different driving scenarios may correspond to the same driving strategy to be recommended. Therefore, during display or voice broadcast, the same driving strategies to be recommended can be combined and displayed only once, or only voice broadcast once.
  • the terminal device 002 may receive user instructions input by the user.
  • the user instruction is used to indicate whether the to-be-recommended driving strategy displayed to the user is executed, or to indicate whether the to-be-recommended driving strategy broadcasted to the user is executed.
  • the user's instruction may be determined by receiving the user's operation on the display screen or by collecting specific voice information. For example, the user detects certain keyword information spoken by the user by touching a corresponding option on the display screen, or by touching a physical button connected on the terminal device 002, or by using voice recognition. Among them, the keyword information such as “execute”, “confirm execution”, “ok”, “do not use”, etc. may be used as keywords indicating the user's intention. Of course, if multiple driving strategies to be recommended are displayed or voice broadcast in S304, the keyword information can also be, for example, "start XX driving mode" or "XX driving mode” to directly represent a specific driving strategy. Of course, the specific keyword information can be arbitrarily set according to the actual situation, which is not limited in this application.
  • the user instruction received in S305 for executing the to-be-recommended driving strategy must be Indicates that there are no mutually-executive driving strategies to be recommended that conflict with each other.
  • FIG. 5A when there is an execution conflict between the A driving mode and the C driving mode, after the user chooses to execute the A driving mode, the corresponding option of the corresponding C driving mode cannot be selected by the user.
  • the option corresponding to the C driving mode is grayed out. It will be appreciated that grayed out options represent options that are not selectable by the user.
  • FIG. 5A shows an execution conflict between the A driving mode and the C driving mode
  • the corresponding options of the C driving mode are not displayed, or the C driving mode may not be displayed as shown in FIG. 5D .
  • the user may be prompted by a text pop-up window and/or a voice broadcast, for example, prompting "A driving mode and C driving mode have execution conflicts, choose A to drive. Mode C will not be available for selection" or other equivalent expressions. So that the user knows that there is an execution conflict between the A driving mode and the C driving mode. It can be understood that, it can also be implemented in any other equivalent manner, which is not limited in this application.
  • the driving modes that are displayed normally and can be selected by the user it means that the driving modes are compatible, and there is no execution conflict.
  • a certain to-be-recommended driving strategy forms an overlay with other to-be-recommended driving strategies, it may be considered that there is an execution conflict between such to-be-recommended driving strategies.
  • the terminal device 002 determines to execute one or more displayed or voice recommended driving strategies to be recommended according to the user instruction received in S305. Of course, in some examples, it may also be determined according to the user instruction received in S305 that one or more displayed or voice recommended driving strategies selected by the user to be recommended are not to be executed.
  • the corresponding driving strategy to be recommended is executed according to the corresponding user instruction. Obviously, there is no execution conflict between the executed one or more driving strategies to be recommended.
  • the terminal device 002 may remove the corresponding to-be-recommended driving strategy from the to-be-recommended strategy library after determining to execute at least one to-be-recommended driving strategy.
  • the executed at least one driving strategy to be recommended may be removed from the strategy library to be recommended immediately after the execution is completed. It can be understood that, after the driving strategies to be recommended are removed in this example, the driving strategies to be recommended in the strategy database to be recommended are all driving strategies that have never been used (or executed) by the user.
  • the number of times of execution of each driving strategy to be recommended may also be set, for example, the initial value may be set to zero, indicating that the driving strategy to be recommended is executed zero times. After each execution of the to-be-recommended driving strategy, the number of executions of the correspondingly executed to-be-recommended driving strategy may be increased by one. Then compare the execution times of each driving strategy to be recommended with the recommended times threshold.
  • the recommended times threshold may be preset, such as 3 times, 5 times, and so on. Of course, a separate recommendation times threshold may also be set for each driving strategy to be recommended. The specific value of the recommended times threshold can be arbitrarily set according to the actual situation, which is not limited in this application.
  • the to-be-recommended driving strategies whose execution times are greater than or equal to the recommended times threshold are removed from the to-be-recommended strategy library.
  • the driving strategy to be recommended is recommended to the user several times, so that the user can be familiar with the corresponding driving strategy through repeated use. It avoids the situation where some driving strategies are only recommended once, and users are still unfamiliar with the corresponding driving strategies due to infrequent use.
  • the present application can also record the user data generated when the user executes at least one driving strategy to be recommended, and after the implementation of the recommended driving strategy is completed, send all or part of the generated user data to the cloud server for production Manufacturers or in-vehicle system contractors can optimize driving strategies and upgrade technologies.
  • FIG. 6 is a flowchart of another vehicle driving strategy recommendation method provided by an embodiment of the present application.
  • the to-be-recommended policy library may be updated by receiving an update data package. Therefore, the method shown in FIG. 3 may further include the following steps:
  • the terminal device 002 can receive the update data package delivered by the cloud platform or the server.
  • the update data package may include: a driving strategy to be recommended and a driving scenario corresponding to the driving strategy to be recommended.
  • the terminal device 002 can be updated by way of over-the-air (OTA).
  • OTA over-the-air
  • the update data package may further include function guidance or description corresponding to the driving strategy to be recommended, for providing guidance or description of the driving strategy to be recommended.
  • the driving strategy to be recommended may be a text description, a driving strategy guidance process, and the like.
  • the terminal device 002 parses the update data package obtained in S601, obtains the driving strategy to be recommended and the driving scene corresponding to the driving strategy to be recommended, and adds the driving strategy to be recommended and the driving scene corresponding to the driving strategy to be recommended to the driving strategy to be recommended.
  • Recommended strategy library obtained in S601, obtains the driving strategy to be recommended and the driving scene corresponding to the driving strategy to be recommended, and adds the driving strategy to be recommended and the driving scene corresponding to the driving strategy to be recommended to the driving strategy to be recommended.
  • the mapping table may also be a mapping table combining Table 1 and Table 2, as shown in Table 3, for example.
  • the update data package may further include environmental information for determining the driving scene.
  • the environment information in the update data package is different from the environment information of the corresponding driving scene in Table 3, the environment information in Table 3 can be updated, that is, updated to the environment information of the corresponding driving scene in the update data package.
  • the driving strategy to be recommended in the update data package, the driving scenario corresponding to the driving strategy to be recommended, and the environmental information of the driving scenario can be directly added to Table 3 when updating. .
  • the execution times may be reset to zero. If the updated to-be-recommended driving strategy is not in the to-be-recommended strategy library, but the same driving strategy exists in the conventional strategy library, if a recommended times threshold is set, the corresponding recommended times threshold can be set separately for the to-be-recommended driving strategy , and make the value of the recommended times threshold lower than the recommended times threshold corresponding to the driving strategy to be recommended last time, and at the same time remove the same driving strategy in the conventional strategy library.
  • the recommended number of times threshold set when it was last located in the strategy database to be recommended is 5 times.
  • the update data package contains the driving strategy to be recommended, and after the driving strategy to be recommended is added to the strategy database to be recommended again, the corresponding recommendation times threshold of the driving strategy to be recommended can be set Set to any value less than 5 times, such as 3 times, 2 times, etc. Since the to-be-recommended driving strategy has been known to the user before, it can be considered that the user can learn and become familiar with the updated to-be-recommended driving strategy through fewer executions.
  • the updated driving strategy to be recommended can also be directly added to the strategy database to be recommended, and then the strategy database to be recommended and the conventional strategy database can be checked. And delete the driving strategies that are located in the regular strategy library and appear in both the regular strategy library and the strategy library to be recommended.
  • the conventional strategy library is used to save the driving strategies known to the user.
  • a well-known criterion to the user may be that the driving strategy has been recommended to the user at least once.
  • S601 and S602 the purpose of S601 and S602 is to update the strategy library to be recommended synchronously after receiving the update data package from the cloud platform or server, so as to better recommend driving strategies that are unfamiliar and unclear to the user.
  • FIG. 7 is a schematic diagram of a vehicle driving strategy update provided by an embodiment of the present application.
  • the update process in FIG. 6 is provided.
  • the terminal device 002 receives the update data package delivered by the cloud platform or the server, it can parse the update data package and then update other update contents according to the existing method.
  • the driving strategy to be recommended it is directly added to the strategy library to be recommended.
  • the strategy library to be recommended is only the vehicle driving strategy library. A subset of.
  • the vehicle driving policy library may also include a subset of the conventional policy library.
  • all driving strategies can be defaulted to be the driving strategies to be recommended, and all of them are added to the strategy library to be recommended.
  • FIG. 8 is a schematic structural diagram of a terminal device according to an embodiment of the present application.
  • the present application provides a schematic structural diagram of a terminal device, and the terminal device 800 may be the terminal device 002 involved in FIGS. 2 to 7 .
  • the terminal device 800 includes: a communication module 801 , a decoding module 802 , a distribution module 803 , a strategy library 804 to be recommended, a sensor module 805 , a system data collection module 806 , a processing module 807 and a human-computer interaction module 808 .
  • the processing module 807 may further include a driving scene recognition module 8071 and a matching module 8072 .
  • the human-computer interaction module 808 may further include a display module 8081 and a voice module 8082 .
  • the communication module 801 may be a communication port of the terminal device 800, and may perform wired or wireless communication.
  • wireless communication can be used to connect to a cloud platform or server for OTA updates and download update packages.
  • the decoding module 802 is configured to decode the update data packet downloaded by the communication module 801 .
  • the diversion module 803 is used to identify the driving strategy to be recommended and the driving scene corresponding to the driving strategy to be recommended from the decoding stream decoded by the decoding module 802, and add the driving strategy to be recommended and the driving scene corresponding to the driving strategy to be recommended. to the strategy library 804 to be recommended.
  • the communication module 801 , the decoding module 802 , the offloading module 803 and the strategy library to be recommended 804 complete the process described in FIG. 6 and FIG. 7 , and the specific implementation can refer to the corresponding description in FIG. 6 and FIG. 7 , which will not be repeated here. .
  • the sensor module 805 can include various sensors mounted in the terminal device 800 and can be wired or wirelessly connected to the terminal device 800, and is mainly used to collect external environment data so as to judge the driving scene.
  • the system data collection module 806 mainly collects the internal environment data of the user, such as the operation status of the steering wheel, the car, and the gear shift, so as to judge the driving scene.
  • the driving scene identification module 8071 in the processing module 807 is mainly used to identify the driving scene through the environmental information obtained by the sensor module 805 and/or the system data collection module 806 to determine at least one driving scene.
  • the matching module 8072 is configured to match the corresponding to-be-recommended driving strategy from the to-be-recommended strategy library 804 according to the driving scene determined by the driving scene identification module 807 .
  • the display module 8081 in the human-computer interaction module 808 displays it, or the voice module 8082 in the human-computer interaction module 808 performs a voice broadcast for the user to select.
  • the display module 8081 may be, for example, a display
  • the voice module 8082 may be, for example, a speaker, a microphone, and the like.
  • the strategy library 804 to be recommended, the sensor module 805, the system data collection module 806, the processing module 807 and the human-computer interaction module 808 jointly complete the processes described in Figs. description, which will not be repeated here.
  • Example 1 take the automatic parking function as the driving strategy to be recommended as an example.
  • the terminal device may carry an automatic parking function in an initial state or when it leaves the factory. Since all driving strategies are the driving strategies to be recommended in the initial state or factory default, the automatic parking function can be added to the strategy library to be recommended as the driving strategy to be recommended. Of course, in other examples, the terminal device can also be updated by receiving the update data package sent by the cloud platform or server, and parses that the update data package carries the automatic parking function. At this time, the automatic parking function can be matched with the corresponding The driving scenarios (also known as activation conditions) are added to the strategy library to be recommended. For example, after the user has used it for a period of time, the terminal device may receive a push update sent by a cloud platform or a server, where the push update may be an update data package. In some examples, the update package may also carry functional guidance/instructions for the automatic parking function to provide guidance/instructions when the automatic parking function is activated.
  • the terminal device when the terminal device is working, it can collect various possible environmental information through sensors, such as vehicle temperature, ambient temperature, traffic speed, traffic flow, road signs, environmental signs, vehicle location, internal data of the vehicle system, etc. Then, according to the collected environmental information, a driving scene where the current terminal device may be located is determined. For example, the location where the terminal device is located in the parking lot can be collected by the position sensor, and the road signs/environment signs can be collected by the image sensor to identify the parking space information. It can also be recognized that the user is performing a reversing operation according to the user's vehicle operation within a certain time range. It can be understood that the location is located in the parking lot and the parking space information may belong to the external environment data, while the reversing operation may belong to the internal environment data.
  • the terminal device may determine at least one driving scene in which the terminal device may be located according to a preset rule in combination with the collected external environment data and internal environment data.
  • the preset rule is, for example, the mapping table between the environment information and the driving scene shown in Table 1 or Table 3 above. For example, when it is recognized that the terminal device is located in the parking lot and is located near the parking space, the scene to be parked can be determined. At this time, combined with the reversing operation, the corresponding parking and entering scene can be recognized.
  • the terminal device matches with the strategy library to be recommended according to the determined parking-in-place scene, for example, the mapping table between the driving scene shown in Table 2 or Table 3 and the driving strategy to be recommended. It is determined whether there is a to-be-recommended driving strategy corresponding to the determined driving scenario. For example, according to Table 2 or Table 3, it is determined that there are corresponding driving strategies to be recommended for both the parking-to-be-parked scene and the parking-in-place scene, and both are "automatic parking”. At this time, the matched "automatic parking” can be recommended to the user, for example, displayed through the display screen of the terminal device, or voice broadcast through the speaker. If the display screen is used, it can be shown in FIG. 9 , for example. For example, "The current detected driving scene meets the automatic parking conditions, whether to activate the automatic parking driving mode" is displayed and corresponding options are provided for the user to make a choice.
  • the terminal device recognizes the user instruction by collecting user instructions input by the user, such as touching options on the display screen, pressing physical buttons, or recognizing keywords through speech. Determines whether to implement the to-be-recommended driving strategy "Automatic Parking". For example, when the user clicks "Yes” or detects the voice keywords "Yes”, “Execute”, “Start automatic parking” and so on. It means that the user is willing to implement the to-be-recommended driving strategy of "automatic parking", and the terminal device implements the to-be-recommended driving strategy of "automatic parking”. For example, the terminal device can take over the operation of the vehicle by the user and perform automatic parking. The operation when the specific policy is executed can be adjusted according to the actual situation, which is not limited in this application.
  • the vehicle-mounted assisted driving system on the terminal device exits and prompts the user.
  • the to-be-recommended driving strategy of "automatic parking” can be removed from the to-be-recommended strategy library, for example, moved to the regular strategy library.
  • the “automatic parking” to-be-recommended driving strategy is removed from the to-be-recommended strategy library and moved to the regular strategy library .
  • “automatic parking” can be moved from the strategy library to be recommended to the regular strategy library.
  • Example 2 taking the rest mode as the driving strategy to be recommended as an example.
  • the terminal device may be in a rest mode in an initial state or when it is shipped from the factory. And by default, the rest mode is added to the to-be-recommended strategy library as the to-be-recommended driving strategy.
  • the terminal device receives the update data packet sent by the cloud platform or the server, parses that the update data packet carries the rest mode, and adds the rest mode to the strategy library to be recommended.
  • the terminal device collects various possible environmental information through sensors, such as external environment data and internal environment data.
  • sensors such as external environment data and internal environment data.
  • the user's facial posture, hand posture and posture of other parts are recognized through image recognition technology, such as mouth shape, facial muscle movement, eyebrow distance, eye size, movement, etc. , as well as stretching, covering your mouth, etc.
  • the terminal device may determine at least one driving scene in which the terminal device may be located according to a preset rule in combination with the collected external environment data and internal environment data.
  • the preset rule is, for example, the mapping table between the environment information and the driving scene shown in Table 1 or Table 3 above. For example, when it is recognized that the mouth shape is open and/or accompanied by an action of covering the mouth, it can be determined that the current user may be in a fatigue state, and the driving scene is determined to be a fatigue driving scene.
  • the terminal device matches the determined fatigue driving scenario with the strategy library to be recommended, such as the mapping table between the driving scenario and the driving strategy to be recommended as shown in Table 2 or Table 3. It is determined whether there is a to-be-recommended driving strategy corresponding to the determined driving scenario. For example, according to Table 2 or Table 3, it is determined that there is a driving strategy to be recommended corresponding to the fatigue driving scenario, which is "rest mode". At this time, the matched "rest mode" can be recommended to the user, for example, it is displayed on the display screen of the terminal device, or the voice broadcast is performed through the speaker. If the display screen is used, it can be shown in Figure 11, for example. For example, if the driver fatigue is detected, whether to activate the rest driving mode. After activation, the cruise will be turned on and find a suitable location to automatically park on the side of the road, and provide corresponding options for the user to make a choice.
  • the strategy library to be recommended such as the mapping table between the driving scenario and the driving strategy to be recommended as shown in Table 2 or Table 3. It
  • the terminal device recognizes the user instruction by collecting user instructions input by the user, such as touching options on the display screen, pressing physical buttons, or recognizing keywords through speech. Determines whether to implement the "rest mode" to-be-recommended driving strategy. For example, when the user clicks "Yes” or detects the speech keywords "Yes”, “Execute”, “Start Rest Mode”, etc. It means that the user is willing to implement the to-be-recommended driving strategy of "rest mode", and the terminal device implements the to-be-recommended driving strategy of "automatic parking”. For example, the terminal device can start cruising through the vehicle-mounted assisted driving system, and make a roadside stop at a suitable location. Then execute a series of parameter configurations to generate corresponding vehicle actions.
  • the vehicle will stop to the side of the road, raise the windows, turn on the air conditioner to a suitable temperature, play soothing music, adjust the lights to warm colors, and tilt the seats to preset angles, etc.
  • the operation when the specific policy is executed can be adjusted according to the actual situation, which is not limited in this application.
  • the vehicle-mounted assisted driving system on the terminal device exits and prompts the user.
  • the to-be-recommended driving strategy of "rest mode” can be removed from the to-be-recommended strategy library, for example, moved to the regular strategy library.
  • the “rest mode” to-be-recommended driving strategy is removed from the to-be-recommended strategy library and moved to the regular strategy library.
  • a driving strategy that has not been used or that has been used less frequently is added to the strategy library to be recommended as a driving strategy to be recommended. Then, the environmental information of the vehicle is collected to determine the possible driving scenarios of the current vehicle, and the corresponding driving strategies to be recommended are determined based on the driving scenarios, and are recommended to the user at the same time. The user can be reminded whether to enable driving strategies that have been used or that have been used less frequently.
  • This method can ensure that after the driving strategy is updated, the in-vehicle assisted driving system can "hand in hand” remind the user of the unfamiliar driving strategy at least once, so as to ensure that the user can understand the corresponding driving strategy. It avoids the problem that some driving strategies have never been used or the usage rate is low.
  • FIG. 12 is a schematic diagram of a vehicle driving strategy recommendation device provided by an embodiment of the present application.
  • the present application further provides a vehicle driving strategy recommendation device 1200 .
  • the device 1200 may include: a processor 1210, an external memory interface 1220, an internal memory 1221, a universal serial bus (USB) interface 1230, a charging management module 1240, a power management module 1241, a battery 1242, Antenna 1, Antenna 2, mobile communication module 1250, wireless communication module 1260, audio module 1270, speaker 1270A, receiver 1270B, microphone 1270C, sensor module 1280, buttons 1290, camera 1291 and display screen 1292, etc.
  • a processor 1210 an external memory interface 1220, an internal memory 1221, a universal serial bus (USB) interface 1230, a charging management module 1240, a power management module 1241, a battery 1242, Antenna 1, Antenna 2, mobile communication module 1250, wireless communication module 1260, audio module 1270, speaker 1270A, receiver 1270B, microphone 1270C, sensor module 1280, buttons 1290, camera 1291 and display screen 12
  • the sensor module 1280 may include: pressure sensor 1280A, gyro sensor 1280B, air pressure sensor 1280C, magnetic sensor 1280D, acceleration sensor 1280E, distance sensor 1280F, image sensor 1280G, ultrasonic sensor 1280H, temperature sensor 1280J, touch sensor 1280K, environment Light sensor 1280L and radar 1280M, etc.
  • the radar 1280M may include lidar, millimeter wave radar, and the like.
  • Device 1200 may include more or fewer components than shown, or some components may be combined, or some components may be split, or a different arrangement of components.
  • the illustrated components may be implemented in hardware, software, or a combination of software and hardware.
  • the processor 1210 may be a processor of an advanced reduced instruction set processor (advanced reduced instruction set computing machines, ARM), X86, a microprocessor without interlocked piped stages (MIPS) and other architectures.
  • the processor 1210 may include one or more processing units, such as: application processor (application processor, AP), modem processor, GPU, image signal processor (image signal processor, ISP), controller, video codec processor, digital signal processor (digital signal processor, DSP), baseband processor and/or neural-network processing unit (neural-network processing unit, NPU), etc. Wherein, different processing units may be independent devices, or may be integrated in one or more processors.
  • the controller can generate an operation control signal according to the instruction operation code and timing signal, and complete the control of fetching and executing instructions.
  • a memory may also be provided in the processor 1210 for storing instructions and data.
  • the memory in processor 1210 is cache memory. This memory may hold instructions or data that have just been used or recycled by the processor 1210 . If the processor 1210 needs to use the instruction or data again, it can be called directly from the memory. Repeated accesses are avoided, and the waiting time of the processor 1210 is reduced, thereby improving the efficiency of the system.
  • the processor 1210 may include one or more interfaces.
  • the interface may include an integrated circuit (inter-integrated circuit, I2C) interface, an integrated circuit built-in audio (inter-integrated circuit sound, I2S) interface, a pulse code modulation (pulse code modulation, PCM) interface, a universal asynchronous transceiver (universal asynchronous transmitter) receiver/transmitter, UART) interface, mobile industry processor interface (MIPI), general-purpose input/output (GPIO) interface, subscriber identity module (SIM) interface and/ Or universal serial bus (universal serial bus, USB) interface and so on.
  • I2C integrated circuit
  • I2S integrated circuit built-in audio
  • PCM pulse code modulation
  • PCM pulse code modulation
  • UART universal asynchronous transceiver
  • MIPI mobile industry processor interface
  • GPIO general-purpose input/output
  • SIM subscriber identity module
  • USB universal serial bus
  • the charging management module 1240 is used to receive charging input from the charger.
  • the charger may be a wireless charger or a wired charger.
  • the charging management module 1240 may receive charging input from the wired charger through the USB interface 1230 . In some wireless charging embodiments, the charging management module 1240 may receive wireless charging input through the wireless charging coil of the device 1200 . While the charging management module 1240 charges the battery 1242, the device 1200 can also be powered by the power management module 1241.
  • the wireless communication function of the apparatus 1200 may be implemented by the antenna 1, the antenna 2, the mobile communication module 1250, the wireless communication module 1260, the modem processor, the baseband processor, and the like.
  • the mobile communication module 1250 may provide a wireless communication solution including 2G/3G/4G/5G/6G etc. applied on the device 1200 .
  • the wireless communication module 1260 can provide applications on the device 1200 including wireless local area networks (WLAN), bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM). ), near field communication technology (near field communication, NFC) and infrared technology (infrared, IR) and other wireless communication solutions.
  • the WLAN may be, for example, a wireless fidelity (Wi-Fi) network.
  • the device 1200 implements a display function through a GPU, a display screen 1292, an application processor, and the like.
  • the GPU is a microprocessor for image processing, and is connected to the display screen 1292 and the application processor.
  • the GPU is used to perform mathematical and geometric calculations for graphics rendering.
  • Processor 1210 may include one or more GPUs that execute program instructions to generate or alter display information.
  • Display screen 1292 is used to display images, videos, and the like.
  • Display screen 1292 includes a display panel.
  • the display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active matrix organic light emitting diode, or an active matrix organic light emitting diode (active-matrix organic light).
  • emitting diode, AMOLED organic light-emitting diode
  • flexible light-emitting diode flexible light-emitting diode (flex light-emitting diode, FLED), Miniled, MicroLed, Micro-oLed and quantum dot light-emitting diode (quantum dot light emitting diodes, QLED) and so on.
  • the apparatus 1200 may include 1 or N display screens 194, where N is a positive integer greater than 1.
  • the apparatus 1200 can realize the shooting function through the ISP, the camera 1291, the video codec, the GPU, the display screen 1292, the application processor, and the like.
  • the camera 1291 is used to capture still images or video.
  • the apparatus 1200 may include 1 or N' cameras 1291, where N' is a positive integer greater than 1.
  • the external memory interface 1220 can be used to connect an external memory card, such as a Micro SD card, to realize the storage capability of the expansion device 1200.
  • the external memory card communicates with the processor 1210 through the external memory interface 1220 to realize the data storage function. Such as saving audio, video etc files in external memory card.
  • Internal memory 1221 may be used to store computer executable program code, which includes instructions.
  • the internal memory 1221 may include a storage program area and a storage data area.
  • the storage program area can store an operating system, an application program required for at least one function (such as a sound playback function, an image playback function, etc.), and the like.
  • the storage data area may store data (such as audio data, etc.) created during the use of the device 1200 and the like.
  • the internal memory 1221 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, universal flash storage (UFS), and the like.
  • the processor 1210 executes various functional applications and data processing of the apparatus 1200 by executing instructions stored in the internal memory 1221 and/or instructions stored in a memory provided in the processor.
  • the device 1200 may implement audio functions through an audio module 1270, a speaker 1270A, a receiver 1270B, a microphone 1270C, an application processor, and the like. Such as audio playback, audio capture, etc.
  • Speaker 1270A also referred to as “speaker” is used to convert audio electrical signals into sound signals.
  • Microphone 1270C also called “microphone” or “microphone”, is used to convert sound signals into electrical signals.
  • Keys 1290 include any possible form of keys, such as mechanical keys or tactile keys, and the like.
  • the apparatus 1200 can receive key input and determine the user instruction.
  • the apparatus 1200 provided by the present application can implement any one of the methods described in FIG. 2 to FIG. 11 .
  • the present application pre-sets the strategy library to be recommended. For example, when updating, the driving strategy to be recommended in the update data package is added to the strategy library to be recommended, or in the initial state, all driving strategies are defaulted as the driving strategies to be recommended. And add it to the strategy library to be recommended.
  • the strategy library to be recommended In order to identify the driving scene by collecting the environmental information including the external environment data and the internal environment data, and match the corresponding driving strategy to be recommended according to the identified driving scene to the strategy library to be recommended. After matching the driving strategy to be recommended, it actively recommends the matching driving strategy to be recommended to the user.
  • the in-vehicle assisted driving system can ensure that the "hand-in-hand" reminds the user of the new driving strategy at least once, and ensures that the user knows that the corresponding function has been updated.
  • the active interaction reminds the user to use the new driving strategy, which improves the experience of using the self-driving vehicle and enables the user to fully experience the functions of the self-driving vehicle.
  • the strategy to be recommended is removed from the to-be-recommended strategy library. And the same driving strategy is updated again and re-transferred to the strategy library to be recommended. It is guaranteed that the strategy library to be recommended only contains driving strategies that the user is not familiar with and does not understand.
  • non-transitory English: non-transitory
  • the storage medium is non-transitory ( English: non-transitory) media, such as random access memory, read only memory, flash memory, hard disk, solid state disk, magnetic tape (English: magnetic tape), floppy disk (English: floppy disk), optical disc (English: optical disc) and any combination thereof.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Software Systems (AREA)
  • Computer Security & Cryptography (AREA)
  • Human Computer Interaction (AREA)
  • Traffic Control Systems (AREA)
  • Navigation (AREA)

Abstract

本申请提供了一种车辆驾驶策略推荐方法，包括：采集环境信息。并根据采集到的环境信息确定驾驶场景。再将驾驶场景与待推荐策略库进行匹配。其中，待推荐策略库中可以包括驾驶场景与待推荐驾驶策略的对应关系。当匹配有待推荐驾驶策略时，可以将待推荐驾驶策略进行显示。以便终端设备可以根据用户输入的用户指令执行待推荐驾驶策略。

Description

一种车辆驾驶策略推荐方法及装置
本申请要求于2021年4月26日提交至中国国家知识产权局、申请号为202110454338.4、申请名称为“一种车辆驾驶策略推荐方法及装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及智能车领域，尤其涉及一种基于驾驶场景进行车辆驾驶策略推荐方法及装置。
背景技术
传统的汽车是通过驾驶员进行车辆驾驶，但随着科技进步，人工智能(artificial intelligence，AI)的技术也在逐步提升。目前基于AI提出了自动驾驶汽车的概念，同时自动驾驶汽车也被誉为是未来的汽车形态。但是，目前的汽车仍然无法实现任意场景下的全自动驾驶，只是在一些特定的场景下才能够实现自动驾驶。对于每种自动驾驶的场景会对应一个自动驾驶策略。自动驾驶策略也可以认为是自动驾驶汽车的一种新功能。例如，针对泊车场景的自动泊车策略、针对堵车场景的低速巡航策略等。
车载辅助驾驶系统为车辆上装载的一种系统，通常由汽车厂家或者车载系统承包商通过云端进行系统更新，例如采用空中下载(over-the-air，OTA)更新。在更新的同时，通常会有新自动驾驶策略(也可称新功能)加入，同时自动驾驶策略库也随之更新。在OTA更新后，目前会提供一个文字性的更新说明，用于用户查阅详细的更新内容。
但是，目前用户并不习惯于阅读长篇的文字更新，通常在更新完毕后顺手关闭更新说明。即便用户在更新时查看了更新说明，过后往往也会忘记。当用户真正可以用到更新的新自动驾驶策略时，通常会想不起来。这导致了车载辅助系统的很多自动驾驶策略被用户遗忘，甚至更新后从来没有被使用过。这将严重降低用户的使用体验。
发明内容
本申请实施例提供了一种车辆驾驶策略推荐的方法，通过采集车辆的外部环境数据和/或内部环境数据确定当前车辆可能的驾驶场景。以便根据驾驶场景从待推荐策略库中进行匹配，确定驾驶场景对应的待推荐驾驶策略并推荐给用户。通过主动推荐待推荐驾驶策略给用户，可以确保在驾驶策略更新后，用户可以知晓新增的驾驶策略，并充分体验新增的驾驶策略。避免用户对文字更新内容的感知力低而导致新增的驾驶策略用户不知情的情况。
第一方面，提供了一种车辆驾驶策略推荐方法，该方法可以应用于终端设备，方法可以包括：采集至少一个环境信息。其中，环境信息可以包括外环境数据和/或内环境数据。之后，采集到的根据至少一个环境信息，确定至少一个驾驶场景。再将至少一个驾驶场景与待推荐策略库进行匹配。其中，待推荐策略库中可以包括驾驶场景与待推荐驾驶策略的对应关系。当匹配有至少一个待推荐驾驶策略时，可以将至少一个待推荐驾驶策略进行显示。以便终端设备可以根据用户输入的用户指令执行一个或多个显示的待推荐驾驶策略。本申请通过采集环境信息确定相应的驾驶场景，再结合驾驶场景从待推荐策略库中匹配相应的待推荐策略后 显示给用户，可以确保在驾驶策略更新后，用户可以知晓新增的驾驶策略。避免用户对文字更新内容的感知力低而导致新增的驾驶策略用户不知情的情况。当通过用户指令执行待推荐策略时，使得用户可以充分体验新增的驾驶策略。
在一个可能的实施方式中，在采集至少一个环境信息之前，方法还可以包括：获取更新数据包。其中该更新数据包可以包括待推荐驾驶策略以及与待推荐驾驶策略对应的驾驶场景。然后，将更新数据包中的待推荐驾驶策略和与待推荐驾驶策略对应的驾驶场景添加至待推荐策略库。本申请通过将更新时新增的驾驶策略存入待推荐策略库中，以便终端设备根据环境信息确定驾驶场景并确定出待推荐驾驶策略，保障了更新后新增的驾驶策略可以被用户所知晓甚至充分体验，避免用户对文字更新内容的感知力低而导致新增的驾驶策略用户不知情的情况。
在一个可能的实施方式中，待推荐驾驶策略可以包括优先级信息。将至少一个待推荐驾驶策略进行显示，可以包括：根据优先级信息，将优先级最高的至少一个待推荐驾驶策略进行显示。
在一个可能的实施方式中，驾驶场景可以包括单一驾驶场景和复合驾驶场景。其中，复合驾驶场景对应待推荐驾驶策略的优先级高于单一驾驶场景对应待推荐驾驶策略的优先级。
在一个可能的实施方式中，根据用户指令执行一个或多个显示的待推荐驾驶策略，可以包括：若多个待推荐驾驶策略存在执行冲突，则根据用户指令执行多个待推荐驾驶策略中的部分待推荐驾驶策略。其中，执行的部分待推荐驾驶策略不存在执行冲突。
在一个可能的实施方式中，方法还可以包括：将执行的至少一个待推荐驾驶策略从待推荐策略库中移除。或者，对执行的至少一个待推荐驾驶策略的执行次数加一。其中，每个待推荐驾驶策略的执行次数初始值可以设置为零。然后，将执行次数大于或等于推荐次数阈值的待推荐驾驶策略从待推荐策略库中移除。本申请通过将用户执行过的驾驶策略从待推荐策略库中移除，可以保证推荐的驾驶策略大部分为用户不熟悉甚至不知道的驾驶策略，使得用户可以充分体验新增的驾驶策略。
第二方面，提供了一种车辆驾驶策略推荐装置，该装置为终端设备，该装置可以包括：传感器，用于采集至少一个环境信息，环境信息包括外环境数据和/或内环境数据；处理器用于与存储器耦合，以及读取并执行存储在存储器中的指令；当处理器运行时执行指令，使得处理器用于根据至少一个环境信息，确定至少一个驾驶场景；将至少一个驾驶场景与待推荐策略库进行匹配，其中，待推荐策略库包括驾驶场景与待推荐驾驶策略的对应关系；当匹配有至少一个待推荐驾驶策略时，控制显示器将至少一个待推荐驾驶策略进行显示，以便根据用户指示执行至少一个待推荐驾驶策略。本申请通过采集环境信息确定相应的驾驶场景，再结合驾驶场景从待推荐策略库中匹配相应的待推荐策略后显示给用户，可以确保在驾驶策略更新后，用户可以知晓新增的驾驶策略。避免用户对文字更新内容的感知力低而导致新增的驾驶策略用户不知情的情况。当通过用户指令执行待推荐策略时，使得用户可以充分体验新增的驾驶策略。
在一个可能的实施方式中，该装置还包括：接收器，用于获取更新数据包，更新数据包包括待推荐驾驶策略以及与待推荐驾驶策略对应的驾驶场景；处理器还用于，将待推荐驾驶策略以及与待推荐驾驶策略对应的驾驶场景添加至待推荐策略库。本申请通过将更新时新增的驾驶策略存入待推荐策略库中，以便终端设备根据环境信息确定驾驶场景并确定出待推荐驾驶策略，保障了更新后新增的驾驶策略可以被用户所知晓甚至充分体验，避免用户对文字 更新内容的感知力低而导致新增的驾驶策略用户不知情的情况。
在一个可能的实施方式中，待推荐驾驶策略包括优先级信息；处理器还用于：根据优先级信息，控制显示器将优先级最高的至少一个待推荐驾驶策略进行显示。
在一个可能的实施方式中，驾驶场景包括单一驾驶场景和复合驾驶场景，复合驾驶场景对应待推荐驾驶策略的优先级高于单一驾驶场景对应待推荐驾驶策略的优先级。
在一个可能的实施方式中，接收器还用于：接收用户指令；处理器还用于：若多个待推荐驾驶策略存在执行冲突，则根据用户指令执行多个待推荐驾驶策略中的部分待推荐驾驶策略，其中，执行的部分待推荐驾驶策略不存在执行冲突。
在一个可能的实施方式中，处理器还用于：将执行的至少一个待推荐驾驶策略从待推荐策略库中移除；或，对执行的至少一个待推荐驾驶策略的执行次数加一，其中，每个待推荐驾驶策略的执行次数初始值为零；将执行次数大于或等于推荐次数阈值的待推荐驾驶策略从待推荐策略库中移除。本申请通过将用户执行过的驾驶策略从待推荐策略库中移除，可以保证推荐的驾驶策略大部分为用户不熟悉甚至不知道的驾驶策略，使得用户可以充分体验新增的驾驶策略。
第三方面，提供了一种计算机可读存储介质，计算机可读存储介质中存储有指令，当指令在终端上运行时，使得终端执行如第一方面中的任意一项方法。
第四方面，提供了一种包含指令的计算机设备，当其在终端上运行时，使得终端执行如第一方面中的任意一项方法。
第五方面，提供了一种包含指令的计算机程序产品，当其在计算机上运行时，使得计算机执行第一方面中任意一项的方法。
本申请公开了一种车辆驾驶策略推荐方法及装置，通过采集车辆的环境信息确定当前车辆可能的驾驶场景，再基于驾驶场景确定对应的待推荐驾驶策略并推荐给用户。确保了在驾驶策略更新后，用户可以知晓新增的驾驶策略，避免用户对文字更新内容的感知力低而导致新增的驾驶策略用户不知情的情况。同时执行待推荐驾驶策略使得用户可以充分体验新增的驾驶策略。
附图说明
图1为本申请实施例提供的一种应用场景示意图；
图2为本申请实施例提供的一种车辆驾驶策略推荐系统架构示意图；
图3为本申请实施例提供的一种车辆驾驶策略推荐方法流程图；
图4为本申请实施例提供的一种显示待推荐驾驶策略界面示意图；
图5A为本申请实施例提供的另一种显示待推荐驾驶策略界面示意图；
图5B为本申请实施例提供的又一种显示待推荐驾驶策略界面示意图；
图5C为本申请实施例提供的再一种显示待推荐驾驶策略界面示意图；
图5D为本申请实施例提供的另一种显示待推荐驾驶策略界面示意图；
图6为本申请实施例提供的另一种车辆驾驶策略推荐方法流程图；
图7为本申请实施例提供的一种车辆驾驶策略更新示意图；
图8为本申请实施例提供的一种终端设备结构示意图；
图9为本申请实施例提供的示例一中显示待推荐驾驶策略界面示意图；
图10为本申请实施例提供的一种移除待推荐驾驶策略示意图；
图11为本申请实施例提供的示例二中显示待推荐驾驶策略界面示意图；
图12为本申请实施例提供的一种车辆驾驶策略推荐装置示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行描述。
本申请主要应用于车辆驾驶场景，例如图1所示出的，用户在驾驶车辆过程中，可能会面对不同的情况，例如开车时可能遇到一些路段会限速，或者可能需要进行超车等，又例如，用户可能准备泊车，或者停在路边进行短暂休息等。对于不同的情况，相应地车辆可以提供对应的驾驶策略。然而，用户对于车辆中的驾驶策略并不是完全了解，例如车辆是用户近期刚购买的，显然对于车辆内的所有驾驶策略均不了解。又或者当车辆上更新了新的驾驶策略后，用户对于更新后新增的驾驶策略也处于不知情或者不了解的状态。
在一些情况下，例如车辆上更新了新的驾驶策略，通常会给出一个版本更新说明，用于描述本次更新的内容。例如，更新内容可以是“第XXXX.X版本，1、开发者反馈优化：增加智能客服、申诉、问题反馈等功能，反馈入口：右上角图标；页面右下角悬浮按钮；2、首页优化改版，新增‘特别推荐’、‘演示项目’等，寻找服务更加方便；3、报表优化：下载安装报表，支持按照应用版本维度查看数据；4、崩溃服务：支持XX系统应用崩溃分析；5、远程配置服务增强：支持XX系统应用；6、A/B测试服务增强：支持XX系统应用；7、新增XXX驾驶策略。”。可以看出，通常更新说明会通过上述文字方式描述本次更新的新增内容。然而，对于用户而言，往往会顺手将其关闭。即使当时看了文字的更新说明。由于其并未真正使用过新增的各种功能，当过一段时间后，用户仍然会忘记更新内容，或者在适当的时候想不起新增的功能。例如，某次更新新增了自动泊车驾驶策略，可以通过方向盘上的特定按钮激活自动泊车。但是用户在真正泊车时可能并不会记得新增的自动泊车驾驶策略，而往往会沿用以前的方式进行泊车。对于车辆新增的自动泊车驾驶策略则仍然处于一种“不知道——不使用”的状态。
因此，本申请提供了一种车辆驾驶策略推荐方法，终端设备通过采集车辆的环境信息确定当前车辆可能所处的驾驶场景，然后根据驾驶场景确定对应的待推荐驾驶策略。终端设备将待推荐驾驶策略推荐给用户后，根据用户指示执行一个或多个显示的待推荐驾驶策略。通过上述方式确保了在驾驶策略更新后，用户可以知晓新增的驾驶策略，避免用户对文字更新内容的感知力低而导致用户对新增的驾驶策略不知情的情况。同时执行待推荐驾驶策略使得用户可以充分体验新增的驾驶策略。
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行详细描述。
图2为本申请实施例提供的一种车辆驾驶策略推荐系统架构示意图。该系统中可以包括有传感器001和终端设备002。其中，传感器001可以是终端设备或车辆上搭载的各种传感器，用于采集环境信息，以便终端设备根据采集到的环境信息进行驾驶场景的确定。在一些例子中，传感器可以包括图像传感器、超声波传感器、激光雷达、毫米波雷达、压力传感器、陀螺仪传感器、气压传感器、磁传感器、加速度传感器、距离传感器、温度传感器、环境光传感器等。可以理解的是，传感器001可以包括任意可能的传感器，本申请在此不做限定。
终端设备002例如可以是智能车或者是车载智能终端等。终端设备002上搭载有车载辅助驾驶系统，其中，车载辅助驾驶系统中可以包括有车辆驾驶策略库，该车辆驾驶策略库中包含有至少一条驾驶策略。可以理解的是，每条驾驶策略可以适用于不同驾驶场景，以控制 车辆完成相应的操作。终端设备根据传感器001获取的环境信息，确定可能的驾驶场景。再结合车辆驾驶策略库中的驾驶策略，确定当前驾驶场景适用的驾驶策略，并向用户进行推荐。在一个例子中，可以是通过显示屏和/或麦克风等形式将驾驶策略推荐给用户。
可以理解的是，图2中的传感器001可以部署在终端设备002上，当然，部分传感器001也可以部署在特定位置，并通过有线或无线的方式与终端设备002相连接。在一些例子中，例如，终端设备002为智能车时，传感器001可以部署在智能车上，用于采集车内和/或车外的环境信息。又例如，终端设备还可以是与车辆通过有线或无线方式连接的车载智能终端，如包括但不限于手机、智能电视、智能音响、可穿戴设备、平板电脑、桌面型计算机、手持计算机、笔记本电脑、超级移动个人计算机(ultra-mobile personal computer，UMPC)、上网本、个人数字助理(personal digitalassistant，PDA)、膝上型计算机(laptop)、移动电脑、增强现实(augmented reality，AR)设备、虚拟现实(virtual reality，VR)设备、人工智能(artificial intelligence，AI)设备和/或车载设备等任意终端设备或便携式终端设备。
图3为本申请实施例提供的一种车辆驾驶策略推荐方法流程图。
如图3所示，本申请提供了一种车辆驾驶策略推荐方法。该方法可以应用于图2所示的系统，在一些例子中，可以应用于图2中的终端设备002。该方法可以包括以下步骤：
S301，采集至少一个环境信息。
终端设备002可以通过传感器001采集至少一个环境信息。在一些例子中，传感器可以是上述图2所涉及到的任意一种传感器，可以采集终端设备002的环境信息。其中，环境信息可以包括外环境数据和/或内环境数据。
在一些例子中，外环境数据可以是表示终端设备002外部环境的数据，例如车内温度、环境温度、车流速度、车流量、道路标识、环境标识、车辆位置等，其中部分数据可以采集后经过处理器进行相应处理后确定的，例如道路标识、环境标识等，可以是通过摄像头采集到图像后，经过图像识别后确定的，其具体实现过程可以参考现有方式实现，在此不再赘述。
在另一些例子中，内环境数据可以是表示终端设备002上运行的车载系统的状态数据、参数变化数据、操作日志等。例如，可以包括用户进行硬件操作所产生的操作记录，如用户进行倒车操作后产生了日志，该日志用于记录用户在某时刻执行倒车操作。
可以理解的是，终端设备002可以通过外环境数据感知终端设备002的外部环境场景情况，和/或可以通过内环境数据感知终端设备002的内部状态场景情况。
S302，根据至少一个环境信息，确定至少一个驾驶场景。
当终端设备002通过S301采集到了至少一个环境信息后，可以根据采集到的环境信息确定对应的驾驶场景。例如，根据外环境数据和/或内环境数据，按照预设的规则，确定出终端设备002可能对应的驾驶场景。其中，驾驶场景可以包括外部场景、终端内部场景和/或复合驾驶场景。
在一个例子中，终端设备002可以根据外环境数据确定终端设备002的外部场景。例如，若外环境数据为终端设备002的位置信息，则可以确定当前终端设备002的驾驶场景可以是位置场景；或者外环境数据为道路标识信息，则可以根据该道路标识信息确定出当前终端设备002的驾驶场景可以是道路场景；又或者，外环境数据为终端设备002的温度信息，则可以根据该温度信息确定出当前终端设备002的驾驶场景可以是温度场景；再或者，外环境数据为车流速度信息，则可以根据该车流速度信息确定出当前终端设备002的驾驶场景可以是 行驶场景等。可以理解是的，外环境数据还可以为其它任意可能的数据，并根据外环境数据确定出终端设备002对应的外部场景。当然在一些例子中，还可以结合多个外环境数据进行综合分析，以确定出终端设备002的外部场景，例如可以结合道路标识信息和位置信息，综合确定出终端设备002的驾驶场景可以是行驶场景。以道路标识信息为停车位标识，以及位置信息为终端设备002处于停车场为例，则可以确定终端设备002可能位于停车位附近的这一场景。
当然，对于部分外环境数据可以是传感器采集到的原始数据，例如位置信息、温度信息等；另外部分外环境数据可以是以传感器采集到的原始数据进行分析得到的，例如传感器为摄像头，采集到的图像信息，并对该图像信息进行图像识别，例如可以识别得到限速牌、道路标识等等。以便终端设备002根据外环境数据确定对应的外部场景。
在另一些例子中，终端设备002还可以根据内环境数据确定终端设备002的终端内部场景。例如，假设内环境数据记录了用户操作车辆进行倒车操作，因此终端设备002可以确定当前终端设备002的驾驶场景可以是倒车场景。又例如，假设内环境数据记录了用户踩踏油门进行车辆加速，则终端设备002可以确定当前终端设备002的驾驶场景可以是加速场景。显然，还可以结合多个内环境数据进行综合分析，以确定出终端设备002的终端内部场景，例如可以结合记录了用户踩踏油门进行车辆加速，以及记录了用户拨动转向灯等内环境数据，终端设备002可以综合确定出的驾驶场景可以是加速超车场景。
再又一些例子中，终端设备002还可以结合外环境数据和内环境数据，共同确定终端设备002驾驶场景的复合驾驶场景情况。可以理解的是，单一驾驶场景表示通过某一个环境信息确定出的驾驶场景，而复合驾驶场景可以表示通过多个环境信息确定出的驾驶场景。例如，可以结合多个外环境数据和内环境数据进行分析，其中，外环境数据包括道路标识信息为停车位标识和位置信息为停车场，以及内环境数据包括车辆进行的倒车操作，则终端设备002可以确定驾驶场景可以是停车场进停车位这一种驾驶场景。
在一些例子中，在确定驾驶场景时，可以根据预先存储的环境信息与驾驶场景的对应关系表进行识别。可以例如表1所示。
Figure PCTCN2022084442-appb-000001
Figure PCTCN2022084442-appb-000002
表1
可以理解的是，表1仅仅提供了一些可能的示例，当然还可以包括更多环境信息和驾驶场景的对应关系。当然具体的环境信息内容与对应的驾驶场景可以根据实际情况进行任意调整或修改，本申请在此不作限定。
在一些例子中，可以预先设定单一驾驶场景和复合驾驶场景的对应关系，例如，“待停车”与“正在倒车”这两个单一驾驶场景同时出现可以对应“正在泊车入位”这一复合驾驶场景。则可以直接确定“正在泊车入位”这一复合驾驶场景。当然在另一些例子中，可以同时确定出“待停车”、“正在倒车”和“正在泊车入位”这三种驾驶场景。
显然，上述过程可以根据至少一个环境信息确定出至少一个驾驶场景。
S303，将至少一个驾驶场景与待推荐策略库进行匹配。
当终端设备002通过S302中确定出了至少一个驾驶场景后，可以结合预先设定的待推荐策略库进行匹配，确定是否存在驾驶场景对应的待推荐驾驶策略。其中，待推荐策略库中可以包括：驾驶场景与待推荐驾驶策略的对应关系。
其中，待推荐策略库是预先配置好的，待推荐策略库中包含的待推荐驾驶策略为用户从未使用过的驾驶策略，或是执行次数小于推荐次数阈值的驾驶策略。可见，处于待推荐策略库中的驾驶策略均是用户不熟悉、不了解的驾驶策略。
在一个例子中，待推荐策略库中可以设置用于表示驾驶场景与待推荐驾驶策略之间对应关系的映射表。以便终端设备002可以根据S302中确定的驾驶场景在映射表中匹配到对应的待推荐驾驶策略。例如可以如表2所示出的驾驶场景与待推荐驾驶策略的对应关系。
Figure PCTCN2022084442-appb-000003
Figure PCTCN2022084442-appb-000004
表2
可以看出，通过表2所示出的驾驶场景与待推荐驾驶策略的对应关系，匹配S302中确定的至少一个驾驶场景所对应的待推荐驾驶策略。当然，对于部分驾驶场景对应的待推荐驾驶策略可以为“暂无”，以表示当前该驾驶场景暂时没有合适的待推荐驾驶策略。在一些例子中，可能存在多种不同的驾驶场景对应同一个待推荐驾驶策略。但是同一种驾驶场景显然不会对应多个不同的待推荐驾驶策略。可以理解的是，表2仅仅提供了一些可能的示例，当然还可以包括更多驾驶场景和待推荐驾驶策略的对应关系。具体的驾驶场景内容与对应的待推荐驾驶策略可以根据实际情况进行任意调整或修改，本申请在此不作限定。
在另一些例子中，待推荐策略库内每个待推荐驾驶策略可以对应一个二分类的神经网络。将S301中采集到的环境信息进行参数化，并作为输入层输入至每个待推荐驾驶策略对应的二分类的神经网络中。针对每个二分类的神经网络，根据输出层的结果确定是否符合该神经网络对应的待推荐驾驶策略的激活条件。例如将采集到的环境信息进行参数化后输入至A待推荐驾驶策略对应的二分类的神经网络中，其输出结果为65％“满足”和35％“不满足”。若设定满足占比60％为待推荐策略激活条件，则可以确定符合A待推荐驾驶策略的激活条件。又或者输出结果为“满足”，设定当输出“满足”为待推荐策略激活条件，也可以直接确定符合A待推荐驾驶策略的激活条件。
S304，当匹配有至少一个待推荐驾驶策略时，将至少一个待推荐驾驶策略进行显示。
当确定出了至少一个待推荐驾驶策略时，可以将确定出的至少一个待推荐驾驶策略通过终端设备002告知用户。例如可以通过终端设备002中的显示器进行显示，或是通过终端设备002中的扬声器进行语音播报。
在一些例子中，若通过终端设备002中的显示器进行显示，则可以显示待推荐驾驶策略，以及是否执行的选项，以便用户进行确定。显然，当确定出了至少一个待推荐驾驶策略时，则意味着存在用户不熟悉、不了解的驾驶策略。例如用户从未使用过的驾驶策略，或是执行次数小于推荐次数阈值的驾驶策略。因此，可以将确定出的待推荐驾驶策略推荐给用户，以便用户选择是否执行。
在一些例子中，待推荐驾驶策略中可以包括优先级信息。匹配有至少一个待推荐驾驶策略时，可以按照匹配到的待推荐驾驶策略的优先级信息进行显示或语音播报。例如，若采用显示的方式，可以按照优先级信息将优先级最高的待推荐驾驶策略进行显示；或者按照优先级信息由大至小依次排序，并以列表的形式进行显示，或顺序依次显示。又例如，若采用语音播报的方式告知用户，则可以按照优先级信息将优先级最高的待推荐驾驶策略进行语音播报；或者按照优先级信息由大至小依次语音播报。可以理解的是，若优先级最高的待推荐驾驶策略存在多个时，也可以将多个优先级最高的待推荐驾驶策略同时进行显示或进行语音播报。
例如图4示出了一种显示待推荐驾驶策略界面示意图，可以看出，该界面是以推荐一个待推荐驾驶策略为例进行显示。该界面包括推荐给用户的待推荐驾驶策略的内容，以及提供给用户进行选择的选项。该示例适用于仅匹配到一个待推荐驾驶策略，或是按照优先级信息仅推荐优先级最高的待推荐驾驶策略的情况。当然，图5A则示出了另一种显示待推荐驾驶策略界面示意图。例如当推荐一个待推荐驾驶策略时，可按照预设的顺序显示在显示器上。预设的顺序例如按照待推荐驾驶策略的优先级信息，由大至小顺序显示。通过图5A还可以看出，对于显示的每个待推荐驾驶策略，均可以具有与之对应的选项，用于用户进行选择。可以理解的是，若待推荐驾驶策略在一个页面中无法全部显示，则可以分多个页面进行显示。以便用户通过滑动屏幕或通过物理按键、语音等方式切换屏幕，并选择显示的待推荐驾驶策略。
在一些例子中，若待推荐驾驶策略中包括优先级信息，则可以设定复合驾驶场景对应待推荐驾驶策略的优先级高于单一驾驶场景对应待推荐驾驶策略的优先级。其原因在于可以认为复合驾驶场景相比于单一驾驶场景可能更加贴近真实的驾驶场景。同时在匹配待推荐驾驶策略时，可以先匹配复合驾驶场景对应待推荐驾驶策略，再匹配单一驾驶场景对应待推荐驾驶策略。在一个例子中，还可以在匹配到复合驾驶场景对应待推荐驾驶策略时就停止匹配。
在一些例子中，对于不同的驾驶场景，可能对应相同的待推荐驾驶策略。因此在显示或语音播报时，可以将相同的待推荐驾驶策略进行合并，仅显示一次，或仅语音播报一次即可。
S305，接收用户指令。
终端设备002可以接收用户输入的用户指令。该用户指令用于指示显示给用户的待推荐驾驶策略是否执行，或是用于指示语音播报给用户的待推荐驾驶策略是否执行。
在一个例子中，可以通过接收用户在显示屏上的操作或是通过采集特定的语音信息确定用户指令。例如，用户通过触摸显示屏上的相应选项，或是通过触控终端设备002上接入的物理按键，又或是通过语音识别检测到用户说的某些关键字信息。其中，关键字信息例如“执行”、“确认执行”、“好的”、“不使用”等可能用于表示用户意愿的关键词。当然，若S304中显示或者语音播报了多个待推荐驾驶策略，则关键字信息还可以例如为“启动XX驾驶模式”或“XX驾驶模式”等用于直接表示某个具体的驾驶策略。当然，具体的关键词信息可以根据实际情况进行任意设定，本申请并不做限定。
在一些例子中，若S304中推荐给用户的多个待推荐驾驶策略中，部分待推荐驾驶策略存在执行上的冲突，则S305中接收的用于表示执行待推荐驾驶策略的用户指令，则须指示相互不存在执行冲突的待推荐驾驶策略。例如仍以图5A为例，当A驾驶模式与C驾驶模式之间存在执行冲突，当用户选择执行A驾驶模式后，对应的C驾驶模式的相应选项则不可以被用户选择。如图5B所示将C驾驶模式对应的选项置灰。可以理解的是，灰色的选项表示不可被用户选择的选项。又或者如图5C所示不显示C驾驶模式的相应选项，也可以如图5D所示不显 示C驾驶模式。当然，在另一些例子中，还可以在用户选择执行A驾驶模式时，以文字弹窗和/或语音播报的方式提示用户，例如提示“A驾驶模式与C驾驶模式存在执行冲突，选择A驾驶模式后将无法选择C驾驶模式”或其它等效的表达方式。以便用户知晓A驾驶模式与C驾驶模式之间存在执行冲突。可以理解的是，还可以其它任意等效的方式实现，本申请在此不作限定。
显然，对于正常显示并且可被用户选择的驾驶模式，意味着驾驶模式之间是可以相容的，不存在执行冲突。在一些情况下，若某个待推荐驾驶策略与其它待推荐驾驶策略形成覆盖时，可以认为此类待推荐驾驶策略之间存在执行冲突。
S306，根据用户指令执行一个或多个显示的待推荐驾驶策略。
终端设备002根据S305中接收到的用户指令，确定执行用户选择的一个或多个显示或语音推荐的待推荐驾驶策略。当然，在一些例子中，也可以根据S305中接收到的用户指令，确定不执行用户选择的一个或多个显示或语音推荐的待推荐驾驶策略。
可以理解的是，当用户输入用户指令指示了一个或多个显示或语音播报的待推荐驾驶策略，则根据相应的用户指令执行对应的待推荐驾驶策略。显然，执行的一个或多个待推荐驾驶策略之间不存在执行冲突。
为了保证可以对待推荐策略库进行实时更新，因此在S306之后还可以包括以下步骤：
S307，将执行的至少一个待推荐驾驶策略从待推荐策略库中移除。或者，对执行的至少一个待推荐驾驶策略的执行次数加一，将执行次数大于或等于推荐次数阈值的待推荐驾驶策略从待推荐策略库中移除。
终端设备002可以在确定执行至少一个待推荐驾驶策略后，将相应的待推荐驾驶策略从待推荐策略库移除。
在一些例子中，例如可以将执行的至少一个待推荐驾驶策略在执行完毕后后，立即从待推荐策略库移除。可以理解的是，在该示例中经过移除待推荐驾驶策略后，待推荐策略库中的待推荐驾驶策略均为用户从未使用过(或执行过)的驾驶策略。
在又一些例子中，还可以每个待推荐驾驶策略设置执行次数，例如初始值可以设置为零，表示该待推荐驾驶策略执行了零次。在每次执行待推荐驾驶策略后，可以对相应执行的待推荐驾驶策略的执行次数进行加一。然后对比每个待推荐驾驶策略的执行次数和推荐次数阈值。可以理解的是，推荐次数阈值可以是预先设定的，例如3次、5次等。当然，还可以针对每个待推荐驾驶策略设定单独的推荐次数阈值。推荐次数阈值的具体数值可以根据实际情况进行任意设定，本申请在此不作限定。之后，将执行次数大于或等于推荐次数阈值的待推荐驾驶策略从待推荐策略库中移除。本申请通过设定推荐次数阈值，可以保障将待推荐驾驶策略多推荐几次给用户，以便用户可以通过多次使用以熟悉相应的驾驶策略。避免了部分驾驶策略仅推荐一次，而用户由于不经常使用仍然会不熟悉相应驾驶策略的情况。
目前的一些车载辅助驾驶系统由于并不会推荐用户一些驾驶策略，由于用户并未使用过某些驾驶策略，使得生产厂商或车载系统承包商可以收集的用户数据反馈过少，过少的数据反馈会降低车载辅助驾驶系统的开发。因此，本申请在S306之后，还可以记录用户执行至少一个待推荐驾驶策略时产生的用户数据，并在待推荐驾驶策略执行完毕后，将产生的用户数据全部或部分发送至云服务器，以便生产厂商或车载系统承包商可进行驾驶策略的优化、技术升级等。
图6为本申请实施例提供的另一种车辆驾驶策略推荐方法流程图。
例如图6所示，在S301之前还可以通过接收更新数据包，对待推荐策略库进行更新。因此，图3所示的方法还可以包括以下步骤：
S601，获取更新数据包。
终端设备002可以接收云平台或服务器下发的更新数据包。其中，更新数据包中可以包括：待推荐驾驶策略和与待推荐驾驶策略对应的驾驶场景。
在一个例子中，终端设备002可以通过空中下载(over-the-air，OTA)的方式进行更新。
在一些例子中，更新数据包中还可以包括与待推荐驾驶策略对应的功能引导或说明，用于提供引导或说明该待推荐驾驶策略。例如可以是文字说明、驾驶策略引导流程等。
S602，将更新数据包中的待推荐驾驶策略以及与待推荐驾驶策略对应的驾驶场景添加至待推荐策略库。
终端设备002将S601中获取到的更新数据包进行解析，得到待推荐驾驶策略以及与待推荐驾驶策略对应的驾驶场景，并将待推荐驾驶策略和与待推荐驾驶策略对应的驾驶场景添加至待推荐策略库中。
在一个例子中，例如以表2为例，将更新数据包中的待推荐驾驶策略和与待推荐驾驶策略对应的驾驶场景添加至表2所示出的映射表中。当然，在另一个例子中，该映射表还可以是将表1和表2相结合的映射表，例如表3所示。
Figure PCTCN2022084442-appb-000005
Figure PCTCN2022084442-appb-000006
表3
相应的，更新数据包中还可以包括用于确定驾驶场景的环境信息。当更新数据包中的环境信息与表3中对应驾驶场景的环境信息不同时，可以对表3中的环境信息进行更新，即更新为更新数据包中相应驾驶场景的环境信息。当然，对于表3中没有的驾驶场景，则在更新时可以直接将更新数据包中的待推荐驾驶策略、与待推荐驾驶策略对应的驾驶场景和驾驶场景的环境信息一并添加至表3中。
在一些例子中，若更新的待推荐驾驶策略仍然在待推荐策略库中时，且设置有执行次数，则可以将执行次数归零。若更新的待推荐驾驶策略并不在待推荐策略库中，但是在常规策略库中存在相同的驾驶策略时，若设置有推荐次数阈值，则可以针对该待推荐驾驶策略单独设置对应的推荐次数阈值，并使得推荐次数阈值的数值低于上一次该待推荐驾驶策略对应的推荐次数阈值，同时移除位于常规策略库中相同的驾驶策略。例如，假设某个待推荐驾驶策略已经从待推荐策略库中移除，且上一次位于待推荐策略库中时设定的推荐次数阈值为5次。当终端设备接收到更新数据包后，更新数据包中包含该待推荐驾驶策略，则将该待推荐驾驶策略再次添加至待推荐策略库后，相应的该待推荐驾驶策略的推荐次数阈值可以设定为小于5次的任意数值，例如3次、2次等。由于该待推荐驾驶策略之前已经被用户所熟知，因此可以认为用户可以通过更少的执行次数即可了解和熟悉更新后的该待推荐驾驶策略。
当然，在另一些例子中，还可以直接将更新的待推荐驾驶策略添加至待推荐策略库中，再检视待推荐策略库和常规策略库。并删除位于常规策略库中且同时出现在常规策略库和待推荐策略库中的驾驶策略。其中，常规策略库用于保存被用户所熟知的驾驶策略。用户所熟知的标准可以是该驾驶策略已经向用户推荐过至少一次。
当S602执行完，可以继续执行S301。
可以理解是的，S601和S602的目的是当接收到云平台或服务器的更新数据包后，可以同步更新待推荐策略库，以便更好的将用户不熟悉、不清楚的驾驶策略进行推荐。
图7为本申请实施例提供的一种车辆驾驶策略更新示意图。
例如图7所示，提供了图6中的更新过程。可以看出，当终端设备002接收到云平台或服务器下发的更新数据包后，可以对更新数据包进行解析然后对于其它更新内容，可以根据现有方式进行更新。而对于待推荐驾驶策略，则直接添加至待推荐策略库中。通过图7还可以看出，对于终端设备002而言，具有一个更大的策略库，即车辆驾驶策略库，其中包含有所有的驾驶策略，显然，待推荐策略库仅仅是车辆驾驶策略库中的一个子集。当然，车辆驾 驶策略库还可以包括常规策略库这一子集。
在一个例子中，当终端设备002刚出厂时或是初始状态下，可以默认所有的驾驶策略均为待推荐驾驶策略，并均添加至待推荐策略库中。
图8为本申请实施例提供的一种终端设备结构示意图。
如图8所示，本申请提供了一种终端设备的结构示意图，该终端设备800可以是图2至图7所涉及的终端设备002。该终端设备800包括：通信模块801、解码模块802、分流模块803、待推荐策略库804、传感器模块805、系统数据收集模块806、处理模块807和人机交互模块808。其中，处理模块807还可以包括驾驶场景识别模块8071和匹配模块8072。人机交互模块808还可以包括显示模块8081和语音模块8082。
通信模块801可以是终端设备800的通信端口，可以进行有线或无线通信。例如，可以利用无线通信连接至云平台或服务器，以进行OTA更新，下载更新数据包。
解码模块802用于将通信模块801下载的更新数据包进行解码。
分流模块803用于从解码模块802中解码得到的解码流中识别出待推荐驾驶策略和与待推荐驾驶策略对应的驾驶场景，并将待推荐驾驶策略和与待推荐驾驶策略对应的驾驶场景添加至待推荐策略库804中。
通信模块801、解码模块802、分流模块803和待推荐策略库804共同完成了图6和图7所描述的过程，具体实现方式可以参考图6和图7中相应的描述，在此不再赘述。
传感器模块805可以包括搭载在终端设备800内以及可以与终端设备800进行有线或无线相连接的各种传感器，主要用于采集外环境数据，以便对驾驶场景进行判断。
系统数据收集模块806主要用户采集内环境数据，例如方向盘、啥车、挂挡等操作状态，以便对驾驶场景进行判断。
处理模块807中的驾驶场景识别模块8071主要用于通过传感器模块805和/或系统数据收集模块806获取到的环境信息，对驾驶场景进行识别，以确定出至少一个驾驶场景。
匹配模块8072则用于根据驾驶场景识别模块807确定的驾驶场景，从待推荐策略库804中匹配相应的待推荐驾驶策略。
当匹配到至少一个待推荐驾驶策略时，则通过人机交互模块808中的显示模块8081进行显示，或是通过人机交互模块808中的语音模块8082进行语音播报，以便用户进行选择。其中，显示模块8081例如可以是显示器，语音模块8082例如可以是扬声器、麦克风等。
待推荐策略库804、传感器模块805、系统数据收集模块806、处理模块807和人机交互模块808共同完成了图2至图5D所描述的过程，具体实现方式可以参考图2至图5D中相应的描述，在此不再赘述。
接下来，本申请提供了两种更为具体的示例，对上述图2至图8所描述的方案进行阐述。
示例一，以自动泊车功能作为待推荐驾驶策略为例。
在一些例子中，终端设备可以是在初始状态下或出厂时所携带自动泊车功能。由于在的初始状态下或出厂时默认所有的驾驶策略均为待推荐驾驶策略，因此自动泊车功能可作为待推荐驾驶策略添加至待推荐策略库中。当然，在另一些例子中，终端设备还可以通过接收云平台或服务器发送的更新数据包进行更新，并解析到更新数据包中携带有自动泊车功能，此时可以将自动泊车功能和对应的驾驶场景(也可称为激活条件)添加至待推荐策略库中。例如，终端设备在用户使用了一段时间后，可以接收云平台或服务器发送的推送更新，其中推送更新可以是更新数据包。在一些例子中，更新数据包中还可以携带自动泊车功能的功能引 导/说明，以在启动自动泊车功能时提供引导/说明。
之后，终端设备在工作状态下，可以通过传感器采集各种可能的环境信息，例如车内温度、环境温度、车流速度、车流量、道路标识、环境标识、车辆位置、车载系统的内部数据等。然后根据采集到的环境信息，确定当前终端设备可能所处的驾驶场景。例如，可以通过位置传感器采集终端设备所处的位置位于停车场，以及通过图像传感器采集道路标识/环境标识并识别出停车位信息。还可以根据用户在一定时间范围内的车辆操作识别到用户正在进行倒车操作。可以理解的是，位置位于停车场、停车位信息可以属于外环境数据，而倒车操作可以属于内环境数据。
终端设备可以结合上述采集到外环境数据和内环境数据按照预设的规则，确定终端设备可能所处的至少一个驾驶场景。预设规则例如上述表1或表3所示的环境信息与驾驶场景的映射表。例如，当识别到终端设备位于停车场，并位于停车位附近时，可以确定出待停车场景。此时再结合倒车操作则可以识别到对应的正在泊车入位场景。
终端设备根据确定出的正在泊车入位场景，与待推荐策略库进行匹配，例如表2或表3所示出的驾驶场景与待推荐驾驶策略的映射表。确定是否存在符合确定出的驾驶场景所对应的待推荐驾驶策略。例如，根据表2或表3，确定了待停车场景和正在泊车入位场景均存在对应的待推荐驾驶策略，且均为“自动泊车”。此时，可以将匹配到的“自动泊车”推荐给用户，例如通过终端设备的显示屏进行显示，或是通过扬声器进行语音播报。若采用显示屏显示的方式，可以例如图9所示。如显示“当前检测到驾驶场景符合自动泊车条件，是否启动自动泊车驾驶模式”并提供相应选项，以便用户做出选择。
终端设备通过采集用户输入的用户指令，例如触摸显示屏上的选项、按压物理按键或是通过语音识别关键字等方式识别到用户指令。确定是否执行“自动泊车”这一待推荐驾驶策略。例如当用户点击“是”或是检测到语音关键字“是”、“执行”、“启动自动泊车”等。则表示用户愿意执行“自动泊车”这一待推荐驾驶策略，终端设备则执行“自动泊车”这一待推荐驾驶策略。终端设备例如可以接管用户对车辆的操作，并进行自动泊车。其具体策略执行时的操作可以根据实际情况进行调整，本申请并不做限定。
当“自动泊车”这一待推荐驾驶策略执行完毕后，终端设备上的车载辅助驾驶系统退出，并提示用户。同时可以将“自动泊车”这一待推荐驾驶策略从待推荐策略库中移除，例如移动到常规策略库中。当然在另一些例子中，也可以将“自动泊车”这一待推荐驾驶策略的执行次数进行加一，并检视该待推荐驾驶策略的执行次数是否大于或等于待推荐驾驶策略对应的推荐次数阈值。若待推荐驾驶策略的执行次数大于或等于待推荐驾驶策略对应的推荐次数阈值，则将“自动泊车”这一待推荐驾驶策略从待推荐策略库中移除，并移动到常规策略库中。例如图10所示出的，当满足一定条件时可以将“自动泊车”从待推荐策略库中移到常规策略库中。
示例二，以休息模式作为待推荐驾驶策略为例。
在一些例子中，终端设备可以是在初始状态下或出厂时所携带休息模式。并默认将休息模式作为待推荐驾驶策略添加至待推荐策略库中。当然，也可以是终端设备通过接收云平台或服务器发送的更新数据包，解析到更新数据包中携带有休息模式，并将休息模式添加至待推荐策略库中。
之后，终端设备在工作状态下，通过传感器采集各种可能的环境信息，例如采集到外环境数据和内环境数据。例如，通过图像传感器采集到图像后，通过图像识别技术，识别出用 户的面部姿态、手部姿态以及其它部位的姿态，如口型、面部肌肉的移动情况、眉间距、眼睛的大小、移动等，以及伸展、捂嘴动作等。
终端设备可以结合上述采集到外环境数据和内环境数据按照预设的规则，确定终端设备可能所处的至少一个驾驶场景。预设规则例如上述表1或表3所示的环境信息与驾驶场景的映射表。例如，当识别到口型为张开和/或伴随有捂嘴动作，则可以确定当前用户可能处于疲劳状态，并确定驾驶场景为疲劳驾驶场景。
终端设备根据确定出的疲劳驾驶场景，与待推荐策略库进行匹配，例如表2或表3所示出的驾驶场景与待推荐驾驶策略的映射表。确定是否存在符合确定出的驾驶场景所对应的待推荐驾驶策略。例如，根据表2或表3，确定了疲劳驾驶场景存在对应的待推荐驾驶策略，为“休息模式”。此时，可以将匹配到的“休息模式”推荐给用户，例如通过终端设备的显示屏进行显示，或是通过扬声器进行语音播报。若采用显示屏显示的方式，可以例如图11所示。如显示“当前检测到驾驶员疲劳，是否启动休息驾驶模式。启动后将开启巡航并查找合适位置自动停靠至路边”并提供相应选项，以便用户做出选择。
终端设备通过采集用户输入的用户指令，例如触摸显示屏上的选项、按压物理按键或是通过语音识别关键字等方式识别到用户指令。确定是否执行“休息模式”这一待推荐驾驶策略。例如当用户点击“是”或是检测到语音关键字“是”、“执行”、“启动休息模式”等。则表示用户愿意执行“休息模式”这一待推荐驾驶策略，终端设备则执行“自动泊车”这一待推荐驾驶策略。终端设备例如可以通过车载辅助驾驶系统开启巡航，并在合适位置进行路边停靠。再执行系列参数配置产生相应的车辆动作，如休息模式执行完成后，车辆停靠至路边，并升起车窗、空调开至合适温度、播放舒缓音乐、灯光调节为暖色光、倾斜座椅至预设角度等。其具体策略执行时的操作可以根据实际情况进行调整，本申请并不做限定。
当“休息模式”这一待推荐驾驶策略执行完毕后，终端设备上的车载辅助驾驶系统退出，并提示用户。同时可以将“休息模式”这一待推荐驾驶策略从待推荐策略库中移除，例如移动到常规策略库中。当然也可以将“休息模式”这一待推荐驾驶策略的执行次数进行加一，并检视该待推荐驾驶策略的执行次数是否大于或等于待推荐驾驶策略对应的推荐次数阈值。若待推荐驾驶策略的执行次数大于或等于待推荐驾驶策略对应的推荐次数阈值，则将“休息模式”这一待推荐驾驶策略从待推荐策略库中移除，并移动到常规策略库中。
本申请所涉及的一种车辆驾驶策略推荐方法及装置，通过构建待推荐策略库，将未被使用过或是使用次数较少的驾驶策略作为待推荐驾驶策略添加至待推荐策略库。再采集车辆的环境信息确定当前车辆可能的驾驶场景，并基于驾驶场景确定对应的待推荐驾驶策略，同时推荐给用户。可以提醒用户是否启用被使用过或是使用次数较少的驾驶策略。这种方式可以确保在驾驶策略更新后，车载辅助驾驶系统可以“手把手”的提醒用户至少一次不熟悉的驾驶策略，以确保用户可以了解相应的驾驶策略。避免了用户不知情的情况下导致的部分驾驶策略从未被使用或是使用率偏低的问题。
图12为本申请实施例提供的一种车辆驾驶策略推荐装置示意图。
如图12所示，本申请还提供了一种车辆驾驶策略推荐装置1200。该装置1200可以包括：处理器1210、外部存储器接口1220、内部存储器1221、通用串行总线(un iversa l ser ia l bus，USB)接口1230、充电管理模块1240、电源管理模块1241、电池1242、天线1、天线2、移动通信模块1250、无线通信模块1260、音频模块1270、扬声器1270A、受话器1270B、麦克风1270C、传感器模块1280、按键1290、摄像头1291和显示屏1292等。其中，传感器模块 1280可以包括：压力传感器1280A、陀螺仪传感器1280B、气压传感器1280C、磁传感器1280D、加速度传感器1280E、距离传感器1280F、图像传感器1280G、超声波传感器1280H、温度传感器1280J、触摸传感器1280K、环境光传感器1280L和雷达1280M等。雷达1280M可以包括激光雷达、毫米波雷达等。
可以理解的是，本申请实施例示意的结构并不构成对装置1200的具体限定。装置1200可以包括比图示更多或更少的部件，或者组合某些部件，或者拆分某些部件，或者不同的部件布置。图示的部件可以以硬件，软件或软件和硬件的组合实现。
处理器1210可以是高级精简指令集处理器(advanced reduced instruction set computing machines，ARM)、X86、无内部互锁流水级的微处理器(microprocessor without interlocked piped stages，MIPS)等架构的处理器。处理器1210可以包括一个或多个处理单元，例如：应用处理器(application processor，AP)，调制解调处理器，GPU，图像信号处理器(image signal processor，ISP)，控制器，视频编解码器，数字信号处理器(digital signal processor，DSP)，基带处理器和/或神经网络处理器(neural-network processing unit，NPU)等。其中，不同的处理单元可以是独立的器件，也可以集成在一个或多个处理器中。
控制器可以根据指令操作码和时序信号，产生操作控制信号，完成取指令和执行指令的控制。
处理器1210中还可以设置存储器，用于存储指令和数据。在一些实施例中，处理器1210中的存储器为高速缓冲存储器。该存储器可以保存处理器1210刚用过或循环使用的指令或数据。如果处理器1210需要再次使用该指令或数据，可从所述存储器中直接调用。避免了重复存取，减少了处理器1210的等待时间，因而提高了系统的效率。
在一些实施例中，处理器1210可以包括一个或多个接口。接口可以包括集成电路(inter-integrated circuit，I2C)接口、集成电路内置音频(inter-integrated circuit sound，I2S)接口、脉冲编码调制(pulse code modulation，PCM)接口、通用异步收发传输器(universal asynchronous receiver/transmitter，UART)接口、移动产业处理器接口(mobile industry processor interface，MIPI)，通用输入输出(general-purpose input/output，GPIO)接口、用户标识模块(subscriber identity module，SIM)接口和/或通用串行总线(universal serial bus，USB)接口等。
充电管理模块1240用于从充电器接收充电输入。其中，充电器可以是无线充电器，也可以是有线充电器。
在一些有线充电的实施例中，充电管理模块1240可以通过USB接口1230接收有线充电器的充电输入。在一些无线充电的实施例中，充电管理模块1240可以通过装置1200的无线充电线圈接收无线充电输入。充电管理模块1240为电池1242充电的同时，还可以通过电源管理模块1241为装置1200供电。
装置1200的无线通信功能可以通过天线1，天线2，移动通信模块1250，无线通信模块1260，调制解调处理器以及基带处理器等实现。
移动通信模块1250可以提供应用在装置1200上的包括2G/3G/4G/5G/6G等无线通信的解决方案。无线通信模块1260可以提供应用在装置1200上的包括无线局域网(wireless local area networks，WLAN)、蓝牙(bluetooth，BT)、全球导航卫星系统(global navigation satellite system，GNSS)、调频(frequency modulation，FM)、近距离无线通信技术(near  field communication，NFC)和红外技术(infrared，IR)等无线通信的解决方案。其中，WLAN例如可以是无线保真(wireless fidelity，Wi-Fi)网络。
装置1200通过GPU，显示屏1292，以及应用处理器等实现显示功能。GPU为图像处理的微处理器，连接显示屏1292和应用处理器。GPU用于执行数学和几何计算，用于图形渲染。处理器1210可包括一个或多个GPU，其执行程序指令以生成或改变显示信息。
显示屏1292用于显示图像，视频等。显示屏1292包括显示面板。显示面板可以采用液晶显示屏(liquid crystal display，LCD)、有机发光二极管(organic light-emitting diode，OLED)、有源矩阵有机发光二极体或主动矩阵有机发光二极体(active-matrix organic light emitting diode的，AMOLED)、柔性发光二极管(flex light-emitting diode，FLED)、Miniled、MicroLed、Micro-oLed和量子点发光二极管(quantum dot light emitting diodes，QLED)等。在一些实施例中，装置1200可以包括1个或N个显示屏194，N为大于1的正整数。
装置1200可以通过ISP、摄像头1291、视频编解码器、GPU、显示屏1292以及应用处理器等实现拍摄功能。
摄像头1291用于捕获静态图像或视频。在一些实施例中，装置1200可以包括1个或N’个摄像头1291，N’为大于1的正整数。
外部存储器接口1220可以用于连接外部存储卡，例如Micro SD卡，实现扩展装置1200的存储能力。外部存储卡通过外部存储器接口1220与处理器1210通信，实现数据存储功能。例如将音频，视频等文件保存在外部存储卡中。
内部存储器1221可以用于存储计算机可执行程序代码，可执行程序代码包括指令。内部存储器1221可以包括存储程序区和存储数据区。其中，存储程序区可存储操作系统，至少一个功能所需的应用程序(比如声音播放功能，图像播放功能等)等。存储数据区可存储装置1200使用过程中所创建的数据(比如音频数据等)等。此外，内部存储器1221可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件，闪存器件，通用闪存存储器(universal flash storage，UFS)等。处理器1210通过运行存储在内部存储器1221的指令，和/或存储在设置于处理器中的存储器的指令，执行装置1200的各种功能应用以及数据处理。
装置1200可以通过音频模块1270、扬声器1270A、受话器1270B、麦克风1270C以及应用处理器等实现音频功能。例如音频播放，音频采集等。
扬声器1270A，也称“喇叭”，用于将音频电信号转换为声音信号。麦克风1270C，也称“话筒”，“传声器”，用于将声音信号转换为电信号。
按键1290包括任意可能形式的按键，例如机械按键或触摸式按键等。装置1200可以接收按键输入，确定用户指令。
本申请所提供的装置1200可以实现上述图2至图11中描述的任意一种方法，具体实现方式可以参考述图2至图11的相应描述，在此不再赘述。
本申请通过预先设定待推荐策略库，例如在进行更新是，将更新数据包中的待推荐驾驶策略添加到待推荐策略库中，或是在初始状态下默认所有驾驶策略为待推荐驾驶策略并添加到待推荐策略库中。以便可以通过采集包含外环境数据和内环境数据的环境信息识别驾驶场景，并根据识别到的驾驶场景到待推荐策略库匹配相应的待推荐驾驶策略。当匹配到待推荐驾驶策略后主动向用户推荐匹配搭配的待推荐驾驶策略。使得通过主动与用户交互的方式，能够确保在新的驾驶策略更新后，车载辅助驾驶系统能够确保“手把手”的提醒用户至少一 次新的驾驶策略，确保用户知道更新了对应功能。同时主动交互提醒用户使用新驾驶策略的方式，提升了自动驾驶车辆的使用体验，使得用户能够充分体验自动驾驶车辆的功能。
当然，进一步的，本申请还可以在待推荐策略库内的待推荐驾驶策略被执行预设次数后，移出待推荐策略库。以及同一驾驶策略再次更新，重新调到待推荐策略库。保障了待推荐策略库中仅包含用户不熟悉、不了解的驾驶策略。
本领域普通技术人员应该还可以进一步意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、计算机软件或者二者的结合来实现，为了清楚地说明硬件和软件的可互换性，在上述说明中已经按照功能一般性地描述了各示例的组成及步骤。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分步骤是可以通过程序来指令处理器完成，所述的程序可以存储于计算机可读存储介质中，所述存储介质是非短暂性(英文：non-transitory)介质，例如随机存取存储器，只读存储器，快闪存储器，硬盘，固态硬盘，磁带(英文：magnetic tape)，软盘(英文：floppy disk)，光盘(英文：optical disc)及其任意组合。
以上所述，仅为本申请较佳的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到的变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应该以权利要求的保护范围为准。

Claims (14)

  1. 一种车辆驾驶策略推荐方法，其特征在于，所述方法应用于终端设备，所述方法包括：
    采集至少一个环境信息，所述环境信息包括外环境数据和/或内环境数据；
    根据所述至少一个环境信息，确定至少一个驾驶场景；
    将所述至少一个驾驶场景与待推荐策略库进行匹配，其中，所述待推荐策略库包括驾驶场景与待推荐驾驶策略的对应关系；
    当匹配有至少一个待推荐驾驶策略时，将所述至少一个待推荐驾驶策略进行显示，以便根据用户指令执行一个或多个显示的待推荐驾驶策略。
  2. 如权利要求1所述的方法，其特征在于，所述在采集至少一个环境信息之前，所述方法还包括：
    获取更新数据包，所述更新数据包包括待推荐驾驶策略以及与所述待推荐驾驶策略对应的驾驶场景；
    将所述待推荐驾驶策略以及与所述待推荐驾驶策略对应的驾驶场景添加至所述待推荐策略库。
  3. 如权利要求1或2所述的方法，其特征在于，所述待推荐驾驶策略包括优先级信息；
    所述将所述至少一个待推荐驾驶策略进行显示，包括：
    根据所述优先级信息，将优先级最高的至少一个待推荐驾驶策略进行显示。
  4. 如权利要求3所述的方法，其特征在于，所述驾驶场景包括单一驾驶场景和复合驾驶场景，所述复合驾驶场景对应待推荐驾驶策略的优先级高于所述单一驾驶场景对应待推荐驾驶策略的优先级。
  5. 如权利要求1-4任意一项所述的方法，其特征在于，所述根据用户指令执行一个或多个显示的待推荐驾驶策略，包括：
    若多个待推荐驾驶策略存在执行冲突，则根据所述用户指令执行多个待推荐驾驶策略中的部分待推荐驾驶策略，其中，执行的所述部分待推荐驾驶策略不存在执行冲突。
  6. 如权利要求1-5任意一项所述的方法，其特征在于，所述方法还包括：
    将执行的所述至少一个待推荐驾驶策略从所述待推荐策略库中移除；或，
    对执行的所述至少一个待推荐驾驶策略的执行次数加一，其中，每个待推荐驾驶策略的执行次数初始值为零；
    将所述执行次数大于或等于推荐次数阈值的待推荐驾驶策略从所述待推荐策略库中移除。
  7. 一种车辆驾驶策略推荐装置，其特征在于，所述装置为终端设备，所述装置包括：
    传感器，用于采集至少一个环境信息，所述环境信息包括外环境数据和/或内环境数据；
    处理器用于与存储器耦合，以及读取并执行存储在所述存储器中的指令；
    当所述处理器运行时执行所述指令，使得所述处理器用于根据所述至少一个环境信息，确定至少一个驾驶场景；将所述至少一个驾驶场景与待推荐策略库进行匹配，其中，所述待推荐策略库包括驾驶场景与待推荐驾驶策略的对应关系；当匹配有至少一个待推荐驾驶策略时，控制显示器将所述至少一个待推荐驾驶策略进行显示，以便根据用户指示执行一个或多个显示的待推荐驾驶策略。
  8. 如权利要求7所述的装置，其特征在于，所述装置还包括：
    接收器，用于获取更新数据包，所述更新数据包包括待推荐驾驶策略以及与所述待推荐驾驶策略对应的驾驶场景；
    处理器还用于，将所述待推荐驾驶策略以及与所述待推荐驾驶策略对应的驾驶场景添加至所述待推荐策略库。
  9. 如权利要求7或8所述的装置，其特征在于，所述待推荐驾驶策略包括优先级信息；
    所述处理器还用于：
    根据所述优先级信息，控制所述显示器将优先级最高的至少一个待推荐驾驶策略进行显示。
  10. 如权利要求9所述的装置，其特征在于，所述驾驶场景包括单一驾驶场景和复合驾驶场景，所述复合驾驶场景对应待推荐驾驶策略的优先级高于所述单一驾驶场景对应待推荐驾驶策略的优先级。
  11. 如权利要求7-10任意一项所述的装置，其特征在于，所述接收器还用于：接收用户指令；
    所述处理器还用于：
    若多个待推荐驾驶策略存在执行冲突，则根据所述用户指令执行多个待推荐驾驶策略中的部分待推荐驾驶策略，其中，执行的所述部分待推荐驾驶策略不存在执行冲突。
  12. 如权利要求7-11任意一项所述的装置，其特征在于，所述处理器还用于：
    将执行的所述至少一个待推荐驾驶策略从所述待推荐策略库中移除；或，
    对执行的所述至少一个待推荐驾驶策略的执行次数加一，其中，每个待推荐驾驶策略的执行次数初始值为零；
    将所述执行次数大于或等于推荐次数阈值的待推荐驾驶策略从所述待推荐策略库中移除。
  13. 一种计算机可读存储介质，所述计算机可读存储介质中存储有指令，其特征在于，当所述指令在终端上运行时，使得所述终端执行如权利要求1-6任意一项所述的方法。
  14. 一种包含指令的计算机设备，当其在终端上运行时，使得所述终端执行如权利要求1-6中的任意一项所述的方法。
PCT/CN2022/084442 2021-04-26 2022-03-31 一种车辆驾驶策略推荐方法及装置 WO2022228024A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP22794496.4A EP4328765A1 (en) 2021-04-26 2022-03-31 Method and apparatus for recommending vehicle driving strategy
US18/494,519 US20240070213A1 (en) 2021-04-26 2023-10-25 Vehicle driving policy recommendation method and apparatus

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110454338.4 2021-04-26
CN202110454338.4A CN115248889A (zh) 2021-04-26 2021-04-26 一种车辆驾驶策略推荐方法及装置

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/494,519 Continuation US20240070213A1 (en) 2021-04-26 2023-10-25 Vehicle driving policy recommendation method and apparatus

Publications (1)

Publication Number Publication Date
WO2022228024A1 true WO2022228024A1 (zh) 2022-11-03

Family

ID=83697476

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/084442 WO2022228024A1 (zh) 2021-04-26 2022-03-31 一种车辆驾驶策略推荐方法及装置

Country Status (4)

Country Link
US (1) US20240070213A1 (zh)
EP (1) EP4328765A1 (zh)
CN (1) CN115248889A (zh)
WO (1) WO2022228024A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150317337A1 (en) * 2014-05-05 2015-11-05 General Electric Company Systems and Methods for Identifying and Driving Actionable Insights from Data
CN111152790A (zh) * 2019-12-29 2020-05-15 的卢技术有限公司 一种基于使用场景的多设备交互车载抬头显示方法及系统
US20200211719A1 (en) * 2018-10-08 2020-07-02 Cerner Innovation, Inc. Intelligent touch care corresponding to a patient reporting a change in condition
CN111605555A (zh) * 2020-05-15 2020-09-01 腾讯科技（深圳）有限公司 车辆驾驶策略的推荐方法、装置、介质及电子设备
CN112477878A (zh) * 2019-09-11 2021-03-12 北京百度网讯科技有限公司 自动驾驶车辆的驾驶决策共享方法、装置、设备和介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150317337A1 (en) * 2014-05-05 2015-11-05 General Electric Company Systems and Methods for Identifying and Driving Actionable Insights from Data
US20200211719A1 (en) * 2018-10-08 2020-07-02 Cerner Innovation, Inc. Intelligent touch care corresponding to a patient reporting a change in condition
CN112477878A (zh) * 2019-09-11 2021-03-12 北京百度网讯科技有限公司 自动驾驶车辆的驾驶决策共享方法、装置、设备和介质
CN111152790A (zh) * 2019-12-29 2020-05-15 的卢技术有限公司 一种基于使用场景的多设备交互车载抬头显示方法及系统
CN111605555A (zh) * 2020-05-15 2020-09-01 腾讯科技（深圳）有限公司 车辆驾驶策略的推荐方法、装置、介质及电子设备

Also Published As

Publication number Publication date
CN115248889A (zh) 2022-10-28
US20240070213A1 (en) 2024-02-29
EP4328765A1 (en) 2024-02-28

Similar Documents

Publication Publication Date Title
US11314389B2 (en) Method for presenting content based on checking of passenger equipment and distraction
US9020566B2 (en) Vehicle on-board unit and mobile device linkage system
CN112861638A (zh) 一种投屏方法及装置
US20240086476A1 (en) Information recommendation method and related device
US11325473B2 (en) Electronic device including display and operating method thereof
WO2022267279A1 (zh) 一种数据标注方法及装置、电子设备和存储介质
WO2022142331A1 (zh) 车载显示屏的控制方法及装置、电子设备和存储介质
WO2022228024A1 (zh) 一种车辆驾驶策略推荐方法及装置
CN112667290A (zh) 指令管理方法、装置、设备及计算机可读存储介质
WO2023036233A1 (zh) 一种控制方法、装置、设备及存储介质
WO2023169448A1 (zh) 一种感知目标的方法和装置
EP4365733A1 (en) Management system, method and apparatus, and device and storage medium
WO2023284355A9 (zh) 信息处理方法、装置、系统、存储介质和电子设备
CN112703128B (zh) 显示控制方法及终端设备
CN106098066B (zh) 语音识别方法及装置
WO2017206133A1 (zh) 语音识别方法及装置
CN113791843A (zh) 一种执行方法、装置、设备及存储介质
US20220078337A1 (en) Operation control device, imaging device, and operation control method
KR102371513B1 (ko) 대화 시스템 및 대화 처리 방법
CN113534780B (zh) 一种遥控泊车参数及功能定义方法、汽车及可读存储介质
WO2023241185A1 (zh) 人机交互方法和装置
WO2024078419A1 (zh) 语音交互方法、语音交互装置和电子设备
KR102396343B1 (ko) 전자 장치의 움직임과 관련된 상태의 변화에 기반하여 데이터를 전송하는 방법 및 장치
WO2024093648A1 (zh) 一种多指令执行的方法、电子设备、装置和运载工具
WO2024067052A1 (zh) 投屏显示方法、电子设备及系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22794496

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2022794496

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2022794496

Country of ref document: EP

Effective date: 20231120