Recommended Control Method, Device, Electronic Device, System and Storage Medium for a Vehicle

Abstract

An embodiment of the present invention discloses a recommended control method, device, electronic device, system and storage medium for a vehicle. The method includes: obtaining a vehicle control portrait of a driver of the vehicle from a portrait server; extracting historical control data of a target component of the vehicle from the vehicle control portrait, inputting the current scene information, historical scene information and historical control scheme corresponding to the historical scene information of the target component into a scheme recommendation model to obtain a candidate control scheme for the target component and the recommendation degree of the candidate control scheme; determining a user weight corresponding to the current scene information of the target component; determining the user acceptance degree of the candidate control scheme according to the recommendation degree of the candidate control scheme of the target component and the user weight corresponding to the current scene information of the target component, and determining a recommendation strategy for the candidate control scheme according to the user acceptance degree. The method of the embodiment of the present invention improves the accuracy of the candidate control scheme recommended for the user and further improves the user experience.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of intelligent recommendation, and in particular, to a method, device, electronic device, system and storage medium for recommending and controlling a vehicle. Background Art

[0002] With the continuous development and progress of science and technology, intelligent connected vehicles have become increasingly common. Intelligent connected vehicles can recommend driving behaviors (such as driving mode, driving route, adjusting air conditioner temperature and seat mode, etc.) for users while driving.

[0003] In the existing vehicle networking intelligent recommendation system, the entire recommendation system is constructed through a manually designed recommendation logic expression. This method relies on the guesswork of designers to recommend control schemes for vehicle components for users. This method does not pay attention to the real intentions of users, so it cannot achieve true intelligent recommendation and reduces the user experience. Summary of the Invention

[0004] The present invention provides a method, device, electronic device, system and storage medium for recommending and controlling a vehicle, which can recommend reliable and accurate control schemes for vehicle components for drivers.

[0005] In a first aspect, an embodiment of the present invention provides a method for recommending and controlling a vehicle, including:

[0006] Obtaining a vehicle control portrait of the driver of the vehicle from a portrait server;

[0007] Extracting historical control data of a target component of the vehicle from the vehicle control portrait, where the historical control data includes historical scenario information and a historical control scheme corresponding to the historical scenario information;

[0008] Inputting the current scenario information of the target component, the historical scenario information and the historical control scheme corresponding to the historical scenario information into a scheme recommendation model to obtain a candidate control scheme for the target component and a recommendation degree of the candidate control scheme;

[0009] Determining a user weight corresponding to the current scenario information of the target component;

[0010] Determining an acceptance degree of the candidate control scheme by the user according to the recommendation degree of the candidate control scheme of the target component and the user weight corresponding to the current scenario information of the target component, and determining a recommendation strategy for the candidate control scheme according to the acceptance degree.

[0011] In a second aspect, an embodiment of the present invention further provides a device for recommending and controlling a vehicle, including:

[0012] A data acquisition module, configured to acquire a vehicle control portrait of a driver of the vehicle from a portrait server;

[0013] A data extraction module, configured to extract historical control data of a target component of the vehicle from the vehicle control portrait, where the historical control data includes historical scenario information and a historical control scheme corresponding to the historical scenario information;

[0014] A scheme determination module, configured to input the current scenario information of the target component, the historical scenario information, and the historical control scheme corresponding to the historical scenario information into a scheme recommendation model to obtain a candidate control scheme for the target component and a recommendation degree of the candidate control scheme;

[0015] A weight determination module, configured to determine a user weight corresponding to the current scenario information of the target component;

[0016] A strategy determination module, configured to determine an acceptance degree of the candidate control scheme according to the recommendation degree of the candidate control scheme of the target component and the user weight corresponding to the current scenario information of the target component, and determine a recommendation strategy for the candidate control scheme according to the acceptance degree;

[0017] In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes:

[0018] One or more processors;

[0019] A memory, configured to store one or more programs;

[0020] When the one or more programs are executed by the one or more processors, the one or more processors implement the recommended control method for a vehicle provided in any embodiment of the present invention.

[0021] In a fourth aspect, an embodiment of the present invention further provides a recommended control system for a vehicle, where the recommended control system for the vehicle includes a vehicle, a portrait server, and an electronic device configured to implement the recommended control method for a vehicle provided in any embodiment of the present invention when executed.

[0022] In a fifth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the recommended control method for a vehicle provided in any embodiment of the present invention is implemented.

[0023] In an embodiment of the present invention, a vehicle control image of a driver of a vehicle can be obtained from an image server; historical control data of a target component of the vehicle is extracted from the vehicle control image, and the historical control data includes historical scene information and a historical control scheme corresponding to the historical scene information; the current scene information, the historical scene information, and the historical control scheme corresponding to the historical scene information of the target component are input into a scheme recommendation model to obtain a candidate control scheme for the target component and the recommendation degree of the candidate control scheme; a user weight corresponding to the current scene information of the target component is determined; according to the recommendation degree of the candidate control scheme of the target component and the user weight corresponding to the current scene information of the target component, the user acceptance degree of the candidate control scheme is determined, and a recommendation strategy for the candidate control scheme is determined according to the user acceptance degree. That is, the method of the embodiment of the present invention can extract the historical control data of the target component of the vehicle from the vehicle control image, paying attention to the information on the control of the target component by the driver when using the vehicle before; further correcting the candidate control scheme by using the user weight to obtain the user acceptance degree of the candidate control scheme, being able to pay attention to the control information of the target component selected by the driver himself from the historical control data, making the determined candidate control scheme of the target component more in line with the user's wishes, improving the accuracy of the candidate control scheme recommended for the user, and further improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a flowchart of a recommended control method for a vehicle provided by an embodiment of the present invention;

[0025] Figure 2 It is a flowchart of another recommended control method for a vehicle provided by an embodiment of the present invention;

[0026] Figure 3 It is a flowchart of sending a general image to a recommendation server provided by an embodiment of the present invention;

[0027] Figure 4 It is a flowchart of recommending a candidate control scheme for a vehicle provided by an embodiment of the present invention;

[0028] Figure 5 It is a schematic structural diagram of a recommended control device for a vehicle provided by an embodiment of the present invention;

[0029] Figure 6 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention;

[0030] Figure 7 It is a schematic structural diagram of a recommended control system for a vehicle provided by an embodiment of the present invention;

[0031] Figure 8 It is a flowchart of a vehicle control system provided by an embodiment of the present invention to provide a candidate control scheme to a user. Detailed implementation manners

[0032] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the present invention, rather than limiting the present invention. In addition, it should be noted that, for the sake of description, only parts related to the present invention rather than all structures are shown in the accompanying drawings.

[0033] Figure 1 FIG. is a flowchart of a recommended control method for a vehicle provided by an embodiment of the present invention. This embodiment can recommend a reliable and accurate solution for controlling vehicle components to a driver. This method can be executed by a recommended control device for a vehicle in an embodiment of the present invention, and this device can be implemented in a software and / or hardware manner. In a specific embodiment, this device can be integrated in an electronic device, such as a computer, a server, etc. When the electronic device is a server, this server can be a recommended server. The following embodiments will be described by taking this device integrated in an electronic device as an example. The recommended control method for a vehicle provided by this embodiment specifically includes the following steps:

[0034] Step 101: Obtain a vehicle control portrait of a driver of the vehicle from a portrait server.

[0035] Among them, the portrait server stores vehicle control portraits of all drivers who have used the vehicle. The vehicle control portrait includes the identification information of the driver and the historical control data of each component of the vehicle when the driver uses the vehicle. The identification information of the driver can be the driver's mobile phone number, the driver's user name, the facial information pre-stored by the driver in the server, etc. The portrait server can identify different drivers according to the identification information of the driver. The historical control data of each component of the vehicle by the driver includes information such as the time, weather, destination reached, driving route to the destination, driving mode selected by the driver, air-conditioning mode selected by the driver, and seat adjustment mode selected by the driver when the driver uses the vehicle. Specifically, when the driver uses the vehicle, the portrait server can obtain the identification information of the driver, query the vehicle control portrait of the driver according to the identification information of the driver, and send the vehicle control portrait of the driver to the recommended server. For example, when the driver starts to use the vehicle, the vehicle's display screen can prompt the driver whether to perform face recognition. When the driver selects to agree, the in-vehicle camera can take a facial photo of the driver to obtain the driver's face image. After obtaining the driver's face image, the camera sends the face image to the portrait server. The portrait server queries the vehicle control portrait corresponding to the face image information according to the face image information of the driver, and sends the vehicle control portrait to the recommended server. Further, the recommended server can obtain the vehicle control portrait of the driver of the vehicle from the portrait server.

[0036] Step 102: Extract the historical control data of the target component of the vehicle from the vehicle control portrait. The historical control data includes historical scenario information and the historical control scheme corresponding to the historical scenario information.

[0037] Among them, the target component of the vehicle is a vehicle component that the recommendation server provides to the driver and needs to be functionally controlled. Such as the navigation and positioning system in the vehicle, the seat mode adjustment component, the air-conditioning mode adjustment component, etc. The historical control data includes historical scenario information and the historical control scheme corresponding to the historical scenario information. Among them, the historical scenario information includes information such as the time, weather, destination information, location of the vehicle, and whether there is someone in the co-pilot when the driver uses the vehicle. The historical control scheme corresponding to the historical scenario information includes the specific scheme for the driver to functionally control the target component under the historical scenario information. Specifically, after the recommendation server obtains the vehicle control portrait of the driver of the vehicle from the portrait server, it extracts the historical control data of the target component of the vehicle from the vehicle control portrait.

[0038] For example, when the driver starts using the vehicle, the portrait server sends the vehicle control portrait of the driver to the recommendation server according to the driver's identification information. The historical control data of the driver's control of each component of the vehicle in the vehicle control portrait includes: 1) Time: 8:20, the co-pilot is A, the weather condition is normal, the location of the vehicle: at the driver's home, seat recommendation received. 2) Time: 9:12, the co-pilot is A, the weather condition is normal, the location of the vehicle: at the driver's home, seat recommendation received. 3) 20:13, no co-pilot, the weather condition is normal, the location of the vehicle: at the driver's workplace, seat recommendation received. 4) 9:20, no co-pilot, the weather condition is hot, the location of the vehicle: at the driver's workplace, air-conditioning mode recommendation received. 5) 20:34, no co-pilot, the weather condition is normal, the location of the vehicle: at the driver's workplace, destination recommendation received. Assuming that the target component is the component for controlling the seat mode, the historical control data of the target component is: 1) Time: 8:20, the co-pilot is A, the weather condition is normal, the location of the vehicle: at the driver's home, seat recommendation received. 2) Time: 9:12, the co-pilot is A, the weather condition is normal, the location of the vehicle: at the driver's home, seat recommendation received. 3) 20:13, no co-pilot, the weather condition is normal, the location of the vehicle: at the driver's workplace, seat recommendation received.

[0039] Step 103: Input the current scenario information, historical scenario information, and the historical control scheme corresponding to the historical scenario information of the target component into the scheme recommendation model to obtain the candidate control scheme of the target component and the recommendation degree of the candidate control scheme.

[0040] Among them, the current scenario information of the target component includes information such as the current time, weather, destination information, the location of the vehicle, and whether there is a passenger in the co-pilot. The solution recommendation model can be a prediction model. The prediction model can calculate the candidate control solution of the target component and the recommendation degree of the candidate control solution based on the current scenario information, historical scenario information of the target component, and the historical control solution corresponding to the historical scenario information. For example, the GBRT combined optimization prediction model (Gradient Boosting Regression Tree), the GBRT model consists of multiple decision trees, and the output results of all trees are accumulated to obtain the final output result. The candidate control solution is the control solution that should be recommended to the user calculated by the prediction model, and the recommendation degree of the candidate control solution is the possibility that the user will accept the candidate control solution calculated by the solution recommendation model. Specifically, after inputting the current scenario information, historical scenario information of the target component, and the historical control solution corresponding to the historical scenario information into the solution recommendation model, the solution recommendation model can calculate to obtain the candidate control solution of the target component and the recommendation degree of the candidate control solution.

[0041] For example, the target component is a component for controlling the seat mode. The current scenario information of the target component is as follows: time: 20:10, location of the vehicle: at the unit, there is co-pilot A, and the weather condition is normal. The historical scenario information of the target component and the historical control solution corresponding to the historical scenario information are as follows: 1) time: 8:20, its co-pilot is A, the weather condition is normal, location of the vehicle: at the driver's home, and seat recommendation has been received. 2) time: 9:12, its co-pilot is A, the weather condition is normal, location of the vehicle: at the driver's home, and seat recommendation has been received. 3) time: 20:13, there is no co-pilot, the weather condition is normal, location of the vehicle: at the driver's workplace, and seat recommendation has been received. Then, input the current scenario information, historical scenario information of the target component, and the historical control solution corresponding to the historical scenario information into the GBRT model. The GBRT model calculates through multiple decision trees, and accumulates the output results of all trees to obtain the final candidate control solution: recommend adjusting the seat mode to mode A for the user, and the recommendation degree is 0.7.

[0042] Step 104: Determine the user weight corresponding to the current scenario information of the target component.

[0043] Among them, according to the vehicle control data of the driver in the image server and the current scene information, the user weight corresponding to the current scene information of the target component can be determined. Specifically, when there is matching information between the current scene information and the historical scene information, and the driver has accepted the control scheme of the target component recommended by the recommendation server, the user weight corresponding to the current scene information can be generated. For example, the historical scene includes the time when the driver is using the vehicle: 12:20, hot weather, destination: the driver's workplace, the location of the vehicle: the driver's residence, and the user has accepted the recommendation of Scheme A. The current scene information is 12:20, cold weather, the driver's workplace, and the location of the vehicle: the driver's residence. By matching the historical scene information with the current scene information where the driver is located, the current scene information that matches the historical scene information is obtained as 12:20, destination: the driver's workplace, and the location of the vehicle: the driver's residence. The importance levels of the successfully matched current scene information are added together to obtain the user weight. The user weight can be used to correct the recommendation degree of the candidate control scheme of the target component. The control information of the target component selected by the driver himself can be noticed from the historical control data, further making the determined candidate control scheme of the target component more in line with the user's wishes and improving the user experience.

[0044] Step 105: Determine the user acceptance degree of the candidate control scheme according to the recommendation degree of the candidate control scheme of the target component and the user weight corresponding to the current scene information of the target component, and determine the recommendation strategy of the candidate control scheme according to the user acceptance degree.

[0045] Among them, the user acceptance level of a candidate control solution represents the likelihood that a driver can accept the candidate control solution. The recommendation strategy for the candidate control solution includes recommending or not recommending. The candidate control solution for the target component and the recommendation level of the candidate control solution are obtained through a solution recommendation model. The solution recommendation model can calculate the candidate control solution for the target component and the recommendation level of the candidate control solution based on the current scenario information, historical scenario information, and historical control solutions corresponding to the historical scenario information of the target component. However, the solution recommendation model does not pay attention to the control information of the target component selected by the driver himself during the calculation process, and the recommendation level of the candidate control solution obtained only based on the solution recommendation model is not accurate enough. Therefore, after obtaining the recommendation level of the candidate control solution for the target component, the recommendation level of the candidate control solution can be multiplied by the user weight corresponding to the current scenario information of the target component to obtain the user acceptance level of the candidate control solution. Specifically, when the user acceptance level is relatively large, it means that the driver is very likely to accept the recommendation of the candidate control solution, and then the recommendation strategy for the candidate control solution is determined to be recommend. When the user acceptance level is relatively small, it means that the driver is very likely to not accept the recommendation of the candidate control solution, and then the recommendation strategy for the candidate control solution is determined to be not recommend.

[0046] This solution obtains the vehicle control portrait of the driver of the vehicle from the portrait server; extracts the historical control data of the target component of the vehicle from the vehicle control portrait, and the historical control data includes historical scenario information and historical control solutions corresponding to the historical scenario information; inputs the current scenario information, historical scenario information, and historical control solutions corresponding to the historical scenario information of the target component into the solution recommendation model to obtain the candidate control solution for the target component and the recommendation level of the candidate control solution; determines the user weight corresponding to the current scenario information of the target component; determines the user acceptance level of the candidate control solution according to the recommendation level of the candidate control solution for the target component and the user weight corresponding to the current scenario information of the target component, and determines the recommendation strategy for the candidate control solution according to the user acceptance level. This solution pays attention to the information on the driver's control of the target component when using the vehicle before; further corrects the candidate control solution using the user weight to obtain the user acceptance level of the candidate control solution, can pay attention to the control information of the target component selected by the driver himself from the historical control data, makes the determined candidate control solution for the target component more in line with the user's wishes, improves the accuracy of the candidate control solution recommended for the user, and further improves the user experience.

[0047] Figure 2 It is the flowchart of another vehicle recommendation control method provided by an embodiment of the present invention. This embodiment further refines the vehicle recommendation control method, such as Figure 2 shown. The refined vehicle recommendation control method mainly includes the following steps:

[0048] Step 201: Obtain the vehicle control image of the driver of the vehicle from the image server.

[0049] Step 202: Extract the historical control data of the target component of the vehicle from the vehicle control image. The historical control data includes historical scenario information and the historical control scheme corresponding to the historical scenario information.

[0050] Step 203: Input the current scenario information, historical scenario information, and the historical control scheme corresponding to the historical scenario information of the target component into the scheme recommendation model to obtain multiple intermediate control schemes for the target component and the recommendation degree of each intermediate control scheme in the intermediate control schemes.

[0051] Among them, the current scenario information of the target component includes information such as the current time, weather, destination information, the location of the vehicle, and whether there is someone in the co-pilot. The scheme recommendation model can calculate the candidate control scheme and the recommendation degree of the candidate control scheme for the target component based on the current scenario information, historical scenario information, and the historical control scheme corresponding to the historical scenario information of the target component. Specifically, after obtaining the current scenario information, historical scenario information, and historical scenario information of the target component, through the calculation of the regression prediction algorithm, multiple intermediate control schemes can be determined. At the same time, according to the current scenario information, historical scenario information, and historical scenario information of the target component, the corresponding recommendation degree can be generated for each intermediate control scheme.

[0052] Step 204: Use the intermediate control scheme with the highest recommendation degree among the multiple intermediate control schemes as the candidate control scheme for the target component to obtain the candidate control scheme for the target component and the recommendation degree of the candidate control scheme.

[0053] Specifically, after obtaining the multiple intermediate control schemes for the target component and the recommendation degree of each intermediate control scheme in the intermediate control schemes, sort the intermediate control schemes according to the recommendation degree of each intermediate control scheme, and select the intermediate control scheme with the highest recommendation degree as the candidate control scheme. For example, the current scenario information of the target component includes A, B, C, D, E, the historical scenario information and the historical control scheme corresponding to the historical scenario information include A, F, C, D, E, scheme O, H, B, I, D, E, scheme P, A, B, J, D, E, scheme Q, etc. The scheme recommendation model obtains two intermediate control schemes, scheme O and scheme Q, through the calculation of the regression prediction algorithm. Suppose according to the calculation of the file recommendation model, the recommendation degree of scheme O is 0.7, and the recommendation degree of scheme Q is 0.6. Then select scheme O as the candidate control scheme, and the recommendation degree of the candidate control scheme is 0.7.

[0054] Step 205: Obtain the importance degree of each dimension information in the preset historical scenario information.

[0055] Among them, the importance of each dimension information can be set according to specific requirements and the actual environment. For example, the historical scenario information includes dimension information such as weather dimension information, time dimension information, location dimension information, co-pilot information, and whether in a parking space. For the target component, different dimension information has different importance levels. For example, when the target component is a component for controlling the air-conditioning mode, the weather dimension information and the time dimension information are more important than other dimension information (regardless of the driver's destination, in a hot weather condition, the driver is likely to accept the recommendation to turn on the air conditioner). When the target component is a component for controlling the navigation route, the time dimension information and the location dimension information are more important than other dimension information. Further, obtain the importance of each dimension information in the preset historical scenario information.

[0056] Step 206: Based on the importance of each dimension information and the historical scenario information, determine the user weight corresponding to the current scenario information of the target component.

[0057] Among them, the user weight can be used to correct the recommendation degree of the candidate control scheme of the target component obtained by the solution recommendation model, so that the determined candidate control scheme of the target component is more in line with the user's mind. In the embodiment of this solution, optionally, determining the user weight corresponding to the current scenario information of the target component based on the importance of each dimension information and the historical scenario information includes the following steps A1 - step A2:

[0058] Step A1: Match each dimension information in the current scenario information with each dimension information in the historical scenario information to obtain the current scenario dimension information in the current scenario information that matches each dimension information in the historical scenario information.

[0059] Among them, the historical scenario information and the current scenario information include each dimension information, such as weather dimension information, time dimension information, location dimension information, co-pilot information, and whether in a parking space. Specifically, starting from the dimension information with the greatest importance, each dimension information in the current scenario information can be matched with each dimension information in the historical scenario information, and the current scenario dimension information in the current scenario information that matches each dimension information in the historical scenario information can be screened out.

[0060] Exemplarily, the historical scenario information and the corresponding historical control solution are as follows: 1) Time: 8:20, the co-pilot is A, the weather condition is normal, the location of the vehicle: at the driver's home, the vehicle is in the parking space, and has received seat recommendations. 2) Time: 9:12, the co-pilot is A, the weather condition is normal, the location of the vehicle: at the driver's home, the vehicle is in the parking space, and has received seat recommendations. 3) Time: 20:13, no co-pilot, the weather condition is normal, the location of the vehicle: at the driver's workplace, the vehicle is in the parking space, and has received seat recommendations. The current scenario information is: Time: 20:10, there is co-pilot A, the weather condition is normal, the location of the vehicle: at the driver's workplace, the vehicle is in the parking space. Assume the target component is seat recommendation, and the importance levels of each dimension information in the historical scenario information of the pre-set seat recommendation are shown in Table 1 below:

[0061] Dimension information Degree of importance Time 0.32 Location of the vehicle 0.27 Passenger in the co-driver seat 0.22 Weather 0.05 Whether in a parking space 0.14

[0062] Table 1

[0063] Then, starting from the dimension information with the highest importance level (time dimension information), match each dimension information in the current scenario information with that in the historical scenario information. From the time: 20:10 in the current scenario information, it can be matched with the time: 20:13 in the historical scenario information (matching is successful if the time difference does not exceed 30 minutes). Further, the current scenario information can be matched with other dimension information in 3) of the historical data information. Finally, the current scenario dimension information that matches each dimension information in the historical scenario information can be screened out as: weather dimension information, location of the vehicle, and whether it is in the parking space.

[0064] Step A2: Add up the importance levels of each dimension information in the historical scenario information that matches the current scenario dimension information to determine the user weight corresponding to the current scenario information of the target component.

[0065] After obtaining the current scenario dimension information that matches each dimension information in the historical scenario information in the current scenario information, add up its importance levels to obtain the user weight corresponding to the current scenario information of the target component. For example, as described in Step A1 above, the current scenario dimension information that finally matches each dimension information in the historical scenario information in the current scenario information is: weather dimension information, location of the vehicle, and whether it is in the parking space. According to the importance levels of each dimension information in the historical scenario information recorded in Table 1, the user weight corresponding to the current scenario information of the target component can be determined as: 0.32 + 0.27 + 0.05 + 0.14 = 0.78.

[0066] According to the above steps, the control information of the target component selected by the driver himself can be concerned from the historical control data, and the user weight can be accurately calculated to correct the recommendation degree of the candidate control model.

[0067] Step 207: Multiply the recommendation degree of the candidate control solution by the user weight corresponding to the current scenario information of the target component to determine the user acceptance degree of the candidate control solution.

[0068] Among them, the user weight can be used to correct the recommendation degree of the candidate control solution of the target component, so that the determined candidate control solution of the target component is more in line with the user's wishes. Specifically, the correction coefficient of the recommendation degree of the candidate control solution by the user weight can be preset according to specific requirements and actual situations. The correction coefficient can represent the proportion of the user weight in the recommended control method of the entire vehicle. For example, if the correction coefficient is 0.1, it means that the proportion of the user weight in the recommended control method of the entire vehicle is 0.1. Specifically, because the user weight is corrected based on the candidate control solution of the target component and the recommendation degree of the candidate control solution, when calculating the user acceptance degree of the candidate control solution, the self - proportion of the recommendation degree of the candidate control solution needs to be added to the user weight. Among them, the self - proportion of the recommendation degree of the candidate control solution is 1. For example, the user weight is: 0.32 + 0.27 + 0.05 + 0.14 = 0.78, the correction coefficient is 0.1, and the recommendation degree of the candidate control solution is 0.7, then the user acceptance degree of the candidate control solution is (0.1×0.78 + 1)×0.7 = 0.7546.

[0069] Step 208: Perform data analysis on all historical control data in the portrait server to obtain the user recommendation threshold.

[0070] Among them, the user's recommendation threshold is used to judge whether the user will accept the current recommended solution. And the user's recommendation threshold is not for a certain user. The user's recommendation threshold is calculated based on all historical control data in the portrait server. Therefore, according to the user's recommendation threshold, it can be judged whether the user will accept the current recommended solution. For example, after analyzing all historical control data in the portrait server, it is obtained that when the recommendation server recommends a candidate control solution to the driver, when the user acceptance degree is less than 0.4, the driver basically will not accept the candidate control solution recommended by the recommendation server. When the user acceptance degree is not less than 0.4, the driver may accept the candidate control solution recommended by the recommendation server. Then 0.4 is determined as the user recommendation threshold.

[0071] Step 209: Determine the recommendation strategy of the candidate control solution based on the user recommendation threshold and the user acceptance degree.

[0072] Specifically, after obtaining the user acceptance degree of the candidate control scheme, it is necessary to compare the user recommendation threshold with the user acceptance degree, and then determine the recommendation strategy of the candidate control scheme. In the embodiment of this scheme, optionally, based on the user recommendation threshold and the user acceptance degree, determining the recommendation strategy of the candidate control scheme includes the following steps B1 to B3:

[0073] Step B1: Compare the user acceptance level with the user recommendation threshold.

[0074] Step B2: When the user acceptance level exceeds the user recommendation threshold, the recommendation strategy of the candidate control scheme is determined as recommended.

[0075] Specifically, the user's recommendation threshold can be used to determine whether the user will accept the current recommendation solution. For example, after analyzing all historical control data in the portrait server, the user recommendation threshold is 0.4, and the user acceptance degree of the candidate control solution is 0.7546. At this time, the user acceptance degree exceeds the user recommendation threshold, and the recommendation strategy of the candidate control solution is determined to be recommended.

[0076] Step B3: When the user acceptance level does not exceed the user recommendation threshold, the recommendation strategy of the candidate control scheme is determined to be not recommended.

[0077] Specifically, the user's recommendation threshold can be used to determine whether the user will accept the current recommendation solution. For example, after analyzing all historical control data in the portrait server, the user recommendation threshold is 0.4, and the user acceptance degree of the candidate control solution is 0.3546. At this time, the user acceptance degree is less than the user recommendation threshold, and the recommendation strategy of the candidate control solution is determined to be not recommended.

[0078] According to the above steps, it is possible to more accurately determine whether the user will accept the candidate recommendation solution, thereby avoiding the situation where unnecessary solutions are recommended to the user as much as possible, thereby improving the user experience.

[0079] Step 210: After determining that the recommended strategy of the candidate control scheme is recommended, recommend the candidate control scheme to the vehicle.

[0080] Specifically, if it is determined that the recommended strategy of the candidate control solution is recommended, it indicates that the driver is likely to accept the candidate control solution recommended by the recommendation server. Further, the candidate control solution is recommended to the vehicle. For example, the candidate control solution is displayed to the driver on the vehicle screen, or the candidate control solution is broadcast to the driver through voice broadcast.

[0081] Step 211: Obtain driver's feedback information on the recommended candidate control schemes from the vehicle.

[0082] Specifically, after a candidate control solution is recommended for the vehicle, the driver can choose to accept or not accept the recommended candidate control solution. For example, after the candidate control solution is displayed for the driver on the in-vehicle screen, the driver can select to accept or not accept the candidate control solution through the in-vehicle screen. Further, after the driver selects to accept or not accept the candidate control solution, feedback information of the driver on the recommended candidate control solution is obtained from the vehicle.

[0083] Step 212: Send the feedback information to the portrait server so that the portrait server updates the vehicle control portrait of the driver of the vehicle based on the feedback information.

[0084] Among them, the vehicle control portraits of all drivers of the vehicle are stored in the portrait server. The vehicle control portrait includes historical control data, and the historical control data includes historical scenario information and the historical control solution corresponding to the historical scenario information. The historical control solution also includes the acceptance situation of the driver for the historical control solution. The portrait server can update the vehicle control portrait of the driver of the vehicle in real time according to the feedback information of the driver on the recommended candidate control solution, making the vehicle control portrait of the driver of the vehicle more complete. At the same time, the portrait server can obtain the identification information of the driver, query the vehicle control portrait of the driver according to the identification information of the driver, and send the vehicle control portrait of the driver to the recommendation server. When the portrait server cannot query the vehicle control portrait of the driver according to the identification information of the driver, it means that the driver may be using the vehicle for the first time and the recommended candidate control solution for the driver cannot be determined. At this time, the portrait server can analyze the vehicle control portraits of all drivers of the vehicle to obtain a general control portrait. When the portrait server cannot query the vehicle control portrait of the driver according to the identification information of the driver, the portrait server can send the general control portrait to the recommendation server. The recommendation server can recommend the candidate control solution corresponding to the general control portrait to the vehicle according to the general control portrait. Figure 3 It is a flowchart of sending a general portrait to the recommendation server provided by an embodiment of the present invention. As Figure 3 shown, the portrait server can obtain the identification information of the driver and check whether there is a corresponding vehicle control portrait according to the identification information of the driver. When a corresponding vehicle control portrait is found, the vehicle control portrait is sent to the recommendation server. When no corresponding vehicle control portrait is found, the general control portrait is sent to the recommendation server.

[0085] Figure 4 It is a flowchart of recommending a candidate control solution for the vehicle provided by an embodiment of the present invention. As Figure 4As shown, all historical control data is stored in the image server, and the historical control data includes historical scenario information and the corresponding historical control scheme for the historical scenario information. The historical scenario information and the historical control scheme are input into the scheme prediction model to obtain a candidate control scheme and the corresponding recommendation degree for the candidate control scheme. The user acceptance degree is calculated based on the recommendation degree and the user weight. It is determined whether the user acceptance degree exceeds the user recommendation threshold. When the user acceptance degree exceeds the user recommendation threshold, the recommendation strategy for the candidate control scheme is determined to be recommended. When the user acceptance degree does not exceed the user recommendation threshold, the recommendation strategy for the candidate control scheme is determined not to be recommended. After determining that the recommendation strategy for the candidate control scheme is recommended, the candidate control scheme is recommended to the vehicle, and the feedback information of the user is sent to the image server so that the image server updates the vehicle control image of the driver of the vehicle based on the feedback information.

[0086] The recommended control method for a vehicle provided by an embodiment of the present invention can obtain the vehicle control portrait of the driver of the vehicle from a portrait server; extract the historical control data of the target component of the vehicle from the vehicle control portrait, where the historical control data includes historical scenario information and the historical control scheme corresponding to the historical scenario information; input the current scenario information, historical scenario information, and the historical control scheme corresponding to the historical scenario information of the target component into a scheme recommendation model to obtain multiple intermediate control schemes for the target component and the recommendation degree of each intermediate control scheme in the multiple intermediate control schemes; use the intermediate control scheme with the highest recommendation degree among the multiple intermediate control schemes as the candidate control scheme for the target component, to obtain the candidate control scheme for the target component and the recommendation degree of the candidate control scheme; obtain the importance degree of each dimension information in the preset historical scenario information; determine the user weight corresponding to the current scenario information of the target component based on the importance degree of each dimension information and the historical scenario information; multiply the recommendation degree of the candidate control scheme by the user weight corresponding to the current scenario information of the target component to determine the user acceptance degree of the candidate control scheme; perform data analysis on all the historical control data in the portrait server to obtain a user recommendation threshold; determine the recommendation strategy of the candidate control scheme based on the user recommendation threshold and the user acceptance degree. After determining that the recommendation strategy of the candidate control scheme is to recommend, recommend the candidate control scheme to the vehicle; obtain the feedback information of the driver of the vehicle on the recommended candidate control scheme from the vehicle; send the feedback information to the portrait server so that the portrait server can update the vehicle control portrait of the driver of the vehicle based on the feedback information. This solution can further correct the candidate control scheme using the user weight, making the determined candidate control scheme for the target component more in line with the user's wishes and improving the accuracy of the candidate control scheme recommended for the user. And in this solution, sending the feedback information to the portrait server can enable the portrait server to update the vehicle control portrait of the driver of the vehicle based on the feedback information, continuously improving the vehicle control portrait in the portrait server. When the portrait server cannot find the driver's information, it can send a general control portrait to the recommendation server. This solves the "cold start" problem in the recommendation system and avoids the situation where no control scheme can be shown to the user when the user needs to view the recommended control scheme, improving the user experience.

[0087] Figure 5 The following is a schematic structural diagram of a recommended control device for a vehicle provided by an embodiment of the present invention. An embodiment of the present invention provides a recommended control device for a vehicle, including:

[0088] A data acquisition module 501, configured to obtain the vehicle control portrait of the driver of the vehicle from a portrait server;

[0089] A data extraction module 502, configured to extract historical control data of a target component of the vehicle from the vehicle control portrait, where the historical control data includes historical scenario information and a historical control scheme corresponding to the historical scenario information;

[0090] A scheme determination module 503, configured to input the current scenario information of the target component, the historical scenario information, and the historical control scheme corresponding to the historical scenario information into a scheme recommendation model, to obtain a candidate control scheme of the target component and a recommendation degree of the candidate control scheme;

[0091] A weight determination module 504, configured to determine a user weight corresponding to the current scenario information of the target component;

[0092] A policy determination module 505, configured to determine an acceptance degree of the candidate control scheme according to the recommendation degree of the candidate control scheme of the target component and the user weight corresponding to the current scenario information of the target component, and determine a recommendation policy of the candidate control scheme according to the acceptance degree.

[0093] Optionally, the scheme determination module 503 is specifically configured to:

[0094] Input the current scenario information of the target component, the historical scenario information, and the historical control scheme corresponding to the historical scenario information into the scheme recommendation model, to obtain multiple intermediate control schemes of the target component and a recommendation degree of each intermediate control scheme in the intermediate control schemes;

[0095] Use the intermediate control scheme with the largest recommendation degree among the multiple intermediate control schemes as the candidate control scheme of the target component, to obtain the candidate control scheme of the target component and the recommendation degree of the candidate control scheme.

[0096] Optionally, the weight determination module 504 is specifically configured to:

[0097] Obtain the importance degree of each dimension information in the preset historical scenario information;

[0098] Determine the user weight corresponding to the current scenario information of the target component based on the importance degree of each dimension information and the historical scenario information

[0099] Optionally, the weight determination module 504 is further configured to:

[0100] Match each dimension information in the current scenario information with each dimension information in the historical scenario information, to obtain current scenario dimension information in the current scenario information that matches each dimension information in the historical scenario information;

[0101] Add the importance levels of the dimension information in the historical scene information that matches the current scene dimension information to determine the user weight corresponding to the current scene information of the target component.

[0102] Optionally, the policy determination module 505 is specifically configured to:

[0103] Multiply the recommendation level of the candidate control solution by the user weight corresponding to the current scene information of the target component to determine the user acceptance level of the candidate control solution.

[0104] Optionally, the policy determination module 505 is further configured to:

[0105] Perform data analysis on all historical control data in the portrait server to obtain a user recommendation threshold;

[0106] Based on the user recommendation threshold and the user acceptance level, determine the recommendation strategy for the candidate control solution.

[0107] Optionally, the policy determination module 505 is further configured to:

[0108] Compare the user acceptance level with the user recommendation threshold;

[0109] When the user acceptance level exceeds the user recommendation threshold, determine that the recommendation strategy for the candidate control solution is to recommend;

[0110] When the user acceptance level does not exceed the user recommendation threshold, determine that the recommendation strategy for the candidate control solution is not to recommend.

[0111] Optionally, after determining that the recommendation strategy for the candidate control solution is to recommend, it further includes:

[0112] Recommend the candidate control solution to the vehicle;

[0113] Obtain feedback information from the vehicle on the recommended candidate control solution by the driver;

[0114] Send the feedback information to the portrait server so that the portrait server updates the vehicle control portrait of the driver of the vehicle based on the feedback information.

[0115] The recommended control device for a vehicle provided by an embodiment of the present invention can execute the recommended control method for a vehicle provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method.

[0116] Figure 6 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. Refer to Figure 6, which shows a schematic structural diagram of a computer system 12 of an electronic device suitable for implementing the embodiments of the present invention. Figure 6 The illustrated electronic device is merely an example and should not impose any limitations on the functions and usage scope of the embodiments of the present invention. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 connecting different system components (including the system memory 28 and the processing unit 16).

[0117] The bus 18 represents one or more of several types of bus structures, including a memory bus or a memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus structures. For example, these architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0118] The electronic device 12 typically includes a variety of computer system-readable media. These media can be any available media accessible by the electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0119] The system memory 28 may include computer system-readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, a storage system 34 may be used for reading and writing non-removable, non-volatile magnetic media ( Figure 6 not shown, commonly referred to as a "hard disk drive"). Although Figure 6 not shown in the figure, a disk drive for reading and writing removable non-volatile disks (such as "floppy disks") and an optical disk drive for reading and writing removable non-volatile optical disks (such as CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 through one or more data media interfaces. The memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0120] A program / utilities 40 having a set (at least one) of program modules 42 can be stored, for example, in a memory 28. Such program modules 42 include—but are not limited to—an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. The program modules 42 generally execute the functions and / or methods in the embodiments described in the present invention.

[0121] The electronic device 12 can also communicate with one or more external devices 14 (such as a keyboard, a pointing device, a display 24, etc.), and can also communicate with one or more devices that enable a user to interact with the electronic device 12, and / or communicate with any device that enables the electronic device 12 to communicate with one or more other computing devices (such as a network card, a modem, etc.). Such communication can be carried out through an input / output (I / O) interface 22. Additionally, in this embodiment of the electronic device 12, the display 24 does not exist as an independent entity but is embedded in the mirror. When the display surface of the display 24 is not being displayed, the display surface of the display 24 visually merges with the mirror surface. Moreover, the electronic device 12 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 20. As shown in the figure, the network adapter 20 communicates with other modules of the electronic device 12 through a bus 18. It should be understood that although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0122] The processing unit 16 executes various functional applications and the recommended control of the vehicle by running programs stored in the system memory 28. For example, it implements a method for recommended control of a vehicle provided in the embodiments of the present invention: obtaining a vehicle control portrait of the driver of the vehicle from a portrait server; extracting historical control data of the target component of the vehicle from the vehicle control portrait, where the historical control data includes historical scenario information and a historical control scheme corresponding to the historical scenario information; inputting the current scenario information of the target component, the historical scenario information, and the historical control scheme corresponding to the historical scenario information into a scheme recommendation model to obtain a candidate control scheme for the target component and the recommendation degree of the candidate control scheme; determining a user weight corresponding to the current scenario information of the target component; and determining the user acceptance degree of the candidate control scheme according to the recommendation degree of the candidate control scheme of the target component and the user weight corresponding to the current scenario information of the target component, and determining the recommendation strategy of the candidate control scheme according to the user acceptance degree.

[0123] Figure 7 This is a schematic structural diagram of the recommended control system for a vehicle provided by an embodiment of the present invention. As Figure 7 shown, the recommended control system for a vehicle includes a vehicle 701, an electronic device 702, and a portrait server 703.

[0124] Next, in combination with Figure 7 the system shown, the flowchart of providing a candidate control solution to a user provided by an embodiment of the present invention will be described. As Figure 8 shown, the vehicle 701 obtains the identification information of the driver and sends the identification information of the driver to the portrait server 703. After receiving the identification information of the driver, the portrait server 703 searches for whether there is a corresponding vehicle 701 control portrait according to the identification information of the driver. When a corresponding vehicle 701 control portrait is found, the vehicle 701 control portrait is sent to the electronic device 702. When no corresponding vehicle 701 control portrait is found, the general control portrait is sent to the electronic device 702. If the electronic device 702 receives the vehicle 701 control portrait, it determines the recommended strategy for the candidate control solution according to the vehicle 701 control portrait. After determining that the recommended strategy for the candidate control solution is to recommend, the candidate control solution is recommended to the vehicle 701. After the vehicle 701 provides the candidate recommended solution to the driver, it obtains the user feedback information of the driver on the recommended candidate control solution and sends the user feedback information to the electronic device 702. After receiving the feedback information of the user, the electronic device 702 sends the feedback information to the portrait server 703 so that the portrait server 703 updates the vehicle 701 control portrait of the driver of the vehicle 701 based on the feedback information.

[0125] An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements a recommended control method for a vehicle provided by all embodiments of the present invention: obtaining a vehicle control portrait of the driver of the vehicle from a portrait server; extracting historical control data of a target component of the vehicle from the vehicle control portrait, where the historical control data includes historical scenario information and a historical control scheme corresponding to the historical scenario information; inputting the current scenario information of the target component, the historical scenario information, and the historical control scheme corresponding to the historical scenario information into a scheme recommendation model to obtain a candidate control scheme for the target component and a recommendation degree of the candidate control scheme; determining a user weight corresponding to the current scenario information of the target component; determining a user acceptance degree of the candidate control scheme according to the recommendation degree of the candidate control scheme of the target component and the user weight corresponding to the current scenario information of the target component, and determining a recommendation strategy for the candidate control scheme according to the user acceptance degree. One or more arbitrary combinations of computer-readable media can be used. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the computer-readable storage medium include: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device.

[0126] The computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, and the computer-readable medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device.

[0127] The program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0128] Computer program code for performing the operations of the present invention may be written in one or more programming languages or combinations thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network - including a local area network (LAN) or a wide area network (WAN) - or, alternatively, may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0129] Note that the above is only a preferred embodiment of the present invention and the technical principles applied. Those skilled in the art will understand that the present invention is not limited to the specific embodiments here, and various obvious changes, re-adjustments and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments only. Without departing from the concept of the present invention, more other equivalent embodiments may be included, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A recommended control method for a vehicle, characterized in that, it includes: Obtain the vehicle control portrait of the driver of the vehicle from the portrait server; Extract the historical control data of the target component of the vehicle from the vehicle control portrait, where the historical control data includes historical scenario information and the historical control scheme corresponding to the historical scenario information; Input the current scenario information of the target component, the historical scenario information, and the historical control scheme corresponding to the historical scenario information into a scheme recommendation model to obtain a candidate control scheme for the target component and the recommendation degree of the candidate control scheme; Determine the user weight corresponding to the current scenario information of the target component; According to the recommendation degree of the candidate control scheme of the target component and the user weight corresponding to the current scenario information of the target component, determine the user acceptance degree of the candidate control scheme, and determine the recommendation strategy of the candidate control scheme according to the user acceptance degree; Among them, the determining the recommendation strategy of the candidate control scheme according to the user acceptance degree further includes: Perform data analysis on all historical control data in the portrait server to obtain a user recommendation threshold; Based on the user recommendation threshold and the user acceptance degree, determine the recommendation strategy of the candidate control scheme; Among them, the determining the recommendation strategy of the candidate control scheme based on the user recommendation threshold and the user acceptance degree includes: Compare the user acceptance degree with the user recommendation threshold; When the user acceptance degree exceeds the user recommendation threshold, determine that the recommendation strategy of the candidate control scheme is to recommend; When the user acceptance degree does not exceed the user recommendation threshold, determine that the recommendation strategy of the candidate control scheme is not to recommend.

2. The method according to claim 1, characterized in that, The inputting the current scenario information of the target component, the historical scenario information, and the historical control scheme corresponding to the historical scenario information into a scheme recommendation model to obtain a candidate control scheme for the target component and the recommendation degree of the candidate control scheme includes: Input the current scenario information of the target component, the historical scenario information, and the historical control scheme corresponding to the historical scenario information into the scheme recommendation model to obtain multiple intermediate control schemes for the target component and the recommendation degree of each intermediate control scheme in the intermediate control schemes; Use the intermediate control scheme with the highest recommendation degree among the multiple intermediate control schemes as the candidate control scheme of the target component to obtain the candidate control scheme of the target component and the recommendation degree of the candidate control scheme.

3. The method according to claim 1, characterized in that, The determining the user weight corresponding to the current scenario information of the target component includes: Obtain the importance degree of each dimension information in the preset historical scenario information; Based on the importance degree of each dimension information and the historical scenario information, determine the user weight corresponding to the current scenario information of the target component.

4. The method according to claim 3, characterized in that, Determining the user weight corresponding to the current scenario information of the target component based on the importance degrees of the respective dimension information and the historical scenario information includes: Matching each dimension information in the current scenario information with the dimension information in the historical scenario information to obtain the current scenario dimension information in the current scenario information that matches the dimension information in the historical scenario information; Adding up the importance degrees of the respective dimension information in the historical scenario information that matches the current scenario dimension information to determine the user weight corresponding to the current scenario information of the target component.

5. The method according to claim 1, wherein, Determining the user acceptance degree of the candidate control scheme according to the recommendation degree of the candidate control scheme of the target component and the user weight corresponding to the current scenario information of the target component includes: Multiplying the recommendation degree of the candidate control scheme by the user weight corresponding to the current scenario information of the target component to determine the user acceptance degree of the candidate control scheme.

6. The method according to claim 1, wherein, After determining that the recommendation strategy of the candidate control scheme is recommendation, it further includes: Recommending the candidate control scheme to the vehicle; Obtaining feedback information of the driver of the vehicle on the recommended candidate control scheme from the vehicle; Sending the feedback information to the portrait server so that the portrait server updates the vehicle control portrait of the driver of the vehicle based on the feedback information.

7. A recommended control device for a vehicle, wherein, It includes: A data acquisition module, configured to acquire the vehicle control portrait of the driver of the vehicle from a portrait server; A data extraction module, configured to extract historical control data of the target component of the vehicle from the vehicle control portrait, where the historical control data includes historical scenario information and a historical control scheme corresponding to the historical scenario information; A scheme determination module, configured to input the current scenario information, the historical scenario information, and the historical control scheme corresponding to the historical scenario information of the target component into a scheme recommendation model to obtain a candidate control scheme of the target component and the recommendation degree of the candidate control scheme; A weight determination module, configured to determine the user weight corresponding to the current scenario information of the target component; A strategy determination module, configured to determine the user acceptance degree of the candidate control scheme according to the recommendation degree of the candidate control scheme of the target component and the user weight corresponding to the current scenario information of the target component, and determine the recommendation strategy of the candidate control scheme according to the user acceptance degree; wherein, the strategy determination module is further configured to: Perform data analysis on all historical control data in the portrait server to obtain a user recommendation threshold; Determine the recommendation strategy of the candidate control scheme based on the user recommendation threshold and the user acceptance degree; wherein, the strategy determination module is further configured to: Compare the user acceptance degree with the user recommendation threshold; When the user acceptance degree exceeds the user recommendation threshold, determine that the recommendation strategy of the candidate control scheme is recommendation; When the user acceptance level does not exceed the user recommendation threshold, determine that the recommendation strategy for the candidate control solution is not to recommend.

8. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein, when the processor executes the program, it implements the recommended control method for a vehicle according to any one of claims 1 to 6.

9. A recommended control system for a vehicle, wherein, the recommended control system for the vehicle includes a vehicle, a portrait server, and an electronic device for executing the recommended control method for a vehicle according to any one of claims 1 to 6.

10. A computer-readable storage medium, on which a computer program is stored, wherein, when the program is executed by a processor, it implements the recommended control method for a vehicle according to any one of claims 1 - 6.

Images