Function recommendation method and system based on intelligent cabin, vehicle and equipment

Abstract

The invention discloses a function recommendation method and system based on an intelligent cabin, a vehicle and equipment. The function recommendation method based on the intelligent cockpit comprises the following steps: acquiring a user identity; when the user identity is determined as a target user, obtaining a driving scene of a vehicle; the driving scene is input into a pre-trained recommendation model, function state selection matched with the driving scene is obtained, and the recommendation model is pre-trained according to collected operation data of a target user in a non-driving scene; and recommending the function state selection to the target user. By the adoption of the automobile seat cushion, the degree of adhesion with a driver is higher, the automobile seat cushion is closer to an ideal seat cabin, meanwhile, the driver can drive more securely, the maximum relaxation feeling is met, the purpose of reducing driving fatigue is achieved, customers can be better served, and the individualized requirements of more scenarios can be met.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a function recommendation method, system, vehicle and equipment based on a smart cockpit. Background Art

[0002] Generally speaking, when the vehicle leaves the factory, the functions of the central control are basically determined. If there are other personalized needs, it is necessary to develop and integrate the APP in the background and then build it into the application store. Customers can only use the relevant APP after downloading it through the application store.

[0003] However, from the time when customers raise functional requirements to the development and integration of APP, and finally the closed loop where customers download the app through the app store, the time and R&D costs are very high. In addition, customer needs are ever-changing, and the newly integrated APP can only meet the individual needs of a part of customers for a period of time. It cannot meet the functional requirements of different states and scenarios in the long term, affecting the vehicle's user experience. Summary of the invention

[0004] Based on this, it is necessary to provide a function recommendation method, system, vehicle and equipment based on a smart cockpit to address the above-mentioned technical problems, meet the personalized needs of customers, and conduct big data model training based on the collected driver behavior data to meet the needs of different modules corresponding to drivers in different scenarios. At the same time, it can be dynamically adjusted according to the driver's status. Compared with traditional fixed-function APPs, it has a higher degree of adhesion with the driver and is closer to the ideal cockpit. At the same time, it can also allow the driver to drive more safely and satisfy the maximum sense of relaxation, so as to achieve the purpose of reducing driving fatigue, and can better serve customers and meet more scenario-based personalized needs.

[0005] In a first aspect, a function recommendation method based on a smart cockpit is provided, comprising:

[0006] Get user identity;

[0007] When the user is determined as a target user according to the user identity, obtaining a driving scene of the vehicle;

[0008] Inputting the driving scenario into a pre-trained recommendation model to obtain a function state selection matching the driving scenario, wherein the recommendation model is pre-trained based on the collected operation data of the target user in different driving scenarios;

[0009] The functional status selection is recommended to the target user.

[0010] In some examples, obtaining the user identity includes:

[0011] Log in to the car application;

[0012] The user identity is obtained according to the login information.

[0013] In some examples, before inputting the driving scenario into a pre-trained recommendation model to obtain a function state selection matching the driving scenario, the method further includes:

[0014] Collecting operation data and driving scenarios of target users within a predetermined time, wherein the operation data at least includes driving behavior data and entertainment behavior data;

[0015] The initial recommendation model is trained according to the operation data and driving scenarios of the target users within a predetermined time to obtain a trained recommendation model.

[0016] In some examples, the training of the initial recommendation model according to the operation data and driving scenarios of the target user within a predetermined time to obtain the trained recommendation model includes:

[0017] Obtaining a driving function operation according to the driving behavior data of the target user within a predetermined time, and establishing a corresponding relationship between the driving function operation and the driving scene;

[0018] Obtaining entertainment function operations according to the entertainment behavior data of the target user within a predetermined time, and establishing a corresponding relationship between the entertainment function operations and the driving scene;

[0019] The initial recommendation model is trained according to the correspondence between the driving function operation and the driving scene, and the correspondence between the entertainment function operation and the driving scene to obtain the trained recommendation model.

[0020] In some examples, the selecting and recommending the functional state to the target user includes:

[0021] The function status selection is recommended to the target user through voice broadcast.

[0022] In some examples, this also includes:

[0023] According to the target user's response, determining whether to execute a function corresponding to the function state selection;

[0024] If so, the function is executed.

[0025] In the second aspect, a function recommendation system based on a smart cockpit is provided, including:

[0026] Identity recognition module, used to obtain user identity;

[0027] An acquisition module, used for obtaining a driving scene of a vehicle when the user is determined as a target user according to the user identity;

[0028] A calculation module, used for inputting the driving scenario into a pre-trained recommendation model to obtain a function state selection matching the driving scenario, wherein the recommendation model is pre-trained based on the collected operation data of the target user in different driving scenarios;

[0029] A control module is used to recommend the functional state selection to the target user.

[0030] A third aspect provides a vehicle, comprising: a function recommendation system based on the smart cockpit according to the second aspect.

[0031] In a fourth aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the function recommendation method based on the smart cockpit of the above-mentioned first aspect and any possible implementation method of the first aspect are implemented.

[0032] In a fifth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the steps of the function recommendation method based on the smart cockpit of the above-mentioned first aspect and any possible implementation method of the first aspect are implemented.

[0033] In a sixth aspect, a computer program product is provided, on which a computer program is stored. When the program is executed by a processor, the steps of the function recommendation method based on the smart cockpit in the above-mentioned first aspect and any possible implementation method of the first aspect are implemented.

[0034] By adopting the embodiment of the present application, the user identity is obtained, and when the user is determined as a target user based on the user identity, the driving scene of the vehicle is obtained, the driving scene is input into the pre-trained recommendation model, and the function state selection matching the driving scene is obtained, and the function state selection is recommended to the target user. In this way, the personalized needs of customers are met, and the big data model training based on the collected driver behavior data can meet the needs of different modules corresponding to drivers in different scenarios, and can be dynamically adjusted according to the driver's state. Compared with traditional fixed-function APPs, it has a higher degree of adhesion with the driver and is closer to the ideal cockpit. At the same time, it can also allow the driver to drive more safely and meet the maximum sense of relaxation, so as to achieve the purpose of reducing driving fatigue, and can better serve customers and meet more scenario-based personalized needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0036] Figure 1A flow chart of a function recommendation method based on a smart cockpit provided in an embodiment of the present application;

[0037] Figure 2 A structural block diagram of a function recommendation system based on a smart cockpit provided in an embodiment of the present application;

[0038] Figure 3 A structural block diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0039] The present application is further described in detail below in conjunction with the embodiments and drawings. It is to be understood that the specific embodiments described herein are only used to explain the relevant application, rather than to limit the application. It is also necessary to explain that, for ease of description, only the parts related to the application are shown in the drawings.

[0040] It should be noted that, in the absence of conflict, the embodiments of the present application, that is, the features of the embodiments, can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0041] The following describes in detail the function recommendation method, system, device and medium based on the smart cockpit according to the embodiments of the present application in conjunction with the accompanying drawings.

[0042] Figure 1 FIG. 1 is a flow chart of a method for recommending functions based on a smart cockpit according to an embodiment of the present application. Figure 1 As shown, according to the function recommendation method based on the smart cockpit according to the embodiment of the present application, the following steps are included:

[0043] S101: Obtain user identity.

[0044] In one embodiment of the present application, obtaining the user identity includes: logging into the vehicle-mounted application; and obtaining the user identity based on the login information.

[0045] S102: When the user is determined as a target user according to the user identity, a driving scene of the vehicle is obtained.

[0046] The driving scenarios include, for example, high-speed driving scenarios, expressway driving scenarios, and urban road driving scenarios. In the high-speed driving scenario, the driving speed and the like may also be included.

[0047] S103: Inputting the driving scenario into a pre-trained recommendation model to obtain a function state selection matching the driving scenario, wherein the recommendation model is pre-trained based on collected operation data of target users in different driving scenarios.

[0048] In one embodiment of the present application, before the driving scenario is input into a pre-trained recommendation model to obtain a functional state selection matching the driving scenario, it also includes: collecting the target user's operation data and driving scenarios within a predetermined time, wherein the operation data at least includes driving behavior data and entertainment behavior data; training the initial recommendation model based on the target user's operation data and driving scenarios within the predetermined time to obtain a trained recommendation model.

[0049] In this example, the initial recommendation model is trained according to the operation data and driving scenarios of the target user within the predetermined time to obtain the trained recommendation model, including: obtaining the driving function operation according to the driving behavior data of the target user within the predetermined time, and establishing the correspondence between the driving function operation and the driving scenario; obtaining the entertainment function operation according to the entertainment behavior data of the target user within the predetermined time, and establishing the correspondence between the entertainment function operation and the driving scenario; training the initial recommendation model according to the correspondence between the driving function operation and the driving scenario, and the correspondence between the entertainment function operation and the driving scenario to obtain the trained recommendation model.

[0050] S104: Recommend the function status selection to the target user.

[0051] In one embodiment of the present application, recommending the function status selection to the target user includes: recommending the function status selection to the target user through voice announcement.

[0052] Furthermore, based on the function recommendation method of the smart cockpit, after recommending the function status selection to the target user through voice broadcast, it also includes: judging whether to execute the function corresponding to the function status selection according to the response of the target user; if so, executing the function.

[0053] The embodiments of the present application, under the premise of satisfying information security regulations, can collect and summarize the driving behaviors and entertainment behaviors of customers with different identity statuses in different driving scenarios, and automatically generate personalized and scenario-based functional demand states, so as to better meet the personalized needs of customers and satisfy the relatively maximized sense of relaxation after driving, so as to achieve the purpose of reducing driving fatigue.

[0054] That is: after the driver gets on the car, he logs in to the car owner APP with his own identity information. After a series of operation authorizations are completed on the car computer, the car computer begins to record the driver's operation information. The collection time can be set by yourself (such as one month, two months, etc.). After collecting the information data, the car computer trains the information data, and then in the car owner APP, different modules can be selected to meet the driver's personalized needs on the way to work.

[0055] For example: After driver A gets in the car, he logs in from the car owner APP and can authorize according to the projects he is interested in or has needs, and set the collection period of relevant information during driving, so as to better fit the needs to train the data model, such as: driving habits (whether he likes to turn on the air conditioner directly after getting in the car, whether he is used to checking all the lights before driving, whether he likes to use cruise control, etc.), entertainment habits (whether he directly turns on the radio to play a designated radio station after getting in the car, whether he connects Bluetooth to play music in the car, whether he often makes and receives calls through the Bluetooth channel, etc.), driving scenarios (whether he goes directly to the highway / expressway / urban road after leaving the parking lot, etc.).

[0056] Data training is performed based on the overall driving habits of driver A collected over a certain period of time. In different driving scenarios, the driver's driving operations, such as lighting operation, air conditioning operation, speed control operation, entertainment behavior operation, etc., are monitored. After the model training is completed, a text message and a pop-up window on the car computer are sent to driver A to inform the current car owner that the APP function has been completed and simulated operations can be performed;

[0057] The details are as follows, taking the entertainment function module as an example:

[0058] Every time driver A gets in the car, he will connect the Bluetooth of his mobile phone, then open a music app, select a singer's song from the classic music to play, and then start the car; when the member's song is played, A will manually switch to the next song; when the singer's playlist is finished, the driver will request to play dynamic music through voice. At the same time, during this time period, driver A has the habit of smoking. A will open the car window through voice while smoking, and about 5 minutes after smoking, he will manually close the car window and then lower the air-conditioning temperature; after the dynamic music playlist is finished, A will request to play crosstalk through voice, and at the same time, when getting on the highway, when the car speed increases to 120, he will request to lower the air-conditioning temperature and increase the crosstalk volume.

[0059] During this process, the driver repeatedly operates the mobile phone, car computer, car body and other related components through voice and manual operation. When the above information is collected, the main operating status of the process is practiced through the model to achieve a high degree of unification with the driver's status.

[0060] Next, based on the driver's behavioral habits, relevant recommendations are made, such as crosstalk recommendations, dynamic music recommendations, air-conditioning temperature recommendations, etc. When there is overlap with the driver's multiple behaviors, the driver's wishes are consulted through voice to better meet individual personalized needs.

[0061] After the driver completes the simulation operation, he / she should confirm whether the function status is consistent with his / her expected status. If he / she likes it, he / she can select this training model in the car owner APP to push and execute related modules during driving. If he / she does not like it, he / she can make suggestions in the car owner APP or directly turn off the related functions.

[0062] During use, the driver's operating behavior will still be recorded and collected, and the richness of the modules will be continuously improved to provide the driver with professional, personalized, and real-time scenario-based multiple functional status options.

[0063] According to the function recommendation method based on the smart cockpit of the embodiment of the present application, the user identity is obtained, and when the user is determined as a target user based on the user identity, the driving scene of the vehicle is obtained, and the driving scene is input into the pre-trained recommendation model to obtain the function state selection that matches the driving scene, and the function state selection is recommended to the target user. In this way, the personalized needs of customers are met, and the big data model training based on the collected driver behavior data can meet the needs of different modules corresponding to drivers in different scenarios. At the same time, it can be dynamically adjusted according to the driver's state. Compared with traditional fixed-function APPs, it has a higher degree of adhesion with the driver and is closer to the ideal cockpit. At the same time, it can also allow the driver to drive more safely and meet the maximum sense of relaxation, so as to achieve the purpose of reducing driving fatigue, and can better serve customers and meet more scenario-based personalized needs.

[0064] Figure 2 FIG. 1 is a structural block diagram of a function recommendation system based on a smart cockpit according to an embodiment of the present application. Figure 2 As shown, according to an embodiment of the present application, a function recommendation system based on a smart cockpit includes: an identity recognition module 210, an acquisition module 220, a calculation module 230 and a control module 240, wherein:

[0065] An identity recognition module 210, used to obtain a user identity;

[0066] An acquisition module 220, configured to obtain a driving scene of a vehicle when the user is determined as a target user according to the user identity;

[0067] The calculation module 230 is used to input the driving scenario into a pre-trained recommendation model to obtain a function state selection matching the driving scenario, wherein the recommendation model is pre-trained based on the collected operation data of the target user in different driving scenarios;

[0068] The control module 240 is used to recommend the function status selection to the target user.

[0069] The embodiments of the present application, under the premise of satisfying information security regulations, can collect and summarize the driving behaviors and entertainment behaviors of customers with different identity statuses in different driving scenarios, and automatically generate personalized and scenario-based functional demand states, so as to better meet the personalized needs of customers and satisfy the relatively maximized sense of relaxation after driving, so as to achieve the purpose of reducing driving fatigue.

[0070] That is: after the driver gets on the car, he logs in to the car owner APP with his own identity information. After a series of operation authorizations are completed on the car computer, the car computer begins to record the driver's operation information. The collection time can be set by yourself (such as one month, two months, etc.). After collecting the information data, the car computer trains the information data, and then in the car owner APP, different modules can be selected to meet the driver's personalized needs on the way to work.

[0071] For example: After driver A gets in the car, he logs in from the car owner APP and can authorize according to the projects he is interested in or has needs, and set the collection period of relevant information during driving, so as to better fit the needs to train the data model, such as: driving habits (whether he likes to turn on the air conditioner directly after getting in the car, whether he is used to checking all the lights before driving, whether he likes to use cruise control, etc.), entertainment habits (whether he directly turns on the radio to play a designated radio station after getting in the car, whether he connects Bluetooth to play music in the car, whether he often makes and receives calls through the Bluetooth channel, etc.), driving scenarios (whether he goes directly to the highway / expressway / urban road after leaving the parking lot, etc.).

[0072] Data training is performed based on the overall driving habits of driver A collected over a certain period of time. In different driving scenarios, the driver's driving operations, such as lighting operation, air conditioning operation, speed control operation, entertainment behavior operation, etc., are monitored. After the model training is completed, a text message and a pop-up window on the car computer are sent to driver A to inform the current car owner that the APP function has been completed and simulated operations can be performed;

[0073] The details are as follows, taking the entertainment function module as an example:

[0074] Every time driver A gets in the car, he will connect the Bluetooth of his mobile phone, then open a music app, select a singer's song from the classic music to play, and then start the car; when the member's song is played, A will manually switch to the next song; when the singer's playlist is finished, the driver will request to play dynamic music through voice. At the same time, during this time period, driver A has the habit of smoking. A will open the car window through voice while smoking, and about 5 minutes after smoking, he will manually close the car window and then lower the air-conditioning temperature; after the dynamic music playlist is finished, A will request to play crosstalk through voice, and at the same time, when getting on the highway, when the car speed increases to 120, he will request to lower the air-conditioning temperature and increase the crosstalk volume.

[0075] During this process, the driver repeatedly operates the mobile phone, car computer, car body and other related components through voice and manual operation. When the above information is collected, the main operating status of the process is practiced through the model to achieve a high degree of unification with the driver's status.

[0076] Next, based on the driver's behavioral habits, relevant recommendations are made, such as crosstalk recommendations, dynamic music recommendations, air-conditioning temperature recommendations, etc. When there is overlap with the driver's multiple behaviors, the driver's wishes are consulted through voice to better meet individual personalized needs.

[0077] After the driver completes the simulation operation, he / she should confirm whether the function status is consistent with his / her expected status. If he / she likes it, he / she can select this training model in the car owner APP to push and execute related modules during driving. If he / she does not like it, he / she can make suggestions in the car owner APP or directly turn off the related functions.

[0078] During use, the driver's operating behavior will still be recorded and collected, and the richness of the modules will be continuously improved to provide the driver with professional, personalized, and real-time scenario-based multiple functional status options.

[0079] According to the function recommendation system based on the smart cockpit of the embodiment of the present application, the user identity is obtained, and when the user is determined as a target user according to the user identity, the driving scene of the vehicle is obtained, and the driving scene is input into the pre-trained recommendation model to obtain the function state selection matching the driving scene, and the function state selection is recommended to the target user. In this way, the personalized needs of customers are met, and the big data model training based on the collected driver behavior data can meet the needs of different modules corresponding to drivers in different scenarios, and can be dynamically adjusted according to the driver's state. Compared with traditional fixed-function APPs, it has a higher degree of adhesion with the driver and is closer to the ideal cockpit. At the same time, it can also allow the driver to drive more safely and meet the maximum sense of relaxation, so as to achieve the purpose of reducing driving fatigue, and can better serve customers and meet more scenario-based personalized needs.

[0080] For the specific definition of the function recommendation system based on the smart cockpit, please refer to the definition of the function recommendation method based on the smart cockpit above, which will not be repeated here. The various modules of the above-mentioned function recommendation system based on the smart cockpit can be implemented in whole or in part through software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0081] In one embodiment, a vehicle is provided, including: according to the function recommendation system based on the smart cockpit described in the above embodiment, the vehicle obtains the user identity, and when it is determined as a target user according to the user identity, obtains the driving scene of the vehicle, inputs the driving scene into a pre-trained recommendation model, obtains the function state selection matching the driving scene, and recommends the function state selection to the target user. In this way, the personalized needs of customers are met, and the big data model training is carried out for the collected driver behavior data, which can meet the needs of different modules corresponding to the driver in different scenarios, and can be dynamically adjusted according to the driver's state. Compared with traditional fixed-function APPs, it has a higher degree of adhesion with the driver and is closer to the ideal cockpit. At the same time, it can also allow the driver to drive more safely and meet the maximum sense of relaxation, so as to achieve the purpose of reducing driving fatigue, and can better serve customers and meet more scenario-based personalized needs.

[0082] In addition, other structures and functions of the vehicle according to the embodiment of the present application are known to ordinary technicians in the field and will not be elaborated here.

[0083] In one embodiment, a computer device is provided. Figure 3 This is a block diagram of the computer device provided in the embodiment of the present application, refer to Figure 3 The computer device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the above-mentioned function recommendation method based on the smart cockpit is implemented. For example, the following steps are performed: obtaining the user identity;

[0084] When the user is determined as a target user according to the user identity, obtaining a driving scene of the vehicle;

[0085] Inputting the driving scenario into a pre-trained recommendation model to obtain a function state selection matching the driving scenario, wherein the recommendation model is pre-trained based on the collected operation data of the target user in different driving scenarios;

[0086] The functional status selection is recommended to the target user.

[0087] The embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the processor executes the computer program, the above-mentioned function recommendation method embodiment based on the smart cockpit is implemented. For example, the following steps are executed: obtaining the user identity;

[0088] When the user is determined as a target user according to the user identity, obtaining a driving scene of the vehicle;

[0089] Inputting the driving scenario into a pre-trained recommendation model to obtain a function state selection matching the driving scenario, wherein the recommendation model is pre-trained based on the collected operation data of the target user in different driving scenarios;

[0090] The functional status selection is recommended to the target user.

[0091] The present application embodiment provides a computer program product, which includes instructions. When the instructions are executed, the method described in the embodiment of the present application is executed. For example, it can be executed Figure 1 The various steps of the function recommendation method based on the smart cockpit shown, for example, perform: obtaining the user identity;

[0092] When the user is determined as a target user according to the user identity, obtaining a driving scene of the vehicle;

[0093] Inputting the driving scenario into a pre-trained recommendation model to obtain a function state selection matching the driving scenario, wherein the recommendation model is pre-trained based on the collected operation data of the target user in different driving scenarios;

[0094] The functional status selection is recommended to the target user.

[0095] Those of ordinary skill in the art can understand that all or part of the processes in the methods for implementing the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0096] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0097] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent application shall be subject to the attached claims.

Claims

1. A function recommendation method based on smart cockpit, It is characterized in that include: Get user identity; When the user is determined as a target user according to the user identity, obtaining a driving scene of the vehicle; Inputting the driving scenario into a pre-trained recommendation model to obtain a function state selection matching the driving scenario, wherein the recommendation model is pre-trained based on the collected operation data of the target user in different driving scenarios; The functional status selection is recommended to the target user.

2. The function recommendation method based on the smart cockpit according to claim 1, It is characterized in that The obtaining of the user identity comprises: Log in to the car application; The user identity is obtained according to the login information.

3. The function recommendation method based on the smart cockpit according to claim 1 or 2, It is characterized in that Before inputting the driving scenario into a pre-trained recommendation model to obtain a function state selection matching the driving scenario, the method further includes: Collecting operation data and driving scenarios of target users within a predetermined time, wherein the operation data at least includes driving behavior data and entertainment behavior data; The initial recommendation model is trained according to the operation data and driving scenarios of the target users within a predetermined time to obtain a trained recommendation model.

4. The function recommendation method based on the smart cockpit according to claim 3, It is characterized in that The initial recommendation model is trained according to the operation data and driving scenarios of the target user within the predetermined time to obtain a trained recommendation model, including: Obtaining a driving function operation according to the driving behavior data of the target user within a predetermined time, and establishing a corresponding relationship between the driving function operation and the driving scene; Obtaining entertainment function operations according to the entertainment behavior data of the target user within a predetermined time, and establishing a corresponding relationship between the entertainment function operations and the driving scene; The initial recommendation model is trained according to the correspondence between the driving function operation and the driving scene, and the correspondence between the entertainment function operation and the driving scene to obtain the trained recommendation model.

5. The function recommendation method based on the smart cockpit according to claim 1, It is characterized in that The selecting and recommending the functional state to the target user includes: The function status selection is recommended to the target user through voice broadcast.

6. The function recommendation method based on the smart cockpit according to claim 5, It is characterized in that Also includes: According to the target user's response, determining whether to execute a function corresponding to the function state selection; If so, the function is executed.

7. A function recommendation system based on smart cockpit, It is characterized in that include: Identity recognition module, used to obtain user identity; An acquisition module, used for obtaining a driving scene of a vehicle when the user is determined as a target user according to the user identity; A calculation module, used for inputting the driving scenario into a pre-trained recommendation model to obtain a function state selection matching the driving scenario, wherein the recommendation model is pre-trained based on the collected operation data of the target user in different driving scenarios; A control module is used to recommend the functional state selection to the target user.

8. A vehicle, It is characterized in that include: A function recommendation system based on a smart cockpit according to claim 7.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the program, the function recommendation method based on the smart cockpit according to any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the program is executed by a processor, the function recommendation method based on the smart cockpit according to any one of claims 1 to 6 is implemented.

Images