Vehicle control scheme generation method, device and equipment, readable storage medium and product

Abstract

The invention provides a vehicle control scheme generation method, device and equipment, a readable storage medium and a product, and relates to the field of artificial intelligence, in particular to the field of intelligent cabins. According to the specific implementation scheme, in response to vehicle starting, identity information associated with a user is recognized; obtaining a plurality of historical vehicle control schemes matched with the user based on the identity information, and collecting current target environment data; inputting the plurality of historical vehicle control schemes, the target environment data and the vehicle control capability data associated with the vehicle into a preset big language model, so that the big language model outputs at least one to-be-selected vehicle control scheme, and the vehicle control scheme comprises control parameters of at least one vehicle-mounted device associated with the vehicle; and determining a current target vehicle control scheme based on the at least one to-be-selected vehicle control scheme, and controlling the vehicle to execute the target vehicle control scheme. A personalized vehicle control scheme which better fits the use habits of the user and real-time environment data can be accurately generated.

Description

Technical Field

[0001] The present disclosure relates to an intelligent cockpit in artificial intelligence, and in particular to a vehicle control solution generation method, device, equipment, readable storage medium and product. Background Art

[0002] When users are driving a vehicle, in order to obtain a better driving experience, they can generally adjust facilities such as air conditioning, car seats, and windows. However, how to achieve personalized adjustment of vehicle facilities has become an urgent problem to be solved. Summary of the invention

[0003] The present disclosure provides a method, apparatus, device, readable storage medium and product for generating a personalized vehicle control solution that is more in line with user usage habits and real-time environmental data.

[0004] According to a first aspect of the present disclosure, a vehicle control solution generation method is provided, comprising:

[0005] In response to the vehicle being started, identifying identity information associated with the user;

[0006] Acquiring multiple historical vehicle control solutions matching the user based on the identity information, and collecting current target environment data;

[0007] Inputting the plurality of historical vehicle control schemes, target environment data, and vehicle control capability data associated with the vehicle into a preset large language model, so that the large language model outputs at least one vehicle control scheme to be selected, wherein the vehicle control scheme includes control parameters of at least one vehicle-mounted device associated with the vehicle;

[0008] A current target vehicle control scheme is determined based on at least one candidate vehicle control scheme, and the vehicle is controlled to execute the target vehicle control scheme.

[0009] According to a second aspect of the present disclosure, a vehicle control solution generating device is provided, comprising:

[0010] an identification module for identifying identity information associated with a user in response to vehicle startup;

[0011] An acquisition module, used to acquire multiple historical vehicle control solutions matching the user based on the identity information, and to collect current target environment data;

[0012] a generating module, configured to input the plurality of historical vehicle control schemes, target environment data, and vehicle control capability data associated with the vehicle into a preset large language model, so that the large language model outputs at least one vehicle control scheme to be selected, wherein the vehicle control scheme includes control parameters of at least one vehicle-mounted device associated with the vehicle;

[0013] The processing module is used to determine a current target vehicle control scheme based on at least one candidate vehicle control scheme, and control the vehicle to execute the target vehicle control scheme.

[0014] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0015] at least one processor; and

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect.

[0018] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the method described in the first aspect.

[0019] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising: a computer program, wherein the computer program is stored in a readable storage medium, at least one processor of an electronic device can read the computer program from the readable storage medium, and the at least one processor executes the computer program so that the electronic device executes the method described in the first aspect.

[0020] The technology disclosed in the present invention can accurately generate a personalized vehicle control solution that is more in line with user usage habits and real-time environmental data.

[0021] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0023] Figure 1 A diagram of the system architecture on which the embodiments of the present disclosure are based;

[0024] Figure 2 A schematic diagram of a process flow of a vehicle control solution generation method provided in an embodiment of the present disclosure;

[0025] Figure 3 A schematic diagram of a process flow of a vehicle control solution generation method provided by another embodiment of the present disclosure;

[0026] Figure 4A schematic diagram of a process flow of a vehicle control solution generation method provided by another embodiment of the present disclosure;

[0027] Figure 5 A schematic diagram of a process flow of a vehicle control solution generation method provided by another embodiment of the present disclosure;

[0028] Figure 6 A schematic diagram of a process flow of a vehicle control solution generation method provided by another embodiment of the present disclosure;

[0029] Figure 7 A schematic diagram of an application scenario provided for an embodiment of the present disclosure;

[0030] Figure 8 A schematic diagram of the structure of a vehicle control solution generating device provided in an embodiment of the present disclosure;

[0031] Fig. 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0032] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0033] In the process of driving a vehicle, in order to obtain a better driving experience, users can generally adjust facilities such as air conditioning, car seats, and windows. In related technologies, users generally need to manually adjust the on-board equipment, or users can adjust the on-board equipment by adjusting the vehicle scene mode. However, the above method is often cumbersome to adjust the on-board equipment, and generally only general adjustments can be made. Therefore, the vehicle control solution obtained by adjustment often does not meet the actual user needs and real-time environment, resulting in a poor user experience.

[0034] In the process of solving the above technical problems, the inventors discovered through research that in order to make the vehicle control solution more in line with the user's usage habits and real-time environmental data, the vehicle control solution can be generated based on historical vehicle control data, real-time environmental data and the current vehicle's vehicle control capabilities.

[0035] Optionally, in order to improve the quality and generation efficiency of the generated vehicle control solution, the vehicle control solution can also be generated through a preset large language model. The historical vehicle control data, real-time environmental data and the vehicle control capability of the current vehicle can be input into the large language model together, so that the large language model generates the vehicle control solution according to the historically learned vehicle control cases.

[0036] In addition, the large language model can also generate two sets of vehicle control solutions at the same time, a personalized solution and a general solution, so that users can more flexibly choose the current vehicle control solution according to actual needs.

[0037] The present disclosure provides a vehicle control solution generation method, device, equipment, readable storage medium and product, which are applied to a smart cockpit in artificial intelligence to achieve personalized vehicle control solution generation operations based on user usage habits and real-time environmental data.

[0038] It should be noted that the head model in this embodiment is not a head model for a specific user and cannot reflect the personal information of a specific user. It should be noted that the two-dimensional face image in this embodiment comes from a public data set.

[0039] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0040] In order to enable readers to more deeply understand the implementation principle of the present disclosure, the following Figure 1-Figure 9 The embodiments of the present disclosure are further refined.

[0041] Figure 1 This is a system architecture diagram based on the embodiments of the present disclosure, such as Figure 1 As shown, the system architecture based on the present disclosure includes at least a vehicle control solution generation device 11, an image acquisition device 12, a preset database 13, and at least one sensor 14, wherein the vehicle control solution generation device 11 can be pre-set in the vehicle, or the vehicle control solution generation device 11 can also be coupled to the server. The vehicle control solution generation device 11 can be communicated with the image acquisition device 12, the preset database 13, and at least one sensor 14, respectively.

[0042] Based on the above system architecture, the vehicle control solution generation device 11 can obtain the user image captured by the image acquisition device 12, and identify the user identity information based on the user image. Based on the identity information, multiple historical vehicle control solutions associated with the user are obtained in the preset database 13. And the target environment data can be obtained based on at least one sensor 14 and a preset external data source. Then, the vehicle control solution generation device 11 can call the preset large language model to generate the target vehicle control solution based on multiple historical vehicle control solutions, target environment data, and vehicle control capabilities supported by the vehicle.

[0043] Figure 2 A flow chart of a method for generating a vehicle control solution provided by an embodiment of the present disclosure is shown in FIG. Figure 2 As shown, the method includes:

[0044] Step 201: In response to vehicle startup, identify user-associated identity information.

[0045] The execution subject of this embodiment is a vehicle control solution generating device, which can be coupled to the vehicle, or the vehicle control solution generating device can also be coupled to the server.

[0046] In this embodiment, driving comfort, driving safety and ease of use are improved. After the vehicle is started, the vehicle can be controlled by a vehicle control solution, wherein the vehicle control solution includes control parameters of at least one on-board device associated with the vehicle, such as seat adjustment angle, air-conditioning temperature, window lifting height, etc.

[0047] In order to make the vehicle control solution more in line with the user's usage habits, the current vehicle control solution can be generated based on the user's historical vehicle control data.

[0048] Optionally, in response to the vehicle starting, the identity information associated with the user can be identified. The user's identity information can be identified by face recognition, or by manually entering an account number and password, or based on identification information of a terminal device held by the user, which is not limited in the present disclosure.

[0049] It should be noted that the identity information is obtained after obtaining full authorization from the user. For example, a prompt message can be sent to the user's terminal device in advance to prompt the user whether to authorize the vehicle control solution generation device to obtain the identity information. The user can authorize the operation through a preset consent control or a disapproval control.

[0050] Step 202: Acquire multiple historical vehicle control solutions that match the user based on the identity information, and collect current target environment data.

[0051] In this embodiment, a plurality of historical vehicle control schemes that have been used by the user in the past can be stored in advance. The historical vehicle control schemes can accurately represent the historical usage habits of the user.

[0052] Therefore, after obtaining the user's identity information, multiple historical vehicle control solutions matching the user can be obtained based on the identity information, so as to generate a current vehicle control solution based on the user's historical usage habits.

[0053] Optionally, in order to make the vehicle control solution more adaptable to environmental changes, for example, in rainy and snowy weather or strong sunlight, the wiper speed and sunshade position are automatically adjusted. The vehicle control solution can also be generated based on the user's historical usage habits and real-time environmental data.

[0054] Therefore, the current target environment data can also be collected, wherein the target environment data includes but is not limited to temperature, humidity, rainfall, ultraviolet intensity, air quality index, etc.

[0055] Step 203: input the multiple historical vehicle control schemes, target environment data, and vehicle control capability data associated with the vehicle into a preset large language model, so that the large language model outputs at least one vehicle control scheme to be selected, and the vehicle control scheme includes control parameters of at least one vehicle-mounted device associated with the vehicle.

[0056] In this embodiment, in order to improve the accuracy and efficiency of the generated vehicle control solution, a large language model can be called to realize the generation of the vehicle control solution.

[0057] Optionally, after obtaining multiple historical vehicle control solutions and target environment data respectively, the multiple historical vehicle control solutions and target environment data can be processed by a large language model to generate a vehicle control solution, wherein the vehicle control solution includes control parameters of at least one vehicle-mounted device associated with the vehicle.

[0058] As an implementable method, in order to avoid the candidate vehicle control schemes generated by the large language model exceeding the vehicle's vehicle control capabilities, multiple historical vehicle control schemes, target environment data, and vehicle-related vehicle control capability data can also be input into the preset large language model so that the large language model outputs at least one candidate vehicle control scheme.

[0059] In order to enable users to select the target vehicle control plan more flexibly, the large language model can simultaneously generate two different candidate vehicle control plans: a personalized plan and a general plan based on multiple historical vehicle control plans currently input, target environment data, and vehicle-related vehicle control capability data.

[0060] It should be noted that the general solution will be closer to the current target environment data. For example, the user prefers the cool mode, and the air-conditioning temperature is generally set to a lower level. However, when the outside temperature is low, the general solution will increase the temperature of the car air-conditioning based on the target environment data. The personalized solution will be more in line with the user's usage habits. For example, the user prefers the cool mode, and the air-conditioning temperature is generally set to a lower level. However, when the outside temperature is low, the personalized solution will not increase the temperature of the car air-conditioning based on the outside temperature, but will control the car air-conditioning to maintain a temperature that is common to the user.

[0061] In order to enable the large language model to generate two different vehicle control solutions based on the same input data, different weight relationships can be set in advance for the general solution and the personalized solution, so that the large language model can accurately generate vehicle control solutions based on the different weight relationships.

[0062] For example, in a general solution, the same type of vehicle-mounted equipment can be set with the same control parameters. For example, each seat is adjusted to the same angle, each window is adjusted to the same lifting height, and each vehicle-mounted air conditioner is set to the same wind speed, direction, temperature, etc.

[0063] In the personalized solution, different control parameters can be set for vehicle-mounted devices in different positions according to the user's usage habits and target environment data. For example, when user A sits in the main driver's seat, he is accustomed to adjusting the seat angle to 100 degrees, and sets a seat angle of 120 degrees for relatives and friends in the co-pilot seat. Therefore, when the vehicle starts, it is recognized that user A is sitting in the main driver's seat. The personalized solution can set a seat adjustment angle of 100 degrees for the main driver, but set a seat adjustment angle of 120 degrees for the co-pilot passenger, etc.

[0064] Step 204: Determine a current target vehicle control scheme based on at least one candidate vehicle control scheme, and control the vehicle to execute the target vehicle control scheme.

[0065] In this embodiment, after obtaining at least one candidate vehicle control scheme, a current target vehicle control scheme may be determined based on the at least one candidate vehicle control scheme, and the vehicle may be controlled to execute the target vehicle control scheme.

[0066] The vehicle control plan generation method provided in this embodiment generates a candidate vehicle control plan by acquiring multiple historical vehicle control plans, target environmental data and vehicle control capability data associated with the vehicle, and processes the above data based on a preset large language model, so as to quickly generate target vehicle control data that is more in line with the user's usage habits and real-time environmental data.

[0067] Optionally, based on any of the above embodiments, step 201 includes:

[0068] The associated image of the user is acquired through a preset image acquisition device.

[0069] An image recognition operation is performed on the associated image based on a preset face recognition algorithm, and the identity information of the user is determined based on the recognition result.

[0070] In this embodiment, the user's identity information can be identified through face recognition.

[0071] Optionally, an image acquisition device may be pre-installed in the vehicle. In response to the vehicle starting, the associated image of the user may be acquired through the image acquisition device. The associated image is acquired after obtaining full authorization from the user.

[0072] Furthermore, the associated image may be subjected to image recognition operation by a preset face recognition algorithm, and the identity information of the user may be determined based on the recognition result. Any algorithm capable of implementing face recognition operation may be used to implement the recognition operation of identity information, and the present disclosure does not limit this.

[0073] The vehicle control solution generation method provided in this embodiment pre-sets the image acquisition device, thereby enabling the acquisition of user-associated images based on the image acquisition device, and accurately identifying the user's identity information based on the face recognition algorithm, thereby improving the efficiency and accuracy of identity information recognition.

[0074] Further, based on any of the above embodiments, step 202 includes:

[0075] The first environmental data is collected by at least one preset vehicle-mounted sensor.

[0076] The second environment data is collected through a preset external data source.

[0077] The first environment data and the second environment data are determined as the target environment data, wherein the first environment data and the second environment data do not overlap.

[0078] In this embodiment, the target environmental data includes, but is not limited to, parameters such as temperature, humidity, rainfall, ultraviolet intensity, and air quality index.

[0079] For the above parameters, some parameters can be collected by preset vehicle sensors, while some parameters cannot be collected by vehicle sensors. Therefore, in order to ensure the comprehensiveness of the target environmental data obtained, an external data source can also be set, where the external data source can be a network channel, a broadcast channel, etc., and environmental parameters such as air quality index can be obtained from the network channel.

[0080] Therefore, the first environment data is collected by at least one preset vehicle-mounted sensor, the second environment data is collected by a preset external data source, and the first environment data and the second environment data are determined as target environment data, wherein the first environment data and the second environment data do not overlap.

[0081] The vehicle control solution generation method provided in this embodiment pre-sets at least one vehicle-mounted sensor and an external data source, so as to obtain more comprehensive and real-time target environment data based on at least one vehicle-mounted sensor and an external data source, so as to subsequently generate a target vehicle control solution that is more suitable for the current environment.

[0082] Further, based on any of the above embodiments, the at least one vehicle control solution to be selected includes a general solution and a personalized solution. The method further includes:

[0083] Preset text description information is input into the large language model, and the text description information is used to instruct the large language model to generate the general solution based on the multiple historical vehicle control solutions, target environment data and the vehicle control capability data according to a preset first weight relationship, and to generate the personalized solution based on the multiple historical vehicle control solutions, target environment data and the vehicle control capability data according to a preset second weight relationship.

[0084] At least one historical case associated with the user is input into the large language model respectively, and the historical case includes historical input data associated with the user and historical general cases and historical personalized cases determined based on the historical input data, so that the large language model learns to generate a candidate vehicle control solution based on the at least one historical case, wherein the historical input data includes at least one vehicle control solution and historical environmental data historically used by the user, and the historical general case and historical personalized case are pre-set based on the historical input data.

[0085] In this embodiment, in order to enable the large language model to generate general solutions and personalized solutions based on multiple input historical vehicle control solutions, target environment data, and vehicle-associated vehicle control capability data, preset text description information and at least one historical case associated with the user can be input into the large language model in advance to fine-tune the large language model so that the large language model can generate a vehicle control solution that is more in line with the user's usage habits.

[0086] Among them, the text description information is used to instruct the large language model to generate a general solution based on multiple historical vehicle control solutions, target environment data and vehicle control capability data according to a preset first weight relationship, and to generate a personalized solution based on multiple historical vehicle control solutions, target environment data and vehicle control capability data according to a preset second weight relationship.

[0087] Among them, the general solution will pay more attention to the current target environment data, while the personalized solution will pay more attention to the user's usage habits. Therefore, the weight factor of the impact of the target environment data on the general solution is greater than that of the historical vehicle control solution, and the weight factor of the impact of the historical vehicle control solution on the personalized solution is greater than that of the target environment data.

[0088] It should be noted that the general solution refers to the vehicle control solution that does not distinguish between locations, in which the target environment data has a greater weight factor for this type of solution. For example, if the large language model is input with the following inputs: the current temperature is 38 degrees Celsius, the humidity is 70%, and the ultraviolet rays are high, the large model will recommend vehicle control solutions related to ventilation, cooling, and shading, such as turning on seat ventilation, turning on the air conditioner and setting it to 24 degrees Celsius, and starting the shading system (such as window sunshades or sunroof sunshades).

[0089] Personalized solutions refer to vehicle control solutions for specific locations, and different personalized recommendation solutions can be provided for different locations. The user's historical vehicle control data has a greater weight factor on this type of solution. For example, if it is detected that the user likes to have a 10-minute seat massage after getting in the car, this solution will be recommended first. Real-time environmental data can also intervene in the user's personalized recommendation solutions. For example, if it is detected that the user likes to turn on seat ventilation, but the current real-time temperature is low (such as below 20 degrees Celsius), the seat ventilation solution will not be recommended.

[0090] In addition, in order to enable the large language model to have the ability to generate vehicle control solutions, at least one historical case associated with the user can be input into the large language model respectively, and the historical case includes historical input data associated with the user and historical general cases and historical personalized cases determined based on the historical input data, so that the large language model can learn to generate candidate vehicle control solutions based on at least one historical case, wherein the historical input data includes at least one vehicle control solution and historical environmental data historically used by the user, and the historical general cases and historical personalized cases are pre-set based on the historical input data.

[0091] For example, the historical general cases and historical personalized cases are pre-set by the technician based on the historical input data associated with the user. Alternatively, the case generation model obtained through pre-training can be generated based on the historical input data and the preset first weight relationship and second weight relationship, and the present disclosure does not limit this.

[0092] As an implementable method, before fine-tuning the large language model using at least one historical case associated with a user, a large amount of training data can be used to train the large language model. The training data includes general solutions, personalized solutions, and associated historical cases associated with multiple users. The historical cases include at least one vehicle control solution and historical environmental data used by the user in the past. This enables the large language model to have the ability to generate general solutions and personalized solutions.

[0093] By using user-associated historical input data and historical cases to perform the above-mentioned fine-tuning process on the large language model, the large language model can generate a vehicle control solution that is more in line with the user's usage habits.

[0094] In addition, since the large language model uses a large amount of training data to train the model in advance, it already has the ability to generate general solutions and personalized solutions. For users who use the large language model to generate vehicle control solutions for the first time, since they are not associated with a personalized vehicle control solution, a general solution can be generated through the large language model. Determine the adjustment parameters for the vehicle-mounted equipment during the user's multiple uses of the general solution, adjust the general solution based on the adjustment parameters, and obtain multiple personalized solutions associated with the user. Therefore, the large language model can be fine-tuned and personalized solutions can be generated based on the personalized solutions associated with the user.

[0095] The vehicle control plan generation method provided in this embodiment pre-inputs historical vehicle control plans and text description information into a large language model, thereby enabling the large language model to accurately generate candidate vehicle control plans based on the currently input historical vehicle control plans, target environment data, and vehicle control capability data associated with the vehicle.

[0096] Further, based on any of the above embodiments, after step 203, the method further includes:

[0097] The large language model is controlled to generate the general solution and the personalized solution based on the target environment data and different weight ratios corresponding to multiple historical vehicle control solutions.

[0098] In this embodiment, in order to enable the large language model to generate two different vehicle control solutions based on the same input data, different weight ratios can be set in advance for the target environment data and multiple historical vehicle control solutions. When generating a general solution, the weight ratio of the target environment data is greater than the weight ratio of multiple historical vehicle control solutions. When generating a personalized solution, the weight ratio of multiple historical vehicle control solutions is greater than the weight ratio of the target environment data.

[0099] This enables the large language model to be controlled to generate general and personalized solutions based on the target environment data and the different weight ratios corresponding to multiple historical vehicle control solutions.

[0100] Further, based on any of the above embodiments, the controlling the large language model to generate the general solution and the personalized solution based on the target environment data and different weight ratios corresponding to a plurality of historical vehicle control solutions includes:

[0101] Controlling the large language model to generate the general solution based on the multiple historical vehicle control solutions, the target environment data, and the vehicle control capability data according to a preset first weight relationship, wherein in the first weight relationship, the weight of the target environment data is greater than the weight of the multiple historical vehicle control solutions;

[0102] Control the large language model to generate the personalized solution based on the multiple historical vehicle control solutions, the target environment data and the vehicle control capability data according to a preset second weight relationship, wherein in the second weight relationship, the weights of the multiple historical vehicle control solutions are greater than the weight of the target environment data.

[0103] In this embodiment, in order to enable the large language model to generate two different vehicle control solutions based on the same input data, a first weight relationship can be set in advance for the general solution and a second weight relationship can be set for the personalized solution, so that the large language model can accurately generate vehicle control solutions based on the different weight relationships.

[0104] Therefore, after a plurality of historical vehicle control schemes, target environment data, and vehicle control capability data associated with the vehicle are input into a preset large language model, the large language model can generate a general scheme based on the plurality of historical vehicle control schemes, target environment data, and vehicle control capability data according to a preset first weight relationship based on the indication of the text description information, wherein in the first weight relationship, the weight of the target environment data is greater than the weight of the plurality of historical vehicle control schemes. For example, in the first weight relationship, the weight of the target environment data may be 80%, and the weight of the plurality of historical vehicle control schemes may be 20%.

[0105] In addition, the large language model can also be controlled to generate a personalized solution based on multiple historical vehicle control solutions, target environment data, and vehicle control capability data according to a preset second weight relationship, wherein in the second weight relationship, the weight of multiple historical vehicle control solutions is greater than the weight of the target environment data. For example, in the first weight relationship, the weight of the target environment data of multiple historical vehicle control solutions can be 80%, while the weight of the target environment data can be 20%.

[0106] The vehicle control solution generation method provided in this embodiment sets a first weight relationship for the general solution and a second weight relationship for the personalized solution in advance, so that the large language model can generate two different vehicle control solutions for users to choose from based on the same input content, so that the vehicle control solution used is more in line with the actual needs of the user.

[0107] Figure 3 A flow chart of a method for generating a vehicle control solution according to another embodiment of the present disclosure is provided. Based on any of the above embodiments, Figure 3 As shown, after step 204, the following steps are also included:

[0108] Step 301: The identity information associated with the user and the target vehicle control solution are associated and stored in a preset storage path, wherein the storage path is used to store multiple historical vehicle control solutions that match the user.

[0109] Step 302: In response to the storage time associated with any historical vehicle control solution in the storage path reaching a preset time threshold, the historical vehicle control solution is deleted.

[0110] In this embodiment, after the target vehicle control solution is generated, in order to provide a data basis for the subsequent generation of vehicle control solutions, the user's associated identity information and the target vehicle control solution can also be associated and stored in a preset storage path, where the storage path is used to store multiple historical vehicle control solutions that match the user. Therefore, when the user starts the vehicle later, the user's identity information can be automatically identified and the user's historical vehicle control solutions can be loaded.

[0111] Furthermore, in order to ensure the real-time nature of the data and make the generated vehicle control plan more in line with the user's recent usage habits, in response to the storage time associated with any historical vehicle control plan in the storage path reaching a preset time threshold, the historical vehicle control plan is deleted. For example, the preset time threshold may be 30 days, and the historical vehicle control plan stored for more than 30 days may be deleted.

[0112] Optionally, in order to protect user privacy and data security, the identity information and the target vehicle control solution may be encrypted before being associated and stored in the preset storage path. Any encryption algorithm may be used to implement the data encryption operation, and the present disclosure does not limit this.

[0113] The vehicle control scheme generation method provided in this embodiment associates and stores the target vehicle control scheme and the user's identity information after generating the target vehicle control scheme, so that when the user starts the vehicle later, the user's identity information can be automatically identified and the user's historical vehicle control scheme can be loaded. In addition, by regularly deleting the historical vehicle control scheme, it can be ensured that the target vehicle control scheme generated later is more in line with the user's recent usage habits.

[0114] Figure 4 This is a flow chart of a method for generating a vehicle control solution provided by another embodiment of the present disclosure. Based on any of the above embodiments, the target environment data includes multiple environment parameters. Figure 4 As shown, after step 204, the following steps are also included:

[0115] Step 401: For any target environmental parameter in the target environmental data, collect the current environmental parameter in real time.

[0116] Step 402: Calculate the difference between the current environmental parameter and the target environmental parameter.

[0117] Step 403: If the difference is less than the difference threshold associated with the environmental parameter, the control parameters of the vehicle-mounted equipment associated with the environmental parameter in the target vehicle control scheme and the current environmental parameter are input into the large language model, so that the large language model generates the adjustment parameters associated with the vehicle-mounted equipment based on the control parameters and the current environmental parameter.

[0118] Step 404: perform adjustment operations on the vehicle-mounted device based on the adjustment parameters.

[0119] In this embodiment, in order to make the currently used target vehicle control scheme more consistent with the actual environmental data, when the real-time environment changes, the target vehicle control scheme can also be adjusted based on the environmental data.

[0120] Optionally, after the vehicle is controlled based on the target vehicle control scheme, the real-time environment of the vehicle often changes as the vehicle travels, as time passes, etc. The target environment data includes multiple environmental parameters, such as temperature, humidity, ultraviolet intensity, rainfall, etc.

[0121] In order to make the currently used target vehicle control solution more in line with the actual environmental data, the current environmental parameters are collected in real time for any target environmental parameter in the target environmental data. The collection operation of each environmental parameter can be realized through two methods: sensors and external data sources.

[0122] Furthermore, in order to be able to adjust the target vehicle control scheme in a timely manner when the environment changes greatly, a difference threshold associated with the environment parameter can be set for each environment parameter. Therefore, the difference between the current environment parameter and the target environment parameter can be calculated. If the difference is less than the difference threshold associated with the environment parameter, the control parameters of the vehicle-mounted device associated with the environment parameter in the target vehicle control scheme and the current environment parameter are input into the large language model, so that the large language model generates the adjustment parameters associated with the vehicle-mounted device based on the control parameters and the current environment parameters. The vehicle-mounted device is adjusted based on the adjustment parameters.

[0123] Taking practical applications as an example, the environmental parameter may be a temperature parameter. When the external temperature is gradually rising based on the difference between the current environmental parameter and the target environmental parameter, the external circulation mode of the air conditioner may be turned on to accelerate the cooling of the vehicle interior; as the vehicle travels or the environment changes, when the temperature reaches a suitable level, the air conditioner may be automatically switched to the internal circulation mode to maintain a comfortable temperature in the vehicle. This dynamic adjustment mechanism not only improves the user's comfort, but also effectively reduces energy consumption.

[0124] The vehicle control solution generation method provided in this embodiment monitors environmental data in real time and automatically updates the vehicle control solution when the environment changes significantly, thereby making the currently used target vehicle control solution more suitable for the actual environment.

[0125] Figure 5 This is a flow chart of a method for generating a vehicle control solution provided by another embodiment of the present disclosure. Based on any of the above embodiments, the at least one vehicle control solution to be selected includes a general solution and a personalized solution. Figure 5 As shown, step 204 includes:

[0126] Step 501: Display the currently generated general solution and the personalized solution on a preset display interface respectively.

[0127] Step 502: In response to a selection operation of a user on any vehicle control solution, the vehicle control solution selected by the user is determined as a target vehicle control solution.

[0128] In this embodiment, in order to make the final generated target vehicle control solution more in line with the user's personalized needs, after generating a general solution and a personalized solution based on the large language model, the user can also select the target vehicle control solution from the general solution and the personalized solution according to actual needs.

[0129] Optionally, after the general solution and the personalized solution are generated based on the large language model, the currently generated general solution and the personalized solution can be displayed on a preset display interface, so that the user can browse the general solution and the personalized solution on the display interface.

[0130] Further, in response to a user's selection operation on any vehicle control scheme, the vehicle control scheme selected by the user is determined as a target vehicle control scheme.

[0131] Among them, the user can select the vehicle control scheme by manually triggering the operation of any vehicle control scheme, or the user can select the vehicle control scheme through a simple voice command, and the present disclosure does not impose any restrictions on this.

[0132] The vehicle control solution generation method provided in this embodiment generates a general solution and a personalized solution at the same time, and determines the target vehicle control solution based on the user's selection operation, so that the user can more flexibly select the current vehicle control solution according to actual needs, so that the currently used target vehicle control solution is more in line with the user's personalized needs.

[0133] Figure 6 This is a flow chart of a method for generating a vehicle control solution provided by another embodiment of the present disclosure. Based on any of the above embodiments, the at least one vehicle control solution to be selected includes a general solution and a personalized solution. Figure 6 As shown, step 204 includes:

[0134] Step 601: Display the currently generated general solution and the personalized solution on a preset display interface respectively.

[0135] Step 602: Obtain editing data generated by the user for any vehicle control solution, wherein the editing data includes control parameters of at least one vehicle-mounted device.

[0136] Step 603: adjusting the vehicle control scheme selected by the user based on the edited data, and determining the adjusted vehicle control scheme as the target vehicle control scheme.

[0137] In this embodiment, in order to make the final generated target vehicle control solution more in line with the user's personalized needs, after generating a general solution and a personalized solution based on the large language model, the user can also edit any vehicle control solution according to actual needs to obtain the target vehicle control solution.

[0138] Optionally, after the general solution and the personalized solution are generated based on the large language model, the currently generated general solution and the personalized solution can be displayed on a preset display interface, so that the user can browse the general solution and the personalized solution on the display interface.

[0139] Furthermore, the user can perform editing operations by triggering any vehicle control scheme, wherein the user can edit and adjust the control parameters of any vehicle-mounted device in the currently triggered vehicle control scheme to generate editing data.

[0140] Accordingly, the edit data generated by the user for any vehicle control scheme can be obtained, and the edit data includes the control parameters of at least one vehicle-mounted device. The vehicle control scheme selected by the user is adjusted based on the edit data, and the adjusted vehicle control scheme is determined as the target vehicle control scheme.

[0141] As an implementable method, the user can adjust any vehicle control scheme by manually entering editing data in the display interface, or the user can also implement real-time adjustment operations on any vehicle control scheme by issuing language commands. The present disclosure does not impose any restrictions on this.

[0142] Figure 7 A schematic diagram of an application scenario provided by an embodiment of the present disclosure, such as Figure 7As shown, after obtaining multiple historical vehicle control solutions 71 and target environment data 72 respectively, the multiple historical vehicle control solutions 71, the target environment data 72 and the vehicle control capability data 73 supported by the current vehicle can be input into the preset large language model 74. The general solution 75 and the personalized solution 76 output by the large language model 74 are obtained. Based on the user's triggering operation, the current target vehicle control solution 77 is determined in the general solution 75 and the personalized solution 76, so that the vehicle can be controlled based on the target vehicle control solution 77 later.

[0143] The vehicle control solution generation method provided in this embodiment can make the currently used target vehicle control solution more in line with the user's personalized needs by editing any solution based on the user's editing operation after simultaneously generating a general solution and a personalized solution.

[0144] Figure 8 A schematic diagram of the structure of a vehicle control solution generating device provided in an embodiment of the present disclosure, such as Figure 8 As shown, the device includes: an identification module 81, an acquisition module 82, a generation module 83 and a processing module 84. Among them, the identification module 81 is used to identify the identity information associated with the user in response to the vehicle starting. The acquisition module 82 is used to obtain multiple historical vehicle control schemes matching the user based on the identity information, and collect the current target environment data. The generation module 83 is used to input the multiple historical vehicle control schemes, target environment data and vehicle control capability data associated with the vehicle into a preset large language model, so that the large language model outputs at least one vehicle control scheme to be selected, and the vehicle control scheme includes the control parameters of at least one vehicle-mounted device associated with the vehicle. The processing module 84 is used to determine the current target vehicle control scheme based on at least one vehicle control scheme to be selected, and control the vehicle to execute the target vehicle control scheme.

[0145] Further, based on any of the above embodiments, the recognition module includes: a first acquisition unit, configured to acquire the associated image of the user through a preset image acquisition device; a recognition unit, configured to perform an image recognition operation on the associated image based on a preset face recognition algorithm, and determine the identity information of the user based on the recognition result.

[0146] Further, based on any of the above embodiments, the acquisition module includes: a second acquisition unit, configured to acquire the first environmental data through at least one preset vehicle-mounted sensor; a third acquisition unit, configured to acquire the second environmental data through a preset external data source; and a determination unit, configured to determine the first environmental data and the second environmental data as the target environmental data, wherein the first environmental data and the second environmental data do not overlap.

[0147] Further, on the basis of any of the above embodiments, wherein the at least one vehicle control scheme to be selected includes a general scheme and a personalized scheme. The device further includes: an input module, which is used to input preset text description information into the large language model, wherein the text description information is used to instruct the large language model to generate the general scheme based on the multiple historical vehicle control schemes, target environment data and the vehicle control capability data according to a preset first weight relationship, and to generate the personalized scheme based on the multiple historical vehicle control schemes, target environment data and the vehicle control capability data according to a preset second weight relationship. A training module, which is used to input at least one historical case associated with the user into the large language model respectively, wherein the historical case includes the historical input data associated with the user and the historical general case and the historical personalized case determined based on the historical input data, so that the large language model learns to generate the vehicle control scheme to be selected based on the at least one historical case, wherein the historical input data includes at least one vehicle control scheme and historical environment data used by the user in history, and the historical general case and the historical personalized case are pre-set based on the historical input data.

[0148] Furthermore, based on any of the above embodiments, the device also includes: a control module, used to control the large language model to generate the general solution and the personalized solution based on the target environment data and different weight ratios corresponding to multiple historical vehicle control solutions.

[0149] Further, on the basis of any of the above embodiments, the control module further includes: a first generation unit, used to control the large language model to generate the general solution based on the multiple historical vehicle control solutions, target environment data and the vehicle control capability data according to a preset first weight relationship, wherein in the first weight relationship, the weight of the target environment data is greater than the weight of the multiple historical vehicle control solutions. A second generation unit, used to control the large language model to generate the personalized solution based on the multiple historical vehicle control solutions, target environment data and the vehicle control capability data according to a preset second weight relationship, wherein in the second weight relationship, the weight of the multiple historical vehicle control solutions is greater than the weight of the target environment data.

[0150] Further, based on any of the above embodiments, the device further includes: a storage module, configured to associate and store the identity information associated with the user and the target vehicle control scheme in a preset storage path, wherein the storage path is used to store multiple historical vehicle control schemes matching the user. A deletion module, configured to delete the historical vehicle control scheme in response to the storage duration associated with any historical vehicle control scheme in the storage path reaching a preset duration threshold.

[0151] Further, based on any of the above embodiments, the target environment data includes multiple environment parameters. The device also includes: a collection module, which is used to collect the current environment parameters in real time for any target environment parameter in the target environment data. A calculation module, which is used to calculate the difference between the current environment parameters and the target environment parameters. An update module, which is used to input the control parameters of the vehicle-mounted equipment associated with the environment parameters in the target vehicle control scheme and the current environment parameters into the large language model if the difference is less than the difference threshold associated with the environment parameters, so that the large language model generates the adjustment parameters associated with the vehicle-mounted equipment based on the control parameters and the current environment parameters. An adjustment module, which is used to adjust the vehicle-mounted equipment based on the adjustment parameters.

[0152] Further, based on any of the above embodiments, the at least one vehicle control solution to be selected includes a general solution and a personalized solution. The processing module includes: a display unit, which is used to display the currently generated general solution and the personalized solution on a preset display interface. A selection unit, which is used to determine the vehicle control solution selected by the user as a target vehicle control solution in response to a user's selection operation on any vehicle control solution.

[0153] Further, based on any of the above embodiments, the at least one vehicle control scheme to be selected includes a general scheme and a personalized scheme. The processing module includes: a display unit, which is used to display the currently generated general scheme and the personalized scheme on a preset display interface. An acquisition unit, which is used to acquire the editing data generated by the user for any vehicle control scheme, wherein the editing data includes control parameters of at least one vehicle-mounted device. An adjustment unit, which is used to adjust the vehicle control scheme selected by the user based on the editing data, and determine the adjusted vehicle control scheme as the target vehicle control scheme.

[0154] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0155] According to an embodiment of the present disclosure, the present disclosure also provides a computer program product, which includes: a computer program, the computer program is stored in a readable storage medium, at least one processor of an electronic device can read the computer program from the readable storage medium, and at least one processor executes the computer program so that the electronic device executes the solution provided by any of the above embodiments.

[0156] Fig. 9A schematic diagram of an electronic device provided for an embodiment of the present disclosure. The electronic device 900 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0157] like Fig. 9 As shown, the device 900 includes a computing unit 901, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 902 or a computer program loaded from a storage unit 908 into a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the device 900 can also be stored. The computing unit 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0158] A number of components in the device 900 are connected to the I / O interface 905, including: an input unit 906, such as a keyboard, a mouse, etc.; an output unit 907, such as various types of displays, speakers, etc.; a storage unit 908, such as a disk, an optical disk, etc.; and a communication unit 909, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 909 allows the device 900 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0159] The computing unit 901 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 901 performs the various methods and processes described above, such as the vehicle control solution generation method. For example, in some embodiments, the vehicle control solution generation method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 908. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 900 via the ROM 902 and / or the communication unit 909. When the computer program is loaded into the RAM 903 and executed by the computing unit 901, one or more steps of the vehicle control solution generation method described above may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured to execute the vehicle control solution generation method in any other appropriate manner (e.g., by means of firmware).

[0160] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0161] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0162] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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 foregoing.

[0163] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0164] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0165] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0166] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0167] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A vehicle control solution generation method, comprising: In response to the vehicle being started, identifying identity information associated with the user; Acquiring multiple historical vehicle control solutions matching the user based on the identity information, and collecting current target environment data; Inputting the plurality of historical vehicle control schemes, target environment data, and vehicle control capability data associated with the vehicle into a preset large language model, so that the large language model outputs at least one vehicle control scheme to be selected, wherein the vehicle control scheme includes control parameters of at least one vehicle-mounted device associated with the vehicle; A current target vehicle control scheme is determined based on at least one candidate vehicle control scheme, and the vehicle is controlled to execute the target vehicle control scheme.

2. The method according to claim 1, wherein: The identification information associated with the user includes: Capturing the associated image of the user through a preset image acquisition device; An image recognition operation is performed on the associated image based on a preset face recognition algorithm, and the identity information of the user is determined based on the recognition result.

3. The method according to claim 1, wherein: The collecting of current target environment data includes: Collecting first environmental data through at least one preset vehicle-mounted sensor; Collecting second environment data through a preset external data source; The first environment data and the second environment data are determined as the target environment data, wherein the first environment data and the second environment data do not overlap.

4. The method according to claim 1, wherein: The at least one vehicle control solution to be selected includes a general solution and a personalized solution; After the plurality of historical vehicle control schemes, the target environment data and the vehicle control capability data associated with the vehicle are input into the preset large language model, the method further comprises: The large language model is controlled to generate the general solution and the personalized solution based on the target environment data and different weight ratios corresponding to a plurality of historical vehicle control solutions.

5. The method according to claim 4, wherein: The controlling the large language model to generate the general solution and the personalized solution based on the target environment data and different weight ratios corresponding to a plurality of historical vehicle control solutions includes: Controlling the large language model to generate the general solution based on the multiple historical vehicle control solutions, the target environment data, and the vehicle control capability data according to a preset first weight relationship, wherein in the first weight relationship, the weight of the target environment data is greater than the weight of the multiple historical vehicle control solutions; Control the large language model to generate the personalized solution based on the multiple historical vehicle control solutions, the target environment data and the vehicle control capability data according to a preset second weight relationship, wherein in the second weight relationship, the weights of the multiple historical vehicle control solutions are greater than the weight of the target environment data.

6. The method according to claim 1, after controlling the vehicle to execute the target vehicle control scheme, further comprises: The identity information associated with the user and the target vehicle control scheme are stored in a preset storage path, wherein the storage path is used to store multiple historical vehicle control schemes matching the user; In response to a storage time associated with any historical vehicle control scheme in the storage path reaching a preset time threshold, the historical vehicle control scheme is deleted.

7. The method according to any one of claims 1 to 6, wherein the target environment data comprises multiple environment parameters; After controlling the vehicle to execute the target vehicle control scheme, the method further includes: For any target environmental parameter in the target environmental data, collect the current environmental parameter in real time; Calculating the difference between the current environmental parameter and the target environmental parameter; If the difference is less than the difference threshold associated with the environmental parameter, inputting the control parameter of the vehicle-mounted device associated with the environmental parameter in the target vehicle control scheme and the current environmental parameter into the large language model, so that the large language model generates the adjustment parameter associated with the vehicle-mounted device based on the control parameter and the current environmental parameter; An adjustment operation is performed on the vehicle-mounted device based on the adjustment parameter.

8. The method according to any one of claims 1 to 6, wherein the at least one vehicle control solution to be selected comprises a general solution and a personalized solution; The determining of the current target vehicle control scheme based on at least one candidate vehicle control scheme includes: The currently generated general solution and the personalized solution are respectively displayed on a preset display interface; In response to a selection operation of a user on any vehicle control scheme, the vehicle control scheme selected by the user is determined as a target vehicle control scheme.

9. The method according to any one of claims 1 to 6, wherein the at least one vehicle control solution to be selected comprises a general solution and a personalized solution; The determining of the current target vehicle control scheme based on at least one candidate vehicle control scheme includes: The currently generated general solution and the personalized solution are respectively displayed on a preset display interface; Acquire editing data generated by the user for any vehicle control solution, wherein the editing data includes control parameters of at least one vehicle-mounted device; An adjustment operation is performed on the vehicle control scheme selected by the user based on the edited data, and the adjusted vehicle control scheme is determined as a target vehicle control scheme.

10. A vehicle control scheme generating device, comprising: an identification module for identifying identity information associated with a user in response to vehicle startup; An acquisition module, used to acquire multiple historical vehicle control solutions matching the user based on the identity information, and to collect current target environment data; a generating module, configured to input the plurality of historical vehicle control schemes, target environment data, and vehicle control capability data associated with the vehicle into a preset large language model, so that the large language model outputs at least one vehicle control scheme to be selected, wherein the vehicle control scheme includes control parameters of at least one vehicle-mounted device associated with the vehicle; The processing module is used to determine a current target vehicle control scheme based on at least one candidate vehicle control scheme, and control the vehicle to execute the target vehicle control scheme.

11. The device according to claim 10, wherein: The identification module comprises: A first acquisition unit, configured to acquire the associated image of the user through a preset image acquisition device; The recognition unit is used to perform an image recognition operation on the associated image based on a preset face recognition algorithm, and determine the identity information of the user based on the recognition result.

12. The device according to claim 10, wherein: The acquisition module comprises: A second collection unit, used to collect first environmental data through at least one preset vehicle-mounted sensor; A third collection unit, used to collect second environment data through a preset external data source; A determination unit is used to determine the first environment data and the second environment data as the target environment data, wherein the first environment data and the second environment data do not overlap.

13. The device according to claim 10, wherein: The at least one vehicle control solution to be selected includes a general solution and a personalized solution; the device also includes: A control module is used to control the large language model to generate the general solution and the personalized solution based on the target environment data and different weight ratios corresponding to multiple historical vehicle control solutions.

14. The device according to claim 13, wherein the control module further comprises: A first generating unit, configured to control the large language model to generate the general scheme based on the plurality of historical vehicle control schemes, the target environment data, and the vehicle control capability data according to a preset first weight relationship, wherein in the first weight relationship, the weight of the target environment data is greater than the weight of the plurality of historical vehicle control schemes; A second generation unit is used to control the large language model to generate the personalized plan based on the multiple historical vehicle control plans, the target environment data and the vehicle control capability data according to a preset second weight relationship, wherein in the second weight relationship, the weight of the multiple historical vehicle control plans is greater than the weight of the target environment data.

15. The apparatus according to claim 10, further comprising: A storage module, used for associating and storing the identity information associated with the user and the target vehicle control scheme in a preset storage path, wherein the storage path is used for storing a plurality of historical vehicle control schemes matching the user; The deletion module is used to delete the historical vehicle control scheme in response to the storage time associated with any historical vehicle control scheme in the storage path reaching a preset time threshold.

16. The device according to any one of claims 10 to 15, wherein the target environment data comprises a plurality of environment parameters; The device also includes: A collection module, used for collecting current environmental parameters in real time for any target environmental parameter in the target environmental data; A calculation module, used for calculating the difference between the current environmental parameter and the target environmental parameter; an updating module, configured to input the control parameters of the vehicle-mounted device associated with the environmental parameter in the target vehicle control scheme and the current environmental parameter into the large language model if the difference is less than the difference threshold associated with the environmental parameter, so that the large language model generates the adjustment parameters associated with the vehicle-mounted device based on the control parameters and the current environmental parameter; An adjustment module is used to perform an adjustment operation on the vehicle-mounted device based on the adjustment parameters.

17. The device according to any one of claims 10 to 15, wherein the at least one vehicle control solution to be selected comprises a general solution and a personalized solution; and the processing module comprises: A display unit, used to display the currently generated general solution and the personalized solution respectively on a preset display interface; The selection unit is used to determine the vehicle control scheme selected by the user as a target vehicle control scheme in response to a selection operation of the user on any vehicle control scheme.

18. The device according to any one of claims 10 to 15, wherein the at least one vehicle control solution to be selected comprises a general solution and a personalized solution; and the processing module comprises: A display unit, used to display the currently generated general solution and the personalized solution respectively on a preset display interface; An acquisition unit, configured to acquire the edited data generated by the user for any vehicle control solution, wherein the edited data includes control parameters of at least one vehicle-mounted device; An adjustment unit is used to adjust the vehicle control scheme selected by the user based on the editing data, and determine the adjusted vehicle control scheme as a target vehicle control scheme.

19. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 9.

20. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-9.

21. A computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 9.

Images