Vehicle scenario mode generation method and apparatus, electronic device and storage medium

Abstract

A vehicle scenario mode generation method, a vehicle scenario mode generation apparatus, an electronic device, a storage medium and a vehicle. The method comprises: acquiring vehicle scenario mode data, the vehicle scenario mode data comprising vehicle state data, user state data, environment state data and instruction data corresponding to a vehicle scenario mode state; on the basis of the vehicle state data, the user state data, the environment state data and the instruction data corresponding to the vehicle scenario mode state, marking a category label for a vehicle scenario mode instruction; on the basis of data of the vehicle scenario mode state and the category label corresponding to the vehicle scenario mode instruction, training a classification neural network model; acquiring current vehicle scenario data; inputting the current vehicle scenario data into the classification neural network model, and outputting classification data corresponding to the vehicle scenario mode state; and, on the basis of the classification data, recommending a vehicle operating mode or controlling the vehicle operating mode.

Description

Vehicle scene mode generation method, device, electronic device and storage medium Technical Field

[0001] The present application relates to the field of scene modes, and in particular to a vehicle scene mode generation method, a vehicle scene mode generation device, an electronic device, a storage medium, and a vehicle. Background Art

[0002] New energy vehicle models are experiencing explosive growth, and with the field of artificial intelligence becoming increasingly intelligent, scenes of interaction between humans and machines are appearing more and more frequently. In order to cope with the above situation, two modes are mostly adopted in existing technical applications: 1. Preset scene mode. Car manufacturers preset some commonly used scene modes in functional applications, such as baby mode, rest mode, refreshment mode, rain mode, haze mode, etc. Users usually need to actively click to start or close the scene mode, and the system cannot automatically identify which mode is suitable for the current environment. 2. Custom scene mode. Users need to actively set music, lights, air conditioning, seats and other functions, and they also need to manually trigger the start of their functions. From this, it can be seen that the current scene mode solution is not very intelligent and cannot easily meet the scene model that users want based on the current environment.

[0003] Therefore, a vehicle scene mode generation solution is needed, which can automatically generate scene modes according to the vehicle environment and constructively recommend scene modes based on the current environment.

[0004] Summary of the Invention

[0005] The object of the present invention is to provide a vehicle scene mode generation method, a vehicle scene mode generation device, an electronic device, a storage medium and a vehicle, so as to solve at least one of the above-mentioned technical problems.

[0006] The present invention provides the following solutions:

[0007] According to one aspect of the present invention, a vehicle scene mode generation method is provided, the vehicle scene mode generation method comprising:

[0008] Get vehicle scene mode data;

[0009] The vehicle scene mode data includes vehicle state data, user state data, environment state data and instruction data corresponding to the vehicle scene mode state;

[0010] The vehicle scene mode instruction is labeled with a category label according to the vehicle state data, the user state data, the environment state data, and the instruction data corresponding to the vehicle scene mode state;

[0011] Training a classification neural network model based on the data of the vehicle scene mode state and the category label corresponding to the vehicle scene mode instruction;

[0012] Get current vehicle scene data;

[0013] Inputting the current vehicle scene data into a classification neural network model, and outputting classification data corresponding to the vehicle scene mode state;

[0014] A vehicle operating mode is recommended or controlled based on the classification data.

[0015] Furthermore, the training of a classification neural network model based on the data of the vehicle scene mode state and the category label corresponding to the vehicle scene mode instruction includes:

[0016] Obtain vehicle scene mode data of group users;

[0017] Training a large model of a classification neural network based on the vehicle scene pattern data of the group of users;

[0018] Obtain vehicle scene mode data for individual users;

[0019] Training a small model of a classification neural network based on the vehicle scene pattern data of the individual user;

[0020] According to the large model of the classification neural network and the small model of the classification neural network, classification data corresponding to the vehicle scene mode state is output.

[0021] Furthermore, the small model for training the classification neural network includes:

[0022] Training a large model of a classification neural network based on the vehicle scene pattern data of the group of users;

[0023] Outputting classification data of the vehicle scene mode status corresponding to the group of users according to the large model of the classification neural network;

[0024] A small model of a classification neural network is trained based on the vehicle scene mode data of the individual user and the vehicle scene mode state classification data of the corresponding group of users.

[0025] Furthermore, it is characterized in that the training classification neural network model includes:

[0026] Updating and acquiring vehicle scene mode data includes updating vehicle scene mode data;

[0027] Based on the updated vehicle scene pattern data, the large model of the classification neural network and the small model of the classification neural network are trained iteratively simultaneously;

[0028] Wherein, updating the vehicle scene mode data includes updating the vehicle scene mode data corresponding to the user characteristics.

[0029] Furthermore, it is characterized in that the training classification neural network model also includes:

[0030] Updating and acquiring vehicle scene mode data includes updating vehicle scene mode data;

[0031] Based on the updated vehicle scene pattern data, the large model of the classification neural network and the small model of the classification neural network are trained iteratively simultaneously;

[0032] Wherein, updating the vehicle scene mode data includes updating the characteristics of the corresponding user and the vehicle scene mode data corresponding to the user characteristics.

[0033] Furthermore, it is characterized in that the recommending a vehicle operating mode or controlling a vehicle operating mode based on the classification data includes:

[0034] The result of selecting and executing the vehicle operating mode when monitoring the recommended vehicle operating mode;

[0035] Monitor the results of vehicle operation mode modification when controlling the vehicle operation mode;

[0036] According to the execution result of monitoring the vehicle operation mode, the vehicle scene mode data is iteratively obtained.

[0037] According to two aspects of the present invention, there is provided a vehicle scene pattern generating device, the vehicle scene pattern generating device comprising:

[0038] A scene data module is used to obtain vehicle scene mode data, wherein the vehicle scene mode data includes vehicle state data, user state data, environment state data, and instruction data corresponding to the vehicle scene mode state;

[0039] A category labeling module, configured to label the vehicle scene mode instruction with a category label based on the vehicle state data, the user state data, the environment state data, and the instruction data corresponding to the vehicle scene mode state;

[0040] A training classification module, configured to train a classification neural network model based on the vehicle scene mode state data and the category label corresponding to the vehicle scene mode instruction;

[0041] Current scene data module, used to obtain current vehicle scene data;

[0042] A classification data module, configured to input current vehicle scene data into a classification neural network model and output classification data corresponding to the vehicle scene mode state;

[0043] The operating mode module is used to recommend a vehicle operating mode or control the vehicle operating mode according to the classification data.

[0044] According to three aspects of the present invention, there is provided an electronic device, comprising: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0045] A computer program is stored in the memory, and when the computer program is executed by the processor, the processor is caused to perform the steps of the vehicle scene mode generating method.

[0046] According to four aspects of the present invention, a computer-readable storage medium is provided, comprising: a computer program executable by an electronic device is stored therein, and when the computer program runs on the electronic device, the electronic device executes the steps of the vehicle scene mode generation method.

[0047] According to five aspects of the present invention, there is provided a vehicle comprising:

[0048] An electronic device, configured to implement the steps of the vehicle scene pattern generating method;

[0049] a processor, the processor running a program, and executing the steps of the vehicle scene mode generating method based on data output by the electronic device when the program is running;

[0050] The storage medium is used to store a program, and when the program is running, it executes the steps of the vehicle scene mode generation method for data output from the electronic device.

[0051] Through the above solution, the following beneficial technical effects are achieved:

[0052] This application uses vehicle status data, user status data, environment status data and instruction data corresponding to the vehicle scene mode status as training input data to learn the vehicle control method made by the user in response to the environment, so that the training model is closer to the real user intention.

[0053] This application trains models through group users and individual users respectively, and the mode recommendations made based on the two models are more comprehensive and more suitable for current users.

[0054] This application synchronizes model updates by iterating large and small models simultaneously, obtaining timely and accurate model recommendations to adapt to the continuous growth or changes of users. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] FIG1 is a flowchart of a vehicle scene mode generation method provided by one or more embodiments of the present invention.

[0056] FIG2 is a structural diagram of a vehicle scene pattern generating device provided by one or more embodiments of the present invention.

[0057] FIG3 is a schematic diagram of vehicle scene data training according to a specific embodiment of the present invention.

[0058] FIG4 is a schematic diagram of a vehicle scene mode recommendation according to a specific embodiment of the present invention.

[0059] FIG5 is a schematic diagram of a vehicle scene mode implementation according to a specific embodiment of the present invention.

[0060] FIG6 is a block diagram of an electronic device structure of a vehicle scene mode generation method provided by one or more embodiments of the present invention. DETAILED DESCRIPTION

[0061] The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0062] FIG1 is a flowchart of a vehicle scene mode generation method provided by one or more embodiments of the present invention.

[0063] The vehicle scene pattern generation method shown in FIG1 includes:

[0064] Step S1, obtaining vehicle scene mode data;

[0065] Step S2, the vehicle scene mode data includes vehicle state data, user state data, environment state data and instruction data corresponding to the vehicle scene mode state;

[0066] Step S3, marking a category label for the vehicle scene mode instruction based on the vehicle state data, the user state data, the environment state data, and the instruction data corresponding to the vehicle scene mode state;

[0067] Step S4, training a classification neural network model based on the vehicle scene mode state data and the category label corresponding to the vehicle scene mode instruction;

[0068] Step S5, obtaining current vehicle scene data;

[0069] Step S6, inputting the current vehicle scene data into the classification neural network model, and outputting classification data corresponding to the vehicle scene mode state;

[0070] Step S7: recommending a vehicle operating mode or controlling the vehicle operating mode based on the classification data.

[0071] Specifically, based on the vehicle state, user state, environmental state, and vehicle scenario mode state, the user's instructions for parameter adjustment and function activation, etc., become a set of data for generating a vehicle scenario mode, serving as the raw input data. The vehicle scenario mode instructions are labeled with category labels. Based on the category label instructions, the vehicle scenario mode data is characterized by features. A classification neural network model is trained using the vehicle scenario mode state data and the category labels corresponding to the vehicle scenario mode instructions, so that the output data generated by the model closely matches the user's selection. By inputting the current vehicle scenario data into the classification neural network model, classification data corresponding to the vehicle scenario mode state is output, i.e., instructions for possible vehicle scenario modes to be selected. Based on the classification data, the recommended vehicle operating mode or controlled vehicle operating mode can be made to closely match the vehicle operating mode selected by the user, i.e., the vehicle operating mode generated by the parameter adjustment and function activation instructions. Operations that require a user request to execute use the recommended vehicle operating mode, while operations that do not require a user request use the controlled vehicle operating mode.

[0072] In this embodiment, training a classification neural network model based on the data of the vehicle scene mode state and the category label corresponding to the vehicle scene mode instruction includes:

[0073] Obtain vehicle scene mode data of group users;

[0074] Based on the vehicle scene pattern data of group users, a large model of classification neural network is trained;

[0075] Obtain vehicle scene mode data for individual users;

[0076] Based on the vehicle scene pattern data of individual users, a small model of the classification neural network is trained;

[0077] According to the large model of the classification neural network and the small model of the classification neural network, classification data corresponding to the vehicle scene mode state is output.

[0078] Specifically, based on the vehicle scene mode data of a group of users, a large model of a classification neural network is trained. This model contains the same vehicle state data, user state data, environmental state data, and instruction data corresponding to the vehicle scene mode state under different user characteristics. Based on the vehicle scene mode data of an individual user, a small model of a classification neural network is trained. This model only contains the same vehicle state data, user state data, environmental state data, and instruction data corresponding to the vehicle scene mode state under the characteristics of the target user. The large model has the breadth of data and can increase redundancy for special cases. The small model has the uniqueness of data and can make recommendations for the current user more targeted. Classification data can be generated by finding overlapping or close parts in the output data of the two models to recommend vehicle operation modes or control vehicle operation modes.

[0079] In this embodiment, the small model for training the classification neural network includes:

[0080] Based on the vehicle scene pattern data of group users, a large model of classification neural network is trained;

[0081] Output classification data of vehicle scene mode status corresponding to the group of users based on the large model of the classification neural network;

[0082] A small model of the classification neural network is trained based on the vehicle scene mode data of individual users and the vehicle scene mode state classification data of the corresponding group of users.

[0083] Specifically, small models can be trained independently of the large model, or they can be trained based on the large model and then combined with individual user characteristics. Training small models based on the large model prevents over-emphasis on individual user characteristics, which could distort the small model's output. This could lead to the recommended or controlled vehicle operating mode being operated at an extreme state for onboard equipment, severely impacting other passengers.

[0084] For example, using individual user data, the network parameters that are most responsive to the individual user are obtained from the large model as the initial parameters of the small model. Then, the data containing the user's personal characteristic information is added to the small model.

[0085] In this embodiment, training the classification neural network model includes:

[0086] Updating and acquiring vehicle scene mode data includes updating vehicle scene mode data;

[0087] Based on the updated vehicle scene pattern data, the large model of the classification neural network and the small model of the classification neural network are trained iteratively simultaneously;

[0088] Wherein, updating the vehicle scene mode data includes updating the vehicle scene mode data corresponding to the user characteristics.

[0089] Specifically, the vehicle and environmental states change as the vehicle operates and moves, and the user's physical characteristics can also vary. Therefore, the instructions corresponding to the vehicle's scenario mode state are not static. This requires iterating the model through updates to ensure that it does not become ineffective over time.

[0090] In this embodiment, training the classification neural network model further includes:

[0091] Updating and acquiring vehicle scene mode data includes updating vehicle scene mode data;

[0092] Based on the updated vehicle scene pattern data, the large model of the classification neural network and the small model of the classification neural network are trained iteratively simultaneously;

[0093] Wherein, updating the vehicle scene mode data includes updating the characteristics of the corresponding user and the vehicle scene mode data corresponding to the user characteristics.

[0094] Specifically, in addition to updating the vehicle scene mode data under the corresponding user characteristics, the vehicle scene mode data also includes updating the corresponding user characteristics. The vehicle state and environmental state are non-biological state changes. However, changes in user characteristics are different from vehicle state and environmental state. In addition to being affected by vehicle operation and movement, they are also affected by factors outside the vehicle environment. Changes in user characteristics do not necessarily lead to changes in the vehicle scene mode. Therefore, when training the model, the user characteristics can be separately used as an update at the same level as the vehicle scene mode corresponding to the user characteristics.

[0095] In this embodiment, recommending a vehicle operating mode or controlling a vehicle operating mode based on the classification data includes:

[0096] The result of selecting and executing the vehicle operating mode when monitoring the recommended vehicle operating mode;

[0097] Monitor the results of vehicle operation mode modification when controlling the vehicle operation mode;

[0098] According to the execution result of monitoring the vehicle operation mode, the vehicle scene mode data is iteratively obtained.

[0099] Specifically, after recommending a vehicle operating mode or controlling a vehicle operating mode based on the classification data, it is necessary to further understand the user's reaction to the recommended vehicle operating mode or the control of the vehicle operating mode. For example, by monitoring the results of the vehicle operating mode selection execution, the person's inclination towards the current vehicle operating mode can be learned, and by monitoring the results of the vehicle operating mode modification execution, the person's rejection of the current vehicle operating mode can be learned. Based on the results of monitoring the vehicle operating mode execution, the vehicle scene mode data obtained can be iteratively acquired. For example, the person's operation on the vehicle operating mode can be used as instruction data corresponding to the vehicle scene mode state, and then used again to train the model, so that the model output results are closer to the user's inclination and avoid user rejection.

[0100] FIG2 is a structural diagram of a vehicle scene pattern generating device provided by one or more embodiments of the present invention.

[0101] The vehicle scene pattern generation device shown in FIG2 includes: a scene data module, a category label module, a training classification module, a current scene data module, a classification data module, and an operation mode module;

[0102] A scene data module is used to obtain vehicle scene mode data, which includes vehicle status data, user status data, environment status data, and instruction data corresponding to the vehicle scene mode status;

[0103] A category labeling module is used to label the vehicle scene mode instruction with a category label based on the vehicle state data, the user state data, the environment state data, and the instruction data corresponding to the vehicle scene mode state;

[0104] A training classification module is used to train a classification neural network model based on the data of the vehicle scene mode state and the category label corresponding to the vehicle scene mode instruction;

[0105] Current scene data module, used to obtain current vehicle scene data;

[0106] The classification data module is used to input the current vehicle scene data into the classification neural network model and output the classification data corresponding to the vehicle scene mode state;

[0107] The operating mode module is used to recommend a vehicle operating mode or control the vehicle operating mode based on the classification data.

[0108] It is worth noting that although this system only discloses the scene data module, category label module, training classification module, current scene data module, classification data module, and operation mode module, relatively speaking, what the present invention wants to express is that, based on the above-mentioned basic functional modules, those skilled in the art can arbitrarily add one or more functional modules in combination with the existing technology to form an infinite number of embodiments or technical solutions. In other words, this system is open rather than closed. Just because this embodiment only discloses individual basic functional modules, it cannot be considered that the scope of protection of the claims of the present invention is limited to the above-mentioned basic functional modules.

[0109] Through the above solution, the following beneficial technical effects are achieved:

[0110] This application uses vehicle status data, user status data, environment status data and instruction data corresponding to the vehicle scene mode status as training input data to learn the vehicle control method made by the user in response to the environment, so that the training model is closer to the real user intention.

[0111] This application trains models through group users and individual users respectively, and the mode recommendations made based on the two models are more comprehensive and more suitable for current users.

[0112] This application synchronizes model updates by iterating large and small models simultaneously, obtaining timely and accurate model recommendations to adapt to the continuous growth or changes of users.

[0113] FIG3 is a schematic diagram of vehicle scene data training according to a specific embodiment of the present invention.

[0114] FIG4 is a schematic diagram of a vehicle scene mode recommendation according to a specific embodiment of the present invention.

[0115] FIG5 is a schematic diagram of a vehicle scene mode implementation according to a specific embodiment of the present invention.

[0116] In one specific embodiment, as shown in Figure 3, the local vehicle system sends the vehicle's current state data to the cloud to obtain the scene mode instructions recommended by the large model. The large model's recommended scene mode instructions are then sent back to the local vehicle-side small network, which provides feedback with scene mode instructions that reflect user characteristics. Based on the scene mode instructions, a scene mode is generated to control various vehicle devices, such as the air conditioning, lighting, music, and seats. The parameters of the small model are iteratively updated and simultaneously transmitted to the cloud to iteratively update the large model. The large model cloud synchronizes the response parameters to the small model.

[0117] The first step is to collect a large amount of vehicle status, user status, external environment status data state_data and its corresponding instruction data instruct_data in various scene modes.

[0118] Step 2: Divide these instruction data into KN categories in detail (the KN categories mainly include all scenario situations, with an estimated range of 10 < KN < 500. For example: cloudy mode, light rain mode, moderate rain mode, heavy rain mode, rainstorm mode, typhoon mode, light snow mode, heavy snow mode, ……, simple refreshing mode, extremely refreshing mode, super-awake refreshing mode, etc., with relatively detailed classification). Then label these instructions with the corresponding category labels.

[0119] Step 3: Train a large classification neural network model through a large amount of scenario mode state data (state_data) and their corresponding instruction data category labels (KN1, KN2, KN3, KN, KN5, ……). (Network model algorithms: DenseNet, ResNet, CNN, GNN, RNN, etc., and various mature classification convolutional neural networks can be tried).

[0120] Step 4: Use the large cloud model and the in-vehicle device local individual user scenario mode data to generate a small individual recommendation network model.

[0121] In the large network model generated in Step 3, when training the network, the characteristics of the group data are considered. The recommended scenario modes obtained from the large model are only suitable for general situations. For some individual users, the scenario modes obtained from the large model may not be suitable. Therefore, some characteristic data of the user itself also need to be considered to obtain the most suitable scenario mode for the user.

[0122] The generation of the small model is to use the individual user data to obtain the part of the network parameters with the highest response to the individual user in the large model as the initial parameters of the small model. Then, the data with the personal characteristic information of the user is added to the small model.

[0123] Step 5: Synchronous update between the data of the large model and the small model. In real life, the owner of a car may change, and the user's hobbies and habits may also change gradually. Correspondingly, in some states, the originally suitable scenario mode may no longer be appropriate, and the algorithm model needs to gradually perceive these changes. The same is true for group users; the habits of group users will also change with the environment. Therefore, the small model also needs to timely perceive the changes of individuals, and the large model needs to timely perceive the changes of the group.

[0124] The parameter update and exchange between the large model and the small model need to be carried out under a suitable strategy (such as when the user parks for a long time, when the user is resting, etc.).

[0125] When optimizing the large model, it is necessary to continuously absorb the custom scenario mode data set by the user to complete the optimization of its own model.

[0126] In another specific embodiment, as shown in Figures 4 and 5,

[0127] 1. Obtain state data (state_data) on the vehicle, the user, and the external environment. Send the state_data to the cloud server via network transmission.

[0128] 2. The cloud server model processes the received data and initiates model inference calculations to predict the classification result Group_classification_result to which the data belongs. The cloud server then sends the predicted classification result data Group_classification_result to the vehicle terminal.

[0129] 3. The vehicle computer inputs the received Group_classification_result and the individual user's characteristic data User_characteristic_data stored in the vehicle computer into the vehicle computer small model.

[0130] Among them, the vehicle-side recommendation small model receives two types of data: Group_classification_result and User_characteristic_data, and then uses the vehicle-side local small network algorithm model to infer scene mode instructions with personal characteristics.

[0131] 4. The vehicle computer executes the final scene mode instructions recommended by the intelligent system.

[0132] 5. Monitor user experience effects.

[0133] If the user is not satisfied with the recommended scene mode, such as adjusting the air conditioning, lights, temperature, windows, music, etc. in the scene mode, the car computer will save the adjustment data and transmit it to the server cloud model and the car computer model to update the network model at an appropriate time.

[0134] FIG6 is a block diagram of an electronic device structure of a vehicle scene mode generation method provided by one or more embodiments of the present invention.

[0135] As shown in FIG6 , the present application provides an electronic device, comprising: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0136] A computer program is stored in the memory. When the computer program is executed by the processor, the processor executes the steps of a vehicle scene mode generation method.

[0137] The present application also provides a computer-readable storage medium storing a computer program executable by an electronic device. When the computer program runs on the electronic device, the electronic device executes the steps of a vehicle scene mode generation method.

[0138] The present application also provides a vehicle, comprising:

[0139] An electronic device for implementing the steps of the vehicle scene pattern generation method;

[0140] a processor, the processor running a program, and executing the steps of the vehicle scene mode generation method based on data output by the electronic device when the program is running;

[0141] The storage medium is used to store a program, and when the program is running, the program executes the steps of the vehicle scene mode generation method for data output from the electronic device.

[0142] The communication bus mentioned in the electronic device mentioned above may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used in the figure, but this does not mean that there is only one bus or only one type of bus.

[0143] The electronic device includes a hardware layer, an operating system layer running on the hardware layer, and an application layer running on the operating system. The hardware layer includes hardware such as a central processing unit (CPU), a memory management unit (MMU), and memory. The operating system can be any one or more computer operating systems that control electronic devices through processes, such as the Linux operating system, the Unix operating system, the Android operating system, the iOS operating system, or the Windows operating system. In the embodiments of the present invention, the electronic device can be a handheld device such as a smartphone or a tablet computer, or an electronic device such as a desktop computer or a portable computer, which is not particularly limited in the embodiments of the present invention.

[0144] The execution subject of the electronic device control in the embodiment of the present invention can be an electronic device, or a functional module in the electronic device that can call a program and execute the program. The electronic device can obtain the firmware corresponding to the storage medium. The firmware corresponding to the storage medium is provided by the supplier. The firmware corresponding to different storage media can be the same or different, and is not limited here. After the electronic device obtains the firmware corresponding to the storage medium, it can write the firmware corresponding to the storage medium into the storage medium, specifically, burn the firmware corresponding to the storage medium into the storage medium. The process of burning the firmware into the storage medium can be implemented using existing technology and will not be described in detail in the embodiment of the present invention.

[0145] The electronic device can also obtain a reset command corresponding to the storage medium. The reset command corresponding to the storage medium is provided by the supplier. The reset commands corresponding to different storage media can be the same or different, and are not limited here.

[0146] In this case, the storage medium of the electronic device is a storage medium in which the corresponding firmware is written. The electronic device can respond to the reset command corresponding to the storage medium in which the corresponding firmware is written, thereby resetting the storage medium in which the corresponding firmware is written according to the reset command corresponding to the storage medium. The process of resetting the storage medium according to the reset command can be implemented in the existing technology and will not be described in detail in the embodiments of the present invention.

[0147] For the convenience of description, the above devices are described as various units and modules according to their functions. Of course, when implementing this application, the functions of each unit and module can be implemented in the same or multiple software and / or hardware.

[0148] Those skilled in the art will understand that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by those skilled in the art in the art to which the present invention pertains. It should also be understood that terms such as those defined in common dictionaries should be understood to have meanings consistent with those in the context of the prior art and, unless specifically defined, will not be interpreted in an idealized or overly formal sense.

[0149] For simplicity of description, the method embodiments are described as a series of actions. However, those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because certain steps can be performed in other orders or simultaneously according to the embodiments of the present invention. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0150] From the description of the above embodiments, it can be seen that those skilled in the art can clearly understand that the present application can be implemented by means of software plus the necessary general-purpose hardware platform. Based on this understanding, the technical solution of the present application, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments of the present application or certain portions of the embodiments.

[0151] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for generating a vehicle scenario mode, characterized in that, The vehicle scenario mode generation method includes: Obtain vehicle scenario mode data; The vehicle scenario mode data includes vehicle status data, user status data, environmental status data, and instruction data corresponding to the vehicle scenario mode status; According to the vehicle status data, user status data, environmental status data, and instruction data corresponding to the vehicle scenario mode status, label category tags for the vehicle scenario mode instructions; Train a classification neural network model based on the data of the vehicle scenario mode status and the category tags corresponding to the vehicle scenario mode instructions; Obtain current vehicle scenario data; Input the current vehicle scenario data into the classification neural network model to output classification data corresponding to the vehicle scenario mode status; Recommend a vehicle operation mode or control a vehicle operation mode based on the classification data.

2. The vehicle scenario mode generation method according to claim 1, wherein The training of the classification neural network model according to the data of the vehicle scenario mode status and the category tags corresponding to the vehicle scenario mode instructions includes: Obtain vehicle scenario mode data of a group of users; Train a large model of a classification neural network based on the vehicle scenario mode data of the group of users; Obtain vehicle scenario mode data of an individual user; Train a small model of a classification neural network based on the vehicle scenario mode data of the individual user; Output classification data corresponding to the vehicle scenario mode status according to the large model of the classification neural network and the small model of the classification neural network.

3. The vehicle scenario mode generation method according to claim 2, wherein The training of the small model of the classification neural network includes: Train a large model of a classification neural network based on the vehicle scenario mode data of the group of users; Output classification data corresponding to the vehicle scenario mode status of the group of users according to the large model of the classification neural network; Train a small model of a classification neural network based on the vehicle scenario mode data of the individual user and the classification data of the vehicle scenario mode status of the group of users corresponding thereto.

4. The vehicle scene mode generation method according to any one of claims 1 to 3, characterized in that The training of the classification neural network model includes: Updating and obtaining vehicle scenario mode data includes updating vehicle scenario mode data; Synchronously and iteratively train the large model of the classification neural network and the small model of the classification neural network according to the updated vehicle scenario mode data; Among them, updating vehicle scenario mode data includes updating vehicle scenario mode data under corresponding user characteristics.

5. The vehicle scene mode generation method according to any one of claims 1 to 3, characterized in that, The training of the classification neural network model further includes: Updating and obtaining vehicle scenario mode data includes updating vehicle scenario mode data; Synchronously and iteratively train the large model of the classification neural network and the small model of the classification neural network according to the updated vehicle scenario mode data; Among them, updating vehicle scenario mode data includes updating the characteristics of the corresponding user and the vehicle scenario mode data corresponding to the user characteristics.

6. The vehicle scene mode generation method according to any one of claims 1 to 3, characterized in that The recommending a vehicle operation mode or controlling a vehicle operation mode according to the classification data includes: Monitor the execution result of the selection of the vehicle operation mode when recommending a vehicle operation mode; Monitor the execution result of the modification of the vehicle operation mode when controlling the vehicle operation mode; Iteratively obtain vehicle scenario mode data according to the monitored execution result of the vehicle operation mode.

7. A vehicle scene mode generation device, characterized in that, The vehicle scenario mode generation device includes: A scene data module for obtaining vehicle scene mode data, where the vehicle scene mode data includes vehicle status data, user status data, environmental status data, and instruction data corresponding to the vehicle scene mode status; A category label module for labeling category labels for vehicle scene mode instructions according to the vehicle status data, user status data, environmental status data, and instruction data corresponding to the vehicle scene mode status; A training classification module for training a classification neural network model according to the data of the vehicle scene mode status and the category labels corresponding to the vehicle scene mode instructions; A current scene data module for obtaining current vehicle scene data; A classification data module for inputting the current vehicle scene data into the classification neural network model and outputting classification data corresponding to the vehicle scene mode status; An operation mode module for recommending or controlling the vehicle operation mode according to the classification data; 8. An electronic device, characterized in that, Comprising: A processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory complete mutual communication through the communication bus; A computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the vehicle scene mode generation method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, Comprising: It stores a computer program executable by an electronic device, and when the computer program runs on the electronic device, the electronic device executes the steps of the vehicle scene mode generation method according to any one of claims 1 to 6.

10. A vehicle, characterized in that, Comprising: An electronic device for implementing the steps of the vehicle scene mode generation method according to any one of claims 1 to 6; A processor, the processor runs a program, and when the program runs, it executes the steps of the vehicle scene mode generation method according to any one of claims 1 to 6 for the data output from the electronic device; A storage medium for storing a program, and when the program runs, it executes the steps of the vehicle scene mode generation method according to any one of claims 1 to 6 for the data output from the electronic device.

Images