Vehicle machine system control method, device, equipment, medium and program product
By acquiring and processing data in the vehicle computer system, using prediction models to predict user operation behaviors, and controlling resource allocation in advance, the slow response problem caused by lag in the vehicle computer system is solved, and the system fluency and user experience are improved.
Patent Information
- Application Number
- CN202510321053.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-18
- Publication Date
- 2025-07-08
AI Technical Summary
The lag-up processing method of the vehicle-machine system in the prior art is difficult to ensure timely response of users' operations, resulting in slow response speed and poor user experience.
By obtaining vehicle status information, time information and external environment information, data processing and feature extraction are performed, the user's operation behavior is predicted using the prediction model, and the resource allocation and response of the vehicle-machine system are controlled in advance based on the prediction results.
It improves the response speed of the vehicle and machine system to users' operating behavior, enhances the system fluency and user experience, and conforms to user usage habits.
Smart Images
Figure CN120277388A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the technical field of intelligent vehicles, and particularly to a method, device, equipment, medium and program product for controlling a vehicle-mounted system. Background Art
[0002] The vehicle-mounted system, also known as the core program of the in-vehicle infotainment system or in-vehicle computer system, is a set of electronic device systems integrated in modern vehicles and an indispensable part of modern vehicles. The vehicle-mounted system is mainly responsible for managing vehicle-mounted hardware and software resources and is the cornerstone of the vehicle computer system. The vehicle-mounted system plays a crucial role in the vehicle, responsible for coordinating various hardware devices and software application programs to ensure their efficient and stable operation. The vehicle-mounted system can not only provide rich multimedia entertainment functions and navigation services, but also realize various convenient functions such as intelligent interconnection and voice control.
[0003] Lag is a common problem that easily occurs in the vehicle-mounted system. Currently, the lag of the vehicle-mounted system is usually handled by restarting the vehicle-mounted system, but this handling method has a slow response speed to user operations, it is difficult to ensure the fluency of the vehicle-mounted system, and the user experience is poor. Summary of the Invention
[0004] This application provides a method, device, equipment, medium and program product for controlling a vehicle-mounted system, aiming to solve the defect that the existing method for handling the lag of the vehicle-mounted system is difficult to ensure the timely response of the vehicle-mounted system to user operations, and improve the response speed of the vehicle-mounted system to user operations.
[0005] In a first aspect, this application provides a method for controlling a vehicle-mounted system, including:
[0006] Obtain target data; the target data includes at least one of vehicle status information, time information, and external environment information;
[0007] Perform data processing on the target data to obtain feature data;
[0008] Input the feature data into a prediction model, and perform prediction on the feature data through the prediction model to obtain a behavior prediction result of the user's operation on the vehicle-mounted system of the vehicle output by the prediction model; the behavior prediction result includes at least one user operation behavior;
[0009] Based on the behavior prediction result, control the operation of the vehicle-mounted system.
[0010] Optionally, the performing data processing on the target data to obtain feature data includes:
[0011] Perform preprocessing on the target data to obtain processed data;
[0012] Perform dimensionality reduction on the processed data to obtain reduced-dimensional data;
[0013] Extract features from the reduced-dimensional data to obtain the feature data.
[0014] Optionally, the prediction model is trained in the following manner:
[0015] Obtain a training sample set; the training sample set includes multiple groups of historical feature data and historical behavior prediction results respectively corresponding to the multiple groups of historical feature data;
[0016] Train an initial model based on the training sample set to obtain the prediction model.
[0017] Optionally, controlling the operation of the in-vehicle system based on the behavior prediction result includes:
[0018] If the behavior prediction result is a user operation behavior, control the in-vehicle system to load data related to the user operation behavior based on the response priority of the user operation behavior, and after receiving a first instruction issued by the user corresponding to the user operation behavior, control the in-vehicle system to respond to the first instruction;
[0019] If the behavior prediction result is multiple user operation behaviors, control the in-vehicle system to load data related to each user operation behavior based on the response priority of each user operation behavior among the multiple user operation behaviors, and after receiving a second instruction issued by the user corresponding to any one of the multiple user operation behaviors, control the in-vehicle system to respond to the second instruction.
[0020] Optionally, the vehicle state information includes at least one of the vehicle's position information, driving state, and driving speed; the external environment information includes at least one of weather conditions and traffic conditions.
[0021] Optionally, the method for controlling the in-vehicle system further includes:
[0022] Every preset period, obtain a preset number of target instructions of the user for the in-vehicle system, and the behavior prediction result corresponding to each target instruction;
[0023] If the consistency rate between the preset number of target instructions and the behavior prediction results corresponding to each target instruction is lower than a preset threshold, optimize the parameters of the prediction model.
[0024] In a second aspect, the present application further provides an in-vehicle system control device, including:
[0025] The acquisition module is used to obtain target data; the target data includes at least one of vehicle status information, time information, and external environment information;
[0026] The processing module is used to process the target data to obtain feature data;
[0027] The prediction module is used to input the feature data into a prediction model, and predict the feature data through the prediction model to obtain a behavior prediction result of the user's operation on the vehicle's in-vehicle system output by the prediction model; the behavior prediction result includes at least one user operation behavior;
[0028] The control module is used to control the operation of the in-vehicle system based on the behavior prediction result.
[0029] In a third aspect, the present application also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the method described in the first aspect is implemented.
[0030] In a fourth aspect, the present application also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described in the first aspect is implemented.
[0031] In a fifth aspect, the present application also provides a computer program product, including a computer program. When the computer program is executed by a processor, the method described in the first aspect is implemented.
[0032] The in-vehicle system control method, device, equipment, medium, and program product provided by the present application process the target data to obtain feature data, predict the feature data through a prediction model to obtain the predicted user operation behavior on the in-vehicle system, and then control the in-vehicle system to react in advance to the predicted user operation behavior, thereby improving the response speed of the in-vehicle system to the user's actual operation behavior, improving the fluency of the in-vehicle system, making the in-vehicle system more in line with the user's usage habits, and enhancing the user experience. Description of the Drawings
[0033] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.
[0034] Figure 1 It is a schematic flowchart of the in-vehicle system control method provided by the embodiments of the present application;
[0035] Figure 2 It is a schematic structural diagram of a vehicle-mounted system control device provided by an embodiment of the present application;
[0036] Figure 3 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners
[0037] To make the objectives, technical solutions, and advantages of the present application clearer, the technical solutions in the present application will be clearly and completely described below with reference to the accompanying drawings in the present application. Apparently, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.
[0038] An embodiment of the present application provides a vehicle-mounted system control method, and the execution subject thereof may be an electronic device. For example, it may be a controller. Hereinafter, an example will be given with the execution subject of this method being a controller. Figure 1 It is a schematic flowchart of the vehicle-mounted system control method provided by an embodiment of the present application. Referring to Figure 1 , this method may include:
[0039] Step 110, obtain target data; the target data includes at least one of vehicle state information, time information, and external environment information;
[0040] Step 120, perform data processing on the target data to obtain feature data;
[0041] Step 130, input the feature data into a prediction model, and perform prediction on the feature data through the prediction model to obtain a behavior prediction result of the user for the vehicle-mounted system of the vehicle output by the prediction model; the behavior prediction result includes at least one user operation behavior;
[0042] Step 140, control the operation of the vehicle-mounted system based on the behavior prediction result.
[0043] In step 110, the controller may obtain the target data at intervals of a preset duration. The target data includes at least one of vehicle state information, time information, and external environment information. Among them, the vehicle state information mainly represents the current state of the vehicle, such as whether the vehicle is in a driving state now. The time information mainly represents the current moment. The external environment information mainly represents the environmental information outside the vehicle.
[0044] In step 120, the controller may perform data processing on the target data, for example: feature extraction, so as to obtain feature data. The feature data can represent the main features of the target data.
[0045] In step 130, the controller can input the feature data into the prediction model, and the prediction model predicts the feature data to obtain the behavior prediction result of the user for the in-vehicle system of the vehicle output by the prediction model. Specifically, the prediction model can be a deep learning model, such as a multi-modal fusion model. Deep learning algorithms, especially sequence models combined with the Transformer attention mechanism (such as Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU)), can predict the user's next operation requirements by analyzing the user's operation habits and historical behavior patterns, improving the prediction accuracy for complex behavior patterns, especially enhancing the model's analysis ability in multi-task concurrent scenarios. In the in-vehicle system, the deep learning model can be used to pre-load functions or content that the user may need in advance (such as navigation routes, music recommendations, commonly used applications, etc.), thereby reducing the user's waiting time. Combining current scenario characteristics, such as driving state, current geographical location, time period and other data features, the deep learning algorithm can further optimize the accuracy and real-time performance of the prediction, providing support for the intelligence and fluency of the in-vehicle system. The prediction model can use cross-entropy loss as the loss function, while optimizing the prediction accuracy, increasing the constraint weights on real-time performance and resource utilization. The behavior prediction result output by the prediction model includes at least one user operation behavior, that is to say, when the prediction model predicts that the user may perform multiple operations, multiple operations will be output.
[0046] In step 140, the controller can control the operation of the in-vehicle system based on the behavior prediction result. After the controller obtains the behavior prediction result output by the prediction model, the controller can control the in-vehicle system to make a corresponding reaction in advance according to the behavior prediction result. For example: allocate the computing resources of the in-vehicle system in advance, so that the in-vehicle system can quickly respond to the user's instruction after receiving the user's instruction (i.e., the user's actual behavior) that is consistent with the behavior prediction result.
[0047] The in-vehicle system control method provided by the embodiments of the present application processes the target data to obtain feature data, predicts the feature data through the prediction model to obtain the predicted user operation behavior for the in-vehicle system, and then controls the in-vehicle system to react in advance to the predicted user operation behavior, thereby improving the response speed of the in-vehicle system to the user's actual operation behavior, improving the fluency of the in-vehicle system, making the in-vehicle system more in line with the user's usage habits, and enhancing the user experience.
[0048] In some embodiments, processing the target data to obtain feature data includes: preprocessing the target data to obtain processed data; performing data dimensionality reduction on the processed data to obtain reduced-dimensional data; and extracting features from the reduced-dimensional data to obtain feature data.
[0049] The controller can preprocess the target data. For example, it can clean, filter, denoise, fill in missing values, remove outliers, standardize, etc. the target data to obtain processed data. Then, it performs dimensionality reduction on the processed data to extract important information by reducing the dimensionality of the data, thereby obtaining dimensionality-reduced data. Then, it extracts features from the dimensionality-reduced data to obtain feature data.
[0050] The in-vehicle infotainment system control method provided by the embodiments of this application preprocesses the target data, performs dimensionality reduction on the data, and extracts features to obtain feature data, so as to predict the user operation behavior for the in-vehicle infotainment system. Then, it controls the in-vehicle infotainment system to react in advance to the predicted user operation behavior, can select the features most relevant to the predicted behavior, reduce the computational overhead, thereby improving the response speed of the in-vehicle infotainment system to the actual user operation behavior, improving the fluency of the in-vehicle infotainment system, making the in-vehicle infotainment system more in line with the user's usage habits, and enhancing the user experience.
[0051] In some embodiments, the prediction model is trained in the following manner: obtaining a training sample set; the training sample set includes multiple groups of historical feature data and the historical behavior prediction results respectively corresponding to the multiple groups of historical feature data; training an initial model based on the training sample set to obtain a prediction model.
[0052] The controller can train the initial model through the training sample set, mainly training the ability of the initial model to obtain the behavior prediction result from the feature data, and when the number of predictions or the prediction accuracy of the initial model meets the target requirements, taking it as the prediction model. Among them, the training sample set includes multiple groups of historical feature data and the historical behavior prediction results respectively corresponding to the multiple groups of historical feature data. Each group of historical feature data and its corresponding historical behavior prediction result can be the historical feature data and its corresponding historical user operation behavior. The controller can anonymize the historical user operation data to avoid disclosing personal privacy, and use encrypted storage and transmission technologies to protect data security.
[0053] The in-vehicle infotainment system control method provided by the embodiments of this application trains the initial model through the training sample set to obtain a prediction model, which can improve the prediction accuracy of the prediction model, improve the fluency of the in-vehicle infotainment system, make the in-vehicle infotainment system more in line with the user's usage habits, and enhance the user experience.
[0054] In some embodiments, based on the behavior prediction result, the operation of the in-vehicle system is controlled, including: if the behavior prediction result is a user operation behavior, controlling the in-vehicle system to load data related to the user operation behavior based on the response priority of the user operation behavior, and after receiving the first instruction corresponding to the user operation behavior issued by the user, controlling the in-vehicle system to respond to the first instruction; if the behavior prediction result is multiple user operation behaviors, controlling the in-vehicle system to load data related to each user operation behavior based on the response priority of each user operation behavior among the multiple user operation behaviors, and after receiving the second instruction corresponding to any one of the multiple user operation behaviors issued by the user, controlling the in-vehicle system to respond to the second instruction.
[0055] Each user operation behavior corresponds to a preset response priority. The response priorities of different user operation behaviors can be the same or different. The higher the response priority of a user operation behavior, the faster the in-vehicle system needs to respond to this user operation behavior.
[0056] When the behavior prediction result of the prediction model is a user operation behavior, the controller can control the resource allocation of the in-vehicle system based on the response priority of the user operation behavior, load the data related to the user operation behavior, and after receiving the first instruction corresponding to the user operation behavior issued by the user, control the in-vehicle system to respond to the first instruction. For example, when the predicted user operation behavior is to turn on the reverse camera, the controller can control the resource allocation of the in-vehicle system based on the response priority of turning on the reverse camera, load the data of the reverse camera, and after receiving the first instruction to turn on the reverse camera issued by the user, control the in-vehicle system to turn on the reverse camera.
[0057] When the behavior prediction result of the prediction model is multiple user operation behaviors, the controller can control the resource allocation of the in-vehicle system based on the response priority of each user operation behavior among the multiple user operation behaviors, and load the data related to each user operation behavior. The higher the response priority of a user operation behavior, the earlier the data related to this user operation behavior is loaded. After receiving the second instruction corresponding to any one of the multiple user operation behaviors issued by the user, the controller controls the in-vehicle system to respond to the second instruction. For example, if the predicted user operation behaviors are to plan a navigation route and play target music, and the response priority of planning the navigation route is higher than that of playing target music, the controller can control the in-vehicle system to preferentially load the navigation data, then load the target music data, and after receiving the second instruction to open the navigation interface issued by the user, open the navigation interface and recommend the planned navigation route; or after receiving the second instruction to open the music playing interface issued by the user, open the music playing interface and recommend the target music.
[0058] The vehicle-mounted system control method provided by the embodiments of the present application can load data related to user operation behaviors based on the response priorities of user operation behaviors in the behavior prediction results. After the user issues relevant instructions, it can control the vehicle-mounted system to quickly respond to the user instructions, optimize the resource allocation of the vehicle-mounted system, improve the fluency of the vehicle-mounted system, make the vehicle-mounted system more in line with the user's usage habits, and enhance the user experience.
[0059] In some embodiments, the vehicle state information includes at least one of the position information, driving state, and driving speed of the vehicle; the external environment information includes at least one of the weather condition and traffic condition.
[0060] Specifically, when the vehicle is near home and the driving speed of the vehicle is lower than a preset threshold (such as 5 km / h), the prediction model predicts that the user may park the vehicle, and the user operation behavior may be to turn on the reverse camera. When the driving state of the vehicle is driving, the time information is the target time period, and the weather condition is the preset condition, the prediction model predicts that the user operation behavior is to play the target music. The traffic condition can also assist in the planning of the navigation path.
[0061] The vehicle-mounted system control method provided by the embodiments of the present application can, by collecting target data in real time, predict the user operation behaviors for the vehicle-mounted system in real time, and timely control the vehicle-mounted system to react in advance to the predicted user operation behaviors, thereby improving the response speed of the vehicle-mounted system to the actual user operation behaviors, improving the fluency of the vehicle-mounted system, making the vehicle-mounted system more in line with the user's usage habits, and enhancing the user experience.
[0062] In some embodiments, the vehicle-mounted system control method further includes: obtaining the target instructions of a preset number of times for the vehicle-mounted system by the user at each preset interval, and the behavior prediction results corresponding to each target instruction; if the consistency rate between the target instructions of the preset number of times and the behavior prediction results corresponding to each target instruction is lower than a preset threshold, optimizing the parameters of the prediction model.
[0063] At each preset interval (such as one month), the controller can obtain the target instructions of a preset number of times for the vehicle-mounted system by the user, and the behavior prediction results corresponding to each target instruction. If the consistency rate between the target instructions of the preset number of times and the behavior prediction results corresponding to each target instruction is lower than a preset threshold, it indicates that the prediction accuracy of the prediction model is poor. At this time, the parameters of the prediction model can be further optimized.
[0064] The vehicle-mounted system control method provided by the embodiments of the present application re-evaluates the prediction accuracy of the prediction model at each preset interval, and optimizes the parameters of the prediction model when the prediction accuracy is poor, which can further improve the prediction accuracy rate of the prediction model, improve the fluency of the vehicle-mounted system, make the vehicle-mounted system more in line with the user's usage habits, and enhance the user experience.
[0065] This application also provides an application example of the in-vehicle system control method described in the above embodiments.
[0066] Example 1:
[0067] Historical user operation behavior: In daily driving, the user often travels from home to the company and uses the navigation function to plan the route. This historical user operation behavior can be used to train a prediction model with the user's historical navigation data (such as time, starting point, ending point, and route taken).
[0068] Specific steps:
[0069] Data collection: Collect the current status information (such as the user's current location, system time, and traffic conditions).
[0070] Feature extraction: Time feature - Travel records at 8 am on weekdays indicate a high probability of the "home - company" route. Location feature - The current location is within the geographical range close to "home". Environmental feature - The real-time traffic conditions show that the common route is unobstructed.
[0071] Model prediction: Input the extracted multi-dimensional features into a prediction model (such as a time series model based on LSTM or Transformer). The output result is "high probability of selecting the company as the destination".
[0072] Optimized execution: The in-vehicle system pre-loads the navigation data from home to the company, including the route, traffic information, and common waypoints. When the user opens the navigation interface, it directly recommends "the company" as the destination and can display the optimal route at the same time.
[0073] Example 2:
[0074] Historical user operation behavior: When driving, the user often plays music through the in-vehicle system and habitually switches to the most frequently listened-to playlist or a specific type of music. This historical user operation behavior can be used to train a prediction model with the user's music playback history data, including song names, playlists, and types (such as pop, classical).
[0075] Specific steps:
[0076] Data collection: Record and obtain the current scene data (such as driving time, driving speed, and weather).
[0077] Feature extraction: Time feature: The user prefers to listen to soothing music during the evening commute home. Type feature: The user has played the "pop music playlist" multiple times recently. Environmental feature: Light music is often played when the weather is sunny.
[0078] Model prediction: Input the extracted features into a prediction model (such as a multi-modal fusion model that combines time, environment, and historical behavior). The output result is "recommend playing a specific song from the pop music playlist".
[0079] Optimized execution: The in-vehicle system caches the recommended playlists and songs in advance to avoid network lag during playback. When the user opens the music application, it directly enters the recommended playlist interface, reducing the user's selection operations.
[0080] Example 3:
[0081] Historical user operation behavior: When the user parks or reverses the vehicle, they usually quickly switch to the reverse camera or 360° surround view function.
[0082] Specific steps:
[0083] Data collection: Collect the user's driving speed and record the vehicle's location information (such as parking lot, home entrance).
[0084] Feature extraction: Status feature: The vehicle is in a low-speed or stationary state. Geographical feature: The current location is close to the entrance of the parking lot or the marked common parking points.
[0085] Model prediction: Use a prediction model based on time and space information to predict that the user has a high probability of needing the reverse camera inside the parking lot.
[0086] Optimized execution: When the in-vehicle system detects low-speed driving and proximity to the parking area, it pre-loads the reverse camera module in advance. After receiving the instruction from the user to turn on the reverse camera, it turns on the reverse camera.
[0087] Example 4:
[0088] Historical user operation behavior: The user often opens certain specific applications (such as weather query, radio station) during driving. This historical user operation behavior trains the prediction model using the applications frequently used by the user, their usage frequency, and time period (such as listening to the news radio in the morning).
[0089] Specific steps:
[0090] Data collection: Obtain the real-time driving status (such as the vehicle is in motion).
[0091] Feature extraction: Time feature: 7 - 8 am is the high-frequency usage period for the news radio. Application feature: There is a 90% probability of using the radio application during this time period in the past week.
[0092] Model prediction: Based on the time series prediction model, predict that the user will open the "radio station" during the current time period. The prediction model outputs a recommendation to pre-load the radio application first.
[0093] Optimized execution: The in-vehicle system starts the radio application in advance and caches the radio data to ensure immediate response when the user clicks. Highlight the "radio station" icon on the main interface of the in-vehicle system to simplify the user operation path.
[0094] Based on the above examples, the vehicle-mounted system control method provided by the embodiments of the present application can preload functions or content that the user may use according to the prediction results (such as navigation routes, common music lists); dynamically adjust the priority of system resources to ensure that the predicted key tasks obtain priority resource support; reduce the running frequency of low-priority tasks (such as application updates, cache cleaning) to avoid jamming caused by resource contention. Specifically, the vehicle-mounted system can be optimized for actual application scenarios. For example: Navigation optimization: Predict the destination based on the user's common routes and the current location, preload relevant map data in advance, and provide more accurate intelligent recommendations in real time when the user enters the destination. Entertainment system optimization: Based on the user's music playing habits, predict the next song that may be played, preload the cache in advance, and preload frequently used applications (such as music and video players) in advance. Optimization for complex driving scenarios: Prioritize loading the reverse image application when parking or reversing, and automatically predict navigation requirements and adjust the interface in advance when the vehicle is traveling at high speed.
[0095] The present application can also evaluate the performance improvement of the vehicle-mounted system through the response time of user operations (such as application startup time, navigation loading time). Measure the effect of the prediction model through prediction accuracy and user satisfaction surveys. And the prediction model can be updated regularly to adapt to the changing user behavior patterns. Adjust the prediction model parameters and resource management strategies to balance the performance of the vehicle-mounted system and the computing cost.
[0096] Based on the above description, the vehicle-mounted system control method provided by the present application can solve the following problems:
[0097] Slow response speed: Most current vehicle-mounted systems process user requests based on static logic and need to wait for an operation to trigger before loading resources, resulting in response delays. The deep learning prediction model reduces the loading waiting time by predicting user behavior in advance, greatly improving the fluency of the vehicle-mounted system.
[0098] Inaccurate resource allocation: Traditional vehicle-mounted systems are difficult to dynamically optimize resource allocation according to user needs, easily causing resource waste or insufficiency. The prediction model can accurately predict high-frequency operations and optimize resource allocation, making the vehicle-mounted system run more efficiently.
[0099] Lack of personalization: Most current technologies use general logic to process user needs and lack personalized functions. The prediction model provides predictions and optimizations that are more in line with personal usage habits based on user behavior data, enhancing the user experience.
[0100] Poor adaptability: Traditional vehicle-mounted systems respond slowly to changes in requirements in complex driving scenarios (such as switching navigation, playing music). The prediction model can adjust the prediction strategy by combining real-time data (such as location, time) to improve the adaptability of the vehicle-mounted system.
[0101] Operational redundancy: The existing in-vehicle infotainment system requires users to perform multiple steps to complete a target task, while the prediction model can reduce unnecessary interaction steps through intelligent prediction and improve operation efficiency.
[0102] The method for controlling an in-vehicle infotainment system provided in this application has the following advantages:
[0103] Significantly improve fluency: Reduce operation latency and provide a smoother user experience.
[0104] Improve resource utilization: Optimize hardware performance through intelligent scheduling and reduce system lags.
[0105] Enhance the competitiveness of the in-vehicle system and attract consumers: (1) Intelligent experience: Consumers of in-vehicle infotainment systems have an increasing demand for intelligent in-vehicle systems. By predicting user behavior and optimizing system response, a smooth and considerate intelligent experience is provided, attracting user groups with higher requirements for a sense of technology, being more in line with user usage habits, and enabling highly personalized services. (2) Differentiated advantage: Compared with traditional in-vehicle systems, the deep learning optimization technology appears more advanced and can be used as a marketing selling point to shape the brand's leading technology image and enhance consumers' desire to purchase.
[0106] Enhance brand loyalty and user word-of-mouth: (1) High-quality user experience: Quick response and personalized recommendations improve the driving experience, reduce dissatisfaction caused by in-vehicle infotainment system lags or complex operations, and thus increase user satisfaction. (2) Word-of-mouth spread: Intelligent in-vehicle functions are likely to trigger discussions and recommendations among users. Especially in the Internet era, a good experience is more easily spread through social media, bringing additional exposure to the brand.
[0107] Increase the premium ability of high-end models: (1) Added value: The intelligent in-vehicle system is one of the important selling points of high-end models. The introduction of deep learning technology can provide a pricing premium space for automobile companies and increase the profit margin of each vehicle. (2) Shaping a sense of technology: This technology is often associated by consumers with "future cars" or "luxury experiences", especially attracting users with higher requirements for intelligence and a sense of technology, such as young consumers or high-end market customers.
[0108] Expand value-added services and subsequent revenue sources: (1) Sale of personalized services: Deep learning technology supports personalized recommendations and can combine with vehicle networking applications to launch value-added services (such as high-quality navigation subscriptions, music services, precise advertisement push), bringing a long-term revenue stream to the company. (2) Revenue from software upgrades: Continuously optimize in-vehicle infotainment functions through OTA (Over-the-Air) upgrades, which can be used as an after-sales value-added item, allowing consumers to pay for long-term software services.
[0109] Improve customer decision-making efficiency: (1) Test drive attraction: When consumers test drive a vehicle, the intelligence and smoothness of the in-vehicle system will directly affect their overall evaluation of the vehicle. The optimized functions of deep learning technology can easily enable consumers to feel the convenience brought by technology in a short time. (2) Reduce purchase hesitation: Intelligent recommendations make the in-vehicle system appear to "understand users", reduce consumers' concerns about the learning cost of complex functions, increase their confidence in the vehicle system, and thus accelerate the purchase decision.
[0110] Drive innovation and cooperation in the automotive ecosystem: (1) Technical ecosystem attraction: The in-vehicle system driven by deep learning attracts more third-party developers to develop applications for the in-vehicle platform, forming a rich application ecosystem and further enhancing consumers' purchase interest. (2) Cooperation opportunities: Collaborate with Internet companies, navigation service providers, and content providers through deep learning algorithms to strengthen the technical capabilities of automotive brands and at the same time enhance the functionality of the in-vehicle system.
[0111] Improve user stickiness and after-sales business opportunities: (1) Continuous usage feedback: The in-vehicle system can be continuously optimized through deep learning, enabling user behavior analysis, helping the company better understand user needs, and providing support for after-sales service. (2) After-sales function upgrade: Users can unlock more intelligent functions (such as customized driving modes, entertainment service expansion) during the later stage of purchase, increasing after-sales revenue and maintaining users' long-term attention to the vehicle.
[0112] The following describes the in-vehicle system control device provided by this application. The in-vehicle system control device described below can be correspondingly referred to the in-vehicle system control method described above.
[0113] Figure 2 is a schematic structural diagram of the in-vehicle system control device provided by an embodiment of this application. Refer to Figure 2 This application provides an in-vehicle system control device, which may include:
[0114] An acquisition module 210, configured to obtain target data; the target data includes at least one of vehicle status information, time information, and external environment information;
[0115] A processing module 220, configured to perform data processing on the target data to obtain feature data;
[0116] A prediction module 230, configured to input the feature data into a prediction model, and perform prediction on the feature data through the prediction model to obtain a behavior prediction result of the user for the in-vehicle system of the vehicle output by the prediction model; the behavior prediction result includes at least one user operation behavior;
[0117] A control module 240, configured to control the operation of the in-vehicle system based on the behavior prediction result.
[0118] The vehicle-mounted system control device provided by the embodiment of the present application processes target data to obtain feature data, predicts the feature data through a prediction model to obtain a predicted user operation behavior for the vehicle-mounted system, and then controls the vehicle-mounted system to react in advance to the predicted user operation behavior, thereby improving the response speed of the vehicle-mounted system to the actual user operation behavior, enhancing the fluency of the vehicle-mounted system, making the vehicle-mounted system more in line with the user's usage habits, and enhancing the user experience.
[0119] In some embodiments, the processing module is specifically configured to:
[0120] Preprocess the target data to obtain processed data;
[0121] Reduce the dimension of the processed data to obtain dimension-reduced data;
[0122] Extract features from the dimension-reduced data to obtain the feature data.
[0123] In some embodiments, the prediction model is trained in the following manner:
[0124] Obtain a training sample set; the training sample set includes multiple groups of historical feature data and historical behavior prediction results respectively corresponding to the multiple groups of historical feature data;
[0125] Train an initial model based on the training sample set to obtain the prediction model.
[0126] In some embodiments, the control module is specifically configured to:
[0127] If the behavior prediction result is a user operation behavior, control the vehicle-mounted system to load data related to the user operation behavior based on the response priority of the user operation behavior, and after receiving a first instruction corresponding to the user operation behavior issued by the user, control the vehicle-mounted system to respond to the first instruction;
[0128] If the behavior prediction result is multiple user operation behaviors, control the vehicle-mounted system to load data related to each user operation behavior based on the response priority of each user operation behavior among the multiple user operation behaviors, and after receiving a second instruction corresponding to any one of the multiple user operation behaviors issued by the user, control the vehicle-mounted system to respond to the second instruction.
[0129] In some embodiments, the vehicle state information includes at least one of the position information, driving state, and driving speed of the vehicle; the external environment information includes at least one of the weather condition and traffic condition.
[0130] In some embodiments, the acquisition module is further configured to:
[0131] Obtain a preset number of target instructions of the user for the vehicle-mounted system at preset intervals, and the behavior prediction results corresponding to each target instruction;
[0132] If the consistency rate between the preset number of target instructions and the behavior prediction results corresponding to each target instruction is lower than a preset threshold, optimize the parameters of the prediction model.
[0133] Specifically, the vehicle-mounted system control device provided in the embodiments of the present application can implement all the method steps implemented by the method embodiments with the controller as the execution subject, and can achieve the same technical effects. The same parts and beneficial effects as those in the method embodiments will not be specifically described herein.
[0134] Figure 3 It is a schematic structural diagram of an electronic device provided in an embodiment of the present application. As Figure 3 shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330, and a communication bus 340. Among them, the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 can call the logic instructions in the memory 330 to execute the vehicle-mounted system control method, for example, including:
[0135] Obtain target data; the target data includes at least one of vehicle status information, time information, and external environment information;
[0136] Perform data processing on the target data to obtain feature data;
[0137] Input the feature data into a prediction model, and predict the feature data through the prediction model to obtain the behavior prediction result of the user for the vehicle-mounted system of the vehicle; the behavior prediction result includes at least one user operation behavior;
[0138] Based on the behavior prediction result, control the operation of the vehicle-mounted system.
[0139] In addition, when the logical instructions in the above-mentioned memory 330 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.
[0140] On the other hand, the present application also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is used to execute the steps of the vehicle-mounted system control method provided by the above-mentioned various methods, for example, including:
[0141] Obtain target data; the target data includes at least one of vehicle status information, time information, and external environment information;
[0142] Perform data processing on the target data to obtain feature data;
[0143] Input the feature data into a prediction model, and perform prediction on the feature data through the prediction model to obtain a behavior prediction result of the user for the vehicle-mounted system of the vehicle output by the prediction model; the behavior prediction result includes at least one user operation behavior;
[0144] Based on the behavior prediction result, control the operation of the vehicle-mounted system.
[0145] On another aspect, the present application also provides a computer program product. The computer program product includes a computer program, the computer program can be stored on a non-transitory computer-readable storage medium, and when the computer program is executed by a processor, the computer can execute the steps of the vehicle-mounted system control method provided by the above-mentioned various methods, for example, including:
[0146] Obtain target data; the target data includes at least one of vehicle status information, time information, and external environment information;
[0147] Perform data processing on the target data to obtain feature data;
[0148] Input the feature data into a prediction model, and use the prediction model to predict the feature data to obtain a behavior prediction result of a user's vehicle head unit system output by the prediction model; the behavior prediction result includes at least one user operation behavior.
[0149] Based on the behavior prediction result, control the operation of the vehicle head unit system.
[0150] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.
[0151] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0152] In addition, it should be noted that in the embodiments of the present application, the terms "first", "second", etc. are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that such terms can be interchanged under appropriate circumstances so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first" and "second" are usually of the same category, and the number of objects is not limited. For example, the first object can be one or multiple.
[0153] In the embodiments of the present application, the term "and / or" describes the association relationship of associated objects and indicates that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects before and after.
[0154] In the embodiments of this application, "determining B based on A" means that the factor A should be considered when determining B. It is not limited to "determining B only based on A", but also includes: "determining B based on A and C", "determining B based on A, C, and E", "determining C based on A and further determining B based on C", etc. Additionally, it can also include using A as a condition for determining B. For example, "when A meets the first condition, use the first method to determine B"; for another example, "when A meets the second condition, determine B"; for yet another example, "when A meets the third condition, determine B based on the first parameter", etc. Of course, it can also be that A is used as a condition for the factor of determining B. For example, "when A meets the first condition, use the first method to determine C and further determine B based on C", etc.
[0155] In the embodiments of this application, the term "a plurality of" means two or more, and other quantifiers are similar.
[0156] In the embodiments of this application, the orientation or positional relationship indicated by terms such as "center", "longitudinal", "transverse", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the embodiments of this application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the embodiments of this application.
[0157] In the embodiments of this application, unless otherwise clearly specified and limited, the terms "connected" and "coupled" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of this application can be understood according to specific circumstances.
[0158] In the embodiments of this application, unless otherwise clearly specified and limited, the first feature being "on" or "under" the second feature can be that the first and second features are in direct contact, or the first and second features are indirectly in contact through an intermediate medium. Moreover, the first feature being "above", "over", and "on top of" the second feature can be that the first feature is directly above or obliquely above the second feature, or merely indicates that the first feature is at a higher horizontal level than the second feature. The first feature being "under", "beneath", and "underneath" the second feature can be that the first feature is directly below or obliquely below the second feature, or merely indicates that the first feature is at a lower horizontal level than the second feature.
[0159] In the embodiments of the present application, the descriptions with reference to terms such as "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the embodiments of the present application. In the embodiments of the present application, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.
[0160] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. A method for controlling a vehicle-mounted system, characterized in that, Including: Obtain target data; the target data includes at least one of vehicle status information, time information, and external environment information; Perform data processing on the target data to obtain feature data; Input the feature data into a prediction model, and use the prediction model to predict the feature data to obtain a behavior prediction result of the user for the in-vehicle infotainment system of the vehicle output by the prediction model; the behavior prediction result includes at least one user operation behavior; Based on the behavior prediction result, control the operation of the in-vehicle infotainment system.
2. The vehicle infotainment system control method according to claim 1, wherein The performing data processing on the target data to obtain feature data includes: Perform preprocessing on the target data to obtain processed data; Perform data dimensionality reduction on the processed data to obtain dimensionality-reduced data; Perform feature extraction on the dimensionality-reduced data to obtain the feature data.
3. The vehicle-mounted system control method according to claim 1, characterized in that, The prediction model is trained in the following manner: Obtain a training sample set; the training sample set includes multiple groups of historical feature data and historical behavior prediction results respectively corresponding to the multiple groups of historical feature data; Based on the training sample set, train an initial model to obtain the prediction model.
4. The vehicle-mounted system control method according to claim 1, characterized in that, The based on the behavior prediction result, controlling the operation of the in-vehicle infotainment system includes: If the behavior prediction result is one user operation behavior, control the in-vehicle infotainment system to load data related to the user operation behavior based on the response priority of the user operation behavior, and after receiving a first instruction corresponding to the user operation behavior issued by the user, control the in-vehicle infotainment system to respond to the first instruction; If the behavior prediction result is multiple user operation behaviors, control the in-vehicle infotainment system to load data related to each user operation behavior based on the response priority of each user operation behavior among the multiple user operation behaviors, and after receiving a second instruction corresponding to any one of the multiple user operation behaviors issued by the user, control the in-vehicle infotainment system to respond to the second instruction.
5. The vehicle-mounted system control method according to claim 1, characterized in that The vehicle status information includes at least one of the vehicle's position information, driving status, and driving speed; the external environment information includes at least one of weather conditions and traffic conditions.
6. The vehicle-mounted system control method according to any one of claims 1 to 5, characterized in that, Also included: Every preset period, obtain a preset number of target instructions of the user for the in-vehicle infotainment system, and the behavior prediction result corresponding to each target instruction; If the consistency rate between the preset number of target instructions and the behavior prediction result corresponding to each target instruction is lower than a preset threshold, optimize the parameters of the prediction model.
7. A vehicle-mounted system control device, characterized in that, Including: An acquisition module for obtaining target data; The target data includes at least one of vehicle status information, time information, and external environment information; A processing module for performing data processing on the target data to obtain feature data; A prediction module for inputting the feature data into a prediction model, and using the prediction model to predict the feature data to obtain a behavior prediction result of the user for the in-vehicle infotainment system of the vehicle output by the prediction model; the behavior prediction result includes at least one user operation behavior; A control module for controlling the operation of the in-vehicle infotainment system based on the behavior prediction result.
8. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, the vehicle-mounted system control method according to any one of claims 1 to 6 is implemented.
9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the vehicle-mounted system control method according to any one of claims 1 to 6 is implemented.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, the vehicle-mounted system control method according to any one of claims 1 to 6 is implemented.