Vehicle remote control method and electronic device

Abstract

The application provides a vehicle remote control method and an electronic device, and relates to the technical field of vehicle control. The method comprises the following steps: obtaining vehicle use related data, vehicle state and perception data, and external environment information and road condition information of a target user; determining a vehicle use behavior feature of the target user based on the vehicle use related data, the vehicle state and perception data, the external environment information and the road condition information; predicting a vehicle use demand of the target user according to the vehicle use behavior feature; determining a corresponding vehicle control action based on the vehicle use demand, generating a remote control strategy according to the vehicle control action, and obtaining an optimal execution time based on the remote control strategy and the vehicle use related data, so that the vehicle executes the remote control strategy at the optimal execution time, thereby automatically triggering the vehicle to execute the remote control strategy without manually initiating an instruction.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and in particular to a vehicle remote control method and electronic device. Background Technology

[0002] With the continuous development of intelligent vehicle technology, remote vehicle control has gradually become an indispensable part of automobiles.

[0003] In related technologies, vehicle remote control functions are initiated by the user actively clicking control buttons on a mobile application to select the corresponding function. The application then uploads the received control commands to the vehicle-to-everything (V2X) cloud server. After verification, the V2X cloud server sends the commands to the in-vehicle telematics terminal. This terminal parses the commands and drives the relevant vehicle components to perform the corresponding operations. Once completed, the execution results are fed back to the application on the mobile terminal.

[0004] However, current vehicle remote control functions require users to manually initiate commands, resulting in low levels of intelligence. Furthermore, the generated remote control strategies cannot meet diverse and personalized vehicle usage needs, leading to a poor user experience. Summary of the Invention

[0005] This application provides a vehicle remote control method and electronic device to solve the problem that current vehicle remote control functions require users to manually initiate commands, have a low level of intelligence, and are prone to causing poor user experience.

[0006] In a first aspect, embodiments of this application provide a method for remote vehicle control, including: Acquire target users' vehicle-related data, vehicle status and perception data, as well as external environmental and road condition information; Based on the vehicle-related data, the vehicle status and perception data, the external environment information, and the road condition information, the vehicle usage behavior characteristics of the target user are determined. Based on the aforementioned car usage behavior characteristics, predict the car usage needs of the target user; Based on the vehicle usage requirements, corresponding vehicle control actions are determined. Based on the vehicle control actions, a remote control strategy is generated. Based on the remote control strategy and the vehicle usage-related data, the optimal execution time is obtained so that the vehicle executes the remote control strategy at the optimal execution time.

[0007] Current vehicle remote control functions typically require manual user commands, resulting in low levels of intelligence. To address this issue, this application's embodiments first acquire the target user's vehicle-related data, vehicle status and perception data, as well as external environmental and road condition information. Without requiring manual user commands, this multi-dimensional data allows for a comprehensive and accurate determination of the user's vehicle usage behavior characteristics. Second, by utilizing these behavioral characteristics, the target user's usage needs can be predicted, transforming remote vehicle control from a passive response to an active prediction approach, thus enhancing the intelligence and user experience of remote vehicle control. Finally, based on the predicted usage needs, corresponding vehicle control actions can be determined. According to these actions, a precise remote control strategy is generated, and the optimal execution time is determined based on the strategy and vehicle-related data. This ensures the vehicle executes the remote control strategy at the optimal time, thereby improving the intelligence and automation of remote vehicle control. Furthermore, when determining vehicle usage behavior characteristics, this application embodiment also comprehensively considers external environmental information and road condition information. In the process of predicting the vehicle usage needs of target users and generating remote control strategies, it can take into account the influence of the external environment and road conditions, thereby further improving the intelligence level of vehicle remote control and the user experience.

[0008] Here, this application embodiment introduces user vehicle data, external environment and road condition information, and proactively predicts vehicle needs by analyzing user vehicle behavior characteristics. At the same time, it abandons the simple reminder mode and directly and dynamically generates remote control strategies that adapt to the needs. Combining the remote control strategy and vehicle-related data, it calculates the optimal execution time and autonomously controls the vehicle to perform actions, which solves the pain points of low intelligence and insufficient personalization in the prior art, and optimizes the vehicle experience and vehicle control efficiency.

[0009] In one possible implementation, determining the target user's vehicle usage behavior characteristics based on the vehicle-related data, the vehicle status and perception data, the external environment information, and the road condition information includes: Based on the vehicle-related data, the vehicle status and perception data, the external environment information, and the road condition information, vehicle usage time characteristics, travel scenario characteristics, vehicle usage characteristics, and vehicle status characteristics are obtained. The vehicle usage behavior characteristics are obtained by performing correlation analysis on the vehicle usage time characteristics, travel scenario characteristics, vehicle usage characteristics, and vehicle status characteristics.

[0010] In the above implementation method, to accurately determine the target user's car-use behavior characteristics, it is necessary to first extract information from car-related data, vehicle status and perception data, external environmental information, and road condition information to obtain car-use time characteristics, travel scenario characteristics, vehicle usage characteristics, and vehicle status characteristics. Then, by performing correlation analysis on the above multi-source data, car-use behavior characteristics are obtained. This facilitates accurate inference of car-use needs in subsequent steps.

[0011] In one possible implementation, the vehicle-related data includes trip information, user location, and vehicle preference information; the vehicle status and perception data includes real-time vehicle status data and in-vehicle environment perception data; the external environment information includes environmental status data of the external environment in which the vehicle is located; and the road condition information includes real-time road condition data of the road segment in which the vehicle travels. The process of obtaining vehicle usage time characteristics, travel scenario characteristics, vehicle usage characteristics, and vehicle status characteristics based on the vehicle-related data, vehicle status and perception data, external environmental information, and road condition information includes: Based on the trip information and the user location, the vehicle usage time characteristics are determined, and based on the trip information, the user location, and the environmental status data of the external environment where the vehicle is located and the real-time traffic data of the road segment where the vehicle is traveling, the travel scenario characteristics are determined. Based on the vehicle usage preference information, the vehicle usage characteristics are obtained, and based on the real-time vehicle status data and the in-vehicle environment perception data, the vehicle status characteristics are obtained.

[0012] To obtain characteristics of vehicle usage time, travel scenario, vehicle usage, and vehicle status, we first determine the usage time characteristics based on trip information and user location. Next, we determine the travel scenario characteristics based on trip information, user location, environmental data of the vehicle's external environment, and real-time traffic data of the route the vehicle travels. Then, we obtain the vehicle usage characteristics based on usage preference information. Finally, we obtain the vehicle status characteristics based on real-time vehicle status data and in-vehicle environmental perception data. By performing layer-by-layer analysis of the acquired multi-source data, we can accurately extract the characteristics of usage time, travel scenario, vehicle usage, and vehicle status, laying the foundation for accurate inference of subsequent vehicle usage behavior characteristics.

[0013] In one possible implementation, before obtaining the vehicle usage time characteristics, travel scenario characteristics, vehicle usage characteristics, and vehicle status characteristics based on the vehicle-related data, the vehicle status and perception data, the external environment information, and the road condition information, the following method is further included: The vehicle-related data, vehicle status and perception data, external environment information, and road condition information are standardized; wherein, the standardization process includes data cleaning, format standardization, and data anonymization and encryption. Data verification is performed on the standardized vehicle-related data, vehicle status and perception data, external environmental information, and road condition information. The data verification includes data integrity verification, timeliness verification, and consistency verification.

[0014] Here, in order to ensure the quality and timeliness of the collected data, it is also necessary to standardize and verify the vehicle-related data, vehicle status and perception data, external environmental information and road condition information in turn, so as to ensure the credibility of the data.

[0015] In one possible implementation, predicting the target user's car usage needs based on the car usage behavior characteristics includes: Based on the aforementioned vehicle usage behavior characteristics, the target vehicle usage scenario is determined; The vehicle usage behavior features are input into the vehicle usage demand prediction model under the target vehicle usage scenario to obtain the vehicle usage demand of the target user output by the vehicle usage demand prediction model. The vehicle usage demand prediction model is trained based on different vehicle usage behavior characteristics and their corresponding vehicle usage demands under the target vehicle usage scenario.

[0016] In this embodiment of the application, in order to accurately predict the vehicle usage needs of target users, a vehicle usage demand prediction model for various vehicle usage scenarios is constructed. By inputting vehicle usage behavior characteristics into the vehicle usage demand prediction model for the target vehicle usage scenario, the vehicle usage needs of the target users can be obtained.

[0017] In one possible implementation, after inputting the vehicle usage behavior features into the vehicle usage demand prediction model under the target vehicle usage scenario to obtain the vehicle usage demand of the target user output by the vehicle usage demand prediction model, the method further includes: Based on the aforementioned car usage needs, the target users are prompted with their car usage needs. If feedback information from the target user is received, semantic analysis and intent recognition are performed on the feedback information to determine demand adjustment data, and the vehicle usage demand is adjusted based on the demand adjustment data. Based on the vehicle usage demand, the corresponding vehicle control actions are determined, and a remote control strategy is generated according to the vehicle control actions, including: Based on the adjusted vehicle usage requirements, the corresponding vehicle control actions are determined, and a remote control strategy is generated based on the vehicle control actions.

[0018] Based on the above technical content, in order to improve the naturalness of the interaction, the vehicle usage needs can also be adjusted according to the feedback information of the target users, effectively avoiding vehicle usage needs that do not meet the user's expectations, and making the adjusted vehicle usage needs more in line with the user's preferences and usage habits.

[0019] In one possible implementation, before determining the corresponding vehicle control action based on the vehicle usage demand and generating a remote control strategy based on the vehicle control action, the method further includes: The vehicle usage demand is compared with historical vehicle usage demand to determine the confidence level of the vehicle usage demand; Based on the confidence level and the preset confidence level evaluation criteria, determine whether the vehicle usage demand is valid; Based on the vehicle usage demand, the corresponding vehicle control actions are determined, and a remote control strategy is generated according to the vehicle control actions, including: If the vehicle usage request is valid, then based on the vehicle usage request, the corresponding vehicle control action is determined, and a remote control strategy is generated according to the vehicle control action.

[0020] In this embodiment of the application, to avoid invalidity or misoperation caused by erroneous judgments, and to further improve the reliability and accuracy of remote control, it is necessary to determine whether the vehicle usage demand is valid before generating the remote control strategy. After determining that the vehicle usage demand is valid, the remote control strategy and optimal execution time for the vehicle are generated based on the usage demand.

[0021] In one possible implementation, the historical vehicle usage demand refers to the vehicle usage demand that has the same usage time, the same travel scenario, and the same vehicle status as the historical vehicle usage demand. The step of comparing the vehicle usage demand with historical vehicle usage demand to determine the confidence level of the vehicle usage demand includes: The vehicle usage demand is compared with historical vehicle usage demand to obtain demand similarity. Based on the demand similarity, the confidence level of the vehicle use demand is determined; wherein the confidence level is positively correlated with the demand similarity.

[0022] Here, to accurately characterize the confidence level of vehicle usage demand, the current demand can be compared with historical demand. By using demand similarity, the confidence level of the demand can be accurately determined. This enables a quantitative assessment of the effectiveness of the vehicle usage demand, providing a reliable basis for the subsequent generation of remote control strategies.

[0023] In one possible implementation, obtaining the optimal execution time based on the remote control strategy and the vehicle-related data includes: The optimal execution time is determined based on the response time of each control action in the remote control strategy and the vehicle-related data.

[0024] In the above implementation method, by simultaneously considering the response time of relevant control actions in the remote control strategy and vehicle-related data, the optimal execution time can be comprehensively determined, thereby realizing intelligent remote vehicle control and improving the user's vehicle experience.

[0025] Secondly, embodiments of this application provide a vehicle remote control device, comprising: The acquisition module is used to acquire vehicle-related data, vehicle status and perception data, as well as external environmental information and road condition information of the target user; The determination module is used to determine the vehicle usage behavior characteristics of the target user based on the vehicle-related data, the vehicle status and perception data, the external environment information and the road condition information; The prediction module is used to predict the vehicle usage needs of the target user based on the vehicle usage behavior characteristics. The generation module is used to determine the corresponding vehicle control actions based on the vehicle usage requirements, generate a remote control strategy based on the vehicle control actions, and obtain the optimal execution time based on the remote control strategy and the vehicle-related data, so that the vehicle executes the remote control strategy at the optimal execution time.

[0026] In one possible implementation, a module is defined for: Based on the vehicle-related data, the vehicle status and perception data, the external environment information, and the road condition information, vehicle usage time characteristics, travel scenario characteristics, vehicle usage characteristics, and vehicle status characteristics are obtained. The vehicle usage time characteristics, travel scenario characteristics, vehicle usage characteristics, and vehicle status characteristics are correlated to obtain the vehicle usage behavior characteristics. In one possible implementation, In one possible implementation, the vehicle-related data includes trip information, user location, and vehicle preference information; the vehicle status and perception data includes real-time vehicle status data and in-vehicle environment perception data; the external environment information includes environmental status data of the external environment in which the vehicle is located; and the road condition information includes real-time road condition data of the road segment in which the vehicle travels. The determination module is used for: Based on the trip information and the user location, the vehicle usage time characteristics are determined, and based on the trip information, the user location, and the environmental status data of the external environment where the vehicle is located and the real-time traffic data of the road segment where the vehicle is traveling, the travel scenario characteristics are determined. Based on the vehicle usage preference information, the vehicle usage characteristics are obtained, and based on the real-time vehicle status data and the in-vehicle environment perception data, the vehicle status characteristics are obtained.

[0027] In one possible implementation, a module is defined for: The vehicle-related data, vehicle status and perception data, external environment information, and road condition information are standardized; wherein, the standardization process includes data cleaning, format standardization, and data anonymization and encryption. Data verification is performed on the standardized vehicle-related data, vehicle status and perception data, external environmental information, and road condition information. This data verification includes data integrity verification, timeliness verification, and consistency verification. In one possible implementation, In one possible implementation, the prediction module is used for: Based on the aforementioned vehicle usage behavior characteristics, the target vehicle usage scenario is determined; The vehicle usage behavior features are input into the vehicle usage demand prediction model under the target vehicle usage scenario to obtain the vehicle usage demand of the target user output by the vehicle usage demand prediction model. The vehicle usage demand prediction model is trained based on different vehicle usage behavior characteristics and their corresponding vehicle usage demands under the target vehicle usage scenario.

[0028] In one possible implementation, the prediction module is used for: Based on the aforementioned car usage needs, the target users are prompted with their car usage needs. If feedback information from the target user is received, semantic analysis and intent recognition are performed on the feedback information to determine demand adjustment data, and the vehicle usage demand is adjusted based on the demand adjustment data. Generate modules for: Based on the adjusted vehicle usage requirements, the corresponding vehicle control actions are determined, and a remote control strategy is generated according to these actions.

[0029] In one possible implementation, Generate modules for: The vehicle usage demand is compared with historical vehicle usage demand to determine the confidence level of the vehicle usage demand; Based on the confidence level and the preset confidence level evaluation criteria, determine whether the vehicle usage demand is valid; If the vehicle usage request is valid, then based on the vehicle usage request, the corresponding vehicle control action is determined, and a remote control strategy is generated according to the vehicle control action.

[0030] In one possible implementation, the historical vehicle usage demand refers to the vehicle usage demand that has the same usage time, the same travel scenario, and the same vehicle status as the historical vehicle usage demand. Generate modules for: The vehicle usage demand is compared with historical vehicle usage demand to obtain demand similarity. Based on the demand similarity, the confidence level of the vehicle use demand is determined; wherein the confidence level is positively correlated with the demand similarity.

[0031] In one possible implementation, a generation module is used for: The optimal execution time is determined based on the response time of each control action in the remote control strategy and the vehicle-related data.

[0032] Thirdly, embodiments of this application provide an electronic device, including a memory and a processor, wherein the memory stores a computer program that can run on the processor, and the processor executes the computer program to implement the vehicle remote control method as described in any of the first aspects.

[0033] It is understood that the beneficial effects of the second and third aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here.

[0034] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this specification. Attached Figure Description

[0035] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 This is a schematic diagram of an application scenario provided by an embodiment of this application; Figure 2 This is a schematic flowchart of a vehicle remote control method provided in an embodiment of this application; Figure 3 This is a flowchart illustrating a vehicle remote control method according to another embodiment of this application; Figure 4 This is a schematic diagram of the structure of a vehicle remote control device provided in one embodiment of this application; Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0037] The present application will be described more clearly below with reference to specific embodiments. These embodiments will help those skilled in the art to further understand the function of the present application, but do not limit the present application in any way. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of the present application. These all fall within the protection scope of the present application.

[0038] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0039] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0040] In the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0041] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0042] Furthermore, the term "multiple" mentioned in the embodiments of this application should be interpreted as two or more.

[0043] First, the terms used in the embodiments of this application will be explained: Telematics Service Provider (TSP): A platform that provides remote information services for vehicles. Its core functions include command forwarding, data management, and service delivery.

[0044] The vehicle-mounted remote control terminal (Telematics Box, T-Box) is the core component connecting the vehicle and the TSP platform, responsible for receiving, parsing, executing, and uploading commands.

[0045] With the continuous development of intelligent vehicle technology, remote vehicle control has gradually become an indispensable part of automobiles. Through remote vehicle control, a comfortable in-car environment can be provided for drivers and passengers in advance. Among related technologies, remote vehicle control allows the vehicle to be in optimal driving condition upon the user's arrival, significantly improving the convenience and experience of using the vehicle.

[0046] For example, some related technologies can determine the standby time based on in-vehicle environmental parameters, ideal environmental parameters, and standby conditions. Then, based on the standby time and vehicle start-up time, the standby reminder time can be calculated. When the standby reminder time arrives, a standby reminder can be sent to the target user to remind the user to prepare the vehicle in time before the vehicle start-up time.

[0047] However, the applicant found that the core objective of the aforementioned vehicle preparation method is to send a vehicle preparation reminder to the target user. However, this method determines the preparation time and reminder time solely based on fixed in-vehicle environmental parameters, ideal parameters, and preparation conditions. It does not involve dynamic collection and analysis of user vehicle usage data, real-time external environment, or real-time road conditions. It cannot proactively perceive and analyze user behavior, requiring users to pre-set conditions, essentially making it a passive response. Furthermore, the output is only the vehicle preparation reminder time; its function is limited to sending a reminder to the user. Subsequent vehicle preparation actions and vehicle control commands still require the user to manually initiate them after receiving the reminder. This reliance on user manual triggering of subsequent operations further illustrates its passive response nature and its inability to meet diverse and personalized vehicle usage scenarios. Therefore, it is necessary to consider a new remote vehicle control method that proactively predicts usage needs based on the target user's travel information and automatically triggers remote control, thereby improving the user's vehicle experience.

[0048] To improve the user experience and address the current issue of not being able to automatically trigger remote control based on user trip information, this application's embodiments utilize acquired vehicle-related data, vehicle status and perception data, external environmental information, and road condition information. Without requiring manual user commands, it can comprehensively and accurately determine the user's vehicle usage behavior characteristics based on these multi-dimensional data. By obtaining these behavior characteristics, the target user's usage needs can be predicted, transforming remote vehicle control from a passive response to an active prediction, thus enhancing the intelligence and user experience of remote vehicle control. Finally, based on the predicted usage needs, a precise remote control strategy can be generated. Then, based on the remote control strategy and vehicle-related data, the optimal execution time can be determined, allowing the vehicle to execute the remote control strategy at the optimal time, thereby improving the intelligence and automation of remote vehicle control.

[0049] In summary, the aforementioned vehicle standby reminder technologies calculate standby time and reminder time based solely on fixed in-vehicle environment, ideal parameters, and standby conditions. Relying on pre-set conditions by the user, they ultimately only send a reminder, requiring the user to manually initiate subsequent control. This passive, auxiliary logic is widely adopted by those skilled in the art, lacking any motivation for proactive optimization. This application overcomes the biases of existing technologies by adding multi-dimensional data collection dimensions, incorporating user vehicle usage data, external environment, and road condition information. It proactively predicts vehicle usage needs by analyzing user behavior characteristics, rather than passively waiting for user presets. Simultaneously, it abandons the simple reminder mode, directly and dynamically generating remote control strategies adapted to specific needs. Combining these strategies with relevant vehicle data, it calculates the optimal execution time and autonomously controls the vehicle to perform actions, requiring no manual user operation or pre-set time. This application's solution represents a qualitative leap from passive reminders to proactive intelligent control, addressing the pain points of low intelligence and insufficient personalization in existing technologies, and optimizing the user experience and vehicle control efficiency.

[0050] First refer to Figure 1 , Figure 1A schematic diagram illustrating an application scenario provided according to an embodiment of this application is shown. The device involved in this application scenario includes a vehicle 110, a user's mobile terminal 120, a processing unit 130, and a TSP platform 140. The user's mobile terminal 120 has a remote control application, and the vehicle 110 is equipped with a T-Box. Currently, the vehicle remote control method operates as follows: First, the user opens the remote control application on the mobile terminal 120 and manually sets preset conditions. Next, the processing unit 130 determines the standby time based on in-vehicle environmental parameters, ideal environmental parameters, and standby conditions. Then, based on the standby time and vehicle start-up time, it calculates the standby reminder time and sends a standby reminder to the user when the reminder time arrives. The user uploads remote control commands to the TSP platform 140 through the remote control application on the mobile terminal 120. After converting the received remote control commands and verifying their validity, the TSP platform 140 sends them to the T-Box on the vehicle 110 via a communication network. After receiving a remote control command, the T-Box drives the vehicle to perform corresponding operations based on the command and feeds back the execution results to the TSP platform 140 and the user's mobile terminal 120. The aforementioned vehicle remote control method is passively reactive, unable to autonomously predict or adaptively execute, and is cumbersome and lacks intelligence. To proactively predict user needs and automatically trigger remote control, this embodiment deploys an electronic device for vehicle remote control in the cloud. By acquiring the target user's vehicle-related data, vehicle status and perception data, as well as external environmental and road condition information, the device can accurately generate a remote control strategy and optimal execution time based on the aforementioned multi-dimensional data without requiring manual user input. This ensures the vehicle executes the remote control strategy at the optimal time, thereby improving the intelligence and automation of vehicle remote control.

[0051] In this embodiment, the vehicle remote control method can be integrated as a program into an electronic device in the cloud to achieve remote vehicle control. This electronic device can be an AI intelligent decision-making device.

[0052] The following is combined with Figure 1 Application scenarios, refer to Figures 2-3 This application describes a vehicle remote control method provided according to exemplary embodiments. It should be noted that the above application scenarios are shown only to facilitate understanding of the spirit and principles of this application, and the embodiments of this application are not limited in any way. Rather, the embodiments of this application can be applied to any applicable scenario.

[0053] refer to Figure 2 , Figure 2 This is a schematic flowchart illustrating a vehicle remote control method provided in one embodiment of this application. Figure 2As shown, the method in the embodiments of this application may include: Step 201: Obtain the target user's vehicle-related data, vehicle status and perception data, as well as external environment information and road condition information.

[0054] When a target user uses the vehicle remote control method for the first time to remotely control the vehicle, the target user needs to authorize the collection of relevant data through the remote control application on the mobile terminal, such as the target user's vehicle-related data, vehicle status and perception data, external environmental information and road condition information, so as to obtain and analyze relevant data with the target user's permission.

[0055] In addition, to ensure accurate access to multi-source data, standardized access interfaces have been established, covering all data sources to ensure the comprehensiveness and timeliness of data collection.

[0056] In some embodiments, vehicle-related data may include the target user's trip information, user location, and vehicle preference information; vehicle status and perception data may include real-time vehicle status data and in-vehicle environment perception data; external environment information may include environmental status data of the external environment in which the vehicle is located; and road condition information may include real-time road condition data of the road segment in which the vehicle travels.

[0057] In this embodiment, the target user can automatically obtain vehicle-related data, vehicle status and perception data, as well as external environment information and road condition information by authorizing an electronic device deployed in the cloud for remote vehicle control. This allows the target user to automatically obtain the aforementioned multi-source data without requiring manual input from the user.

[0058] For example, once authorized by the target user, an AI-powered intelligent decision-making device deployed in the cloud can automatically acquire the target user's vehicle-related data, vehicle status and perception data, as well as external environmental information and road condition information.

[0059] Step 202: Based on vehicle-related data, vehicle status and perception data, external environment information and road condition information, determine the vehicle usage behavior characteristics of the target user.

[0060] In this embodiment, after obtaining vehicle-related data, vehicle status and perception data, external environment information and road condition information in step 201, the vehicle-related data, vehicle status and perception data, external environment information and road condition information can be used for reasoning and analysis to obtain the vehicle-use behavior characteristics of the target user.

[0061] For example, the target user's car usage behavior characteristics can be a fusion of feature information representing the target user's car usage trips, usage patterns, and usage preferences. For instance, the target user's car usage behavior characteristics could be: going to the zoo from location A at 3 PM tomorrow, traveling with children, traveling in the rain, vehicle in normal condition, slightly congested road conditions, preferring an air conditioning temperature of 27 degrees Celsius, and having the seat in a normal position.

[0062] In some embodiments, when the acquired data is natural language data, the acquired natural language data can be parsed and processed by a large language model to generate structured data, which is convenient for integration with other data.

[0063] Step 203: Based on the characteristics of car usage behavior, predict the car usage needs of the target users.

[0064] In this embodiment, the vehicle usage requirement refers to the relevant operations or preparations that the target user expects the vehicle to perform in advance for the upcoming vehicle usage scenario, so as to ensure that the vehicle can enter the adaptation state in advance and meet the actual usage needs of the target user in the vehicle usage scenario, thereby improving the convenience and comfort of vehicle use.

[0065] In step 202, after obtaining the vehicle usage behavior features that can characterize the target user's vehicle usage trips, usage patterns, and usage preferences, the vehicle usage behavior features can be analyzed to predict the target user's vehicle usage needs in the usage scenario.

[0066] For example, let's take the target user's car usage behavior characteristics identified in the above steps as an example. The target user's car usage behavior characteristics are: traveling from location A to the zoo at 3 PM tomorrow, with children in the car, traveling in the rain, vehicle in normal condition, slight traffic congestion, preferring an air conditioning temperature of 27 degrees Celsius, and the seat in a normal position. Based on the above car usage behavior characteristics, the target user's predicted car usage needs can be the following when traveling with children in the rain: requirements for in-car temperature, in-car seats, window defrosting, driving safety, and convenient car use.

[0067] Step 204: Based on vehicle usage needs, determine the corresponding vehicle control actions, generate a remote control strategy based on the vehicle control actions, and obtain the optimal execution time based on the remote control strategy and vehicle-related data, so that the vehicle executes the remote control strategy at the optimal execution time.

[0068] Once the vehicle usage needs of the target users are determined, the remote control strategy and optimal execution time for the vehicle can be automatically generated based on those needs.

[0069] In this embodiment, the remote control strategy is a series of control actions that the vehicle needs to automatically execute to meet usage requirements. The optimal execution time is how far in advance the vehicle needs to execute the above remote control strategy to meet usage requirements.

[0070] For example, let's continue with the predicted user's car usage needs from the above example. These needs include managing the car's interior temperature, seats, window defrosting, driving safety, and ease of use when traveling with children in the rain. Based on these needs, the generated remote control strategy could be to adjust the car's air conditioning temperature, activate the window defrosting function, and start navigation from location A to the zoo, putting the vehicle in a travel-ready state. The optimal execution time can be determined based on various data, such as the time it takes for the air conditioning and defrosting to reach a comfortable state, or by combining user's usual pre-trip start-up habits, vehicle status, and perception data.

[0071] In this embodiment of the application, taking an AI intelligent decision-making device deployed in the cloud as the execution subject as an example, after obtaining the remote control strategy and the optimal execution time, the AI ​​intelligent decision-making device starts timing. When the optimal execution time is reached, the remote control strategy is issued, so that the vehicle executes the remote control strategy.

[0072] Optionally, after obtaining the remote control strategy and the optimal execution time, the AI ​​intelligent decision-making device can directly send the information to the vehicle, and the vehicle will start timing. When the optimal execution time is reached, the remote control strategy will be executed.

[0073] In addition, after obtaining the remote control strategy and the optimal execution time, the AI ​​intelligent decision-making device starts timing and triggers the vehicle to start timing at the same time. When the optimal execution time is reached, the remote control strategy is issued. The vehicle further determines whether the optimal execution time has been reached by its own timing. If so, the remote control strategy is executed.

[0074] Here, by providing multiple remote control strategy execution methods such as cloud-based AI intelligent decision-making device timing distribution, vehicle local timing execution, and dual verification of cloud and vehicle dual-end synchronous timing, it can adapt to different network environments and vehicle computing power conditions. While achieving global unified scheduling, it reduces dependence on real-time communication links, reduces command latency and loss risks, and effectively improves the real-time performance, accuracy, reliability and security of remote control execution, meeting the precise control needs of diverse automotive scenarios.

[0075] Currently, vehicle remote control functions typically require manual user commands, resulting in a low level of intelligence. Therefore, this embodiment first acquires the target user's vehicle-related data, vehicle status and perception data, as well as external environmental and road condition information. Without requiring manual user commands, it can comprehensively and accurately determine the user's vehicle usage behavior characteristics based on this multi-dimensional data. Secondly, by using the obtained vehicle usage behavior characteristics, the target user's vehicle needs can be predicted, transforming vehicle remote control from a passive response to an active prediction, thus improving the intelligence level and user experience of vehicle remote control. Finally, by predicting vehicle needs, a precise remote control strategy and optimal execution time can be generated, ensuring the vehicle executes the remote control strategy at the optimal time, thereby improving the intelligence and automation of vehicle remote control. Furthermore, this embodiment also comprehensively considers external environmental and road condition information when determining vehicle usage behavior characteristics. This allows for the integration of the influence of the external environment and road conditions during the prediction of the target user's vehicle needs and the generation of remote control strategies, further enhancing the intelligence level of vehicle remote control and the user experience.

[0076] In addition, when predicting the vehicle usage needs of target users based on the acquired multi-source data, this application embodiment also needs to analyze the obtained vehicle usage needs to avoid misjudgment leading to invalidity or misoperation. Figure 3 A flowchart illustrating a vehicle remote control method according to another embodiment of this application is shown below. Figure 3 As shown, the method includes: Step 301: Obtain the target user's vehicle-related data, vehicle status and perception data, as well as external environment information and road condition information.

[0077] In some embodiments, vehicle-related data may include the target user's trip information, user location, and vehicle preference information.

[0078] In this embodiment, the target user's travel information can be obtained in various ways, such as based on the calendar information authorized by the target user, based on the target user's fixed car usage patterns, based on the user's voice commands, or based on the travel information input by the target user. These methods will not be elaborated here.

[0079] For example, if the calendar information indicates taking the child to the zoo at 3 PM tomorrow, the user's travel information can be determined by converting the natural language in the calendar information into structured data. If there is no relevant travel information in the calendar, the user's travel information can be automatically determined based on the user's regular car usage patterns, such as going to work at 7:30 AM and leaving work at 6:30 PM on weekdays.

[0080] In this embodiment, the user's location can be determined through a remote control application on the target user's mobile phone, or it can be determined directly through the target user's mobile phone.

[0081] In this embodiment, vehicle usage preference information can be determined through pre-stored user behavior profiles. These profiles can include the target user's consistent vehicle usage patterns and vehicle usage preferences. By learning from historical data, the target user's consistent usage patterns and preferences can be extracted to generate a user behavior profile. Furthermore, the user behavior profile can be dynamically updated based on newly acquired data.

[0082] For example, historical data may include core user-side data, third-party data, and vehicle-side data. Core user-side data may include historical vehicle usage records obtained through remote control applications authorized by the target user, user-authorized calendar trip data, anonymized geolocation data, and data proactively reported by the user. Third-party data may include data obtained through API integration with mainstream service platforms, including weather data, map navigation services, and overseas adaptation data. Vehicle-side data may include vehicle-to-everything (V2X) interaction data, real-time vehicle status data, and onboard sensor data.

[0083] In this embodiment, a user behavior profile can be determined by constructing a machine learning model.

[0084] For example, a hybrid architecture consisting of a time-series prediction model and a collaborative filtering algorithm can be used to accurately determine user behavior profiles. The time-series prediction model is responsible for mining time patterns, learning and predicting time-series features such as usage periods, usage cycles, and advance preparation time from the target user's historical usage records and trip time series, thereby determining the target user's fixed usage patterns. The collaborative filtering algorithm is responsible for mining the correlation of usage preference information, learning the correlation between various different usage scenarios and control parameters, thereby generating usage preference information. In addition, when training the machine learning model, industry-standard usage features can also be incorporated. Furthermore, an incremental learning mechanism can be used to dynamically update the trained machine learning model to ensure that the obtained user behavior profile is suitable for the target user.

[0085] In this embodiment, real-time vehicle status data may include battery SOC, tire pressure, fuel level, engine / motor operating status, etc. In-vehicle environmental perception data may include in-vehicle temperature, in-vehicle air quality, and seat occupancy status, etc.

[0086] Step 302: Based on vehicle-related data, vehicle status and perception data, external environment information and road condition information, obtain vehicle usage time characteristics, travel scenario characteristics, vehicle usage characteristics and vehicle status characteristics.

[0087] In some embodiments, after acquiring vehicle-related data, vehicle status and perception data, external environment information and road condition information, in order to ensure the quality of the collected data and the timeliness of data collection, it is also necessary to perform standardization processing and data verification on the vehicle-related data, vehicle status and perception data, external environment information and road condition information in sequence, so as to ensure the credibility of the data.

[0088] In this embodiment, the vehicle-related data, vehicle status and perception data, external environmental information, and road condition information are first standardized. Standardization processing may include data cleaning, format standardization, and data anonymization and encryption. Then, the standardized vehicle-related data, vehicle status and perception data, external environmental information, and road condition information are validated to filter out invalid data and improve the reliability of the obtained data. Data validation may include data integrity verification, timeliness verification, and consistency verification.

[0089] For example, data cleaning can filter out abnormal data, format standardization can convert heterogeneous data from different data sources into a unified format, and data anonymization and encryption can encrypt and store sensitive user data, removing personally identifiable information. When storing different types of acquired data, storage levels can be divided according to importance and access frequency. High-frequency accessed real-time data can be stored in an in-memory database, while historical behavioral data can be stored in a distributed database, thus determining data access efficiency and storage security.

[0090] For example, integrity verification can be implemented through keyword rule verification. A predefined whitelist of required fields is used to check each data entry for missing keywords. If a keyword is missing, the data is deemed invalid and filtered out. Required fields can include usage time, trip information, etc. Timeliness verification uses real-time timestamp comparison. Real-time data such as weather, road conditions, vehicle status, and sensor data are timestamped, and the difference between the timestamp and the current time is calculated to strictly ensure that the data delay is less than a time threshold. Data exceeding the time threshold is discarded. Consistency verification uses multi-source data for cross-validation. For example, the time and destination of a calendar trip are logically compared with the user's geographic location / vehicle positioning data, and the data from onboard sensors is logically compared with the status data reported by the vehicle's infotainment system. If logical conflicts exist, the data is considered abnormal.

[0091] In some embodiments, vehicle usage time characteristics, travel scenario characteristics, vehicle usage characteristics, and vehicle status characteristics can also be determined through layer-by-layer reasoning.

[0092] In this embodiment, the usage time characteristics can be determined first through trip information and user location. Next, based on trip information, user location, environmental status data of the vehicle's external environment, and real-time traffic data of the route the vehicle travels, the travel scenario characteristics can be determined. Then, vehicle usage characteristics are obtained based on usage preference information. Finally, vehicle status characteristics are obtained based on real-time vehicle status data and in-vehicle environmental perception data.

[0093] In this embodiment, the vehicle usage time characteristics may include at least one or more characteristics such as usage time period, travel date, or trip duration.

[0094] Specifically, trip information can be determined through calendar information authorized by the target user, regular usage patterns, or information issued by the user via voice commands. Therefore, by combining trip information and user location, the target user's usage time characteristics can be determined.

[0095] For example, if a target user's calendar indicates that they will be taking their child to the zoo at 2:00 PM today, this calendar information can be used to determine the date and time of the car rental as 2:00 PM today. For target users who have not set any calendar schedules, the car rental time characteristics can be determined through fixed car rental patterns and user location in the user behavior profile, such as starting work at 7:30 AM and finishing work at 3:30 PM on weekdays.

[0096] In this embodiment, the travel scenario features may include at least one or more features such as travel destination, trip type, whether there are passengers, road condition level, and weather environment.

[0097] For example, if a target user's calendar indicates taking their child to the zoo at 2 PM today, and the target user is detected to be in location A, with rain and slight traffic congestion, then the travel scenario characteristics can be determined as: from location A to the zoo, traveling with a child, slight traffic congestion, and rain. If the target user has not set any calendar trips, then based on their regular driving habits, their location being in location A, and the detected real-time weather of 25°C and clear traffic, the travel scenario characteristics can be determined as: weekday commuting, from location A to the company, 25°C, and clear traffic.

[0098] For example, a large model can be used to vectorize and semantically associate trip information, user location, and environmental status data of the vehicle's external environment with real-time traffic data of the route the vehicle is traveling on, thereby uniformly encoding all information to form a complete travel scenario feature. The large model can be an open-source model or a paid model; there are no restrictions here.

[0099] In this embodiment, vehicle usage characteristics may include at least one or more features such as frequently used air conditioning temperature, multimedia preferences, driving modes, and vehicle start-stop habits. Vehicle usage characteristics can be determined using vehicle preference information from pre-stored user behavior profiles.

[0100] For example, during winter commutes, the target user's preferred driving experience is an air conditioning temperature of 24°C + seat heating + vehicle / battery preheating. When traveling with children, the preferred air conditioning temperature is 28°C.

[0101] In this embodiment, vehicle status characteristics may include battery SOC value, fuel level, tire pressure, interior temperature, interior humidity, and seat occupancy status, etc.

[0102] Step 303: Perform correlation analysis on the characteristics of vehicle usage time, travel scenario, vehicle usage, and vehicle status to obtain vehicle usage behavior characteristics.

[0103] By performing correlation analysis and fusion on the vehicle usage time characteristics, travel scenario characteristics, vehicle usage characteristics and vehicle status characteristics obtained in step 302, the vehicle usage behavior characteristics of the target user can be obtained.

[0104] For example, by performing correlation analysis on the relevant features obtained in step 302, the resulting vehicle usage behavior features can be: the target user traveled from location A to the zoo at 14:00 today, with a child in the car, it was raining, the route was slightly congested, the preferred air conditioning temperature was 28℃, and the seat was in a normal position.

[0105] Step 304: Based on the characteristics of car usage behavior, predict the car usage needs of the target users.

[0106] In some embodiments, there may be a variety of different car usage scenarios. Therefore, a car usage demand prediction model corresponding to each car usage scenario can be constructed. Thus, based on different car usage scenarios, the car usage demand of the target user can be predicted.

[0107] In this embodiment, the target vehicle usage scenario can first be determined based on vehicle usage behavior characteristics. Then, the vehicle usage behavior characteristics are input into a vehicle usage demand prediction model for the target vehicle usage scenario to obtain the vehicle usage demand of the target user. This vehicle usage demand prediction model is trained based on different vehicle usage behavior characteristics and their corresponding vehicle usage demands within the target vehicle usage scenario.

[0108] In this embodiment, the target vehicle usage scenarios include various types, such as commuting scenarios, long-distance scenarios, and complex scenarios. Commuting scenarios include weekday commuting scenarios, winter commuting scenarios, temporary overtime work scenarios, smoggy weather scenarios, and rainy weather scenarios. Complex scenarios may include rainy weather scenarios with children and hot weather scenarios requiring pre-cooling measures.

[0109] For example, consider the target user's car usage characteristics as follows: traveling from location A to the zoo at 3 PM tomorrow, with a child in the car, traveling in the rain, vehicle in normal condition, slight traffic congestion, preferring an air conditioning temperature of 27 degrees Celsius, and the seat in a normal position. Based on these characteristics, the target usage scenario can be determined as traveling with a child in the rain. Inputting these characteristics into a car usage demand prediction model for this scenario yields the target user's specific needs when traveling with a child in the rain, including requirements for in-car temperature, seat adjustment, window defrosting, driving safety, and convenient car usage. Examples include requirements for an air conditioning temperature of 23 degrees Celsius, child seat adjustment, window defrosting, and low-speed warnings.

[0110] In this embodiment, the vehicle demand prediction model differs for different vehicle usage scenarios. After determining the target vehicle usage scenario based on vehicle behavior characteristics, this embodiment can then determine the vehicle demand prediction model for that target scenario. Thus, by inputting the vehicle behavior characteristics into the vehicle demand prediction model for that target scenario, the vehicle demand of the target user can be obtained.

[0111] In different vehicle usage scenarios, user behavior characteristics and influencing factors vary significantly. A single model cannot simultaneously adapt to the feature distributions and prediction targets of multiple scenarios, leading to low prediction accuracy and poor generalization ability. This embodiment constructs or selects dedicated vehicle demand prediction models for different usage scenarios, enabling the models to better match the behavioral patterns and demand characteristics of the corresponding scenarios, reducing interference from irrelevant features, and improving the accuracy, relevance, and reliability of vehicle demand prediction, thereby better supporting subsequent intelligent decision-making and control.

[0112] For example, taking the training of a vehicle demand prediction model in any vehicle usage scenario as an example, this embodiment first obtains different vehicle usage behavior characteristics in the vehicle usage scenario and their corresponding user needs. Then, based on the different vehicle usage behavior characteristics in the vehicle usage scenario and their corresponding user needs, a dedicated vehicle demand prediction model for the vehicle usage scenario is trained, so that the model is more in line with the behavior patterns and demand characteristics in the corresponding scenario, and improves the accuracy of subsequent processing.

[0113] In some embodiments, to improve the naturalness of the interaction, after anticipating the need for a vehicle, the anticipated need can be sent to the target user to provide a prompt.

[0114] In this embodiment, if the target user responds to the prompt, the feedback information is semantically parsed and intent is identified to determine demand adjustment data. Based on this data, the user's transportation needs are adjusted accordingly.

[0115] For example, if a user provides feedback in natural language such as "It's a bit cold today," the feedback information is analyzed and intent is recognized to determine that the air conditioning temperature needs to be increased. Consequently, the user's usage needs are adjusted accordingly, and the air conditioning temperature is increased.

[0116] In this embodiment, it can also be determined whether to prompt the target user based on the confidence level of the vehicle usage demand.

[0117] For example, if the confidence level of the car-use request is greater than or equal to a preset confidence threshold, there is no need to send a car-use request notification to the target user. If the confidence level of the car-use request is less than the preset confidence threshold, then a car-use request notification needs to be sent to the target user.

[0118] Step 305: Compare the vehicle usage demand with historical vehicle usage demand to determine the confidence level of the vehicle usage demand.

[0119] In some embodiments, to avoid invalidity or misoperation caused by incorrect judgment, it is necessary to compare the vehicle usage demand with historical vehicle usage demand after the vehicle usage demand is predicted.

[0120] In this embodiment, historical car usage requests can be those that occur at the same time, in the same travel scenario, and under the same vehicle condition as previous requests. First, the current car usage request is compared with the historical request to obtain a similarity score. Then, based on the similarity score, the confidence level of the car usage request is determined. The confidence level is positively correlated with the similarity score.

[0121] For example, demand similarity can be calculated by performing vector similarity calculations on the current car usage demand and historical car usage demands. Then, the demand similarity is mapped to the confidence level of the car usage demand. Thus, the confidence level of the current car usage demand can be determined.

[0122] Step 306: Based on the confidence level and the preset confidence level evaluation criteria, determine whether the vehicle usage demand is valid.

[0123] In some embodiments, the confidence level evaluation criteria can be as follows: when the confidence level is greater than or equal to a first confidence threshold, it indicates that the car usage request is highly credible, and the validity of the request is directly determined. When the confidence level is greater than or equal to a second confidence threshold but less than the first confidence threshold, it indicates that the car usage request is moderately credible, and a prompt message needs to be sent to the user. Based on the user's confirmation, the validity of the request is determined. When the confidence level is less than the second confidence threshold, it indicates that the credibility of the request is insufficient, and the user's request is deemed invalid.

[0124] In this embodiment, the first confidence threshold is greater than the second confidence threshold.

[0125] For example, the first confidence threshold can be 90%, and the second confidence threshold can be 50%.

[0126] It should be noted that the confidence level evaluation criteria can be set based on the actual application scenario, and no restrictions are imposed here.

[0127] By judging vehicle usage needs based on confidence evaluation criteria, misjudgments can be effectively avoided, thus providing a reliable basis and decision support for the formulation of subsequent remote control strategies.

[0128] Step 307: If the vehicle usage demand is valid, determine the corresponding vehicle control action based on the vehicle usage demand, generate a remote control strategy based on the vehicle control action, and obtain the optimal execution time based on the remote control strategy and vehicle-related data, so that the vehicle executes the remote control strategy at the optimal execution time.

[0129] In this embodiment, the remote control strategy may include adjusting the temperature of the vehicle's air conditioning, turning on the window defroster, adjusting the child seat, adjusting the seat heating, turning on the air purifier, and related driving safety reminders.

[0130] For example, let's continue with the previous vehicle usage requirements: setting the in-car air conditioning temperature to 23°C, adjusting the child seat, defogging the windows, and activating the low-speed warning function. Based on these requirements, the corresponding vehicle control actions include adjusting the in-car air conditioning temperature to 23°C, adjusting the child seat, activating the window defroster, and activating the low-speed warning function. A remote control strategy is then generated based on these vehicle control actions.

[0131] In this embodiment, the optimal execution time can be determined by comprehensively considering the response time of relevant control actions in the remote control strategy and vehicle-related data.

[0132] For example, if a user leaves home for work at 7:30 on a regular weekday, the real-time weather temperature is 25°C, and the user's preferred air conditioning temperature is 24°C, then based on the fact that it usually takes 4-10 minutes for the air conditioning to reach 24°C, the optimal execution time can be determined to be 7:20-7:24.

[0133] In some embodiments, if a change in travel information is detected, any unexecuted remote control policies are automatically terminated.

[0134] In this embodiment, if it is detected that the target user has canceled their travel plan, the unexecuted remote control policy corresponding to that travel plan will be automatically terminated.

[0135] For example, if the target user cancels a travel plan in their calendar, any unexecuted remote control policy will be automatically terminated.

[0136] In some embodiments, the optimal execution time can be adjusted based on real-time traffic data of the detected vehicle travel segment.

[0137] In this embodiment, if congestion is detected on the road segment where the vehicle is traveling, the optimal execution time will be automatically modified, and the modified optimal execution time will be pushed to the target user. If the target user cancels the remote control policy corresponding to the optimal execution time via natural language feedback, the unexecuted remote control policy will be automatically terminated.

[0138] In some embodiments, when the optimal execution time is reached, a remote control policy can be sent to the vehicle's T-Box via a remote service provider platform. Alternatively, the remote control policy can be sent directly to the vehicle's T-Box to drive the vehicle to perform relevant control actions.

[0139] In this embodiment, after receiving the remote control policy, the TSP platform first needs to perform multi-dimensional validity verification. Then, after the verification passes, the policy is distributed in the form of a message queue according to its priority.

[0140] Specifically, multi-dimensional legitimacy verification can include user permission verification, vehicle status verification, and command validity verification. User permission verification confirms that the triggering user is an authorized user of the vehicle; vehicle status verification confirms that the vehicle is online, fault-free, and in a safe state; and command validity verification confirms that the command matches the vehicle configuration, such as electric vehicle-specific commands that only apply to electric vehicles.

[0141] In some embodiments, after receiving a remote control strategy from the TSP platform, the vehicle's T-Box parses the remote control strategy and drives the vehicle control unit and corresponding actuators to complete the operation. The execution result is then fed back to the TSP platform and the user's remote control application in real time.

[0142] In this embodiment, the vehicle usage needs of the target user are predicted based on their vehicle usage behavior characteristics. To avoid misjudgment leading to erroneous triggering of remote control strategies and impacting user experience, a vehicle usage need confidence verification mechanism is introduced. This mechanism compares the confidence level of the predicted usage needs with a preset confidence evaluation standard to accurately determine whether the vehicle usage needs are genuine and valid. After confirming the validity of the usage needs, a remote control strategy and optimal execution time for the vehicle are generated based on these needs. This improves the intelligence level of vehicle remote control and enhances the user experience.

[0143] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0144] Figure 4 This is a schematic diagram of the structure of a vehicle remote control device provided in one embodiment of this application. Figure 4 As shown, the vehicle remote control device provided in this embodiment may include: an acquisition module 401, a determination module 402, a prediction module 403, and a generation module 404.

[0145] Among them, the acquisition module 401 is used to acquire the target user's vehicle-related data, vehicle status and perception data, as well as external environment information and road condition information; The determination module 402 is used to determine the vehicle usage behavior characteristics of the target user based on the vehicle-related data, the vehicle status and perception data, the external environment information and the road condition information. The prediction module 403 is used to predict the vehicle usage needs of the target user based on the vehicle usage behavior characteristics. The generation module 404 is used to determine the corresponding vehicle control action based on the vehicle usage demand, generate a remote control strategy based on the vehicle control action, and obtain the optimal execution time based on the remote control strategy and the vehicle-related data, so that the vehicle executes the remote control strategy at the optimal execution time.

[0146] In one possible implementation, module 402 is configured to: Based on the vehicle-related data, the vehicle status and perception data, the external environment information, and the road condition information, vehicle usage time characteristics, travel scenario characteristics, vehicle usage characteristics, and vehicle status characteristics are obtained. The vehicle usage time characteristics, travel scenario characteristics, vehicle usage characteristics, and vehicle status characteristics are correlated to obtain the vehicle usage behavior characteristics. In one possible implementation, In one possible implementation, the vehicle-related data includes trip information, user location, and vehicle preference information; the vehicle status and perception data includes real-time vehicle status data and in-vehicle environment perception data; the external environment information includes environmental status data of the external environment in which the vehicle is located; and the road condition information includes real-time road condition data of the road segment in which the vehicle travels. Determine module 402, used for: Based on the trip information and the user location, the vehicle usage time characteristics are determined, and based on the trip information, the user location, and the environmental status data of the external environment where the vehicle is located and the real-time traffic data of the road segment where the vehicle is traveling, the travel scenario characteristics are determined. Based on the vehicle usage preference information, the vehicle usage characteristics are obtained, and based on the real-time vehicle status data and the in-vehicle environment perception data, the vehicle status characteristics are obtained.

[0147] In one possible implementation, module 402 is configured to: The vehicle-related data, vehicle status and perception data, external environment information, and road condition information are standardized; wherein, the standardization process includes data cleaning, format standardization, and data anonymization and encryption. Data verification is performed on the standardized vehicle-related data, vehicle status and perception data, external environmental information, and road condition information. This data verification includes data integrity verification, timeliness verification, and consistency verification. In one possible implementation, In one possible implementation, the prediction module 403 is used for: Based on the aforementioned vehicle usage behavior characteristics, the target vehicle usage scenario is determined; The vehicle usage behavior features are input into the vehicle usage demand prediction model under the target vehicle usage scenario to obtain the vehicle usage demand of the target user output by the vehicle usage demand prediction model. The vehicle usage demand prediction model is trained based on different vehicle usage behavior characteristics and their corresponding vehicle usage demands under the target vehicle usage scenario.

[0148] In one possible implementation, the prediction module 403 is used for: Based on the aforementioned car usage needs, the target users are prompted with their car usage needs. If feedback information from the target user is received, semantic analysis and intent recognition are performed on the feedback information to determine demand adjustment data, and the vehicle usage demand is adjusted based on the demand adjustment data. Module 404 is generated for: Based on the adjusted vehicle usage requirements, the corresponding vehicle control actions are determined, and a remote control strategy is generated based on the vehicle control actions.

[0149] In one possible implementation, the generation module 404 is used for: The vehicle usage demand is compared with historical vehicle usage demand to determine the confidence level of the vehicle usage demand; Based on the confidence level and the preset confidence level evaluation criteria, determine whether the vehicle usage demand is valid; If the vehicle usage request is valid, then based on the vehicle usage request, the corresponding vehicle control action is determined, and a remote control strategy is generated according to the vehicle control action.

[0150] In one possible implementation, the historical vehicle usage demand refers to the vehicle usage demand that has the same usage time, the same travel scenario, and the same vehicle status as the historical vehicle usage demand. Module 404 is generated for: The vehicle usage demand is compared with historical vehicle usage demand to obtain demand similarity. Based on the demand similarity, the confidence level of the vehicle use demand is determined; wherein the confidence level is positively correlated with the demand similarity.

[0151] In one possible implementation, the generation module 404 is used for: The optimal execution time is determined based on the response time of each control action in the remote control strategy and the vehicle-related data.

[0152] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0153] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. For example... Figure 5 As shown, the electronic device 500 of this embodiment includes a processor 510 and a memory 520, wherein the memory 520 stores a computer program 521 that can run on the processor 510. When the processor 510 executes the computer program 521, it implements the steps in any of the above-described method embodiments, for example... Figure 2 The steps shown illustrate a vehicle remote control method. Alternatively, when processor 510 executes computer program 521, it implements the functions of each module / unit in the above-described device embodiments, for example... Figure 4 The functions of the acquisition module 401, determination module 402, prediction module 403, and generation module 404 are shown.

[0154] For example, computer program 521 may be divided into one or more modules / units, one or more of which are stored in memory 520 and executed by processor 510 to complete this application. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 521 in electronic device 500.

[0155] Those skilled in the art will understand that Figure 5 This is merely an example of an electronic device and does not constitute a limitation on the electronic device. It may include more or fewer components than shown, or combinations of certain components, or different components, such as input / output devices, network access devices, buses, etc.

[0156] The processor 510 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0157] The memory 520 can be an internal storage unit of the electronic device, such as a hard drive or memory, or an external storage device, such as a plug-in hard drive, SmartMedia Card (SMC), Secure Digital (SD) card, or Flash Card. The memory 520 can also include both internal and external storage units. The memory 520 is used to store computer programs and other programs and data required by the electronic device. The memory 520 can also be used to temporarily store data that has been output or will be output.

[0158] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0159] An embodiment of this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described vehicle remote control method.

[0160] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0161] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0162] In the embodiments provided in this application, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings or direct couplings or communication connections may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0163] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0164] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0165] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0166] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for remote vehicle control, characterized in that, include: Acquire target users' vehicle-related data, vehicle status and perception data, as well as external environmental and road condition information; Based on the vehicle-related data, the vehicle status and perception data, the external environment information, and the road condition information, the vehicle usage behavior characteristics of the target user are determined. Based on the aforementioned car usage behavior characteristics, predict the car usage needs of the target user; Based on the vehicle usage requirements, corresponding vehicle control actions are determined. Based on the vehicle control actions, a remote control strategy is generated. Based on the remote control strategy and the vehicle usage-related data, the optimal execution time is obtained so that the vehicle executes the remote control strategy at the optimal execution time.

2. The vehicle remote control method according to claim 1, characterized in that, The process of determining the target user's vehicle usage behavior characteristics based on the vehicle-related data, vehicle status and perception data, external environmental information, and road condition information includes: Based on the vehicle-related data, the vehicle status and perception data, the external environment information, and the road condition information, vehicle usage time characteristics, travel scenario characteristics, vehicle usage characteristics, and vehicle status characteristics are obtained. The vehicle usage behavior characteristics are obtained by performing correlation analysis on the vehicle usage time characteristics, travel scenario characteristics, vehicle usage characteristics, and vehicle status characteristics.

3. The vehicle remote control method according to claim 2, characterized in that, The vehicle-related data includes trip information, user location, and vehicle preference information; the vehicle status and perception data includes real-time vehicle status data and in-vehicle environment perception data; the external environment information includes environmental status data of the external environment in which the vehicle is located; and the road condition information includes real-time road condition data of the road segment in which the vehicle travels. The process of obtaining vehicle usage time characteristics, travel scenario characteristics, vehicle usage characteristics, and vehicle status characteristics based on the vehicle-related data, vehicle status and perception data, external environmental information, and road condition information includes: Based on the trip information and the user location, the vehicle usage time characteristics are determined, and based on the trip information, the user location, and the environmental status data of the external environment where the vehicle is located and the real-time traffic data of the road segment where the vehicle is traveling, the travel scenario characteristics are determined. Based on the vehicle usage preference information, the vehicle usage characteristics are obtained, and based on the real-time vehicle status data and the in-vehicle environment perception data, the vehicle status characteristics are obtained.

4. The vehicle remote control method according to claim 2, characterized in that, Before obtaining the vehicle usage time characteristics, travel scenario characteristics, vehicle usage characteristics, and vehicle status characteristics based on the vehicle-related data, the vehicle status and perception data, the external environment information, and the road condition information, the method further includes: The vehicle-related data, vehicle status and perception data, external environment information, and road condition information are standardized; wherein, the standardization process includes data cleaning, format standardization, and data anonymization and encryption. Data verification is performed on the standardized vehicle-related data, vehicle status and perception data, external environmental information, and road condition information. The data verification includes data integrity verification, timeliness verification, and consistency verification.

5. The vehicle remote control method according to any one of claims 1 to 4, characterized in that, The step of predicting the vehicle usage needs of the target user based on the vehicle usage behavior characteristics includes: Based on the aforementioned vehicle usage behavior characteristics, the target vehicle usage scenario is determined; The vehicle usage behavior features are input into the vehicle usage demand prediction model under the target vehicle usage scenario to obtain the vehicle usage demand of the target user output by the vehicle usage demand prediction model. The vehicle usage demand prediction model is trained based on different vehicle usage behavior characteristics and their corresponding vehicle usage demands under the target vehicle usage scenario.

6. The vehicle remote control method according to claim 5, characterized in that, After inputting the vehicle usage behavior features into the vehicle usage demand prediction model under the target vehicle usage scenario to obtain the vehicle usage demand of the target user output by the vehicle usage demand prediction model, the method further includes: Based on the aforementioned car usage needs, the target users are prompted with their car usage needs. If feedback information from the target user is received, semantic analysis and intent recognition are performed on the feedback information to determine demand adjustment data, and the vehicle usage demand is adjusted based on the demand adjustment data. Based on the vehicle usage demand, the corresponding vehicle control actions are determined, and a remote control strategy is generated according to the vehicle control actions, including: Based on the adjusted vehicle usage requirements, the corresponding vehicle control actions are determined, and a remote control strategy is generated based on the vehicle control actions.

7. The vehicle remote control method according to any one of claims 1 to 4, characterized in that, Before determining the corresponding vehicle control action based on the vehicle usage demand and generating a remote control strategy based on the vehicle control action, the method further includes: The vehicle usage demand is compared with historical vehicle usage demand to determine the confidence level of the vehicle usage demand; Based on the confidence level and the preset confidence level evaluation criteria, determine whether the vehicle usage demand is valid; Based on the vehicle usage demand, the corresponding vehicle control actions are determined, and a remote control strategy is generated according to the vehicle control actions, including: If the vehicle usage request is valid, then based on the vehicle usage request, the corresponding vehicle control action is determined, and a remote control strategy is generated according to the vehicle control action.

8. The vehicle remote control method according to claim 7, characterized in that, The historical vehicle usage demand refers to the vehicle usage demand that has the same usage time, the same travel scenario, and the same vehicle status as the historical vehicle usage demand. The step of comparing the vehicle usage demand with historical vehicle usage demand to determine the confidence level of the vehicle usage demand includes: The vehicle usage demand is compared with historical vehicle usage demand to obtain demand similarity. Based on the demand similarity, the confidence level of the vehicle use demand is determined; wherein the confidence level is positively correlated with the demand similarity.

9. The vehicle remote control method according to any one of claims 1 to 4, characterized in that, The process of obtaining the optimal execution time based on the remote control strategy and the vehicle-related data includes: The optimal execution time is determined based on the response time of each control action in the remote control strategy and the vehicle-related data.

10. An electronic device comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, characterized in that, When the processor executes the computer program, it implements the vehicle remote control method as described in any one of claims 1 to 8.

Images