A vehicle seat layout intelligent control method and system

Abstract

The application discloses a kind of vehicle seat layout intelligent control method and system, the method includes: obtaining the driving behavior data of user and vehicle state information;According to the driving behavior data of user and vehicle state information, whether the user will select riding mode is predicted using algorithm model;When predicting that the user will select riding mode, the preset riding mode parameter information is obtained, and the preset riding mode parameter information is sent to the car system, so that the car system automatically adjusts the seat layout of vehicle according to the preset riding mode parameter information, so that the space for storing bicycle is formed in vehicle.The method provided by the application can realize intelligent identification of user riding travel habit and automatic adjustment of seat layout through deep analysis of user historical vehicle data by cloud platform.

Description

Technical Field

[0001] This invention relates to the field of vehicle control technology, specifically to an intelligent control method and system for vehicle seat layout. Background Technology

[0002] With the rise in popularity of cycling, the demand for the "4+2" mode of traveling by car with a bicycle has increased dramatically. However, current automotive technology has not yet provided a corresponding intelligent control solution. When loading a bicycle, car owners still need to manually adjust the seat, a process that is both cumbersome and inconvenient, resulting in a poor user experience.

[0003] Advances in intelligent vehicle technology have led to the widespread application of cloud platforms in the automotive industry, particularly in data processing and storage. Cloud platforms can process data generated by vehicle sensors in real time and accurately predict user behavior through machine learning and big data technologies. Based on these technologies, cloud platforms can intelligently decide whether to activate specific vehicle modes, such as the "4+2" mode, according to the user's driving habits. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a vehicle seat layout intelligent control method and system to address the shortcomings of the prior art. This method can achieve intelligent recognition of users' riding habits and automatic adjustment of seat layout through in-depth analysis of users' historical vehicle usage data.

[0005] To achieve the above objectives, according to one aspect of the present invention, a vehicle seat layout intelligent control method is provided, comprising:

[0006] Acquire user driving behavior data and vehicle status information;

[0007] Based on the user's driving behavior data and vehicle status information, an algorithm model is used to predict whether the user will select riding mode.

[0008] When it is predicted that the user will select a riding mode, the preset riding mode parameter information is obtained and sent to the vehicle system. The vehicle system then automatically adjusts the vehicle's seat layout according to the preset riding mode parameter information to create space inside the vehicle for storing a bicycle.

[0009] In the above solution, an algorithmic model is used to predict whether the user will select the cycling mode. The specific method is as follows:

[0010] Use an algorithm model to determine the probability that a user will activate cycling mode;

[0011] This method also sets a probability threshold for activating cycling mode;

[0012] Compare the obtained probability of a user activating cycling mode with the probability threshold of activating cycling mode;

[0013] If the probability of a user activating cycling mode is greater than the probability threshold for activating cycling mode, then it is predicted that the user will select cycling mode.

[0014] In the above scheme, the formula for calculating the probability of the user activating cycling mode by the algorithm model is as follows:

[0015]

[0016] Where P(cycling mode|user data) is the probability that the user activates cycling mode; β0,β1,…,β n These are the model parameters, learned from the training dataset; x1, x2, ..., x n β is a feature variable representing the user's driving behavior data and vehicle status information. The algorithm model's formula is used to predict whether a user will choose riding mode in a specific situation. By analyzing the user's historical data and the current situation to adjust the model parameters (i.e., the β value), it can predict whether the user will be more inclined to use riding mode the next time they use the vehicle.

[0017] In the above scheme, the user's driving behavior data and vehicle status information include the number of times the user activated the riding mode in the past 7 days, the user's usage time preferences, weather conditions, the user's geographical location information, destination feature information, time information, and other related information.

[0018] In the above scheme, the preset riding mode parameter information includes the seat tilt angle and the trunk space configuration.

[0019] In the above scheme, the preset riding mode parameters are set by the user on the mobile terminal associated with the vehicle according to personal preferences.

[0020] The above solution also includes: when it is predicted that the user will select the riding mode, sending a notification message to the mobile terminal and / or the vehicle system for the user to confirm.

[0021] In the above scheme, the notification information also includes the user's preset cycling mode parameter information, which the user can modify.

[0022] Furthermore, the above method also includes:

[0023] When a signal is received indicating that the user has decided to cancel the riding mode, the signal is sent to the vehicle's infotainment system, which then adjusts the vehicle's seat layout back to normal in real time.

[0024] According to another aspect of the present invention, a vehicle seat layout intelligent control system is provided, the control system being configured on a cloud platform, comprising:

[0025] The acquisition module is used by the cloud platform to remotely acquire user driving behavior data and vehicle status information from the vehicle's infotainment system.

[0026] The prediction module is used by the cloud platform to predict whether the user will select the riding mode based on the user's driving behavior data and vehicle status information using an algorithm model.

[0027] The execution module is used to remotely obtain preset riding mode parameter information from the mobile terminal associated with the vehicle when the cloud platform predicts that the user will select the riding mode, and remotely send the preset riding mode parameter information to the vehicle system so that the vehicle system can automatically adjust the seat layout of the vehicle according to the preset riding mode parameter information, so that a space for storing bicycles is created inside the vehicle.

[0028] In summary, compared with the prior art, the above-described technical solutions conceived by this invention can achieve the following beneficial effects:

[0029] (1) The present invention provides a vehicle seat layout intelligent control method. This method collects user driving data and vehicle status information, uses a cloud platform to comprehensively analyze and predict the user's possible travel needs, can automatically switch to riding mode, and automatically adjust the seat layout in the vehicle to make room for bicycle storage, thereby providing users with a more intelligent and convenient riding travel solution.

[0030] (2) The present invention provides a vehicle seat layout intelligent control method, which allows users to confirm or cancel switching to riding mode through a mobile terminal or vehicle system, and to adjust preset riding mode parameter information, which is convenient and quick. Attached Figure Description

[0031] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0032] Figure 1 This is a flowchart illustrating a vehicle seat layout intelligent control method according to Embodiment 1 of the present invention.

[0033] Figure 2 This is a schematic diagram of a vehicle seat layout intelligent control system according to Embodiment 1 of the present invention.

[0034] Figure 3This is a schematic diagram of a vehicle seat layout intelligent control system according to Embodiment 3 of the present invention. Detailed Implementation

[0035] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. Furthermore, the technical features involved in the various embodiments of this invention described below can be combined with each other as long as they do not conflict with each other.

[0036] It should be understood that the sequence number of each step in the embodiment 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.

[0037] Example 1

[0038] This application provides, in one aspect, a control method for a cloud-based intelligent riding "4+2" mode, which is described in the following embodiment. Figure 1 ,include:

[0039] S1 acquires user driving behavior data and vehicle status information.

[0040] Specifically, in this embodiment of the application, the user's driving behavior data and vehicle status information include the number of times the user activated the riding mode in the past 7 days, the user's vehicle usage time preference, the user's geographical location information, destination feature information, and time information.

[0041] S2 uses an algorithm model to predict whether a user will select riding mode based on the user's driving behavior data and vehicle status information.

[0042] Specifically, in this embodiment of the application, an algorithmic model is used to predict whether a user will select the cycling mode. The specific method is as follows:

[0043] Use an algorithm model to determine the probability that a user will activate cycling mode;

[0044] This method also sets a probability threshold for activating the cycling mode; in this embodiment of the application, the probability threshold for activating the cycling mode is 70%.

[0045] Compare the probability of a user activating cycling mode with the probability threshold for activating cycling mode.

[0046] If the probability of a user activating cycling mode is greater than the probability threshold for activating cycling mode, then it is predicted that the user will select cycling mode.

[0047] The algorithm used above calculates the probability of a user activating cycling mode using the following formula:

[0048]

[0049] Where P(cycling mode|user data) is the probability that a user activates cycling mode; β0, β1, ..., β n These are the model parameters, learned from the training dataset; x1, x2, ..., x n These are feature variables, representing user behavior and vehicle status information. It is understood that, in the embodiments of this application, feature variables may be the number of times the user has activated the riding mode in the past 7 days, the user's usage time preference, weather conditions, the user's geographical location information, destination feature information, time information, and other related information.

[0050] In this embodiment of the application, the formula of the algorithm model is used to predict whether a user will choose the cycling mode in a specific situation. By analyzing the user's historical data and the current situation to adjust the model parameters (i.e., the β value), it is possible to predict whether the user will be more inclined to use the cycling mode the next time they use the vehicle.

[0051] Specifically, in this embodiment of the application, the construction of the dataset includes the following steps:

[0052] (1) Data collection: Collect a large amount of historical data containing user driving behavior and vehicle status; this data should include, but is not limited to, user driving time, location information, weather conditions, navigation destination, etc.

[0053] (2) Feature extraction: Extract feature variables from the collected data, such as the user's car usage time, frequency, location, weather, etc.

[0054] (3) Model Training: The extracted feature variables and their corresponding target variables (whether cycling mode is enabled) are used to train the logistic regression model. During training, the gradient descent algorithm is used to optimize the model parameters β0, β1, ..., β. n To minimize prediction error.

[0055] (4) Model evaluation: The performance of the model is evaluated by price difference verification and performance on the test set to ensure that it has high accuracy and generalization ability in predicting whether users will activate the riding mode.

[0056] In this embodiment of the application, the probability threshold for activating the cycling mode is set to 70%. That is, when the probability of the user activating the cycling mode calculated by the algorithm model is greater than 70%, the system will predict that the user will select the cycling mode.

[0057] S3, when it predicts that the user will select a riding mode, obtains the preset riding mode parameter information and sends the preset riding mode parameter information to the vehicle system, so that the vehicle system can automatically adjust the vehicle's seat layout according to the preset riding mode parameter information, so that space can be created inside the vehicle to store the bicycle.

[0058] Specifically, in this embodiment of the application, the preset riding mode parameter information includes the seat tilt angle and the trunk space configuration; wherein the user presets the riding mode parameter information by setting it on a mobile terminal associated with the vehicle according to personal preferences.

[0059] In the above solution, the vehicle system also monitors the entire process of automatically adjusting the vehicle's seat layout to ensure that all adjustments meet safety standards and can notify the user upon completion.

[0060] A specific implementation process of this application embodiment is as follows: The user's driving behavior data and vehicle status information are acquired, including the number of times the user activated cycling mode in the past 7 days, the user's usage time preferences, the user's geographical location information, destination feature information, and time information. Based on the user's driving behavior data and vehicle status information, an algorithm model is used to predict whether the user will select cycling mode. The specific prediction process is as follows: The user's driving behavior data and vehicle status information are input into a pre-trained algorithm model. The formula for calculating the probability of the user activating cycling mode is:

[0061]

[0062] Where P(cycling mode|user data) is the probability that a user activates cycling mode; β0, β1, ..., β n These are the model parameters, learned from the training dataset; x1, x2, ..., x n These are feature variables, representing user driving behavior data and vehicle status information. It is understood that, in the embodiments of this application, feature variables may be the number of times the user has activated the riding mode in the past 7 days, the user's vehicle usage time preference, weather conditions, the user's geographical location information, destination feature information, time information, and other related information.

[0063] Specifically, in the embodiments of this application, the feature variables include:

[0064] 1. Number of times a user activated cycling mode in the past 7 days (feature variable x1)

[0065] 2. User's vehicle usage time preferences (e.g., the time periods during which the vehicle is used each day, feature variable x2, represented by time periods, e.g., morning = 1, noon = 2, afternoon = 3, evening = 4, night = 5, the number of times the user used the vehicle in each time period in the past month)

[0066] 3. User's destination (e.g., locations frequently visited by the user, feature variable x3, represented by latitude and longitude coordinates or location categories, e.g., home = 1, workplace = 2, school = 3, countryside greenway = 4, sports venue = 5)

[0067] 4. Environmental factors (such as weather conditions, temperature, humidity, etc., characteristic variable x4, which can be specific to the weather, for example, sunny day = 1, rainy day = 2, snowy day = 3)

[0068] Model parameters β0,β1,…,β n The values ​​obtained through training datasets are as follows, as tested in this embodiment:

[0069] β0 (intercept): -3.0 (based on initial model settings);

[0070] β1 (number of times cycling mode was activated in the past 7 days): 0.3;

[0071] β2 (vehicle usage time preference): 0.2;

[0072] β3 (User's destination):

[0073] Family = 0.1;

[0074] Work location = 0.2;

[0075] School = 0.3;

[0076] Countryside greenways = 0.8 (with increased weighting to encourage use in suitable cycling locations);

[0077] Sports venue = 0.5.

[0078] β4 (Environmental factors):

[0079] Sunny day = 0.1 (Sunny weather may slightly increase the willingness to cycle);

[0080] Rainy days = -1.2 (significantly reduces the willingness to cycle and increases the response to adverse weather conditions);

[0081] Snowy weather = -1.5 (extremely adverse weather conditions, greatly reducing the willingness to cycle);

[0082] Specifically, in the embodiments of this application, the specific test values ​​of the feature variables are as follows:

[0083] x1 = 8 (number of times the user activated cycling mode in the past 7 days);

[0084] x2 = 5 (user's preferred car usage time, for example, the most frequent time to use the vehicle is at night, i.e., 5);

[0085] x3 = 4 (the places users visit most often, such as suburban greenways = 4);

[0086] x4 = 1 (weather conditions, sunny = 1).

[0087] The algorithm model yielded a 97.6% probability of activating riding mode, exceeding the 70% probability threshold. This indicates the user will select riding mode, and the system retrieves the user's preset riding mode parameters, sending these parameters to the vehicle's infotainment system. Upon receiving these parameters, the system automatically adjusts the vehicle's seating layout based on the seat tilt angle and trunk space configuration. Simultaneously, the system monitors the entire automatic seating adjustment process to ensure all adjustments meet safety standards and notifies the user upon completion.

[0088] Another aspect of this application provides a vehicle seat layout intelligent control system, which is set on a cloud platform, see below. Figure 2 ,include:

[0089] The acquisition module is used by the cloud platform to remotely acquire user driving behavior data and vehicle status information from the vehicle's infotainment system.

[0090] The prediction module is used by the cloud platform to predict whether a user will select riding mode based on the user's driving behavior data and vehicle status information using an algorithm model.

[0091] The execution module is used to remotely obtain preset riding mode parameter information from the mobile terminal associated with the vehicle when the cloud platform predicts that the user will select the riding mode, and remotely send the preset riding mode parameter information to the vehicle system so that the vehicle system can automatically adjust the seat layout of the vehicle according to the preset riding mode parameter information, so that a space for storing bicycles can be created inside the vehicle.

[0092] This application provides a vehicle seat layout intelligent control method and system. The method collects user driving data and vehicle status information, uses a cloud platform to comprehensively analyze and predict the user's possible travel needs, can automatically switch to cycling mode, and automatically adjust the seat layout in the vehicle to make room for bicycle storage, thereby providing users with a more intelligent and convenient cycling travel solution.

[0093] Example 2

[0094] The principle and steps of this embodiment are basically the same as those of Embodiment 1, except that the method further includes:

[0095] When it is predicted that a user will select riding mode, a notification message is sent to the mobile device and / or the vehicle system for user confirmation.

[0096] In the above scheme, the notification information also includes user-preset cycling mode parameters, which users can modify.

[0097] The above methods also include:

[0098] When the system receives a signal from the user that they want to cancel the riding mode, it sends the signal to the vehicle's infotainment system, which then adjusts the vehicle's seat layout in real time to return to normal.

[0099] A specific implementation process of this application embodiment is as follows: The cloud platform, based on the acquired user's driving behavior data and vehicle status information, uses an algorithm model to predict that the user will select riding mode. It then sends a notification to the mobile terminal for user confirmation. This notification also includes preset riding mode parameters that the user can modify. The user receives the confirmation message from the cloud platform using their mobile app and confirms to enter riding mode, simultaneously changing the preset riding mode parameters. After receiving the user's confirmation, the cloud platform sends the modified riding mode parameters to the vehicle's infotainment system. Upon receiving the modified riding mode parameters, the vehicle's infotainment system automatically adjusts the vehicle's seat layout according to the seat tilt angle and trunk space configuration information. Shortly after, the user decides to cancel riding mode and sends this information to the cloud platform using their mobile app. The cloud platform receives this information and sends it to the vehicle's infotainment system. Upon receiving this information, the vehicle's infotainment system adjusts the vehicle's seat layout in real time to return to normal.

[0100] This embodiment provides a method for intelligent control of vehicle seat layout. Users can confirm or cancel switching to riding mode via mobile device or vehicle system, and can adjust preset riding mode parameters, which is convenient and quick.

[0101] Example 3

[0102] This application provides an intelligent control system for vehicle seat layout, which is installed in the vehicle's infotainment system. (See attached document.) Figure 3 ,include:

[0103] The acquisition module is used by the vehicle system to acquire user driving behavior data and vehicle status information;

[0104] The prediction module is used by the vehicle system to predict whether the user will select riding mode based on the user's driving behavior data and vehicle status information using an algorithm model.

[0105] The execution module is used to send a notification message to the mobile terminal and / or display terminal associated with the vehicle when the vehicle system predicts that the user will select the riding mode, so that the user can confirm. The module remotely obtains the preset riding mode parameter information from the mobile terminal associated with the vehicle and remotely sends the preset riding mode parameter information to the vehicle system, so that the vehicle system can use vehicle control to automatically adjust the vehicle's seat layout according to the preset riding mode parameter information, so that space for storing bicycles is created inside the vehicle.

[0106] This embodiment provides an intelligent control system for vehicle seat layout, which allows users to confirm or cancel switching to riding mode via a mobile device and / or display device, and to adjust preset riding mode parameters, making it convenient and quick.

[0107] In summary, this invention provides a vehicle seat layout intelligent control method and system. This method, through in-depth analysis of users' historical vehicle usage data via a cloud platform, can achieve intelligent recognition of users' cycling habits and automatic adjustment of seat layout.

[0108] It should be noted that, depending on the implementation needs, the various steps described in this application can be broken down into more steps, or two or more steps or parts of the steps can be combined into new steps to achieve the purpose of this invention.

[0109] Those skilled in the art will readily understand that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for intelligent control of vehicle seat layout, characterized in that, include: Acquire user driving behavior data and vehicle status information; Based on the user's driving behavior data and vehicle status information, an algorithm model is used to predict whether the user will select riding mode. When it is predicted that the user will select the riding mode, the preset riding mode parameter information is obtained and sent to the vehicle system, so that the vehicle system can automatically adjust the vehicle's seat layout according to the preset riding mode parameter information, so that a space for storing bicycles can be created inside the vehicle. The algorithmic model is used to predict whether a user will select cycling mode. The specific method is as follows: Use an algorithm model to determine the probability that a user will activate cycling mode; This method also sets a probability threshold for activating cycling mode; The probability of the user activating cycling mode is compared with the probability threshold of activating cycling mode. If the probability of the user activating cycling mode is greater than the probability threshold for activating cycling mode, then it is predicted that the user will select cycling mode. The algorithm model calculates the probability that the user will activate cycling mode using the following formula: ； in, The probability of activating cycling mode for the user; These are the model parameters, learned from the training dataset; These are feature variables, representing the user's driving behavior data and vehicle status information.

2. The intelligent control method for vehicle seat layout according to claim 1, characterized in that, The user's driving behavior data and vehicle status information include the number of times the user activated the riding mode in the past 7 days, the user's usage time preferences, weather conditions, the user's geographical location information, destination characteristics information, and time information.

3. The intelligent control method for vehicle seat layout according to claim 1, characterized in that, The preset riding mode parameters include seat tilt angle and trunk space configuration.

4. The intelligent control method for vehicle seat layout according to claim 1, characterized in that, The preset riding mode parameters are set by the user on a mobile device associated with the vehicle according to their personal preferences.

5. The intelligent control method for vehicle seat layout according to claim 1, characterized in that, The method also includes: When it is predicted that the user will select the riding mode, a notification message is sent to the mobile device and / or the vehicle system for the user's confirmation.

6. The intelligent control method for vehicle seat layout according to claim 5, characterized in that, The notification information also includes the user's preset cycling mode parameters, which the user can modify.

7. The intelligent control method for vehicle seat layout according to claim 1, characterized in that, The method also includes: When a signal is received indicating that the user has decided to cancel the riding mode, the signal is sent to the vehicle's infotainment system, which then adjusts the vehicle's seat layout back to normal in real time.

8. A vehicle seat layout intelligent control system, applied to the method of claim 1, characterized in that, The control system is set up on a cloud platform and includes: The acquisition module is used by the cloud platform to remotely acquire user driving behavior data and vehicle status information from the vehicle's infotainment system. The prediction module is used by the cloud platform to predict whether the user will select the riding mode based on the user's driving behavior data and vehicle status information using an algorithm model. The execution module is used to remotely obtain preset riding mode parameter information from the mobile terminal associated with the vehicle when the cloud platform predicts that the user will select the riding mode, and remotely send the preset riding mode parameter information to the vehicle system so that the vehicle system can automatically adjust the seat layout of the vehicle according to the preset riding mode parameter information, so that a space for storing bicycles is created inside the vehicle.

Images