Seat posture adjusting method and device, vehicle and computer readable storage medium

Abstract

The invention provides a seat posture adjusting method and device, a vehicle and a storage medium, and relates to the technical field of vehicles. The method comprises the steps that an image of a driver located on a driving seat is obtained; recommending a first driving seat posture matched with the body type of the driver according to the image; a driving seat posture generated after the driving seat is manually adjusted is obtained, so that at least one second driving seat posture is obtained; fusing the first driving seat posture with the at least one second driving seat posture to obtain a target driving seat posture; and adjusting the current driving seat posture of the driving seat to the target driving seat posture. Based on the real-time state of the driver sitting on the driving seat, the body shape of the driver and the habit of manually adjusting the driving seat of the driver serve as the adjusting basis of the driving seat posture of the driving seat posture, automatic adjusting of the driving seat posture is achieved, the adjusted driving seat posture better meets the seat adjusting requirement of the driver, and the driving seat posture adjusting efficiency is improved. And the driving experience of the driver is improved.

Description

Technical Field

[0001] The present application relates to the field of vehicles, and more specifically, to a seat posture adjustment method, device, vehicle and computer-readable storage medium in the field of vehicles. Background Art

[0002] With the progress of society and the development of science and technology, the automobile industry has risen rapidly, and the popularity of vehicles has become increasingly higher. Vehicle seats are the parts that people come into contact with the most, and they play a vital role in people's driving experience.

[0003] The main way to adjust the posture of traditional vehicle seats is for users to adjust them manually. However, the process of users manually adjusting the driving seat is rather cumbersome, resulting in a poor driving experience for users. Summary of the invention

[0004] The present application provides a seat posture adjustment method, device, vehicle and computer-readable storage medium, which can adjust the driving seat posture based on the real-time status of the driver sitting on the driving seat, taking the driver's body shape and the driver's habit of manually adjusting the driving seat as the basis for adjusting the driving seat posture. On the basis of realizing automatic adjustment of the driving seat posture, the adjusted driving seat posture is more in line with the driver's seat adjustment needs, which is beneficial to improving the driver's driving experience.

[0005] The driving seat posture is automatically adjusted according to the driver's body shape and the driving seat posture data after manual adjustment of the driving seat, thereby improving the driver's comfort in the seat and enhancing the driving experience.

[0006] In a first aspect, a seat posture adjustment method is provided, the method comprising: acquiring an image of a driver in a driving seat; recommending a first driving seat posture suitable for the driver's body shape based on the image; acquiring a driving seat posture generated after the driving seat is manually adjusted to obtain at least one second driving seat posture; fusing the first driving seat posture and the at least one second driving seat posture to obtain a target driving seat posture; and adjusting the current driving seat posture of the driving seat to the target driving seat posture.

[0007] In the embodiment of the present application, by adopting the technical scheme of obtaining an image of the driver in the driving seat, recommending a first driving seat posture adapted to the driver's body type according to the image, obtaining the driving seat posture generated after the driving seat is manually adjusted to obtain at least one second driving seat posture, fusing the first driving seat posture and the at least one second driving seat posture to obtain a target driving seat posture, and adjusting the current driving seat posture of the driving seat to the target driving seat posture, the seat posture of the driving seat is automatically adjusted based on the real-time state of the driver sitting on the driving seat without manual adjustment. Since the first driving seat posture is obtained through the driver's body type recommendation and is associated with the driver's body type, the obtained second driving seat postures are all generated by the user who previously drove the vehicle manually adjusting the driving seat according to his own habits, so the second driving seat posture can reflect the driver's seat adjustment habits, and the current driving seat posture of the driving seat is adjusted to the target driving seat posture, while taking the driver's body type as the adjustment basis, the user's habit of manually adjusting the driving seat is taken into consideration, so that the adjusted driving seat posture is more in line with the driver's seat adjustment needs, which is conducive to improving the driver's driving experience.

[0008] In combination with the first aspect, in certain possible implementations, recommending a first driving seat posture that is suitable for the driver's body type based on the image includes: obtaining facial information of the driver based on the image; determining whether there is preset facial information in a preset information library that matches the facial information; and if so, recommending a first driving seat posture that is suitable for the driver's body type based on the image.

[0009] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, the determining whether there is preset facial information matching the facial information in the preset information library includes: determining the similarity between the facial information and each preset facial information in the preset information library to obtain multiple similarities; determining whether there is a similarity greater than a similarity threshold among the multiple similarities to determine whether there is preset facial information matching the facial information in the preset information library.

[0010] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, recommending the first driving seat posture that is adapted to the driver's body shape based on the image includes: inputting the image into a pre-trained seat posture recommendation model, and having the seat posture recommendation model extract the driver's body features from the image, and outputting multiple alternative seat postures corresponding to the body features and probability values ​​corresponding to the multiple alternative seat postures; determining the maximum probability value among the probability values ​​corresponding to the multiple alternative seat postures; and determining the alternative seat posture corresponding to the maximum probability value among the multiple alternative seat postures as the first driving seat posture.

[0011] In the embodiment of the present application, the first driving seat posture is recommended through the model and the image, which is conducive to improving the efficiency and accuracy of the driving seat posture recommendation. In addition, the first driving seat posture is recommended based on the user's body shape characteristics, which conforms to the user's body shape characteristics. The first driving seat posture is used as the basis for adjusting the driving seat, making the user more comfortable when sitting in the driving seat, thereby improving the user experience.

[0012] In combination with the first aspect and the above-mentioned implementation methods, in certain possible implementation methods, obtaining the driving seat posture generated after the driving seat is manually adjusted to obtain at least one second driving seat posture includes: when there is preset facial information matching the facial information in the preset information library, obtaining the driving seat posture of the driver after adjusting the driving seat in the past to obtain the at least one second driving seat posture; wherein, the seat posture includes the distance between the seat cushion of the driving seat and the vehicle floor, the distance between the seat cushion of the driving seat and the brake pedal, and the angle between the seat cushion of the driving seat and the backrest.

[0013] In an embodiment of the present application, when there is preset facial information matching the facial information in the preset information library, the driving seat posture of the driving seat after the driver previously adjusted the driving seat is obtained to obtain at least one second driving seat posture, and the obtained second driving seat posture can accurately reflect the driver's adjustment habits for the driving seat.

[0014] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, the fusing of the first driving seat posture and the at least one second driving seat posture to obtain the target driving seat posture includes: setting weight values ​​for the first driving seat posture and the at least one second driving seat posture, respectively, and performing weighted operations on the first driving seat posture and the at least one second driving seat posture according to the weight values ​​to obtain the target driving seat posture.

[0015] In an embodiment of the present application, a target driving seat posture is obtained by setting weights for the first driving seat posture and at least one second driving seat posture and then fusing them, so that the result of the target driving seat posture obtained better combines the first driving seat posture and the second driving seat posture.

[0016] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, setting weight values ​​for the first driving seat posture and the at least one second driving seat posture respectively includes: determining the weight value of the first driving seat posture according to the number of the first driving seat postures, the number of adjustments n of the driving seat corresponding to the at least one second driving seat posture, and the natural constant e; determining the weight value of the driving seat posture MCi generated by the i-th manual adjustment of the driving seat according to the weight value of the first driving seat posture and the number of adjustments n; wherein n is a positive integer, i=1,2,3,...,n, MCi belongs to the at least one second driving seat posture.

[0017] In an embodiment of the present application, weights are set for a first driving seat posture and at least one second driving seat posture through an exponential function model. The first driving seat posture is recommended based on the user's body shape, and the second driving seat posture is obtained based on data manually adjusted by the user, which represents the driver's personal habits. Therefore, weights are set for the first driving seat posture and the second driving seat posture through an exponential function model. While taking the user's body shape into consideration, the driver's personal habits are also taken into consideration, thereby improving the comfort of the driver sitting on the seat and enhancing the user experience.

[0018] In a second aspect, a vehicle control device is provided, the device comprising:

[0019] A first acquisition module is used to acquire an image of a driver in a driving seat;

[0020] a recommendation module, configured to recommend a first driving seat posture adapted to the driver's body type according to the image;

[0021] A second acquisition module, used to acquire a driving seat posture generated after the driving seat is manually adjusted, to obtain at least one second driving seat posture;

[0022] a third acquisition module, configured to fuse the first driving seat posture and the at least one second driving seat posture to obtain a target driving seat posture;

[0023] The adjustment module is used to adjust the current driving seat posture of the driving seat to the target driving seat posture.

[0024] In conjunction with the second aspect, in some implementations of the second aspect, the recommendation module includes:

[0025] an information acquisition unit, configured to acquire facial information of the driver according to the image;

[0026] An information matching unit, used for determining whether there is preset facial information matching the facial information in a preset information database;

[0027] A posture recommendation unit is used to recommend a first driving seat posture that is suitable for the driver's body type based on the image.

[0028] In combination with the second aspect and the above-mentioned implementation methods, in some implementation methods of the second aspect, the information matching unit is used to determine the similarity between the facial information and each preset facial information in the preset information library to obtain multiple similarities; and judge whether there is a similarity greater than a similarity threshold among the multiple similarities to judge whether there is preset facial information in the preset information library that matches the facial information.

[0029] In combination with the second aspect and the above-mentioned implementation methods, in certain implementation methods of the second aspect, the posture recommendation unit is used to input the image into a pre-trained seat posture recommendation model, and the seat posture recommendation model extracts the body features of the driver from the image, and outputs multiple alternative seat postures corresponding to the body features and probability values ​​corresponding to the multiple alternative seat postures; determines the maximum probability value among the probability values ​​corresponding to the multiple alternative seat postures; and determines the alternative seat posture corresponding to the maximum probability value among the multiple alternative seat postures as the first driving seat posture.

[0030] In combination with the second aspect and the above-mentioned implementation methods, in certain implementation methods of the second aspect, the second acquisition module is specifically used to: when there is preset facial information matching the facial information in the preset information library, obtain the driving seat posture of the driver after adjusting the driving seat in the past, and obtain the at least one second driving seat posture; wherein the seat posture includes the distance between the seat cushion of the driving seat and the vehicle floor, the distance between the seat cushion of the driving seat and the brake pedal, and the angle between the seat cushion of the driving seat and the backrest.

[0031] In combination with the second aspect and the above-mentioned implementation methods, in some implementation methods of the second aspect, the third acquisition module is specifically used to: set weight values ​​for the first driving seat posture and the at least one second driving seat posture, respectively, and perform weighted operations on the first driving seat posture and the at least one second driving seat posture according to the weight values ​​to obtain the target driving seat posture.

[0032] In combination with the second aspect and the above-mentioned implementation methods, in certain implementation methods of the second aspect, the third acquisition module is specifically used to set weight values ​​for the first driving seat posture and the at least one second driving seat posture respectively, by: determining the weight value of the first driving seat posture according to the number of the first driving seat postures, the number of adjustments n of the driving seat corresponding to the at least one second driving seat posture, and the natural constant e; determining the weight value of the driving seat posture MCi generated by the i-th manual adjustment of the driving seat according to the weight value of the first driving seat posture and the number of adjustments n; wherein n is a positive integer, i=1,2,3,...,n, and MCi belongs to the at least one second driving seat posture.

[0033] In a third aspect, a vehicle is provided, comprising a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the vehicle executes the method in the first aspect or any possible implementation of the first aspect.

[0034] In a fourth aspect, a computer program product is provided, comprising: a computer program code, which, when executed on a computer, enables the computer to execute the method in the first aspect or any possible implementation of the first aspect.

[0035] In a fifth aspect, a computer-readable storage medium is provided, which stores a computer program code. When the computer program code runs on a computer, the computer executes the method in the above-mentioned first aspect or any possible implementation manner of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A schematic diagram of a scenario of a seat posture adjustment method provided in an embodiment of the present application is shown;

[0037] Figure 2 A schematic diagram of a process of adjusting a seat posture provided in an embodiment of the present application is shown;

[0038] Figure 3 A schematic diagram of a process of driver facial recognition provided by an embodiment of the present application is shown;

[0039] Figure 4 A structural schematic diagram of a seat posture recommendation model provided in an embodiment of the present application is shown;

[0040] Figure 5 A schematic structural diagram of a seat posture adjustment device provided in an embodiment of the present application is shown;

[0041] Figure 6A schematic structural diagram of a vehicle provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0042] The technical solution in the present application will be described clearly and in detail below in conjunction with the accompanying drawings. In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B: "and / or" in the text is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, "multiple" means two or more than two.

[0043] In the following, the terms "first", "theoretical" and "theoretical" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature qualified as "first" or "theoretical" may explicitly or implicitly include one or more of the features.

[0044] like Figure 1 As shown, Figure 1 A scene schematic diagram of a seat posture adjustment method provided by an embodiment of the present application is shown. The scene includes a vehicle 100. When a user drives the vehicle 100, on the one hand, the traditional vehicle seat posture adjustment method is mainly adjusted manually by the user, but the process of manually adjusting the driving seat by the user is cumbersome, resulting in a poor driving experience for the user. On the other hand, in order to make up for the shortcomings of manually adjusting the driving seat, a seat posture automatic adjustment technology has emerged. At present, the automatic adjustment technology of the seat posture mainly associates different heights and weights with corresponding seat postures in advance. The user needs to set the seat posture in advance by setting the seat posture with one key. For example, after the user enters his height and weight, the vehicle calculates the corresponding seat posture according to the input height and weight. After the user sets the required seat posture, the vehicle stores and memorizes the seat posture set by the user. When the user subsequently uses the seat posture set by himself, he needs to manually trigger the intelligent seat adjustment button on the vehicle terminal of the vehicle, so that the vehicle adjusts the seat to the seat posture set by the user. Although this solution realizes the automatic adjustment of the seat, after the seat adjustment is completed, the seat posture is always fixed and unchanged, and will be used permanently. The seat cannot be adjusted in real time according to the real-time status of the user, which reduces the driving experience of the user.

[0045] In order to solve the above problems, the present application proposes a seat posture adjustment method, device, vehicle and computer-readable storage medium, which can automatically adjust the driving seat posture according to the driver's body shape and the posture data of the driving seat after manual adjustment, thereby improving the driver's comfort in the seat and enhancing the driving experience.

[0046] The following is an exemplary embodiment of a seat posture adjustment method provided in an embodiment of the present application.

[0047] like Figure 2 As shown, Figure 2 A schematic diagram of a seat posture adjustment method provided in an embodiment of the present application is shown, and the method includes the following schemes:

[0048] S210, acquiring an image of the driver in the driving seat.

[0049] In an exemplary embodiment, the image of the driver in the driver's seat refers to an image of the driver sitting in the driver's seat captured in real time by a camera, or an image of the driver getting on the vehicle but not sitting in the driver's seat, wherein the image includes full-body image information of the driver. After acquiring the image of the driver in the driver's seat and determining that the driver is sitting in the driver's seat, S210 is executed. The driver described in the image is referred to as the current driver, i.e., the user currently driving the vehicle.

[0050] S220: Recommending a first driving seat posture suitable for the driver's body type according to the image.

[0051] The image can be used to identify the current driver's body shape, which includes height and weight, and recommend a driving seat posture suitable for the current driver's body shape to obtain a first driving seat posture, that is, the first driving seat posture is associated with the current driver's body shape. Using the first driving seat posture as data for driving seat adjustment is more accurate and convincing.

[0052] S230, obtaining a driving seat posture generated after the driving seat is manually adjusted to obtain at least one second driving seat posture.

[0053] The manual adjustment of the driver's seat can be understood as the fact that when the same vehicle was used before, the driver's seat of the vehicle may have been manually adjusted by the same driver or by multiple different drivers. Regardless of which driver manually adjusted the driver's seat, a driver's seat posture will be generated, and the data of the driver's seat posture generated after the manual adjustment of the driver's seat will be stored in the posture database for subsequent use. In order to facilitate distinction, the driver who adjusted the driver's seat in the past is called a historical driver, and the historical driver may include the current driver.

[0054] The driving seat posture generated after the driving seat is manually adjusted is obtained from the posture database to obtain at least one second driving seat posture. Since the obtained second driving seat postures are all generated by historical drivers who have driven the vehicle in the past and manually adjusted the driving seat according to their own habits, the obtained second driving seat posture can reflect the seat adjustment habits of the historical drivers. If the obtained second driving seat posture includes the driving seat posture generated by the current driver's previous adjustment of the driving seat, it can accurately reflect the current driver's seat adjustment habits.

[0055] S240: Fusing the first driving seat posture and the at least one second driving seat posture to obtain a target driving seat posture.

[0056] After obtaining the first driving seat posture and at least one second driving seat posture, the first driving seat posture and at least one second driving seat posture are merged to obtain a target driving seat posture, and the target driving seat posture is used to represent the best seat posture for the current driver's seat adjustment needs. When the driving seat is located at the target driving seat posture, it is considered that the current driver is most comfortable sitting on the driving seat. Since the first driving seat posture is recommended based on the driver's body shape, and the second driving seat posture is obtained by manually adjusting the driving seat, the obtained target driving seat posture combines the current driver's body shape and personal seat adjustment habits, and using the target driving seat posture as the adjustment target of the driving seat is more in line with the current driver's seat adjustment needs.

[0057] S250, adjusting the current driving seat posture of the driving seat to the target driving seat posture.

[0058] After obtaining the target driving seat posture, the current driving seat posture is adjusted to the target driving seat posture. The above-mentioned current driving seat posture, the first driving seat posture, the second driving seat posture and the target driving seat posture all include the distance D1 between the driving seat cushion and the vehicle floor, the distance D2 between the driving seat cushion and the brake pedal, and the angle B between the driving seat cushion and the backrest. For example, D1=X1, D2=Y1, B=Z1 in the current driving seat posture, and D1=X2, D2=Y2, B=Z2 in the target driving seat posture. The current driving seat posture is adjusted to the target driving seat posture, that is, X1 is adjusted to X2, Y1 is adjusted to Y2, and Z1 is adjusted to Z2. In the process of automatically adjusting the driving seat posture, the current driver's body shape is used as the adjustment basis while the current driver's habit of manually adjusting the driving seat is taken into consideration, so that the adjusted driving seat posture is more in line with the current driver's seat adjustment requirements, which is conducive to improving the current driver's driving experience. Since the above-mentioned images are taken in real time, the current state of the driver can be obtained through the images. Then, according to the real-time taken images and the driver's seat being manually adjusted, the driving seat posture generated can realize real-time adjustment of the driving seat posture.

[0059] In the technical solution provided by the embodiment of the present application, by adopting the method of acquiring an image of the driver in the driving seat, recommending a first driving seat posture adapted to the driver's body type according to the image, acquiring the driving seat posture generated after the driving seat is manually adjusted to obtain at least one second driving seat posture, fusing the first driving seat posture and the at least one second driving seat posture to obtain a target driving seat posture, and adjusting the current driving seat posture of the driving seat to the target driving seat posture, the technical solution is realized to automatically adjust the seat posture of the driving seat based on the real-time state of the driver sitting on the driving seat without manual adjustment. Since the first driving seat posture is obtained through the driver's body type recommendation and is associated with the driver's body type, the second driving seat posture obtained is generated by the current driver who has previously driven the vehicle manually adjusting the driving seat according to his own habits, so the second driving seat posture can reflect the current driver's seat adjustment habits, and the current driving seat posture of the driving seat is adjusted to the target driving seat posture, while taking the current driver's body type as the adjustment basis, the current driver's habit of manually adjusting the driving seat is taken into account, so that the adjusted driving seat posture is more in line with the current driver's seat adjustment needs, which is conducive to improving the current driver's driving experience.

[0060] In a possible implementation manner, the recommending, according to the image, a first driving seat posture adapted to the driver's body shape comprises the following scheme:

[0061] Acquiring facial information of the driver according to the image;

[0062] Determining whether there is preset facial information matching the facial information in a preset information database;

[0063] If so, a first driving seat posture adapted to the driver's body type is recommended based on the image.

[0064] The facial information of the driver is obtained by extracting features from the acquired image, thereby obtaining the facial features of the driver, and the facial information of the driver is represented by the facial features. The feature extraction of the acquired image is mainly performed by using a histogram of oriented gradients (HOG), and there are other feature extraction methods that can also complete the feature extraction operation, which is not limited in the embodiment of the present application.

[0065] The preset information library includes the facial information of all historical drivers who have driven the vehicle in the past. After the facial information of the driver is obtained, it is determined whether there is preset facial information matching the facial information in the preset information library. The purpose of determining whether there is preset facial information matching the facial information in the preset information library is to determine whether the current driver has driven the vehicle before. If there is preset facial information matching the facial information in the preset information library, it means that the current driver has driven the vehicle before. Since the current driver has driven the vehicle before, he will adjust the driving seat, and the posture database will store the data of the driving seat posture generated by the current driver manually adjusting the driving seat, so the driving seat posture used to represent the current driver's seat adjustment habits can be obtained, and then the step of recommending the first driving seat posture adapted to the driver's body shape according to the image is performed. If there is no preset facial information matching the facial information in the preset information library, it means that the current driver has not driven the vehicle before, that is, the posture database will not store the data of the driving seat posture generated by the current driver manually adjusting the driving seat, so the driving seat posture used to represent the current driver's seat adjustment habits cannot be obtained, that is, the seat posture adjustment method ends.

[0066] like Figure 3 As shown, Figure 3 A schematic diagram of a driver facial recognition process provided by an embodiment of the present application is shown. In a possible implementation, the determining whether there is preset facial information matching the facial information in the preset information library includes the following schemes:

[0067] S310: Determine the similarity between the facial information and each preset facial information in the preset information library to obtain multiple similarities;

[0068] S320: Determine whether there is a similarity greater than a similarity threshold among the multiple similarities, so as to determine whether there is preset facial information matching the facial information in the preset information library; if there is a similarity greater than the similarity threshold among the multiple similarities, it indicates that there is preset facial information matching the facial information in the preset information library, that is, the facial information matching is successful; if there is no similarity greater than the similarity threshold among the multiple similarities, it indicates that there is no preset facial information matching the facial information in the preset information library, that is, the facial information matching fails.

[0069] After the facial information is obtained, the similarity between the facial information and each preset facial information in the preset information library is calculated to obtain multiple similarities. By judging whether there is a similarity greater than a similarity threshold among the multiple similarities, it is judged whether there is preset facial information matching the facial information in the preset information library. Specifically, if there is a similarity greater than the similarity threshold among the multiple similarities, it means that there is preset facial information matching the facial information in the preset information library, that is, the current driver has driven the vehicle before and often drives the vehicle; if there is no similarity greater than the similarity threshold among the multiple similarities, it means that there is no preset facial information matching the facial information in the preset information library, that is, the current driver has not driven the vehicle before. For example, the multiple similarities are obtained as follows: 80%, 10%, 5%, 4%, 1%, and the similarity threshold is set to 75%. Among them, 80% is greater than 75%, then it is considered that there is preset facial information matching the facial information in the preset information library, that is, the preset facial information corresponding to the similarity of 80% matches the acquired facial information. By similarity matching, it is determined whether there is preset facial information matching the facial information in the preset information library, so that the determination result is more accurate.

[0070] In a possible implementation manner, the recommending, according to the image, a first driving seat posture adapted to the driver's body shape comprises the following scheme:

[0071] Inputting the image into a pre-trained seat posture recommendation model, the seat posture recommendation model extracts the body shape features of the driver from the image, and outputs a plurality of candidate seat postures corresponding to the body shape features and probability values ​​corresponding to the plurality of candidate seat postures;

[0072] Determining a maximum probability value among the probability values ​​corresponding to the plurality of candidate seat postures;

[0073] The alternative seat posture corresponding to the maximum probability value among the multiple alternative seat postures is determined as the first driving seat posture.

[0074] The seat posture recommendation model adopts a deep neural network algorithm, and can also be trained using other neural network algorithms, which is not limited in the embodiments of the present application. The seat posture recommendation model is pre-trained and includes multiple network layers, namely L1, L2, ...Ln. The training process of the seat posture recommendation model is: prepare a large number of sample images including the user's entire body, each sample image can obtain the current driver's body shape characteristics, namely height characteristics and weight characteristics, and then annotate the corresponding seat posture for each sample image, and then divide all sample images into training sets and verification sets, and use the training sets and verification sets to iteratively train the seat posture recommendation model until the model converges and stops training. Among them, the input of the seat posture recommendation model is an image, and the output is a plurality of driving seat postures with probability values. The final output is the driving seat posture with the largest probability value as the final model output result.

[0075] like Figure 4 As shown, Figure 4 The schematic diagram of the seat posture recommendation model provided by the embodiment of the present application is shown. The input 410 of the seat posture recommendation model 430 is the image of the above-mentioned driver in the driving seat, that is, the image of the current driver in the driving seat, and the output 420 is the first driving seat posture. Specifically, the image of the current driver in the driving seat is input into the seat posture recommendation model, and the seat posture recommendation model extracts the body shape features of the current driver from the image, and then calculates multiple seat postures that match the body shape features, which are called multiple candidate seat postures, and then outputs multiple candidate seat postures and probability values ​​corresponding to multiple candidate seat postures, and then determines the candidate seat posture corresponding to the maximum probability value as the first driving seat posture, and uses it as the final output result. For example, the multiple candidate seat postures are posture 1, posture 2 and posture 3, respectively, wherein the probability value corresponding to posture 3 is the maximum value among the probability values ​​of posture 1, posture 2 and posture 3, and posture 3 is the first driving seat posture.

[0076] The first driving seat posture is recommended through the model and the image, which is beneficial to the efficiency and accuracy of the driving seat posture recommendation. In addition, the first driving seat posture is recommended based on the current driver's body shape characteristics, which conforms to the user's body shape characteristics. The first driving seat posture is used as the basis for adjusting the driving seat, so that the current driver can sit more comfortably in the driving seat, thereby improving the driving experience.

[0077] In a possible implementation, the acquiring the driving seat posture generated after the driving seat is manually adjusted to obtain at least one second driving seat posture includes the following scheme:

[0078] In the case where preset facial information matching the facial information exists in the preset information library, the driving seat posture of the driver after adjusting the driving seat in the past is obtained to obtain the at least one second driving seat posture.

[0079] After determining that the current driver has driven the vehicle, the posture database stores data on the driving seat posture generated by the current driver after adjusting the driving seat in the past. Therefore, the data on the driving seat posture generated by the current driver after adjusting the driving seat in the past can be obtained from the posture database. Then, when there is preset facial information matching the facial information in the preset information library, the driving seat posture of the current driver after adjusting the driving seat in the past is obtained to obtain at least one second driving seat posture. The obtained second driving seat posture can accurately reflect the current driver's adjustment habits for the driving seat. Among them, the driving seat posture stored in the posture database includes: the distance between the seat cushion of the driving seat and the vehicle floor, the distance between the seat cushion of the driving seat and the brake pedal, and the angle between the seat cushion of the driving seat and the backrest.

[0080] In a possible implementation, the fusing the first driving seat posture and the at least one second driving seat posture to obtain a target driving seat posture includes the following scheme:

[0081] Weight values ​​are respectively set for the first driving seat posture and the at least one second driving seat posture, and weighted operations are performed on the first driving seat posture and the at least one second driving seat posture according to the weight values ​​to obtain the target driving seat posture.

[0082] When obtaining at least one second driving seat posture, it is necessary not only to record the second driving seat posture, but also to record the generation time corresponding to the adjustment of each second driving seat posture. The closer to the current time, the lower the weight set for the corresponding second driving seat posture. For example, the current time is October 7, and the driving seat posture has been manually adjusted 3 times, at 9:00 on October 1, 17:00 on October 1, and 12:00 on October 3. When setting the weight, the weight set for the second driving seat posture at 9:00 on October 1 is 0.47, the weight set for the second driving seat posture at 17:00 on October 1 is 0.29, and the weight set for the second driving seat posture at 12:00 on October 3 is 0.24.

[0083] By setting weight values ​​for the first driving seat posture and at least one second driving seat posture, the weight values ​​for the first driving seat posture and at least one second driving seat posture are different, and when there are multiple second driving seat postures, each of the multiple second driving seat postures corresponds to a time point, and the closer the time point is to the current time point, the smaller the weight value of the second driving seat posture. For example, the multiple second driving seat postures are posture A, posture B, and posture C, and the time points of posture A, posture B, and posture C are arranged in chronological order as posture A, posture B, and posture C, then the weight value of posture A>the weight value of posture B>the weight value of posture C. After setting weight values ​​for the first driving seat posture and at least one second driving seat posture respectively, weighted operations are performed on the first driving seat posture and the at least one second driving seat posture according to the weight values ​​to obtain a target driving seat posture, thereby realizing the fusion of the first driving seat posture and the at least one second driving seat posture, that is, the driving seat posture related to the current driver's body shape and the driving seat posture reflecting the current driver's seat adjustment habits are integrated. When the target driving seat posture is used as the target adjustment basis for the driving seat, the adjusted driving seat posture can be more in line with the current driver's seat adjustment needs, which is beneficial to improving the current driver's driving experience.

[0084] In a possible implementation, setting weight values ​​for the first driving seat posture and the at least one second driving seat posture respectively includes the following schemes:

[0085] determining a weight value of the first driving seat posture according to the number of the first driving seat postures, the number of times n of adjusting the driving seat corresponding to the at least one second driving seat posture, and a natural constant e;

[0086] Determine the driving seat posture MC generated by the i-th manual adjustment of the driving seat according to the weight value of the first driving seat posture and the adjustment number n i The weight value; where n is a positive integer, i = 1, 2, 3, ..., n, MC i Belongs to the at least one second driving seat posture.

[0087] Specifically, the first driving seat posture and the at least one second driving seat posture are input into a preset exponential function model, and the preset exponential function model sets weight values ​​for the first driving seat posture and the at least one second driving seat posture respectively, and performs weighted operation on the first driving seat posture and the at least one second driving seat posture according to the weight values ​​to obtain the target driving seat posture; wherein the preset exponential function model is:

[0088]

[0089]

[0090] Where n represents the number of times the driver's seat is adjusted, RC represents the first driver's seat posture, and MC i represents the driving seat posture resulting from the i-th manual adjustment of the driving seat, MC i Belongs to the second driving seat posture, that is, the second driving seat posture includes MC i , C represents the target driving seat posture, i represents the total number of manual adjustments to the driving seat posture, i=1,2,3,...,n, b is a parameter less than a preset value, for example, b<-2, wherein the weight values ​​of the first driving seat posture and the second driving seat posture can be adjusted by adjusting b.

[0091] The fusion of a first driving seat posture and at least one second driving seat posture is achieved through a preset exponential function model, thereby improving the efficiency of generating a target driving seat posture. The target driving seat posture is calculated through a preset exponential function model, so that the seat posture is continuously close to the ideal seat posture of the driver currently driving the vehicle, making the adjustment of the vehicle driving seat posture more intelligent, which is conducive to improving the driving experience.

[0092] like Figure 5 As shown, Figure 5 The structure diagram of a seat posture adjustment device provided in an embodiment of the present application is shown. The seat posture adjustment device 500 includes:

[0093] A first acquisition module 510 is used to acquire an image of a driver in a driving seat;

[0094] A recommendation module 520, for recommending a first driving seat posture adapted to the driver's body type according to the image;

[0095] A second acquisition module 530 is used to acquire a driving seat posture generated after the driving seat is manually adjusted, and obtain at least one second driving seat posture;

[0096] A third acquisition module 540, configured to fuse the first driving seat posture and at least one second driving seat posture to obtain a target driving seat posture;

[0097] The adjustment module 550 is used to adjust the current driving seat posture of the driving seat to the target driving seat posture.

[0098] In a possible implementation, the recommendation module 520 includes:

[0099] An information acquisition unit, used for acquiring the driver's facial information according to the image;

[0100] An information matching unit, used for determining whether there is preset facial information matching the facial information in a preset information database;

[0101] The posture recommendation unit is used to recommend a first driving seat posture adapted to the driver's body type based on the image if so.

[0102] In one possible implementation, the information matching unit is specifically used to determine the similarity between the facial information and each preset facial information in a preset information library to obtain multiple similarities; and to determine whether there is a similarity greater than a similarity threshold among the multiple similarities to determine whether there is preset facial information in the preset information library that matches the facial information.

[0103] In one possible implementation, the posture recommendation unit is specifically used to input the image into a pre-trained seat posture recommendation model, and the seat posture recommendation model extracts the driver's body features from the image, and outputs multiple alternative seat postures corresponding to the body features and probability values ​​corresponding to the multiple alternative seat postures; determines the maximum probability value among the probability values ​​corresponding to the multiple alternative seat postures; and determines the alternative seat posture corresponding to the maximum probability value among the multiple alternative seat postures as the first driving seat posture.

[0104] In one possible implementation, the second acquisition module 530 is specifically used to: when there is preset facial information matching the facial information in the preset information library, obtain the driving seat posture of the driving seat after the driver previously adjusted the driving seat, and obtain at least one second driving seat posture; wherein the seat posture includes the distance between the seat cushion of the driving seat and the vehicle floor, the distance between the seat cushion of the driving seat and the brake pedal, and the angle between the seat cushion of the driving seat and the backrest.

[0105] In one possible implementation, the third acquisition module 540 is specifically used to: set weight values ​​for the first driving seat posture and at least one second driving seat posture respectively, perform weighted operations on the first driving seat posture and at least one second driving seat posture according to the weight values, and obtain the target driving seat posture.

[0106] In a possible implementation, the third acquisition module 540 is specifically used to set weight values ​​for the first driving seat posture and the at least one second driving seat posture respectively: determine the weight value of the first driving seat posture according to the number of the first driving seat postures, the number of adjustment times n of the driving seat corresponding to the at least one second driving seat posture, and the natural constant e; determine the driving seat posture MC generated by the i-th manual adjustment of the driving seat according to the weight value of the first driving seat posture and the number of adjustment times n. i The weight value; where n is a positive integer, i = 1, 2, 3, ..., n, MC iBelongs to the at least one second driving seat posture.

[0107] Figure 6 FIG. 1 shows a schematic diagram of the structure of a vehicle provided in an embodiment of the present application. Figure 6 As shown, the vehicle 600 includes: a memory 601 and a processor 602, wherein the memory 601 stores an executable program code 6011, and the processor 602 is used to call and execute the executable program code 6011 to perform a method for adjusting a seat posture.

[0108] In addition, an embodiment of the present application also protects a device, which may include a memory and a processor, wherein the memory stores an executable program code, and the processor is used to call and execute the executable program code to execute a seat posture adjustment method provided in an embodiment of the present application.

[0109] In this embodiment, the functional modules of the device can be divided according to the above method example. For example, each functional module can be corresponded, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0110] In the case of dividing each functional module according to each function, the device may further include a first acquisition module, a recommendation module, a second acquisition module, a third acquisition module, and an adjustment module, etc. It should be noted that all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, which will not be repeated here.

[0111] It should be understood that the device provided in this embodiment is used to execute the above-mentioned method for adjusting the seat posture, and thus can achieve the same effect as the above-mentioned implementation method.

[0112] In the case of an integrated unit, the device may include a processing module and a storage module. When the device is applied to a vehicle, the processing module may be used to control and manage the actions of the vehicle. The storage module may be used to support the vehicle in executing mutual program codes, etc.

[0113] The processing module may be a processor or a controller, which may implement or execute various exemplary logic blocks, modules and circuits disclosed in the present application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module may be a memory.

[0114] In addition, the device provided in the embodiments of the present application may specifically be a chip, a component or a module, and the chip may include a connected processor and a memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute a seat posture adjustment method provided in the above embodiments.

[0115] This embodiment also provides a computer-readable storage medium, in which a computer program code is stored. When the computer program code is run on a computer, the computer executes the above-mentioned related method steps to implement a seat posture adjustment method provided in the above embodiment.

[0116] This embodiment also provides a computer program product. When the computer program product is run on a computer, the computer is caused to execute the above-mentioned related steps to implement a seat posture adjustment method provided in the above embodiment.

[0117] Among them, the device, computer-readable storage medium, computer program product or chip provided in this embodiment is used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, and will not be repeated here.

[0118] Through the description of the above implementation methods, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0119] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0120] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A seat posture adjustment method, characterized in that: The method comprises: Acquire an image of a driver in a driving seat; recommending a first driving seat posture adapted to the driver's body type according to the image; Acquiring a driving seat posture generated after the driving seat is manually adjusted to obtain at least one second driving seat posture; fusing the first driving seat posture and the at least one second driving seat posture to obtain a target driving seat posture; Adjust the current driving seat posture of the driving seat to the target driving seat posture.

2. The method according to claim 1, characterized in that The recommending, according to the image, a first driving seat posture adapted to the driver's body shape comprises: Acquiring facial information of the driver according to the image; Determining whether there is preset facial information matching the facial information in a preset information database; If so, a first driving seat posture adapted to the driver's body type is recommended based on the image.

3. The method according to claim 2, characterized in that The determining whether there is preset facial information matching the facial information in the preset information database comprises: Determine the similarity between the facial information and each preset facial information in the preset information library to obtain multiple similarities; It is determined whether there is a similarity greater than a similarity threshold among the multiple similarities, so as to determine whether there is preset facial information matching the facial information in the preset information library.

4. The method according to claim 2, characterized in that: The recommending, according to the image, a first driving seat posture adapted to the driver's body shape comprises: Inputting the image into a pre-trained seat posture recommendation model, the seat posture recommendation model extracts the body shape features of the driver from the image, and outputs a plurality of candidate seat postures corresponding to the body shape features and probability values ​​corresponding to the plurality of candidate seat postures; Determining a maximum probability value among the probability values ​​corresponding to the plurality of candidate seat postures; The alternative seat posture corresponding to the maximum probability value among the multiple alternative seat postures is determined as the first driving seat posture.

5. The method according to claim 2, characterized in that: The step of obtaining a driving seat posture generated after the driving seat is manually adjusted to obtain at least one second driving seat posture comprises: When there is preset facial information matching the facial information in the preset information library, the driving seat posture of the driver after previously adjusting the driving seat is obtained to obtain the at least one second driving seat posture; wherein, the driving seat posture includes the distance between the seat cushion of the driving seat and the vehicle floor, the distance between the seat cushion of the driving seat and the brake pedal, and the angle between the seat cushion of the driving seat and the backrest.

6. The method according to any one of claims 1 to 5, characterized in that: The fusing the first driving seat posture and the at least one second driving seat posture to obtain a target driving seat posture comprises: Weight values ​​are respectively set for the first driving seat posture and the at least one second driving seat posture, and weighted operations are performed on the first driving seat posture and the at least one second driving seat posture according to the weight values ​​to obtain the target driving seat posture.

7. The method according to claim 6, characterized in that The setting of weight values ​​for the first driving seat posture and the at least one second driving seat posture respectively comprises: determining a weight value of the first driving seat posture according to the number of the first driving seat postures, the number of times n of adjusting the driving seat corresponding to the at least one second driving seat posture, and a natural constant e; Determine the driving seat posture MC generated by the i-th manual adjustment of the driving seat according to the weight value of the first driving seat posture and the adjustment number n i The weight value; where n is a positive integer, i = 1, 2, 3, ..., n, MC i Belongs to the at least one second driving seat posture.

8. A seat posture adjustment device, characterized in that: The device comprises: A first acquisition module is used to acquire an image of a driver in a driving seat; a recommendation module, configured to recommend a first driving seat posture adapted to the driver's body type according to the image; A second acquisition module, used to acquire a driving seat posture generated after the driving seat is manually adjusted, to obtain at least one second driving seat posture; a third acquisition module, configured to fuse the first driving seat posture and the at least one second driving seat posture to obtain a target driving seat posture; The adjustment module is used to adjust the current driving seat posture of the driving seat to the target driving seat posture.

9. A vehicle, characterized in that: The vehicle comprises: A memory for storing executable program codes; A processor, configured to call and run the executable program code from the memory, so that the vehicle executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the method according to any one of claims 1 to 7 is implemented.

Images