Seat adjusting method and device, electronic equipment, vehicle and storage medium

Abstract

The invention relates to a seat adjusting method and device, electronic equipment, a vehicle and a storage medium, and relates to the technical field of vehicle seats. The method comprises the following steps: acquiring real-time pressure information, wherein the real-time pressure information is used for reflecting the pressure distribution condition of a passenger on each position of a seat; determining a comfort level score based on the real-time pressure information; under the condition that the comfort level score is smaller than a preset threshold value, the seat is adjusted based on the mapping relation between the seat adjusting parameters and the change trend of the pressure distribution; the change trend of the pressure distribution affects the comfort level score. Therefore, the problems that in the prior art, the accuracy of adjusting the comfort degree of the seat is poor, and the real-time requirement of passengers for the comfort degree cannot be met can be at least solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle seats, in particular to the field of adaptive adjustment of vehicle seats, and specifically to a seat adjustment method and device, an electronic device, a vehicle and a storage medium. BACKGROUND

[0002] With the continuous development of automobile technology and the continuous development of the demand for comfort of drivers and passengers, the comfort of the seat inside the vehicle is also increasingly high. The seat inside the vehicle is the main human-computer interaction interface of the vehicle passenger, and the comfort of the seat is an important factor affecting the driving experience of the passenger.

[0003] In the related art, when adjusting the seat, the preset digital human model or database is usually relied on to obtain the human body features, and the corresponding optimal seat posture is searched in the preset digital human model or database to adjust the seat. However, based on the static human body feature data to adjust the seat, it may not adapt to the dynamic changes of the passenger during the ride, and thus the accuracy of the seat comfort adjustment is poor, and the real-time demand of the passenger for comfort cannot be met. SUMMARY

[0004] The present application provides a seat adjustment method, device, electronic device, vehicle and storage medium to at least solve the problem that the accuracy of the related art seat comfort adjustment is poor and the real-time demand of the passenger for comfort cannot be met. The technical solutions of the present application are as follows:

[0005] According to a first aspect of the present application, a seat adjustment method is provided, which comprises:

[0006] Obtaining real-time pressure information, the real-time pressure information being used to reflect the pressure distribution of the passenger on each position of the seat;

[0007] Based on the real-time pressure information, determining a comfort score;

[0008] In the case where the comfort score is less than a preset threshold, adjusting the seat based on the mapping relationship between the seat adjustment parameters and the change trend of the pressure distribution; the change trend of the pressure distribution affects the high and low of the comfort score.

[0009] According to the above technical means, compared with the related art, when the seat is adjusted, only the human body characteristics of the occupant (for example, the height and weight of the occupant) are usually considered, the accuracy of the seat comfort adjustment is poor, and the real-time demand of the occupant for comfort cannot be met. The method provided in the embodiment of the present application obtains the pressure distribution of the seat of the occupant based on the real-time pressure information, and determines the comfort score based on the real-time pressure information, so as to determine the satisfaction degree of the occupant for the comfort of the seat and the comfort state of the occupant in real time, and provide accurate data support for the seat adjustment. At the same time, the method provided in the present application adjusts the seat based on the mapping relationship between the change trend of the pressure distribution and the seat adjustment parameter when the comfort score does not meet the preset threshold, so as to timely respond to the change of the posture of the occupant, adapt to the real-time demand of the occupant, and realize the accuracy of the seat adjustment.

[0010] In addition, based on the real-time pressure information, the comfort adjustment can be performed without relying on the human body characteristics such as height and weight which have limitations, but can fully consider the individualized demand of the occupant with different body characteristics and body shapes for comfort, improve the accuracy of the seat adjustment, and further improve the use experience of the occupant.

[0011] In a possible implementation, when the comfort score is less than the preset threshold, the seat is adjusted based on the mapping relationship between the seat adjustment parameter and the change trend of the pressure distribution, including: when the comfort score is less than the preset threshold, a target change trend of the pressure distribution is determined; the target change trend is used to improve the comfort score; based on the target change trend and the mapping relationship between the seat adjustment parameter and the change trend of the pressure distribution, a trend of adjustment of the seat adjustment parameter is determined; and the seat is adjusted based on the trend of adjustment of the seat adjustment parameter.

[0012] According to the above technical means, when the comfort score is less than the preset threshold, the method provided in the present application can determine that the satisfaction degree of the user for the comfort of the seat is low at this time, and the target change trend of the pressure distribution which can improve the comfort score is determined at this time, and the trend of adjustment of the seat adjustment parameter is determined based on the mapping relationship between the seat adjustment parameter and the change trend of the pressure distribution, so as to provide a clear direction for the seat adjustment, and ensure that the adjustment of the seat can effectively improve the comfort of the occupant.

[0013] In a possible implementation, the target change trend of the pressure distribution is determined, including: based on the trained comfort prediction model, a target change trend of the pressure distribution is determined when the comfort score is greater than or equal to the preset threshold; and the comfort prediction model is used to predict the comfort score of the seat of the occupant.

[0014] According to the technical means, the comfort degree prediction model can predict the comfort degree score of the passenger on the seat under the current or dynamically changing condition. The method provided in the application can determine the target change trend of the pressure distribution in the process of continuously optimizing the comfort degree score until the comfort degree score is greater than or equal to the preset threshold, so as to determine the adjustment trend of the seat based on the target change trend of the pressure distribution. In general, the method provided in the application continuously optimizes and adjusts the comfort degree of the seat based on the comfort degree prediction model, which can ensure the accuracy of the seat comfort adjustment and improve the comfort degree of the passenger.

[0015] In a possible implementation, the method further includes: obtaining first historical pressure information in a first preset time period and a seat adjustment parameter corresponding to the first historical pressure information; and establishing a mapping relationship between the seat adjustment parameter and the change trend of the pressure distribution based on the first historical pressure information and the seat adjustment parameter corresponding to the first historical pressure information.

[0016] According to the technical means, the method provided in the application can obtain the historical pressure information and the corresponding seat adjustment parameter, and establish the mapping relationship between the seat adjustment parameter and the change trend of the pressure distribution, which can facilitate subsequent determination of the adjustment trend of the seat based on the target change trend of the pressure distribution, so as to adjust the seat. In addition, the method provided in the application optimizes the adjustment of the seat based on the historical pressure information and other historical data, which can improve the accuracy and efficiency of the seat adjustment.

[0017] In a possible implementation, the method further includes: obtaining comfort degree measurement information; the comfort degree measurement information includes: a region of local stimulation, a local comfort degree of each region of the human body to the local stimulation, and an overall comfort degree; determining a weight coefficient of each region of the human body based on the comfort degree measurement information; the weight coefficient is used to reflect the influence degree of the local comfort degree of each region of the human body on the overall comfort degree; determining a target pressure distribution index of each region from a preselected pressure distribution index based on the weight coefficient; constructing a comfort degree prediction model based on the target pressure distribution index of each region; the comfort degree prediction model is used to predict the comfort degree score of the passenger on the seat.

[0018] According to the technical means, the method provided in the application can accurately determine the key region affecting the overall comfort degree and the weight coefficient thereof by obtaining and analyzing comprehensive comfort degree measurement information (for example, the region of local stimulation, the local comfort degree of each region of the human body to the local stimulation, and the overall comfort degree, and the like). By weighting the comfort degrees of different regions through the weight coefficient, the physical sensitivity of different body parts of different passengers can be fully considered, so that the seat adjustment is no longer a generalization, but a targeted optimization of the seat setting.

[0019] In addition, the method provided in the application determines the target pressure distribution index of each region from the preselected pressure distribution index based on the weight coefficient, which can make the construction of the comfort prediction model more accurate and enable the comfort prediction model to more accurately reflect the comfort feeling of the occupant.

[0020] In a possible implementation, the determination of the target pressure distribution index of each region from the preselected pressure distribution index based on the weight coefficient includes: determining a correlation coefficient between each preselected pressure distribution index and the local comfort degree of each region; determining the number of target pressure distribution indexes of each region based on the weight coefficient; and determining the target pressure distribution index of each region from the preselected pressure distribution index based on the number of target pressure distribution indexes of each region and the correlation coefficient ranking of the preselected pressure distribution index of each region.

[0021] According to the above technical means, the correlation coefficient can determine the relationship between different pressure distribution indexes and comfort, so as to more accurately predict the influence of pressure distribution change on comfort. By combining the weight coefficient and the correlation coefficient, the target pressure distribution index of each region can be determined from the preselected pressure distribution index, which can make the construction of the comfort prediction model more accurate. The comfort prediction model can determine which pressure distribution index has a greater influence on comfort, so as to optimize the seat adjustment strategy to achieve the best comfort improvement.

[0022] In a possible implementation, the determination of the comfort score based on the real-time pressure information includes: inputting the real-time pressure information into the trained comfort prediction model to obtain the comfort score.

[0023] According to the above technical means, by inputting the real-time pressure information into the trained comfort prediction model, the comfort score can be quickly determined in real time based on the current pressure state of the occupant, and the comfort feeling of the occupant for the seat can be sensed in time, so as to subsequently dynamically adjust the seat based on the comfort score to adapt to the dynamic comfort demand of the occupant under different driving or riding conditions.

[0024] According to a second aspect provided in the application, a seat adjustment device is provided, including:

[0025] The acquisition module is configured to acquire real-time pressure information, the real-time pressure information being used to reflect the pressure distribution of the occupant on each position of the seat.

[0026] The determination module is configured to determine a comfort score based on the real-time pressure information.

[0027] The adjusting module is configured to adjust the seat based on a mapping relationship between the seat adjusting parameter and the change trend of the pressure distribution when the comfort score is less than the preset threshold; and the change trend of the pressure distribution affects the comfort score.

[0028] In a possible implementation, the determining module is further configured to determine a target change trend of the pressure distribution when the comfort score is less than the preset threshold; the target change trend is used to improve the comfort score; determine an adjusting trend of the seat adjusting parameter based on the target change trend and the mapping relationship between the seat adjusting parameter and the change trend of the pressure distribution; and the adjusting module is specifically configured to adjust the seat based on the adjusting trend of the seat adjusting parameter.

[0029] In a possible implementation, the determining module is specifically configured to determine a target change trend of the pressure distribution when the comfort score is greater than or equal to the preset threshold based on the trained comfort prediction model; and the comfort prediction model is used to predict the comfort score of the seat for the occupant.

[0030] In a possible implementation, the apparatus further includes a constructing module, and the obtaining module is further configured to obtain first historical pressure information in a first preset time period and a seat adjusting parameter corresponding to the first historical pressure information; and the constructing module is configured to establish the mapping relationship between the seat adjusting parameter and the change trend of the pressure distribution based on the first historical pressure information and the seat adjusting parameter corresponding to the first historical pressure information.

[0031] In a possible implementation, the obtaining module is further configured to obtain comfort measurement information; the comfort measurement information includes a region of local stimulation, a local comfort degree of each region of the human body to the local stimulation, and an overall comfort degree; the determining module is further configured to determine a weight coefficient of each region of the human body based on the comfort measurement information; the weight coefficient is used to reflect an influence degree of the local comfort degree of each region of the human body on the overall comfort degree; determine a target pressure distribution index of each region from preselected pressure distribution indexes based on the weight coefficient; and the constructing module is further configured to construct a comfort prediction model based on the target pressure distribution index of each region; and the comfort prediction model is used to predict the comfort score of the seat for the occupant.

[0032] In a possible implementation, the determining module is specifically configured to determine a correlation coefficient between each preselected pressure distribution index and the local comfort degree of each region; determine a number of the target pressure distribution index of each region based on the weight coefficient; and determine the target pressure distribution index of each region from the preselected pressure distribution indexes based on the number of the target pressure distribution index of each region and a correlation coefficient ranking of the preselected pressure distribution index of each region.

[0033] In a possible implementation, the determining module is specifically configured to input the real-time pressure information into the trained comfort prediction model to obtain the comfort score.

[0034] According to a third aspect provided in the present application, an electronic device is provided, comprising a memory and a processor; the memory and the processor are coupled; the memory is configured to store computer program code, the computer program code comprising computer instructions; when the processor executes the computer instructions, the electronic device performs the seat adjustment method of the first aspect and any possible implementation thereof.

[0035] According to a fourth aspect provided in the present application, a vehicle is provided, comprising the electronic device.

[0036] According to a fifth aspect provided in the present application, a computer readable storage medium is provided, when instructions in the computer readable storage medium are executed by a processor of an electronic device, the electronic device can perform the seat adjustment method of the first aspect and any possible implementation thereof.

[0037] Therefore, the above technical features of the present application have the following beneficial effects:

[0038] (1) Compared with the related art, in which only the human body features of the occupant (for example, the height and weight of the occupant) are considered when the seat is adjusted, the accuracy of the seat comfort adjustment is poor, and the real-time demand of the occupant for comfort cannot be met. The method provided in the embodiments of the present application obtains the pressure distribution of the occupant on the seat based on real-time pressure information, and determines the comfort score based on the real-time pressure information, so as to determine the satisfaction degree of the occupant for the comfort of the seat and the comfort state of the occupant in real time, and provide accurate data support for the seat adjustment. At the same time, in the case where the comfort score does not meet the preset threshold, the seat is adjusted based on the change trend of the pressure distribution and the mapping relationship of the seat adjustment parameters, so as to timely respond to the change of the posture of the occupant, adapt to the real-time demand of the occupant, and realize the accuracy of the seat adjustment.

[0039] In addition, based on the real-time pressure information, the comfort adjustment can be performed without relying on the human body features such as height and weight, which have limitations, but can fully consider the individualized demand of the occupant with different body features and body types for comfort, improve the accuracy of the seat adjustment, and further improve the use experience of the occupant.

[0040] (2) The method provided by the application can determine that the user is less satisfied with the comfort of the seat when the comfort score is less than the preset threshold value, and the target change trend of the pressure distribution that can improve the comfort score is determined, and the adjustment trend of the seat adjustment parameter is determined based on the mapping relationship between the seat adjustment parameter and the change trend of the pressure distribution, so that the seat adjustment can be provided with a clear direction, and the comfort of the passenger can be effectively improved by adjusting the seat.

[0041] (3) The comfort prediction model can predict the comfort score of the seat of the passenger in the current or dynamic change situation, and the method provided by the application can determine the target change trend of the pressure distribution in the process of continuously optimizing the comfort score until the comfort score is greater than or equal to the preset threshold value, so as to determine the adjustment trend of the seat based on the target change trend of the pressure distribution. In general, the method provided by the application continuously optimizes and adjusts the comfort of the seat based on the comfort prediction model, so as to ensure the accuracy of the seat comfort adjustment and improve the comfort of the passenger.

[0042] (4) The method provided by the application can determine the adjustment trend of the seat based on the target change trend of the pressure distribution by obtaining historical pressure information and corresponding seat adjustment parameters and establishing a mapping relationship between the change trend of the seat adjustment parameter and the pressure distribution, so as to adjust the seat. In addition, the method provided by the application optimizes the adjustment of the seat based on historical pressure information and other historical data, so as to improve the accuracy and efficiency of the seat adjustment.

[0043] (5) The method provided by the application can accurately determine the key area affecting the overall comfort and its weight coefficient by obtaining and analyzing comprehensive comfort measurement information (such as the area of local stimulation, the local comfort degree of each area of the human body to the local stimulation, and the overall comfort degree, etc.). By setting the weight coefficient to weight the comfort of different areas, the physical sensitivity of different body parts of different passengers can be fully considered, so that the seat adjustment is no longer a generalization, but a targeted optimization of the seat setting.

[0044] In addition, the method provided by the application determines the appropriate target pressure distribution index for each area from the preselected pressure distribution index based on the weight coefficient, so that the construction of the comfort prediction model is more accurate, and the comfort prediction model can more accurately reflect the comfort feeling of the passenger.

[0045] (6) The correlation coefficient can determine the relationship between different pressure distribution indicators and comfort, so as to more accurately predict the influence of pressure distribution changes on comfort. By combining the weight coefficient and the correlation coefficient, the appropriate target pressure distribution indicator for each region can be determined from the pre-selected pressure distribution indicators, which can make the construction of the comfort prediction model more accurate. The comfort prediction model can determine which pressure distribution indicators have a greater influence on comfort, so as to optimize the seat adjustment strategy to achieve the best comfort improvement.

[0046] (7) By inputting real-time pressure information into the trained comfort prediction model, the comfort score can be quickly determined in real time based on the current pressure state of the occupant, and the comfort feeling of the occupant for the seat can be sensed in time, so as to dynamically adjust the seat based on the comfort score in the subsequent process to adapt to the dynamic comfort needs of the occupant under different driving or riding conditions.

[0047] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0048] The accompanying drawings incorporated in and forming a part of the specification illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the application without imposing on the application any unnecessary limitations.

[0049] Figure 1 A schematic diagram of a seat adjustment system according to an embodiment of the present application;

[0050] Figure 2 A comparison diagram of different positions of a seat and body regions of an occupant according to an embodiment of the present application;

[0051] Figure 3 A flowchart of a seat adjustment method according to an embodiment of the present application;

[0052] Figure 4 A flowchart of another seat adjustment method according to an embodiment of the present application;

[0053] Figure 5 A flowchart of still another seat adjustment method according to an embodiment of the present application;

[0054] Figure 6 A flowchart of still another seat adjustment method according to an embodiment of the present application;

[0055] Figure 7 A flowchart of still another seat adjustment method according to an embodiment of the present application;

[0056] Figure 8 A comfort indicator according to an embodiment of the present application;

[0057] Figure 9 A schematic diagram of a placement position of a thin steel sheet provided for an embodiment of the present application;

[0058] Figure 10 A flowchart of another seat adjustment method provided for an embodiment of the present application;

[0059] Figure 11 A flowchart of another seat adjustment method provided for an embodiment of the present application;

[0060] Figure 12 A schematic diagram of a seat adjustment device provided for an embodiment of the present application;

[0061] Figure 13 A schematic diagram of an electronic device provided for an embodiment of the present application. DETAILED DESCRIPTION

[0062] In order for those skilled in the art to better understand the technical solutions of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying drawings.

[0063] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely some methods of the present application as detailed in the appended claims.

[0064] In the user product index attention coefficient, comfort has always been among the top three indicators of user attention, which also makes the comfort of the car seat develop with the needs of the passengers for comfort, and the cabin gradually evolves into the third space of people's life, and users demand higher comfort for the seat. Body pressure information (also known as pressure information, used to reflect the pressure distribution of the passenger on the seat surface) is considered to be able to more completely represent the contact information of the passenger-seat interface, and it has always been a research hotspot of seat static posture comfort. In recent years, flexible manufacturing and additive manufacturing processes have been continuously developed, and flexible printed electronic pressure sensors that can be carried by vehicle seats can already be mass-produced, which also lays the foundation for completing the adaptive adjustment of seat posture based on real-time body pressure sensing information.

[0065] In order to improve the comfort of the seat, the related technology proposes some methods. As an example, the existing seat adaptive adjustment method mostly obtains the human body features through the preset digital human body model or database, and adjusts the optimal posture in the digital human body model or database. For example, the related technology proposes a vehicle seat adjustment method of selecting human body feature key points and obtaining the optimal posture based on the digital human body model. For another example, the related technology also proposes a vehicle seat adjustment method of obtaining driver human body feature parameters and searching for the corresponding preset position in the preset database for adjustment. However, the digital human body model or the preset database cannot cover all body feature groups, and it is difficult to meet the comfort needs of people of different body types.

[0066] As another example, the related technology can also achieve seat adjustment by wearing corresponding modules by the passenger. For example, the related technology proposes an adjustment method of controlling the seat to wrap the passenger's body contour according to the seat bearing pressure information, which controls the seat to wrap the passenger's body contour and the position of the seat in the cabin by obtaining the passenger's eye movement information and the seat bearing pressure information. However, this method also requires the passenger to wear a three-dimensional motion capture module, which is cumbersome to operate.

[0067] It can be seen that the related technology has various problems in improving the comfort of the seat. Based on this, the present application provides a seat adjustment method, device, electronic equipment and storage medium to at least solve the problem that the related technology has poor accuracy in adjusting the comfort of the seat, and cannot meet the real-time needs of the passenger for comfort.

[0068] For ease of understanding, the seat adjustment method provided by the present application is specifically introduced below in combination with the drawings.

[0069] Figure 1 The schematic diagram of the seat adjustment system provided by the embodiment of the present application is shown in FIG. 1. As shown in the figure, the seat adjustment system includes an information acquisition module 110, a model processing module 120, an adjustment module 130, a vehicle end communication module 140 and a cloud module 150. Among them, the information acquisition module 110, the model processing module 120 and the adjustment module 130 are sequentially and communicatively connected, and the vehicle end communication module 140 is communicatively connected with the cloud module 150 and the model processing module 120. Figure 1 It should be noted that the connection relationship between the above different modules is only an example given by the embodiment of the present application, and different connection relationships can be designed based on different needs in actual implementation. For example, if the information acquisition module 110 has the ability to interact with the cloud, the cloud module 150 can also be directly communicatively connected with the information acquisition module 110, which is not limited by the embodiment of the present application.

[0070]

[0071] ​In some embodiments, the information acquisition module 110 is configured to acquire, in real time, pressure information of an occupant on a seat of a vehicle, and send the pressure information to the model processing module 120.

[0072] In some embodiments, the pressure information is used to reflect pressure distribution of the occupant on different positions of the seat. For example, the pressure information includes pressure distribution of different parts (e.g., shoulder, back, waist, hip, thigh, and calf) of the occupant on corresponding positions of the seat.

[0073] For example, Figure 2 The table shows the correspondence between different positions of the seat and body regions of the occupant. As shown, Figure 2 from top to bottom: headrest region, shoulder region, back region, waist region, waist side wing, hip region, seat cushion side wing, thigh region, and calf region.

[0074] In some embodiments, the pressure distribution of different parts on corresponding positions of the seat can be reflected based on a pressure distribution index and a specific value of the pressure distribution index. For example, the pressure distribution index includes at least one of the following: average pressure, contact area, peak pressure, pressure distribution index, maximum pressure gradient, and average pressure gradient.

[0075] It should be noted that the above-mentioned pressure distribution index is only some examples given by the present application, and different pressure distribution indexes can be selected based on actual needs in actual implementation, and the embodiments of the present application are not limited thereto.

[0076] In some embodiments, the information acquisition module 110 can also acquire seat adjustment parameters of the vehicle. For example, the information acquisition module 110 can acquire, in real time, the seat adjustment parameters through the built-in sensor of the seat. The seat adjustment parameters include at least one of the following: backrest angle, leg rest angle, and seat cushion angle.

[0077] It should be noted that the seat adjustment parameters are closely related to the pressure distribution of the occupant on different positions of the seat, and the above-mentioned seat adjustment parameters are only examples given by the present application, and different seat adjustment parameters can be selected based on actual needs in actual implementation, and the embodiments of the present application are not limited thereto.

[0078] In some embodiments, the information acquisition module 110 can also acquire data such as manual adjustment records of the user for the seat adjustment parameters, pressure information of the user after completing manual adjustment of the seat, and pressure distribution indexes, and send them to the model processing module 120. After receiving the above-mentioned data, the model processing module 120 will send them to the vehicle end communication module 140, and then the vehicle end communication module 140 will send the above-mentioned data to the cloud module 150.

[0079] The model processing module 120 is configured to receive the pressure information in a certain seat state acquired in real time by the information acquisition module 110, and input the pressure information into a pre-established comfort prediction model of pressure distribution to obtain a comfort score in the seat state.

[0080] In some embodiments, the model processing module 120 can input the real-time acquired pressure information into an optimal control target algorithm for maximizing the output result of the comfort prediction model, and based on the mapping relationship between the change trend of the pressure distribution and the seat adjustment parameters, continuously calculate the seat adjustment parameters with a higher comfort score, and stop calculating and adjusting the seat adjustment parameters such as the backrest angle, the leg rest angle, and the cushion angle when the comfort score is greater than or equal to a preset threshold.

[0081] In some embodiments, the model processing module 120 can receive the data such as the manual adjustment record of the user for the seat adjustment parameters, the pressure information after the user completes the manual adjustment of the seat, and the pressure distribution index collected locally by the vehicle end, and send the data to the vehicle end communication module 140, and then the vehicle end communication module 140 sends the data to the cloud module 150.

[0082] The adjustment module 130 is configured to control the seat adjustment device to adjust the backrest angle, the leg rest angle, and the cushion angle of the seat to the corresponding positions based on the seat adjustment parameters in a certain state and the seat adjustment parameters with a higher comfort score determined by the model processing module 120, until the comfort score is greater than or equal to a preset threshold.

[0083] The vehicle end communication module 140 is configured to communicate and exchange data with systems and modules inside or outside the vehicle.

[0084] In some embodiments, the vehicle end communication module 140 can receive the data such as the manual adjustment record of the user for the seat adjustment parameters, the pressure information after the user completes the manual adjustment of the seat, and the pressure distribution index collected locally by the vehicle end, which are sent by the model processing module 120, and forward the data to the cloud module 150.

[0085] The cloud module 150 is configured to receive the data such as the manual adjustment record of the user for the seat adjustment parameters, the pressure information after the user completes the manual adjustment of the seat, and the pressure distribution index collected and uploaded by the vehicle locally, which are sent by the vehicle end communication module 140, and based on the received data, update and optimize the comfort prediction model, and update the mapping relationship between the change trend of the pressure distribution and the seat adjustment parameters.

[0086] It should be noted that the above scenarios are used to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that, with the evolution of system architecture and the appearance of new business scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0087] The seat adjustment method provided by the embodiments of the present application is introduced below.

[0088] Figure 3 The flowchart of the seat adjustment method provided by the embodiments of the present application is shown in FIG. 1. As shown in FIG. 1, the method comprises steps S101-S103. Figure 3

[0089] S101, acquiring real-time pressure information.

[0090] The real-time pressure information is used to reflect the pressure distribution of the passenger on each position of the seat.

[0091] For example, the real-time pressure information includes the pressure distribution of different parts of the passenger, such as the shoulder, back, waist, hip, thigh and calf, on each position of the seat.

[0092] In some embodiments, the backrest, cushion and leg support part of the seat are configured with sensors (such as flexible printed electronic pressure sensors). When the passenger sits on the seat, the body contacts the backrest, cushion and leg support part of the seat and generates pressure. At this time, the pressure information of the passenger can be acquired in real time based on the above-mentioned sensors to determine the pressure distribution of the contact surface of the passenger on the seat.

[0093] In some embodiments, the pressure distribution of different parts on each position of the seat can be reflected based on the pressure distribution index and the specific value of the pressure distribution index. For example, the pressure distribution index includes at least one of the following: average pressure, peak pressure, contact area, pressure distribution index, maximum pressure gradient, average pressure gradient.

[0094] It should be noted that the above-mentioned pressure distribution index is only some examples given by the present application. In actual implementation, different pressure distribution indexes can be selected based on actual needs, and the embodiments of the present application do not limit this.

[0095] In some embodiments, the average pressure can be denoted as P v For example, the average pressure P v can be represented by the following formula (1):

[0096]

[0097] P i ​N represents the pressure value at the i-th pressure point on the contact surface between the occupant and the seat. P Let N be the number of pressure points on the seat, and let N be the number of pressure detection points on the seat. P ≤N.

[0098] In some embodiments, the peak pressure can be denoted as P. m It is used to indicate the maximum pressure across all pressure monitoring points. For example, the peak pressure P... m It can be expressed as the following formula (2):

[0099] P m =max(P1,P2,……,P) N ) Formula (2)

[0100] Among them, P i Let N be the pressure value at the i-th pressure point on the contact surface between the occupant and the seat, and N be the number of pressure detection points on the seat.

[0101] In some embodiments, the contact area refers to the area of ​​contact between the occupant and the seat, which can characterize the degree of overlap between the human body and the seat. The contact area can be described by a human sitting posture pressure distribution image, and the size of the contact area affects the contact pressure between the occupant and the seat.

[0102] In some embodiments, the pressure distribution index can be denoted as C. u It is used to reflect the ratio of the sum of the absolute values ​​of the pressure differences at symmetrical pressure detection points to the total pressure. For example, the pressure distribution index C... u It can be expressed as the following formula (3):

[0103]

[0104] Among them, P iL and P iR Let C be the pressure value of the i-th pair of symmetrical pressure detection points, ΔS be the area of ​​pressure sensing at a single pressure detection point, and N be the number of pressure detection points on the seat. Where 0 ≤ C u ≤1. In some embodiments, when C u When C = 0, the pressure distribution on the left and right is completely symmetrical. u When C = 1, the pressure is concentrated on one side. u The larger the pressure, the more asymmetrical the pressure distribution.

[0105] In some embodiments, the pressure gradient refers to the rate of change of pressure magnitude along a certain direction, reflecting the relationship between two adjacent pressure detection points. The maximum pressure gradient is the pressure gradient with the largest numerical value, and can be denoted as G. mThe maximum pressure gradient G m The average pressure gradient G

[0106] G m The average pressure gradient G N ) Formula (4)

[0107] The average pressure gradient G i is the numerical value of the pressure gradient at the i-th pressure point.

[0108] In some embodiments, the pressure gradient calculation is performed on the pressure points of the contact surface between the occupant and the seat, the pressure gradients of all the pressure points are obtained, and then the arithmetic mean of the pressure gradients of the individual pressure points is determined, which is the average pressure gradient. Exemplarily, the average pressure gradient can be denoted as G v The average pressure gradient G v can be represented by the following formula (5):

[0109]

[0110] It should be noted that the numerical calculation of the above pressure distribution indicators is only some examples given by the embodiments of the present application, and in specific implementation, different numerical calculation methods can be selected based on different actual designs, and the embodiments of the present application do not limit this.

[0111] S102, determining a comfort score based on the real-time pressure information.

[0112] In some embodiments, the comfort score is used to reflect the comfort degree of the occupant to the current seat state, that is, it can reflect the subjective comfort score of the occupant to the current seat state. As an example, the standard and rule of comfort evaluation can be predefined, the collected real-time pressure information is matched with the predefined comfort evaluation rule, and the comfort score is determined based on the quantitative scoring system according to the matching result. Exemplarily, a score can be assigned to each rule, if a certain measured value in the real-time pressure information is within the preset range of a certain rule, the corresponding score is given, and finally all the scores are added to determine the overall comfort score.

[0113] As another example, the determination of the comfort score based on the real-time pressure information can be specifically implemented as follows: the real-time pressure information is input into a trained comfort prediction model to obtain the comfort score. Exemplarily, after the real-time pressure information is collected, the collected data can be filtered and denoised to extract useful pressure data. Then, the processed pressure data is input into a pre-trained comfort prediction model to obtain the comfort score.

[0114] In some embodiments, the comfort level prediction model can be a model based on a machine learning algorithm (e.g., a neural network), which can predict the comfort level score based on real-time pressure information.

[0115] As a further example, the comfort level score can also be determined in response to a triggering operation of the user. For example, the comfort level score of the user can be determined in response to an input operation of the user on a display screen of the vehicle, or a voice operation of the user.

[0116] S103, in the case where the comfort level score is less than a preset threshold, adjusting the seat based on a mapping relationship between the seat adjustment parameter and the change trend of the pressure distribution.

[0117] The change trend of the pressure distribution affects the level of the comfort level score.

[0118] In some embodiments, the real-time pressure information of the shoulder, back, waist, hip, thigh and calf obtained by the orthogonal test can be input into the trained comfort level prediction model to obtain the comfort level score under different seat conditions. In combination with the subjective evaluation of the subject, a preset threshold of the comfort level score can be selected. For example, the preset threshold can be 85 points.

[0119] In some embodiments, the seat adjustment parameter includes at least one of the following: seat back angle, leg rest angle, cushion angle.

[0120] In some embodiments, the seat back angle, leg rest angle, cushion angle and other parameters can be obtained based on the sensors built in the seat. For example, the sensors can be Hall sensors.

[0121] In some embodiments, in the case where the comfort level score is less than the preset threshold, the change trend of the pressure distribution can be predicted in the case where the comfort level score is continuously improved, and then the adjustment trend of the seat adjustment parameter can be determined based on the mapping relationship between the seat adjustment parameter and the change trend of the pressure distribution, and the seat can be continuously adjusted to continuously improve the comfort level score.

[0122] It can be understood that, compared with the related art, the accuracy of the seat comfort adjustment is poor when only the human body characteristics of the occupant (such as the height and weight of the occupant) are considered during the seat adjustment, and the real-time demand of the occupant for comfort cannot be met. The method provided in the embodiments of the present application acquires the pressure distribution of the seat of the occupant based on the real-time pressure information, and determines the comfort score based on the real-time pressure information, so as to determine the satisfaction degree of the occupant for the comfort of the seat and the comfort state of the occupant in real time, and provide accurate data support for the seat adjustment. At the same time, the method provided in the present application adjusts the seat based on the mapping relationship between the change trend of the pressure distribution and the seat adjustment parameters when the comfort score does not meet the preset threshold, so as to timely respond to the change of the posture of the occupant, adapt to the real-time demand of the occupant, and realize the accuracy of the seat adjustment.

[0123] In addition, the comfort adjustment can be performed based on the real-time pressure information without relying on the human body characteristics such as height and weight, which have limitations, but can fully consider the individualized demand of the occupant with different body characteristics and body shapes for comfort, improve the accuracy of the seat adjustment, and further improve the use experience of the occupant.

[0124] In some embodiments, as shown in FIG. 10, the step S103 can be implemented as steps S1031-S1033. Figure 4

[0125] S1031, when the comfort score is less than the preset threshold, determining a target change trend of the pressure distribution.

[0126] The target change trend is used to improve the comfort score.

[0127] In some embodiments, when the comfort score is less than the preset threshold, the current pressure information can be analyzed to identify the key area (such as the area with too high or too low pressure on the seat) that causes the low comfort score, and then based on the identified result, the target change trend of the pressure distribution is determined. For example, the target change trend can be to reduce the pressure of a certain specific area or to increase the pressure of a certain specific area.

[0128] S1032, determining the adjustment trend of the seat adjustment parameter based on the target change trend and the mapping relationship between the seat adjustment parameter and the change trend of the pressure distribution.

[0129] ​In some embodiments, a mapping relationship between the seat adjustment parameters and the change trend of the pressure distribution can be established based on historical data and feedback of the occupant. Using the mapping relationship, a specific adjustment direction and angle of the seat adjustment parameters required to achieve the target change trend can be predicted, and based on the prediction result, an adjustment trend of the seat adjustment parameters can be determined. For example, the adjustment trend of the seat adjustment parameters can be to increase the waist support intensity or to increase the support angle of the leg rest, etc.

[0130] S1033, adjusting the seat based on the adjustment trend of the seat adjustment parameters.

[0131] In some embodiments, the seat can be adjusted based on the determined adjustment trend of the seat parameters, and after the adjustment, the pressure information of the occupant on the seat can be collected again, and then it is determined whether the comfort score is greater than or equal to the preset threshold based on the pressure information to verify the adjustment result. If the comfort score still does not reach the preset threshold, the seat can be continuously adjusted until the requirement is met or the maximum number of adjustments set by the system is reached.

[0132] It can be understood that, in the case where the comfort score is less than the preset threshold, the method provided by the present application can determine that the user's satisfaction with the comfort of the seat is low at this time, and at this time, the present application can determine the target change trend of the pressure distribution that can improve the comfort score, and determine the adjustment trend of the seat adjustment parameters based on the mapping relationship between the seat adjustment parameters and the change trend of the pressure distribution, which can provide a clear direction for the adjustment of the seat and ensure that the adjustment of the seat can effectively improve the comfort of the occupant.

[0133] In some embodiments, as shown in Figure 5 the above step S1031 can be implemented as step S201.

[0134] S201, determining, based on the trained comfort prediction model, a target change trend of the pressure distribution in the case where the comfort score is greater than or equal to the preset threshold.

[0135] The comfort prediction model is used to predict the comfort score of the occupant on the seat.

[0136] In some embodiments, the pressure distribution on the seat can be monitored in real time, and the trained comfort prediction model can be used to predict the current comfort score. If the predicted comfort score is less than the preset threshold, the system can identify the pressure distribution area that needs to be improved. When the predicted comfort score is greater than or equal to the preset threshold, the system will analyze the current predicted pressure distribution, and then determine the target change trend of the pressure distribution.

[0137] In some embodiments, as shown in Figure 6As shown, the above method further comprises steps S301-S302.

[0138] S301, acquire first historical pressure information in a first preset time period and seat adjustment parameters corresponding to the first historical pressure information.

[0139] Illustratively, the first preset time period can be the past week or the past 12 hours.

[0140] In some embodiments, the seat adjustment parameters of the backrest angle, the legrest angle, and the cushion angle, which are closely related to the occupant's posture and pressure distribution and can be directly adjusted by the seat, can be selected as the influencing factors. An orthogonal experiment of different influencing factor levels is designed to obtain the first historical pressure information in the first preset time period and the seat adjustment parameters corresponding to the first historical pressure information. Illustratively, the average pressure, contact area, and peak pressure of the occupant's shoulder, back, waist, hip, thigh, and calf in the horizontal position can be obtained, and the first historical pressure information such as the pressure distribution index, maximum pressure gradient, and average pressure gradient can be calculated, as well as the corresponding backrest angle, legrest angle, and cushion angle.

[0141] Illustratively, the seat of the vehicle can be placed on the horizontal ground, and the backrest angle, legrest angle, and cushion angle of the seat can be pre-adjusted according to the designed orthogonal experiment. The cushion and backrest pressure test mats are fixed on the seat cushion and backrest, and the data acquisition line, power supply, and notebook computer are connected. The software is started and debugged. The occupant sits down and waits for the pressure data to stabilize before starting the timing measurement. The occupant maintains the same posture and sits continuously for 8 minutes, during which the pressure test system starts to collect the first historical pressure information on the seat cushion and backrest. After the experiment, the average pressure, contact area, and peak pressure of the occupant's shoulder, back, waist, hip, thigh, and calf in the horizontal position can be exported, and the pressure distribution index, maximum pressure gradient, and average pressure gradient can be calculated.

[0142] S302, based on the first historical pressure information and the seat adjustment parameters corresponding to the first historical pressure information, a mapping relationship between the seat adjustment parameters and the change trend of the pressure distribution is established.

[0143] In some embodiments, based on the first historical pressure information and the seat adjustment parameters corresponding to the first historical pressure information, the mapping relationship between the seat adjustment parameters and the change trend of the pressure distribution can be established by numerical fitting.

[0144] It can be understood that the method provided in the application can facilitate subsequent determination of the adjustment trend of the seat based on the target change trend of the pressure distribution by acquiring historical pressure information and corresponding seat adjustment parameters and establishing a mapping relationship between the seat adjustment parameters and the change trend of the pressure distribution, so as to adjust the seat. In addition, the method provided in the application can optimize the adjustment of the seat based on historical data such as historical pressure information, thereby improving the accuracy and efficiency of the seat adjustment.

[0145] In some embodiments, the mapping relationship between the seat adjustment parameters and the change trend of the pressure distribution can be regarded as a mapping model. In order to optimize the mapping model, the pressure information of the occupant can be collected and stored, and the mapping relationship between the seat adjustment parameters and the change trend of the pressure distribution (i.e., the numerical change of the pressure distribution index) of different body types of people can be automatically updated and optimized by clustering algorithm, thereby optimizing the mapping model.

[0146] For example, the pressure information of the occupant can be grouped according to gender and human percentile, and the mapping model between the seat adjustment parameters and the change trend of the pressure distribution of the 95th percentile, the 50th percentile of male and the 95th percentile, the 50th percentile of female can be respectively established by nonlinear fitting.

[0147] It can be understood that, compared with the related art, which mostly adjusts by presetting a digital human model or database, obtaining human features, and searching for corresponding optimal posture in the digital human model or database for adjustment, although different body types of human features are clustered, the purpose is to better obtain the corresponding relationship between the human features and the optimal posture of the human body. In the method provided in the embodiments of the application, different body types of people are divided by clustering algorithm, and the purpose is to update and optimize the mapping relationship between the seat adjustment parameters and the change trend of the pressure distribution (i.e., the numerical change of the pressure distribution index) of different body types of people, thereby updating and optimizing the mapping relationship to meet the comfort needs of occupants of different body types and improve the accuracy and reliability of the mapping model.

[0148] In some embodiments, as shown in Figure 7 The above method further includes steps S401-S404.

[0149] S401, acquiring comfort measurement information.

[0150] The comfort measurement information includes: the area of local stimulation, the local comfort degree of each area of the human body to the local stimulation, and the overall comfort degree.

[0151] In some embodiments, before obtaining the comfort measurement information, personal information of the subject, such as height, weight, etc., can also be collected, and the subject can be explained the specific content and steps of the present obtaining of the comfort measurement information. In order to obtain the comfort measurement information, a comfort scale can be preset, and the filling rules and precautions of the comfort scale can be defined in advance. For example, Figure 8 The comfort scale is intended to measure the comfort. As shown in Figure 8 , the comfort scale includes: name, area of local stimulation, measurement date, local comfort degree of each area of the human body (shoulder, back, waist, hip, thigh, and calf) to the local stimulation, and overall comfort degree. The comfort degree can include five levels: very serious, serious, moderate, slight, and none, each of which corresponds to a different comfort score. The comfort score corresponding to "very serious" is 1, the comfort score corresponding to "serious" is 2, the comfort score corresponding to "moderate" is 3, the comfort score corresponding to "slight" is 4, and the comfort score corresponding to "none" is 5.

[0152] In some embodiments, as shown in Figure 8 , in order to more accurately grasp the comfort of the seat, the level of the overall comfort degree can be divided more finely. For example, 9 levels can be set from 1 to 5 with an interval of 0.5.

[0153] In some embodiments, for the parts of the human body that have a relatively high frequency of discomfort, the human body is divided into six areas: shoulder, back, waist, hip, thigh, and calf, and a thin steel plate is placed in each of the areas for easy differentiation and evaluation. For example, Figure 9 is a schematic diagram of the placement position of the thin steel plate. As shown in Figure 9 , a thin steel plate for the shoulder, a thin steel plate for the back, a thin steel plate for the waist, a thin steel plate for the hip, a thin steel plate for the thigh, and a thin steel plate for the calf are respectively placed between the six areas (shoulder, back, waist, hip, thigh, and calf) and the seat. For example, the size of the thin steel plate can be 250 mm in length, 150 mm in width, and 4 mm in thickness. After the thin steel plates are placed between each area of the human body and the seat, local stimulation can be performed on each area of the human body, so that there is a significant difference in comfort between a certain area of the subject's body (i.e., the area subjected to local stimulation) and other areas, thereby obtaining the comfort rule that cannot be reflected in the absence of stimulation.

[0154] In some embodiments, the seat angle and sitting posture of the subject can be adjusted to the most comfortable state, and the subject's back is close to the seat back, the subject's feet are supported by a slope pad with an inclination angle of 26 degrees, and local stimulation is performed on each region of the human body. After the subject continuously sits for 8 minutes, the subject can fill out a comfort scale to evaluate the discomfort of the whole body and each region of the human body, and obtain the local comfort degree of each region of the human body to the local stimulation and the overall comfort degree.

[0155] In some embodiments, after placing a thin steel plate between each region of the human body and the seat, the seat can be wrapped with a cloth skin to reduce the influence of factors such as the edge of the steel plate, the color and appearance design of the seat on the comfort score of the subject.

[0156] S402, determining the weight coefficient of each region of the human body based on the comfort measurement information.

[0157] The weight coefficient is used to reflect the influence degree of the local comfort degree of each region of the human body on the overall comfort degree.

[0158] In some embodiments, the corresponding relative human body region of the seat region is divided into six regions of shoulder, back, waist, hip, thigh and calf, and the influence law of the local comfort of the human body on the overall comfort of the human body is determined by the discomfort rating of the subject to different regions, and then the weight coefficient of each region of the human body is determined, that is, the influence degree of the local comfort degree of each region of the human body on the overall comfort degree. For example, the average relative score rate can be used as a comparison basis, and the analytic hierarchy process is used to study the influence degree or law of the local comfort degree of each region of the human body on the overall comfort degree, and the weight coefficient of the multiple local regions stimulated is identified.

[0159] It can be understood that the method provided by the present application quantifies the influence degree of the local comfort degree of each region of the human body on the overall comfort degree as a weight coefficient, which can provide a reference for the evaluation and improvement of seat comfort, and improve the accuracy of seat comfort adjustment.

[0160] S403, determining the target pressure distribution index of each region from the preselected pressure distribution index based on the weight coefficient.

[0161] In some embodiments, the preselected pressure distribution index includes at least one of the following: average pressure, peak pressure, contact area, pressure distribution index, maximum pressure gradient, average pressure gradient.

[0162] In some embodiments, based on the weight coefficient of each region of the human body, each region of the human body can be sorted to determine the number of target pressure distribution indexes of each region, and then the target pressure distribution index of each region is determined from the preselected pressure distribution index.

[0163] S404, constructing a comfort degree prediction model based on the target pressure distribution index of each region.

[0164] The comfort degree prediction model is used to predict a comfort degree score of the passenger on the seat.

[0165] In some embodiments, the selected target pressure distribution index of each region is taken as a parameter of the comfort degree prediction model, and according to the support vector machine algorithm theory, a comfort degree prediction model based on pressure information under multiple degrees of freedom can be established.

[0166] It can be understood that the method provided in the present application can accurately determine the key region affecting the overall comfort degree and the weight coefficient thereof by acquiring and analyzing comprehensive comfort degree measurement information (such as information of a region of local stimulation, a local comfort degree of each region of the human body to the local stimulation, and an overall comfort degree, etc.). By setting the weight coefficient to weight the comfort degrees of different regions, the physical sensitivity of different body parts of different passengers can be fully considered, so that the seat adjustment is no longer a generalization, but is targeted to optimize the seat setting.

[0167] In addition, the method provided in the present application determines a suitable target pressure distribution index for each region from the preselected pressure distribution index based on the weight coefficient, which can make the construction of the comfort degree prediction model more accurate, and make the comfort degree prediction model more accurately reflect the comfort feeling of the passenger.

[0168] In some embodiments, as shown in FIG. 5, the above step S403 can be implemented as steps S501-S503. Figure 10

[0169] S501, determining a correlation coefficient between each preselected pressure distribution index and the local comfort degree of each region.

[0170] ​In some embodiments, after the seat area is divided into six regions of shoulder, back, waist, hip, thigh and calf corresponding to the relative human body regions, the correlation coefficient between each pre-selected pressure distribution index and the local comfort degree of each region can be determined by local stimulation of different regions. For example, according to the setting of different stimulation working conditions, the subject can adjust the seat back angle, knee angle, angle between the torso and thigh, and the distance between the foot support pad and the seat to adjust to a comfortable sitting posture after sitting. Then, the seat cushion and backrest pressure test pads can be placed on the seat cushion and backrest of the seat respectively, and the data acquisition line, power supply and notebook computer and other equipment are connected, and the software is started and debugged. The subject sits again, and after the pressure information is stable, the timing measurement starts. For example, the subject can keep the posture unchanged and sit continuously for 8 minutes, and during this period, the pressure information on the seat cushion and backrest can be collected simultaneously. After the collection is completed, the specific values of the pre-selected pressure distribution indexes of each region can be exported. For example, the average pressure, maximum pressure and contact area of each region can be exported, and the maximum pressure gradient and average pressure gradient can be calculated.

[0171] In some embodiments, the correlation coefficient between each pre-selected pressure distribution index and the local comfort degree of each region can be statistically analyzed based on statistical product and service solutions (SPSS) software. For example, the correlation coefficient can be a Pearson correlation coefficient.

[0172] In some embodiments, the significance of the correlation coefficient can also be verified by a two-tailed test. For example, the significance level a = 0.05, and sig is the two-tailed test value under the given significance level. If sig < a, it is considered that the correlation between the two variables is significant.

[0173] S502, based on the weight coefficient, determine the number of target pressure distribution indexes of each region.

[0174] As an example, the number of target pressure distribution indexes of the region with a larger weight coefficient can be 2, and the number of target pressure distribution indexes of the region with a smaller weight coefficient can be 1. For example, the weight coefficient is greater than or equal to 0.6, which is considered to be a large weight coefficient. The weight coefficient is less than 0.6, which is considered to be a small weight coefficient.

[0175] As another example, based on the weight coefficient, all regions can be sorted in descending order of the weight coefficient. For the regions ranked in the top 30%, the number of target pressure distribution indexes can be 2, and for the regions ranked in the last 70%, the number of target pressure distribution indexes can be 1.

[0176] S503, determining the target pressure distribution index of each region from the preselected pressure distribution index based on the number of target pressure distribution indexes of each region and the correlation coefficient ranking of the preselected pressure distribution index of each region.

[0177] In some embodiments, the target pressure distribution index of each region is determined from the preselected pressure distribution index based on the number of target pressure distribution indexes of each region in the order of the absolute value of the correlation coefficient from high to low.

[0178] It can be understood that the correlation coefficient can determine the relationship between different pressure distribution indexes and comfort, so as to more accurately predict the influence of pressure distribution change on comfort. By combining the weight coefficient and the correlation coefficient, the appropriate target pressure distribution index of each region can be determined from the preselected pressure distribution index, so that the construction of the comfort prediction model is more accurate, and the comfort prediction model can determine which pressure distribution index has greater influence on comfort, so as to optimize the seat adjustment strategy to achieve the best comfort improvement.

[0179] In some embodiments, after the comfort prediction model is constructed, the comfort prediction model can be trained and optimized. For example, the manual adjustment record of the passenger to the seat can be collected and stored, and the seat adjustment parameter after the passenger completes the manual adjustment is taken as the pressure distribution in the most comfortable state of the passenger, so as to continuously update and optimize the comfort prediction model. For example, a plurality of groups of data of the passenger in a historical time period can be collected, the plurality of groups of data including pressure information and comfort scores under the pressure information. Then, the plurality of groups of data are filtered and randomly shuffled, and the processed plurality of groups of data are divided into two parts of training samples and test samples. The training samples are used to establish and train the comfort prediction model, and the test samples are used to test the comfort prediction model. For example, the training samples can be 75% of the total number of data, and the test samples can be 25% of the total number of data.

[0180] In some embodiments, since the pressure information and the comfort score belong to highly nonlinear data samples, the radial basis can be selected as the kernel function in the regression model, the value of the insensitivity loss parameter ε is set to 0.01, and the cuckoo search algorithm is applied to optimize the support vector machine penalty factor C and the kernel function width parameter σ 2 to establish and train the comfort prediction model with the obtained optimal parameters.

[0181] It can be understood that the method provided by the application can improve the accuracy and reliability of the model by training and optimizing the comfort prediction model, thereby improving the accuracy of seat adjustment and improving the riding experience of the occupant. In addition, in the method provided by the application, the comfort prediction model established based on the vector machine algorithm requires a small amount of data for training and testing, is easy to implement, and is not prone to overfitting problems.

[0182] It can be understood that the method provided by the application can improve the comfort of riding and simplify the operation of the occupant by arranging sensors (such as flexible printed electronic pressure sensors arranged on the seat) on the seat to obtain pressure information, inputting the pressure information into the comfort prediction model, and adjusting the seat adjustment parameters to meet the comfort needs of passengers of different sizes in order to improve the comfort score.

[0183] In some embodiments, the optimization of the comfort prediction model and the mapping relationship between the change trend of the pressure distribution and the seat adjustment parameters can be performed on a cloud server. The vehicle can collect the preference setting information of the user and upload it to the cloud server, and continuously update and optimize the comfort prediction model on the cloud server, and update and optimize the mapping relationship between the change trend of the pressure distribution and the seat adjustment parameters.

[0184] In some embodiments, the cloud server can also send the updated comfort prediction model and the updated mapping relationship between the change trend of the pressure distribution and the seat adjustment parameters to the communication device (such as a vehicle-side communication module) inside the vehicle, and the communication device inside the vehicle forwards the updated comfort prediction model and the updated mapping relationship between the change trend of the pressure distribution and the seat adjustment parameters to the model processing module (such as a seat controller) inside the vehicle.

[0185] It can be understood that the method provided by the application can effectively improve the accuracy of seat adjustment by optimizing and updating the mapping relationship between the comfort prediction model and the change trend of the pressure distribution and the seat adjustment parameters, and can provide the best comfort for occupants of different body types.

[0186] The above is an embodiment of the seat adjustment method provided by the application. In order to facilitate understanding, the above seat adjustment method will be further described in the form of examples. For example, as shown in Figure 11 The seat adjustment method includes the following steps:

[0187] Step Sa1, real-time acquisition of pressure information of the occupant's shoulder, back, waist, hip, thigh and calf parts on the target vehicle seat.

[0188] The pressure information is used to reflect the pressure distribution of different parts of the occupant on the target vehicle seat.

[0189] Step Sa2, controlling the seat adjusting device to adjust the backrest angle, leg rest angle and cushion angle of the target vehicle seat according to the real-time acquired pressure information.

[0190] The above mainly introduces the scheme provided by the embodiments of the present application from the perspective of method. In order to realize the above functions, the seat adjusting device comprises the hardware structure and / or software module for executing each function. Those skilled in the art should easily realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in the present application can be realized in the form of hardware or the combination of hardware and computer software. Whether a certain function is realized in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0191] The embodiments of the present application can divide the functional modules of the seat adjusting device according to the above method, for example, the seat adjusting device can comprise each functional module corresponding to each function, or two or more functions can be integrated in one processing module. The above integrated module can be realized in the form of hardware or software functional module. It should be noted that the division of modules in the embodiments of the present application is illustrative, and is only a logical function division. When actually implemented, there can be another division method.

[0192] Figure 12 The composition schematic diagram of the seat adjusting device provided by the embodiments of the present application is shown in the figure. Figure 12 As shown in the figure, the seat adjusting device 100 comprises an acquisition module 101, a determination module 102, an adjusting module 103 and a construction module 104.

[0193] The acquisition module 101 is configured to acquire real-time pressure information, and the real-time pressure information is used to reflect the pressure distribution of the occupant on each position of the seat.

[0194] The determination module 102 is configured to determine the comfort score based on the real-time pressure information.

[0195] The adjusting module 103 is configured to adjust the seat based on the mapping relationship between the seat adjusting parameter and the change trend of the pressure distribution in the case that the comfort score is less than the preset threshold. The change trend of the pressure distribution affects the high and low of the comfort score.

[0196] In a possible implementation, the determining module 102 is further configured to determine a target change trend of the pressure distribution when the comfort score is less than a preset threshold; the target change trend is used to improve the comfort score; determine an adjustment trend of the seat adjustment parameter based on the target change trend and a mapping relationship between the seat adjustment parameter and the change trend of the pressure distribution; and the adjusting module 103 is specifically configured to adjust the seat based on the adjustment trend of the seat adjustment parameter.

[0197] In a possible implementation, the determining module 102 is specifically configured to determine a target change trend of the pressure distribution when the comfort score is greater than or equal to a preset threshold based on the trained comfort prediction model; and the comfort prediction model is used to predict the comfort score of the occupant to the seat.

[0198] In a possible implementation, the obtaining module 101 is further configured to obtain first historical pressure information in a first preset time period and a seat adjustment parameter corresponding to the first historical pressure information; and the constructing module 104 is configured to establish a mapping relationship between the seat adjustment parameter and the change trend of the pressure distribution based on the first historical pressure information and the seat adjustment parameter corresponding to the first historical pressure information.

[0199] In a possible implementation, the obtaining module 101 is further configured to obtain comfort measurement information; the comfort measurement information includes: a region of local stimulation, a local comfort degree of each region of the human body to the local stimulation, and an overall comfort degree; the determining module 102 is further configured to determine a weight coefficient of each region of the human body based on the comfort measurement information; the weight coefficient is used to reflect an influence degree of the local comfort degree of each region of the human body on the overall comfort degree; determine a target pressure distribution index of each region from preselected pressure distribution indexes based on the weight coefficient; and the constructing module 104 is further configured to construct a comfort prediction model based on the target pressure distribution index of each region; and the comfort prediction model is used to predict the comfort score of the occupant to the seat.

[0200] In a possible implementation, the determining module 102 is specifically configured to determine a correlation coefficient between each preselected pressure distribution index and the local comfort degree of each region; determine a number of the target pressure distribution index of each region based on the weight coefficient; and determine the target pressure distribution index of each region from the preselected pressure distribution indexes based on the number of the target pressure distribution index of each region and a correlation coefficient ranking of the preselected pressure distribution index of each region.

[0201] In a possible implementation, the determining module 102 is specifically configured to input the real-time pressure information into the trained comfort prediction model to obtain the comfort score.

[0202] In an exemplary embodiment, the embodiments of the present application further provide an electronic device.Figure 13 This is a schematic diagram illustrating the composition of an electronic device provided in an embodiment of this application. For example... Figure 13 As shown, the electronic device 200 includes: a processor 201, a memory 202, an execution device 203, a communication device 204, and a sensor 205.

[0203] Processor 201 is used to execute instructions stored in memory 202 to implement the seat adjustment method provided in the above embodiments of this application. Processor 201 may be a CPU, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller (MCU) / single-chip microcomputer / microcontroller, a programmable logic device (PLD), or any combination thereof. Processor 201 may also be any other device with processing functions, such as a circuit, device, or software module, which is not limited in this embodiment.

[0204] In some embodiments, one or more instructions / programs are executed by one or more processors 201, causing one or more processors to implement the seat adjustment method provided in this application.

[0205] The memory 202 can be used to store instructions, software programs, or various data executable by the processor 201. The memory 202 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, application programs required by at least one functional module (such as a determination unit, processing unit, etc.), etc. Furthermore, the memory 202 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0206] The actuator 203 is used to adjust the posture of the seat.

[0207] The communication device 204 is used to realize communication transmission between the sensor 205, the processor 201, the memory 202, and the execution device 203. In some embodiments, the communication device 204 includes a communication interface and a communication bus.

[0208] Sensor 205 is used to collect occupant pressure information and seat adjustment parameters.

[0209] It should be noted that those skilled in the art will understand that Figure 13 The electronic device structure shown does not constitute a limitation on the electronic device; the electronic device may include, but is not limited to, other electronic devices.Figure 13 more or less components, or combinations of certain components, or different arrangements of the components. In an example embodiment, a computer-readable storage medium is also provided, including instructions, such as the memory 202 including software instructions, executable by the processor 201 of the electronic device to implement the method in the above embodiments.

[0210] In actual implementation, Figure 12 The functions of the acquisition module 101, the determination module 102, the adjustment module 103, and the construction module 104 in the above embodiment can be implemented by the processor 201 calling the computer program stored in the memory 202. The specific execution process can refer to the description of the method part in the above embodiment, and will not be repeated here. Figure 13 The processor 201 in the above embodiment can call the computer program stored in the memory 202 to implement. The specific execution process can refer to the description of the method part in the above embodiment, and will not be repeated here.

[0211] Optionally, the computer-readable storage medium can be a non-transitory computer-readable storage medium, for example, the non-transitory computer-readable storage medium can be a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0212] In some embodiments, the computer-readable storage medium includes an on-vehicle storage medium and a cloud storage medium. The on-vehicle storage medium stores a program and related data of vehicle seat adaptive adjustment, and the program of vehicle seat adaptive adjustment can implement the seat adjustment method provided by the present application when executed by the processor, which will not be repeated here.

[0213] The cloud storage medium stores data such as user seat manual adjustment parameter records and user pressure distribution indexes after completing seat manual adjustment uploaded by the on-vehicle storage medium through wireless communication, as well as an updated and optimized comfort prediction model and a mapping model, which can be downloaded to the on-vehicle storage medium through wireless communication.

[0214] In an example embodiment, the embodiments of the present application also provide a computer program product including one or more instructions executable by the processor 201 of the electronic device to complete the method in the above embodiments.

[0215] It should be noted that the instructions in the above computer-readable storage medium or one or more instructions in the computer program product are executed by the processor of the electronic device to implement each process of the above method embodiments, and can achieve the same technical effects as the above method. To avoid repetition, it will not be repeated here.

[0216] Through the description of the above embodiments, those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of functional modules is taken as an example, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete the full classification or part of the functions described above.

[0217] In several embodiments provided in the present application, it should be understood that the disclosed device and method can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of modules or units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed units can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0218] The units described as separate components can or can not be physically separated, and the components displayed as units can be one physical unit or multiple physical units, that is, can be located in one place or can be distributed to multiple different places. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0219] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0220] If the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical scheme of the embodiment of the present application essentially or the part that contributes to the prior art or the full classification or part of the technical scheme can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for making a device (which can be a single chip, a chip, etc.) or a processor execute all or part of the steps of the method of each embodiment of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a ROM, a RAM, a magnetic disk or an optical disk and various program code storage media.

[0221] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited to this. Any change or replacement within the technical scope disclosed by the present application should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for adjusting a seat, characterized in that, The method includes: Acquire real-time pressure information, which is used to reflect the pressure distribution of the occupant at various positions of the seat; Based on the real-time pressure information, a comfort score is determined; If the comfort score is less than a preset threshold, the seat is adjusted based on the mapping relationship between the seat adjustment parameters and the changing trend of the pressure distribution; the changing trend of the pressure distribution affects the level of the comfort score.

2. The method according to claim 1, characterized in that, When the comfort score is less than a preset threshold, the seat is adjusted based on the mapping relationship between the seat adjustment parameters and the changing trend of pressure distribution, including: If the comfort score is less than the preset threshold, a target trend for the change in the pressure distribution is determined; the target trend is used to improve the comfort score. Based on the target change trend and the mapping relationship between the seat adjustment parameters and the pressure distribution change trend, the adjustment trend of the seat adjustment parameters is determined; The seat is adjusted based on the adjustment trend of the seat adjustment parameters.

3. The method according to claim 2, characterized in that, Determining the target trend of change in the pressure distribution includes: Based on a trained comfort prediction model, the target change trend of the pressure distribution is determined when the comfort score is greater than or equal to the preset threshold; the comfort prediction model is used to predict the occupant's comfort score for the seat.

4. The method according to any one of claims 1-3, characterized in that, The method further includes: Obtain the first historical pressure information within a first preset time period and the seat adjustment parameters corresponding to the first historical pressure information; Based on the first historical pressure information and the corresponding seat adjustment parameters, a mapping relationship is established between the seat adjustment parameters and the changing trend of the pressure distribution.

5. The method according to claim 1, characterized in that, The method further includes: Acquire comfort measurement information; the comfort measurement information includes: the area of ​​local stimulation, the local comfort level of each area of ​​the human body to the local stimulation, and the overall comfort level; Based on the comfort measurement information, a weighting coefficient for each region of the human body is determined; the weighting coefficient is used to reflect the degree of influence of the local comfort level of each region of the human body on the overall comfort level. Based on the weighting coefficients, the target pressure distribution index for each region is determined from the pre-selected pressure distribution indices; Based on the target pressure distribution index of each of the regions, a comfort prediction model is constructed, which is used to predict the comfort score of the occupant for the seat.

6. The method according to claim 5, characterized in that, The step of determining the target pressure distribution index for each region from the pre-selected pressure distribution indices based on the weighting coefficients includes: Determine the correlation coefficient between each of the pre-selected pressure distribution indicators and the local comfort level of each of the regions; Based on the weighting coefficients, the number of target pressure distribution indicators for each region is determined; Based on the number of target pressure distribution indicators for each region and the correlation coefficient ranking of the pre-selected pressure distribution indicators for each region, the target pressure distribution indicator for each region is determined from the pre-selected pressure distribution indicators.

7. The method according to claim 5, characterized in that, The process of determining a comfort score based on the real-time pressure information includes: The real-time stress information is input into the trained comfort prediction model to obtain the comfort score.

8. A seat adjustment device, characterized in that, The device includes: The acquisition module is used to acquire real-time pressure information, which reflects the pressure distribution of the occupant at various positions of the seat. The determination module is used to determine a comfort score based on the real-time pressure information; The adjustment module is used to adjust the seat based on the mapping relationship between the seat adjustment parameters and the changing trend of the pressure distribution when the comfort score is less than a preset threshold; the changing trend of the pressure distribution affects the level of the comfort score.

9. The apparatus according to claim 8, characterized in that, The determining module is further configured to determine a target trend of change in the pressure distribution when the comfort score is less than the preset threshold; the target trend of change is used to improve the comfort score. Based on the target change trend and the mapping relationship between the seat adjustment parameters and the pressure distribution change trend, the adjustment trend of the seat adjustment parameters is determined; The adjustment module is specifically used to adjust the seat based on the adjustment trend of the seat adjustment parameters.

10. An electronic device, characterized in that, include: Memory and processor; The memory and the processor are coupled; The memory is used to store computer program code, which includes computer instructions; When the processor executes the computer instructions, the electronic device performs the method as described in any one of claims 1 to 7.

11. A vehicle, characterized in that, Including the electronic device as described in claim 10.

12. A computer-readable storage medium, characterized in that, When the computer-executable instructions stored in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is capable of performing the method as described in any one of claims 1 to 7.

Images