Self-adaptive adjusting method and system for posture-adjustable seat

Abstract

The invention discloses a self-adaptive adjustment method and system for a posture-adjustable seat, and relates to the technical field of smart home, and the method comprises the steps: receiving the posture number and ID information of a user through a user side, and retrieving a local use log through the information; and if the log data volume is insufficient, the system can match the user portrait according to the user ID and obtain the related networking log online by combining the seat model. Based on local and networking logs, the system calibrates the vertical position, the horizontal position and the inclination angle of the seat, and finally target adjustment parameters are obtained. And according to the target parameters, the system initializes an adjusting module, and self-adaptive adjustment of the seat posture is achieved. The technical problem that in the prior art, personalized adjustment of a posture self-adaptive control system is insufficient is solved, and the technical effect of carrying out personalized adjustment according to individual differences of users is achieved.

Description

Technical Field

[0001] The present application relates to the field of smart home technology, and in particular to an adaptive adjustment method and system for a posture-adjustable chair. Background Art

[0002] As people's demand for comfort and health increases, posture adjustment technology has been widely used in various seating fields. However, most existing posture adjustment technologies rely on fixed mode conversions and cannot be customized according to the individual differences of different users. This lack of personalized adjustment methods results in users being unable to obtain optimal comfort and health support when using seats. Especially among user groups with different body shapes, weights, and sitting habits, traditional adjustment technologies fail to fully meet the needs of each user, which in turn affects comfort and efficiency after long-term use. Therefore, how to provide more precise posture adjustment based on individual differences has become a key issue in the existing technology.

[0003] In the current related technologies, there is a technical problem of insufficient personalized adjustment of the attitude adaptive control system. Summary of the invention

[0004] The present application solves the technical problem of insufficient personalized adjustment of posture adaptive control systems in the prior art by providing an adaptive adjustment method and system for a posture adjustable seat.

[0005] The present application provides an adaptive adjustment method for a posture-adjustable seat, comprising:

[0006] Receive a user posture number and user ID information through the user end; retrieve the local usage log belonging to the user posture number based on the user ID information; when the data volume of the local usage log is less than or equal to the fitting data volume threshold, match the user portrait information according to the user ID information; retrieve the networked usage log belonging to the user posture number based on the user portrait information and the seat model; frequently calibrate the vertical position, horizontal position and inclination angle of the seat surface according to the networked usage log and the local usage log to obtain the target vertical position, horizontal position and inclination angle of the seat surface; initialize the seat vertical position adjustment module, the seat horizontal position adjustment module and the seat inclination angle adjustment module according to the target vertical position, the target horizontal position and the target inclination angle of the seat surface to adjust the seat posture.

[0007] The present application provides an adaptive adjustment system for a posture-adjustable seat, comprising:

[0008] A user information receiving module, the user information receiving module is used to receive a user posture number and user ID information through a user terminal; an information retrieval module, the information retrieval module is used to retrieve a local usage log belonging to the user posture number based on the user ID information; a user portrait information matching module, the user portrait information matching module is used to match the user portrait information according to the user ID information when the data volume of the local usage log is less than or equal to the fitting data volume threshold; an online usage log retrieval module, the online usage log retrieval module is used to retrieve the online usage log belonging to the user posture number according to the user portrait information and the seat model; a frequency calibration module, the frequency calibration module is used to perform frequency calibration on the vertical position, horizontal position and inclination angle of the seat surface according to the online usage log and the local usage log, and obtain the target vertical position, horizontal position and inclination angle of the seat surface; a seat posture adjustment module, the seat posture adjustment module is used to initialize the seat vertical position adjustment module, the seat horizontal position adjustment module and the seat inclination angle adjustment module to perform seat posture adjustment according to the target vertical position, the target horizontal position and the target inclination angle of the seat surface.

[0009] The adaptive adjustment method and system for posture-adjustable seats proposed in this application first receives the user's posture number and ID information through the user terminal, and uses the information to retrieve local usage logs. If the amount of log data is insufficient, the system will match the user portrait according to the user ID, and obtain related network logs online in combination with the seat model. Based on local and networked logs, the system calibrates the vertical position, horizontal position and tilt angle of the seat surface, and finally obtains the target adjustment parameters. According to the target parameters, the system initializes the adjustment module to realize adaptive adjustment of the seat posture, achieving the technical effect of personalized adjustment based on individual differences of users. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0011] Figure 1 A schematic flow chart of an adaptive adjustment method for a posture-adjustable seat provided in an embodiment of the present application;

[0012] Figure 2A schematic diagram of the structure of an adaptive adjustment system for a posture-adjustable seat provided in an embodiment of the present application.

[0013] Explanation of the accompanying drawings: user information receiving module 10, information retrieval module 20, user portrait information matching module 30, network usage log retrieval module 40, frequency calibration module 50, seat posture adjustment module 60. DETAILED DESCRIPTION

[0014] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0015] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0016] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0017] The present application embodiment provides an adaptive adjustment method for a posture-adjustable seat, such as Figure 1 As shown, the method includes:

[0018] Step S100, receiving the user posture number and user ID information through the user terminal. Specifically, the user inputs relevant information through the user terminal, including the user posture number and user ID information. The user posture number corresponds to a specific seat posture or adjustment mode, which helps to identify the posture to which the user wants the seat to be adjusted (such as sitting position, lying position, etc.). The user ID is a number that uniquely identifies the user's identity. The system tracks and manages the personalized needs of different users through this number. After the user enters the information on the interface, the system will transmit it to the central control system via a wireless or wired network for processing. The system customizes appropriate adjustment settings for each user based on information retrieval and matching related historical usage data or logs. The system can accurately provide users with personalized seat posture adjustment services based on their specific needs and historical data.

[0019] Step S200, based on the user ID information, retrieve the local usage log belonging to the user posture number. Specifically, based on the user ID information, the system first retrieves the usage log related to the user from the local data storage. Each user's ID will be matched with the log records in the local storage. The log contains various operation records of the user when using the seat in the past, such as the vertical position, horizontal position and tilt angle of the seat surface. The system uses the user ID to accurately find the corresponding record to ensure that the extracted log data can reflect the user's personalized usage preferences. Subsequently, the system will load the valid local usage log and analyze the user's adjustment habits based on historical data, such as the frequency of preferred angle or height adjustment, to further provide a basis for subsequent adjustment decisions. It ensures that the system can provide accurate personalized adjustment solutions based on the unique needs of each user.

[0020] In a possible implementation, the local use log belonging to the user posture number is retrieved based on the user ID information, and step S200 further includes step S210, when the data volume of the local use log is greater than the fitting data volume threshold, the vertical position of the seat surface, the horizontal position of the seat surface and the tilt angle of the seat surface are frequently calibrated according to the local use log to obtain the target vertical position of the seat surface, the target horizontal position of the seat surface and the target tilt angle of the seat surface. Specifically, when the data volume of the local use log exceeds the set fitting data volume threshold, the system will frequently calibrate the vertical position of the seat surface, the horizontal position of the seat surface and the tilt angle of the seat surface. In this process, the system first analyzes the local use log to identify the frequent adjustment of the chair adjustment parameters by the user in different time periods. The adjustment data will be counted according to the frequency of occurrence, the amplitude of adjustment and the duration to determine the adjustment range preferred by the user. Then, based on the analysis results, the system will calculate the target values ​​of the vertical position of the seat surface, the horizontal position of the seat surface and the tilt angle of the seat surface to ensure that the parameters can more accurately reflect the user's usage habits and needs. For example, if the user frequently adjusts the chair surface tilt angle to 20 degrees, the system will set it as the target value and give priority to analyzing this angle in subsequent adjustments. Finally, the system fine-tunes the chair through the adjustment module based on the target chair surface parameters obtained to ensure that the user's comfort is maximized every time they use it.

[0021] Step S300, when the data volume of the local usage log is less than or equal to the fitting data volume threshold, the user portrait information is matched according to the user ID information. Specifically, when the data volume of the local usage log is less than or equal to the fitting data volume threshold, the system cannot rely on the local log data for effective posture adjustment. At this time, the system will use the user ID information to match the user portrait data to make up for the problem of insufficient data volume. Specifically, the system retrieves the portrait data related to the user through the user ID. The user portrait usually contains the user's basic information (such as age, height, weight), historical usage habits, health status, etc. Through this information, the system can establish a personalized user demand model. Even if the local usage log is insufficient, the seat position can still be adjusted according to the user's characteristics. For example, if the user has a special type of functional impairment, the system can adjust the seat angle to adapt to his physical needs. In this way, the system can ensure that the user is provided with appropriate posture adjustment by matching and using user portrait information in the absence of sufficient log data.

[0022] Step S400, based on the user portrait information and the seat model, the networked usage log belonging to the user posture number is retrieved online. Specifically, based on the user portrait information (such as age, height, weight, type of functional impairment, etc.) and the seat model, the system obtains the usage log related to the user posture number through online retrieval. First, the system uses the user's personalized information to filter out historical usage data that matches the user's needs. For example, if the user's functional impairment type involves lower limb movement difficulties, the system will obtain adjustment experience by retrieving seat adjustment data containing users with similar needs. In addition, the seat model is a key retrieval parameter because different models of seats have different adjustment ranges and configurations. In the above manner, the system can obtain the adjustment history data under a specific seat model and combine it with the user's specific posture number to find the most relevant usage log. The networked log provides data support for the adjustment system, helping to accurately adjust the seat to meet the personalized needs of different users, and further optimize the seat adjustment process to improve comfort and adaptability.

[0023] In a possible implementation, the networked use log belonging to the user posture number is retrieved online according to the user portrait information and the seat model, and step S400 further includes step S410, wherein the user portrait information includes age, height, weight, type of functional impairment and leg length. Specifically, the user portrait information includes age, height, weight, type of functional impairment and leg length. Age data helps the system identify the user's health status and needs, such as elderly users may need more support to reduce the burden on the spine and joints, while young users may prefer more flexible adjustments. Height determines the user's needs for cushions and backrests. Taller users need greater support, while shorter users need a more closely fitting design. Weight data helps the system determine the structural strength and support of the seat. Heavier users need more stable seats, while lighter users may need more flexible adjustments. Functional impairment type data guides the focus of seat adjustment. For example, users with lower limb dysfunction need specially designed lifting or support functions to make it more convenient to use the seat, and users with spinal dysfunction need a higher backrest to support the waist. Leg length information helps the system adjust the seat depth and height. Users with longer legs need deeper cushions and appropriate seat height to ensure knee and waist comfort. The comprehensive use of data enables the seat to provide customized adjustment solutions for different users, thereby improving comfort and user experience.

[0024] Step S420, constructing classification constraints according to the dysfunction type and the seat model. Specifically, according to the user's dysfunction type and seat model, the process of constructing classification constraints includes two important aspects: first, classifying users according to their dysfunction type, and different types of dysfunction require different seat designs and functions. For example, users with lower limb dysfunction require the seat to provide a large height adjustment range to help users easily switch from sitting to standing; users with spinal dysfunction require the seat to provide good back support, especially in the lumbar area, to support the natural curve of the spine; users with upper limb dysfunction have special requirements for the height, width and adjustment angle of the seat armrests; users with comprehensive dysfunction require a comprehensive seat design that can provide multi-directional adjustment to support multiple needs. Secondly, the choice of seat model is also crucial, because different models of seats have differences in function, support and adjustment range. According to the design characteristics of the seat, such as adjustment range, support, comfort and material, quantitative constraints can be constructed. For example, the lifting range of the seat should be suitable for users with lower limb dysfunction, and back support is an important factor for users with spinal dysfunction when choosing a seat. By combining constraints, the system is able to select the most suitable seat model based on the user's obstacle type and the characteristics of the seat model.

[0025] Step S430, constructing a quantitative constraint based on the age, height, weight and leg length. Specifically, based on the user's age, height, weight and leg length information, a quantitative constraint can be constructed for the design of the seat to ensure that the seat meets the personalized needs of different users. First, age affects the functional requirements of the seat. For example, elderly users may require a seat with a higher adjustment range and soft support to facilitate sitting and standing, while young users may prefer a seat with higher flexibility. Height directly affects the height and back support position of the seat. Users with taller heights require a larger seat lifting range, while users with shorter heights require a lower seat height and appropriate back support. Weight is an important factor affecting the load-bearing capacity and comfort of the seat. Users with heavier weight require a seat with a stronger load-bearing capacity and a more solid support system, while users with lighter weight may require a softer seat support. Leg length affects the seat cushion depth and armrest height of the seat. Users with longer legs require a deeper seat cushion and a suitable armrest height, while users with shorter legs require a shorter seat cushion and a lower armrest. Through comprehensive quantitative constraints, customized seat adjustment solutions can be provided for each user to improve the comfort and functionality of the seat.

[0026] Step S440, according to the classification constraint and the quantitative constraint, the networked use log belonging to the user posture number is retrieved in combination with the seat model. Specifically, the system first determines the user's needs and seat configuration according to the user's classification constraints (such as the matching of the dysfunction type and the seat model) and quantitative constraints (such as the numerical range of the user's physiological data such as age, height, weight and leg length). Constraints help the system ensure that appropriate seat settings are recommended based on individual needs and physical characteristics. Then, the system retrieves the networked use log corresponding to the user posture number through the network in combination with the constraint conditions. The log contains historical data of the user's past use of the seat, such as seat adjustment position, adjustment frequency and user comfort feedback. By obtaining networked data, the system can provide users with accurate seat adjustment solutions based on historical data. Through the above process, the system can better understand the user's personalized needs, and then adjust the parameters such as the vertical position, horizontal position and tilt angle of the seat to maximize the user's comfort and use experience.

[0027] In a possible implementation, according to the classification constraint and the quantification constraint, the networked use log belonging to the user posture number is retrieved in combination with the seat model, and step S440 further includes step S441, when at least one condition that the retrieved user's functional impairment type is different from the functional impairment type and the retrieved user's seat model is different from the seat model is triggered, it is deemed that the retrieved user does not meet the classification constraint. Specifically, when the user's functional impairment type retrieved by the system is different from the preset functional impairment type, or the user's seat model is inconsistent with the seat model recommended by the system, the system will consider that the user does not meet the classification constraint. For example, if the seat is designed for a user with a physical disability, but the user's functional impairment is a visual impairment, the system will determine that the two do not match; similarly, if the system recommends an electric adjustment seat, and the user uses a manual seat, the system will also determine that the two do not match. At this time, the system will trigger the mismatch condition, consider that the user does not meet the classification constraint, and then stop the condition-based seat adjustment or personalized configuration. In this way, the system ensures that the user's seat adjustment process not only accurately matches the individual's functional needs, but also avoids inappropriate seat settings, ensuring the user's comfort and safety.

[0028] Step S442, constructing age deviation threshold, height deviation threshold, weight deviation threshold and leg length deviation threshold. Specifically, the system constructs deviation thresholds for age, height, weight and leg length according to the specific physical parameters of the user, so as to evaluate the adaptability of the user's physical characteristics to the seat design. Specifically, the age deviation threshold is set as the tolerance error between the actual age of the user and the recommended age, for example, allowing the user's age to be within the range of ±5 years of the recommended age; the height deviation threshold is used to ensure that the seat is adapted to users of different heights, usually set to ±3 cm, so that users with heights within the specified range can use the seat comfortably; the weight deviation threshold ensures that the seat can withstand users of different weights, set to ±5 kg, for example, it is adapted to users whose weight is roughly within the recommended range of ±5 kg; and the leg length deviation threshold helps ensure that the seat depth and support position can provide comfortable support for users with different leg lengths, usually set to ±2 cm, to ensure that most users can get the best experience within the leg length adaptation range. Through the setting of the deviation threshold, the system can accurately provide personalized seat adjustment for each user, maximizing the comfort and safety of the seat.

[0029] Step S443: When the age deviation of the retrieved user and the age is less than or equal to the age deviation threshold, and the height deviation of the retrieved user and the height is less than or equal to the height deviation threshold, and the weight deviation of the retrieved user and the weight is less than or equal to the weight deviation threshold, and the leg length deviation of the retrieved user and the leg length is less than or equal to the leg length deviation threshold, it is considered that the quantitative constraint is met. Specifically, the system compares the user's age, height, weight and leg length with the preset standard values ​​to ensure that the body parameters are within a reasonable range, thereby determining whether the quantitative constraint is met. The specific process is as follows: First, the system compares the user's age with the standard age recommended by the seat. If the difference between the user's age and the standard age is less than or equal to the preset age deviation threshold (such as ±5 years), it is considered to meet the standard; then, the system compares the user's height with the standard height for seat adaptation. If the difference between the two is less than or equal to the preset height deviation threshold (such as ±3 cm), the height is considered to meet the requirements; similarly, the system will compare the user's weight with the standard weight range. If the weight difference does not exceed the preset weight deviation threshold (such as ±5 kg), the weight is considered to meet the requirements; finally, the system will also compare the user's leg length with the standard leg length. If the leg length difference is less than or equal to the set leg length deviation threshold (such as ±2 cm), the leg length is considered to be adapted. Only when the differences in age, height, weight and leg length are within the specified threshold range, the system will consider that the user meets the quantitative constraints, and then provide personalized seat posture adjustment for them to ensure the best comfort and adaptability.

[0030] Step S444, otherwise, it is deemed that the quantitative constraint is not satisfied. Specifically, when the difference between the retrieved user's age, height, weight or leg length and the preset standard exceeds the corresponding deviation threshold, the system will automatically determine that the user does not meet the quantitative constraint. Specifically, if the difference between the user's age and the standard age is greater than the set age deviation threshold (such as ±5 years old), the height difference exceeds the set height deviation threshold (such as ±3 cm), the weight difference exceeds the set weight deviation threshold (such as ±5 kg), or the leg length difference exceeds the set leg length deviation threshold (such as ±2 cm), it will be deemed that the quantitative constraint is not satisfied. Only when all parameters meet the set deviation range, the user is considered to meet the quantitative constraint and can provide a personalized seat posture adjustment solution. If any parameter exceeds the deviation range, the system determines that the user does not meet the conditions and cannot provide optimized seat adjustment settings for him.

[0031] Step S500, frequently calibrate the vertical position, horizontal position and tilt angle of the seat surface according to the networked use log and the local use log, and obtain the target vertical position, horizontal position and tilt angle of the seat surface. Specifically, the system performs frequent calibration on the data in the networked use log and the local use log, and comprehensively analyzes the user's past seat usage records, especially the changes in the vertical position, horizontal position and tilt angle of the seat surface. The frequent calibration process includes identifying the seat surface position and angle that the user adjusts most frequently, and counting the frequency and duration of each adjustment state. Through this analysis, the system determines the seat adjustment mode that the user uses most frequently, thereby generating the target vertical position, horizontal position and tilt angle of the seat surface. Finally, the system uses the target data to automatically adjust various parts of the seat to ensure that it meets the user's comfort and usage habits. For example, if the analysis data shows that the user frequently selects a specific tilt angle and height, the system will optimize the seat surface settings based on these data to improve the user experience.

[0032] In a possible implementation, the vertical position, horizontal position and tilt angle of the seat surface are frequently calibrated according to the networked use log and the local use log to obtain the target vertical position, horizontal position and tilt angle of the seat surface, and step S500 further includes step S510, normalizing and mapping the constraint interval of the vertical position of the seat surface to construct a first coordinate axis. Specifically, the normalized mapping of the vertical position of the seat surface is achieved by converting the actual vertical position range (such as 30 cm to 50 cm) of the seat surface adjustment into a standardized interval between 0 and 1. First, by determining the minimum and maximum values ​​of the vertical position of the seat surface (for example, 30 cm is the minimum value and 50 cm is the maximum value), and then using a normalization formula to convert the actual vertical position into a standardized value, the formula is: normalized value = (actual value - minimum value) / (maximum value - minimum value). The actual vertical position of the seat surface is converted into a value between 0 and 1, indicating the degree of adjustment of the vertical position. Next, the standardized values ​​are used to construct the first coordinate axis, which defines the adjustment range of the vertical position of the seat surface and allows the height of the seat surface to be accurately adjusted within this range. In this way, the adjustment of the vertical position of the seat surface becomes more precise and flexible, and can work in conjunction with other adjustment modules (such as the horizontal position of the seat surface, the tilt angle of the seat surface, etc.) to ensure that the overall adjustment of the seat achieves optimal comfort and functionality.

[0033] Step S520, normalize and map the constraint interval of the horizontal position of the seat surface to construct the second coordinate axis. Specifically, in this scheme, the normalization mapping process of the horizontal position of the seat surface is to convert the actual adjustment range of the horizontal position of the seat surface into a standardized numerical interval (for example, 0 to 1). Specifically, first determine the minimum and maximum values ​​of the horizontal position of the seat surface, such as the adjustment range from 0 cm to 40 cm. Then, use the normalization formula to convert the actual position into a standard value: normalized value = (actual value-minimum value) / (maximum value-minimum value). For example, if the actual value of the horizontal position of the seat surface is 20 cm, the normalized value is 0.5, which means it is in the middle of the entire adjustment range. In this way, the value of the horizontal position of the seat surface is converted into a standardized value, which can be compatible with the data of other adjustment modules. This normalization method enables the horizontal position of the seat surface to be adjusted in a unified standardized space, and works in conjunction with the adjustment modules of the vertical position and tilt angle of the seat surface, thereby ensuring the adjustment accuracy and system consistency. In addition, the standardized data facilitates subsequent control and optimization, ensuring that every adjustment of the seat meets user needs and achieves a more personalized and precise adjustment experience.

[0034] Step S530, normalize and map the constraint interval of the seat surface inclination angle to construct a third coordinate axis. Specifically, it is necessary to first determine the adjustment range of the seat surface inclination angle, for example, from 0 degrees (the backrest is parallel to the seat surface) to 45 degrees (the maximum inclination angle of the backrest). Then, through normalization processing, the actual seat surface inclination angle value is converted into a standardized value. Next, this standardized value is mapped to a new coordinate axis to construct a third coordinate axis, which is used to represent the adjustment range of the seat surface inclination angle, so that the system can accurately adjust the inclination angle through this coordinate axis. Through this normalized method, the adjustment of the seat surface inclination angle can be compatible with the adjustment modules of the vertical position and horizontal position of the seat surface, ensuring the data consistency of each adjustment module and improving the adjustment accuracy of the overall system. Finally, through this process, the system can be optimized and adjusted according to the standardized seat surface inclination angle value to meet the personalized needs of users.

[0035] Step S540, constructing a control constraint space according to the first coordinate axis, the second coordinate axis and the third coordinate axis. Specifically, the process of constructing the control constraint space is to convert the adjustment range of the vertical position of the seat surface, the horizontal position of the seat surface and the tilt angle of the seat surface into a three-dimensional coordinate system. First, the actual value of each adjustment parameter (vertical position of the seat surface, horizontal position of the seat surface, tilt angle of the seat surface) is normalized and mapped to a numerical range of 0 to 1. The normalized values ​​constitute three coordinate axes respectively: the first coordinate axis represents the vertical position of the seat surface, the second coordinate axis represents the horizontal position of the seat surface, and the third coordinate axis represents the tilt angle of the seat surface. Then, by combining the three coordinate axes, a three-dimensional control constraint space is formed, in which each point represents a set of specific adjustment parameters (such as a specific combination of vertical position, horizontal position and tilt angle). On this basis, the system maps historical control data (from online and local use logs) into the control constraint space to form a set of historical control particles, each of which represents an adjustment operation. Finally, the system frequently calibrates the historical control particles to find the target adjustment parameters that meet the user's needs, thereby optimizing the seat adjustment method and achieving personalized and precise posture adjustment. This process can provide the best seat adjustment solution according to the needs of different users.

[0036] Step S550, distribute the network usage log and the local usage log in the control constraint space to obtain a historical control particle set. Specifically, to distribute the network usage log and the local usage log in the control constraint space, it is necessary to first collect and organize the user's historical data. The log data records the user's adjustment of various seat adjustment parameters (such as the vertical position, horizontal position, and tilt angle of the seat surface) and user feedback. Next, the log data is normalized to map the values ​​of each adjustment parameter to a standardized range of 0 to 1 for unified analysis. Then, through the normalized data, each log record is mapped to a three-dimensional control constraint space to form a historical control particle set. Each particle represents an operation of a user under specific adjustment conditions, and each particle in the control constraint space is distributed according to the data points adjusted by the user. Thereafter, the system performs frequency calibration on the particles to analyze which adjustment operations are most common and which are occasionally used, so as to identify the user's main adjustment needs. Finally, based on the historical control particle set, the system can calculate and determine the target seat surface vertical position, horizontal position, and tilt angle according to the frequent adjustment mode, and provide a personalized seat adjustment solution for the user. Through this method, the system can accurately identify and optimize the user's seat adjustment needs, thereby improving the comfort and adjustment accuracy of the seat.

[0037] Step S560, frequency calibration is performed on the historical control particle set to obtain the target seat surface vertical position, target seat surface horizontal position and target seat surface inclination angle. Specifically, a historical control particle set is formed by mapping the networked usage log and the local usage log to the control constraint space. Each particle represents a seat adjustment operation, including parameters such as the seat surface vertical position, horizontal position and inclination angle. The system performs a frequency analysis on the particles, identifies commonly used adjustment settings, and assigns higher weights to particles that appear frequently. Through weighted frequency calibration, the system can identify the seat position and angle that users adjust most frequently, thereby calculating the target seat surface vertical position, horizontal position and inclination angle. Finally, based on the calibrated target value, the seat adjustment module will automatically adjust the seat posture to achieve personalized adaptive adjustment. This enables the system to intelligently optimize the seat adjustment according to the user's historical adjustment behavior, and provide a comfortable and demand-compliant seat posture adjustment solution.

[0038] In a possible implementation, the historical control particle set is frequently calibrated to obtain the target seat surface vertical position, target seat surface horizontal position and target seat surface tilt angle. Step S560 further includes step S561, and the historical control particle set includes a networked historical control particle set and a local historical control particle set. Specifically, the historical control particle set includes a networked historical control particle set and a local historical control particle set. The networked historical control particle set contains seat adjustment data obtained through the networked system, and the data usually reflects the control information shared between multiple devices or users, such as the vertical and horizontal positions and tilt angles of the seat. In this set, the particle data involves information such as user portraits and environmental factors, so it can provide a reference for a wide range of user needs and behavior patterns. The local historical control particle set records the adjustment history of a specific user on a local device, and the data provides more accurate adjustment information because it is based on the user's usage in a specific device and environment. Local records reflect the user's preferences in a familiar environment and can provide a more targeted basis for personalized adjustment. By combining the networked historical control particle set and the local historical control particle set, the user's seat adjustment needs can be fully understood, thereby achieving smarter and more personalized seat adjustment control.

[0039] Step S562, performing frequent particle analysis on the networked historical control particle set to obtain networked control frequent particles, wherein the networked control frequent particles have a first weight. Specifically, when processing the networked historical control particle set, firstly, frequent particle analysis is performed on each particle in the set to identify particles that frequently appear in multiple usage data. Frequent particles play a key role in seat adjustment, representing the common operation mode of users when using seats or the adjustment requirements that have a great impact on seat comfort. Each frequent particle is assigned a weight, called the first weight, which is determined based on the frequency of occurrence of the particle in the historical data and the degree of its influence on the seat adjustment effect. The higher the weight, the greater the contribution of the particle to the adjustment effect. Through this analysis, the adjustment factors that really affect the user experience can be highlighted, thereby optimizing the adaptive adjustment strategy of the seat and ensuring that the adjustment system can make accurate adjustment responses according to the usage habits of different users.

[0040] Step S563, performing frequent particle analysis on the local historical control particle set to obtain local control frequent particles, wherein the local control frequent particles have a second weight. Specifically, in the local historical control particle set, firstly, the particles that appear repeatedly in multiple usage records are identified through frequent particle analysis, and the particles represent the user's common seat posture adjustment needs. Then, a "second weight" is assigned to each identified frequent particle, and the weight value reflects the importance of the particle in the adjustment process. Particles with higher weights indicate that they are the most common and most needed adjustment settings for users, and have a greater impact on seat adjustment, while particles with lower weights indicate that they play a smaller role in seat adjustment. Frequent particles with weights will be used in the seat's adaptive adjustment system to optimize the user experience, ensuring that the system prioritizes and responds to those posture needs that are most important to the user, thereby improving the accuracy and personalization of the adjustment.

[0041] Step S564, according to the first weight and the second weight, the network control frequent particles and the local control frequent particles are weighted mean fused to obtain the target seat surface vertical position, the target seat surface horizontal position and the target seat surface inclination angle. Specifically, the system first performs frequent particle analysis on the network history control particles and the local history control particles to obtain network control frequent particles and local control frequent particles, and assigns the first weight and the second weight to them respectively. The first weight represents the importance of network data, and the second weight represents the importance of local data. Then, the system calculates their weighted mean according to the weights of the two particles, multiplies the adjustment parameters of each particle by the corresponding weight through the formula, and then obtains the weighted average value. This weighted mean reflects the comprehensive impact of network and local data on the adjustment parameters, ensuring that the results meet the personalized needs of users more accurately. Finally, through the data after weighted mean fusion, the system generates the target seat surface vertical position, target seat surface horizontal position and target seat surface inclination angle, and then automatically adjusts the seat through the seat surface adjustment module according to these target values ​​to ensure that the seat posture accurately meets the user's comfort requirements.

[0042] In a possible implementation, frequent particle analysis is performed on the networked historical control particle set to obtain networked control frequent particles, wherein the networked control frequent particles have a first weight, and step S562 further includes step S5621, obtaining the first particle distribution coordinates of the networked historical control particle set. Specifically, the system performs frequent particle analysis on the networked historical control particles and the local historical control particles to obtain networked control frequent particles and local control frequent particles, and assigns a first weight and a second weight to them respectively. The first weight represents the importance of the networked data, and the second weight represents the importance of the local data. Then, the system calculates the weighted mean of the two particles according to their weights, multiplies the adjustment parameters of each particle by the corresponding weight through a formula, and then obtains the weighted average value. The weighted mean reflects the comprehensive influence of the networked and local data on the adjustment parameters, ensuring that the results more accurately meet the personalized needs of users. Finally, through the data fused by the weighted mean, the system generates the target seat surface vertical position, the target seat surface horizontal position and the target seat surface inclination angle, and then automatically adjusts the seat through the seat surface adjustment module according to the target value to ensure that the seat posture accurately meets the user's comfort requirements.

[0043] Step S5622, based on the first particle distribution coordinates from near to far, k neighboring coordinates are sorted from the networked historical control particle set, where 0.5*the total number of networked historical control particle sets ≥ k ≥ 0.3*the total number of networked historical control particle sets. Specifically, after obtaining the first particle distribution coordinates of the networked historical control particle set, the system selects the k particles closest to the first particle by calculating the spatial distance between the first particle and other particles in the set. Specifically, the system first calculates the coordinate difference between each particle and the first particle, and sorts them according to the size of the difference. Then, the k particles with the smallest distance from the first particle are selected from the sorting results. The value of this k is determined by 30% to 50% of the total number of networked historical control particle sets, which ensures that the number of selected particles is neither too small to affect the accuracy of the data nor too large to increase the calculation burden. Through this screening method based on spatial distance sorting, the system can select the particles with the highest similarity to the target particles, providing a basis for subsequent frequent particle analysis.

[0044] Step S5623, calculate the inverse of the mean value of the distribution distance between the first particle distribution coordinate and the k neighboring coordinates, set it as the first particle frequency, and add it to the frequency set. Specifically, first, by calculating the distance between the first particle distribution coordinate and the selected k neighboring coordinates, the Euclidean distance or other measurement methods are usually used to measure the similarity between the first particle and each neighboring particle. Then, these distance values ​​are summed and their mean is calculated to obtain the average distribution distance between the first particle and the neighboring particles. In order to highlight the contribution of particles with a closer distance to the system, the inverse of the mean is then calculated. The inverse value (i.e., frequency) reflects the relative proximity of the particle to the first particle, and particles with a smaller distance will have a higher frequency. Finally, the frequency value of each particle is added to the frequency set to facilitate subsequent data processing and decision-making. In this way, particles that are closer to the target particle and have a higher frequency of occurrence in a specific particle distribution can be identified, providing important input for subsequent control strategies.

[0045] Step S5624, according to the frequency set, extract the maximum frequency value of the particles in the networked historical control particle set, and set it as the networked control frequent particle. Specifically, first, by calculating the frequency of the particles, a frequency set is obtained, in which the frequency of each particle reflects its similarity with the target particle. Next, the value with the largest frequency is extracted from the set, representing the particle that is closest to the target particle and has the greatest influence. The particle corresponding to the maximum frequency value is called the "networked control frequent particle", which is the most suitable particle for the current control needs and can play a key role in the subsequent control strategy optimization. Through this process, the system can accurately identify the most suitable particles, reduce redundancy and interference, ensure the accuracy and stability of control, and effectively optimize system performance.

[0046] Step S600, according to the target seat surface vertical position, the target seat surface horizontal position and the target seat surface inclination angle, initialize the seat surface vertical position adjustment module, the seat surface horizontal position adjustment module and the seat surface inclination angle adjustment module to adjust the seat posture. Specifically, according to the obtained target seat surface vertical position, horizontal position and inclination angle data, the system first inputs these target values ​​into the corresponding adjustment modules, namely the seat surface vertical position adjustment module, the seat surface horizontal position adjustment module and the seat surface inclination angle adjustment module. Each module adjusts the corresponding components of the chair according to the target data. For example, the seat surface vertical position adjustment module adjusts the height of the seat to ensure that it meets the needs of the user; the seat surface horizontal position adjustment module improves the comfort by changing the relative position of the seat and the user; the seat surface inclination angle adjustment module adjusts the inclination of the chair back to provide better back support. All these adjustment processes are carried out automatically, and through real-time monitoring feedback, the system ensures that the adjustment of the seat surface position is always accurate and provides the best sitting experience that meets the needs of the user.

[0047] The embodiment of the present application receives the user's posture number and ID information through the user terminal, and uses the information to retrieve the local usage log. If the amount of log data is insufficient, the system will match the user portrait according to the user ID, and obtain the relevant network log online in combination with the seat model. Based on local and network logs, the system calibrates the vertical position, horizontal position and tilt angle of the seat surface, and finally obtains the target adjustment parameters. According to the target parameters, the system initializes the adjustment module to realize adaptive adjustment of the seat posture, achieving the technical effect of personalized adjustment according to individual differences of users.

[0048] In the above, refer to Figure 1 The adaptive adjustment method for a posture-adjustable seat according to an embodiment of the present invention is described in detail. Figure 2 An adaptive adjustment system for a posture-adjustable seat according to an embodiment of the present invention is described.

[0049] The adaptive adjustment system for a posture-adjustable seat according to an embodiment of the present invention is used to solve the technical problem of insufficient personalized adjustment of the posture adaptive control system in the prior art, and achieves the technical effect of personalized adjustment according to individual differences of users. The adaptive adjustment system for a posture-adjustable seat includes: a user information receiving module 10, an information retrieval module 20, a user portrait information matching module 30, an online use log retrieval module 40, a frequency calibration module 50, and a seat posture adjustment module 60.

[0050] The user information receiving module 10 is used to receive the user posture number and user ID information through the user terminal.

[0051] The information retrieval module 20 is used to retrieve the local usage log belonging to the user gesture number based on the user ID information.

[0052] The user portrait information matching module 30 is used to match the user portrait information according to the user ID information when the data volume of the local usage log is less than or equal to the fitting data volume threshold.

[0053] The online usage log retrieval module 40 is used to retrieve the online usage log belonging to the user posture number based on the user portrait information and the seat model.

[0054] The frequent calibration module 50 is used to frequently calibrate the seat surface vertical position, seat surface horizontal position and seat surface tilt angle according to the networked usage log and the local usage log to obtain the target seat surface vertical position, target seat surface horizontal position and target seat surface tilt angle.

[0055] The seat posture adjustment module 60 is used to initialize the seat surface vertical position adjustment module, the seat surface horizontal position adjustment module and the seat surface inclination angle adjustment module to adjust the seat posture according to the target seat surface vertical position, the target seat surface horizontal position and the target seat surface inclination angle.

[0056] The specific configuration of the information retrieval module 20 will be described in detail below. As described above, based on the user ID information, the local usage log belonging to the user posture number is retrieved, and the information retrieval module 20 further includes: a data volume judgment unit, the data volume judgment unit is used to perform frequent calibration on the vertical position of the seat surface, the horizontal position of the seat surface, and the tilt angle of the seat surface according to the local usage log when the data volume of the local usage log is greater than the fitting data volume threshold, and obtain the target vertical position of the seat surface, the target horizontal position of the seat surface, and the target tilt angle of the seat surface.

[0057] The specific configuration of the online usage log retrieval module 40 will be described in detail below. As described above, the online usage log belonging to the user posture number is retrieved online according to the user portrait information and the seat model, and the online usage log retrieval module 40 further includes: a user portrait information composition unit, the user portrait information composition unit is used for the user portrait information including age, height, weight, functional impairment type and leg length; a classification constraint construction unit, the classification constraint construction unit is used to construct a classification constraint according to the functional impairment type and the seat model; a quantitative constraint construction unit, the quantitative constraint construction unit is used to construct a quantitative constraint according to the age, the height, the weight and the leg length; an online retrieval unit, the online retrieval unit is used to retrieve the online usage log belonging to the user posture number according to the classification constraint and the quantitative constraint in combination with the seat model.

[0058] Among them, according to the classification constraint and the quantitative constraint, combined with the online retrieval of the networked usage log belonging to the user posture number by the seat model, the online retrieval unit further includes: a classification constraint judgment subunit, the classification constraint judgment subunit is used to regard the retrieved user as not satisfying the classification constraint when at least one condition that the functional impairment type of the retrieved user is different from the functional impairment type and the seat model of the retrieved user is different from the seat model is triggered; a deviation threshold construction subunit, the deviation threshold construction subunit is used to construct an age deviation threshold, a height deviation threshold, a weight deviation threshold and a leg length deviation threshold; a quantitative constraint judgment subunit, the quantitative constraint judgment subunit is used to regard the retrieval user's age as satisfying the quantitative constraint when the age deviation of the retrieval user's age is less than or equal to the age deviation threshold, and the height deviation of the retrieval user's height is less than or equal to the height deviation threshold, and the weight deviation of the retrieval user's weight is less than or equal to the weight deviation threshold, and the leg length deviation of the retrieval user's leg length is less than or equal to the leg length deviation threshold; a quantitative constraint dissatisfaction judgment subunit, the quantitative constraint dissatisfaction judgment subunit is used to otherwise regard the quantitative constraint as not satisfying.

[0059] The specific configuration of the frequent calibration module 50 will be described in detail below. As described above, the vertical position, horizontal position and tilt angle of the seat surface are frequently calibrated according to the networked use log and the local use log to obtain the target vertical position, horizontal position and tilt angle of the seat surface. The frequent calibration module 50 further includes: a first coordinate axis construction unit, which is used to normalize and map the constraint interval of the vertical position of the seat surface to construct a first coordinate axis; a second coordinate axis construction unit, which is used to normalize and map the constraint interval of the horizontal position of the seat surface to construct a second coordinate axis; a third coordinate axis construction unit, which is used to normalize and map the constraint interval of the horizontal position of the seat surface to construct a second coordinate axis; The degree constraint interval is normalized and mapped to construct a third coordinate axis; a control constraint space construction unit, the control constraint space construction unit is used to construct a control constraint space according to the first coordinate axis, the second coordinate axis and the third coordinate axis; a historical control particle set acquisition unit, the historical control particle set acquisition unit is used to distribute the network usage log and the local usage log in the control constraint space to obtain a historical control particle set; a target seat surface space parameter acquisition unit, the target seat surface space parameter acquisition unit is used to frequently calibrate the historical control particle set to obtain a target seat surface vertical position, a target seat surface horizontal position and a target seat surface inclination angle.

[0060] The historical control particle set is frequently calibrated to obtain the target seat surface vertical position, the target seat surface horizontal position and the target seat surface inclination angle. The target seat surface spatial parameter acquisition unit further includes: a historical control particle set composition subunit, the historical control particle set composition subunit is used for the historical control particle set to include a networked historical control particle set and a local historical control particle set; a frequent particle analysis subunit, the frequent particle analysis subunit is used to perform frequent particle analysis on the networked historical control particle set to obtain networked control frequent particles, wherein the networked control frequent particles have a first weight; a local control frequent particle acquisition subunit, the local control frequent particle acquisition subunit is used to perform frequent particle analysis on the local historical control particle set to obtain local control frequent particles, wherein the local control frequent particles have a second weight; a weighted mean fusion subunit, the weighted mean fusion subunit is used to perform weighted mean fusion on the networked control frequent particles and the local control frequent particles according to the first weight and the second weight to obtain the target seat surface vertical position, the target seat surface horizontal position and the target seat surface inclination angle.

[0061] wherein, a frequent particle analysis is performed on the networked historical control particle set to obtain networked control frequent particles, wherein the networked control frequent particles have a first weight, and the frequent particle analysis subunit further includes: a first particle distribution coordinate acquisition microunit, the first particle distribution coordinate acquisition microunit is used to obtain the first particle distribution coordinates of the networked historical control particle set; a neighboring coordinate sorting microunit, the neighboring coordinate sorting microunit is used to sort k neighboring coordinates from the networked historical control particle set from near to far based on the first particle distribution coordinates, wherein 0.5*the total number of the networked historical control particle set ≥k ≥0.3*the total number of the networked historical control particle set; a first particle frequency calculation microunit, the first particle frequency calculation microunit is used to calculate the inverse of the mean distribution distance between the first particle distribution coordinate and the k neighboring coordinates, set it as the first particle frequency, and add it to the frequency set; a networked control frequent particle extraction microunit, the networked control frequent particle extraction microunit is used to extract the maximum particle frequency in the networked historical control particle set according to the frequency set, and set it as the networked control frequent particle.

[0062] The adaptive adjustment system for a posture-adjustable seat provided in the embodiment of the present invention can execute the adaptive adjustment method for a posture-adjustable seat provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0063] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0064] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. An adaptive adjustment method for a posture-adjustable seat, characterized in that: An adaptive adjustment system for a posture-adjustable seat, the system includes a seat surface vertical position adjustment module, a seat surface horizontal position adjustment module and a seat surface tilt angle adjustment module, the seat surface tilt angle refers to the lifting angle of the seat surface backrest end, including: Receive user posture number and user ID information through the user terminal; Retrieving a local usage log belonging to the user gesture number based on the user ID information; When the data volume of the local usage log is less than or equal to the fitting data volume threshold, matching the user portrait information according to the user ID information; Retrieving online usage logs belonging to the user posture number based on the user portrait information and the seat model; Frequently calibrating the vertical position, horizontal position and tilt angle of the seat surface according to the networked usage log and the local usage log to obtain a target vertical position, horizontal position and tilt angle of the seat surface; According to the target seat surface vertical position, the target seat surface horizontal position and the target seat surface inclination angle, the seat surface vertical position adjustment module, the seat surface horizontal position adjustment module and the seat surface inclination angle adjustment module are initialized to perform seat posture adjustment.

2. The method according to claim 1, characterized in that Retrieving the local usage log belonging to the user gesture number based on the user ID information, and then further comprising: When the data volume of the local usage log is greater than the fitting data volume threshold, the seat surface vertical position, the seat surface horizontal position and the seat surface inclination angle are frequently calibrated according to the local usage log to obtain the target seat surface vertical position, the target seat surface horizontal position and the target seat surface inclination angle.

3. The method according to claim 1, characterized in that Retrieving the online usage log belonging to the user posture number based on the user portrait information and the seat model, including: The user portrait information includes age, height, weight, type of functional impairment and leg length; constructing a classification constraint according to the type of functional impairment and the seat model; constructing a quantitative constraint based on the age, the height, the weight, and the leg length; According to the classification constraint and the quantification constraint, the networked usage log belonging to the user posture number is retrieved in combination with the seat model.

4. The method according to claim 3, characterized in that include: When at least one of the conditions that the functional impairment type of the retrieved user is different from the functional impairment type and the seat model of the retrieved user is different from the seat model is triggered, it is deemed that the retrieved user does not meet the classification constraint; Construct age deviation threshold, height deviation threshold, weight deviation threshold and leg length deviation threshold; When the age deviation of the retrieved user from the age is less than or equal to the age deviation threshold, and the height deviation of the retrieved user from the height is less than or equal to the height deviation threshold, and the weight deviation of the retrieved user from the weight is less than or equal to the weight deviation threshold, and the leg length deviation of the retrieved user from the leg length is less than or equal to the leg length deviation threshold, the quantitative constraint is deemed to be satisfied; Otherwise, it is deemed that the quantization constraint is not satisfied.

5. The method according to claim 1, characterized in that Frequently calibrating the vertical position, horizontal position, and tilt angle of the seat surface according to the networked usage log and the local usage log to obtain a target vertical position, horizontal position, and tilt angle of the seat surface, including: Normalize and map the vertical position constraint interval of the seat surface to construct the first coordinate axis; Perform normalized mapping on the horizontal position constraint interval of the seat surface to construct the second coordinate axis; Normalize and map the seat tilt angle constraint interval to construct the third coordinate axis; Constructing a control constraint space according to the first coordinate axis, the second coordinate axis and the third coordinate axis; Distributing the network usage log and the local usage log in the control constraint space to obtain a historical control particle set; The historical control particle set is frequently calibrated to obtain a target seat surface vertical position, a target seat surface horizontal position, and a target seat surface inclination angle.

6. The method according to claim 5, characterized in that The historical control particle set is frequently calibrated to obtain a target seat surface vertical position, a target seat surface horizontal position, and a target seat surface tilt angle, including: The historical control particle set includes a networked historical control particle set and a local historical control particle set; Performing frequent particle analysis on the networking history control particle set to obtain networking control frequent particles, wherein the networking control frequent particles have a first weight; Performing frequent particle analysis on the local historical control particle set to obtain local control frequent particles, wherein the local control frequent particles have a second weight; According to the first weight and the second weight, weighted mean fusion is performed on the networked control frequent particles and the local control frequent particles to obtain the target seat surface vertical position, the target seat surface horizontal position and the target seat surface inclination angle.

7. The method according to claim 6, characterized in that Performing frequent particle analysis on the networked historical control particle set to obtain networked control frequent particles includes: Obtaining the first particle distribution coordinates of the networked historical control particle set; Based on the first particle distribution coordinates from near to far, k neighboring coordinates are selected from the networked historical control particle set, wherein 0.5*the total number of networked historical control particle sets ≥ k ≥ 0.3*the total number of networked historical control particle sets; Calculate the inverse of the mean value of the distribution distance between the first particle distribution coordinate and the k neighboring coordinates, set it as the first particle frequency, and add it to the frequency set; According to the frequency set, the maximum frequency value of particles in the networking history control particle set is extracted and set as the networking control frequent particle.

8. An adaptive adjustment system for a posture-adjustable seat, characterized in that: The system is used to implement the adaptive adjustment method for a posture-adjustable seat according to any one of claims 1 to 7, and the system comprises: A user information receiving module, the user information receiving module is used to receive the user posture number and user ID information through the user terminal; An information retrieval module, the information retrieval module is used to retrieve the local usage log belonging to the user gesture number based on the user ID information; A user portrait information matching module, the user portrait information matching module is used to match the user portrait information according to the user ID information when the data volume of the local usage log is less than or equal to the fitting data volume threshold; An online usage log retrieval module, the online usage log retrieval module is used to retrieve the online usage log belonging to the user posture number based on the user portrait information and the seat model; A frequent calibration module, the frequent calibration module is used to frequently calibrate the vertical position, horizontal position and tilt angle of the seat surface according to the network use log and the local use log, and obtain a target vertical position, horizontal position and tilt angle of the seat surface; A seat posture adjustment module, the seat posture adjustment module is used to initialize the seat surface vertical position adjustment module, the seat surface horizontal position adjustment module and the seat surface inclination angle adjustment module to perform seat posture adjustment according to the target seat surface vertical position, the target seat surface horizontal position and the target seat surface inclination angle.

Images