Search

CN-122004597-A - Intelligent table and chair sitting posture adjusting method based on pressure center track

CN122004597ACN 122004597 ACN122004597 ACN 122004597ACN-122004597-A

Abstract

The invention discloses an intelligent table and chair sitting posture adjusting method based on a pressure center track, which comprises the following steps of S1, acquiring pressure distribution data of a user in real time through a pressure sensor array arranged on a seat surface and/or a backrest, calculating and generating the pressure center track changing along with time, S2, preprocessing the acquired pressure center track data, extracting kinematic and statistical characteristics of the acquired pressure center track data, S3, utilizing a pre-trained machine learning classification model to conduct real-time identification and classification on the sitting posture state of the current user based on the extracted characteristics, judging that the current user belongs to a standard sitting posture or one or more predefined bad sitting postures, S4, generating corresponding adjusting instructions if the identification result is the bad sitting posture, and controlling a driving mechanism of the table and chair to execute preset adjusting actions so as to prompt or assist the user to restore to the standard sitting posture. The invention can physically guide the user to recover to the standard sitting posture unconsciously, and improves the comfort and the health level.

Inventors

  • HU LINGLING
  • WANG CHENGFENG

Assignees

  • 浙江农林大学

Dates

Publication Date
20260512
Application Date
20260130

Claims (10)

  1. 1. The intelligent table and chair sitting posture adjusting method based on the pressure center track is characterized by comprising the following steps of: S1, acquiring data, namely acquiring pressure distribution data of a user in real time through a pressure sensor array arranged on a seat surface and/or a backrest, and calculating and generating a pressure center track changing along with time; s2, data processing and feature extraction, namely preprocessing the collected pressure center track data and extracting the kinematic and statistical features of the data; S3, based on the extracted characteristics, carrying out real-time identification and classification on the sitting posture state of the current user by utilizing a pre-trained machine learning classification model, and judging whether the sitting posture state belongs to a standard sitting posture or one or more predefined bad sitting postures; s4, actively intervening and adjusting, namely if the identification result is bad sitting posture, generating a corresponding adjusting instruction, and controlling a driving mechanism of the desk and chair to execute a preset adjusting action so as to promote or assist a user to restore to the standard sitting posture.
  2. 2. The intelligent table-chair sitting posture adjustment method according to claim 1, wherein in step S1, the pressure sensor array is distributed in a grid shape, and covers the main bearing areas of the seat surface and the backrest.
  3. 3. The intelligent table and chair sitting posture adjustment method of claim 1, wherein the coordinates of the center of pressure trajectory are calculated by the following formula: ; ; wherein: , the coordinates of the pressure center on the x axis and the y axis in the plane coordinate system are respectively, Is the first The detected pressure value of the individual pressure sensors, , Is the first The coordinate locations of the individual pressure sensors, Is the total number of pressure sensors.
  4. 4. The intelligent table-chair sitting posture adjustment method according to claim 1, wherein in the step S2, the preprocessing includes filtering denoising, coordinate normalization and time window segmentation, and the extracted features include at least a position mean value of the pressure center track in a plane coordinate system, a track standard deviation, a displacement speed, a total length of the moving track, component features of the track in front-rear direction and left-right direction, and spectrum features of the track.
  5. 5. The intelligent table-chair sitting posture adjustment method according to claim 1, wherein in step S3, the pre-trained machine learning classification model is a classifier constructed based on random forests, support vector machines or neural networks, which is obtained by training a pressure center trajectory dataset labeled with different sitting posture categories.
  6. 6. The intelligent table and chair sitting posture adjusting method according to claim 5, wherein the machine learning classification model adopts a feature weighted fusion strategy, the weights are obtained by optimizing a particle swarm optimization algorithm, and the objective function is as follows: ; wherein: In order to classify the sum of the errors, Is the first The weight coefficient of the class feature, Is the first The classification error corresponding to the class feature, Is the total number of feature classes.
  7. 7. The intelligent table-chair sitting posture adjustment method according to claim 1, wherein in step S4, the preset adjustment action is to change the height of the table top, the height, the inclination angle or the front-rear position of the seat surface and/or the backrest by the driving mechanism, and the adjustment parameters include at least one of an adjustment amplitude, an adjustment rate and an adjustment duration.
  8. 8. The intelligent table and chair sitting posture adjustment method of claim 7, wherein the adjustment amplitude is calculated by the following formula: ; In the formula, In order to adjust the amplitude of the amplitude, Is a coefficient of proportionality and is used for the control of the power supply, As the current center of pressure coordinate, Is the pressure center coordinate corresponding to the standard sitting posture.
  9. 9. The intelligent table and chair sitting posture adjustment method of claim 7, wherein the adjustment rate is calculated by the following formula: ; In the formula, In order to adjust the rate of the flow, In order to adjust the coefficient of the rate, The rate is adjusted on the basis of which, Confidence in bad sitting posture.
  10. 10. The intelligent table and chair sitting posture adjusting method according to claim 1, wherein after the adjusting action is performed in step S4, further comprising a feedback step of continuously monitoring the change of the track of the center of pressure of the user after the adjustment, and calculating a sitting posture recovery index: ; Wherein, the In order to achieve the degree of recovery of the sitting posture, , The coordinates of the pressure center after adjustment on the x axis and the y axis in a plane coordinate system; , The reference coordinates of the pressure center on the x axis and the y axis corresponding to the preset standard sitting posture, , Is a preset minimum value and a preset maximum value of the pressure center coordinates in the x-axis direction, , The minimum value and the maximum value of the pressure center coordinates in the preset y-axis direction are set. If it is And if the time duration is smaller than the set threshold value and exceeds the set time, triggering secondary adjustment or sending out a warning signal.

Description

Intelligent table and chair sitting posture adjusting method based on pressure center track Technical Field The invention relates to an intelligent table and chair sitting posture adjusting method based on a pressure center track, and belongs to the technical fields of ergonomics and intelligent home furnishing. Background With the development of information technology, computer office has become a major office mode. It is counted that more than 30% of adults sit for more than 6 hours per day. In a sedentary state, a user is difficult to maintain a correct sitting posture, and a series of health problems such as lumbago, backache, cervical spondylosis, musculoskeletal diseases and the like are easily caused, so that the personal health and the quality of life are affected, and huge social medical burden and productivity loss are brought. Currently, sitting posture recognition technology has been receiving a great deal of attention, and researchers collect user sitting posture data by using devices such as pressure sensors, inertial measurement units or vision sensors installed in seats, and classify and recognize sitting postures by means of machine learning algorithms (such as support vector machines, random forests, convolutional neural networks, etc.). However, the prior art has significant drawbacks with respect to the way in which poor sitting postures are corrected. The main stream method is that after the bad sitting posture is identified, the user is reminded to adjust the sitting posture by means of voice, light or mobile phone application pushing and the like. The method has the obvious defects that firstly, the reminding has hysteresis, when a user receives the reminding, the bad sitting posture has caused a certain load on the body, secondly, frequent reminding can interfere the work or learning concentration degree of the user, the efficiency is affected, and even the reminding function is closed due to boredom of the user, so that the correction system is invalid. Disclosure of Invention The invention aims to provide an intelligent table and chair sitting posture adjusting method based on a pressure center track. According to the invention, the bad sitting posture is identified in real time and without sense by analyzing the pressure center track characteristics derived from the pressure distribution change of the seat, and the table and chair mechanism can be driven to carry out adaptive adjustment, so that a user is guided to recover to the standard sitting posture unconsciously in a physical mode, and the comfort and the health level are improved. The technical scheme of the invention is that the intelligent table and chair sitting posture adjusting method based on the pressure center track comprises the following steps: S1, acquiring data, namely acquiring pressure distribution data of a user in real time through a pressure sensor array arranged on a seat surface and/or a backrest, and calculating and generating a pressure center track changing along with time; s2, data processing and feature extraction, namely preprocessing the collected pressure center track data and extracting the kinematic and statistical features of the data; S3, based on the extracted characteristics, carrying out real-time identification and classification on the sitting posture state of the current user by utilizing a pre-trained machine learning classification model, and judging whether the sitting posture state belongs to a standard sitting posture or one or more predefined bad sitting postures; s4, actively intervening and adjusting, namely if the identification result is bad sitting posture, generating a corresponding adjusting instruction, and controlling a driving mechanism of the desk and chair to execute a preset adjusting action so as to promote or assist a user to restore to the standard sitting posture. In the above-mentioned intelligent table and chair sitting posture adjusting method, in step S1, the pressure sensor array is distributed in a grid shape, and covers the main bearing areas of the seat surface and the backrest. According to the intelligent table and chair sitting posture adjusting method, the coordinates of the pressure center track are calculated according to the following formula: ; ; wherein: , the coordinates of the pressure center on the x axis and the y axis in the plane coordinate system are respectively, Is the firstThe detected pressure value of the individual pressure sensors,,Is the firstThe coordinate locations of the individual pressure sensors,Is the total number of pressure sensors. In the above-mentioned intelligent table-chair sitting posture adjusting method, in step S2, the preprocessing includes filtering denoising, coordinate normalization and time window segmentation, and the extracted features at least include a position mean value of the pressure center track in a plane coordinate system, a track standard deviation, a displacement speed, a total length of a moving t