Posture correction method and apparatus thereof
The integration of pressure sensors, gyro sensors, and AI algorithms with camera-based systems in the posture correction device addresses the limitations of existing chairs by providing accurate real-time feedback, enhancing posture correction and reducing the risk of cervical spine diseases.
Patent Information
- Application Number
- PCT/KR2023/008709
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-06-19
- Filing Date
- 2023-06-22
- Publication Date
- 2024-12-26
AI Technical Summary
Existing posture correction chairs are ineffective in accurately detecting and correcting incorrect sitting postures, particularly when users sit diagonally or with their neck and waist bent, leading to increased rates of cervical spine diseases due to limitations in pressure sensor accuracy and inability to detect non-perpendicular postures.
A posture correction method and device that utilizes a combination of pressure sensors, gyro sensors, and AI algorithms, synchronized with camera-based AI motion systems, to collect and analyze seating data, providing real-time feedback and updates to improve user posture, distinguishing between correct and incorrect postures with enhanced accuracy.
The solution enables quick and accurate feedback on chair posture correction, improving user posture quality of life by defining correct and incorrect postures, analyzing user-specific sitting habits, and refining the AI algorithm based on user improvements, thereby reducing the risk of cervical spine diseases and other posture-related issues.
Smart Images

Figure KR2023008709_26122024_PF_FP_ABST
Abstract
Description
Posture correction method and device thereof
[0001] The present invention relates to a posture correction method and a device therefor, and more specifically, to a posture correction method and a device therefor that can correct a user's chair sitting posture in real time by collecting sitting data on various postures of a user using an ergonomically designed chair and constructing and utilizing an AI algorithm based on the data.
[0002] Typically, a chair consists of a seat that supports the user's buttocks, legs that support the seat, and a backrest that supports the user's lower back. These chairs are often placed in homes, offices, libraries, and reading rooms, where students and office workers spend long periods of time sitting on them.
[0003] Many users of chairs are adopting incorrect postures, such as leaning forward with their hips pushed back while using cell phones, laptops, etc., and due to these incorrect postures, the rate of cervical spine diseases continues to increase. For example, in Korea, more than 12 million people are already experiencing cervical spine diseases.
[0004] Globally, approximately 10% of the population suffers from diseases such as cervical spine disease, and these individual diseases affect society as a whole, causing various problems such as a decrease in the productive population, an increase in unemployment, a decrease in productivity, and an increase in healthcare costs.
[0005] Several chairs have been proposed in the past to correct users' incorrect chair sitting postures, and Fig. 1 (a) illustrates such an existing posture correction chair. As illustrated, the existing posture correction chair has a pressure sensor (1) provided on the seat, and determines the user's posture type based on the pressure value detected by the pressure sensor (1). However, since the pressure sensor (1) receives data vertically, if the user sits diagonally or crosses over, the pressure value cannot be accurately obtained, which inevitably causes many errors in determining whether the user has the correct posture.
[0006] In particular, in these existing posture correction chairs, if the user's buttocks are evenly positioned on the seat, a pressure value classified as a good posture is derived regardless of the posture of other body areas. For example, as shown in (b) of Fig. 1, even if the user's buttocks are evenly in contact with the seat and the back is evenly in contact with the backrest, the neck and back are considerably bent, which can cause cervical spine disease, etc., and there is a limitation in that the existing posture correction chair cannot detect this incorrect posture at all.
[0007] Therefore, in order to overcome the problems and limitations of these existing posture correction chairs, there is a growing need in the industry, especially among many users suffering from cervical spine disorders, for a new type of posture correction method and device that can correct a user's chair sitting posture in real time by collecting sitting data on various postures using an ergonomically designed chair and building and utilizing an AI algorithm based on the data.
[0008] The present invention has been devised to solve the above problems, and the purpose of the present invention is to provide a posture correction method and device that enable users to receive feedback on chair posture correction more quickly and thereby improve their quality of life.
[0009] In addition, the present invention aims to provide a posture correction method and device that can assist a user who is in an incorrect posture to accurately correct the posture to the correct posture by defining the correct posture that the user should pursue and also defining incorrect postures similar to the correct posture.
[0010] In addition, the present invention aims to provide a posture correction method and device capable of analyzing differences according to a user's various chair sitting postures by using a gyro sensor to identify data on specific postures that cannot be identified with a pressure sensor alone, and thereby providing the user with more customized and accurate customized posture correction information.
[0011] In addition, the present invention aims to provide a posture correction method and device capable of improving the accuracy of posture-specific analysis by confirming a user's posture change according to posture correction content provided based on an AI algorithm for posture correction and reflecting and updating the data of such posture change back into the AI algorithm.
[0012] In addition, the present invention aims to provide a posture correction method and device that can further improve the accuracy of an AI posture analysis algorithm by utilizing a plurality of camera-based AI motion systems to distinguish between correct and incorrect postures.
[0013] The technical problems of the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the description below.
[0014] A posture correction method according to one embodiment of the present invention for solving the above technical problem may include the steps of: collecting a user's sitting data on a chair; constructing a user-specific data cluster based on the collected sitting data; constructing an AI algorithm for posture correction based on the constructed data cluster; and providing information on posture correction based on the constructed AI algorithm and real-time sitting data.
[0015] In addition, the posture correction method may further include a step of analyzing the user's improvements using the constructed AI algorithm; and a step of updating the AI algorithm based on the analyzed improvements.
[0016] Additionally, the step of collecting user sitting data regarding the chair may include a step of collecting pressure values and inclination values from a pressure sensor and a gyro sensor attached to the chair.
[0017] Additionally, the step of collecting the user's sitting data regarding the chair may further include a step of synchronizing the collected pressure values and inclination values with AI vision data implemented by a plurality of cameras.
[0018] In addition, a computer program according to an additional embodiment of the present invention for solving the above technical problem can be stored in a computer-readable recording medium so as to be combined with a computer as hardware to perform the posture correction method.
[0019] In addition, a posture correction device according to another embodiment of the present invention for solving the above technical problem may include a sitting data collection unit configured to collect sitting data of a user with respect to a chair; a data cluster construction unit configured to construct a data cluster for each user based on the collected sitting data; an AI algorithm construction unit configured to construct an AI algorithm for posture correction based on the constructed data cluster; and a posture analysis unit configured to provide information on posture correction based on the constructed AI algorithm and real-time sitting data.
[0020] In addition, the posture correction device may further include an AI algorithm update unit configured to analyze improvements of the user by utilizing the constructed AI algorithm and update the AI algorithm based on the analyzed improvements.
[0021] Additionally, the seating data collection unit may be further configured to collect pressure values and inclination values from a pressure sensor and a gyro sensor attached to the chair.
[0022] Additionally, the seating data collection unit may be further configured to synchronize the collected pressure values and inclination values with AI vision data implemented by multiple cameras.
[0023] In addition, a posture correction system according to another embodiment of the present invention for solving the above technical problem may include the posture correction device; and a user terminal communicatively coupled with the posture correction device.
[0024] According to a posture correction method and device thereof according to one embodiment of the present invention, users can receive feedback on chair posture correction more quickly and thereby improve their quality of life.
[0025] In addition, according to a posture correction method and device thereof according to one embodiment of the present invention, by defining a correct posture that a user should pursue and also defining an incorrect posture similar to the correct posture, it is possible to assist a user who is in an incorrect posture to accurately correct the user to a correct posture.
[0026] In addition, according to the posture correction method and device thereof according to one embodiment of the present invention, data on specific postures that cannot be determined by a pressure sensor alone can be determined by using a gyro sensor, thereby analyzing differences according to various chair sitting postures of the user, and thereby providing more customized and accurate posture correction information to the user.
[0027] In addition, according to the posture correction method and device thereof according to one embodiment of the present invention, the change in the user's posture is confirmed according to the posture correction content provided based on the constructed AI algorithm for posture correction, and the data of such posture change is reflected and updated again in the AI algorithm, thereby further improving the accuracy of the analysis by posture.
[0028] In addition, according to the posture correction method and device thereof according to one embodiment of the present invention, the accuracy of the AI posture analysis algorithm can be further improved by utilizing a plurality of camera-based AI motion systems to distinguish between correct and incorrect postures.
[0029] In order to more fully understand the drawings cited in the detailed description of the present invention, a brief description of each drawing is provided.
[0030] Fig. 1 (a) shows a schematic diagram of a conventional posture correction chair, and Fig. 1 (b) is an example diagram to explain the limitations of the conventional posture correction chair.
[0031] FIG. 2 illustrates a schematic block diagram of a posture correction device (100) and a posture correction system (10) including the same according to one embodiment of the present invention.
[0032] FIG. 3 is a flowchart illustrating the overall flow of a posture correction method / algorithm implemented according to one embodiment of the present invention.
[0033] FIG. 4 (a) is an exemplary diagram for explaining the seat structure of a chair (300) according to one embodiment of the present invention, and FIG. 4 (b) is an exemplary diagram for explaining the back structure of a chair (300) according to one embodiment of the present invention.
[0034] FIG. 5 is an exemplary diagram illustrating a gyro sensor (330) and a pressure sensor (340) attached to a chair (300) according to one embodiment of the present invention.
[0035] FIG. 6a is an exemplary diagram for explaining correct and incorrect postures prescribed when a user sits with his or her back leaning against the back of a chair according to one embodiment of the present invention, and FIG. 6b is an exemplary diagram for explaining correct and incorrect postures prescribed when a user sits with his or her back not leaning against the back of a chair according to one embodiment of the present invention.
[0036] FIG. 7 is a conceptual diagram illustrating AI vision data implemented by multiple cameras according to one embodiment of the present invention.
[0037] FIG. 8 illustrates an exemplary UI service screen of an AI posture correction application implemented to a user according to one embodiment of the present invention.
[0038] Hereinafter, embodiments of the present invention will be described with reference to the attached drawings. When assigning reference numerals to components in each drawing, it should be noted that identical components are assigned the same numerals as much as possible even if they are shown in different drawings. In addition, when describing embodiments of the present invention, if a detailed description of a related known configuration or function is judged to hinder understanding of the embodiments of the present invention, a detailed description thereof will be omitted. In addition, although embodiments of the present invention will be described below, the technical idea of the present invention is not limited thereto and may be modified and implemented in various ways by those skilled in the art.
[0039] Throughout the specification, when a part is said to be "connected" to another part, this includes not only cases where it is "directly connected" but also cases where it is "indirectly connected" with another element in between. Throughout the specification, when a part is said to "include" a certain component, this does not mean that other components are excluded, but rather that other components may be included, unless specifically stated otherwise. In addition, when describing components of embodiments of the present invention, terms such as first, second, A, B, (a), (b), etc. may be used. These terms are only intended to distinguish the components from other components, and the nature, order, or sequence of the components are not limited by the terms.
[0040]
[0041] FIG. 2 illustrates a schematic block diagram of a posture correction device (100) and a posture correction system (10) including the same according to one embodiment of the present invention.
[0042] As illustrated, a posture correction system (10) according to one embodiment of the present invention may be composed of a posture correction device (100), a user terminal (200), a chair (300), etc. For reference, FIG. 2 illustrates a configuration in which a single user terminal (200) is communicatively coupled with the posture correction device (100) and the chair (300), but this is merely an example for easy understanding of the present invention, and it is clear that a plurality of user terminals (e.g., terminals of all family members such as a father, mother, older sister, and younger sister) may be communicatively coupled with the posture correction device (100) and the chair (300) under the condition of user identification.
[0043] A posture correction device (100) according to one embodiment of the present invention may be configured to provide a service for correcting a user's chair sitting posture in real time to a user terminal (200) by collecting sitting data for various postures using an ergonomically designed chair (300) and constructing and utilizing an AI algorithm based on the data. In order to implement such a user-customized posture correction service, the posture correction device (100) may be configured with a control unit (110), an AI learning unit (120), a posture correction unit (130), a communication unit (140), a storage unit (150), etc., as illustrated in FIG. 2.
[0044] For reference, the posture correction device (100) according to one embodiment of the present invention corresponds to a device based on a self-computer program manufactured and operated by an individual or a private company, and may be referred to by various terms such as device, equipment, server, platform, center, etc. according to various expression methods in the related technical field.
[0045] For example, a posture correction device (100) according to one embodiment of the present invention may be configured to correct a user's chair sitting posture in real time by collecting sitting data for various postures using an ergonomically designed chair (300) and constructing and utilizing an AI algorithm based on the data. To this end, the posture correction device (100) may be implemented to provide a user-customized posture correction service in the form of an application or widget. Here, a widget may refer to a mini application that allows direct use of content or functions without going through an application. Therefore, the term 'application' in the present invention below may be interpreted as a comprehensive concept including a widget, and a user may also download and install, for example, an AI posture correction application from an online market, etc., for the posture correction device (100) according to the present invention.
[0046] For reference, the components (110, 120, 130, 140, 150) of the posture correction device (100) illustrated in FIG. 2 are merely exemplary components for explaining the operation, function, etc. of the posture correction device (100) according to one embodiment of the present invention, and therefore, it is clear that the posture correction device (100) according to one embodiment of the present invention may additionally include other components (e.g., a power supply unit, a monitoring unit, a display unit, a notification unit, etc.) other than the illustrated components (110, 120, 130, 140, 150).
[0047] The control unit (110) may be configured to comprehensively control various operations, functions, communications, etc. performed in the posture correction device (100) according to one embodiment of the present invention. For example, the control unit (110) may be configured to comprehensively control an operation of the AI learning unit (120) collecting and learning sitting data, an operation of building a data cluster, an operation of collecting pressure values and inclination values according to the user's sitting from the chair (300), an operation of synchronizing the collected pressure values and inclination values with AI vision data implemented by a plurality of cameras, an operation of building an AI algorithm, an operation of the posture correction unit (130) receiving the user's sitting data in real time, an operation of analyzing the user's posture in real time based on the AI algorithm, an operation of providing posture correction content according to the analyzed result, an operation of the communication unit (140) communicating with the user terminal (200), an operation of the storage unit (150) storing various data, etc.
[0048] For reference, the control unit (110) may be implemented as a processor, a controller, a microprocessor, a micro controller, etc., and may operate at least two or more of the components included in the posture correction device (100) in combination to drive an application program.
[0049] The AI learning unit (120) collects and learns various sitting data of users sitting on a chair (300), thereby constructing a cluster for each user, and based on this, constructs an AI algorithm for chair posture correction, thereby laying the foundation for the posture correction unit (130) to implement real-time posture analysis and correction of the user.
[0050] For example, as exemplarily illustrated in FIG. 2, an AI learning unit (120) according to one embodiment of the present invention may be composed of a seating data collection unit (121), a data cluster construction unit (122), an AI algorithm construction unit (123), an AI algorithm update unit (124), etc.
[0051] The seating data collection unit (121) may be configured to collect user seating data regarding the chair (300). For example, as one of the data required to build an AI algorithm for posture correction, seating data for multiple users (e.g., thousands to tens of thousands) may be collected. Here, each user adjusts the length of the backrest and seat provided on the chair (300) to fit his or her size and sits on the chair (300), and user information is additionally input for data learning, and when the pressure / gyro sensor is ready for operation after a predetermined calibration, the seating data collection unit (121) may collect seating data for each user.
[0052] Here, the user information collected may include nationality (e.g., body type, 15 detailed upper / lower body lengths, etc.), disease (e.g., spinal disease / adult disease, posture according to symptom severity, etc.), age (e.g., under 50, 50 or older), occupation (e.g., daily sitting time, work characteristics, etc.), lifestyle pattern (e.g., usual posture, activity pattern, etc.), gender (e.g., male / female, gender-specific habitual posture, etc.), but this information is only an example of user information and is not limited thereto.
[0053] Additionally, detailed user body shape information may be utilized when developing AI algorithms for posture correction. For example, detailed body shape information may be utilized to compare and analyze specific areas of the user's upper and lower body. This detailed user body shape information may include, but is not limited to, neck-to-hip measurements, shoulder-to-hip measurements, inner arm measurements, total arm measurements, head-to-sole measurements, and shoulder-to-sole measurements.
[0054] Additionally, since multiple users can sit on the chair (300) according to one embodiment of the present invention, sitting data can be collected from each of the multiple users. To this end, a user terminal (200) synchronized with short-range wireless communication, for example, Bluetooth, is identified, and sitting data can be collected based on information of the identified user. For example, if the user sitting on the chair (300) changes from a father of 180 cm / 80 kg to a daughter of 150 cm / 30 kg, the sitting data collection unit (121) according to one embodiment of the present invention can automatically change its user mode to collect sitting data such as pressure values and gyro values based on the input user information of the daughter.
[0055] For example, a seating data collection unit (121) according to one embodiment of the present invention may be further configured to collect input values and inclination values from a pressure sensor and a gyro sensor attached to a chair (300), and synchronize the pressure values and inclination values thus collected with AI vision data implemented by a plurality of cameras. A feature of the present invention is that posture correction of a user is implemented by utilizing AI vision data according to one embodiment of the present invention, and such AI vision data will be described in more detail in FIG. 7 below.
[0056] The data cluster construction unit (122) may be configured to construct user-specific data clusters based on the collected sitting data. More specifically, the data cluster construction unit (122) may construct data clusters among users of similar types based on unique data possessed by each user, and by utilizing AI modeling, the reasons for assuming a specific posture (e.g., crossing one's legs or sticking one's butt out, etc.) may be analyzed (e.g., changes in posture due to habit or occupation, or specific posture due to illness, etc.), and the user's posture pattern may be analyzed based on such common data.
[0057] The AI algorithm construction unit (123) may be configured to construct an AI algorithm for posture correction based on the constructed data cluster. The constructed AI algorithm may function as a program, software, etc. for correcting the user's posture, and may serve as a basis for providing a customized posture correction service to the user terminal (200) in the form of an application such as a so-called "AI posture correction application." In addition, the constructed AI algorithm may serve as a basis for the posture correction unit (130) to analyze the user's sitting posture, correct the posture, and provide content related to posture correction.
[0058] When an AI algorithm for correcting a user's posture is constructed by the AI algorithm construction unit (123), the AI algorithm update unit (124) can be configured to analyze the user's improvement needs by utilizing the constructed AI algorithm. For example, the AI algorithm update unit (124) can utilize AI to analyze and identify the improvement needs to be made by the user, and more specifically, by identifying the time the user sits on the chair (300) and the frequency of correct / incorrect postures, the correlation between posture and pain can be identified, and information necessary for the user can be prepared accordingly.
[0059] In addition, the AI algorithm update unit (124) can be additionally configured to update the AI algorithm by applying all of the user's posture improvement situation, additional considerations (e.g., changes in weight, changes in height, changes in posture, etc.) by utilizing machine learning technology, etc., and important information according to changes in user information along with the update of the AI algorithm can be built as big data and stored in a storage unit (150), etc., so that it can be utilized in medical institutions, etc. in the future.
[0060] The posture correction unit (130) may be configured to provide a user-customized posture correction service based on the results of learning various user sitting data based on an AI algorithm from the AI learning unit (120). To implement such operations and services, the posture correction unit (130) according to one embodiment of the present invention may be configured with a real-time sitting data reception unit (131), a posture analysis unit (132), a content provision unit (133), and the like.
[0061] The real-time sitting data receiving unit (131) may be configured to receive real-time sitting data displayed according to the user's current sitting on the chair (300) from the user terminal (200), more specifically, from the user terminal (200) on which the AI posture correction application is downloaded and installed and which is wirelessly connected to the chair (300). When installing and downloading the AI posture correction application, the user may additionally input certain user information (e.g., nationality, disease, age, occupation, lifestyle pattern, gender, etc.), and the user information thus input may be further utilized when analyzing the user's sitting posture in the posture analysis unit (132).
[0062] More specifically, the posture analysis unit (132) can be configured to analyze the user's posture in real time and provide information on posture correction based on an AI algorithm built and updated in the AI learning unit (120) and real-time sitting data received from the user terminal (200).
[0063] For example, as described in FIG. 6 below, at least one correct posture (i.e., a good posture) and at least one incorrect posture (i.e., a bad posture) may be defined as criteria for implementing a posture correction service according to an embodiment of the present invention. The posture analysis unit (132) may determine whether the current user's posture is correct or incorrect, and may provide posture correction information to a user in an incorrect posture so that the user can correct the incorrect posture to the correct posture. Here, since the determination of whether the posture is correct / incorrect is based on an AI algorithm learned on a data cluster built based on user information, a more user-tailored and user-customized posture correction service may be provided.
[0064] For example, corrections to the user's sitting posture analyzed by the posture analysis unit (132) can be provided in real time to the user terminal (200), and the user terminal (200) can be additionally configured with an interface for selecting a mode for posture correction, and for example, the mode for posture correction can include a normal mode and a training mode.
[0065] More specifically, the regular mode may correspond to a mode in which, after a user sits on a chair (300) for a specified period of time, analysis results are provided in the form of scores, statistics, etc., or guidance is provided. In addition, the training mode may correspond to a mode provided to users who wish to more actively correct their posture, in which a training time such as “10 minutes” or “20 minutes” is set and feedback on posture correction is provided immediately during the set training time.
[0066] The content provision unit (133) may be configured to provide users with various posture- and health-related content based on data regarding user posture analysis by the posture analysis unit (132). For example, the content provision unit (133) may provide users with various posture- or health-related content, such as content regarding diseases that may be caused by specific postures, content regarding prevention methods for specific diseases, content regarding management methods for specific diseases, and content that can share medical knowledge. By providing users with not only information regarding posture correction but also additional content related to posture, health, and diseases, user satisfaction with the AI posture correction service may be further improved.
[0067] The communication unit (140) may be configured to communicate with the user terminal (200). For example, when a user sits on a chair (300) at home, data such as pressure values and gyro values detected by a sensor attached to the chair (300) may be received from the user terminal (200) through the communication unit (140). In addition, information on the user's sitting and correction analyzed based on AI algorithms learned and evolved based on user-specific data clusters, user sitting data received in real time, and various contents related thereto may be transmitted to the user terminal (200) through the communication unit (140).
[0068] For reference, the communication unit (140) is provided for direct connection with the outside or connection via a network, and may be implemented as a wired and / or wireless communication unit (140). More specifically, the communication unit (140) may transmit data from the control unit (110), the AI learning unit (120), the posture correction unit (130), the storage unit (150), etc., by wire or wirelessly, or may receive data from the outside by wire or wirelessly and transmit it to the control unit (110), the AI learning unit (120), the posture correction unit (130), or store it in the storage unit (150). The data may include content such as text, images, and moving images.
[0069] The communication unit (140) can communicate via LAN, WCDMA (Wideband Code Division Multiple Access), LTE (Long Term Evolution), WiBro (Wireless Broadband Internet), RF (Radio Frequency) communication, Wireless LAN, Wi-Fi (Wireless Fidelity), NFC (Near Field Communication), Bluetooth, infrared communication, etc. However, this is merely exemplary, and various wired and wireless communication technologies applicable in the relevant technical field may be used depending on the embodiment to which the present invention is applied.
[0070] The storage unit (150) may be configured to store any data, materials, contents, records, etc. related to various operations, functions, operations, etc. of the posture correction device (100) according to one embodiment of the present invention. For example, the storage unit (150) may store user information, user cluster information, information regarding AI algorithms, information regarding prescribed correct / incorrect postures, information regarding user improvements, information regarding big data, information regarding posture / health-related content, etc.
[0071] For reference, the storage unit (150) may be implemented as various types of storage devices capable of inputting and outputting information, such as a hard disk drive (HDD), a read only memory (ROM), a random access memory (RAM), an electrically erasable and programmable read only memory (EEPROM), a flash memory, a compact flash (CF) card, a secure digital (SD) card, a smart media (SM) card, a multimedia (MMC) card, or a memory stick, as is known to those skilled in the art, and may be provided inside the posture correction device (100) as shown in FIG. 2 or may be provided in a separate external device. Alternatively, the storage unit (150) may be replaced with a web storage that performs a storage function on the Internet.
[0072] The user terminal (200) may be configured to be wirelessly connected to the posture correction device (100) and the chair (300) by downloading and installing a predetermined application, for example, an AI posture correction application. Although a single user terminal (200) is illustrated as an example in FIG. 2, it is as described above that a plurality of user terminals (200) may be connected to the posture correction device (100) and the chair (300) based on user identification so as to be communicatively connected. Therefore, as long as there is a chair (300) in which a pressure sensor and a gyro sensor are attached to the seat and back, there is an advantage in that any family member or any company member can receive a customized posture correction service according to the present invention.
[0073] For reference, the user terminal (200) may also be referred to as a subscriber unit, a subscriber station, a mobile station, a mobile terminal, a remote station, a remote terminal, a mobile device, an access terminal, a terminal, a wireless communication device, a user agent, a user device, or user equipment (UE). The access terminal may be a cellular telephone, a cordless telephone, a Session Initiation Protocol (SIP) telephone, a wireless local loop (WLL) station, a personal digital assistant (PDA), a handheld device with wireless access capabilities, a computing device, or another processing device connected to a wireless modem.
[0074] The chair (300) is a means by which a user can receive a posture correction service in real time while sitting, and can be implemented so that four seats can independently move forward, backward, left, and right, and two backrests can also independently move up, down, left, and right. For reference, the chair (300) utilized in the posture correction system (10) according to one embodiment of the present invention is based on the structural mechanism of Republic of Korea Patent No. 10-2136560 (Seating plate for chair and chair including same) held by the applicant as a patentee, and additionally implements attachment of a sensor for posture correction of the user, and the configuration of such a chair (300) will be described in more detail in FIG. 4 below.
[0075] For reference, although the name 'chair (300)' is used in the following specification, the chair (300) according to one embodiment of the present invention may be referred to as an 'IoT chair' because it corresponds to an Internet of Things-based chair (300) configured to transmit data by an attached pressure sensor and / or gyro sensor to a user terminal (200), or may be referred to as another term such as a 'health care chair' because it is implemented for the ultimate purpose of managing the user's health through the chair (300), but the term 'chair (300)' will be used below to collectively refer to these various expressions regarding chairs.
[0076] By means of a user-tailored posture correction service implemented and provided by a posture correction device (100) and a posture correction system (10) including the same, illustrated in FIG. 2, users can receive feedback on chair posture correction more quickly, and by defining the correct posture that the user should pursue and also defining incorrect postures similar to the correct posture, it is possible to assist users who are in incorrect postures to accurately correct them to the correct posture, and by using a gyro sensor to identify data on specific postures that cannot be identified with a pressure sensor alone, it is possible to analyze differences according to the user's various chair sitting postures, and by checking changes in the user's posture according to the posture correction content provided based on the constructed AI algorithm for posture correction and reflecting and updating the data on such changes in posture back into the AI algorithm, the accuracy of the analysis by posture can be further improved, and by utilizing an AI motion system based on multiple cameras to distinguish between correct posture and incorrect posture, the accuracy of the AI posture analysis algorithm can be further improved.
[0077] Below, the overall flow of a user-customized posture correction service implemented by a posture correction device (100) and a posture correction system (10) including the same, the structure of a chair (300), the regulations on correct and incorrect postures, AI vision data, service UI, etc. will be examined in more detail.
[0078] FIG. 3 is a flowchart illustrating the overall flow of a posture correction method / algorithm implemented according to one embodiment of the present invention.
[0079] First, the seating data collection unit (121) of the AI learning unit (120) can collect the user's seating data (S31). More specifically, the seating data collection unit (121) can be configured to collect seating data for a plurality of users, for example, thousands to tens of thousands of users, wherein each user sits on the chair (300) while adjusting the length of the backrest and seat provided on the chair (300) to suit his or her size, and user information such as nationality / disease / age / occupation / lifestyle pattern / gender can be additionally input for data learning, and after the pressure / gyro sensor is ready for operation through a predetermined correction or calibration, the seating data of each user can be collected.
[0080] Here, individual seating data can be performed for each of a plurality of users seated on a chair (300). For example, a user terminal (200) synchronized with Bluetooth (BL) can be identified, and seating data can be collected according to user classification or user group based on the user information thus identified.
[0081] When sitting data for multiple users is collected, the data cluster construction unit (122) of the AI learning unit (120) can construct a data cluster for each user based on the collected sitting data (S32). More specifically, the data cluster construction unit (122) can construct a data cluster for users of similar types (or types) based on the unique data possessed by each user, and by utilizing AI modeling here, the reason why the user adopts a peculiar posture, such as a leg-crossing posture or a hip-pushing posture, can be analyzed, and the user's posture pattern can be analyzed based on such common data.
[0082] When sitting data for multiple users is continuously collected and a data cluster for each user is built, the AI algorithm building unit (123) of the AI learning unit (120) can build an AI algorithm for more rapid and accurate posture correction of the user (S33).
[0083] For example, the AI algorithm constructed by the AI algorithm construction unit (123) can function as a program, software, etc. for correcting the user's posture, and can be the basis for providing a user-customized posture correction service in the form of an AI posture correction application to the user terminal (200), and can be an important basis for analyzing the user's sitting posture, correcting the posture, and providing content related to posture correction in the posture correction unit (130).
[0084] When an AI algorithm is constructed by the AI algorithm construction unit (123), the AI algorithm update unit (124) of the AI learning unit (120) can analyze the user's improvements by utilizing the constructed AI algorithm and update the related data and AI algorithm based on the analyzed improvements (S34, S35).
[0085] More specifically, the AI algorithm update unit (124) can analyze and identify improvements that the user needs to make by utilizing AI, and more specifically, by identifying the time the user sits on the chair (300) and the frequency of correct / incorrect postures, it can identify the correlation between posture and pain, and prepare necessary information for the user accordingly.
[0086] In addition, the AI algorithm update unit (124) can be additionally configured to update the AI algorithm by applying the user's posture improvement situation, additional considerations, etc. by utilizing machine learning technology, etc., and as mentioned above, important information according to changes in user information along with the update of the AI algorithm is built as big data and stored in a storage unit (150), etc., so that it can be utilized in medical institutions, etc. in the future.
[0087] In this way, when learning of user-specific sitting data, construction of data clusters, analysis of improvements, and updating of data and AI algorithms are performed in the AI learning unit (120), the posture correction unit (130) can provide a user-customized posture correction service based on the results of learning various user sitting data based on the updated AI algorithm and can provide various health / posture-related contents to the user terminal (200) (S36).
[0088] When a customized posture correction service and various health / posture-related contents are provided to the user, the user can check how much change has occurred over a set period of time, that is, the status of posture improvement (S37), and by repeatedly collecting and utilizing the changed posture information as sitting data (S31), the accuracy of analysis for each posture is increased through this customized posture correction service, and ultimately, the user can assist in improving their posture.
[0089] Through this type of customized posture correction service, AI algorithms can identify the characteristics of each posture that are difficult for humans to recognize, thereby implementing and providing more accurate posture correction. When users change their posture to the correct balance, they can reduce pain and discomfort caused by incorrect posture, thereby minimizing unnecessary costs and time.
[0090]
[0091] *In addition, it can help prevent secondary diseases such as cervical spine deformation, high blood pressure, and myocardial infarction through posture correction, and it can also perform the function of anatomically and ergonomically restoring posture habits in modern people who are naturally more likely to be exposed to incorrect postures as the time spent using electronic devices such as cell phones and laptops increases.
[0092] FIG. 4 (a) is an exemplary diagram for explaining the seat structure of a chair (300) according to one embodiment of the present invention, and FIG. 4 (b) is an exemplary diagram for explaining the back structure of a chair (300) according to one embodiment of the present invention.
[0093] As described above, the chair (300) utilized in learning the AI algorithm according to one embodiment of the present invention and implementing and providing a user-customized posture correction service accordingly can utilize the configuration of an ergonomically designed chair described in Republic of Korea Patent Registration No. 10-2136560 held by the applicant of the present invention.
[0094] FIG. 4 (a) exemplarily illustrates the configuration of a seat of a chair (300) according to one embodiment of the present invention, which is ergonomically designed. More specifically, the seat of the chair (300) according to one embodiment of the present invention may be implemented with four seat units (311, 312, 313, 314) each comprising a plurality of frames that are independently configured and implemented to be movable, a support portion configured to support the frames while being coupled to the frames at the lower side of the plurality of frames, and memory foam covering the plurality of frames. For example, independent movement of the plurality of frames can be implemented by combining the omnidirectional movement of the center ball within the recess and the fluid movement of the plurality of frames with respect to the spring group, which shows a significant difference from the seat of a conventional fixedly mounted general chair.
[0095] For example, the seat unit (311, 312, 313, 314) of the chair (300) according to one embodiment of the present invention can move independently so that the user's chin is lowered vertically to look straight ahead and the cervical spine is naturally formed into a C-curve.
[0096] Additionally, FIG. 4 (b) exemplarily illustrates a backrest configuration of a chair (300) according to one embodiment of the present invention, which is ergonomically designed. More specifically, the backrest of the chair (300) according to one embodiment of the present invention is provided with a plurality of backrest frames (for example, two) each of which is implemented in a hollow shape and is implemented to enable independent movement, and these two backrest frames are implemented to enable up-and-down or left-right movement.
[0097] By covering each of these climbing frames with climbing memory foam, two climbing units (321, 322) can be implemented, and like the seat of the chair (300), the climbing frame of the chair (300) can also implement fluid movement of multiple frames and independent movement accordingly.
[0098] In addition, although not explicitly shown in the drawing, an operating means, for example, a stepping motor, can be operated according to the length of the user's upper and lower body to store the position, thereby implementing the most accurate and comfortable posture correction according to the user's body type. For example, by the user-customized posture correction service based on the AI algorithm according to the present invention, turtle neck can be prevented by stabilizing the supraspinatus and supraspinatus capitis muscles, cervical spine curvature can be prevented by stabilizing the serratus anterior superior and serratus anterior inferior muscles, limitations of body type such as weight and height can be overcome, use by multiple users is possible based on user identification, and anyone can be guided to have a correct posture regardless of body type, gender, etc.
[0099] As exemplarily illustrated in FIG. 4, a seat and a backrest of a chair (300) according to one embodiment of the present invention are provided, and a predetermined sensor may be additionally provided in the chair (300) according to one embodiment of the present invention for a process such as constructing an AI algorithm and analyzing various postures of a user to provide a user-customized posture correction service, and an example of such a sensor arrangement configuration is illustrated in FIG. 5.
[0100] FIG. 5 is an exemplary diagram illustrating a gyro sensor (330) and a pressure sensor (340) attached to a chair (300) according to one embodiment of the present invention.
[0101] As exemplarily illustrated in FIG. 5, a chair (300) according to one embodiment of the present invention may be equipped with a gyro sensor (330) and a pressure sensor (340), and thus, it can be clearly contrasted with a conventional posture correction chair that has only a pressure sensor (340) that can only receive data vertically, and thus has a greatly reduced sensing accuracy.
[0102] More specifically, in order to obtain data on the user's posture that does not act perpendicularly to the pressure sensor (340), such as inclination data, a gyro sensor (330) may be additionally attached to the chair (300), more specifically to each of the seat units (311, 312, 313, 314) of the seat and each of the backrest units (321, 322) of the backrest, in addition to the pressure sensor (340), so that more accurate pressure values and inclination values can be detected for various postures that the user can take with respect to the chair (300).
[0103] For example, the gyro sensor (330) can obtain data that is difficult for the pressure sensor (340) to detect because it does not act perpendicularly to the pressure sensor (340) according to the user's posture by analyzing the angle or inclination, and the pressure sensor (340) can sense the distribution of pressure according to the user's posture, and the posture analysis unit (132) of the posture correction unit (130) can analyze the user's posture more precisely and accurately (for example, analyze the difference according to the posture the user takes) by using the pressure value by the pressure sensor (340) and the inclination value (or angle value) by the gyro sensor (330).
[0104] In addition, since existing posture correction chairs are not ergonomically designed and are usually configured by attaching a sensor pad inside a cushion, there are problems such as data loss due to detection data being transmitted when the film is crumpled or rolled, but the pressure sensor (340) according to one embodiment of the present invention is individually and independently attached to each of the four seat units (311, 312, 313, 314) and the two backrest units (321, 322), thereby minimizing data loss of the pressure sensor (340).
[0105] For reference, the pressure sensor (340) may be attached to each seat unit (311, 312, 313, 314) and each step unit (321, 322) as an individual sensor type, or may be attached in the form of a pad to the surface of each seat unit (311, 312, 313, 314) and each step unit (321, 322) to implement more improved sensor accuracy.
[0106] FIG. 6a is an exemplary diagram for explaining correct and incorrect postures prescribed when a user sits with his or her back leaning against the back of a chair according to one embodiment of the present invention, and FIG. 6b is an exemplary diagram for explaining correct and incorrect postures prescribed when a user sits with his or her back not leaning against the back of a chair according to one embodiment of the present invention.
[0107] As previously described, in order to implement a user-tailored posture correction service according to one embodiment of the present invention, various correct and incorrect postures can be defined in advance when constructing an AI algorithm, and examples of such correct and incorrect postures are illustrated in FIGS. 6A and 6B, respectively. For reference, in the present invention, the 'correct posture' can be defined as a posture in which the body's balance is properly maintained so as not to strain the joints, nerves, and muscles when the user sits on the chair (300).
[0108] For example, FIG. 6A illustrates an exemplary diagram for explaining the correct posture and incorrect posture that are defined when a user sits with his / her back against the back of a chair according to one embodiment of the present invention. The correct posture 1 can be defined as class 1 as a desirable posture that a user should assume when sitting with his / her back against the back of a chair, and for example, this correct posture 1 can be defined as a gyro sensor (330) facing the rearward center of both the seat and the back, and a pressure sensor (340) facing the mid-rear center in the case of the seat and facing the center in the case of the back.
[0109] In addition, when a user sits with his or her back against the back of the chair, many users mistakenly believe that this is a correct posture, but in reality, it is a wrong posture that puts a strain on the lower back, and wrong posture 1-1 can be defined as class 3. For example, this wrong posture 1-1 can be defined as the gyro sensor (330) being close to horizontal in the case of the seat and facing the center of the upper back in the case of the back, and the pressure sensor (340) facing the center in the case of the seat and facing the center of the upper back in the case of the back.
[0110] In addition, incorrect postures 1-2 that should not be taken when a user leans his or her back against the backrest of a chair can be defined as class 5, and for example, incorrect postures 1-2 can be defined as the gyro sensor (330) being directed toward the excessive forward center in the case of the seat and toward the upper back center in the case of the backrest, and the pressure sensor (340) being directed toward the forward center in the case of the seat and toward the upper back center in the case of the backrest.
[0111] Similarly, FIG. 6b illustrates an exemplary diagram for explaining the correct posture and incorrect posture defined when a user does not lean his / her back against the backrest of a chair according to one embodiment of the present invention. The correct posture 2, which is a desirable posture to be assumed when a user does not lean his / her back against the backrest of a chair, can be defined as class 2, and for example, this correct posture 2 can be defined as the gyro sensor (330) facing the forward center in the case of the seat and the pressure sensor (340) facing the forward center in the case of the seat.
[0112] In addition, many users mistakenly believe that they are in a good posture when they do not lean their back against the back of the chair, but in reality, this is a bad posture that puts a strain on the lower back, and bad posture 2-1 can be defined as class 4. For example, this bad posture 2-1 can be defined as the gyro sensor (330) being close to horizontal in the case of the seat and the pressure sensor (340) being oriented toward the center in the case of the seat.
[0113] In addition, a wrong posture 2-2 that should not be taken when the user does not lean his or her back against the backrest of the chair can be defined as class 6, and for example, this wrong posture 2-2 can be defined as a gyro sensor (330) facing an excessively forward center in the case of the seat and a pressure sensor (340) facing a forward center in the case of the seat.
[0114] For reference, in the example of FIG. 6, the inclination value by the gyro sensor (330) is described as the direction or distribution and the pressure value by the pressure sensor (340) is also described as the direction or distribution for a common and universal expression. However, in implementing a user-customized posture correction service according to one embodiment of the present invention, the range of the inclination value of the gyro sensor (330) specified for each user cluster and the range of the pressure value of the pressure sensor (340) specified for each user cluster can be derived, and analysis and judgment of correct posture and incorrect posture for each class can be preferably performed based on these inclination values and / or pressure values.
[0115] In addition, in FIG. 6, one correct posture and two incorrect postures are described for each posture, that is, for cases where the user leans against the backrest and cases where the user does not lean against the backrest, for a total of six postures (two correct postures and four incorrect postures), but this is only an example for easy understanding of the present invention, and it will be clear that the number of correct postures and incorrect postures defined in advance for correcting the user's posture may be different depending on various implementation examples or various embodiments, and more preferably, the precision of posture analysis may be further improved by increasing the number.
[0116] For example, the detection values (tilt values and pressure values) that are defined as correct posture or incorrect posture may differ depending on the user classification or grouping, and through such user classification, a more optimized and more accurate customized posture correction service may be provided to each user.
[0117] FIG. 7 is a conceptual diagram illustrating AI vision data implemented by multiple cameras according to one embodiment of the present invention.
[0118] According to one embodiment of the present invention, a pressure value collected by a pressure sensor (340) attached to a chair (300) and a tilt value collected by a gyro sensor (330) attached to the chair (300) are synchronized and stored with AI vision data implemented by a plurality of cameras (400), thereby enabling more accurate and precise analysis of various postures that a user can take. An example of an AI vision system implemented with such a plurality of cameras (400) is exemplarily illustrated in FIG. 7.
[0119] By utilizing an AI motion system as exemplarily illustrated in FIG. 7, the user's correct posture and incorrect posture can be distinguished more accurately, and for example, the accuracy can be significantly improved when implementing the six postures (i.e., two correct postures and four incorrect postures) of the user visualized through vision as sensor data expressed in numbers. For example, computer vision can be measured with multiple cameras (400), for example, up to 12 cameras (400), and a skeleton, joint point values, etc. can be generated for each posture of the user (for example, based on HPE (Human Pose Estimation) technology), and the tilt values and pressure values obtained for each of the user's various postures can be accurately synchronized by having up to 12 cameras (400) film the user's sitting from all directions of 360 degrees.
[0120] In other words, by analyzing postures according to the user's posture distribution, analyzing each user's body data, analyzing motion data according to real-time posture changes, and analyzing specific seat and back angles for each posture, the accuracy of the AI posture analysis algorithm can be significantly improved through the combination of real-time vision data and sensor integration data.
[0121] FIG. 8 illustrates an exemplary UI service screen of an AI posture correction application implemented to a user according to one embodiment of the present invention.
[0122] According to one embodiment of the present invention, a user-customized posture correction service as a type of so-called AI posture correction application can be provided to a user through a user terminal (200), and an example of such a user interface (UI) is illustrated in FIG. 8. As illustrated, through the user-customized posture correction service provided through the AI posture correction application, each user can receive a score for correct posture, various analysis results, advice for improving posture, statistics, etc.
[0123] For example, through real-time posture analysis of the user, relevant posture information can be provided to enable the user to maintain the correct posture, more intensive and quick feedback correction training can be provided for a set period of time through a training mode, daily / weekly / monthly comparison results and growth rates of correct and incorrect postures can be provided, and customized medical information, health content, etc. can be provided to the user terminal (200).
[0124] For example, users who have shown excellent results with posture correction may be provided with a certain reward (e.g., points, savings, etc.), thereby more actively encouraging user interest and participation in the customized posture correction service.
[0125]
[0126] As described above, according to the posture correction method and device thereof according to one embodiment of the present invention, users can receive feedback on chair posture correction more quickly and thereby improve their quality of life.
[0127] In addition, according to a posture correction method and device thereof according to one embodiment of the present invention, it is possible to assist a user who is in an incorrect posture to accurately correct the posture by defining a correct posture that the user should pursue and also defining an incorrect posture similar to the correct posture.
[0128] In addition, according to the posture correction method and device thereof according to one embodiment of the present invention, data on specific postures that cannot be determined by a pressure sensor alone can be determined by using a gyro sensor, thereby analyzing differences according to various chair sitting postures of the user, and thereby providing more customized and accurate posture correction information to the user.
[0129] In addition, according to the posture correction method and device thereof according to one embodiment of the present invention, the change in the user's posture is confirmed according to the posture correction content provided based on the constructed AI algorithm for posture correction, and the data of such posture change is reflected and updated again in the AI algorithm, thereby further improving the accuracy of the analysis by posture.
[0130] In addition, according to the posture correction method and device thereof according to one embodiment of the present invention, the accuracy of the AI posture analysis algorithm can be further improved by utilizing a plurality of camera-based AI motion systems to distinguish between correct and incorrect postures.
[0131]
[0132] Meanwhile, the various embodiments described herein may be implemented by hardware, middleware, microcode, software, and / or a combination thereof. For example, the various embodiments may be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, other electronic units designed to perform the functions presented herein, or a combination thereof.
[0133] Additionally, for example, various embodiments may be embodied or encoded in a computer-readable medium containing instructions. Instructions embodied or encoded in the computer-readable medium may cause a programmable processor or other processor to perform a method when the instructions are executed, for example. A computer-readable medium includes a computer storage medium, which may be any available medium that can be accessed by a computer. For example, such a computer-readable medium may include a RAM, a ROM, an EEPROM, a CD-ROM or other optical disk storage medium, a magnetic disk storage medium, or other magnetic storage devices.
[0134] Such hardware, software, firmware, etc. may be implemented within the same device or within separate devices to support the various operations and functions described herein. Additionally, components, units, modules, components, etc. described as “units” in the present invention may be implemented together or individually as separate but interoperable logic devices. The depiction of different features for modules, units, etc. is intended to highlight different functional embodiments and does not necessarily imply that they must be realized by separate hardware or software components. Rather, the functionality associated with one or more modules or units may be performed by separate hardware or software components, or integrated into common or separate hardware or software components.
[0135] Although operations are depicted in the drawings in a specific order, this should not be construed as requiring that these operations be performed in the specific order depicted, or in any sequential order, or that all depicted operations be performed to achieve the desired results. In certain circumstances, multitasking and parallel processing may be advantageous. Furthermore, the distinction between the various components in the embodiments described above should not be construed as requiring such distinction in all embodiments, and it should be understood that the components depicted may generally be integrated together into a single software product or packaged into multiple software products.
[0136] As described above, the best practice embodiments have been disclosed in the drawings and specifications. While specific terminology has been used herein, it is solely for the purpose of describing the present invention and is not intended to limit the scope of the invention as defined in the claims. Therefore, those skilled in the art will understand that various modifications and equivalent embodiments are possible. Therefore, the true technical protection scope of the present invention should be determined by the technical spirit of the appended claims.
[0137] 100: Posture Correction Device
[0138] 110: Control unit
[0139] 120: AI Learning Department
[0140] 121: Seating Data Collection Unit
[0141] 122: Data Cluster Construction Unit
[0142] 123: AI Algorithm Building Unit
[0143] 124: AI Algorithm Update Unit
[0144] 130: Posture Correction Department
[0145] 131: Real-time seating data receiving unit
[0146] 132: Posture Analysis Unit
[0147] 133: Content Provider Unit
[0148] 140: Communications Department
[0149] 150: Storage
[0150] 200: User terminal
[0151] 300: Chair
[0152] 311, 312, 313, 314: Seat units
[0153] 321, 322: Climbing Unit
[0154] 330: Gyro sensor
[0155] 340: Pressure sensor
[0156] 400: Camera
[0157] 10: Posture Correction System
Claims
1. As a method of posture correction, A step of collecting user sitting data on a chair; A step of constructing a user-specific data cluster based on the above-collected seating data; A step of building an AI algorithm for posture correction based on the above-mentioned data cluster; and A step of providing information on posture correction based on the above-mentioned AI algorithm and real-time sitting data, How to correct your posture.
2. In paragraph 1, A step of analyzing the user's improvements by utilizing the above-mentioned AI algorithm; and Further comprising a step of updating the AI algorithm based on the above analyzed improvements. How to correct your posture.
3. In paragraph 1, The step of collecting user sitting data on the above chair includes the step of collecting pressure values and inclination values from a pressure sensor and a gyro sensor attached to the chair. How to correct your posture.
4. In paragraph 3, The step of collecting the user's sitting data on the above chair further includes the step of synchronizing the collected pressure values and inclination values with AI vision data implemented by multiple cameras. How to correct your posture.
5. A computer-readable recording medium that is combined with a computer as hardware and is stored so as to perform the method according to paragraph 1. Computer program.
6. As a posture correction device (100), A sitting data collection unit (121) configured to collect a user's sitting data on a chair (300); A data cluster construction unit (122) configured to construct a user-specific data cluster based on the above-collected seating data; An AI algorithm construction unit (123) configured to construct an AI algorithm for posture correction based on the above-mentioned constructed data cluster; and A posture analysis unit (132) configured to provide information on posture correction based on the above-mentioned AI algorithm and real-time sitting data, Posture correction device (100).
7. In paragraph 6, Further comprising an AI algorithm update unit (124) configured to analyze the user's improvements by utilizing the constructed AI algorithm and update the AI algorithm based on the analyzed improvements. Posture correction device (100).
8. In paragraph 6, The above seating data collection unit (121) is additionally configured to collect pressure values and inclination values from a pressure sensor (340) and a gyro sensor (330) attached to the chair (300). Posture correction device (100).
9. In paragraph 8, The above seating data collection unit (121) is further configured to synchronize the collected pressure values and slope values with AI vision data implemented by multiple cameras. Posture correction device (100).
10. Posture correction device (100) according to Article 6; and A user terminal (200) that is communicatively coupled with the posture correction device (100) is included. Posture correction system (10).
Citation Information
Patent Citations
A seat board for chair, and a chair comprising the same
KR102136560B1
Apparatus and method of measuring the probability of muscular skeletal disease
KR1020160076488A
Method, Apparatus and System for Displaying User Interface for Translating Based on Web
KR1020240053712A
Customized posture correction cusion, customized posture correction system, and method thereof
KR102268667B1
Method for producing stainless container
KR102284465B1
