System and method for providing user-customized service based on at least one of musculoskeletal system and nervous system

Abstract

To provide a system and method for providing a user-customized service based on at least one of a musculoskeletal system and a nervous system.SOLUTION: The method includes receiving state information of a user, determining one or more musculoskeletal examination items based on the received state information of the user, outputting the determined one or more musculoskeletal examination items, receiving one or more images including at least one of a posture or a motion of the user with respect to each of the output one or more musculoskeletal examination items, receiving meta information about an examination device that captures the one or more images, and performing, using a first machine learning model, the method includes analyzing state information, one or more images, and meta information of a user and outputting a customized result for the user.SELECTED DRAWING: Figure 15

Description

[Technical Field]

[0001] The present invention relates to a system and method for providing a user-customized service based on at least one of a user's musculoskeletal system or nervous system, and more specifically, to a system and method for providing a service that designs test items and sequences using user condition information, quantitatively / qualitatively evaluates the user's musculoskeletal function, and provides a user-customized result based on the results, and that performs customized management for the user using user condition information that is updated as the service is continuously used. [Background technology]

[0002] Musculoskeletal disorders are a core factor in late-onset diseases, and their recurrence rate is high. Their incidence is continually increasing, not only among the elderly but also among all age groups. Approximately 80% of these musculoskeletal disorders are classified as lifestyle diseases that require prevention and management in the wellness field, but the reality is that there is a lack of standardized screening, result interpretation, and management solutions.

[0003] Existing musculoskeletal or wellness services generally collect standardized physical information from clients and provide standardized interpretations and services based on that information. Such conventional musculoskeletal function tests are limited to quantitative functional assessments, and often exclude qualitative functional assessments that are closely related to the nervous system, such as incorrect posture and muscle imbalances, balance and movement coordination, and speed. This often results in a discrepancy between the overall assessment results and the actual injury risk.

[0004] Generally, users lack a deep understanding of musculoskeletal functions, and tend to focus only on the quantitative functions of exercise without fully understanding the qualitative musculoskeletal functions closely related to the nervous system. This can lead to the perpetuation of incorrect exercise patterns and lifestyle habits, which can actually result in poor health. For example, the continued learning of incorrect posture and joint movement patterns and an imbalanced motor nervous system can accumulate uneven loads on specific muscles and joints, leading to long-term, delayed damage and injury. Such issues point to the limitations of existing services, which lack a personalized approach.

[0005] A user's individual condition is defined by various factors, such as gender, age, region, occupation, consumption level, physical and mental health status, goals and objectives, interests, willpower, spare time, lifestyle patterns, nutritional status, sleep status, and desired coaching style and method. Therefore, standardized musculoskeletal function test items and fixed interpretations of results often do not match the user's initial motivation for participating in and continuing to use health services. In addition, many users have difficulty interpreting specialized musculoskeletal function information, indicating a high demand for customized information.

[0006] Most existing personalized health services focus on customized management services that utilize user-input information based on limited and standardized user health information, with test items, order, and test result interpretations fixed regardless of the user's characteristics or condition. Such service designs often do not match the motivational factors for inducing users' initial participation (service intake) and ongoing participation (service retention). Users desire detailed information on their health status and needs, and existing services that do not meet user needs for personalized management services based on customized tests and result interpretations result in low user satisfaction.

[0007] The above-mentioned background art is what the inventors possessed or learned in the process of deriving the contents of the disclosure of this application, and is not necessarily publicly known art that was made public to the general public prior to this application. Summary of the Invention [Problem to be solved by the invention]

[0008] The problem to be solved by the present invention is to provide a method and apparatus (system) for providing user-customized services based on at least one of the musculoskeletal system and the nervous system. [Means for solving the problem]

[0009] The present invention may be embodied in various ways, including as a method, an apparatus (system), a computer program stored on a computer-readable recording medium, and / or a computer-readable medium having a computer program stored thereon.

[0010] According to an embodiment of the present disclosure, a method for providing a user-customized service based on at least one of a musculoskeletal system or a nervous system may be performed by at least one processor. In one embodiment, the method for providing a user-customized service based on at least one of a musculoskeletal system or a nervous system may include receiving status information related to a user, determining one or more musculoskeletal test items based on the received status information related to the user, outputting the determined one or more musculoskeletal test items, receiving one or more images including at least one of a posture or a movement of the user for each of the output one or more musculoskeletal test items, receiving meta-information related to testing equipment capturing the one or more images, and analyzing the status information related to the user, the one or more images, and the meta-information using a first machine learning model, and outputting a customized result for the user.

[0011] In one embodiment, the step of outputting a customized result for the user may include analyzing the received one or more images and the meta-information to generate a result related to balance of at least one of the user's musculoskeletal system or nervous system, and using the first machine learning model to generate a customized test result for the user based on the result related to balance of at least one of the user's musculoskeletal system or nervous system and the received user-related condition information.

[0012] In one embodiment, determining the one or more musculoskeletal test items may include determining a plurality of musculoskeletal test items and an order of the plurality of musculoskeletal test items based on condition information related to the user.

[0013] In one embodiment, the condition information related to the user includes information related to the user's gender and age, and the method further includes determining a biological age related to the user based on balance-related results of at least one of the user's musculoskeletal system or nervous system and the user's gender and age information, and the step of determining a biological age related to the user based on balance-related results of at least one of the user's musculoskeletal system or nervous system and the user's gender and age information may include using the first machine learning model to generate customized test results for the user based on the biological age related to the user, balance-related results of at least one of the user's musculoskeletal system or nervous system, and the condition information related to the user.

[0014] In one embodiment, the customized test result for the user may include interest and desire information related to the user and function prediction information based on the interest and desire information.

[0015] In one embodiment, the step of generating customized test results for the user using the first machine learning model based on the biological age of the user, balance-related results for at least one of the user's musculoskeletal system or nervous system, and status information for the user may include the steps of determining elements and exposure priorities to be used in the customized test results based on interest and desire information for the user, determining user-customized function prediction information based on the interest and desire information for the user and the status of at least one of the user's musculoskeletal system or nervous system, and generating the customized function prediction information for the user as a customized result for the user using the determined elements and the exposure priorities.

[0016] In one embodiment, the method may further include generating stage-specific goal information and customized coaching information for the user based on function prediction information based on the interest and desire information and status information related to the user using a second machine learning model.

[0017] In one embodiment, the method further includes receiving step-by-step goal achievement information achieved by the user and the user-customized coaching performance information, and generating the step-by-step goal information and the customized coaching information for the user may include regenerating the step-by-step goal information and the customized coaching information for the user based on the step-by-step goal achievement information achieved by the user, the user-customized coaching performance information, function prediction information based on the interest and desire information, and status information related to the user, using the second machine learning model.

[0018] In one embodiment, receiving status information related to the user may include receiving status information related to the user updated based on at least one of step-by-step goal achievement information achieved by the user, customized coaching performance information for the user, interest and desire information related to the user, or function prediction information based on the interest and desire information.

[0019] In one embodiment, the state information related to the user may include fixed information related to the user and change information related to the user. [Effects of the Invention]

[0020] According to one embodiment, a system and method for providing a user-customized service based on at least one of the musculoskeletal system and the nervous system utilizes accumulated user status information to evaluate the user's musculoskeletal function and provides a user-customized result based on the evaluation. This has the advantage of enabling the user to clearly and easily grasp the user's physical weaknesses and select information of interest to automate the intake and continuous management of health services.

[0021] In addition, while conventional approaches have focused only on quantitative assessment of musculoskeletal function, a system and method for providing a user-customized service based on at least one of the musculoskeletal system and the nervous system according to one embodiment utilizes user status information to simultaneously perform not only quantitative functional assessments such as the number of repetitions of the user's actions and / or movements and the distance traveled, but also qualitative functional assessments that are highly related to the nervous system, such as postural alignment, muscle imbalances, and compensatory movements, thereby providing an advantage in that the user's musculoskeletal function can be more comprehensively assessed.

[0022] In addition, conventional musculoskeletal function tests separately test each item (e.g., flexibility by region, muscle strength by region, stamina by region, balance, posture, etc.), and the information is not integrated, so only partial interpretations of musculoskeletal function related to a single region and element are possible, which has complex correlations. On the other hand, a system and method for providing a user-customized service based on at least one of the musculoskeletal system and nervous system according to one embodiment simultaneously performs quantitative and qualitative assessments of the user's musculoskeletal function, and can identify and interpret weaknesses in the body's musculoskeletal function, the epicenter of underlying problems, and the correlation between weak musculoskeletal function regions and motor nervous system test elements, thereby having the advantage of being able to design clear solutions to identify and resolve physical function weaknesses and problems.

[0023] In addition, the system and method for providing a user-customized service based on at least one of the musculoskeletal system and the nervous system according to one embodiment has the advantage that, unlike conventional musculoskeletal function tests that can test each part and function individually, a comprehensive user-customized test can be designed that combines the test parts, items, and order required by the user, thereby identifying repetitive muscle and nerve balance and imbalance patterns that the user cannot recognize, and performing an integrated analysis and interpretation.

[0024] In addition, the system and method for providing a user-customized service based on at least one of the musculoskeletal system and the nervous system according to one embodiment has the advantage of improving the expertise and usability in unmanned service design by comprehensively configuring the types and order of musculoskeletal function assessment items, thereby dramatically reducing the required time.

[0025] In addition, the system and method for providing a user-customized service based on at least one of the musculoskeletal system and the nervous system according to the embodiment has the advantage of being able to induce the user to continuously participate in health services by setting detailed goals for each stage to achieve a final goal corresponding to the user's interests and desires, and guiding and coaching the user to achieve the step-by-step goal information.

[0026] The effects of the system and method for providing user-customized services based on at least one of the musculoskeletal system or the nervous system according to the embodiments are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those of ordinary skill in the art from the description below. [Brief explanation of the drawings]

[0027] The following drawings attached to this specification illustrate preferred embodiments of the present disclosure and, together with the detailed description of the invention, serve to further understand the technical concepts of the present disclosure, and the present disclosure should not be interpreted as being limited solely to the matters shown in such drawings. [Figure 1] 1 is a diagram illustrating a process of generating musculoskeletal-based user-customized results through an information processing system according to an embodiment of the present disclosure. [Figure 2] 1 is a schematic diagram illustrating a configuration in which an information processing system is communicatively coupled to a plurality of testing devices to provide search results according to one embodiment of the present disclosure. [Figure 3] 1 is a block diagram showing an internal configuration of an inspection device and an information processing system according to an embodiment of the present disclosure; [Figure 4] 1 is a diagram illustrating user status information according to an embodiment of the present disclosure. [Figure 5] 10 is a diagram illustrating a process of deriving a user-customized test item through an information processing system according to an embodiment of the present disclosure. [Figure 6] 1 is a diagram illustrating a process of deriving balance of at least one of the musculoskeletal system and the nervous system through an information processing system according to an embodiment of the present disclosure. [Figure 7] 1 is a diagram illustrating a process of generating musculoskeletal-based user-customized results through a first machine learning model according to an embodiment of the present disclosure. [Figure 8] 1 is a diagram illustrating a process of generating a musculoskeletal-based user-customized result taking biological age into consideration through a first machine learning model according to an embodiment of the present disclosure. [Figure 9] 1 is a diagram illustrating musculoskeletal-based user-customized results according to one embodiment of the present disclosure. [Figure 10] 1 is a flowchart illustrating a method for generating customized results for a user based on interest and desire information related to the user according to one embodiment of the present disclosure. [Figure 11] 1 is a diagram illustrating a machine learning model according to one embodiment of the present disclosure. [Figure 12] 10 is a diagram illustrating a process of generating user stage-specific goal information and customized coaching information through a second machine learning model according to an embodiment of the present disclosure. [Figure 13] 10 is a diagram illustrating a process of regenerating user stage-specific goal information and customized coaching information through a second machine learning model according to an embodiment of the present disclosure. [Figure 14] 1 is a diagram illustrating a user interface (UI) for providing a skeleton-based user-customized service according to an embodiment of the present disclosure. [Figure 15] 1 is a flowchart illustrating a method for providing user-customized services based on at least one of a musculoskeletal system or a nervous system according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0028] The various embodiments described herein are exemplified for the purpose of clearly explaining the technical idea of ​​the present disclosure and are not intended to limit the technical idea to specific embodiments. The technical idea of ​​the present disclosure includes various modifications, equivalents, alternatives, and embodiments that are selectively combined from all or part of the embodiments described herein. Furthermore, the scope of the technical idea of ​​the present disclosure is not limited to the various embodiments presented below and the specific descriptions thereof.

[0029] Terms used herein, including technical or scientific terms, may have the meaning commonly understood by one of ordinary skill in the art to which this disclosure belongs, unless otherwise defined.

[0030] As used herein, terms such as "include," "can include," "comprise," "can comprise," "have," and "can have" imply the presence of the feature in question (e.g., a function, operation, or component) and do not exclude the presence of other additional features. That is, such terms should be understood as open-ended terms that include the possibility of including a second embodiment.

[0031] In this specification, the singular form includes the plural form unless the context clearly dictates otherwise. Furthermore, the plural form includes the singular form unless the context clearly dictates otherwise. Throughout the specification, when a part includes a certain element, this does not exclude other elements, and means that other elements may also be included, unless specifically stated to the contrary.

[0032] Furthermore, the terms "module" or "module" used in this specification refer to a software or hardware component, and a "module" or "module" may perform any function. However, the term "module" or "module" is not limited to software or hardware. A "module" or "module" may be configured to reside on an addressable storage medium and to execute one or more processors. Thus, as an example, a "module" or "module" may include components such as software components, object-oriented software components, class components, and task components, as well as at least one of processes, functions, attributes, procedures, subroutines, program code segments, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The components and functions provided by a "module" or "module" may be combined into fewer components and "modules" or "modules," or may be further separated into additional components and "modules" or "modules."

[0033] According to one embodiment of the present disclosure, a "module" or "unit" may be embodied as a processor and memory. "Processor" should be broadly interpreted to include a general-purpose processor, a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a controller, a microcontroller, a state machine, a graphics processing unit (GPU), a neural network processing unit (NPU, TPU, VPU, etc.), etc. In some environments, "processor" may refer to an application-specific semiconductor (ASIC), a programmable logic device (PLD), a field-programmable gate array (FPGA), etc. "Processor" may refer to a combination of processing devices, such as, for example, a combination of a DSP and a microprocessor, a combination of multiple microprocessors, a combination of one or more microprocessors in conjunction with a DSP core, or any other such configuration. Additionally, "memory" should be broadly interpreted to include any electronic component capable of storing electronic information. "Memory" may refer to various types of processor-readable media, such as random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), programmable read-only memory (PROM), erasable-programmable read-only memory (EPROM), electrically erasable PROM (EEPROM), flash memory, magnetic or optical data storage devices, and registers. Memory is said to be in electronic communication with a processor if the processor can read and write information from and to the memory. Memory that is integrated into a processor is in electronic communication with the processor.

[0034] As used herein, unless the context indicates otherwise, the terms "first," "second," "initial," "second," and the like, when referring to multiple similar objects, are used to distinguish one object from another and do not limit the order or importance of those objects.

[0035] As used herein, phrases such as "A, B, and C," "A, B, or C," "A, B, and / or C," or "at least one of A, B, and C," "at least one of A, B, or C," "at least one of A, B, and / or C," "at least one selected from A, B, and C," "at least one selected from A, B, or C," and "at least one selected from A, B, and / or C" may refer to each listed item or all possible combinations of listed items. For example, "at least one selected from A and B" may refer to any of (1) A, (2) at least one of A, (3) B, (4) at least one of B, (5) at least one of A and at least one of B, (6) at least one of A and B, (7) at least one of B and A, or (8) A and B.

[0036] As used herein, the phrase "based on" is used to describe one or more factors that influence the decision, act of judgment, or behavior described in the phrase or sentence in which it appears, and does not exclude additional factors that influence the decision, act of judgment, or behavior.

[0037] As used in this specification, the expression that a component (e.g., a first component) is "coupled" or "connected" to another component (e.g., a second component) may mean not only that the component is directly coupled or connected to the other component, but also that the component is coupled or connected via a new component (e.g., a third component).

[0038] As used herein, the expression "configured to" may have meanings such as "set to," "capable of," "modified to," "made to," "capable of," etc., depending on the context. The expression is not limited to the meaning of "specially designed in hardware." For example, a processor configured to perform a specific operation may refer to a generic-purpose processor that can perform the specific operation by executing software.

[0039] Hereinafter, various embodiments of the present disclosure will be described with reference to the accompanying drawings. In the accompanying drawings and descriptions relating to the drawings, identical or substantially equivalent components may be designated by the same reference numerals. In addition, in the following description of various embodiments, duplicated descriptions of identical or corresponding components may be omitted, but this does not mean that the components are not included in the embodiments.

[0040] FIG. 1 is a diagram illustrating a process of generating user-customized results based on musculoskeletal foundations through an information processing system according to an embodiment of the present disclosure.

[0041] 1, in one embodiment, the information processing system 230 may provide a user-customized service based on at least one of the musculoskeletal system and the nervous system, where the user-customized service may refer to a user-customized examination, interpretation, and / or management service.

[0042] In one embodiment, the information processing system 230 may generate musculoskeletal-based user-customized results 140 using the user state information 110, one or more user images 120, and meta information 130 of the examination equipment that captured the images.

[0043] Here, the user status information 110 may refer to information related to the user's status, including, but not limited to, the user's gender and age information, medical information, disease information, lifestyle information, health information, and preference information.

[0044] Also, here, the one or more user images 120 may refer to one or more images including at least one of the user's posture or movement for each of one or more musculoskeletal test items.

[0045] In this case, the one or more musculoskeletal test items may be determined based on the user state information 110, and may be determined based on rules or a machine learning model. For example, the information processing system 230 may determine one or more musculoskeletal test items based on the user state information 110, guide the user to assume a specific posture or perform a specific movement based on the determined one or more musculoskeletal test items, and acquire the user image 120 generated by capturing or photographing a scene in which the user assumes a specific posture or performs a specific movement. For example, the information processing system 230 may receive a 2D and / or 3D image of the user as the user image 120 and extract information related to body joints and / or muscles from the user image 120 using a segmentation model or the like. Based on the extracted information, the posture and / or movement of the user in the user image 120 may be analyzed.

[0046] Also, here, the meta information 130 of the inspection equipment capturing the image may refer to detailed information, characteristics, or related data about the inspection equipment, such as, but not limited to, the performance of the inspection equipment capturing the image, information about the environment when the image was captured, etc.

[0047] Also, here, the user customized result 140 may refer to a result derived by analyzing the user state information 110, one or more images 120, and meta information 130. For example, the user customized result 140 may include, but is not limited to, the user's biological age, interest and desire information, functional prediction information, and customized result interpretation. Here, the user's biological age may refer to an index generated based on at least one of the functional status of at least one of the user's musculoskeletal system or nervous system, body composition, or health, function, and physical fitness.

[0048] FIG. 2 is a schematic diagram illustrating a configuration in which an information processing system is communicatively coupled to a plurality of testing devices to provide search results according to one embodiment of the present disclosure.

[0049] 2, a plurality of testing devices 210_1, 210_2, 210_3, and 210_4 may be connected to an information processing system 230 that can provide a user-customized service (e.g., a user-customized test, interpretation, and / or management service) based on at least one of the musculoskeletal system and the nervous system via a network 220. Here, the plurality of testing devices 210_1, 210_2, 210_3, and 210_4 may include a user terminal that receives the user-customized service based on at least one of the musculoskeletal system and the nervous system. Here, the network 220 may be connected to the information processing system 230 not only for communication using a communication network (e.g., a mobile communication network, a wired Internet, a wireless Internet, a broadcasting network, a satellite network, etc.) that may be included in the network 220, but also for internal communication between the plurality of testing devices 210_1, 210_2, 210_3, and 210_4.

[0050] In one embodiment, the information processing system 230 may include one or more server devices and / or databases, or one or more distributed computing devices and / or distributed databases in a cloud computing service infrastructure, that can store, provide, and execute computer-executable programs (e.g., downloadable applications) and data related to user-customized services based on at least one of the musculoskeletal system or the nervous system.

[0051] The user-customized service based on at least one of the musculoskeletal system and the nervous system provided by the information processing system 230 may be provided to a user via a user-customized service application, a web browser, a web browser extension program, etc., based on at least one of the musculoskeletal system and the nervous system provided in each of the plurality of testing equipments 210_1, 210_2, 210_3, and 210_4. For example, the information processing system 230 may provide information corresponding to a customized result request received from the testing equipment 210_1, 210_2, 210_3, and 210_4 via a user-customized service application, etc., based on at least one of the musculoskeletal system and the nervous system, or perform a corresponding process.

[0052] The plurality of test equipments 210_1, 210_2, 210_3, 210_4 may communicate with an information processing system 230 via a network 220.

[0053] The network 220 may be configured to enable communication between the plurality of test equipments 210_1, 210_2, 210_3, and 210_4 and the information processing system 230. Depending on the installation environment, the network 220 may be configured as a wired network such as Ethernet, a wired home network (power line communication), a telephone line communication device, and RS-serial communication, a mobile communication network, a wireless network such as WLAN (Wireless LAN), Wi-Fi, Bluetooth, and ZigBee, or a combination thereof. The communication method is not limited to a communication method using a communication network that the network 220 may include (e.g., a mobile communication network, a wired Internet, a wireless Internet, a broadcast network, a satellite network, etc.), as well as short-range wireless communication between the test equipments 210_1, 210_2, 210_3, and 210_4, and internal communication among the test equipments 210_1, 210_2, 210_3, and 210_4.

[0054] 2, a mobile phone terminal 210_1, a tablet terminal 210_2, a PC terminal 210_3, and a kiosk 210_4 are illustrated as examples of test equipment, but are not limited thereto. The test equipment 210_1, 210_2, 210_3, and 210_4 may be any computer device capable of wired and / or wireless communication, and capable of being provided with and running a user-customized service application or a web browser based on at least one of the musculoskeletal system and the nervous system. For example, the test equipment may include an AI speaker, a smartphone, a mobile phone, a navigation system, a computer, a laptop, a digital broadcasting terminal, a PDA (Personal Digital Assistant), a PMP (Portable Multimedia Player), a tablet PC, a game console, a wearable device, an IoT (Internet of Things) device, a VR (Virtual Reality) device, an AR (Augmented Reality) device, a set-top box, etc.

[0055] Also, although FIG. 2 illustrates four pieces of testing equipment 210_1, 210_2, 210_3, and 210_4 communicating with the information processing system 230 via the network 220, this is not limiting, and a different number of testing equipments may be configured to communicate with the information processing system 230 via the network 220.

[0056] FIG. 2 exemplarily illustrates a configuration in which a user's request is transmitted to the information processing system 230 via the inspection equipment 210_1, 210_2, 210_3, and 210_4, but is not limited thereto. The user's request may be provided to the information processing system 230 via an input device associated with the information processing system 230 without passing through the inspection equipment 210_1, 210_2, 210_3, and 210_4, and the result of processing the user's request may be provided to the user via an output device (e.g., a display) associated with the information processing system 230.

[0057] 2 illustrates the testing equipment 210_1, 210_2, 210_3, and 210_4 receiving a user-customized service based on at least one of the musculoskeletal system and the nervous system from the information processing system 230, but is not limited thereto. For example, a user-customized service based on at least one of the musculoskeletal system and the nervous system may be provided through a user-customized service providing program / application provided in the testing equipment 210_1, 210_2, 210_3, and 210_4 without communication with the information processing system 230. Furthermore, the information processing system 230 is illustrated as a single device, but is not limited thereto, and the information processing system 230 may be configured with multiple devices.

[0058] Although FIG. 2 illustrates a configuration in which the inspection equipments 210_1, 210_2, 210_3, and 210_4 are connected to the information processing system 230 via a network, the network can be configured not only as a cloud-based network but also via internal communication within the equipment.

[0059] FIG. 3 is a block diagram showing the internal configuration of an inspection device and an information processing system according to an embodiment of the present disclosure.

[0060] Referring to FIG. 3, the testing equipment 210 refers to any computer device capable of executing applications, a web browser, etc. and capable of wired / wireless communication. For example, the testing equipment 210 in FIG. 2 may include a mobile phone terminal 210_1, a tablet terminal 210_2, a PC terminal 210_3, and a kiosk 210_4.

[0061] 3, the test equipment 210 may include a memory 312, a processor 314, a communication module 316, and an input / output interface 318. Similarly, the information processing system 230 may include a memory 332, a processor 334, a communication module 336, and an input / output interface 338.

[0062] 3, the inspection equipment 210 and the information processing system 230 may be configured to communicate information and / or data via a network 220 using their respective communication modules 316, 336. For example, the network 220 may include an internal communication network processed on-premise within the equipment as well as an external communication network such as the cloud. Furthermore, the input / output device 320 may be configured to input information and / or data to the inspection equipment 210 via an input / output interface 318 or to output information and / or data generated by the inspection equipment 210.

[0063] The memories 312 and 332 may include any non-transitory computer-readable recording medium. According to one embodiment, the memories 312 and 332 may include a permanent mass storage device such as a read only memory (ROM), a disk drive, a solid state drive (SSD), or a flash memory. As another example, a non-transitory mass storage device such as a ROM, an SSD, a flash memory, or a disk drive may be included in the testing equipment 210 or the information processing system 230 as a separate permanent storage device distinct from the memory. The memories 312 and 332 may also store an operating system and at least one program code.

[0064] Such software components may be loaded from a computer-readable recording medium separate from the memories 312, 332. Such separate computer-readable recording medium may include a recording medium directly connectable to the testing equipment 210 and the information processing system 230, such as a floppy drive, a disk, a tape, a DVD / CD-ROM drive, or a memory card. As another example, the software components may be loaded into the memories 312, 332 via the communication modules 316, 336, which are not computer-readable recording media. For example, at least one program may be loaded into the memories 312, 332 based on a computer program provided by a developer or a file distribution system that distributes application installation files over the network 220.

[0065] The processors 314, 334 may be configured to process computer program instructions by performing basic arithmetic, logic, and input / output operations. The instructions may be provided to the processors 314, 334 by the memory 312, 332 or the communication modules 316, 336. For example, the processors 314, 334 may be configured to execute instructions received from program code stored in a storage device, such as the memory 312, 332.

[0066] The communication modules 316 and 336 may provide a configuration or function for the testing equipment 210 and the information processing system 230 to communicate with each other via the network 220, and may also provide a configuration or function for the testing equipment 210 and / or the information processing system 230 to communicate with other testing equipment or other systems (e.g., a separate cloud system). For example, a request or data (e.g., a request for providing customized results) generated by the processor 314 of the testing equipment 210 using program code stored in a storage device such as the memory 312 may be transmitted to the information processing system 230 via the network 220 under the control of the communication module 316. Conversely, a control signal or command provided under the control of the processor 334 of the information processing system 230 may be received by the testing equipment 210 via the communication module 316 of the testing equipment 210 via the communication module 336 and the network 220.

[0067] The input / output interface 318 also serves as a means for interfacing with the input / output device 320. For example, the input device may include a camera including an audio sensor and / or an image sensor, various sensors such as a lidar sensor and a 3D sensor, a keyboard, a microphone, a mouse, etc., and the output device may include a display, a speaker, a haptic feedback device, etc. As another example, the input / output interface 318 may also serve as a means for interfacing with a device that integrates input and output functions, such as a touchscreen. For example, when the processor 314 of the inspection equipment 210 processes instructions from a computer program loaded in the memory 312, a service screen configured using information and / or data provided by the information processing system 230 or other inspection equipment may be displayed on the display via the input / output interface 318. While FIG. 3 illustrates the input / output device 320 as not being included in the inspection equipment 210, the input / output device 320 is not limited thereto and may be configured as a single device together with the inspection equipment 210. The input / output interface 338 of the information processing system 230 also serves as a means for interfacing with an input or output device (not shown) that may be connected to or included in the information processing system 230. In FIG. 3, the input / output interfaces 318, 338 are illustrated as elements configured separately from the processors 314, 334, but are not limited thereto, and the input / output interfaces 318, 338 may be configured to be included in the processors 314, 334.

[0068] The test equipment 210 and the information processing system 230 may include more components than those shown in FIG. 3 . However, it is not necessary to clearly illustrate most conventional technical components. In one embodiment, the test equipment 210 may be embodied to include at least some of the input / output devices 320 described above. The test equipment 210 may also include other components such as a transceiver, a global positioning system (GPS) module, a camera, various sensors, and a database. For example, if the test equipment 210 is a smartphone, the test equipment 210 may be embodied to include various components that are typically included in a smartphone, such as an acceleration sensor, a gyro sensor, a microphone module, a camera module, various physical buttons, buttons using a touch panel, an input / output port, and a vibrator for vibration.

[0069] While a program or application for a user-customized service based on at least one of the musculoskeletal system or the nervous system is running, the processor 314 may receive input or selected text, images, videos, sounds, and / or actions through an input device such as a touch screen, keyboard, camera including an audio sensor and / or image sensor, or microphone connected to the input / output interface 318, and may store the received text, images, videos, sounds, and / or actions in the memory 312 or provide them to the information processing system 230 via the communication module 316 and the network 220.

[0070] The processor 314 of the inspection equipment 210 may be configured to manage, process, and / or store information and / or data received from the input / output device 320, other inspection equipment, the information processing system 230, and / or multiple external systems. The information and / or data processed by the processor 314 may be provided to the information processing system 230 via the communication module 316 and the network 220. The processor 314 of the inspection equipment 210 may transmit and output information and / or data to the input / output device 320 via the input / output interface 318. For example, the processor 314 may output or display the received information and / or data on a screen associated with the inspection equipment 210.

[0071] The processor 334 of the information processing system 230 may be configured to manage, process, and / or store information and / or data received from the plurality of test equipments 210 and / or the plurality of external systems. The information and / or data processed by the processor 334 may be provided to the test equipment 210 via the communication module 336 and the network 220.

[0072] FIG. 4 is a diagram illustrating user status information according to one embodiment of the present disclosure.

[0073] Referring to FIG. 4, the user state information 110 applicable to an embodiment of the present disclosure may include user fixed information 401 and user variable information 402.

[0074] First, the user-specific information 401 refers to information that remains constant regardless of the user. For example, the user-specific information 401 may include, but is not limited to, gender and age information 410, medical information 420 (e.g., health checkup records, family strength, etc.), and disease information 430 (e.g., past disease diagnoses, treatment records, etc.).

[0075] The user variation information 402 may refer to information that can vary depending on the user. For example, the user variation information 402 may include, but is not limited to, lifestyle information 440 (e.g., region, occupation, consumption level, spare time, lifestyle pattern, sleep state, etc.), health information 450 (e.g., posture and body shape / muscle imbalance, mobility and stability, muscle tone, health functional fitness (e.g., muscle strength, muscle endurance, flexibility, balance, agility, etc.), body composition, stress intensity, nutritional status, biological information, etc.), and preference information 460 (e.g., health service purpose, goal, interest, priority, improvement level, willpower, desired coaching style, etc.).

[0076] FIG. 5 is a diagram illustrating a process of deriving a user-customized test item through an information processing system according to an embodiment of the present disclosure.

[0077] Referring to FIG. 5, in one embodiment, the information processing system 230 may determine a user-customized test item 510 using the user-fixed information 401 and the user-variable information 402 .

[0078] In one embodiment, the information processing system 230 may determine a plurality of musculoskeletal test items using the user-fixed information 401 and the user-variable information 402, and determine the order of the determined plurality of musculoskeletal test items.

[0079] In one embodiment, the information processing system 230 may determine a plurality of musculoskeletal test items and an order of the plurality of musculoskeletal test items based on rules using the user fixed information 401 and the user variable information 402. For example, the information processing system 230 may preset rules for the musculoskeletal test items and the order of the test items required for each of the user fixed information 401 and the user variable information 402, and when the user fixed information 401 and the user variable information 402 are acquired, the information processing system 230 may determine the musculoskeletal test items and the order corresponding to the user fixed information 401 and the user variable information 402 based on the preset rules. Here, the preset rules may be arbitrarily modified or changed by an authorized user (e.g., an administrator, an actual user, etc.), but are not limited thereto.

[0080] In one embodiment, the information processing system 230 may determine a plurality of musculoskeletal test items and an order of the plurality of musculoskeletal test items based on a machine learning model using the user-fixed information 401 and the user-variable information 402.

[0081] Here, the machine learning model (hereinafter referred to as the "third machine learning model") is a model that uses user fixed information 401 and user variable information 402 as input data, and is trained by a machine learning method (e.g., semi-supervised learning, supervised learning, etc.) using learning data in which musculoskeletal test items and their order are correct answer data, and that derives the musculoskeletal test items and the order of each test item required by the user by inputting user fixed information 401 and user variable information 402.

[0082] As an example, the third machine learning model may be, but is not limited to, a CNN (Convolutional Neural Network), a Transformer, a RL (Reinforcement Learning)-based model, an MLP (Multi-Layer Perceptron) model, and an ensemble model.

[0083] Here, the test items determined from the user fixed information 401 and the user variable information 402 may include quantitative functional assessment metrics and qualitative functional assessment metrics.

[0084] First, quantitative function evaluation items are items that measure quantitative aspects of musculoskeletal function, and may include, but are not limited to, muscle contraction count, which indicates the total number of muscle contractions during exercise, exercise distance, which indicates the total distance traveled during exercise, repetition count, which indicates the number of times a specific exercise movement is repeated, exercise intensity, which indicates the degree of force or resistance used during exercise, load amount, which indicates the weight or resistance applied to muscles during exercise, and exercise volume, which indicates the total amount of exercise.

[0085] In addition, the qualitative function assessment items are items that evaluate the qualitative aspects of musculoskeletal function that are closely related to the motor nervous system, and may include, for example, posture alignment, which indicates the posture and alignment of the body during exercise; muscle imbalance, which indicates the state of muscle development between left and right or upper and lower body parts; range of motion (ROM), which indicates the range of motion of a joint; movement accuracy, which indicates the accuracy and consistency of exercise movements; balance and stability, which indicates the balance and stability of the body during exercise; exercise tempo, which indicates the speed at which exercise is performed; muscle activation pattern, which indicates the activation state of specific muscles during exercise; breathing pattern, which indicates the consistency and efficiency of breathing during exercise; and fatigue levels, which indicate the state of fatigue during and after exercise.

[0086] For example, if the information processing system 230 determines based on the user fixed information 401 and the user variable information 402 that the user has a sedentary lifestyle, is an office worker, is a woman in her 40s, and has a history of neck pain, it can determine the areas, test items, and order of each area through a comprehensive assessment of the shoulders, neck, and pelvic area and physical functions that are mechanically and kinematically related.

[0087] In this case, the information processing system 230 may determine the order of the test items by taking into consideration the operational flow of each test item (position and location, whether the test overlaps, factors affecting the test, priority, precautions to be taken during the test, test item categories that require attention, test time, etc.), but is not limited to this.

[0088] FIG. 6 is a diagram illustrating a process of deriving balance of at least one of the musculoskeletal system and the nervous system through an information processing system according to an embodiment of the present disclosure.

[0089] Referring to FIG. 6 , in one embodiment, the information processing system 230 may derive a balance 630 of at least one of the musculoskeletal system or the nervous system using one or more user images 120 and meta information 130 of the inspection equipment that captures the images. Here, the balance 630 of at least one of the musculoskeletal system or the nervous system may include information on the state of each of posture, health, function, strength, body shape, stability, mobility, and body components, and / or balance information on multiple organic relationships among posture, health, function, strength, body shape, stability, mobility, and body components. For example, the balance 630 of at least one of the musculoskeletal system or the nervous system may be expressed as an index related to the state of each of posture, health, function, strength, body shape, stability, mobility, and body components. Additionally or alternatively, the balance 630 of at least one of the musculoskeletal system or the nervous system may represent an index related to the balance of multiple organic relationships among posture, health, function, strength, body shape, stability, mobility, and body components.

[0090] In one embodiment, the information processing system 230 may analyze one or more user images 120 to recognize a user's actions (behaviors). For example, the information processing system 230 may receive 2D and / or 3D images of a user as the user images 120 and extract information related to body joints and / or muscles in the user images 120 using a segmentation model or the like. Based on the extracted information, the user's actions (behaviors) in the user images 120 may be analyzed. Based on the analyzed actions (e.g., static actions, dynamic actions, etc.), a quantitative / qualitative functional assessment of the user's musculoskeletal function may be performed. For example, the user's musculoskeletal function may include information related to posture, body shape, mobility, stability, health, physical strength, and / or body composition. Based on the quantitative / qualitative functional assessment, a balance 630 of at least one of the musculoskeletal system or the nervous system may be derived. As an example, the information processing system 230 may predefine the balance 630 of at least one of the musculoskeletal system or the nervous system based on a quantitative / qualitative functional assessment, and may derive the balance 630 of at least one of the musculoskeletal system or the nervous system corresponding to the results of the quantitative / qualitative functional assessment performed on the user based on the predefined information.

[0091] Here, the balance 630 of at least one of the musculoskeletal system or the nervous system may refer to, but is not limited to, balance within the musculoskeletal system, balance within the nervous system, or balance between the musculoskeletal system and the nervous system.

[0092] In one embodiment, the balance 630 of at least one of the musculoskeletal system or the nervous system can be derived using the integrated test item result information of the information processing system 230.

[0093] Here, the integrated test item result information is information by type of test item, and may include, for example, but is not limited to, the user's posture and body shape, mobility and stability derived by simultaneously performing quantitative functional evaluation and dynamic functional evaluation, and healthy functional strength and body composition (body components) derived by simultaneously performing quantitative functional evaluation and dynamic functional evaluation.

[0094] FIG. 7 is a diagram illustrating a process of generating musculoskeletal-based user-customized results through a first machine learning model according to one embodiment of the present disclosure.

[0095] Referring to FIG. 7, the information processing system 230 may derive a musculoskeletal-based user-customized result 140 through a machine learning model (hereinafter referred to as the “first machine learning model 700”) using user state information 110 and the balance 630 of at least one of the musculoskeletal system or the nervous system.

[0096] Here, the first machine learning model 700 may refer to a model trained by a machine learning method (e.g., semi-supervised learning and / or supervised learning) that uses user state information 110 and at least one balance 630 of the musculoskeletal system or the nervous system as input data and trains the model to output the user customized result 140 using training data including ground truth data corresponding to the user customized result 140. For example, the user customized result 140 may include, but is not limited to, interest and desire information, function prediction information based on the interest and desire information, etc.

[0097] In one embodiment, the first machine learning model 700 includes two different input networks and one output network, and can extract two different results through each of the two input networks and combine the two results through the output network to derive one result data.

[0098] For example, the first machine learning model 700 may include, but is not limited to, a first input network that receives test environment information (e.g., the distance between the equipment and the user, the angle of the equipment, the test environment (indoor, outdoor, lighting, etc.), meta information of 2D / 3D unstructured data (e.g., resolution, aspect ratio, etc.)) and test item integration result information (e.g., posture and body shape, mobility and stability derived from simultaneous performance of quantitative functional assessment and qualitative functional assessment, health function physical strength and body composition (body components) derived from simultaneous performance of quantitative functional assessment and qualitative functional assessment) as input and extracts a first feature vector related to the balance 630 of at least one of the musculoskeletal system or the nervous system, a second input network that receives user state information 110 and extracts a second feature vector, and a first output network that combines the first feature vector and the second feature vector to extract a latent vector and derives a user customized result 140 based on the extracted latent vector.

[0099] Here, the first machine learning model 700 may be, but is not limited to, a CNN (Convolutional Neural Network), a Transformer, a RL (Reinforcement Learning)-based model, an MLP (Multi-Layer Perceptron), or an ensemble model.

[0100] In addition, the process of extracting a latent vector by fusing the first feature vector and the second feature vector includes various well-known techniques such as Concat, Multiply, Average, Dot, Plus, and Minus, and various techniques such as these may be selectively utilized. Therefore, in this specification, a specific method for extracting a latent vector by fusing the first feature vector and the second feature vector will not be described.

[0101] The musculoskeletal-based user-customized results 140 generated through the above-described process may include, but are not limited to, biological age, interest and desire information, function prediction information based on interest and desire, and customized result interpretation.

[0102] FIG. 8 is a diagram illustrating a process of generating a musculoskeletal-based user-customized result that takes biological age into consideration through a first machine learning model according to an embodiment of the present disclosure.

[0103] Referring to FIG. 8, in one embodiment, the information processing system 230 may derive the musculoskeletal-based user-customized result 140 via the first machine learning model 700 taking into account the user's biological age 810.

[0104] More specifically, the information processing system 230 may first determine the user's biological age 810 based on the balance 630 of at least one of the musculoskeletal system and the nervous system and the user's gender and age information 410 in the user condition information 110.

[0105] As an example, the information processing system 230 may determine the user's biological age 810 using a rule-based bio age model. For example, the information processing system 230 may determine rules for determining biological age (e.g., biometric indicators, values, etc. indicated for each biological age), and when the user's gender and age information 410 and the balance 630 of at least one of the musculoskeletal system or the nervous system are acquired, the information processing system 230 may estimate the biological age 810 by applying the predetermined rules to the user's gender and age information 410 and the balance 630 of at least one of the musculoskeletal system or the nervous system.

[0106] As another example, the information processing system 230 may extract the biological age 810 by inputting the user's gender and age information 410 and the balance 630 of at least one of the musculoskeletal system and the nervous system into the AI-based biological age model. Here, the AI-based biological age model may be a model trained to use the user's gender and age information 410 and the balance 630 of at least one of the musculoskeletal system and the nervous system as input data and output the biological age 810 using correct answer data corresponding to the biological age 810, but is not limited thereto.

[0107] Thereafter, the information processing system 230 may generate a customized test result 140 for the user based on the biological age 810, balance 630 of at least one of the skeletal system or nervous system, and user condition information 110 related to the user through the first machine learning model 700.

[0108] FIG. 9 is a diagram illustrating musculoskeletal-based user-customized results according to one embodiment of the present disclosure.

[0109] Referring to FIG. 9, the musculoskeletal-based user-customized results 140 may include biological age 810, interest and desire information 910, predicted function information 920, and customized result interpretation 930.

[0110] First, the bio age 810 refers to the biological age of the user, not the actual age, and may be, for example, but not limited to, a value derived through a bio age model.

[0111] Next, the interest and desire information 910 means information indicating health or body-related desires that the user wishes to improve. For example, the interest and desire information 910 may include, but is not limited to, function indicating an interest in maintaining or improving a specific body function, beauty indicating a desire related to appearance or body shape, and pain indicating a desire for the purpose of alleviating physical pain.

[0112] Such interest and desire information 920 may be information derived by analyzing the balance 630 of at least one of the musculoskeletal system or the nervous system and the user state information 110 through an artificial intelligence-based interest and desire model (Wellness Needs Model), but is not limited to this.

[0113] Next, the functional prediction information 920 means a physical function or condition predicted based on the user's interests and desires. For example, the functional prediction information 920 may include, but is not limited to, sex (physiological), exercise (sports, etc.), learning (mental functions), digestion (endocrine system organs), breathing (circulatory system organs), sleep (hormones), disability (loss of function), immunity (infection), and mental health (depression, anxiety) in the functional area, body shape changes (body shaping and dieting) in the beauty area, and physical illness (medical care) in the pain area.

[0114] Such function prediction information 920 may be information derived by analyzing the balance 630 of at least one of the musculoskeletal system or the nervous system and the user state information 110 through an artificial intelligence-based function prediction model, but is not limited to this.

[0115] Finally, the customized result interpretation 930 means the result of interpreting the biological age 810, the interest and desire information 910, and the function prediction information 920 to suit the user, and may include, for example, but is not limited to, text and visual effects corresponding to the biological age 810, the interest and desire information 910, and the function prediction information 920, information on the user's condition derived based on the biological age 810, the interest and desire information 910, and the function prediction information 920, recommended lifestyle habits, dietary therapy, exercise methods, disease prevention and / or treatment methods, etc. related to the user's condition.

[0116] Here, the customized result interpretation 930 may include all the contents corresponding to the biological age 810, the interest and desire information 910, and the function prediction information 920, but may also include only the information corresponding to the user's area of ​​interest depending on the case.

[0117] FIG. 10 is a flowchart illustrating a method for generating customized results for a user based on interest and desire information related to the user (S1000) according to an embodiment of the present disclosure.

[0118] Referring to FIG. 10, in one embodiment, the information processing system 230 may generate customized results for a user based on interest and desire information related to the user.

[0119] In step S1010, the information processing system 230 may determine elements and exposure priorities to be used in the customized search results based on interest and desire information related to the user.

[0120] Here, the elements used in the customized test results are text corresponding to the user's biological age, interest and desire information, and predicted functional information, but also images generated by visualizing information corresponding to the user's biological age, interest and desire information, and predicted functional information, depending on the case.

[0121] In operation S1020, the information processing system 230 may determine user-customized function prediction information based on interest and desire information related to the user and the status of at least one of the user's musculoskeletal or nervous system.

[0122] In step S1030, the information processing system 230 may generate customized results for the user by processing the customized function prediction information determined in step S1020 using the elements and exposure priorities determined in step S1010.

[0123] FIG. 11 is a diagram illustrating a machine learning model according to one embodiment of the present disclosure.

[0124] Referring to FIG. 11, the machine learning model 1100 may include an input layer 1120 to which input data 1110 is input, hidden layers 1130_1, 1130_n, and an output layer 1140 that outputs result data 1150.

[0125] Here, the machine learning model 1100 may include, but is not limited to, a model that derives musculoskeletal-based user-customized results from user condition information and information regarding the balance of at least one of the musculoskeletal system or the nervous system (e.g., a first machine learning model (700 in Figures 7 and 8)), a model that derives user stage-specific goal information and customized coaching information from user condition information and functional prediction information (e.g., a second machine learning model (1200 in Figures 12 and 13)), and a model that derives musculoskeletal test items and order from user condition information (e.g., a third machine learning model).

[0126] More specifically, a machine learning model (e.g., a neural network) is composed of one or more network functions, which may be composed of a set of interconnected computational units also commonly referred to as "nodes." Such "nodes" are also referred to as "neurons." One or more network functions are composed of at least one or more nodes. The nodes (or neurons) constituting one or more network functions may be connected to each other by one or more "links."

[0127] Within a machine learning model, one or more nodes connected via links may form a relative relationship between an input node and an output node. The concepts of input node and output node are relative, and any node that has an output node relationship with one node may also have an input node relationship with another node, and vice versa. As described above, the input node-to-output node relationship may be generated around links. One or more output nodes may be connected to one input node via links, and vice versa.

[0128] In a relationship between an input node and an output node connected via a link, the value of the output node may be determined based on data input to the input node. Here, the node connecting the input node and the output node may have a weight. The weight is variable and may be changed by a user or an algorithm so that the machine learning model performs a desired function. For example, when one or more input nodes are connected to one output node via respective links, the output node may determine its output node value based on the value input to the input node connected to the output node and the weight set for the link corresponding to each input node.

[0129] As described above, a machine learning model has one or more nodes connected to each other via one or more links to form a system of input nodes and output nodes. The characteristics of the machine learning model may be determined by the number of nodes and links, the relationships between the nodes and links, and the weights assigned to each link. For example, if two machine learning models have the same number of nodes and links but different weights between the links, the two machine learning models may be recognized as different from each other.

[0130] Some of the nodes constituting a machine learning model may constitute a layer based on their distance from the initial input node. For example, a set of nodes whose distance from the initial input node is n may constitute n layers. The distance from the initial input node may be defined by the minimum number of links that must be traversed to reach the node from the initial input node. However, this definition of a layer is arbitrary for the purpose of explanation, and the order of layers in a machine learning model may be defined in a manner different from that described above.

[0131] An initial input node may refer to one or more nodes within a machine learning model to which data is directly input without a link between other nodes. Similarly, a final output node may refer to one or more nodes within a machine learning model that do not have an output node between other nodes. Furthermore, a hidden node may refer to a node constituting a machine learning model that is neither an initial input node nor a final output node. A machine learning model according to an embodiment of the present invention is also a machine learning model in which there are more nodes in an input layer than in a hidden layer closer to the output layer, and the number of nodes decreases as one progresses from the input layer to the hidden layer.

[0132] A machine learning model may include one or more hidden layers. Hidden nodes in a hidden layer may receive inputs from the outputs of previous layers and surrounding hidden nodes. The number of hidden nodes in each hidden layer may be the same or different. The number of nodes in an input layer is determined based on the number of data fields in the input data and may be the same as or different from the number of hidden nodes. Input data input to the input layer is operated on by hidden nodes in the hidden layer and output by a fully connected layer (FCL), which is an output layer.

[0133] In various embodiments, the machine learning model is also a deep learning model.

[0134] A deep learning model (e.g., a deep neural network (DNN)) can refer to a machine learning model that includes multiple hidden layers in addition to an input layer and an output layer. A deep neural network can be used to understand the latent structures of data, i.e., the latent structures of a photo, text, video, and / or audio (e.g., what objects are in the photo, the user's posture, the user's movements, the user's body shape, etc.).

[0135] Deep neural networks may include, but are not limited to, convolutional neural networks (CNNs), recurrent neural networks (RNNs), autoencoders, generative adversarial networks (GANs), restricted boltzmann machines (RBMs), deep belief networks (DBNs), Q-networks, U-networks, Siamese networks, etc.

[0136] In various embodiments, the network function may include an autoencoder, which is also a type of artificial neural network for generating output data that is similar to input data.

[0137] An autoencoder includes at least one hidden layer, and one or more hidden layers may be located between the input and output layers. The number of nodes in each layer is reduced to an intermediate layer called a bottleneck layer (encoder) relative to the number of nodes in the input layer, and may be expanded symmetrically from the bottleneck layer to the output layer (symmetrical to the input layer). The nodes in the dimensionality reduction layer and the dimensionality restoration layer may be symmetric or asymmetric. An autoencoder may also perform nonlinear dimensionality reduction. The number of input and output layers may correspond to the number of sensors remaining after preprocessing of the input data. In an autoencoder structure, the number of nodes in the hidden layer included in the encoder may decrease with increasing distance from the input layer. The number of nodes in the bottleneck layer (the layer with the fewest nodes located between the encoder and decoder) may be kept above a certain number (e.g., more than half of the input layer) because an excessively small number of nodes may not convey sufficient information.

[0138] FIG. 12 is a diagram illustrating a process of generating user stage-specific goal information and customized coaching information through a second machine learning model according to an embodiment of the present disclosure.

[0139] Referring to FIG. 12, in one embodiment, the information processing system 230 may generate step-by-step goal information and customized coaching information 1210 for the user based on the function prediction information 920 according to the interest and desire information and the user state information 110.

[0140] Here, the step-by-step goal information of the user refers to information about detailed goals set for each step to achieve a final goal corresponding to the user's interests and desires, and may include information about goals to be achieved by the user for each step (e.g., lifestyle habits, exercise adjustment, nutritional diet, mental management, etc., subdivided so as to be easily accomplished and achieved for each step). For example, if the interests and desires of a female office worker in her 40s with a sedentary lifestyle include beauty (diet) and pain (lower back) management, the step-by-step goal information of the user may include, but is not limited to, lifestyle habits and exercise adjustment that can be accomplished in daily life to resolve potential factors related to lower back pain, and the execution of a nutritional diet for adjusting body composition and losing weight, as well as the pain level and weight, body fat distribution by region, and body size through the above.

[0141] In addition, the customized coaching information for a user is information for guiding and coaching the user to achieve step-by-step goal information, and is information designed in consideration of the results of analyzing the user's service participation pattern, such as access frequency, time, prescription execution intensity, etc., and updated user status information, such as conversations input by the user in real time, changes in health status, changes in preferences, changes in lifestyle patterns, etc. For example, the customized coaching information may include, but is not limited to, notification intervals, prescription execution intensity, etc.

[0142] In one embodiment, the information processing system 230 can generate step-by-step goal information and customized coaching information 1210 related to usage for the user through a machine learning model (hereinafter referred to as the "second machine learning model 1200") based on the function prediction information 920 based on interest and desire information and the user state information 110.

[0143] Here, the second machine learning model 1200 may refer to a model trained by a machine learning method (e.g., semi-supervised learning and / or supervised learning) using learning data in which the user state information 110 and function prediction information 920 based on interest and desire information are input data and the stage-specific goal information and customized coaching information 1210 are correct answer data.

[0144] In one embodiment, the second machine learning model 1200 includes two different input networks and one output network, and can extract two different results through each of the two input networks and combine the two results through the output network to derive one result data.

[0145] For example, the second machine learning model 1200 may include, but is not limited to, a third input network that receives function prediction information 920 based on the user's interest and desire information and extracts a third feature vector, a fourth input network that receives user state information 110 and extracts a fourth feature vector, and a second output network that combines the third feature vector and the fourth feature vector to extract a latent vector and derives a user-customized result 140 based on the extracted latent vector.

[0146] Here, the second machine learning model 1200 may be, but is not limited to, a CNN (Convolutional Neural Network), a Transformer, a RL (Reinforcement Learning)-based model, an MLP (Multi-Layer Perceptron), or an ensemble model.

[0147] In one embodiment, when user status information is updated based on at least one of interest and desire information related to the user, function prediction information based on the interest and desire information, stage-specific goal achievement information achieved by the user, and customized coaching performance information for the user, the information processing system 230 may receive the updated user status information and regenerate stage-specific goal information related to the user and customized coaching information for the user based on the updated user status information. Under such a configuration, the test-interpretation-management process may be repeatedly performed based on the user status information, and the user's musculoskeletal system and / or weaknesses in the musculoskeletal system may be gradually resolved.

[0148] FIG. 13 is a diagram illustrating a process of regenerating user stage-specific goal information and customized coaching information through a second machine learning model according to an embodiment of the present disclosure.

[0149] Referring to FIG. 13, the information processing system 230 can generate regenerated user stage-specific goal information and customized coaching information 1330 by regenerating stage-specific goal information and customized coaching information based on the stage-specific achievement goals and coaching performance information achieved by the user.

[0150] In one embodiment, the information processing system 230 receives the stage-based goal achievement information 1310 and the user customized coaching performance information 1320 performed by the user, and regenerates the stage-based goal information for the user and the customized coaching information 1320 for the user based on the stage-based goal achievement information 1310 performed by the user, the user customized coaching performance information 1320, the function prediction information based on interest and desire information 920, and the user state information 110 using a second machine learning model, thereby generating regenerated user stage-based goal information and customized coaching information 1330.

[0151] For example, the information processing system 230 can extract a user's behavioral pattern based on the step-by-step goal achievement information 1310 and the user-customized coaching performance information 1320 performed by the user, and adjust the step goal information related to the user based on the extracted behavioral pattern.

[0152] That is, the information processing system 230 may monitor how well the user has achieved the step-by-step goals, and depending on the user's achievement of the step-by-step goals, may adjust the default step-by-step goals for the user upward, maintain, or downward, thereby setting appropriate goals for the user.

[0153] FIG. 14 is a diagram illustrating a user interface (UI) that provides a skeleton-based user-customized service according to an embodiment of the present disclosure.

[0154] Referring to FIG. 14, in one embodiment, the information processing system 230 can provide a user interface (UI) that provides user-customized services based on at least one of the musculoskeletal system or the nervous system.

[0155] Here, the UI may include, but is not limited to, a first area 1401 and a second area 1402 .

[0156] First, the first area 1401 may refer to an area displaying the results of the user's mobility and stability test together with an image of the user's test action. In one embodiment, the first area 1401 may include an area 1410 that measures the user's shoulder flexion (left) angle by analyzing the user's test action image 1410, and an area 1420 that evaluates a compensation pattern, such as the degree of core movement, by analyzing the user's test action image 1430. Under such configuration, when the user's stability and mobility are analyzed, the area 1410 of the first area 1401 may provide the range of joint motion, which is a quantitative functional evaluation, as well as the evaluation of a compensation pattern, such as the degree of core movement, which is a qualitative functional evaluation. This may provide the user with a customized result report that allows for integrated result interpretation including the quantitative and qualitative functional evaluation. In the present disclosure, the image 1430 of the first area 1401 is illustrated as an image of the user's test action, but is not limited thereto and may be output as a video or 3D image including the user's test action.

[0157] The second area 1402 may refer to an area that outputs the results of the health functional fitness test. The second area 1402 may determine the layout and text wording of the user interface based on user status information, including the simultaneously analyzed quantitative and qualitative functional assessments. Specifically, the balance and / or status of at least one of the user's musculoskeletal system or nervous system may be output at the time of the expert based on the user's status information, including the user's age, gender, interests, etc. For example, the second area 1402 may include, but is not limited to, a biological age area 1440 that displays the user's biological age, an average movement speed area 1450 that displays the user's average movement speed, a muscle strength level area 1460 that displays the user's muscle strength level, and a record comparison area 1470 that displays a comparison result with the user's previous record. In other words, the configuration and / or layout of the information output in the second area 1402 may vary depending on the user's status information.

[0158] Additionally or alternatively, the text wording may be provided as synthesized voice generated through known text-to-speech (TTS) technology. For example, the UI of FIG. 14 may include an AI speaker icon (not shown). When the AI ​​speaker icon is selected (e.g., by clicking or touching), the order, selective wording, and / or duration of the test result explanation may be determined, taking into account at least one functional status and / or interest request information of the user's musculoskeletal or nervous system. Based on the order, selective wording, and / or duration of the test result explanation, a function may be provided that allows an expert (e.g., an AI coach) to explain the user's test results to the user through synthesized voice, such that the AI ​​expert explains the test results to the user alongside the user. That is, through the UI of FIG. 14, the user may be provided with audio of the test results and a 3D result sheet.

[0159] FIG. 15 is a flowchart illustrating a method (S1500) for providing a user-customized service based on at least one of a musculoskeletal system or a nervous system according to an embodiment of the present disclosure.

[0160] Here, although it has been described that the information processing system 230 is the entity that performs each step included in the method (S1500) for providing a user-customized service based on at least one of the musculoskeletal system or the nervous system according to FIG. 15, the method is not limited thereto, and depending on the case, the steps may be performed by the testing equipment 210, or may be performed by both the information processing system 230 and the testing equipment 210.

[0161] Also, some steps may be performed by the information processing system 230 and the remaining steps may be performed by the inspection equipment 210 .

[0162] Referring to FIG. 15, in operation S1510, the information processing system 230 may receive status information related to a user.

[0163] In one embodiment, the information processing system 230 can collect user status information via a user data channel.

[0164] Here, the status information related to the user is information related to the user's status, and may include, but is not limited to, fixed information such as the user's gender and age information, medical information, and disease information, and variable information such as lifestyle information, health information, and preference information.

[0165] Here, the user data channel may also be, but is not limited to, a user's wearable device or a mobile application installed on the user's mobile.

[0166] In one embodiment, the information processing system 230 can repeatedly collect user status information at predetermined intervals, but is not limited to this.

[0167] In step S1520, the information processing system 230 may determine one or more musculoskeletal test items for the user based on the status information related to the user received in step S1510.

[0168] In one embodiment, the information processing system 230 may determine one or more musculoskeletal test items and the order in which they are required for the user by analyzing the condition information related to the user through a third machine learning model, or may determine one or more musculoskeletal test items and the order in which they are required for the user by analyzing the condition information related to the user based on predetermined rules.

[0169] In one embodiment, the information processing system 230 may dynamically adjust the type and order of one or more musculoskeletal test items based on user condition information collected at predetermined intervals.

[0170] In the past, unnecessary test items were included regardless of user information, and test items once determined were all tested in a predetermined order. However, according to the present disclosure, user status information is updated (tagged and categorized) in real time, and the test items and order are flexibly and dynamically adjusted based on this information, so that tests appropriate for the user can be performed. For example, when the user status information is updated, a categorized tag (e.g., normal / caution / risk, etc.) may be tagged, and the test items and / or order may be adjusted based on the updated status information and tag. Here, test items corresponding to risk factors may be designed to be performed first.

[0171] In addition, by allowing the user to select only the necessary test items from among the many musculoskeletal function test items, the cost and time required for the test can be dramatically reduced.

[0172] In step S1530, the information processing system 230 may output one or more musculoskeletal test items and their order determined in step S1520.

[0173] In step S1540, the information processing system 230 may receive one or more user images relating to one or more postures or movements of the user in response to one or more musculoskeletal test items output through step S1530.

[0174] As an example, when one or more musculoskeletal test items are determined based on the user condition information 110, the information processing system 230 may guide the user to assume a specific posture or perform a specific movement based on the determined one or more musculoskeletal test items, and in response thereto, may acquire a user image generated by capturing an image of the user assuming a specific posture or performing a specific movement.

[0175] In step S1550, the information processing system 230 can output customized results for the user by analyzing the image received through step S1540 and the status information related to the user received through step S1510 through a first machine learning model.

[0176] In this case, when the information processing system 230 analyzes the image and recognizes multiple postures and movements of the user, it can select only the postures and movements requested from the user from the multiple postures and movements, or filter out the postures and movements not requested from the user as noise.

[0177] In one embodiment, the information processing system 230 can generate a user-customized result form based on the user's musculoskeletal function test results.

[0178] For example, the information processing system 230 can determine the configuration, structure, and arrangement order of a UI that outputs the user's musculoskeletal function test results in accordance with the user.

[0179] In addition, the information processing system 230 can select the language and words to be used to create a user-customized result sheet based on the interest and desire information, and can process the results analyzed through the biological age model and function prediction model to suit the user's preferences, adjust the difficulty of the language and words to suit the user's level, or select expressions.

[0180] The user-customized result sheet generated in the above manner may include all information related to the user's musculoskeletal function test results, or may include only information corresponding to the user's area of ​​interest, or may include only information selected by the user or administrator, depending on the case. For example, but not limited to, the user or administrator may optionally modify and change the information included in the user-customized result sheet.

[0181] As described above, those skilled in the art to which the present disclosure pertains will understand that the present disclosure can be embodied in other specific forms without changing the technical spirit or essential characteristics thereof. Therefore, it should be understood that the above-described embodiments are illustrative in all respects and are not limiting. The scope of the present disclosure is defined by the claims set forth below, rather than the detailed description. All modifications and variations derived from the meaning and scope of the claims and equivalent concepts should be construed as being within the scope of the present disclosure.

[0182] The features and advantages described herein are not all-inclusive, and many additional features and advantages will become apparent to those skilled in the art, particularly in view of the drawings, specification, and claims. Furthermore, it should be noted that the language used in this specification has been selected primarily for ease of reading and instructional purposes, and may not be selected to delineate or limit the subject matter of the present disclosure.

[0183] The foregoing description of embodiments of the present disclosure has been presented for purposes of illustration. It is not intended to limit the disclosure to the precise form disclosed or to make it exhaustive. Those skilled in the art will recognize that numerous modifications and variations are possible in light of the foregoing disclosure.

[0184] Accordingly, the scope of the present disclosure is not limited by this detailed description, but rather by any claims of an application based thereon. Accordingly, the disclosure of embodiments of the present disclosure is illustrative and does not limit the scope of the present disclosure, which is set forth in the following claims. [Explanation of symbols]

[0185] 210 Inspection Equipment 220 Network 230 Information Processing Systems

Claims

1. 1. A method for providing user-customized services based on at least one of a musculoskeletal system or a nervous system, performed by at least one processor, comprising: receiving status information relating to a user; determining one or more musculoskeletal test items based on the received condition information relating to the user; outputting the determined one or more musculoskeletal test items; receiving, for each of the one or more output musculoskeletal test items, one or more images including at least one of a posture or a movement of the user; receiving meta information related to inspection equipment capturing the one or more images; and analyzing status information, the one or more images, and the meta information related to the user using a first machine learning model, and outputting a customized result for the user.

2. The step of outputting a customized result for the user comprises: analyzing the received one or more images and the meta-information to generate a result related to balance of at least one of the user's musculoskeletal system and nervous system; and generating a customized test result for the user based on balance-related results of at least one of the user's musculoskeletal system or nervous system using the first machine learning model and the received user-related status information.

3. The step of determining the one or more musculoskeletal parameters comprises:

2. The method for providing a user-customized service based on at least one of the musculoskeletal system and the nervous system according to claim 1, further comprising determining a plurality of musculoskeletal test items and an order of the plurality of musculoskeletal test items based on condition information relating to the user.

4. The status information about the user includes information about the user's gender and age, The method further includes determining a biological age of the user based on a result related to balance of at least one of the user's musculoskeletal system or nervous system and the user's gender and age information; The step of determining a biological age of the user based on a result related to the balance of at least one of the user's musculoskeletal system or nervous system and the user's gender and age information includes:

3. The method of claim 2, further comprising: generating a customized test result for the user based on the biological age of the user, balance-related results of at least one of the user's musculoskeletal system or nervous system, and status information of the user, using the first machine learning model.

5. 5. The method for providing a user-customized service based on at least one of the musculoskeletal system and the nervous system according to claim 4, wherein the customized test results for the user include interest and desire information related to the user and function prediction information based on the interest and desire information.

6. The step of generating a customized test result for the user using the first machine learning model based on the biological age of the user, a balance result of at least one of the user's musculoskeletal system and the nervous system, and status information of the user, includes: determining elements and exposure priorities to be used in the customized search results based on interest and desire information related to the user; determining user-customized function prediction information based on interest and desire information related to the user and a status of at least one of the user's musculoskeletal or nervous system; and generating customized function prediction information for the user as a customized result for the user using the determined elements and the exposure priority.

7. 6. The method for providing a user-customized service based on at least one of the musculoskeletal system and the nervous system of claim 5, further comprising: using a second machine learning model to generate stage-specific goal information for the user and customized coaching information for the user based on function prediction information according to the interest and desire information and status information for the user.

8. The method further includes receiving step-by-step goal achievement information performed by the user and the user-customized coaching performance information; The step of generating step-by-step goal information and customized coaching information for the user includes:

8. The method for providing a user-customized service based on at least one of a musculoskeletal system or a nervous system according to claim 7, further comprising: regenerating step goal information for the user and customized coaching information for the user based on step-by-step goal achievement information achieved by the user, the user-customized coaching performance information, function prediction information based on the interest and desire information, and status information related to the user, using the second machine learning model.

9. The step of receiving status information related to the user includes:

6. The method for providing a user-customized service based on at least one of the musculoskeletal system or the nervous system according to claim 5, comprising receiving status information related to the user updated based on at least one of step-by-step goal achievement information achieved by the user, customized coaching performance information for the user, interest and desire information related to the user, or function prediction information based on the interest and desire information.

10. The method of claim 1 , wherein the state information relating to the user includes fixed information relating to the user and change information relating to the user.

11. A computer program stored on a computer-readable recording medium for executing the method according to any one of claims 1 to 10 on a computer.

Images