Method for generating a customized exercise guide based on assessment data

Abstract

A method for generating a customized exercise guide may include: receiving physical fitness evaluation data for a target user through physical fitness evaluation equipment, measurement result sheets, electronic documents, and user input information, and generating target data by standardizing the physical fitness evaluation data according to a pre-set common physical fitness evaluation schema; the processor calculating a plurality of quantified scores for each of a plurality of physical fitness evaluation items by comparing the target data with pre-set evaluation criteria, and classifying the physical functional status of the target user into at least one target functional group among a plurality of functional groups based on the plurality of quantified scores; the processor generating a physical fitness status profile representing the physical functional status of the target user based on the target data, the plurality of quantified scores, and the at least one target functional group; and the processor generating a customized exercise guide including recommended exercise items, recommended exercise intensity, and recommended exercise priority based on the physical fitness status profile and providing it to a user terminal corresponding to the target user.

Description

Technology Field

[0001] The present invention relates to a method for generating a customized exercise guide based on evaluation data. Background Technology

[0002] With the advancement of an aging society, interest in health management and exercise prescription for the senior population is increasing, leading to the widespread adoption of various physical fitness assessment equipment and health evaluation services. The results of physical fitness assessments can be utilized as foundational data to identify an individual's physical function and design appropriate exercise programs.

[0003] However, in actual practice, physical fitness assessment equipment, health checkup results, body composition analyzers, and manual records from different manufacturers are used in combination, and there is a problem in that it is difficult to utilize results in an integrated manner because data formats and evaluation criteria vary by equipment and institution.

[0004] Furthermore, physical fitness assessment results are often managed in various forms, such as paper documents, PDF files, image files, or computerized documents, which presents challenges in long-term history management and systematic data analysis. Consequently, the analysis of time-series changes for the same user or the tracking of individual health status may be limited.

[0005] Meanwhile, existing exercise prescription services often rely on the experience or subjective judgment of experts, and the criteria for interpreting evaluation results may vary depending on the person in charge. Consequently, there is a possibility that different exercise recommendations may be provided even for the same evaluation result.

[0006] In addition, although automated health management systems are being proposed, they often remain at the level of simple data storage or result output, or fail to sufficiently account for errors and outliers in input data, thus having limitations in providing reliable exercise guidance. In this regard, documents such as Registered Patent Publication No. 10-1959079 and Published Patent Publication No. 10-2011-0023815 have been disclosed. The problem to be solved

[0007] One embodiment of the present invention aims to provide a physical fitness evaluation data processing technology that converts physical fitness evaluation data generated in different formats into a common structure and enables integrated utilization.

[0008] One embodiment of the present invention aims to provide a technology that enables objective comparison of evaluation results by applying quantitative criteria to a plurality of physical fitness evaluation items, and allows for the systematic analysis of a user's physical function status.

[0009] One embodiment of the present invention aims to provide a technology capable of improving data reliability by detecting errors, omissions, or abnormal data included in physical fitness evaluation data and supporting verification and correction processes.

[0010] One embodiment of the present invention aims to provide a technology capable of providing an exercise guide suitable for individual characteristics by classifying a user's physical condition into functional groups and generating a physical condition profile.

[0011] One embodiment of the present invention aims to improve the efficiency of health management tasks and provide a foundation for continuous health management by integrating the processes of physical fitness evaluation, analysis, verification, exercise guide generation, and result provision into a single systematic processing flow.

[0012] The technical problems of the present invention are not limited to those mentioned above, and other unmentioned technical problems will be clearly understood by those skilled in the art from the description below. means of solving the problem

[0013] A method for generating a customized exercise guide based on evaluation data, performed by an electronic device including a processor according to an embodiment of the present invention, may include the following operations: the processor receives physical fitness evaluation data for a target user through physical fitness evaluation equipment, a measurement result sheet, an electronic document, and user input information, and generates target data by standardizing the physical fitness evaluation data according to a pre-set common physical fitness evaluation schema; the processor calculates a plurality of quantified scores for each of a plurality of physical fitness evaluation items by comparing the target data with pre-set evaluation criteria, and classifies the physical functional state of the target user into at least one target functional group among a plurality of functional groups based on the plurality of quantified scores; the processor generates a physical fitness state profile representing the physical functional state of the target user based on the target data, the plurality of quantified scores, and the at least one target functional group; and the processor generates a customized exercise guide including recommended exercise items, recommended exercise intensity, and recommended exercise priority based on the physical fitness state profile and provides it to a user terminal corresponding to the target user.

[0014] The above method for generating a customized exercise guide is,

[0015] The above processor further includes the operation of calculating a final quantified score for the 30-second chair stand test item, which is the target physical fitness evaluation item among the plurality of physical fitness evaluation items, based on [Mathematical Formula 1] below.

[0016] [Mathematical Formula 1]

[0017]

[0018] S_i corresponds to the final quantified score for the 30-second chair standing test item, X_i corresponds to the actual number of times the 30-second chair standing is performed by the target user, K_i corresponds to the chair standing growth limit constant set based on the age and gender of the target user, k corresponds to the non-linear shape parameter constant, p_ij corresponds to the dynamic damping coefficient of lower limb function due to the pre-set decline in cardiorespiratory endurance, T_j corresponds to the minimum biological requirement threshold of the 6-minute walking distance set based on the age and gender, and X_j corresponds to the actual walking distance data of the target user measured through the 6-minute walking test item set as a cross-reference evaluation item with the 30-second chair standing test item among the plurality of physical fitness evaluation items.

[0019] The above method for generating a customized exercise guide is,

[0020] The above processor acquires real-time plantar pressure density distribution data generated during the walking of the target user by using a plurality of pressure sensors embedded in a smart insole worn by the target user;

[0021] The operation of the processor to calculate a gait asymmetry index by calculating the difference in ground contact time and the movement trajectory of the center of pressure (CoP) of the left foot and the right foot based on the plantar pressure density distribution data; and

[0022] The above processor includes an operation in which, if the gait asymmetry index exceeds a preset allowable threshold, it updates the risk indicator within the physical condition profile to a fall risk group and forcibly reassigns the unilateral lower limb muscle strengthening exercise item among the recommended exercise priorities included in the customized exercise guide to the first priority and provides it to the user terminal.

[0023] The above gait asymmetry index is calculated based on [Mathematical Formula 2] below, and

[0024] [Mathematical Formula 2]

[0025]

[0026] G corresponds to the above-mentioned gait asymmetry index, A_T corresponds to the first parameter related to ground contact time, A_P corresponds to the second parameter related to plantar pressure, and A_C corresponds to the third parameter related to movement trajectory, and

[0027] A_T, A_P, and A_C are calculated based on the following [Equation 3], [Equation 4], and [Equation 5], respectively, and

[0028] [Mathematical Formula 3]

[0029]

[0030] [Mathematical Formula 4]

[0031]

[0032] [Mathematical Formula 5]

[0033]

[0034] T_L corresponds to the average ground contact time of the left foot of the target user, T_R corresponds to the average ground contact time of the right foot, and T_avg corresponds to the arithmetic mean of the average ground contact time of the left foot and the average ground contact time of the right foot.

[0035] P_L corresponds to the average plantar pressure of the left foot, P_R corresponds to the average plantar pressure of the right foot, and P_avg corresponds to the arithmetic mean of the average plantar pressure of the left foot and the average plantar pressure of the right foot.

[0036] D_C corresponds to the average deviation distance between the pressure center movement trajectories of the left foot and the right foot, and L_C corresponds to the trajectory reference length set based on the foot length of the target user. Effects of the invention

[0037] The effects of the method for generating a customized exercise guide according to embodiments of the present invention are described as follows.

[0038] According to the present invention, by converting physical fitness evaluation data of different formats into a common physical fitness evaluation schema, compatibility between heterogeneous data can be ensured, and physical fitness evaluation results can be managed according to consistent standards.

[0039] According to the present invention, by quantifying physical fitness evaluation data and classifying it into functional groups, the user's physical functional status can be analyzed more objectively and systematically, and the usability of the evaluation results can be improved.

[0040] According to the present invention, erroneous data or abnormal data can be effectively managed through data reliability evaluation and inspection / correction procedures, thereby improving the accuracy and reliability of the physical condition profile.

[0041] According to the present invention, by generating a customized exercise guide based on a user's physical condition profile, exercise information suitable for an individual's functional state can be provided, and consistency in the exercise program design process can be ensured.

[0042] According to the present invention, as cumulative management and continuous utilization of physical fitness evaluation results become possible, it is possible to support tracking changes in health status, analysis of exercise effects, and health management decision-making, and physical fitness evaluation data can be utilized as a long-term management asset.

[0043] In addition, various effects that can be identified directly or indirectly through this document may be provided. Brief explanation of the drawing

[0044] FIG. 1 is a block diagram showing the components of an electronic device according to an embodiment of the present invention. FIG. 2 is a block diagram showing the components of a customized exercise guide generation system according to one embodiment of the present invention. FIG. 3 is a flowchart of the operation of a method for generating a customized exercise guide according to one embodiment of the present invention. FIG. 4 is a diagram conceptually illustrating the operation method of a customized exercise guide generation system according to one embodiment of the present invention. In relation to the description of the drawings, the same or similar reference numerals may be used for the same or similar components. Specific details for implementing the invention

[0045] Hereinafter, some embodiments of the present invention will be described in detail with reference to exemplary drawings. It should be noted that in assigning reference numerals to the components of each drawing, the same components are given the same reference numeral whenever possible, even if they are shown in different drawings. Furthermore, in describing the embodiments of the present invention, if it is determined that a detailed description of related known components or functions would hinder understanding of the embodiments of the present invention, such detailed description is omitted.

[0046] In describing the components of the embodiments of the present invention, terms such as first, second, A, B, (a), (b), etc., may be used. These terms are intended merely to distinguish the components from other components, and the essence, order, or sequence of the components is not limited by these terms. Furthermore, unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the present invention pertains. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this application.

[0047] Hereinafter, embodiments of the present invention will be described in detail with reference to FIGS. 1 to 3.

[0049] FIG. 1 is a block diagram showing the components of an electronic device according to one embodiment of the present invention.

[0050] According to one embodiment, the electronic device (100) may include a memory (110), a processor (120), a communication interface (130), and / or a display device (140). The configuration of the electronic device (100) shown in FIG. 1 is exemplary and the embodiments of the present invention are not limited thereto. For example, the electronic device (100) may further include components not shown in FIG. 1 (e.g., a user interface, an input device, a notification unit, a sensor unit, or at least one of any combination thereof).

[0051] According to one embodiment, the memory (110) may store instructions or data. For example, the memory (110) may store one or more instructions that cause the electronic device (100) to perform various operations when executed by the processor (120).

[0052] For example, the memory (110) may be implemented as a single chipset with the processor (120). The processor (120) may include at least one of a communication processor or a modem.

[0053] For example, the memory (110) can store various information related to the electronic device (100). For example, the memory (110) can store information regarding the operation history of the processor (120). For example, the memory (110) can store input data acquired by the electronic device (100), output data output by the electronic device (100), data acquired from an external server, a wearable device, a plurality of cameras and / or user terminals, etc.

[0054] For example, the memory (110) may include multiple storage devices of different types. For example, the memory (110) may include volatile and / or non-volatile storage media. For example, the memory (110) may include at least one of RAM (random-access memory), ROM (read only memory), eMMC (Embedded Multi-Media Card), or any combination thereof.

[0055] The steps of the method or algorithm described in connection with the embodiments disclosed in this specification may be directly implemented in hardware, software modules, or a combination of both, executed by the processor (120). The software modules may reside in a storage medium (i.e., memory (110)) such as RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, or a CD-ROM.

[0056] For example, the memory (110) is coupled to a processor (120), and the processor (120) can read information from a storage medium and write information to a storage medium. Alternatively, the memory (110) may be integrated with the processor (120). The memory (110) and the processor (120) may reside within an application-specific integrated circuit (ASIC). The ASIC may reside within a user terminal. Alternatively, the memory (110) and the processor (120) may reside as separate components within the user terminal.

[0057] According to one embodiment, the processor (120) may be operatively connected to the memory (110), the communication interface (130), and / or the display device (140). For example, the processor (120) may control the operation of the memory (110), the communication interface (130), and / or the display device (140).

[0058] According to one embodiment, the communication interface (130) may support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between an electronic device (100) and an external device (e.g., user terminal (210) of FIG. 2, external server (220), etc.), and the performance of communication through the established communication channel. The communication interface (130) may include one or more communication processors that operate independently of the processor (120) (e.g., application processor) and support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication interface (130) may include a wireless communication module (e.g., cellular communication module, short-range wireless communication module, or GNSS (global navigation satellite system) communication module) or a wired communication module (e.g., LAN (local area network) communication module, or power line communication module). The corresponding communication module among these communication modules can communicate with an external electronic device through a first network (e.g., a short-range communication network such as Bluetooth, WiFi (wireless fidelity) direct, or IrDA (infrared data association)) or a second network (e.g., a legacy cellular network, a 5G network, a next-generation communication network, the Internet, or a long-range communication network such as a computer network (e.g., LAN or WAN). These various types of communication modules may be integrated into a single component (e.g., a single chip) or implemented as multiple separate components (e.g., multiple chips). The wireless communication module can identify or authenticate the electronic device (100) within a communication network, such as the first network or the second network, using subscriber information (e.g., International Mobile Subscriber Identifier (IMSI)) stored in a subscriber identification module.

[0059] According to one embodiment, the display device (140) may include at least one output device that provides various information and a user interface to the user.

[0060] For example, the display device (140) may include a display device, an audio output device, a virtual reality output device, etc.

[0061] For example, the display device (140) can provide the user with various types of user interfaces described in the present disclosure visually and / or audibly.

[0062] The components of the electronic device (100) illustrated in FIG. 1 are exemplary, and the embodiments of the present disclosure are not limited thereto.

[0063] At least some of the embodiments of the present disclosure may be implemented as artificial intelligence (AI) through a processor (120) and memory (110) of an electronic device (100). The processor (120) may be composed of one or more processors, and the one or more processors may be general-purpose processors such as a CPU, AP, DSP (digital signal processor), etc., graphics-dedicated processors such as a GPU, VPU (vision processing unit), or artificial intelligence-dedicated processors such as an NPU. The one or more processors may be controlled to process input data according to predefined operation rules or artificial intelligence models stored in memory (110). Alternatively, if the one or more processors are artificial intelligence-dedicated processors, the artificial intelligence-dedicated processors may be designed with a hardware structure specialized for processing a specific artificial intelligence model.

[0064] The predefined operating rules or artificial intelligence models are characterized by being created through learning. Here, being created through learning means that a predefined operating rules or artificial intelligence models are created by a basic artificial intelligence model being trained using multiple learning data by a learning algorithm to perform a desired characteristic (or purpose). Such learning may be performed on the electronic device (100) itself where the artificial intelligence according to the present disclosure is performed, or it may be performed through a separate server and / or system. Examples of learning algorithms include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but are not limited to the examples described above.

[0065] An artificial intelligence model may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weight values ​​and can perform neural network operations through operations between the results of previous layers and the multiple weights. The multiple weights possessed by the multiple neural network layers can be optimized based on the learning results of the artificial intelligence model. For example, the multiple weights can be updated so that the loss value or cost value obtained from the artificial intelligence model during the learning process is reduced or minimized. Artificial neural networks may include, but are not limited to, deep neural networks (DNN), convolutional neural networks (CNN), recurrent neural networks (RNN), restricted Boltzmann machines (RBM), deep belief networks (DBN), bidirectional recurrent deep neural networks (BRDNN), or deep Q-networks.

[0066] In one embodiment, the electronic device (100) may use a document recognition artificial intelligence model to extract physical fitness evaluation items from output documents, PDF files, image files, or scanned documents of the physical fitness evaluation equipment.

[0067] Specifically, the electronic device (100) receives a result sheet image or PDF file as input data and can extract item names, measurement values, measurement units, and evaluation grades using an OCR model and a document structure analysis model.

[0068] In addition, the electronic device (100) can automatically map measurement items of different expressions to common physical fitness evaluation items using a classification model that learns the correspondence between the extracted item name and the pre-set common physical fitness evaluation schema.

[0069] For example, the electronic device (100) can convert expressions such as "Grip Strength," "grip strength," and "Hand Force" used in different equipment into the same grip strength item.

[0070] In one embodiment, the electronic device (100) can identify the function group of the target user using a function group classification artificial intelligence model that receives target data and quantification scores as input.

[0071] The AI ​​model for classifying functional groups can be trained using past physical fitness assessment results and functional group information assigned by experts.

[0072] The functional group classification AI model can calculate probability values ​​corresponding to the muscle strength decline risk group, balance ability decline group, cardiorespiratory endurance decline group, or composite risk group by analyzing combinations of quantified scores for multiple physical fitness assessment items.

[0073] The electronic device (100) can identify a functional group that is greater than or equal to a reference value among the calculated probability values ​​as a target functional group.

[0074] In one embodiment, the electronic device (100) may use an outlier detection artificial intelligence model to determine the possibility of errors in physical fitness evaluation data.

[0075] An outlier detection AI model can be trained using a normal physical fitness assessment dataset and can calculate an anomaly score indicating the degree to which new input data deviates from the normal distribution.

[0076] The electronic device (100) can identify the corresponding physical strength evaluation item as an item to be inspected if the abnormality is greater than or equal to a preset threshold.

[0077] For example, an electronic device (100) may be designated as an item subject to inspection if it significantly deviates from the range of measurements typically seen in a user group of the same age and gender.

[0078] In one embodiment, the electronic device (100) may use a natural language processing-based language model to analyze the reason for modification entered from the administrator terminal.

[0079] A natural language processing-based language model can receive text explaining the reason for modification and classify it into at least one cause category among measurement error, equipment malfunction, change in user state, physical function imbalance, or other causes.

[0080] For example, if a correction reason such as a sensor contact failure is entered at the time of measurement, a natural language processing-based language model can classify this as an equipment malfunction or measurement error.

[0081] In addition, if a reason for modification such as gait impairment due to a history of left lower limb surgery is entered, a natural language processing-based language model can classify this as a physical function imbalance category.

[0082] In one embodiment, the electronic device (100) may use an exercise guide generating artificial intelligence model that receives a fitness status profile and a target function group as inputs.

[0083] An AI model for generating exercise guides can be trained using exercise prescription data designed by experts, exercise performance result data, and health status change data.

[0084] An AI model for generating exercise guides can generate exercise guide information including exercise items, exercise intensity, exercise frequency, and exercise priority.

[0085] For example, if a target user belongs to both the group at risk of muscle weakness and the group at risk of reduced balance ability, the exercise guide generation AI model can generate a customized exercise guide that adjusts the performance ratio of lower limb strength strengthening exercises and balance training exercises.

[0087] FIG. 2 is a block diagram showing the components of a customized exercise guide generation system according to one embodiment of the present invention.

[0088] A customized exercise guide generation system according to the present disclosure may include an electronic device (100), a user terminal (210), an administrator terminal (215), and an external server (220).

[0089] The electronic device (100) is a core component of a customized exercise guide generation system according to one embodiment of the present invention and can perform functions of collecting, analyzing, and processing physical fitness evaluation data. The electronic device (100) may be implemented in the form of a server, a cloud computing system, a workstation, or a similar computing device.

[0090] The electronic device (100) can receive and store physical fitness evaluation data provided in various formats. For example, the electronic device (100) can collect measurement data received directly from physical fitness evaluation equipment, as well as PDF documents, image files, electronic documents, or handwritten input information.

[0091] The electronic device (100) can convert collected data into an analyzable form and build a database for systematically managing the health status of each user. In addition, the electronic device (100) can accumulate and store the physical fitness history, exercise performance history, and evaluation results for each user over a long period.

[0092] The electronic device (100) can analyze the user's health status using various data processing algorithms, statistical models, or artificial intelligence models. For example, the electronic device (100) can perform processing such as classifying functional status, analyzing change trends, analyzing risk, or generating exercise guides.

[0093] In addition, the electronic device (100) can communicate with a user terminal, an administrator terminal, and an external server to transmit and receive data, provide analysis results, or act as a hub connected to an external system.

[0094] The user terminal (210) may be a device for a target user to interact with the electronic device (100). The user terminal (210) may be implemented in various forms, such as a smartphone, tablet PC, laptop, desktop computer, or wearable device.

[0095] The user terminal (210) can display the user's physical fitness evaluation results, health status information, and exercise guide information. The user can check their health status and establish an exercise plan through the user terminal (210).

[0096] Additionally, the user terminal (210) may provide an interface for responding to surveys, entering health information, entering exercise performance results, or providing additional user information. Through this, the user can actively participate in the health management process.

[0097] The user terminal (210) can receive information such as exercise performance status, schedule notifications, or guidance on the time of re-evaluation. Accordingly, the user terminal (210) can support the user's continuous health management and participation in exercise.

[0098] In one embodiment, the user terminal (210) receives a customized exercise guide generated from the electronic device (100) and can output it in a visual, textual, or voice form.

[0099] The administrator terminal (215) may be a device used by a physical education instructor, exercise expert, health manager, or institution representative. The administrator terminal (215) may be implemented in the form of a desktop computer, laptop, tablet, or mobile terminal.

[0100] The administrator terminal (215) may provide a user interface that can review the physical fitness evaluation results processed by the electronic device (100). The administrator can use this to check the automatic analysis results or modify them if necessary.

[0101] Additionally, the administrator terminal (215) can receive information to review the quality of the physical fitness evaluation data and to identify data that may contain outliers or errors. This can improve the reliability of the data.

[0102] The administrator terminal (215) can view the history of physical fitness changes, trends in health status changes, and exercise performance status for each user. It can also provide management functions for integrated management of multiple users.

[0103] In one embodiment, the administrator terminal (215) can improve the operational efficiency of the health care service by storing modification history, inspection results, and management records, or transmitting them to the electronic device (100).

[0104] The external server (220) may be an external information system capable of communicating with the electronic device (100). The external server (220) may include a medical institution server, a health checkup institution server, a physical fitness evaluation equipment server, or a third-party service server.

[0105] The external server (220) can provide the user's health information, evaluation results, or additional information. The electronic device (100) can provide richer health management services by utilizing the information received from the external server (220).

[0106] Additionally, an external server (220) can be linked with the physical fitness evaluation equipment to store or transmit measurement results, and an electronic device (100) can receive this and perform additional analysis.

[0107] In one embodiment, an external server (220) may provide health statistics data, evaluation criteria data, or exercise program data. The electronic device (100) may utilize these data to improve the accuracy of the analysis.

[0108] The external server (220) may be composed of one or more server devices and may be implemented in a cloud environment or a distributed processing environment. Additionally, the external server (220) may support data sharing and service expansion through interaction with the electronic device (100).

[0109] In one embodiment, the health status analysis system can additionally collect not only the user's physical fitness evaluation data but also image analysis data extracted from captured images.

[0110] Specifically, the user can record a video of a predetermined action using a mobile terminal, tablet, kiosk, or other video recording device, and the system can receive the video and extract information on the user's body movements through an artificial intelligence-based video analysis module.

[0111] The video analysis module can analyze the user's joint positions, body part coordinates, posture change information, balance maintenance information, movement execution time, number of repetitions, range of motion, and movement stability information, and based on this, can generate multiple analysis indicators representing the user's functional status.

[0112] In one embodiment, the image analysis module can extract position information of each part of the body using a pose estimation algorithm or a body feature point detection model, and can calculate joint angles, center of gravity movement paths, left-right balance, and body coordination based on the extracted position information.

[0113] In addition, the system can verify the reliability of the data by comparing the functional group classification results derived from the physical fitness assessment with the video analysis results. For example, if lower body function is classified as normal based on the physical fitness assessment results, but balance maintenance ability or lower limb stability is determined to be below a standard value in the video analysis results, the system can perform additional verification or correction procedures on the relevant user data.

[0114] In one embodiment, the system can generate an integrated functional status indicator by combining a functional score based on physical fitness evaluation data and a functional score based on video analysis. In this case, pre-set weights can be applied to each data type, or the weights can be dynamically adjusted according to data reliability.

[0115] In addition, the system can identify the user's movement patterns, postural characteristics, or signs of functional decline from video analysis results and incorporate them into the existing functional group classification results. For example, if reduced gait stability, increased trunk sway, left-right asymmetrical movements, or limited range of motion in specific joints are detected, this information can be reflected in the functional group classification process to generate more precise health status analysis results.

[0116] Furthermore, the system can generate user-specific exercise guides by integrating physical fitness assessment data and video analysis data. For example, if video analysis confirms a decline in balance ability, it can prioritize recommending balance-improving exercises; if limited range of motion in a specific joint is identified, it can additionally provide an exercise program to improve the flexibility of that joint.

[0117] Accordingly, the health status analysis and exercise guide generation system of the present invention can more accurately determine the user's functional status and improve the precision and reliability of customized exercise prescriptions by utilizing not only static evaluation-based health data but also video analysis information obtained from actual movements.

[0119] FIG. 3 is a flowchart of the operation of a method for generating a customized exercise guide according to one embodiment of the present invention.

[0120] According to one embodiment, the components of a customized exercise guide generation system can perform the operations disclosed in FIG. 3. For example, at least some of the components included in the electronic device (100) among the components of the customized exercise guide generation system (e.g., memory (110), processor (120), communication interface (130), and display device (140) of FIG. 1) may be configured to perform the operations of FIG. 3.

[0121] In the following embodiments, the operations S310 to S340 may be performed sequentially, but are not necessarily performed sequentially. For example, the order of each operation may be changed, and at least two operations may be performed in parallel. Additionally, content corresponding to or overlapping with the previously described content in relation to FIG. 3 may be briefly explained or omitted.

[0122] According to one embodiment, the processor (120) receives physical fitness evaluation data for a target user through physical fitness evaluation equipment, measurement result sheets, electronic documents and user input information, and can generate target data by standardizing the physical fitness evaluation data according to a pre-set common physical fitness evaluation schema (S310).

[0123] The electronic device (100) can receive physical fitness evaluation data for the target user through various input paths.

[0124] Here, physical fitness evaluation data may include not only digital measurements transmitted directly from specific physical fitness evaluation equipment, but also measurement result sheets, PDF files, image files, scanned documents, electronic documents, Excel files, or information manually entered by an administrator.

[0125] For example, after performing measurements regarding grip strength, chair standing, walking speed, balance holding time, and cardiorespiratory endurance at a senior center, each measurement result may be provided to an electronic device (100) through equipment output, a paper result sheet, or an input screen of a center staff member.

[0126] Physical fitness assessment data can be generated in different formats depending on the institution, equipment, or assessment method.

[0127] For example, the first device can output the grip strength measurement results under the item name “Grip Strength” and in kg units, the second device can output the same measurement results under the item name “Upper Limb Muscle Strength,” and the third institution can manage the same information under the “Grip Strength (Left / Right)” item of a manual input form.

[0128] In such cases, even though the data represents identical or similar physical functions, direct comparison or integrated analysis may be difficult due to differences in item names, units, data locations, evaluation criteria, and storage formats.

[0129] The electronic device (100) may use a pre-configured common physical fitness evaluation schema to solve these problems. The common physical fitness evaluation schema may be information that defines multiple physical fitness evaluation items in a unified data structure, and may include, for example, item identifiers, standard item names, measurement units, allowable ranges, related function groups, reference values ​​by age group, reference values ​​by gender, and data source information. Accordingly, the electronic device (100) can generate target data by organizing physical fitness evaluation data entered in different formats to fit the common structure.

[0130] The target data may be standardized data in which the source physical fitness assessment data has been converted into an analyzable form.

[0131] For example, even if the source data contains information expressed differently, such as “5 chair standings: 18 seconds”, “Chair Stand: 18 sec”, and “lower limb strength test: 18”, the electronic device (100) can map this to the “chair standing measurement result” item of the common physical fitness evaluation schema and store the measurement value, unit, measurement date, measurement institution, and target user identification information together.

[0132] The electronic device (100) can use character recognition, table area recognition, item name matching, or document layout analysis functions to process a measurement result sheet in the form of a document.

[0133] For example, when an image of a paper result sheet is input, the electronic device (100) can detect a table area within the image, extract the item names and measurements included in each row or column, and then match the extracted items with standard items of a common physical fitness evaluation schema. At this time, the electronic device (100) can improve the mapping accuracy by considering the item name similarity, unit information, data location, and surrounding context together.

[0134] The electronic device (100) can generate target data even in an environment where no equipment API is provided.

[0135] For example, even if the physical fitness assessment equipment used at the center is not connected to an external server, the administrator can photograph the measurement results, upload a PDF file, or directly input the measurement values.

[0136] The electronic device (100) can provide a fitness evaluation data management environment that is not dependent on a specific equipment manufacturer or specific data format by converting such unstructured or semi-structured data to fit a common fitness evaluation schema.

[0137] This contributes to realizing the technical effect of a structure that can be initiated without equipment integration and organizing different formats into common physical fitness assessment data.

[0138] The target data can subsequently be used as basic input data for quantification, functional group classification, creation of a physical condition profile, and creation of a customized exercise guide. Therefore, when generating the target data, the electronic device (100) can store information regarding the source of the source data, conversion history, mapping criteria, and input method together.

[0139] For example, whether a specific measurement value was received via an equipment API, extracted through image recognition, or manually entered by an administrator can be stored as a data attribute.

[0140] In this way, the electronic device (100) can perform preprocessing and standardization functions that not only simply store physical strength evaluation data but also integrate different input paths and data formats into a common system.

[0141] Accordingly, in subsequent stages, physical fitness evaluation data generated by multiple users, multiple evaluation points, and multiple centers can be compared and / or analyzed using the same criteria, and a data foundation can be formed for tracking long-term changes in physical fitness status and generating customized exercise guides.

[0142] According to one embodiment, the processor (120) compares the target data with a preset evaluation standard to calculate a plurality of quantified scores for each of the plurality of physical fitness evaluation items, and based on the plurality of quantified scores, classifies the physical function status of the target user into at least one target function group among a plurality of function groups (S320).

[0143] The electronic device (100) can calculate a quantified score for each of the multiple physical strength evaluation items by comparing the generated target data with a preset evaluation standard.

[0144] Here, evaluation criteria may be established by considering at least one of age, gender, height, weight, presence of underlying diseases, evaluation purpose, or institution-specific evaluation policy.

[0145] For example, the walking speed measurement results of a female user in her 70s can be compared with reference values ​​corresponding to the same age group and gender, and accordingly, the user's walking function level can be converted into a score or grade.

[0146] Quantification scores can be values ​​converted from raw measurements into a form that allows for comparison between users or between time points.

[0147] For example, raw values ​​such as grip strength of 18 kg, chair standing time of 17 seconds, walking speed of 0.8 m / s, and balance maintenance time of 8 seconds differ in their respective measurement units and directions. A higher value for grip strength may indicate better performance, and a lower value for chair standing time may indicate better performance. The electronic device (100) can convert raw measurements into quantified indicators such as 0 to 100 points, grades 1 to 5, or normal / caution / danger by reflecting these item-specific characteristics.

[0148] The electronic device (100) may store evaluation criteria in the form of a single standard table or in a set of multiple conditional standard values.

[0149] For example, the evaluation criteria may include standard values ​​by age group, standard values ​​by gender, standard values ​​of the senior center itself, standard values ​​set by experts, or standard values ​​based on public physical fitness evaluation standards. The electronic device (100) can select the most suitable evaluation criteria by referring together to the attribute information of the target user and the measurement values ​​included in the target data.

[0150] Multiple quantified scores not only indicate the status of individual physical fitness evaluation items but can also be used as basic data for interpreting the user's physical function status in a multifaceted way.

[0151] For example, grip strength scores may be related to upper limb strength or overall muscle strength status, chair-standing scores may be related to lower limb strength or standing function, and walking speed and balance scores may be related to gait stability or fall risk. Cardiorespiratory endurance scores may be related to the ability to remain active for a long time or the capacity to sustain exercise.

[0152] The electronic device (100) can classify the physical function status of a target user into at least one target function group among a plurality of function groups based on a combination of a plurality of quantification scores.

[0153] Here, the functional group may include a group at risk of muscle strength decline, a group at risk of balance decline, a group at risk of cardiorespiratory endurance decline, a group at risk of flexibility decline, a group at risk of gait stability decline, and a group at risk of falls. Additionally, depending on the embodiment, the functional group may be composed of a higher classification system such as a functional maintenance group, a functional decline risk group, a functional limitation group, or a combined risk group.

[0154] Function group classification is not performed based on only one evaluation item, but can be performed by reflecting the relationships between multiple evaluation items.

[0155] For example, if the chair standing score is low and the walking speed score is also low, the electronic device (100) may classify the target user as a group at risk of lower limb muscle weakness or a group at risk of walking stability. Additionally, if the balance maintenance score is low, the walking speed score is low, and there is a recent history of falls, the electronic device (100) may classify the target user as a group at risk of falls.

[0156] The target functional group may not be limited to a single one. For example, the target user may simultaneously belong to the group at risk of muscle strength decline and the group at risk of balance decline, in which case the electronic device (100) can identify multiple target functional groups together. This classification of multiple functional groups may be particularly useful for senior users. This is because the physical functional status of senior users often results from the combined action of muscle strength, balance, gait stability, and cardiorespiratory endurance, rather than a decline in a single specific item.

[0157] The electronic device (100) can classify target function groups using at least one of a rule-based method, a statistics-based method, or an artificial intelligence model-based method.

[0158] For example, in the case of a rule-based method, a rule may be applied to classify a person as being at risk of muscle weakness if, for instance, the grip strength score is below the first criterion and the chair stand score is below the second criterion.

[0159] For example, in the case of a statistics-based method, the level of relative decline can be determined by comparing it with the average or quantile of a user group of the same age group.

[0160] For example, in the case of an AI model-based approach, a model trained on past evaluation data and expert classification results can receive combinations of quantified scores as input and output probability values ​​for each function group.

[0161] The functional group classification result according to the present disclosure can be used not merely as label information, but as key judgment information for generating a subsequent exercise guide.

[0162] For example, resistance training or lower limb strength training may be primarily recommended to users classified as being at risk of muscle weakness, while balance training or fall prevention exercises may be primarily recommended to users classified as being at risk of reduced balance ability. For users classified as being at risk of reduced cardiorespiratory endurance, a guide may be provided to gradually increase exercise intensity, starting with low-intensity aerobic exercise.

[0163] In this way, the electronic device (100) does not treat standardized target data as a simple set of measurements, but can interpret the user's physical function status in units of function groups through a quantification process based on evaluation criteria.

[0164] Accordingly, individual user fitness status can be structured in a form that is easy for managers to understand, and can subsequently be utilized as a consistent decision-making standard during the fitness status profile creation and customized exercise guide creation stages.

[0165] According to one embodiment, the processor (120) can generate a physical condition profile representing the physical function status of a target user based on target data, a plurality of quantification scores and at least one target function group (S330).

[0166] The electronic device (100) can generate a physical condition profile representing the physical function status of a target user based on target data, a plurality of quantified scores, and at least one target function group.

[0167] A physical fitness status profile may be a data structure that comprehensively represents the current physical fitness status of the target user, and may include measured values ​​of individual fitness evaluation items, quantified scores, functional group classification results, caution items, items requiring improvement, and reference information necessary for generating exercise guides.

[0168] A physical condition profile can be distinguished from a simple evaluation results table. While a typical evaluation results table may be limited to listing measurements at a specific point in time, a physical condition profile can be the result of converting measurements into interpretable condition information.

[0169] For example, a raw value of “walking speed 0.8 m / s” can be stored within a fitness status profile along with interpretation information such as “potential for reduced walking stability,” “need for fall prevention exercises,” and “need to check lower limb strength and balance ability.”

[0170] A physical condition profile can represent the target user's physical function status in a multidimensional way.

[0171] For example, the profile may include muscle strength indicators, balance indicators, gait indicators, cardiorespiratory endurance indicators, flexibility indicators, and fall risk indicators. Each indicator may be calculated from one or more physical fitness evaluation items, and the electronic device (100) may combine multiple indicators to distinguish between the target user's strength areas and weakness areas.

[0172] The physical condition profile can also be used for cumulative management per user. The electronic device (100) can store the physical condition profile at the time of a past evaluation and the physical condition profile at the time of the current evaluation together for the same target user.

[0173] Accordingly, the electronic device (100) can analyze whether there is a change compared to the previous month, a change on a quarterly basis, a change before and after participating in a program, or an improvement before and after a specific exercise performance period.

[0174] In one embodiment, the physical condition profile may include data reliability information. For example, if a specific physical evaluation item is received directly via an equipment API, the electronic device (100) may set the data reliability of that item to a relatively high level. Conversely, if the reliability of the number reading in the image recognition result is low, the input value is outside the acceptable range, or there is a lack of logical consistency between items, the electronic device (100) may identify that item as an item subject to inspection.

[0175] In the process of generating a physical condition profile, the electronic device (100) can reflect the results of inspection and correction through the administrator terminal (215). For example, if a chair standing record that should be extracted as “18.0” during the OCR processing is incorrectly extracted as “180”, the electronic device (100) can determine that the value is outside the acceptable range and display it as an item subject to inspection on the administrator terminal (215). If the administrator checks the original result sheet and corrects the value to “18.0 seconds”, the electronic device (100) can generate a physical condition profile using the corrected value.

[0176] The physical condition profile may include summary information that a manager can use for consultation or explanation.

[0177] For example, the electronic device (100) can generate explanatory information such as “lower limb muscle strength indicators are lower than the standard for the same age group, and balance maintenance time is short, so fall prevention exercises are needed first.”

[0178] This explanatory information may be provided to a user terminal (210) or an administrator terminal (215) and may be used as material to help a member or guardian easily understand the evaluation results.

[0179] The fitness status profile can be structured so that it can be used as input to an exercise guide generation algorithm.

[0180] For example, the profile may include target function groups, risk levels by function group, quantified scores by item, exercise restriction conditions, priority improvement items, inspection status, and correction status. The electronic device (100) can use this information to determine exercise items, exercise intensity, and exercise priority.

[0181] For example, the electronic device (100) can calculate the risk level for each functional group using multiple quantified scores. For example, the group at risk of reduced muscle strength can be calculated based on grip strength scores and chair standing scores (and / or quantified scores for the 30-second chair standing test item), and the group at risk of reduced balance ability can be calculated based on balance maintenance scores and walking speed scores.

[0182] The functional group risk (Rj) can be calculated as Rj = (wi × Si). Here, Rj is the risk for the j-th functional group, S_i is the quantified score of the i-th physical fitness evaluation item, and w_i may be the weight assigned to the i-th physical fitness evaluation item.

[0183] The electronic device (100) can classify a target user into at least one of a plurality of target function groups based on the calculated function group risk. Additionally, the function group risk may be included in a physical condition profile and may be used as information to identify function areas that require priority improvement when generating a customized exercise guide.

[0184] In one embodiment, the physical condition profile may be composed of a table format, a score vector, grade information, a text summary, or a combination thereof.

[0185] For example, the electronic device (100) can generate numerical profiles such as “muscle strength 65 points, balance 42 points, gait stability 48 points, cardiorespiratory endurance 55 points” and simultaneously generate classification profiles such as “group with reduced balance ability and group with reduced gait stability.” Additionally, it can store a separate flag indicating whether re-evaluation is required or whether intensive care is needed for center operation.

[0186] In this way, the physical condition profile can function as an intermediate data structure connecting physical fitness assessment data and exercise guides.

[0187] That is, the electronic device (100) does not simply receive measurement values ​​and immediately recommend exercise, but can convert the target user's physical condition into an interpretable profile and then generate a customized exercise guide based on it.

[0188] As a result, the basis for the exercise guide generation process becomes clearer, and administrator review and user explanation can be facilitated.

[0189] According to one embodiment, the processor (120) can generate a customized exercise guide including recommended exercise items, recommended exercise intensity, and recommended exercise priority based on a fitness status profile and provide it to a user terminal corresponding to the target user (S340).

[0190] The electronic device (100) can generate a customized exercise guide to be provided to a target user based on a physical condition profile. The customized exercise guide may be exercise-related information generated by considering the target user's physical condition, functional group classification results, quantification score, precautions, and exercise capability level. The customized exercise guide may include recommended exercise items, recommended exercise intensity, and recommended exercise priority, and may further include information on exercise frequency, exercise time, precautions, contraindicated movements, step-by-step execution methods, and re-evaluation timing according to the embodiment.

[0191] Recommended exercise items may refer to types of exercise corresponding to the target user's function group and vulnerability indicators.

[0192] For example, if the target user is classified as being at risk of muscle weakness, the electronic device (100) may recommend chair standing exercises, band resistance exercises, lower limb strength strengthening exercises, or light squat assistance exercises.

[0193] For example, if the target user is classified as having reduced balance ability, the electronic device (100) may recommend one-leg support assistance exercises, weight shift training, walking stability training, or fall prevention exercises.

[0194] Recommended exercise intensity can indicate the difficulty or load level of the exercise to be performed by the target user.

[0195] For example, the electronic device (100) can classify exercise intensity as low, medium, or high by referring to the quantified score and risk information included in the fitness status profile.

[0196] For example, for senior users, low-intensity exercise is recommended first in the initial stage to ensure safety, and the exercise intensity can then be adjusted in stages based on evaluation results or exercise history.

[0197] Recommended exercise priority may refer to the order of exercise items among multiple exercise items that should be provided to the target user first or with a higher weight.

[0198] For example, if the target user belongs to both the group at risk of muscle weakness and the group at risk of balance weakness, the electronic device (100) may set balance training related to the risk of falls as the first priority and lower limb strength strengthening exercises as the second priority. Conversely, if the decline in cardiorespiratory endurance is the most pronounced, low-intensity aerobic exercise may be prioritized.

[0199] The electronic device (100) can refer to an exercise item database when generating an exercise guide. The exercise item database may include an exercise name, related function group, recommended target, contraindicated target, basic intensity, difficulty level, recommended number of repetitions, recommended time, and precautions.

[0200] For example, “chair standing” can be classified as an exercise related to lower limb strength, “balancing against a wall” can be classified as an exercise related to balance ability, and “indoor walking” can be classified as an exercise related to cardiorespiratory endurance and walking stability.

[0201] The electronic device (100) can limit or adjust the exercise guide by taking into account the risk factors included in the fitness status profile.

[0202] For example, for users classified as being at risk of falling, balance exercises can be recommended, but high-difficulty balance exercises performed alone may be excluded, and low-risk exercises utilizing a chair or wall as an aid may be recommended first.

[0203] For example, for users whose cardiorespiratory endurance score is lower than their critical endurance score, short-duration repetitive exercises may be recommended rather than long-duration sustained exercises.

[0204] In one embodiment, the electronic device (100) can adjust the exercise ratio when multiple functional groups are identified simultaneously. For example, if the target user belongs to both the group at risk of muscle weakness and the group with reduced balance ability, the electronic device (100) may configure 60% of the total exercise guide as lower limb strength strengthening exercises and 40% as balance training. Alternatively, if the target user's gait stability is more severe, the ratio of balance and gait stability exercises may be set higher.

[0205] A customized exercise guide may be provided to a user terminal (210). The user terminal (210) may be a smartphone, tablet, kiosk, wearable device, or a display device within the center. The electronic device (100) may display a list of exercise items, the order of execution, the number of repetitions, exercise intensity, precautions, and the recommended time for the next evaluation on the user terminal (210). Additionally, the user terminal (210) may provide the exercise guide in the form of text, images, videos, voice guidance, or a checklist.

[0206] The customized exercise guide may be provided to the user terminal (210) after being reviewed through the administrator terminal (215).

[0207] For example, the electronic device (100) first provides an automatically generated draft of an exercise guide to the administrator terminal (215), and the administrator can modify some of the exercise items by taking into account the target user's actual consultation content, whether there is pain, exercise experience, or the operation status of the center program.

[0208] Afterwards, the electronic device (100) can confirm the modified exercise guide as the final guide and provide it to the user terminal (210).

[0209] Personalized exercise guides may also be provided in the form of a results report.

[0210] For example, the electronic device (100) can generate a report including a summary of the target user's physical condition, a functional group classification result, caution items, recommended exercise items, exercise intensity, and exercise priority.

[0211] The results report can be generated in different forms for the user, for guardian explanation, or for internal center management.

[0212] That is, the electronic device (100) according to the present disclosure can perform the primary functions of providing result reports that are easy for members, guardians, and centers to understand, and providing counseling support for managers.

[0213] The electronic device (100) can collect exercise performance results or subsequent evaluation results again after providing a customized exercise guide.

[0214] For example, a user can check whether exercise is performed through a user terminal (210), or an administrator can input exercise participation history through an administrator terminal (215). The electronic device (100) can subsequently use this information to update a fitness status profile or regenerate an exercise guide.

[0215] In this way, the electronic device (100) does not provide a simple list of exercises based on a physical condition profile, but rather determines exercise items, intensity, and priority by considering the functional status and risk factors of the target user, and can provide this in an understandable form through the user terminal (210).

[0216] Accordingly, target users can identify exercise directions suitable for their physical condition, and managers can provide counseling and exercise guidance based on consistent standards.

[0217] In summary, the electronic device (100) can first receive physical fitness evaluation data for a target user through physical fitness evaluation equipment, measurement result sheets, electronic documents, or user input information.

[0218] Afterward, the electronic device (100) can standardize the received physical fitness evaluation data according to a common physical fitness evaluation schema to generate analyzable target data.

[0219] The electronic device (100) can calculate a quantified score for each of a plurality of physical fitness evaluation items by comparing the target data with a preset evaluation standard, and classify the physical functional status of the target user into one or more functional groups using a combination of the quantified scores.

[0220] Next, the electronic device (100) can generate a fitness status profile by combining target data, quantification scores, and functional group classification results, and can generate a customized exercise guide including recommended exercise items, recommended exercise intensity, and recommended exercise priority based on the fitness status profile.

[0221] The generated customized exercise guide may be provided to the user terminal (210), and depending on the embodiment, it may be provided to the user terminal (210) after undergoing review or correction by the administrator terminal (215).

[0222] As an example, it can be assumed that a user, a 72-year-old female, undergoes a regular physical fitness assessment at a senior center. The center manager can upload a result sheet containing the output value of the grip strength measuring device, the chair standing test result, the walking speed measurement result, and the balance maintenance test result to an electronic device (100). The electronic device (100) can extract item names and measurement values ​​from the result sheet and generate target data by mapping each item to a standard item of the common physical fitness assessment schema. Subsequently, the electronic device (100) can calculate a quantitative score for each item by comparing the target data with the evaluation criteria based on age and gender.

[0223] In the example described above, if the chair standing score and walking speed score are low and the balance maintenance score is also below the standard, the electronic device (100) can classify the target user into a group at risk of lower limb muscle strength decline and a group with reduced balance ability. Additionally, the electronic device (100) can generate a physical condition profile that includes the measurement value, score, functional group, caution item, and inspection status of each item. The generated physical condition profile can be used not as a simple result table, but as a data structure that describes the physical functional status of the target user.

[0224] The electronic device (100) can generate a customized exercise guide based on a physical condition profile, including lower limb muscle strengthening exercises, walking stability improvement exercises, and fall prevention balance exercises. In this case, if the target user's balance ability is significantly impaired, the electronic device (100) can set the priority of balance assistance exercises to be high and set the exercise intensity to start at a low level. Additionally, the user terminal (210) may display the exercise name, method of performance, number of repetitions, precautions, and the recommended time for the next evaluation.

[0225] According to the above-described embodiment, the electronic device (100) can convert physical fitness evaluation data of different formats into a common structure, perform quantification and functional group classification according to evaluation criteria, and link this to a physical fitness status profile and a customized exercise guide. Accordingly, the physical fitness evaluation data does not remain merely as a measurement result but can be utilized as a data asset to explain the physical functional status of each user and determine the direction of exercise management. This serves as the basis for the content that the technical concept of the present disclosure is not a tool for reading described results, but a system that converts physical fitness evaluation into an operational asset.

[0226] In this specification, the “common physical fitness assessment schema” may refer to reference information for converting physical fitness assessment data of different formats into a unified data structure. The common physical fitness assessment schema may include physical fitness assessment item names, standard item identifiers, measurement units, allowable ranges, evaluation directions by item, corresponding function groups, reference values ​​by age, reference values ​​by gender, and data source information.

[0227] In this specification, “quantified score” may refer to a score or grade obtained by converting a raw measurement value of a physical fitness evaluation item according to a pre-established evaluation standard. The quantified score may be expressed as a score in the range of 0 to 100 points, a grade value of 1 to 5, a status value such as normal, caution, or danger, or a combination thereof.

[0228] In this specification, “functional group” may refer to a group classified from the perspective of exercise management regarding the physical functional status of the target user. A functional group may include a group at risk of muscle strength decline, a group with reduced balance ability, a group with reduced cardiorespiratory endurance, a group with reduced flexibility, a group with reduced gait stability, a group at risk of falls, a group maintaining function, a group at risk of function decline, or a group with limited function.

[0229] In this specification, “fitness status profile” may refer to a data set structured into an interpretable form of the fitness assessment results of a target user. The fitness status profile may include target data, quantified scores, functional group classification results, reliability scores, items subject to verification, calibration history, risk indicators, priority improvement items, and reference information for generating exercise guides.

[0230] In this specification, “personalized exercise guide” may refer to exercise-related guidance information generated based on the physical fitness profile of a target user. The personalized exercise guide may include at least one of recommended exercise items, recommended exercise intensity, recommended exercise priority, exercise frequency, exercise duration, exercise performance method, precautions, contraindicated movements, and recommended re-evaluation timing.

[0232] Additionally, the electronic device (100) calculates a reliability score based on at least one of whether each of the multiple physical fitness evaluation items included in the target data meets a preset allowable range and whether there is a preset logical consistency between the physical fitness evaluation items, identifies a physical fitness evaluation item whose reliability score is less than a preset standard score as an item to be inspected, provides information regarding the item to be inspected to an administrator terminal (215), corrects the item to be inspected using correction information entered through the administrator terminal (215), and then generates a physical fitness status profile using the target data including the corrected item to be inspected.

[0233] The electronic device (100) can calculate a reliability score for each of the multiple physical fitness evaluation items included in the target data before generating a physical fitness status profile.

[0234] A reliability score may be an indicator of the degree to which a measurement or input value of a corresponding physical fitness assessment item is suitable for use in physical fitness status analysis. For example, a reliability score may be expressed as a numerical value in the range of 0 to 100 points, a grade value such as normal / caution / needs inspection, or a flag value indicating whether inspection is required.

[0235] The electronic device (100) can determine whether a preset allowable range is met in order to calculate a reliability score.

[0236] Here, the allowable range may refer to the range of measurement values ​​that can be normally entered for each physical fitness evaluation item.

[0237] For example, the acceptable range for grip strength measurement results may be set to greater than 0 kg and less than or equal to 100 kg, the acceptable range for chair standing measurement results may be set to greater than 0 seconds and less than or equal to 120 seconds, and the acceptable range for walking speed measurement results may be set to greater than 0 m / s and less than or equal to 3 m / s. These figures may be changed according to the center policy, expert standard table, or equipment characteristics depending on the embodiment.

[0238] For example, if the electronic device (100) incorrectly recognizes “18.0 seconds” as “180 seconds” during the process of extracting a chair standing measurement value from a measurement result sheet image, the value may indicate an abnormally low level of function when compared to general evaluation criteria for the same age group or the same item, even if it falls within a preset allowable range. In this case, the electronic device (100) may additionally perform a judgment of logical consistency between items in addition to a simple allowable range judgment.

[0239] Logical consistency among physical fitness evaluation items may refer to whether a generally expected relationship is maintained among multiple physical fitness evaluation items. For example, if a user with very good chair standing measurement results shows an extremely low value in walking speed measurement results, or if a user with very short balance maintenance time shows a very high score related to walking stability, the electronic device (100) may determine that there is a logical discrepancy between the evaluation items.

[0240] The electronic device (100) can calculate a reliability score based on at least one of whether the acceptable range is met and logical consistency. For example, if the measurement value of a specific physical fitness evaluation item is within the acceptable range and the difference in functional level with the related physical fitness evaluation item is less than a preset threshold, the electronic device (100) can assign a high reliability score to the item. Conversely, if the measurement value is outside the acceptable range or the difference in functional level with the related item is greater than or equal to the threshold, the electronic device (100) can assign a low reliability score to the item.

[0241] A reliability score can be calculated by combining multiple judgment factors. For example, the electronic device (100) may calculate a final reliability score by assigning a first weight to whether the allowable range is satisfied and assigning a second weight to logical consistency between items. Additionally, depending on the embodiment, data source, input method, OCR recognition reliability, equipment identification information, difference value from past evaluation history, or manager inspection history may be further reflected.

[0242] In one embodiment, the electronic device (100) can identify a physical fitness evaluation item with a reliability score lower than a preset reference score as an item subject to inspection. For example, if the reference score is set to 70 points and the reliability score of the walking speed measurement result is calculated as 55 points, the electronic device (100) can identify the walking speed measurement result as an item subject to inspection. An item subject to inspection may refer to an item that requires verification by an administrator or an exercise expert.

[0243] The electronic device (100) can provide information regarding the item subject to inspection to the administrator terminal (215). The information regarding the item subject to inspection may include at least one of the following: item name, raw measurement value, standardized value, quantified score, reliability score, reason for inspection, image of the relevant original document, acceptable range, value of the relevant physical fitness evaluation item, and past evaluation history. Accordingly, the administrator can not only check the value but also check why the item was identified as a subject for inspection.

[0244] For example, the administrator terminal (215) can display information such as “chair standing measurement result: 180 seconds, reliability score: 42 points, reason for inspection: exceeding the allowable range boundary value or discrepancy with the walking speed result.” In addition, the corresponding area of ​​the original result sheet image can be displayed together so that the administrator can verify the actual record. This method reduces the inspection burden on the field manager and prevents incorrectly extracted data from being reflected in the profile creation.

[0245] The electronic device (100) can correct the inspection target item using correction information entered through the administrator terminal (215). Here, correction may include modifying the measurement value, unit, item name, evaluation direction, or mapping result of the inspection target item. For example, if “18.0 seconds” is entered as “180 seconds” due to an OCR recognition error, the administrator can check the original result sheet and enter “18.0 seconds” as the correction value, and the electronic device (100) can reflect the correction value in the target data.

[0246] Correction may not be limited to being performed solely by administrator input. In one embodiment, the electronic device (100) may prioritize reflecting correction information entered through the administrator terminal (215), while also applying a correction rule pre-set according to the embodiment. For example, if a measurement unit is missing, the basic unit of the same equipment may be applied, or if an item name is entered in a non-standard expression, it may be converted to a standard item name of the common physical fitness evaluation schema.

[0247] The electronic device (100) can generate a physical condition profile using target data that includes corrected inspection target items. That is, the physical condition profile is not generated based solely on the initially received source data, but can be generated based on target data that has undergone reliability evaluation, administrator inspection, and correction procedures. Accordingly, the accuracy and reliability of the physical condition profile can be improved.

[0248] For example, prior to calibration, the chair-standing measurement results might be evaluated as having an abnormally low functional level, potentially classifying the target user into the functionally restricted group; however, once the actual measurement values ​​are reflected through administrator corrections, the user can be reclassified into the functional decline risk group or the functional maintenance group. As such, the verification and calibration procedures are not merely simple data modification functions, but rather data quality management processes that directly influence the final functional group classification and the results of exercise guide generation.

[0249] Additionally, the electronic device (100) can store both the data before correction and the data after correction. For example, the electronic device (100) can store the raw input value, the correction value, the reason for correction, the time of correction, the identification information of the person performing the correction, and the reason for identifying the item subject to inspection as history information. This correction history can subsequently be used for data quality analysis, equipment error analysis, manager inspection pattern analysis, or improvement of evaluation criteria.

[0250] In this way, the electronic device (100) evaluates the reliability of the target data before generating a physical condition profile, provides items that do not meet the reliability criteria to the administrator terminal (215), and can correct the items subject to inspection by reflecting the administrator's correction information. Accordingly, the present invention is not limited to simply automatically processing physical condition evaluation data, but can generate a reliable physical condition profile by reflecting the inspection of field experts.

[0251] Additionally or generally, the electronic device (100) can calculate a reliability score for each physical fitness evaluation item included in the target data.

[0252] The reliability score can be calculated based on at least one of the tolerance range fit, logical consistency, and data acquisition reliability.

[0253] The reliability score (R) can be calculated by R = aㆍV + bㆍC + cㆍO. Here, R is the reliability score, V is the acceptance range fit, C is the logical consistency score, O is the data acquisition reliability, and a, b, and c may be pre-set weights corresponding to each element.

[0254] For example, if the acceptable range is met, high consistency with relevant physical fitness evaluation items is shown, and the OCR recognition reliability is high, the reliability score can be calculated as a high value.

[0255] Conversely, if it falls outside the acceptable range or lacks logical consistency, a low reliability score may be calculated, and the electronic device (100) can identify the corresponding physical fitness evaluation item as an item subject to inspection.

[0256] Additionally, multiple functional groups may include a group at risk of muscle strength decline, a group at risk of balance ability decline, a group at risk of cardiorespiratory endurance decline, a group at risk of flexibility decline, a group at risk of gait stability decline, and a group at risk of falls. Furthermore, the correction information may include the correction value, the reason for correction, and the time of correction for the item under inspection.

[0257] A plurality of functional groups used by the electronic device (100) may be reference information for classifying the physical functional status of the target user from the perspective of exercise management. Functional groups may not be information that simply classifies disease names, but may be functional classification information for determining what direction of exercise management is needed based on the results of a physical fitness evaluation. For example, functional groups may include a group at risk of muscle strength decline, a group at risk of balance ability decline, a group at risk of cardiorespiratory endurance decline, a group at risk of flexibility decline, a group at risk of gait stability decline, and a group at risk of falls.

[0258] A group at risk of muscle weakness can be identified if indicators related to the upper limb strength, lower limb strength, or whole-body strength of the target user are lower than pre-set criteria. For example, if the results of grip strength measurement, chair standing measurement, or lower limb strength evaluation are lower than the criteria for the same age group and gender, the electronic device (100) can classify the target user as a group at risk of muscle weakness. Users classified as a group at risk of muscle weakness may have high priority set for resistance exercises, lower limb strength strengthening exercises, or exercises to maintain daily living functions.

[0259] A group with reduced balance ability can be identified if the indicators related to the static or dynamic balance of the target user are lower than the standard. For example, if the time spent standing on one leg, the time spent maintaining balance, weight transfer stability, or the degree of swaying during walking do not meet the standard, the electronic device (100) can classify the target user as having reduced balance ability. Users classified as having reduced balance ability may receive priority fall prevention exercises, balance training using assistive devices, or stability exercises.

[0260] A group with reduced cardiorespiratory endurance can be identified when the target user's ability to sustain physical activity or aerobic capacity is low. For example, if indicators related to a 6-minute walk test, a walking test in place, walking distance within a set period of time, or recovery status after exercise are lower than the standard, the electronic device (100) can classify the target user as having reduced cardiorespiratory endurance. In this case, the customized exercise guide may include low-intensity aerobic exercise, short-duration repetitive exercise, or a method of gradually increasing exercise time.

[0261] A group with reduced flexibility can be identified if physical fitness assessment items related to joint range of motion or muscle extensibility are lower than the standard. For example, if the results of a seated forward bend, shoulder flexibility test, or lower limb posterior muscle flexibility test are low, the electronic device (100) can classify the target user as having reduced flexibility. Users classified as having reduced flexibility may be provided with guidance on stretching, range of motion exercises, or warm-up and cool-down exercises.

[0262] A group with reduced walking stability can be identified if the target user's walking speed, stride length, walking rhythm, turning stability, or ability to maintain balance while walking is reduced. For example, if the walking speed is lower than the standard for the same age group and the balance maintenance score is also low, the electronic device (100) can classify the target user as having reduced walking stability. Users classified as having reduced walking stability may be provided with an exercise guide that combines walking posture improvement, walking assistance training, lower limb muscle strengthening, and balance training.

[0263] A fall risk group can be identified by combining at least one of muscle strength, balance, gait stability, and past fall history. For example, if the balance maintenance score is low, the gait speed score is low, and the lower limb muscle strength score is also low, the electronic device (100) can classify the target user as a fall risk group. For users classified as a fall risk group, exercises with higher safety levels may be recommended over high-difficulty exercises, and the use of assistive devices or the presence of a manager may be recommended when performing exercises.

[0264] Multiple functional groups may not be limited to mutually exclusive classifications. For example, a target user may simultaneously belong to the group at risk of muscle strength decline, the group at risk of balance decline, and the group at risk of falls. In this case, the electronic device (100) may calculate the risk level or score for each functional group together and include information on multiple functional groups in the physical fitness status profile. Additionally, the electronic device (100) may determine which functional group among the multiple functional groups will be prioritized for reflection in the generation of exercise guides.

[0265] In one embodiment, the electronic device (100) may pre-set relevant physical fitness evaluation items for each functional group. For example, a group at risk of muscle strength decline may be associated with grip strength measurement results and chair standing measurement results, a group at risk of balance decline may be associated with balance maintenance measurement results, and a group at risk of walking stability decline may be associated with walking speed measurement results. A group at risk of falling may be determined based on a combination of items related to muscle strength, balance, and walking stability.

[0266] The modification information in claim 3 may refer to information that is input or generated through an administrator terminal (215) to correct an item subject to inspection. The modification information may include a modification value, a reason for modification, and a time of modification for the item subject to inspection. The modification value may refer to a value to be applied to the physical fitness evaluation item after correction, the reason for modification may be information explaining why the administrator modified the value, and the time of modification may refer to information about the time when the modification was made.

[0267] For example, if the electronic device (100) extracts the walking speed as “0.08 m / s” from the result sheet image, but the administrator checks the original result sheet and confirms that the actual value is “0.8 m / s,” the administrator can input “0.8 m / s” as the correction value through the administrator terminal (215). At this time, the reason for the correction may be entered as “OCR decimal point recognition error,” and the correction time may be saved as the time when the correction input is completed.

[0268] As another example, if a specific user's balance maintenance time appears to be significantly lower than past evaluation results, the administrator can confirm through user consultation that there was temporary dizziness on the day of the evaluation. In this case, the administrator can enter content such as "temporary deterioration of condition on the day of evaluation" as the reason for the correction without entering a correction value, and the electronic device (100) can store the information as an inspection history or reference information of the physical condition profile.

[0269] Reasons for correction can be used to distinguish between data errors and actual changes in physical condition. For example, reasons for correction such as “poor equipment sensor contact,” “error in recognizing result sheet numbers,” or “unit input error” may be related to measurement or input errors. On the other hand, reasons for correction such as “left knee pain,” “history of surgery,” “unilateral muscle weakness,” or “recovering after a recent fall” may be related to the target user’s actual physical characteristics.

[0270] The electronic device (100) can correct target data using correction values ​​included in the correction information and manage the correction history using the reason for correction and the time of correction. Accordingly, it can track whether the same item is repeatedly corrected, whether errors frequently occur in specific equipment, or whether discrepancies between items are repeated due to the physical characteristics of a specific user. This information can subsequently be used to adjust the allowable range, supplement logical consistency standards, or fine-tune the customized exercise guide.

[0271] In this way, the functional group information and the correction information each perform different roles. The functional group information is information for classifying the physical functional status of the target user from the perspective of exercise management, and the correction information is information for ensuring the reliability of physical fitness evaluation data and managing correction history. By using these two pieces of information together, the electronic device (100) can more accurately interpret the current functional status of the target user and generate a customized exercise guide by distinguishing between data errors and actual physical characteristics.

[0272] For example, after a physical fitness assessment of a target user is performed at a senior center, the electronic device (100) can generate target data including grip strength measurement results, chair standing measurement results, walking speed measurement results, balance maintenance measurement results, and cardiorespiratory endurance measurement results. The electronic device (100) can determine whether the measurement values ​​of each physical fitness assessment item meet a preset allowable range and determine whether the difference in functional levels between related items exceeds a preset standard, thereby calculating a reliability score for each item.

[0273] For example, if the chair standing measurement result is within the normal range but the walking speed measurement result is extremely low compared to the standard for the same age group, and at the same time the balance maintenance result is also low, the electronic device (100) can calculate a low reliability score for the walking speed measurement result and the balance maintenance measurement result. In this case, if the reliability score is below the standard score, the electronic device (100) identifies the item as an item subject to inspection and can provide inspection request information to the administrator terminal (215).

[0274] The administrator can check the original result sheet, extracted value, allowable range, results of related items, and reliability score through the administrator terminal (215). If the administrator determines that the walking speed value was incorrectly extracted due to an OCR error, the administrator can input the correct walking speed value as the correction value and input “error in recognizing result sheet numbers” as the reason for the correction. The electronic device (100) stores the correction value, the reason for the correction, and the time of the correction, and can generate a physical condition profile using the target data containing the corrected value.

[0275] On the other hand, if the administrator determines that the decrease in walking speed is due to the actual user's condition rather than an error, the administrator may not enter a modified value or may maintain the existing value and enter information such as “decreased walking speed due to left lower limb pain” as the reason for modification. The electronic device (100) stores this reason for modification as an inspection history and can refer to it to classify the target user into a group with reduced walking stability or a group at risk of falling.

[0276] Accordingly, the electronic device (100) can reduce the possibility of errors in physical fitness evaluation data while not unconditionally treating differences between evaluation items caused by the actual user's physical characteristics as errors. That is, according to the present embodiment, the electronic device (100) can perform data quality management and user state analysis together, and ultimately generate a more reliable physical fitness status profile and customized exercise guide.

[0277] Meanwhile, in this specification, “reliability score” may refer to an indicator indicating the degree to which a measured value or input value of a physical fitness evaluation item is suitable for use in generating a physical fitness status profile. The reliability score may be calculated based on at least one of the following: whether an acceptable range is met, logical consistency among physical fitness evaluation items, data source, input method, OCR recognition reliability, equipment identification information, and past evaluation history.

[0278] In this specification, “acceptable range” may refer to the range of values ​​that can be normally entered or measured for each physical fitness evaluation item. The acceptable range may be set differently depending on the type of physical fitness evaluation item, the characteristics of the evaluation equipment, the age and gender of the target user, or the operational standards of the institution.

[0279] In this specification, “logical consistency” may mean whether a pre-established relationship is maintained between multiple physical strength evaluation items. For example, if the difference in functional levels between multiple items reflecting the same or similar physical functions is greater than a pre-established threshold, the electronic device (100) may determine that the logical consistency is low.

[0280] In this specification, “items subject to inspection” may refer to physical fitness evaluation items that require administrator verification because their reliability score is determined to be below a standard score, outside the acceptable range, or lacks logical consistency between items.

[0281] In this specification, “modification information” may refer to correction-related information that is input or generated through the administrator terminal (215). The modification information may include at least one of a modification value, a reason for modification, a time of modification, identification information of the person performing the modification, an original value, a difference value before and after modification, and an inspection opinion.

[0283] Additionally, logical consistency among physical fitness evaluation items is determined based on a pre-established correlation between at least two of the following: grip strength measurement results, chair standing measurement results, walking speed measurement results, balance maintenance measurement results, and cardiorespiratory endurance measurement results; and if the difference between the first functional level corresponding to the evaluation result of the first physical fitness evaluation item and the second functional level corresponding to the evaluation result of the second physical fitness evaluation item is greater than or equal to a pre-established threshold, the first physical fitness evaluation item and the second physical fitness evaluation item may be configured to be identified as items subject to inspection.

[0284] The electronic device (100) can analyze the logical consistency between multiple physical fitness evaluation items to determine the reliability of the physical fitness evaluation data.

[0285] Here, logical consistency may refer to whether the relationship of generally expected functional levels is maintained among multiple physical fitness assessment items that evaluate interrelated physical functions.

[0286] During the physical fitness assessment process, results for specific assessment items may appear abnormal due to equipment errors, input errors, OCR recognition errors, or temporary anomalies in the measurement process. For example, there may be cases where specific measurement items are entered as significantly lower or higher than they actually are, even though the user's overall physical function is good. In such cases, it may be difficult to detect the error through simple acceptance range verification alone.

[0287] The electronic device (100) can perform a logical consistency test using correlations between physical fitness evaluation items to solve the above problem. For example, the grip strength measurement result may reflect the upper limb muscle strength status, the chair standing measurement result may reflect the lower limb muscle strength status, and the walking speed measurement result may reflect mobility ability and lower limb function status. In addition, the balance maintenance measurement result may be related to postural stability and fall risk, and the cardiorespiratory endurance measurement result may be related to the ability to perform continuous activity.

[0288] The electronic device (100) can calculate a functional level corresponding to each of these physical fitness evaluation items. The functional level may be a state value converted according to a pre-set evaluation standard for the result of the corresponding physical fitness evaluation item, and may be expressed in the form of a score, grade, or risk level.

[0289] For example, the electronic device (100) can calculate a first functional level corresponding to the result of measuring grip strength and a second functional level corresponding to the result of measuring walking speed. In addition, it can calculate a third functional level corresponding to the result of measuring standing up from a chair, a fourth functional level corresponding to the result of measuring maintaining balance, and a fifth functional level corresponding to the result of measuring cardiorespiratory endurance.

[0290] In one embodiment, the electronic device (100) can calculate the difference between a plurality of function levels. For example, the first function level may be calculated as high because the grip strength measurement result is evaluated as a higher level compared to the same age group, while the second function level may be calculated as low because the walking speed measurement result is evaluated as very low compared to the same age group.

[0291] The electronic device (100) may determine that there is a lack of logical consistency between the physical fitness evaluation items if the difference between the first function level and the second function level is greater than or equal to a preset threshold. For example, if the first function level is 90 points and the second function level is 30 points, the difference between the two function levels may be 60 points, and if the threshold is set to 40 points, it may be determined that there is a lack of logical consistency.

[0292] Threshold values ​​can be set differently depending on the type of physical fitness assessment item, user age, gender, or the purpose of the assessment. For example, a small difference value may be set as the threshold between items reflecting the same physical function, while a relatively large difference value may be allowed between items reflecting different functional areas.

[0293] The electronic device (100) can identify the corresponding physical fitness evaluation items as candidates for inspection if the difference between the functional levels is greater than a threshold. For example, if the difference between the chair standing measurement result and the walking speed measurement result is excessively large, the electronic device (100) can designate both items as items for inspection.

[0294] Additionally, the electronic device (100) may refer to past evaluation history. For example, if the walking speed and balance maintenance results in the user's past evaluations have consistently remained low, it can be determined as an actual physical function characteristic. On the other hand, if the results were at a normal level in past evaluations but changed drastically only at a specific point in time, the possibility of measurement error can be determined to be high.

[0295] In one embodiment, the electronic device (100) may store correlation information between physical fitness evaluation items in advance. The correlation information may be generated based on expert knowledge, statistical analysis results, or past physical fitness evaluation datasets. For example, grip strength and chair standing results may have a correlation related to the muscle strength function group, and walking speed and balance maintenance results may have a correlation related to the walking stability function group.

[0296] The electronic device (100) can apply a stricter threshold to pairs of physical fitness evaluation items that have a high correlation. Conversely, it can apply a more relaxed threshold to pairs of physical fitness evaluation items that have a relatively low correlation.

[0297] For example, if both the grip strength measurement result and the chair standing measurement result correspond to a muscle strength functional group, the electronic device (100) can be expected that the difference between the two functional levels does not exceed a certain range. On the other hand, since the grip strength measurement result and the cardiorespiratory endurance measurement result reflect different functional areas, a wider range of difference may be allowed.

[0298] In another embodiment, the electronic device (100) can consider not only a simple difference in the level of function but also the direction of the difference in the level of function. For example, if a specific user consistently exhibits left-right physical function imbalance, the difference in the level of function can be determined as an actual physical characteristic rather than an error, even if it occurs repeatedly.

[0299] The electronic device (100) can provide information regarding a physical fitness evaluation item identified as an item subject to inspection to an administrator terminal (215). The administrator can check the raw measurement value, functional level, functional level of the relevant item, functional level difference value, and reason for inspection of the physical fitness evaluation item, and can determine whether there is an actual error based on this.

[0300] In this way, the electronic device (100) can identify input errors, measurement errors, or abnormal data that are difficult to detect with simple tolerance range checks alone by analyzing the logical consistency among multiple physical fitness evaluation items. In addition, it can generate a more reliable physical fitness status profile by distinguishing between actual physical function characteristics and data errors.

[0302] Additionally, the method for generating a customized exercise guide may include: analyzing the reason for modification received from the administrator terminal (215) through a text analysis algorithm based on natural language processing (NLP) to classify whether the cause of occurrence of the item to be inspected corresponds to a first cause category corresponding to measurement error or a second cause category corresponding to physical imbalance characteristics of the target user; if the cause is classified as the first cause category, calculating the cumulative error frequency of the target evaluation equipment based on the modification time included in the reason for modification and identification information of the target evaluation equipment, and if the cumulative error frequency exceeds a threshold value, adjusting the allowable range for the physical fitness evaluation item received from the target evaluation equipment; if the cause is classified as the second cause category, updating the threshold between the first physical fitness evaluation item and the second physical fitness evaluation item upward by reflecting the actual difference value between the first function level and the second function level; and calculating a body asymmetry weight based on the difference ratio between the first function level and the second function level classified as the second cause category, and adjusting the left-right exercise ratio or upper-lower limb exercise balance of the recommended exercise item based on the calculated body asymmetry weight.

[0303] The electronic device (100) can identify the cause of the occurrence of the inspection target item by analyzing the reason for modification entered through the administrator terminal (215).

[0304] Here, the reason for modification may be text information entered by the administrator after verifying the item subject to inspection, and may include sentences such as, for example, "poor sensor contact occurred during measurement," "OCR misrecognition of result sheet," "measurement deviation occurred due to user knee pain," or "reflecting deterioration of left lower limb function."

[0305] The electronic device (100) can input the reason for modification into a natural language processing-based text analysis algorithm to analyze the meaning. The natural language processing algorithm can extract semantic information contained in the reason for modification using morphological analysis, keyword extraction, context analysis, or a pre-trained language model.

[0306] The electronic device (100) can classify the cause of occurrence of an item to be inspected into one of a plurality of cause categories based on the analysis results. For example, if "equipment malfunction," "sensor error," "input error," "OCR recognition error," etc. are included, it can be classified as a measurement error, which is the first cause category.

[0307] On the other hand, if expressions such as "unilateral muscle weakness," "recovering after surgery," "physical imbalance," or "limited joint function" are included, the electronic device (100) can classify this as a physical imbalance characteristic, which is a second cause category.

[0308] The electronic device (100) can store the cause category classification results in an inspection history database and can subsequently be used as training data to improve automatic analysis accuracy when the same or similar inspection reasons occur repeatedly.

[0309] For example, if a correction reason such as "poor sensor contact" is repeatedly entered at a specific center, the electronic device (100) can store the expression as a representative pattern of the measurement error category.

[0310] In this way, the electronic device (100) can not only store the reason for modification but also convert the cause of occurrence inherent in the reason for modification into structured data and perform subsequent judgment logic based thereon.

[0311] The electronic device (100) can analyze the condition of the target evaluation equipment when the cause of occurrence is classified as a measurement error, which is a first cause category.

[0312] The electronic device (100) can collect inspection history generated by specific equipment using modification time and equipment identification information included in the modification reason.

[0313] For example, if 50 measurement errors occurred in the same grip strength measuring device during the last 3 months, the electronic device (100) can calculate the cumulative error frequency of the device.

[0314] The cumulative error frequency can be calculated as at least one of the error occurrence rate relative to the total number of measurements, the number of errors per unit period, or the relative error rate relative to the average of the same equipment group.

[0315] The electronic device (100) can determine that the reliability of the equipment has decreased if the cumulative error frequency exceeds a preset threshold.

[0316] For example, if OCR modification or administrator modification occurs repeatedly in a specific device, the electronic device (100) may apply stricter verification criteria to the data received from the device.

[0317] In this case, the electronic device (100) can reduce the allowable range or strengthen the criteria for identifying inspection targets. For example, if a 20% deviation was previously allowed, it can be changed to allow only a 10% deviation.

[0318] Additionally, the electronic device (100) can provide an equipment inspection notification to the administrator terminal (215) when a specific piece of equipment repeatedly causes an error.

[0319] This method allows for continuous monitoring of the quality status of the equipment itself, going beyond simply inspecting the data. Therefore, the electronic device (100) can improve the data collection environment itself by utilizing the inspection data.

[0320] The electronic device (100) may not treat it as a simple error if the cause of occurrence is classified as a physical imbalance characteristic, which is a second cause category.

[0321] For example, there may be cases where a target user maintains a normal level of grip strength despite having a history of knee surgery, resulting in a low walking speed. In such cases, the difference in functional levels between physical fitness assessment items may be a result that reflects actual physical characteristics.

[0322] The electronic device (100) can determine whether a pattern occurs repeatedly in the user or a similar user group by analyzing the actual difference value between the first function level and the second function level.

[0323] If the same type of functional level difference is repeatedly observed, the electronic device (100) may determine that the existing threshold is too strict.

[0324] Accordingly, the electronic device (100) can increase the threshold for the combination of physical fitness evaluation items. For example, if the existing threshold is 40 points, it can be changed to 50 points or 60 points.

[0325] By adaptively adjusting the threshold in this way, the problem of repeatedly misidentifying differences in functional levels caused by actual physical characteristics as errors can be reduced.

[0326] The electronic device (100) can calculate a body asymmetry weight based on differences in functional levels. The body asymmetry weight may be an indicator representing the degree of imbalance in a specific body part or functional area.

[0327] For example, if the lower limb function level is 30 points and the upper limb function level is 80 points, the electronic device (100) can produce a high body asymmetry weight.

[0328] In addition, asymmetric weights can be calculated by reflecting the difference between left and right grip strength, the difference between left and right balance ability, or the difference between upper and lower limb function.

[0329] The electronic device (100) can apply the calculated body asymmetric weights to the process of creating a customized exercise guide.

[0330] For example, if the function of the left lower limb is significantly lower than the function of the right lower limb, the electronic device (100) can increase the rate of performing left lower limb strengthening exercises.

[0331] In addition, if upper limb function is good but lower limb function is lacking, the electronic device (100) can set the proportion of lower limb exercise in the overall exercise composition to be high.

[0332] For example, if 50% upper limb exercise and 50% lower limb exercise are recommended for a general user, the electronic device (100) can adjust to 30% upper limb exercise and 70% lower limb exercise for a user with reduced lower limb function.

[0333] If the decline in balance ability is pronounced, the priority of balance training exercises can be raised, and if the decline in gait stability is pronounced, the emphasis on gait training and lower limb strength exercises can be increased.

[0334] In this way, the electronic device (100) can continuously improve the criteria for judging logical consistency by utilizing physical imbalance information accumulated during the inspection process, and at the same time, the exercise guide itself can be adjusted to be more suitable for the actual physical characteristics of the target user.

[0335] Therefore, according to the present embodiment, the inspection process is not limited to a simple error removal procedure, but can be utilized as a process for generating feedback data for learning user characteristics and optimizing exercise guides.

[0336] As a result, the electronic device (100) can reduce data quality issues caused by measurement errors while simultaneously generating a customized exercise guide with an improved level of personalization by reflecting actual physical imbalance characteristics in the exercise guide.

[0339] FIG. 4 is a diagram conceptually illustrating the operation method of a customized exercise guide generation system according to one embodiment of the present invention.

[0340] Referring to FIG. 4, the electronic device (100) can perform a series of processing steps including a health evaluation step, a result input and analysis step, an exercise solution generation step, an exercise program provision step, and an institution expert linkage step.

[0341] In one embodiment, the health evaluation step may be a basic data collection step for determining the health status of the target user. For example, the electronic device (100) may collect physical fitness data measured through physical fitness evaluation equipment, body composition analysis results, medical history information, health survey results, or health checkup results. The collected data may be generated in different formats, and the electronic device (100) may convert it into analyzable target data by standardizing it according to a common physical fitness evaluation schema.

[0342] In the result input and analysis step (420), the electronic device (100) can calculate a quantified score for each physical fitness evaluation item based on standardized target data and analyze the user's physical function status. For example, the electronic device (100) can determine the user's muscle strength status, balance ability status, walking stability status, and cardiorespiratory function status by analyzing evaluation results related to grip strength, chair standing, walking speed, balance maintenance ability, and cardiorespiratory endurance. Additionally, the electronic device (100) can classify the user into at least one functional group among a muscle strength decline risk group, a balance ability decline group, a cardiorespiratory endurance decline group, a walking stability decline group, or a fall risk group using a functional group classification algorithm or an artificial intelligence model.

[0343] In the exercise solution generation step, the electronic device (100) can generate a fitness status profile based on the analysis results and generate a customized exercise solution corresponding to the fitness status profile. Here, the exercise solution may not be limited to simple exercise recommendations and may include structured exercise management information including the user's functional status, areas requiring improvement, level of exercise performance, precautions, and exercise goals. For example, the electronic device (100) can generate an exercise solution that includes a fall prevention-centered exercise strategy for a user classified as having reduced balance ability, and a lower limb muscle strength strengthening strategy if lower limb muscle strength is also present.

[0344] In the exercise program provision stage, the electronic device (100) can generate an exercise program that can actually be performed based on an exercise solution. For example, the exercise program may include exercise types, exercise intensity, exercise frequency, exercise duration, exercise sequence, exercise priority, or a step-by-step curriculum. Additionally, the electronic device (100) can generate different exercise programs depending on differences in physical condition profiles, even for users belonging to the same functional group. For example, even if users belong to the same risk group for muscle weakness, a program focused on low-intensity chair exercises may be provided to users in the initial stage, while a strength training program using resistance bands may be provided to users with a relatively higher functional level.

[0345] In one embodiment, the institution expert linkage step may be a follow-up support procedure performed after a customized exercise program is created. The electronic device (100) may provide information on institutions or experts that can support the user's exercise performance based on a physical fitness status profile, functional group classification results, exercise solutions, or exercise program information. For example, the electronic device (100) may provide information on hospitals or clinics for users who require rehabilitation exercises, and information on health exercise centers for users who require exercise for health promotion purposes. Additionally, it may provide information on professional instructors or coaches for users who require professional exercise guidance, and information on public and / or private institutions such as public health centers, associations, or local governments for users who require community health care services.

[0346] Here, the institution expert linkage step may be an additional utilization structure for utilizing the results of physical fitness evaluation data analysis and customized exercise guide generation, which are the core of the present invention, and may be performed selectively according to the embodiment. For example, the electronic device (100) may generate only an exercise program and provide it to the user terminal (210), or it may additionally provide information on institutions or experts to support the performance of the exercise program.

[0347] Additionally, the electronic device (100) can continuously collect information on the user's exercise performance results, re-evaluation results, and changes in health status, and can use this to update the physical fitness profile and regenerate subsequent exercise programs. Accordingly, the present invention can be implemented not as a one-time exercise recommendation system, but as a health management support platform in which physical fitness evaluation, functional status analysis, exercise guide generation, and subsequent management are continuously performed.

[0349] The "evaluation criteria" according to the present disclosure may refer to standard information used to determine the functional status of physical fitness evaluation items.

[0350] Evaluation criteria may include at least one of age, gender, body mass index (BMI), presence of underlying diseases, past health history, normal range for each physical fitness evaluation item, expert criteria table, public institution physical fitness evaluation standards, academic society recommendation standards, or institution-specific operational standards.

[0351] In addition, evaluation criteria may be set differently depending on the type of physical fitness evaluation item or the purpose of the evaluation, and may include standard values ​​stored in a database or standard values ​​set by an administrator according to the embodiment.

[0352] The "common physical fitness assessment schema" according to the present disclosure may mean a standard data structure for converting physical fitness assessment data collected from different physical fitness assessment equipment, assessment agencies, or data formats into the same structure.

[0353] A common physical fitness evaluation schema may include at least one of physical fitness evaluation item identification information, measurement value, measurement unit, measurement time, evaluation institution information, user identification information, and evaluation result information.

[0354] The electronic device (100) can unify the data structure in the subsequent analysis process by converting source data of different formats according to the common physical strength evaluation schema.

[0355] According to the present disclosure, "quantified score" may mean a result obtained by quantifying the measurement results of physical fitness evaluation items according to established evaluation criteria.

[0356] Quantified scores can be expressed in the form of score values, percentile values, grade values, risk values, or standardized scores.

[0357] For example, if the grip strength measurement result falls within the top 20% of the same age group, it can be converted into a quantified score of 80 points or higher, and if the walking speed measurement result falls below the standard, it can be converted into a relatively lower quantified score.

[0358] According to the present disclosure, "functional group" may refer to group information for classifying the physical functional status of a target user from the perspective of exercise management based on the results of a physical fitness evaluation.

[0359] The functional group may include at least one of the following: a group at risk of reduced muscle strength, a group at risk of reduced balance ability, a group at risk of reduced cardiorespiratory endurance, a group at risk of reduced flexibility, a group at risk of reduced gait stability, and a group at risk of falling.

[0360] In addition, the target user may belong to multiple function groups simultaneously, and the electronic device (100) can calculate the risk or priority for each function group together.

[0361] The "physical condition profile" according to the present disclosure may mean a structured set of information representing the current physical function status of a target user.

[0362] A physical fitness status profile may include at least one of physical fitness evaluation item information, quantified score information, functional group information, risk information, inspection history information, reliability information, exercise recommendation information, or health status summary information. The electronic device (100) can generate a customized exercise guide based on the physical fitness status profile.

[0363] The "reliability score" according to the present disclosure may refer to an indicator indicating the degree to which the measurement result or input result of a physical fitness evaluation item is suitable for use in physical fitness status analysis.

[0364] The reliability score can be calculated based on at least one of the following: whether the acceptable range is met, logical consistency among physical fitness evaluation items, data source, OCR recognition reliability, input method, equipment status information, or past inspection history.

[0365] The reliability score can be expressed as a numerical value, a grade value, or a flag indicating whether inspection is required.

[0366] The "allowable range" according to the present disclosure may mean a range of values ​​that can be normally entered or measured for each physical fitness evaluation item.

[0367] The allowable range may be set differently depending on the type of physical fitness evaluation item, the age, gender, and health status of the target user, the standards of the evaluation institution, or the characteristics of the equipment.

[0368] The electronic device (100) can reduce the reliability of the corresponding physical fitness evaluation item or identify it as an item subject to inspection if the measurement result falls outside the above allowable range.

[0369] "Logical consistency" according to the present disclosure may mean whether a pre-established correlation or functional relationship is maintained between two or more physical fitness evaluation items.

[0370] For example, logical consistency may be determined to exist if the functional level corresponding to at least two physical fitness evaluation items among the grip strength measurement results, chair standing measurement results, walking speed measurement results, balance maintenance measurement results, or cardiorespiratory endurance measurement results is maintained within a preset range.

[0371] Conversely, if the difference between function levels exceeds a preset threshold, it may be determined that logical consistency is lacking.

[0372] The "functional level" according to the present disclosure may refer to a functional status indicator converted according to a pre-established evaluation standard based on the evaluation results of a specific physical fitness evaluation item.

[0373] Functional levels can be expressed in the form of scores, grades, risk levels, or functional stages.

[0374] For example, the functional level corresponding to the grip strength measurement result may indicate the upper limb muscle strength status, and the functional level corresponding to the walking speed measurement result may indicate the mobility function status.

[0375] The "threshold value" according to the present disclosure may mean a reference value for comparing the difference between functional levels corresponding to a plurality of physical fitness evaluation items.

[0376] The threshold can be set based on the type of physical fitness evaluation item, characteristics of the target user, past evaluation history, or expert criteria.

[0377] The electronic device (100) may determine that there is a lack of logical consistency between the corresponding physical strength evaluation items if the difference between the functional levels is greater than the threshold value.

[0378] Meanwhile, in this specification, the "first cause category" may refer to cases where the abnormal phenomenon in the physical fitness evaluation results is caused by an error that occurred during the measurement process or the data processing process.

[0379] The first cause category may include at least one of equipment error, sensor error, communication error, input error, OCR recognition error, data conversion error, or user mis-input.

[0380] Additionally, in this specification, the "second cause category" may refer to cases where the abnormality in the physical fitness assessment results is attributed to the actual physical characteristics of the target user.

[0381] The second cause category may include at least one of body asymmetry, unilateral muscle weakness, limited joint function, history of surgery, rehabilitation status, or functional decline due to neuromuscular abnormalities or chronic diseases.

[0382] In this specification, "body asymmetry weight" may refer to weight information indicating the degree of imbalance between body parts or functional areas of a target user.

[0383] Body asymmetry weights can be calculated based on at least one of the difference between upper and lower limb function, difference between left and right function, difference in muscle strength levels, difference in balance ability, or difference in mobility ability.

[0384] The electronic device (100) can adjust exercise items, exercise intensity, or exercise rate using body asymmetric weights.

[0386] The above method for generating a customized exercise guide is,

[0387] The above processor further includes the operation of calculating a final quantified score for the 30-second chair stand test item, which is the target physical fitness evaluation item among the plurality of physical fitness evaluation items, based on [Mathematical Formula 1] below.

[0388]

[0389] S_i corresponds to the final quantified score for the 30-second chair standing test item, X_i corresponds to the actual number of times the 30-second chair standing is performed by the target user, K_i corresponds to the chair standing growth limit constant set based on the age and gender of the target user, k corresponds to the non-linear shape parameter constant, p_ij corresponds to the dynamic damping coefficient of lower limb function due to the pre-set decline in cardiorespiratory endurance, T_j corresponds to the minimum biological requirement threshold of the 6-minute walking distance set based on the age and gender, and X_j corresponds to the actual walking distance data of the target user measured through the 6-minute walking test item set as a cross-reference evaluation item with the 30-second chair standing test item among the plurality of physical fitness evaluation items.

[0390] As described above, the final quantified score is not calculated solely by using the measurement results of the 30-second chair standing test item, but can be calculated by considering the lower limb muscle strength performance ability and the cardiorespiratory endurance-based continuous mobility ability of the subject user.

[0391] Specifically, the final quantified score can simultaneously reflect the level of lower limb muscle strength that enables the target user to repeatedly stand up from a chair for a certain period of time, and the level of cardiorespiratory endurance that allows them to perform walking for a long time.

[0392] In one embodiment, the actual number of repetitions data may correspond to the number of repetitions measured during the process of the target user performing a 30-second chair stand test. The electronic device (100) may receive the actual number of repetitions data from a physical fitness evaluation device, a measurement result sheet, an electronic document, or an external server (220).

[0393] For example, if the target user performs a total of 18 chair standings in 30 seconds, the electronic device (100) can identify the number of performances, 18 times, as actual performance count data.

[0394] In one embodiment, the chair-standing growth limit constant may be set based on statistical data or expert standard tables for the same age group and same gender group.

[0395] The chair stand growth limit constant may be a reference value to reflect the characteristic that the growth rate of the quantified score gradually slows down as the number of performances increases.

[0396] For example, if the growth limit constant for chair standing is set to 20 for a group of women aged 70 or older, the increase in the quantified score may gradually decrease as the actual number of performances approaches 20.

[0397] Accordingly, the electronic device (100) can prevent the problem of excessive score increase that may occur in a simple linear scoring method.

[0398] In one embodiment, the nonlinear shape parameter constant may be a parameter for adjusting the shape of the quantification score increase curve.

[0399] The electronic device (100) can determine non-linear shape parameter constants by using values ​​set by a manager or by analyzing a past physical fitness evaluation dataset.

[0400] For example, if the non-linear shape parameter constant increases, the slope of the score increase with increasing actual execution counts may become steep, and if the non-linear shape parameter constant decreases, a gentler score increase curve may be formed.

[0401] In one embodiment, the lower limb function dynamic damping coefficient due to cardiorespiratory endurance decline may be weighting information to reflect the influence of cross-reference evaluation items on target physical fitness evaluation items.

[0402] The electronic device (100) can set the dynamic damping coefficient using expert criteria, past physical fitness evaluation data, or machine learning-based correlation analysis results.

[0403] For example, if it is determined that a decrease in cardiorespiratory endurance has a significant impact on the results of lower limb function evaluation, the dynamic damping coefficient may be set to a relatively large value.

[0404] Conversely, for groups with a low correlation between cardiorespiratory endurance and lower limb function, the dynamic damping coefficient can be set to a small value.

[0405] In one embodiment, the minimum biological requirement threshold may mean a minimum level of 6-minute walking distance required to perform normal daily activities depending on the age and gender of the target user.

[0406] The electronic device (100) can set a minimum biological requirement threshold using public health standards, clinical evaluation standards, academic society recommendation standards, or expert standard tables.

[0407] For example, if the minimum biological requirement threshold for a specific age group is set to 450 meters, the target user can be judged to have normal mobility ability if they record 450 meters or more in the 6-minute walk test.

[0408] In one embodiment, the actual walking distance data may correspond to the actual distance traveled measured through the 6-minute walking test item.

[0409] The electronic device (100) can obtain the actual walking distance data using walking measurement equipment, wearable sensors, smartphone-based location tracking devices, or measurement result sheets.

[0410] For example, if the target user walks a total of 380 meters in 6 minutes, the electronic device (100) can identify 380 meters as actual walking distance data.

[0411] In mathematical formula 1, the first exponential function term may correspond to a term for non-linearly evaluating lower limb muscle strength performance ability based on the actual number of times the target user performs.

[0412] Additionally, the second exponential function term may correspond to a correction term for attenuating the quantification score if the actual walking distance data falls short of the minimum biological requirement threshold.

[0413] For example, it can be assumed that there are two users who have both performed 20 repetitions in the 30-second chair stand test. In this case, the first user may meet the criteria for the 6-minute walk test, while the second user may fall significantly short of the criteria for the 6-minute walk test.

[0414] In a conventional single-evaluation-item-based scoring method, two users may be assigned the same score, but in this embodiment, the final quantified score of the second user may be calculated attenuated.

[0415] Accordingly, the electronic device (100) can perform a more realistic physical function assessment that takes into account not only simple muscle strength performance ability but also cardiorespiratory endurance and mobility ability.

[0416] In addition, through a cross-correction structure using correlations between multiple physical fitness evaluation items, it is possible to prevent over-evaluation or under-evaluation of specific evaluation items and improve the accuracy and reliability of generating physical fitness status profiles.

[0417] Furthermore, the electronic device (100) can improve the accuracy of functional group classification, physical condition profile generation, and customized exercise guide generation using the final quantification score, and can provide an exercise guide that is more in line with the actual physical function status of the target user.

[0419] The above method for generating a customized exercise guide is,

[0420] The above processor acquires real-time plantar pressure density distribution data generated during the walking of the target user by using a plurality of pressure sensors embedded in a smart insole worn by the target user;

[0421] The operation of the processor to calculate a gait asymmetry index by calculating the difference in ground contact time and the movement trajectory of the center of pressure (CoP) of the left foot and the right foot based on the plantar pressure density distribution data; and

[0422] The above processor includes an operation in which, if the gait asymmetry index exceeds a preset allowable threshold, it updates the risk indicator within the physical condition profile to a fall risk group and forcibly reassigns the unilateral lower limb muscle strengthening exercise item among the recommended exercise priorities included in the customized exercise guide to the first priority and provides it to the user terminal.

[0423] The above gait asymmetry index is calculated based on [Mathematical Formula 2] below, and

[0424]

[0425] G corresponds to the above-mentioned gait asymmetry index, A_T corresponds to the first parameter related to ground contact time, A_P corresponds to the second parameter related to plantar pressure, and A_C corresponds to the third parameter related to movement trajectory, and

[0426] A_T, A_P, and A_C are calculated based on the following [Equation 3], [Equation 4], and [Equation 5], respectively, and

[0427]

[0428]

[0429]

[0430] T_L corresponds to the average ground contact time of the left foot of the target user, T_R corresponds to the average ground contact time of the right foot, and T_avg corresponds to the arithmetic mean of the average ground contact time of the left foot and the average ground contact time of the right foot.

[0431] P_L corresponds to the average plantar pressure of the left foot, P_R corresponds to the average plantar pressure of the right foot, and P_avg corresponds to the arithmetic mean of the average plantar pressure of the left foot and the average plantar pressure of the right foot.

[0432] D_C corresponds to the average deviation distance between the pressure center movement trajectories of the left foot and the right foot, and L_C corresponds to the trajectory reference length set based on the foot length of the target user.

[0433] In one embodiment, the electronic device (100) can acquire real-time plantar pressure density distribution data generated during walking by the target user by using a plurality of pressure sensors embedded in a smart insole worn by the target user. The smart insoles may be placed on the target user's left foot and right foot, respectively, and each smart insole may include a plurality of pressure sensors placed at a position corresponding to at least one of the heel area, midfoot area, forefoot area, or toe area.

[0434] The electronic device (100) can receive pressure data that changes over time from the smart insole. For example, while the target user is walking, the point in time when the left foot contacts the ground, the point in time when the right foot contacts the ground, the magnitude of the pressure applied to each foot, the location where the pressure is concentrated, and the path of the center of pressure can be continuously measured. The electronic device (100) can use this pressure data to analyze the target user's left and right walking pattern.

[0435] In one embodiment, the electronic device (100) can calculate the difference in ground contact time between the left foot and the right foot, the difference in average plantar pressure between the left foot and the right foot, and the difference in the center of pressure movement trajectory between the left foot and the right foot based on plantar pressure density distribution data. Here, ground contact time may refer to the time during which the foot remains in contact with the ground during one walking cycle, average plantar pressure may refer to the average of pressure values ​​applied to a specific foot during the walking process, and the center of pressure movement trajectory may refer to the path along which the center of the plantar pressure changes over time.

[0436] The electronic device (100) can calculate the degree of gait asymmetry of the subject user by comparing the ground contact time, average plantar pressure, and pressure center movement trajectory for the left foot and the right foot, respectively. For example, if the subject user places less weight on one lower limb or if muscle strength in a specific lower limb is reduced, the ground contact time or plantar pressure distribution of the left foot and the right foot may differ from each other. Additionally, if balance ability is reduced, the pressure center movement trajectory may show an abnormal difference between the left and right feet.

[0437] Here, the gait asymmetry index may be an indicator of how unbalanced the left and right gait patterns of the target user are with respect to each other. The first parameter related to ground contact time may be a value reflecting the difference in ground contact time between the left foot and the right foot, the second parameter related to plantar pressure may be a value reflecting the difference in average pressure applied to the left foot and the right foot, and the third parameter related to movement trajectory may be a value reflecting the difference in the movement trajectory of the center of pressure between the left foot and the right foot.

[0438] In one embodiment, the average ground contact time of the left foot may refer to the average time during which the left foot of the target user remains in contact with the ground during the walking process. The electronic device (100) may identify a section in which a pressure signal greater than or equal to a preset pressure reference value is detected in at least one of a plurality of pressure sensors included in the left smart insole as the ground contact section of the left foot. Subsequently, the electronic device (100) may calculate the average ground contact time of the left foot by averaging the duration of the ground contact section of the left foot identified over a plurality of walking cycles.

[0439] In one embodiment, the average ground contact time of the right foot may refer to the average time during which the target user's right foot remains in contact with the ground during walking. The electronic device (100) may identify a section in which a pressure signal greater than or equal to a preset pressure reference value is detected at least in one of a plurality of pressure sensors included in the right smart insole as the ground contact section of the right foot. Subsequently, the electronic device (100) may calculate the average ground contact time of the right foot by averaging the duration of the ground contact section of the right foot identified over a plurality of walking cycles.

[0440] In one embodiment, the arithmetic mean of the ground contact time may be the arithmetic mean of the average ground contact time of the left foot and the average ground contact time of the right foot. Specifically, the arithmetic mean of the ground contact time may be calculated by dividing the sum of the average ground contact time of the left foot and the average ground contact time of the right foot by 2. The electronic device (100) can normalize the difference in left and right ground contact time into a dimensionless ratio using the arithmetic mean of the ground contact time. Accordingly, the relative degree of asymmetry in left and right contact time can be compared even among users with different walking speeds or walking cycles.

[0441] In one embodiment, the average plantar pressure of the left foot may refer to the average value of the plantar pressure applied to the left foot of the target user. The electronic device (100) may calculate the average plantar pressure of the left foot by averaging the pressure values ​​obtained from a plurality of pressure sensors included in the left smart insole in units of a walking cycle or a preset time interval. For example, the electronic device (100) may calculate the average plantar pressure of the left foot using the spatial average and the temporal average of the pressure values ​​measured by the plurality of pressure sensors during the ground contact period of the left foot.

[0442] In one embodiment, the average plantar pressure of the right foot may refer to the average value of the plantar pressure applied to the right foot of the target user. The electronic device (100) may calculate the average plantar pressure of the right foot by averaging the pressure values ​​obtained from a plurality of pressure sensors included in the right smart insole in units of a walking cycle or a preset time interval. For example, the electronic device (100) may calculate the average plantar pressure of the right foot using the spatial average and the temporal average of the pressure values ​​measured by the plurality of pressure sensors during the ground contact period of the right foot.

[0443] In one embodiment, the arithmetic mean of the plantar pressure may be the arithmetic mean of the average plantar pressure of the left foot and the average plantar pressure of the right foot. Specifically, the arithmetic mean of the plantar pressure may be calculated by adding the average plantar pressure of the left foot and the average plantar pressure of the right foot and dividing the result by 2. The electronic device (100) can normalize the difference between the left and right plantar pressures into a dimensionless ratio using the arithmetic mean of the plantar pressure. Accordingly, the relative difference in the left and right pressure distribution can be evaluated while mitigating the influence of absolute pressure values ​​due to differences in user body weight, walking speed, or landing intensity.

[0444] In one embodiment, the average deviation distance between the pressure center movement trajectories may be a value representing the spatial difference between the pressure center movement trajectory of the left foot and the pressure center movement trajectory of the right foot. The electronic device (100) can calculate the pressure center coordinates over time using the location information of a plurality of pressure sensors included in the smart insole and the pressure values ​​measured at each pressure sensor. The pressure center coordinates may be calculated, for example, by weighting the coordinates of each pressure sensor with the pressure values ​​measured at the corresponding pressure sensor.

[0445] The electronic device (100) can generate a left foot pressure center movement trajectory based on the temporal change of the pressure center coordinates for the left foot, and generate a right foot pressure center movement trajectory based on the temporal change of the pressure center coordinates for the right foot. Subsequently, the electronic device (100) can align the left foot pressure center movement trajectory and the right foot pressure center movement trajectory based on a walking cycle, and calculate the average deviation distance between the pressure center movement trajectories by averaging the distance between the left and right pressure center coordinates at corresponding points in time or corresponding walking stages.

[0446] In one embodiment, the trajectory reference length may be a reference length for normalizing the average deviation distance between pressure center movement trajectories. The trajectory reference length may be set based on the foot length of the target user. For example, the trajectory reference length may be set based on the length from the heel area to the toe area of ​​the target user's foot, the length of the smart insole, or foot length information corresponding to the shoe size of the target user. The electronic device (100) may normalize the average deviation distance between pressure center movement trajectories into a dimensionless ratio using the trajectory reference length.

[0447] In mathematical formula 3, the first parameter related to ground contact time may be a value obtained by converting the difference in ground contact time between the left and right feet based on a logarithmic function. The electronic device (100) can cause the gait asymmetry index to change sensitively when the difference in left and right contact time is small, and can mitigate the excessive increase in the parameter value when the difference in left and right contact time is very large. Accordingly, it is possible to prevent the gait asymmetry index from being excessively distorted by temporary measurement noise or abnormal single gait cycles.

[0448] In mathematical formula 4, the second parameter related to plantar pressure may be a value obtained by converting the average plantar pressure difference between the left and right feet based on a logarithmic function. The electronic device (100) can reflect the difference in plantar pressure between the left and right feet in the gait asymmetry index when the user supports weight unevenly on one lower limb. Additionally, through a logarithmic function structure, the effect on the asymmetry index can be gradually mitigated as the pressure difference increases.

[0449] In mathematical formula 5, the third parameter related to the movement trajectory may be a value obtained by converting the average deviation distance between the center of pressure movement trajectories based on an exponential function. The electronic device (100) may calculate a low movement trajectory related value when the difference between the left and right center of pressure movement trajectories is small, and may increase the movement trajectory related value as the difference between the trajectories increases, but saturate within a certain range. Accordingly, the difference in the center of pressure movement pattern caused by reduced walking stability or unilateral lower limb function reduction can be effectively reflected.

[0450] In mathematical formula 2, the gait asymmetry index can be calculated based on a non-linear combination of a first parameter related to ground contact time, a second parameter related to plantar pressure, and a third parameter related to movement trajectory. Specifically, the electronic device (100) can increase the gait asymmetry index non-linearly when the three gait asymmetry elements increase simultaneously. Accordingly, complex abnormal gait patterns can be detected more sensitively than a method that determines asymmetry based on only a single element.

[0451] For example, it can be assumed that the average ground contact time of the subject user's left foot is longer than that of the right foot, the average plantar pressure of the left foot is lower than that of the right foot, and there is a significant difference in the trajectory of the center of pressure shift between the left and right feet. In such cases, the subject user may be unable to place sufficient weight on a specific lower limb or may be unable to maintain stable left-right balance while walking. The electronic device (100) can integrate these multiple abnormal signs into a single gait asymmetry index using mathematical formulas 2 to 5.

[0452] In one embodiment, the electronic device (100) can update the risk indicator within the physical condition profile to a fall risk group if the gait asymmetry index exceeds a preset allowable threshold. For example, even if the target user is classified as a simple muscle weakness risk group in the existing physical condition profile, if the gait asymmetry index calculated through the smart insole exceeds the allowable threshold, the electronic device (100) can add fall risk group information to the target user's risk indicator or increase the existing risk level.

[0453] Additionally, the electronic device (100) can adjust the priority of recommended exercises included in the customized exercise guide based on the gait asymmetry index. For example, if the gait asymmetry index exceeds an allowable threshold, the electronic device (100) can reassign at least one of the unilateral lower limb muscle strengthening exercise item, balance assistance exercise item, or gait stability training item to a higher priority. In particular, if unilateral lower limb muscle weakness is determined to be the main cause of gait asymmetry, the electronic device (100) can forcibly reassign the unilateral lower limb muscle strengthening exercise item to a first priority and provide it to the user terminal (210).

[0454] According to the above-described embodiment, the electronic device (100) can analyze the dynamic walking state of the target user by utilizing not only static physical fitness evaluation results but also plantar pressure density distribution data generated in real time during walking. Accordingly, it is possible to detect left-right walking asymmetry, weight support imbalance, and abnormal pressure center shift patterns that are difficult to identify with conventional grip strength, chair standing, walking speed, or balance maintenance tests alone.

[0455] In addition, the electronic device (100) can directly reflect the results of the gait asymmetry index calculation in updating the physical condition profile and rearranging the customized exercise guide, thereby providing a closed feedback structure that is distinct from simple gait analysis or simple exercise recommendations. That is, since the results of the sensor-based gait analysis are linked to updating risk indicators and adjusting exercise priorities, an exercise guide more suitable for the target user's actual gait condition can be generated.

[0456] Mathematical formulas 2 through 5 have a structure that nonlinearly combines the difference in left and right ground contact time, the difference in left and right plantar pressure, and the difference in the trajectory of the center of pressure movement, respectively, after non-dimensionalizing them. Accordingly, the electronic device (100) can integrate time information, pressure information, and distance information with different units into a single walking asymmetry index.

[0457] In addition, since mathematical formulas 3 and 4 include a transformation structure based on a logarithmic function, they can sensitively reflect changes in gait asymmetry in sections where the left-right difference is small, while preventing the gait asymmetry index from increasing excessively due to abnormally large measurements or transient noise.

[0458] In addition, since mathematical formula 5 includes a saturated structure based on an exponential function, as the deviation of the center of pressure movement trajectory increases, the movement trajectory-related parameters increase, but may have the characteristic of becoming saturated beyond a certain range. Accordingly, the electronic device (100) can effectively reflect the decrease in walking stability while mitigating overestimation caused by extreme sensor error values.

[0459] Furthermore, since mathematical formula 2 combines the first parameter related to ground contact time, the second parameter related to plantar pressure, and the third parameter related to movement trajectory based on an exponential function, the gait asymmetry index can be increased non-linearly when multiple gait abnormality elements occur simultaneously. Accordingly, the electronic device (100) can detect complex signs of fall risk more effectively than a method using only a single gait indicator.

[0460] Consequently, according to the above embodiment, the electronic device (100) can reflect the results of dynamic gait analysis based on smart insoles in the process of generating a physical condition profile and a customized exercise guide. Accordingly, the present invention can provide technical effects that go beyond simple exercise recommendations based on physical fitness evaluation results, such as updating fall risk groups and dynamically rearranging exercise priorities using real-time sensor data generated during the actual walking process.

[0462] The above description is merely an illustrative explanation of the technical concept of the present invention, and those skilled in the art to which the present invention pertains will be able to make various modifications and variations within the scope of the essential characteristics of the present invention.

[0463] Accordingly, the embodiments disclosed in this invention are intended to illustrate, not limit, the technical concept of the invention, and the scope of the technical concept of the invention is not limited by these embodiments. The scope of protection of this invention shall be interpreted by the claims below, and all technical concepts within an equivalent scope shall be interpreted as being included within the scope of rights of this invention.

Claims

Claim 1 A method for generating a customized exercise guide based on evaluation data, performed by an electronic device including a processor, wherein the processor receives physical fitness evaluation data for a target user through physical fitness evaluation equipment, a measurement result sheet, an electronic document, and user input information, and generates target data by standardizing the physical fitness evaluation data according to a pre-set common physical fitness evaluation schema; wherein the processor calculates a plurality of quantified scores for each of a plurality of physical fitness evaluation items by comparing the target data with pre-set evaluation criteria, and classifies the physical functional state of the target user into at least one target functional group among a plurality of functional groups based on the plurality of quantified scores; and wherein the processor generates a physical fitness state profile representing the physical functional state of the target user based on the target data, the plurality of quantified scores, and the at least one target functional group. The processor comprises the operation of generating a customized exercise guide, including recommended exercise items, recommended exercise intensity, and recommended exercise priority, based on the physical fitness status profile, and providing it to a user terminal corresponding to the target user. The operation of generating the physical fitness status profile comprises: the processor calculating a reliability score based on at least one of whether each of the plurality of physical fitness evaluation items included in the target data satisfies a preset allowable range and a preset logical consistency between the physical fitness evaluation items; the processor identifying a physical fitness evaluation item whose reliability score is less than a preset reference score as an item subject to inspection and providing information regarding the item subject to inspection to an administrator terminal; and the processor correcting the item subject to inspection using modification information input through the administrator terminal.The processor includes the operation of generating the physical condition profile using the target data including the corrected inspection target item, and the plurality of functional groups include a group at risk of muscle strength decline, a group at risk of balance ability decline, a group at risk of cardiorespiratory endurance decline, a group at risk of flexibility decline, a group at risk of gait stability decline, and a group at risk of falls; the modification information includes a modification value, a reason for modification, and a time of modification for the inspection target item; the logical consistency among the physical fitness evaluation items is determined based on a pre-set correlation between at least two physical fitness evaluation items among grip strength measurement results, chair standing measurement results, walking speed measurement results, balance maintenance measurement results, and cardiorespiratory endurance measurement results; and the first physical fitness evaluation item and the second physical fitness evaluation item are configured to be identified as inspection target items when the difference between the first functional level corresponding to the evaluation result of the first physical fitness evaluation item and the second functional level corresponding to the evaluation result of the second physical fitness evaluation item is greater than or equal to a pre-set threshold; and the method for generating the customized exercise guide is configured such that the processor analyzes the reason for modification received from the administrator terminal through a natural language processing (NLP)-based text analysis algorithm, and the occurrence of the inspection target item An action of classifying whether the cause is either a first cause category corresponding to a measurement error or a second cause category corresponding to the physical imbalance characteristics of the target user; an action in which, if the cause is classified as the first cause category, the processor calculates the cumulative error frequency of the target evaluation equipment based on the correction time included in the correction reason and the identification information of the target evaluation equipment, and if the cumulative error frequency exceeds a threshold, adjusts the allowable range for the physical fitness evaluation item received from the target evaluation equipment;A method for generating a customized exercise guide, comprising: an operation in which, when the cause of occurrence is classified into the second cause category, the processor upwardly updates the threshold between the first physical fitness evaluation item and the second physical fitness evaluation item by reflecting the actual difference value between the first function level and the second function level; and an operation in which the processor calculates a body asymmetry weight based on the difference ratio between the first function level and the second function level classified into the second cause category, and adjusts the left-right exercise ratio or upper-lower limb exercise balance of the recommended exercise item based on the body asymmetry weight. Claim 2 delete Claim 3 delete Claim 4 delete Claim 5 delete

Images