Method, device and program for recognizing user movement on basis of single large-area pressure sensor

Abstract

According to various embodiments of the present invention, a method for recognizing user movement on the basis of a single large-area pressure sensor is disclosed. The method may comprise the steps of: recognizing a pressure change occurring over time from a single large-area pressure sensor; converting the pressure change into a digital signal so as to generate impact variation data; and determining whether a user moves or falls on the basis of the impact variation data.

Description

User motion recognition method, device, and program based on a single large-area pressure sensor

[0001] The present invention relates to a method, device, and program for recognizing user movement based on a single large-area pressure sensor. Specifically, it relates to a technology capable of detecting pressure changes to determine whether a user is moving, whether they have fallen, and the amount of momentum, and thereby recognizing the user's movement state.

[0002]

[0003] In modern society, technologies that analyze and utilize human movement are gaining increasing importance across various fields. For instance, technologies such as gait pattern analysis, momentum calculation, and fall detection are being employed in medical and healthcare, sports performance enhancement, rehabilitation, and safety management for the elderly. To this end, various physical sensors, including pressure sensors, are utilized; common methods include multi-array systems employing multiple pressure sensors or combinations of acceleration and tilt sensors.

[0004] While existing technologies offer advantages such as high resolution or the ability to precisely estimate specific movements, systems utilizing multiple sensors face challenges regarding hardware configuration complexity and high costs. Furthermore, the high power consumption required to operate multiple sensors can reduce the efficiency of the device. In addition, existing technologies rely on the physical characteristics of sensors and limited data analysis methods, which leads to issues such as an inability to adequately reflect complex user movements or reduced accuracy in functions like fall detection.

[0005] Furthermore, systems using multi-array pressure sensors often face limitations in commercialization due to complex installation processes and difficult maintenance. However, demand for such technology remains high, and various attempts are being made in related fields to address these issues. In this regard, Korean Published Patent No. 10-2011-0008644 discloses a fall patient monitoring system using a pressure pad.

[0006]

[0007] The present invention, devised in response to the aforementioned background technology, aims to provide a user motion recognition method, apparatus, and program based on a single large-area pressure sensor.

[0008] 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.

[0009]

[0010] According to an embodiment of the present invention for solving the problem described above, a method for recognizing user movement based on a single large-area pressure sensor is disclosed. The method may include: a step of recognizing a pressure change occurring over time from a single large-area pressure sensor; a step of converting the pressure change into a digital signal to generate impact change data; and a step of determining whether the user is moving or has fallen based on the impact change data.

[0011] In an alternative embodiment, the step of recognizing a pressure change occurring over time from the single large-area pressure sensor may include: determining a reference value of the single large-area pressure sensor; sampling a resistance value recognized according to an external shock occurring within the detection area of ​​the pressure sensor; and processing the sampled resistance value at a preset time interval to recognize a change value relative to the reference value as the pressure change.

[0012] In an alternative embodiment, the step of converting the pressure change into a digital signal to generate the impulse change data may include: a step of sampling the resistance value with an analog-to-digital converter to convert it into digital data; and a step of dividing the digital data into preset time units to generate the impulse change data.

[0013] In an alternative embodiment, the step of determining whether a user moves or falls based on the impact change data comprises the step of inputting the impact change data into a pre-trained motion analysis model to determine whether the user moves or falls; wherein the motion analysis model is composed of a neural network-based machine learning algorithm and can be pre-trained based on learning data regarding movement patterns and fall patterns.

[0014] In an alternative embodiment, the method further comprises the step of calculating momentum based on the movement of the user when it is determined that the user is moving; and the step of calculating momentum based on the movement of the user may include the step of calculating location information where movement occurred based on the pressure change for each preset time interval; the step of calculating walking speed, stride distance, and time between walks based on the location information; and the step of calculating momentum of the user based on the walking speed, stride distance, and time between walks.

[0015] In an alternative embodiment, the method may further include the step of generating an alarm signal and transmitting it to an external device when the fall is determined.

[0016] In an alternative embodiment, the method may further include the step of resetting the reference value of the single large-area pressure sensor at preset intervals.

[0017] In an alternative embodiment, the method may include the step of transmitting the result of determining whether there is movement or a fall and the result of calculating momentum to a server, gateway, or user terminal.

[0018] According to one embodiment of the present invention for solving the above-described problem, an apparatus is disclosed. The apparatus comprises: a memory for storing one or more instructions; and a processor for executing the one or more instructions stored in the memory, and the processor can perform the above-described methods by executing the one or more instructions.

[0019] According to one embodiment of the present invention for solving the above-described problem, a computer program stored on a computer-readable recording medium is disclosed, which is combined with a computer as hardware to perform the above-described methods.

[0020] Other specific details of the present invention are included in the detailed description and drawings.

[0021]

[0022] The present invention recognizes user movement based on a single large-area pressure sensor and determines whether the user is moving, whether they have fallen, and the amount of momentum, thereby solving the problems of complexity and high cost associated with multi-array methods using multiple sensors, and enables movement analysis that maintains high reliability and accuracy while using a single sensor.

[0023] The effects of the present invention are not limited to those mentioned above, and other unmentioned effects will be clearly understood by a person skilled in the art from the description below.

[0024]

[0025] FIG. 1 is a drawing illustrating a system according to one embodiment of the present invention.

[0026] FIG. 2 is a hardware configuration diagram of a computing device according to one embodiment of the present invention.

[0027] FIG. 3 is a drawing for explaining a single large-area pressure sensor according to one embodiment of the present invention.

[0028] FIGS. 4 to 6 are drawings illustrating a user movement recognition method based on a single large-area pressure sensor according to an embodiment of the present invention.

[0029]

[0030] Various embodiments are now described with reference to the drawings. In this specification, various descriptions are provided to facilitate an understanding of the invention. However, it is evident that these embodiments can be practiced without such specific descriptions.

[0031] As used herein, terms such as “component,” “module,” “system,” etc. refer to computer-related entities, hardware, firmware, software, combinations of software and hardware, or executions of software. For example, a component may be, but is not limited to, a procedure executed on a processor, a processor, an object, an execution thread, a program, and / or a computer. For example, both an application executed on a computing device and the computing device itself may be a component. One or more components may reside within a processor and / or an execution thread. A component may be localized within a single computer. A component may be distributed among two or more computers. Additionally, these components may be executed from various computer-readable media having various data structures stored therein. Components may communicate through local and / or remote processes, for example, according to signals having one or more data packets (e.g., data from a component interacting with another component in a local system or distributed system, and / or data transmitted through signals to other systems and networks such as the Internet).

[0032] Furthermore, the term "or" is intended to mean an implicit "or" rather than an exclusive "or." That is, unless otherwise specified or evident from the context, "X uses A or B" is intended to mean one of the natural implicit substitutions. In other words, if X uses A; if X uses B; or if X uses both A and B, "X uses A or B" may apply to any of these cases. Additionally, the term "and / or" as used herein should be understood to refer to and include all possible combinations of one or more of the enumerated related items.

[0033] Additionally, the terms “comprising” and / or “comprising” should be understood to mean that such features and / or components are present. However, the terms “comprising” and / or “comprising” should be understood not to exclude the presence or addition of one or more other features, components and / or groups thereof. Furthermore, unless otherwise specified or clearly evident from the context to indicate a singular form, the singular in this specification and claims should generally be interpreted to mean “one or more.”

[0034] Those skilled in the art should recognize that the various exemplary logical blocks, configurations, modules, circuits, means, logics, and algorithmic steps described in connection with the embodiments disclosed herein may be implemented in electronic hardware, computer software, or a combination of both. To clearly exemplify the interchangeability of hardware and software, various exemplary components, blocks, configurations, means, logics, modules, circuits, and steps have been generally described above in terms of their functionality. Whether such functionality is implemented in hardware or software depends on the specific application and design constraints imposed on the overall system. Skilled technicians may implement the described functionality in various ways for each specific application. However, such decisions regarding implementation should not be interpreted as moving out of the scope of the invention.

[0035] The description of the presented embodiments is provided to enable those skilled in the art to use or practice the present invention. Various modifications to these embodiments will be apparent to those skilled in the art. The general principles defined herein may be applied to other embodiments without departing from the scope of the present invention. Thus, the present invention is not limited to the embodiments presented herein. The present invention should be interpreted in the broadest possible scope consistent with the principles and novel features presented herein.

[0036] In this specification, the term "computer" refers to any type of hardware device comprising at least one processor, and may be understood to include software configurations operating on said hardware device according to the embodiments. For example, the term "computer" may be understood to include smartphones, tablet PCs, desktops, laptops, and user clients and applications running on each of these devices, but is not limited thereto.

[0037] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings.

[0038] Each step described in this specification is described as being performed by a computer, but the subject of each step is not limited thereto, and depending on the embodiment, at least some of each step may be performed on different devices.

[0039]

[0040] FIG. 1 is a drawing illustrating a system according to one embodiment of the present invention.

[0041] Referring to FIG. 1, a system according to one embodiment of the present invention may include a computing device (100), a single large-area pressure sensor (200), a user terminal (300), and an external server (400). The system illustrated in FIG. 1 is according to one embodiment, and its components are not limited to the embodiment illustrated in FIG. 1 and may be added, changed, or deleted as needed.

[0042] In one embodiment, the computing device (100) can recognize user movement based on a single large-area pressure sensor. For example, the computing device (100) can recognize whether the user is moving, whether they have fallen, and the amount of movement, etc., by using pressure changes recognized through the single large-area pressure sensor.

[0043] Specifically, the computing device (100) can recognize pressure changes occurring over time from a single large-area pressure sensor (200). Additionally, the computing device (100) can convert the pressure changes into digital signals to generate impact change data. Furthermore, the computing device (100) can determine whether the user is moving or has fallen based on the impact change data.

[0044] Accordingly, the computing device (100) of the present invention can provide a user movement recognition function that utilizes a single large-area pressure sensor to precisely analyze the user's movement, accurately determine whether movement and falls have occurred, and provide additional information such as the calculation of momentum.

[0045] Hereinafter, an example of a method in which a computing device (100) recognizes user movement based on a single large-area pressure sensor is described with reference to FIGS. 4 to 6.

[0046] In various embodiments, the computing device (100) may provide Web or Application-based services. However, it is not limited thereto.

[0047] The computing device (100) may include any type of computer system or computer device, such as, for example, a microprocessor, a mainframe computer, a digital processor, a portable device, and a device controller. However, it is not limited thereto.

[0048] Hereinafter, the hardware configuration of the computing device (100) will be described with reference to FIG. 2.

[0049] In one embodiment, unlike conventional multi-array sensor methods, a single large-area pressure sensor (200) can be implemented in the form of a flexible film having a single continuous sensing area, and can be manufactured by coating a pressure-sensitive (piezoresistive) material to a certain thickness or through a thin-film process. For example, the single large-area pressure sensor (200) can be implemented to detect pressure changes over a large area as a single structure by laminating an electrode layer and a pressure-sensitive material on a flexible substrate and then forming a protective layer. This allows for a reduction in the number of components, lowering power consumption, and facilitating installation and maintenance compared to conventional multi-array sensors.

[0050] Additionally, the single large-area pressure sensor (200) can be designed to observe changes in resistance occurring across the entire surface without separate sections in order to continuously detect pressure generated during a person's footsteps or falls. Therefore, the computing device (100) can not only detect impacts concentrated in a specific area through the single large-area pressure sensor (200), but also identify pressure changes distributed across the entire sensor area in real time, thereby comprehensively analyzing how far the user's movement or fall has occurred.

[0051] Hereinafter, a description of the single large-area pressure sensor (200) will be given with reference to FIG. 3.

[0052] Meanwhile, the user terminal (300) may be connected to the computing device (100) via a network (500) and may be the terminal of a user to be recognized, such as whether there is movement, whether there has been a fall, and the amount of activity, which is determined by the computing device (100). Additionally, the user terminal (300) may include the terminal of the guardian of the user to be recognized.

[0053] Here, the user terminal (300) may include, for example, various types of computer devices. Specifically, for example, the user terminal (300) may refer to various terminal devices such as smartphones, tablet PCs, desktops, and laptops.

[0054] The user terminal (300) includes a display on at least a part of the terminal and may include an operating system for running applications or extension-based services provided by the computing device (100). For example, the user terminal (300) may be a smartphone, but is not limited thereto, and the user terminal (300) may include all kinds of handheld-based wireless communication devices such as navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) terminal, smartpad, tablet PC, etc., as wireless communication devices that ensure portability and mobility.

[0055] An external server (400) can be connected to a computing device (100) via a network (500), and can transmit and receive various information / data necessary for the computing device (100) to recognize user movement based on a single large-area pressure sensor, and can store and manage various information / data generated as the computing device (100) recognizes user movement based on the single large-area pressure sensor.

[0056] For example, the external server (400) may be a database server that stores information used in a single large-area pressure sensor-based user motion recognition method. As another example, the external server (400) may be a server that provides information used in a single large-area pressure sensor-based user motion recognition method.

[0057] The network (500) may refer to a connection structure capable of exchanging information between each node, such as computing devices, multiple terminals, and servers. For example, the network (500) includes a Local Area Network (LAN), a Wide Area Network (WAN), the World Wide Web (WWW), a wired and wireless data network, a telephone network, a wired and wireless television network, etc.

[0058] Wireless data communication networks include, but are not limited to, 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), 5GPP (5th Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), Wi-Fi, Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth network, NFC (Near-Field Communication) network, satellite broadcasting network, analog broadcasting network, DMB (Digital Multimedia Broadcasting) network, etc.

[0059]

[0060] FIG. 2 is a hardware configuration diagram of a computing device according to one embodiment of the present invention.

[0061] Referring to FIG. 2, a computing device (100) according to one embodiment of the present invention may include one or more processors (110), a memory (120) for loading a computer program (151) executed by the processor (110), a bus (130), a communication interface (140), and a storage (150) for storing the computer program (151). Here, FIG. 2 illustrates only the components related to the embodiment of the present invention. Therefore, a person skilled in the art to which the present invention pertains will understand that other general-purpose components may be included in addition to the components illustrated in FIG. 2.

[0062] The processor (110) controls the overall operation of each component of the computing device (100). The processor (110) may be composed of one or more cores and may include processors for data analysis and deep learning, such as a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), or a tensor processing unit (TPU) of the computing device. Alternatively, it may be configured to include any type of processor well known in the art of the present invention.

[0063] Additionally, the processor (110) can perform operations for at least one application or program for executing the method according to embodiments of the present invention, and the computing device (100) may have one or more processors.

[0064] In various embodiments, the processor (110) may further include RAM (Random Access Memory, not shown) and ROM (Read-Only Memory, not shown) for temporarily and / or permanently storing signals (or data) processed within the processor (110). Additionally, the processor (110) may be implemented in the form of a system-on-chip (SoC) comprising at least one of a graphics processing unit, RAM, and ROM.

[0065] Memory (120) stores various data, instructions and / or information. Memory (120) may load a computer program (151) from storage (150) to execute a method / operation according to various embodiments of the present invention. When the computer program (151) is loaded into memory (120), the processor (110) may perform the method / operation by executing one or more instructions constituting the computer program (151). Memory (120) may be implemented as volatile memory such as RAM, but the technical scope of the present invention is not limited thereto.

[0066] The bus (130) provides communication functions between components of the computing device (100). The bus (130) can be implemented as various types of buses, such as an address bus, a data bus, and a control bus.

[0067] The communication interface (140) supports wired and wireless internet communication of the computing device (100). Additionally, the communication interface (140) may support various communication methods other than internet communication. To this end, the communication interface (140) may be configured to include a communication module well known in the art of the present invention. In some embodiments, the communication interface (140) may be omitted.

[0068] Storage (150) can store a computer program (151) non-temporarily. When performing a process according to an embodiment of the present invention through a computing device (100), storage (150) can store various information necessary to perform a method according to the disclosed embodiment or to provide a service.

[0069] The storage (150) may be configured to include non-volatile memory such as ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), flash memory, a hard disk, a removable disk, or any form of computer-readable recording medium well known in the art to which the present invention belongs.

[0070] A computer program (151) may include one or more instructions that cause a processor (110) to perform a method / operation according to various embodiments of the present invention when loaded into memory (120). That is, the processor (110) may perform the method / operation according to various embodiments of the present invention by executing the one or more instructions.

[0071] In one embodiment, the computer program (151) may include one or more instructions to perform various methods related to various tasks related to learning a neural network model.

[0072] The steps of the method or algorithm described in connection with embodiments of the present invention may be implemented directly in hardware, implemented as a software module executed by hardware, or implemented by a combination thereof. The software module may reside in RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), Flash Memory, a hard disk, a removable disk, a CD-ROM, or any form of computer-readable recording medium well known in the art to which the present invention belongs.

[0073] The components of the present invention may be implemented as a program (or application) and stored on a medium to be executed in combination with a computer, which is hardware. The components of the present invention may be implemented as software programming or software elements, and similarly, embodiments may be implemented in programming or scripting languages ​​such as C, C++, Java, assembler, etc., including various algorithms implemented as combinations of data structures, processes, routines, or other programming configurations. Functional aspects may be implemented as algorithms executed on one or more processors.

[0074]

[0075] FIG. 3 is a drawing for explaining a single large-area pressure sensor according to one embodiment of the present invention.

[0076] Referring to FIG. 3, a single large-area pressure sensor (200) has a structure having a single continuous sensing area, and can measure pressure changes occurring when a user walks over the sensor in an integrated manner across the entire sensor area. Unlike conventional methods in which multiple sensors are arranged in a grid shape, this significantly reduces complex arrangement design and wiring work by allowing the entire sensor surface to function as a single sensing unit.

[0077] For example, the footprint shape illustrated in FIG. 3 is a visual representation of how pressure patterns generated at a location are distributed spatiotemporally when a user walks over a single large-area pressure sensor (200). The user's footsteps generate locally high pressure values ​​on the sensor surface, and as the footstep position moves over time, the pressure distribution within the entire sensor area also changes continuously. Through this, walking patterns, movement paths, and the magnitude of impact can be analyzed using only a single sensor structure.

[0078] Additionally, the communication line (201) shown near the edge of the single large-area pressure sensor (200) may represent a corner of the sensor or a physical or electronic connection between the sensor and an external module. This may include power supply lines, signal lines, ground lines, etc., and in actual implementation, the arrangement and shape of the wiring may vary depending on the structure of the sensor surface or the installation environment. Since the communication line (201) in FIG. 3 is an exemplary representation for illustrative purposes, in reality, it can be configured in various ways, such as drawing lines from various areas or corners of the sensor or implementing them in the form of a connector.

[0079] As shown in FIG. 3, by applying a single large-area pressure sensor (200), a wide range can be uniformly detected without a complex sensor array. In particular, since pressure changes can be measured continuously and in real time across the entire sensor area regardless of where a user's footstep is applied within the sensor, more accurate tracking of movement paths and analysis of walking patterns can be achieved. Through this, the computing device (100) can intuitively and precisely measure the user's movement speed, stride length, and whether a fall has occurred by combining pressure values ​​and time information at each point, and can achieve highly reliable movement recognition by linking with a machine learning-based analysis module.

[0080]

[0081] FIGS. 4 to 6 are drawings illustrating a user movement recognition method based on a single large-area pressure sensor according to an embodiment of the present invention.

[0082] Referring to FIG. 4, the computing device (100) can recognize pressure changes occurring over time from a single large-area pressure sensor (200) (S110).

[0083] Specifically, referring to FIG. 5, the computing device (100) can determine a reference value of a single large-area pressure sensor (200) (S111).

[0084] The computing device (100) can determine a reference value in a normal environment (i.e., a state in which there is little to no movement or only minute vibrations in a negligible range) by sampling the resistance value measured in the initial installation state or stabilization section of a single large-area pressure sensor (200) multiple times and statistically analyzing it.

[0085] For example, pressure data applied to the sensor surface for a certain period of time (e.g., from a few seconds to a few minutes) can be collected, and then the average value, standard deviation, etc. can be calculated and set as a reference value. Here, the computing device (100) may not only measure the reference value at the time of initial installation but may also periodically update the reference value to account for changes in the characteristics of the sensor element or environmental factors (temperature, humidity, etc.).

[0086] Additionally, the computing device (100) can sample a resistance value recognized according to an external shock occurring within the detection area of ​​the pressure sensor (S112).

[0087] For example, when a person walks over the sensor or an object falls, the single large-area pressure sensor (200) outputs a resistance value that changes over time. The computing device (100) samples the resistance value at a constant frequency (e.g., 100Hz, 200Hz, etc.) to recognize even minute changes in impact.

[0088] And, the computing device (100) can process the sampled resistance value at a preset time interval (e.g., several milliseconds to several seconds) to recognize the change value relative to the reference value as a pressure change.

[0089] More specifically, the computing device (100) can calculate how much change has occurred relative to a reference value by accumulating, averaging, or filtering the sampled resistance values, and recognize this as a 'pressure change'.

[0090] For example, the computing device (100) may obtain instantaneous pressure difference in a manner such as Δr = r_sample - r_base, or extract data close to the actual change in impulse by analyzing with a modeling that includes exponential damping characteristics (α (damping coefficient), ε (noise error), etc.).

[0091] In one embodiment, the computing device (100) can convert pressure change into a digital signal to generate impact change data (S120).

[0092] Specifically, referring to FIG. 6, the computing device (100) can convert resistance values ​​into digital data by sampling them with an analog-to-digital converter (S121).

[0093] More specifically, the computing device (100) inputs an analog voltage or current signal output from a single large-area pressure sensor (200) into an ADC module to obtain a digitized sample (e.g., 10-bit, 12-bit resolution, etc.), and in this process, to minimize deviation or noise in the sensor output, excess and outlier removal, a low-pass filter, a moving average filter, etc. may be applied.

[0094] And, the computing device (100) can generate impact change data by dividing digital data into preset time units (S122).

[0095] For example, the computing device (100) can group digital samples collected in units of 10ms to 100ms into a single block to organize how the pressure changed during that period (maximum value, minimum value, average value, or damping characteristics, etc.). Then, the computing device (100) can continuously stitch together time-divided impact changes to identify pressure fluctuation patterns that occur as a user moves over the sensor, or to detect events where a large impact is applied at a rapid speed, such as a fall.

[0096] In one embodiment, the computing device (100) can determine whether the user is moving or falling based on impact change data (S130).

[0097] Specifically, the computing device (100) can input impact change data into a pre-trained motion analysis model to determine whether there is movement or a fall. Here, the motion analysis model is composed of a neural network-based machine learning algorithm (e.g., an algorithm of various structures such as CNN, RNN, LSTM, etc.) and can be pre-trained based on learning data regarding movement patterns and fall patterns. For example, in the case of a fall, a large impact change occurs instantaneously followed by a pattern of no additional movement for a relatively long period, whereas in the case of normal movement, a continuous footprint pattern occurs at relatively constant intervals. The model learns these differences and can probabilistically determine whether the user is moving or has fallen by analyzing the input impact change data.

[0098] More specifically, the computing device (100) may determine whether there is movement or a fall by comparing the output value of the motion analysis model (e.g., mobility probability score, fall probability score, etc.) with a threshold, or may use a method of increasing accuracy by ensembling multiple models.

[0099] Additionally, if a fall is suspected, the computing device (100) may comprehensively review the previously recorded rate of increase in impact force and maximum value, or determine that the fall is effectively confirmed if no movement is detected for a certain period of time or longer. The results of this model-based analysis may be stored in a separate memory or transmitted to a user terminal (such as a smartphone) or an external server to be utilized for taking follow-up actions.

[0100] Accordingly, the computing device (100) of the present invention measures and analyzes the resistance value of a single large-area pressure sensor (200) over time, converts it into a digital signal to derive impact change data, and then can precisely determine whether there is movement or a fall through machine learning-based analysis.

[0101] Through this, the present invention can achieve the accuracy required for user safety management and motion analysis while maintaining simple installation and low costs compared to existing methods that arrange multiple sensors, despite having a single sensor structure.

[0102]

[0103] According to various embodiments of the present invention, when a computing device (100) determines that a user is moving, it can calculate a momentum based on the user's movement.

[0104] Specifically, the computing device (100) can calculate location information where movement occurred based on pressure changes in preset time intervals. That is, the computing device (100) can calculate location information where movement occurred by analyzing pressure changes in preset time intervals to track the user's movement path or by inversely calculating the spatiotemporal distribution of the impact amount generated within the sensor area.

[0105] For example, a computing device (100) can investigate the pressure change accumulated at regular time intervals from t_0 to t_1 on a single large-area pressure sensor (200) and calculate how the pressure center on the sensor has moved during that period.

[0106] In a more specific way, the computing device (100) may use a method of dividing the sensor area into a virtual grid and then integrating the pressure values ​​(or resistance values) detected at each grid point to obtain the centroid. Here, by connecting the continuous change of the centroid along the time axis, the trajectory of the user's movement can be approximated, and if a pattern of pressure rising and falling at a specific location is detected, it can be determined as the point where the foot was placed.

[0107] Additionally, the computing device (100) can calculate walking speed, stride distance, and time between walks based on location information. And, the computing device (100) can calculate the user's exercise amount based on walking speed, stride distance, and time between walks.

[0108] Specifically, the computing device (100) measures the distance S traveled over the sensor at preset time intervals Δt and can calculate the walking speed v = S / Δt.

[0109] For example, the computing device (100) can calculate the stride distance by accumulating the coordinate difference between consecutive points where the user's footprint is detected, or by measuring the point of sudden change in pressure as the step point. Then, the computing device (100) can convert the calculated walking speed v, stride distance S, time between steps Δt, and the user's weight m into momentum p = m × v.

[0110] Additionally, the computing device (100) may comprehensively analyze walking patterns (e.g., regular stride, irregular stride, stationary movement, etc.) to be used for various algorithms such as fall risk or exercise intensity analysis.

[0111] For example, the computing device (100) can measure the time difference between foot placement positions and the stride interval to precisely calculate the walking rhythm or walking symmetry (balance between both feet), and use this for specific signs of gait abnormalities or musculoskeletal rehabilitation evaluation.

[0112] Accordingly, the computing device (100) of the present invention can provide high-precision walking and motion analysis services with a simple, low-cost structure compared to the conventional method of arranging multiple sensors by precisely extracting user movement information based on pressure changes obtained through a single large-area pressure sensor and calculating momentum based on walking speed, stride distance, time between walks, etc.

[0113]

[0114] According to various embodiments of the present invention, when a fall is determined, the computing device (100) can generate an alarm signal and transmit it to an external device.

[0115] Specifically, when the computing device (100) identifies a pattern presumed to be a fall in the impact change data, it can immediately recognize this as an alarm event and transmit it to a user terminal (smartphone, etc.), a guardian terminal, or a medical institution server.

[0116] More specifically, the computing device (100) can comprehensively consider the rapid increase in impact force and the absence of additional movement that occurs thereafter to determine whether a fall has occurred.

[0117] For example, a computing device (100) may determine that a fall has occurred if no significant movement (e.g., pressure change or position change) is detected on the sensor for a certain period of time after a large pressure spike occurs within a short period (e.g., within 0.5 seconds). In this case, the alarm signal may include the time at which the fall occurred, the estimated location, and the trend of pressure change immediately before and after the fall.

[0118] Accordingly, the computing device (100) can provide an immediate notification when a fall occurs, enabling emergency rescue or immediate action, and can perform user safety management more efficiently by linking with a biosignal monitoring system or a hospital emergency server.

[0119]

[0120] According to various embodiments of the present invention, the computing device (100) can reset the reference value of a single large-area pressure sensor (200) at preset intervals.

[0121] Specifically, the computing device (100) can re-evaluate the sensor output and update the reference value at regular intervals (e.g., daily or user-specified time intervals) to compensate for sensor drift caused by changes in the sensor installation environment, ambient temperature and humidity, material deformation, or long-term use.

[0122] More specifically, the computing device (100) can determine the average value and deviation as new reference values ​​after accumulating and observing the sensor output for a certain period when the user is not on the sensor or there is little movement.

[0123] For example, the computing device (100) can collect sensor data during nighttime hours or a known no-load period, calculate a standard deviation that minimizes the impact of sensor noise or temperature changes, and reflect this in updating the reference value.

[0124] Accordingly, the computing device (100) can minimize problems of false detection (unnecessary movement and fall detection) or non-detection (situations where real movement is not detected) and continuously secure stable motion recognition accuracy by periodically resetting the reference value in response to dynamic environmental changes or aging, instead of simply maintaining only the reference value initially set.

[0125]

[0126] According to various embodiments of the present invention, the computing device (100) can transmit the result of determining whether there is movement or a fall and the result of calculating the amount of movement to a server, a gateway, or a user terminal.

[0127] Specifically, the computing device (100) can immediately transmit the analysis results through a network communication module (Wi-Fi, Ethernet, Bluetooth, ZigBee, mobile communication network, etc.) or upload them at regular intervals so that integrated monitoring can be performed on a server or gateway.

[0128] More specifically, the computing device (100) can classify and store recognition results for each user or situation and transmit data to be linked to subsequent statistical analysis or customized feedback services (e.g., exercise coaching, rehabilitation program recommendation, etc.).

[0129] For example, when the computing device (100) detects a pattern of a specific user frequently moving at a fast walking speed, it can provide a corresponding health management alert, or for elderly people at high risk of falling, it can be configured to increase the alarm priority and immediately send it to a relevant server or guardian terminal.

[0130] Accordingly, the computing device (100) can implement a real-time motion analysis environment that can be utilized in various fields such as home medical monitoring, life safety services, and personalized exercise programs by linking and sharing various motion information detected through a single large-area pressure sensor via a network.

[0131]

[0132] As described above, the computing device (100) of the present invention can precisely detect whether a user is moving, whether a fall has occurred, and the amount of movement through a single large-area pressure sensor (200). Through this, the computing device (100) can monitor the user's movements in real time and provide an effective solution that can respond quickly to emergency situations such as falls.

[0133] In particular, the present invention can contribute to ensuring the safety and improving the quality of life of vulnerable groups, such as households of elderly people living alone or households of disabled people living alone, by widely supplying them. Specifically, the motion (especially, fall) recognition method utilized in the present invention utilizes a single large-area pressure sensor (200) and a pressure-based AI analysis algorithm, thereby completely eliminating the risk of personal information leakage associated with existing CCTV-based fall detectors. That is, because physical data such as 'pressure' is utilized, the pattern of user movement can be precisely analyzed, while fundamentally resolving privacy infringement issues that may occur in video-based systems. Through this, users can use the single large-area pressure sensor (200) applied in the present invention with peace of mind, and protection of personal information and efficient fall detection can be achieved simultaneously in various environments such as public facilities, hospitals, and nursing homes.

[0134] Furthermore, the present invention can provide high-performance motion analysis and fall detection with simple installation and maintenance, allowing it to be effectively utilized even in situations where high-cost detection devices cannot be used. These characteristics suggest broad social applicability, particularly in resource-constrained environments, and can possess high economic and technical value as a safety management solution for vulnerable groups such as the elderly living alone and people with disabilities.

[0135]

[0136] According to an additional embodiment of the present invention, a computing device (100) can more precisely analyze the user's movements by fusing pressure data obtained from a single large-area pressure sensor (200) with data from an inertial measurement unit (IMU) embedded in a user terminal (e.g., a wearable device).

[0137] Specifically, the computing device (100) can detect even minute body movements (e.g., the foot dragging slightly on the ground or the center of gravity changing momentarily) by comparing and correcting in real time the walking pattern detected by a single large-area pressure sensor (200) with acceleration, angular velocity, and tilt information collected from an inertial measurement device.

[0138] More specifically, the computing device (100) can synchronize the pressure distribution fluctuation amount measured by a single large-area pressure sensor (200) with the acceleration and gyroscope data of the IMU to calculate the stride length and speed, walking rhythm, and intensity of landing impact in detail.

[0139] For example, the computing device (100) may determine that it is likely a simple jumping event rather than an actual fall if there is no significant pressure change on the single large-area pressure sensor (200) even though rapid vertical acceleration is detected in the inertial data. As another example, the computing device (100) may immediately warn of the possibility of a fall if a sudden pressure spike is detected on the single large-area pressure sensor (200) and the motion trajectory also shows an abnormally large displacement on the IMU.

[0140] For example, the computing device (100) can determine whether the foot placement position and the movement of the body center coincide by cross-verifying the pressure center coordinates at time t and the user's movement vector calculated by the inertial measurement device. Through this process, the computing device (100) can more accurately predict potential falls that occur when only the feet are on the sensor and the upper body shakes significantly, and can also detect upper body shaking that might be missed by simple foot trajectories alone at an early stage.

[0141] Accordingly, the computing device (100) can achieve a high level of motion recognition precision and fall detection reliability by fusing physical pressure information measured by a single large-area pressure sensor (200) and three-dimensional motion data acquired from an IMU sensor. In particular, there have been cases in the past where a multi-array pressure sensor method was partially linked with an IMU, but it was difficult to obtain a substantial synergy effect due to the complexity of the sensor array and issues with communication and power consumption. However, by adopting a single large-area pressure sensor as in the present invention, the hardware configuration is simplified and the number of communication lines is reduced, and high efficiency and accuracy can be simultaneously secured when combined with inertial measurement data in real time.

[0142] Accordingly, the computing device (100) of the present invention can provide significant advantages beyond simple gait analysis, such as providing personalized rehabilitation programs, accurate posture feedback during sports training, and early diagnosis of fall risk, through a combination of a single large-area pressure sensor and an inertial measurement unit (IMU).

[0143]

[0144] Although embodiments of the present invention have been described above with reference to the attached drawings, those skilled in the art will understand that the present invention may be implemented in other specific forms without altering its technical concept or essential features. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive.

Claims

1. A method performed by a computing device comprising at least one processor, A step of recognizing pressure changes occurring over time from a single large-area pressure sensor; A step of converting the above pressure change into a digital signal to generate impulse change data; and A step of determining whether the user is moving or has fallen based on the above impact change data; including, User motion recognition method based on a single large-area pressure sensor.

2. In Paragraph 1, The step of recognizing pressure changes occurring over time from the above single large-area pressure sensor is, A step of determining a reference value of the single large-area pressure sensor; A step of sampling a resistance value recognized according to an external shock occurring within the detection area of ​​the pressure sensor; and A step of processing sampled resistance values ​​at preset time intervals to recognize the change value relative to a reference value as the pressure change; including, User motion recognition method based on a single large-area pressure sensor.

3. In Paragraph 2, The step of converting the above pressure change into a digital signal to generate impulse change data is: A step of converting the above resistance value into digital data by sampling it with an analog-to-digital converter; and A step of generating the impact change data by dividing the digital data into preset time units; including, User motion recognition method based on a single large-area pressure sensor.

4. In Paragraph 1, The step of determining whether the user is moving or has fallen based on the above impact change data is: A step of inputting the above impact change data into a pre-trained motion analysis model to determine whether there is movement or whether there is a fall; Includes, The above motion analysis model is, Composed of neural network-based machine learning algorithms, which are pre-trained based on training data regarding movement patterns and fall patterns, User motion recognition method based on a single large-area pressure sensor.

5. In Paragraph 1, The above method is, A step of calculating momentum based on the movement of the user when it is determined that the user is moving; Includes more, The step of calculating momentum based on the movement of the above-mentioned user is: A step of calculating location information where movement occurred based on the above pressure changes for each preset time interval; A step of calculating walking speed, stride distance, and time between walks based on the above location information; and A step of calculating the user's exercise amount based on the walking speed, stride distance, and time between walks; including, User motion recognition method based on a single large-area pressure sensor.

6. In Paragraph 1, The above method is, If the above-mentioned fall is determined, a step of generating an alarm signal and transmitting it to an external device; including, User motion recognition method based on a single large-area pressure sensor.

7. In Paragraph 2, The above method is, A step of resetting the reference value of the single large-area pressure sensor at preset intervals; including, User motion recognition method based on a single large-area pressure sensor.

8. In Paragraph 1, The above method is, A step of transmitting the result of determining whether there is movement or a fall, and the result of calculating momentum, to a server, gateway, or user terminal; including, User motion recognition method based on a single large-area pressure sensor.

9. Memory for storing one or more instructions; and A processor that executes one or more instructions stored in the memory. Including, The above processor executes the above one or more instructions, A device that performs the method of claim 1.

10. A computer program stored on a computer-readable recording medium that is combined with a computer, which is hardware, to perform the method of claim 1.

Images