[go: up one dir, main page]

WO2018223505A1 - Dispositif portable d'identification de démarche - Google Patents

Dispositif portable d'identification de démarche Download PDF

Info

Publication number
WO2018223505A1
WO2018223505A1 PCT/CN2017/094354 CN2017094354W WO2018223505A1 WO 2018223505 A1 WO2018223505 A1 WO 2018223505A1 CN 2017094354 W CN2017094354 W CN 2017094354W WO 2018223505 A1 WO2018223505 A1 WO 2018223505A1
Authority
WO
WIPO (PCT)
Prior art keywords
current
gait data
preset
external environment
gait
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2017/094354
Other languages
English (en)
Chinese (zh)
Inventor
袁晖
李凝华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Ikmak Tech Co Ltd
Original Assignee
Shenzhen Ikmak Tech Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Ikmak Tech Co Ltd filed Critical Shenzhen Ikmak Tech Co Ltd
Publication of WO2018223505A1 publication Critical patent/WO2018223505A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/117—Identification of persons
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Measuring devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor or mobility of a limb
    • A61B5/112—Gait analysis
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
    • A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
    • A61B5/6802—Sensor mounted on worn items

Definitions

  • the present invention relates to the field of gait recognition, and in particular to a wearable device for recognizing gait.
  • Gait recognition a kind of biometric identification, aims to identify people by walking posture. Compared with other biometric technologies, such as fingerprints, irises, etc., gait recognition has the advantages of non-contact, long distance and not easy to camouflage. The basic working principle is to find and extract the changing characteristics between individuals from the same walking behavior to achieve automatic identification.
  • gait recognition has advantages over face recognition. Gait refers to the way people walk, which is a complex behavioral feature. The uniqueness of gait can be reflected in the differences in personal physiological structure, including different leg bone lengths, different muscle strengths, different heights of center of gravity, and different motor nerve sensitivities. In the technical practice scene, criminals may dress themselves and prevent even one hair on their own from falling to the crime scene, but there is one thing that they can hardly change completely without leaving characteristic marks. This is walking. posture. In addition, the limit distance of gait recognition detection is close to one hundred steps, which should be the farthest distance that biometric technology can detect.
  • the data analysis of walking gait has great value, and can have a variety of application scenarios, including quantitative verification of the use of rehabilitation equipment in the field of rehabilitation, rehabilitation training of patients; Daily analysis and diagnosis of diseases; professional sports injury risk assessment, quantitative training and guidance in the field of sports.
  • the smart wearable device condenses large professional-grade medical equipment into wearable wearable devices, captures the user's foot micro-motion through sensors, collects basic data, and combines artificial intelligence support of the cloud algorithm library to eliminate noise data interference in the environment. Therefore, the accurate gait analysis report of the user in real scenes such as uphill, downhill, and stair climbing is obtained, but the existing gait-based biometric method is susceptible to external environment and misjudges.
  • the main object of the present invention is to provide a wearable device for recognizing gait, which aims to solve the technical problem that gait recognition is susceptible to external environment and misjudgment.
  • the present invention provides a wearable device for recognizing a gait, the wearable device comprising: a device body, a sensor array, and a microprocessor, wherein the sensor array and the microprocessor are disposed in the device body ;
  • the sensor array is configured to acquire current gait feature information and current external environment information of the current user, and send the current gait feature information and the current external environment information to the microprocessor;
  • the microprocessor is configured to generate current gait data according to the current gait feature information, and when the current gait data has an abnormality, determine, according to the current external environment information, whether the abnormality is caused by an external environment, When the abnormality is not caused by the external environment, it is determined that the abnormality is caused by a physical condition.
  • the current external environment information includes a plurality of current external environment feature parameters
  • the microprocessor is further configured to calculate a difference between the current external environment feature parameter and a preset environment feature parameter; when the difference is not in the first preset range, determine that the abnormality is external Caused by the environment.
  • the microprocessor is further configured to compare the current gait data with preset gait data, between the current gait data and the preset gait data. When the matching degree is not in the second preset range, it is determined that the current gait data has an abnormality.
  • the microprocessor is further configured to acquire preset gait data in a preset user account, and compare the current gait data with the preset gait data, where When the matching degree between the current gait data and the preset gait data is in the third preset range, determining that the current user corresponds to the preset user account, storing the current gait data to the Preset user accounts.
  • the microprocessor is further configured to: when the matching degree between the current gait data and the preset gait data is not within a third preset range, determine the current user Not corresponding to the preset user account, and creating a new user account, storing the current gait data to the new user account, and using the new user account as a preset user account.
  • the microprocessor is further configured to store the current external environment information into the preset user account.
  • the microprocessor is further configured to send the preset user account, the current gait data, and the current external environment information to a background server, so that the background server The current gait data and the current external environment information are stored in the preset user account.
  • the microprocessor is further configured to use the current gait data as environment abnormal gait data when the abnormality is caused by an external environment; when the abnormality is not caused by an external environment; And using the current gait data as body abnormal gait data.
  • the wearable device further includes a memory for storing body abnormal gait data, environmental abnormal gait data, current gait data, and current external environment information.
  • the microprocessor is further configured to issue prompt information when the abnormality is determined to be caused by the physical condition of the current user.
  • the microprocessor of the wearable device generates current gait data according to the current gait feature information of the current user, and determines whether the abnormality is from the external environment according to the current external environment information when there is an abnormality in the current gait data.
  • the abnormality is not caused by the external environment, it is determined that the abnormality is caused by a physical condition, thereby preventing the abnormality of the gait data of the user caused by the change of the external environment as being determined that the physical condition of the user has changed, and the improvement is made.
  • the accuracy of gait data analysis is performed by the abnormality is caused by a physical condition.
  • FIG. 1 is a structural block diagram of a wearable device for recognizing a gait according to an embodiment of the present invention
  • FIG. 2 is a schematic structural diagram of a wearable device for recognizing a gait according to an embodiment of the present invention.
  • FIG. 1 a first embodiment of a wearable device for identifying gait according to the present invention is presented.
  • the wearable device includes: a device body, a sensor array, and a microprocessor, wherein the sensor array and a microprocessor are disposed in the device body;
  • the sensor array is configured to acquire current gait feature information and current external environment information of the current user, and send the current gait feature information and the current external environment information to the microprocessor;
  • the microprocessor is configured to generate current gait data according to the current gait feature information, and when the current gait data has an abnormality, determine, according to the current external environment information, whether the abnormality is caused by an external environment, When the abnormality is not caused by the external environment, it is determined that the abnormality is caused by a physical condition.
  • the device body is a main supporting portion of the device, and the sensor array and the microprocessor are disposed in the device body, for example, the wearable device is a smart insole, then the device body It may be a conventional insole in which a sensor array and a microprocessor are disposed.
  • the sensor array may include at least one of a distance sensor, a height sensor, an angle sensor, a pressure sensor, and a time sensor, and further includes at least one of a temperature sensor, a humidity sensor, a brightness sensor, and a sound sensor, and may also include a ground.
  • the sensor array also has the functions of collecting, recording and analyzing external environment information, and can intelligently identify the external environment where the user is located, so that the gait of the user can be more accurately recognized and accurately performed. Biometrics and more effective recording and analysis of user gait information.
  • the sensor array is built in the wearable device, and can acquire real-time gait feature information generated by the user's feet during walking, such as distance information, altitude information, angle information, and pressure information. And time information, etc.
  • the gait feature information may further include more or less feature information than the gait feature information, which is not limited in this embodiment.
  • the sensor array transmits the current gait feature information to the microprocessor.
  • the current gait data is that the microprocessor forms the gait feature information generated by the user during the walking process to form a plurality of data curves, thereby comprehensively fitting and generating the gait data image of the user.
  • Gait data images have stability, periodicity, rhythm, directionality, coordination and individual differences, and can be effectively applied to user identification.
  • the current external environment information is surrounding external environment information where the user is located when the current gait data is generated.
  • current temperature, humidity, brightness, sound, etc. may also include other environmental information, such as the distance of a high-speed moving object such as a vehicle, ground softness, altitude, or radioactive elements, etc., which is not limited in this embodiment. .
  • the microprocessor can record and analyze the change of the gait data of the user for a period of time (may be two or three days), thereby establishing the preset gait data of the user.
  • the microprocessor is configured to identify whether the abnormal gait data is caused by an external environment or by a user's physical condition.
  • the current external environment information is acquired, and the current external environment is analyzed. Whether the mutation occurs at the same time, if there is no mutation in the current external environment at the same time, it can be considered that the abnormal gait data is not caused by the external environment, and the abnormality is recognized as the physical condition of the user.
  • the microprocessor of the wearable device generates current gait data according to the current gait feature information of the current user, and determines whether the abnormality is from the external environment according to the current external environment information when there is an abnormality in the current gait data.
  • the abnormality is not caused by the external environment, it is determined that the abnormality is caused by a physical condition, thereby preventing the abnormality of the gait data of the user caused by the change of the external environment as being determined that the physical condition of the user has changed, and the improvement is made.
  • the accuracy of gait data analysis is performed by the abnormality is caused by a physical condition.
  • the current external environment information includes a plurality of current external environment feature parameters
  • the microprocessor is further configured to calculate a difference between the current external environment feature parameter and a preset environment feature parameter; when the difference is not in the first preset range, determine that the abnormality is external Caused by the environment.
  • the current external environment information includes a plurality of current external environment feature parameters, and the current external environment feature parameters may include current temperature, humidity, brightness, sound, and the like.
  • the current external environment feature parameter may also be Including other environmental characteristic parameters, such as the distance of a high-speed moving object such as a vehicle, the ground softness, the altitude, or the radiation element, etc., this embodiment does not limit this.
  • the preset environment feature parameter is an environment feature parameter in the surrounding external environment information where the user is located when the normal gait data is generated, and the preset environment feature parameter may include: temperature, humidity, brightness, and wind speed. And sounds, etc.
  • the preset environmental feature parameters may also include other environmental feature parameters, such as the distance of a high-speed moving object such as a vehicle, ground softness, altitude, or a radioactive element, which is not limited in this embodiment.
  • calculating a difference between the current external environment feature parameter and the preset environment feature parameter is to calculate the same environment feature parameter type in the current external environment feature parameter and the preset environment feature parameter, For example, the value of the temperature in the current external environment characteristic parameter and the value of the temperature in the preset environmental characteristic parameter are calculated.
  • the currently detected temperature is 25°, and the temperature detected in the next minute. It may be 24°.
  • the human body may not be able to perceive it, and the corresponding gait change will not occur.
  • the temperature suddenly drops by 10° the human body may have a perception, and the gait will change accordingly, for example.
  • the first preset range is an allowable fluctuation range preset according to an influence of an environmental characteristic parameter in the external environment on the human body, and the allowable fluctuation range is a fluctuation change that the human body cannot perceive, the first preset
  • the range sets different ranges for different environmental feature parameter types.
  • the first preset range of the temperature may be preset to a temperature difference of less than 5°
  • the first preset range of the humidity may be preset to have a humidity difference of less than 10%, etc., which is not limited in this embodiment.
  • the range of environmental characteristic parameters that the human body can perceive can be collected to preset a more accurate first preset range.
  • the user first runs in a long boulevard and then enters an open, unshaded road. As the user suddenly feels the strong sunshine, his gait may have some abnormal changes.
  • the current external environment information acquired by the built-in sensor array of the wearable device also changes, acquiring the current external environment feature parameter, comparing the current external environment feature parameter with the preset environment feature parameter, and finding the brightness parameter. There is a difference, and the difference between the brightness parameters is not in the first preset range, then it can be judged that the abnormality is caused by an external environment change.
  • the change of the external environment may be caused by multiple environmental characteristic parameters changing at the same time.
  • the difference of at least one environmental characteristic parameter is not in the first preset range, the abnormality is determined to be Caused by the external environment.
  • the gait data (such as the pressure of the sole, the pace, the stride, the step size, and the like) detected by the wearable device suddenly changes sharply; at the same time, the wearable device acquires The humidity parameter of the current external environment also suddenly rises and receives the sound parameters of the thunder.
  • the difference between the current external environment and the humidity parameter in the preset external environment feature parameter or the difference between the sound parameters is at least one of the first preset ranges the wearing device can intelligently Interpret abnormal gait data as a result of a sudden change in the external environment.
  • the microprocessor is further configured to use the current gait data as environment abnormal gait data when the abnormality is caused by an external environment; and when the abnormality is not caused by an external environment, the current step is State data as body abnormal gait data.
  • the current external environment information is acquired, and whether the current external environment is mutated at the same time is analyzed. If the current external environment is mutated at the same time, the abnormality may be considered as the external environment.
  • the current gait data is taken as the environmental abnormal gait data.
  • the abnormality is determined as the physical condition of the current user, and the current gait data is taken as the physical abnormal gait data.
  • the abnormal gait data in the historical gait data of the stored user may be analyzed, and the relationship between the environmental feature parameter and the abnormal gait data of the environment may be extracted, and the historical gait data is described in the historical gait data.
  • the environment abnormal gait data is set to preset abnormal gait data, thereby establishing a mapping relationship between the environment feature parameter and the preset abnormal gait data. Using historical data, the accuracy of user gait recognition can be further improved.
  • the preset abnormal gait data may also be user gait data monitored when various environmental parameters change, and the mapping relationship includes one or more environmental feature parameters and a preset abnormal gait. Corresponding relationship between the data, the corresponding relationship also setting corresponding preset abnormal gait data according to different ranges of environmental characteristic parameter changes.
  • the corresponding preset abnormal gait data may be searched in the mapping relationship according to the environmental feature parameter; and the preset abnormal gait data and the current gait are The data is compared, and when the preset abnormal gait data substantially matches or has a consistent change trend with the current gait data and the difference is within an allowable range, the abnormality is recognized as being caused by an external environment.
  • the user first runs in a long boulevard and then enters an open, unshaded road. As the user suddenly feels the strong sunshine, his gait may have some abnormal changes.
  • the current external environment data detected by the wearable device also changes, and the corresponding preset abnormal gait data is searched in the mapping relationship according to the range of the brightness parameter change, and the found preset abnormal step is further found.
  • the state data is compared with the current gait data to see if the two basically match or there is a consistent trend of change and the difference is within the allowable range, then it can be determined that the abnormality is caused by an external environment change.
  • the microprocessor is further configured to compare the current gait data with preset gait data, and the matching degree between the current gait data and the preset gait data is not in the second When the preset range is determined, it is determined that the current gait data has an abnormality.
  • the normal gait has stability, periodicity and rhythm, directionality, coordination, when the user's current gait data is different from the preset gait data, and the current gait data and The matching degree between the preset gait data is not in the second preset range, and the second preset range is an allowable data fluctuation range set according to normal fluctuations that may occur in the current normal gait of the user, that is, When the current gait data is not in the normal data fluctuation range, it is determined that the current gait data has an abnormality.
  • the preset gait data is not necessarily the gait data when the user is in good health, but refers to the gait data generated by the user during normal walking.
  • the preset gait data may also be based on The actual setting needs to be set accordingly, and this embodiment does not limit this.
  • the wearer device is used to monitor the gait data of the user, and the gait data of the user at this time is recorded and set as the preset gait data.
  • the current gait data is compared with the preset gait data, and the matching degree between the current gait data and the preset gait data is not in the second pre-
  • the range is within, it is determined that there is an abnormality in the current gait data, and then it is further possible to identify whether the abnormality is caused by a change in physical condition or an external environment.
  • the microprocessor is further configured to acquire preset gait data in a preset user account, compare the current gait data with the preset gait data, and use the current gait data and the When the matching degree between the preset gait data is in the third preset range, it is determined that the current user corresponds to the preset user account, and the current gait data is stored to the preset user account.
  • the wearable device may be used by multiple users, so different user accounts are set up for different users, the user accounts storing relevant gait data for the user. Then, when the user uses, the identity of the user can be identified first, so as to better record and analyze the gait data of the user.
  • the normal gait has individual differences. For different users, their gait data is different, so when the user uses the wearable device, the user's current gait data is firstly used. Compare with preset gait data.
  • the third preset range is an allowable fluctuation range set according to individual differences of different user gaits. In a specific implementation, the appropriate range may be adjusted according to the actual operation accuracy as the third preset range.
  • determining that the current user is a user corresponding to the preset gait data That is, the identification of the user identity is achieved.
  • the microprocessor is further configured to: when the matching degree between the current gait data and the preset gait data is not within a third preset range, determine the current user and the preset user The account does not correspond, and a new user account is created, the current gait data is stored to the new user account, and the new user account is used as a preset user account.
  • the matching degree between the current gait data and the preset gait data is not within the third preset range, determining that the current user is not the user with the preset
  • the user corresponding to the account that is, the preset gait data in the preset user account is not the gait data of the current user, and the current user may be considered as a new user, and a new user account may be created for the new user.
  • the gait data of the new user is recorded and analyzed later.
  • the microprocessor is further configured to store the current external environment information into the preset user account.
  • the wearable device may be used by multiple users, and then, when the user uses, the identity of the current user is first identified, and after determining that the current user is the user corresponding to the preset user account, The current gait data and the current external environment information are stored in the preset user account, so that the gait data of the user is recorded and analyzed more accurately.
  • the microprocessor is further configured to send the preset user account, the current gait data, and the current external environment information to a background server, so that the background server sends the current gait data and the The current external environment information is stored in the preset user account.
  • the preset user account, the current gait data, and the current external environment information are sent to the background server, so that the gait data of the current user is remotely managed, and when the wearable device is damaged or faulty, The gait data of the current user is not lost, and when the current user uses the new wearable device, the background server may also be requested to send the relevant gait data of the current user to the new wearable device, of course,
  • the preset gait data and preset environment feature parameters can also be stored to the background server.
  • the microprocessor is further configured to issue prompt information when the abnormality is determined to be caused by the physical condition of the current user.
  • the current user's body may have a certain disease, and a prompt message is sent to remind the current user to perform a corresponding physical examination.
  • the prompt information may also be sent to a remote medical staff or other user's corresponding device to remind the medical staff to perform a physical examination on the user, or other users understand the physical condition of the user.
  • the wearer device is used to monitor the gait data of the user, and the gait data of the user is recorded and set as the preset gait data for a period of time, such as one month.
  • the gait data of the user is abnormal, that is, the difference between the current gait data and the preset gait data is not in the second preset range.
  • the abnormality is determined to be caused by the physical condition of the user, it may be that the user's physical condition is improved or the disease is deteriorated.
  • the user is diagnosed with diabetes.
  • the wearable device detects an abnormality in the gait data (for example, the sole pressure data is abnormal, and the pressure on some parts of the sole is significantly decreased).
  • the wearable device detects a sudden increase in humidity parameters, as well as sound parameters similar to water flow.
  • the wearable device intelligently determines that the user is passing a road with a puddle, and the user may intentionally raise or raise the feet to avoid directly identifying the abnormality (an abnormality of the sole pressure) as The user's diabetes is getting worse. Therefore, the prompting information to the user, the remote medical staff or other users caused by the misjudgment is avoided.
  • the physical condition of the user also changes when the external environment changes.
  • the abnormality of the gait data of the user is detected, and the external environment is abrupt, other users or remote medical care
  • the person can get in touch with the user to confirm whether the gait is abnormal due to a sudden change in the environment, an abnormal gait, or a change in physical condition.
  • the current gait data is classified more accurately, which provides more accurate reference data for subsequent monitoring, and also ensures that users can get help from other users or remote medical staff in time when the physical condition changes.
  • the memory is configured to store physical abnormal gait data, environmental abnormal gait data, current gait data, and current external environment information.
  • storing abnormal gait data, environmental abnormal gait data, current gait data and current external environment information is beneficial to more in-depth gait data analysis of the user's gait data, which is beneficial to the user step.
  • the management of state data can also extract more accurate gait data as preset gait data, and can understand the physical condition of each stage of the user according to various gait data stored.
  • FIG. 2 is a schematic structural diagram of a wearable device for recognizing a gait according to an embodiment of the present invention.
  • the wearing device is a smart insole comprising: an antibacterial fabric 1, a waterproof layer 2, a printed circuit board layer 3, a memory 4, a battery 5, a waterproof layer 6, and a bio-force layer 7.
  • FIG. 2 does not constitute a definition of a smart insole, may include more or fewer components than illustrated, or combine some components, or different component arrangements.
  • the wearable device may be an insole, a belt, a waist pack, an earphone, a pair of glasses, or a headlight worn on the head, etc., which is not limited in this embodiment.
  • the wearable device can be continuously used multiple times in a real scene, and can identify the external environment. Compared with the large gait analysis device, the time dimension is added to become four-dimensional data, and the analysis of the user timing signal is completed. This can be applied to daily detection of user gait, early warning of chronic diseases (including Alzheimer's disease, Parkinson's disease, diabetic foot, etc.), as well as abnormal gait analysis and early warning tips for children's toddler learning.
  • chronic diseases including Alzheimer's disease, Parkinson's disease, diabetic foot, etc.
  • the wearable device may be used in combination with other wearable devices, for example, when the wearable device is an insole, the user is using In the insole, a belt or a waist bag having a distance detecting function may be attached to the waist at the same time, or a headlight or a headphone or a glasses having a distance detecting function on the head strap may be simultaneously used, and this embodiment does not limit.
  • the embodiment method can be implemented by means of software plus a necessary general hardware platform, and of course hardware, but in many cases the former is a better implementation.
  • the present invention The technical solution in essence or the contribution to the prior art can be embodied in the form of a software product stored in a storage medium (such as ROM/RAM, disk, light).
  • the disc includes a number of instructions for causing a terminal device (which may be a cell phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the methods described in various embodiments of the present invention.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Medical Informatics (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Physics & Mathematics (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Physiology (AREA)
  • Dentistry (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

La présente invention concerne un dispositif portable d'identification de démarche. Un microprocesseur du dispositif portable génère, selon les informations de caractéristique de démarche présentes d'un présent utilisateur, les données présentes de démarche, détermine, à partir des données présentes de démarche indiquant l'anomalie et selon les informations présentes d'un environnement externe, si l'anomalie est causée par l'environnement externe, et décide que l'anomalie est causée par une condition physique si ce n'est pas le cas. De cette manière, la présente invention empêche de déterminer une anomalie de données de démarche d'utilisateur causée par un changement d'environnement externe comme étant causée par une condition physique de l'utilisateur, améliorant ainsi la précision de l'analyse des données de démarche.
PCT/CN2017/094354 2017-06-06 2017-07-25 Dispositif portable d'identification de démarche Ceased WO2018223505A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710420730.0A CN107411753A (zh) 2017-06-06 2017-06-06 一种识别步态的可穿戴设备
CN201710420730.0 2017-06-06

Publications (1)

Publication Number Publication Date
WO2018223505A1 true WO2018223505A1 (fr) 2018-12-13

Family

ID=60429093

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/094354 Ceased WO2018223505A1 (fr) 2017-06-06 2017-07-25 Dispositif portable d'identification de démarche

Country Status (2)

Country Link
CN (1) CN107411753A (fr)
WO (1) WO2018223505A1 (fr)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10624559B2 (en) 2017-02-13 2020-04-21 Starkey Laboratories, Inc. Fall prediction system and method of using the same
US11277697B2 (en) 2018-12-15 2022-03-15 Starkey Laboratories, Inc. Hearing assistance system with enhanced fall detection features
US11559252B2 (en) 2017-05-08 2023-01-24 Starkey Laboratories, Inc. Hearing assistance device incorporating virtual audio interface for therapy guidance
US11638563B2 (en) 2018-12-27 2023-05-02 Starkey Laboratories, Inc. Predictive fall event management system and method of using same
US12095940B2 (en) 2019-07-19 2024-09-17 Starkey Laboratories, Inc. Hearing devices using proxy devices for emergency communication
US12254755B2 (en) 2017-02-13 2025-03-18 Starkey Laboratories, Inc. Fall prediction system including a beacon and method of using same
US12484860B2 (en) 2023-04-26 2025-12-02 Starkey Laboratories, Inc. Predictive fall event management system and method of using same

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108959890A (zh) * 2018-07-17 2018-12-07 三星电子（中国）研发中心 电子终端中的控制方法及电子终端
CN109274930B (zh) * 2018-07-26 2020-06-26 华为技术有限公司 一种基于步态识别的安全监控方法及装置
CN109471263A (zh) * 2018-11-30 2019-03-15 郭志猛 一种步态识别智能眼镜
US20220218233A1 (en) * 2019-05-29 2022-07-14 Nec Corporation Information processing device, personal identification device, personal identification system, information processing method, and storage medium
CN110173867A (zh) * 2019-05-29 2019-08-27 广东美的制冷设备有限公司 空调器的控制方法、空调器及计算机可读存储介质
CN113204009B (zh) * 2021-05-12 2023-12-22 深圳康佳电子科技有限公司 跑步步长提醒方法、装置、终端及计算机可读存储介质
CN120694796B (zh) * 2025-08-28 2025-11-21 大连百首企家科技有限公司 一种骨科支架力学状态异常预警方法及系统

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013059489A (ja) * 2011-09-13 2013-04-04 Toshiba Corp 歩行評価装置
CN103186792A (zh) * 2013-03-26 2013-07-03 北京林业大学 一种基于优化的c-支持向量分类机的步态识别方法
CN103235928A (zh) * 2013-01-08 2013-08-07 沈阳理工大学 一种具有监督机制的步态识别方法
CN104834888A (zh) * 2014-12-04 2015-08-12 龙岩学院 一种辅助筛查帕金森症的异常步态识别方法
US20150230733A1 (en) * 2013-04-17 2015-08-20 Korea University Research And Business Foundation Method for determining abnormal gait
CN105631195A (zh) * 2015-12-18 2016-06-01 合肥工业大学 一种可穿戴式多信息融合的步态分析系统及其方法
CN105931428A (zh) * 2016-06-30 2016-09-07 北京小米移动软件有限公司 报警方法及装置
US20160321947A1 (en) * 2014-06-09 2016-11-03 Twd Sports Tech, Llc System and method for treating patients having conditions that affect walking

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150157279A1 (en) * 2013-12-06 2015-06-11 President And Fellows Of Harvard College Method, computer-readable storage device and apparatus for providing ambient augmented remote monitoring
US9344546B2 (en) * 2014-05-06 2016-05-17 Fitbit, Inc. Fitness activity related messaging
DE102014212535A1 (de) * 2014-06-30 2015-12-31 Robert Bosch Gmbh Arbeitsschuh
KR102292683B1 (ko) * 2014-09-12 2021-08-23 삼성전자주식회사 보행 환경 인식 방법 및 장치
US20160324442A1 (en) * 2015-05-08 2016-11-10 Proteus Digital Health, Inc. Loose wearable receiver systems
US20170038848A1 (en) * 2015-08-07 2017-02-09 Fitbit, Inc. User identification via collected sensor data from a wearable fitness monitor
CN105118236B (zh) * 2015-09-25 2018-08-28 广东乐源数字技术有限公司 瘫倒监测和预防装置及其处理方法
CN206212046U (zh) * 2016-11-15 2017-05-31 天津中德应用技术大学 基于物联网的老年人户外运动监测提醒装置
CN106725507B (zh) * 2016-12-12 2020-09-01 浙江大学 一种可穿戴人体绊倒检测系统及检测方法

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013059489A (ja) * 2011-09-13 2013-04-04 Toshiba Corp 歩行評価装置
CN103235928A (zh) * 2013-01-08 2013-08-07 沈阳理工大学 一种具有监督机制的步态识别方法
CN103186792A (zh) * 2013-03-26 2013-07-03 北京林业大学 一种基于优化的c-支持向量分类机的步态识别方法
US20150230733A1 (en) * 2013-04-17 2015-08-20 Korea University Research And Business Foundation Method for determining abnormal gait
US20160321947A1 (en) * 2014-06-09 2016-11-03 Twd Sports Tech, Llc System and method for treating patients having conditions that affect walking
CN104834888A (zh) * 2014-12-04 2015-08-12 龙岩学院 一种辅助筛查帕金森症的异常步态识别方法
CN105631195A (zh) * 2015-12-18 2016-06-01 合肥工业大学 一种可穿戴式多信息融合的步态分析系统及其方法
CN105931428A (zh) * 2016-06-30 2016-09-07 北京小米移动软件有限公司 报警方法及装置

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10624559B2 (en) 2017-02-13 2020-04-21 Starkey Laboratories, Inc. Fall prediction system and method of using the same
US12254755B2 (en) 2017-02-13 2025-03-18 Starkey Laboratories, Inc. Fall prediction system including a beacon and method of using same
US12310716B2 (en) 2017-02-13 2025-05-27 Starkey Laboratories, Inc. Fall prediction system including an accessory and method of using same
US11559252B2 (en) 2017-05-08 2023-01-24 Starkey Laboratories, Inc. Hearing assistance device incorporating virtual audio interface for therapy guidance
US12064261B2 (en) 2017-05-08 2024-08-20 Starkey Laboratories, Inc. Hearing assistance device incorporating virtual audio interface for therapy guidance
US12446824B2 (en) 2017-05-08 2025-10-21 Starkey Laboratories, Inc. Hearing assistance device incorporating virtual audio interface for therapy guidance
US11277697B2 (en) 2018-12-15 2022-03-15 Starkey Laboratories, Inc. Hearing assistance system with enhanced fall detection features
US12149893B2 (en) 2018-12-15 2024-11-19 Starkey Laboratories, Inc. Hearing assistance system with enhanced fall detection features
US11638563B2 (en) 2018-12-27 2023-05-02 Starkey Laboratories, Inc. Predictive fall event management system and method of using same
US12095940B2 (en) 2019-07-19 2024-09-17 Starkey Laboratories, Inc. Hearing devices using proxy devices for emergency communication
US12484860B2 (en) 2023-04-26 2025-12-02 Starkey Laboratories, Inc. Predictive fall event management system and method of using same

Also Published As

Publication number Publication date
CN107411753A (zh) 2017-12-01

Similar Documents

Publication Publication Date Title
WO2018223505A1 (fr) Dispositif portable d'identification de démarche
US20210275109A1 (en) System and method for diagnosing and notification regarding the onset of a stroke
US10485454B2 (en) Systems and methods for markerless tracking of subjects
US9710920B2 (en) Motion information processing device
US11047706B2 (en) Pedometer with accelerometer and foot motion distinguishing method
KR102338297B1 (ko) 사용자 상태를 판단하기 위한 시스템의 제어 방법, 장치 및 프로그램
CN109171734A (zh) 基于多传感器数据融合的人体行为分析云管理系统
WO2023285898A1 (fr) Criblage d'individus pour une maladie respiratoire à l'aide d'une intelligence artificielle
Hossain et al. A direction-sensitive fall detection system using single 3D accelerometer and learning classifier
CN108711452A (zh) 基于视觉的人体健康状态分析方法和系统
CN108882853A (zh) 使用视觉情境来及时触发测量生理参数
CN117133464A (zh) 一种老年人健康智能监测系统及监测方法
CN109543762A (zh) 一种多特征融合姿态识别系统及方法
US20210022679A1 (en) Sensor Devices and Methods for Detecting when a Sensor Device is Worn
Jovanov et al. A mobile system for assessment of physiological response to posture transitions
CN113271848B (zh) 身体健康状态影像分析装置、方法以及系统
Majumder et al. A novel wireless system to monitor gait using smartshoe-worn sensors
CN113069088B (zh) 一种人工智能交互装置
Nguyen et al. The internet-of-things based fall detection using fusion feature
TW202000134A (zh) 步態辨識系統及步態辨識方法
WO2019161857A1 (fr) Dispositif et procédé pour fournir un transfert de données sûr par l'intermédiaire d'un protocole de communication non sécurisé
Solachidis et al. TeNDER: Towards efficient Health Systems through e-Health platforms employing multimodal monitoring
Liao et al. A vision-based walking posture analysis system without markers
Fujii et al. Personal identification using gait data on slipper-device with accelerometer
Oluwadare Gait analysis on a smart floor for health monitoring

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17912682

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17912682

Country of ref document: EP

Kind code of ref document: A1