CN108831527A - A kind of user movement condition detection method, device and wearable device - Google Patents

A kind of user movement condition detection method, device and wearable device Download PDF

Info

Publication number
CN108831527A
CN108831527A CN201810556612.7A CN201810556612A CN108831527A CN 108831527 A CN108831527 A CN 108831527A CN 201810556612 A CN201810556612 A CN 201810556612A CN 108831527 A CN108831527 A CN 108831527A
Authority
CN
China
Prior art keywords
user
information
state
data
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.)
Granted
Application number
CN201810556612.7A
Other languages
Chinese (zh)
Other versions
CN108831527B (en
Inventor
陈志勇
林晨曦
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.)
Gulinda Ji (xiamen) Ltd By Share Ltd
Original Assignee
Gulinda Ji (xiamen) Ltd By Share 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 Gulinda Ji (xiamen) Ltd By Share Ltd filed Critical Gulinda Ji (xiamen) Ltd By Share Ltd
Priority to CN201810556612.7A priority Critical patent/CN108831527B/en
Publication of CN108831527A publication Critical patent/CN108831527A/en
Application granted granted Critical
Publication of CN108831527B publication Critical patent/CN108831527B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/30—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording 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, mobility of a limb
    • A61B5/1118—Determining activity level
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/20—Movements or behaviour, e.g. gesture recognition

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Physics & Mathematics (AREA)
  • Biophysics (AREA)
  • Medical Informatics (AREA)
  • Animal Behavior & Ethology (AREA)
  • Veterinary Medicine (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Pathology (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Biomedical Technology (AREA)
  • Epidemiology (AREA)
  • Psychiatry (AREA)
  • Dentistry (AREA)
  • Physical Education & Sports Medicine (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Primary Health Care (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physiology (AREA)
  • Social Psychology (AREA)
  • Human Computer Interaction (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

The invention discloses a kind of user movement condition detection method, device and wearable devices, wherein the user movement condition detection method includes：The personal information and/or environmental information for obtaining user, the exercise data type acquired needed for being determined according to personal information and/or environmental information；The primary motor data that user is acquired according to exercise data type establish personal portrait model in conjunction with personal information and/or environmental information；Determine whether that acquiring collateral motion data establishes second level artificial intelligence model according to model.By implementing the present invention, the exercise data type of required acquisition, analysis can finely be screened according to the personal information and locating environmental information of user, the consumption of electricity is effectively reduced to reduce collection capacity, calculation amount by the multistage model for including in a model.

Description

A kind of user movement condition detection method, device and wearable device
Technical field
The present invention relates to intelligence to dress technical field, and in particular to a kind of user movement condition detection method, device and can Wearable device.
Background technique
The identification of human motion posture is led in motion analysis, tumble early warning, disease prevention, rehabilitation, identification etc. There is important role in domain.The pressure and pressure of Human Sole can occur dysfunction with human foot structure or disease occurs Become, and as the variation of the motion state of human body changes.
By being studied in the distribution of stationary state or motion process Human Sole pressure and pressure, it can be found that gait Dynamic property and motility feature.Fast development and universal, existing wearable foot tool with intelligent wearable device, can by To ground reaction force and the information such as human motion position coordinates calculate in gait processes, center of mass motion, the energy of human body Consumption, movement position, joint mechanics situation etc..And the Real-time Alarms such as tumble early warning are carried out according to information obtained.However, by It is limited in the electricity of battery, it is wearable have enough sustainable stringent limitation is also received using duration, it is possible to cause most The period for needing to monitor, wearable foot tool can not continue to use, to affect the monitoring to the motion state of user or even shadow It rings and early warning is carried out to user's body health status at crucial moment.
Summary of the invention
In view of this, the embodiment of the invention provides a kind of user movement condition detection method, device and wearable device, Electric quantity consumption to solve the problems, such as existing wearable device is too fast, sustainable shorter using the time.
According in a first aspect, the embodiment of the invention provides a kind of user movement condition detection methods, including：Obtain user Personal information and/or environmental information, the exercise data class acquired needed for being determined according to the personal information and/or environmental information Type；The actual motion data of user are acquired according to the exercise data type；The actual motion data are analyzed, determine the use The motion state at family.
In embodiments of the present invention, the primary motor data that user is acquired according to exercise data type, in conjunction with personal information And/or environmental information establishes personal portrait model；Determine whether that acquiring collateral motion data establishes the artificial intelligence of second level according to model Energy model, can be fine to required acquisition, the exercise data type of analysis according to the personal information of user and locating environmental information Screening, is effectively reduced the consumption of electricity to reduce collection capacity, calculation amount by the multistage model for including in a model, The time is used to extend the sustainable of the wearable device.
With reference to first aspect, in first aspect first embodiment, the personal information includes：The gender of user is believed At least one of breath, height information, weight information, age information；The environmental information includes：Temperature information and season information At least one of.
With reference to first aspect or first aspect first embodiment, in first aspect second embodiment, according to described The exercise data type that personal information and/or environmental information acquire needed for determining, including：Described in being extracted from the personal information The healthy historical information of user, the data acquired needed for being determined according to the healthy historical information are acceleration information or acceleration Both data and angular velocity data；Or the healthy historical information of the user is extracted from the personal information, according to described The data that healthy historical information and environmental information acquire needed for determining are acceleration information or acceleration information and angular velocity data The two；Or the data acquired needed for being determined according to the environmental information are acceleration information or acceleration information and angular speed number According to the two.
Second embodiment with reference to first aspect, in first aspect third embodiment, the actual motion data packet Include acceleration information；The analysis actual motion data, determine the motion state of the user, including：Added according to described Speed data obtains the acceleration change information in multiple directions of motion；Judge that user is according to the acceleration change information It is no to remain static；When user is not in stationary state, the movement shape of user is judged according to the acceleration change information State belongs to shuttling movement state or non-cyclic motion state.
Third embodiment with reference to first aspect, in the 4th embodiment of first aspect, if the motion state of user Belong to shuttling movement state, then judges that the motion state of user belongs to walking, running or different according to the acceleration change information Normal walking states.
In embodiments of the present invention, in conjunction with the environmental information of acquisition (such as season, temperature, weather etc.), it can screen and be wanted The exercise data type of acquisition.Also, in subsequent data analysis process, combining environmental information only passes through preliminary analysis Step, that is, can determine whether the current motion state of user, and can analyze for subsequent progress health status and provide data and support, without The analytic process for further executing refinement reduces relevant device to greatly reduce the computational processing to exercise data Electric quantity consumption, improve its cruising ability.
Third embodiment with reference to first aspect, in the 5th embodiment of first aspect, the actual motion data are also Including angular velocity data；The analysis actual motion data, determine the motion state of the user, further include：If with The motion state at family belongs to shuttling movement state, then according to the acceleration change information and angular speed change information, judges to use The motion state at family belong to go upstairs, go downstairs, level walking or running；If the motion state of user belongs to shuttling movement State judges that the motion state of user belongs to and sits down, squats then according to the acceleration change information and angular speed change information Under, stand up, jump or fall.
With reference to first aspect second, third, the 4th or the 5th embodiment should in first aspect sixth embodiment User movement condition detection method further includes：The health status of the user is determined according to the actual motion data of the user.
Sixth embodiment with reference to first aspect, it is described according to the user's in the 7th embodiment of first aspect Actual motion data determine the health status of the user, including：It is determined according to the personal information and/or environmental information to be checked The health status range of survey；According to the health status range, acceleration information and in advance the gait that trains deviates model, Determine that the gait of the user deviates the degree of normal sample crowd；If the gait of the user deviates the journey of normal sample crowd Degree is greater than preset threshold, then deviates the degree and the actual motion data of normal sample crowd according to the gait of the user, Judge that the motion state of the user belongs to normal state or morbid state, otherwise, judges that the motion state of the user belongs to normally State.
7th embodiment with reference to first aspect, in the 8th embodiment of first aspect, when can not be according to the individual It is described true according to the actual motion data of the user when information and/or environmental information determine health status range to be detected The health status of the fixed user further includes：According to the acceleration information, angular velocity data and the gait that trains in advance Deviate model, determines that the gait of the user deviates the degree of normal sample crowd；If the gait of the user deviates normal sample The degree of this crowd is greater than preset threshold, then deviates the degree and the reality of normal sample crowd according to the gait of the user Exercise data judges that the motion state of the user belongs to normal state or morbid state, otherwise, judges the motion state of the user Belong to normal state.
7th or the 8th embodiment with reference to first aspect, in the 9th embodiment of first aspect, the user movement shape State detection method further includes：To judge the motion state of the user belong to normal state or morbid state judging result test Card；According to verification result to first pass through in advance SVM algorithm determine every kind of motion state under every kind of morbid state corresponding weight Set and ill threshold value optimize.
9th embodiment with reference to first aspect, in the tenth embodiment of first aspect, described pair judges the user Motion state belong to normal state or morbid state judging result verified, including：According to the actual motion data and Updated gait deviates model, and the gait for redefining the user deviates the degree of normal sample crowd；After the update Gait to deviate model be the model obtained according to the data of the sample population for belonging to normal state screened again；If redefining The gait of the user deviate the degree of normal sample crowd and be greater than the preset threshold, then according to the use that redefines The gait at family deviates the degree and the actual motion data of normal sample crowd, rejudges the motion state category of the user In normal state or morbid state；Last judging result is verified according to the judging result rejudged.
According to second aspect, the embodiment of the invention provides a kind of user movement condition checkout gears, including：Acquisition of information Module determines institute according to the personal information and/or environmental information for obtaining the personal information and/or environmental information of user The exercise data type that need to be acquired；Actual motion data acquisition module, for acquiring user's according to the exercise data type Actual motion data；Moving state determining module determines the movement shape of the user for analyzing the actual motion data State.
In embodiments of the present invention, the primary motor data that user is acquired according to exercise data type, in conjunction with personal information And/or environmental information establishes personal portrait model；Determine whether that acquiring collateral motion data establishes the artificial intelligence of second level according to model Energy model, can be fine to required acquisition, the exercise data type of analysis according to the personal information of user and locating environmental information Screening, is effectively reduced the consumption of electricity to reduce collection capacity, calculation amount by the multistage model for including in a model, The time is used to extend the sustainable of the wearable device.
In conjunction with second aspect, in second aspect first embodiment, the personal information includes：The gender of user is believed At least one of breath, height information, weight information, age information；The environmental information includes：Temperature information and season information At least one of.
In conjunction with second aspect or second aspect first embodiment, in second aspect second embodiment, the information Module is obtained to be specifically used for：The healthy historical information that the user is extracted from the personal information, according to the healthy history The data that information acquires needed for determining are acceleration information or both acceleration information and angular velocity data；Or from the individual The healthy historical information that the user is extracted in information acquires needed for being determined according to the healthy historical information and environmental information Data are acceleration information or both acceleration information and angular velocity data；Or acquisition needed for being determined according to the environmental information Data be acceleration information or both acceleration information and angular velocity data.
In conjunction with second aspect second embodiment, in second aspect third embodiment, the actual motion data packet Include acceleration information；The moving state determining module includes：Acceleration change acquisition of information submodule, for being added according to described Speed data obtains the acceleration change information in multiple directions of motion；Shuttling movement judging submodule, for being added according to described Velocity variations information judges whether user remains static；When user is not in stationary state, become according to the acceleration Change information and judges that the motion state of user belongs to shuttling movement state or non-cyclic motion state.
In conjunction with second aspect third embodiment, in the 4th embodiment of second aspect, the motion state determines mould Block further includes：Motion state judging submodule, if the motion state of user belongs to shuttling movement state, the motion state is sentenced Disconnected submodule judges that the motion state of user belongs to walking, running or abnormal walking states according to the acceleration change information.
In embodiments of the present invention, in conjunction with the environmental information of acquisition (such as season, temperature, weather etc.), it can screen and be wanted The exercise data type of acquisition.Also, in subsequent data analysis process, combining environmental information only passes through preliminary analysis Step, that is, can determine whether the current motion state of user, and can analyze for subsequent progress health status and provide data and support, without The analytic process for further executing refinement reduces relevant device to greatly reduce the computational processing to exercise data Electric quantity consumption, improve its cruising ability.
In conjunction with second aspect third embodiment, in the 5th embodiment of second aspect, the actual motion data are also Including angular velocity data；The moving state determining module further includes：Motion state judging submodule, if the movement shape of user State belongs to shuttling movement state, and the motion state judging submodule is according to the acceleration change information and angular speed variation letter Breath, judge the motion state of user belong to go upstairs, go downstairs, level walking or running；If the motion state category of user In non-cyclic motion state, the motion state judging submodule is according to the acceleration change information and angular speed variation letter Breath, judges that the motion state of user belongs to and sits down, squats down, stands up, jumps or fall.
In conjunction with second aspect second, third, the 4th or the 5th embodiment should in second aspect sixth embodiment User movement condition checkout gear further includes：Health status determining module, for true according to the actual motion data of the user The health status of the fixed user.
In conjunction with second aspect sixth embodiment, in the 7th embodiment of second aspect, the health status determines mould Block includes：Health status range determination submodule, it is to be detected strong for being determined according to the personal information and/or environmental information Health state range；Health status judging submodule, for according to the health status range, acceleration information and training in advance Gait out deviates model, determines that the gait of the user deviates the degree of normal sample crowd；If the gait of the user is inclined Degree from normal sample crowd is greater than preset threshold, then according to the gait of the user deviate normal sample crowd degree and The actual motion data judge that the motion state of the user belongs to normal state or morbid state, otherwise, judge the user's Motion state belongs to normal state.
In conjunction with the 7th embodiment of second aspect, in the 8th embodiment of second aspect, the health status determines mould Block further includes：Gait departure degree determines submodule, for according to the acceleration information, angular velocity data and training in advance Gait out deviates model, determines that the gait of the user deviates the degree of normal sample crowd；Health status determines submodule, If the degree that the gait of the user deviates normal sample crowd is greater than preset threshold, the health status determine submodule according to The gait of the user deviates the degree and the actual motion data of normal sample crowd, judges the motion state of the user Belong to normal state or morbid state, otherwise, judges that the motion state of the user belongs to normal state.
In conjunction with second aspect the 7th or the 8th embodiment, in the 9th embodiment of second aspect, the user movement shape State detection device further includes：Authentication module, for judge the motion state of the user belong to normal state or morbid state sentence Disconnected result is verified；Optimization module, for being existed according to verification result to every kind of motion state that SVM algorithm determines is first passed through in advance Corresponding weight set and ill threshold value optimize under every kind of morbid state.
In conjunction with the 9th embodiment of second aspect, in the tenth embodiment of second aspect, the authentication module is specifically used In：Deviate model according to the actual motion data and updated gait, the gait for redefining the user deviates just The degree of normal sample population；It is according to the sample population for belonging to normal state screened again that the updated gait, which deviates model, The obtained model of data；If the degree that the gait of the user redefined deviates normal sample crowd is greater than described default Threshold value then deviates the degree and the actual motion data of normal sample crowd according to the gait of the user redefined, The motion state for rejudging the user belongs to normal state or morbid state；According to the judging result rejudged to the last time Judging result is verified.
According to the third aspect, the embodiment of the invention provides a kind of wearable devices, including：Memory and processor, institute It states and communicates with each other connection between memory and the processor, computer instruction, the processor are stored in the memory By executing the computer instruction, thereby executing described in any one of first aspect or first aspect embodiment User movement condition detection method.
It is described computer-readable the embodiment of the invention provides a kind of computer readable storage medium according to fourth aspect Storage medium stores computer instruction, and the computer instruction is for making the computer execute first aspect or first aspect Any one embodiment described in user movement condition detection method.
Detailed description of the invention
The features and advantages of the present invention will be more clearly understood by referring to the accompanying drawings, and attached drawing is schematically without that should manage Solution is carries out any restrictions to the present invention, in the accompanying drawings：
Fig. 1 shows the flow chart (one) of the user movement condition detection method of the embodiment of the present invention；
Fig. 2 shows the schematic diagrames for the sole sensitive zones that the intelligence of the embodiment of the present invention has enough；
Fig. 3 A shows the flow chart (two) of the user movement condition detection method of the embodiment of the present invention；
Fig. 3 B shows the flow chart (three) of the user movement condition detection method of the embodiment of the present invention；
Fig. 4 A shows the flow chart (four) of the user movement condition detection method of the embodiment of the present invention；
Fig. 4 B shows the flow chart (five) of the user movement condition detection method of the embodiment of the present invention；
Fig. 4 C shows the flow chart (six) of the user movement condition detection method of the embodiment of the present invention；
Fig. 5 shows the structural schematic diagram (one) of the user movement condition checkout gear of the embodiment of the present invention；
Fig. 6 shows the structural schematic diagram (two) of the user movement condition checkout gear of the embodiment of the present invention；
Fig. 7 shows the structural schematic diagram (three) of the user movement condition checkout gear of the embodiment of the present invention；
Fig. 8 shows the structural schematic diagram of the wearable device of the embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those skilled in the art are not having Every other embodiment obtained under the premise of creative work is made, shall fall within the protection scope of the present invention.
The embodiment of the invention provides a kind of user movement condition detection methods, as shown in Figure 1, the user movement state is examined Survey method mainly includes：
Step S11：The personal information and/or environmental information for obtaining user are determined according to personal information and/or environmental information The exercise data type of required acquisition.
Optionally, in some embodiments of the invention, the personal information of the user refers to：The gender information of user, body At least one of high information, weight information, age information.The environmental information refers in temperature information and season information at least One of.
In practical applications, it realizes that the foundation of the detection of the motion state of user is the real-time motion data of user, and leads to The motion state for analyzing the user that the real-time motion data can be got is crossed, the personal physical trait with user is closely related. For example, the difference in states such as walking, runnings of user of the Sex Determination of user；Similarly, height, weight, age Difference, the movement sign of user may all can be different, therefore, can be obtained according to the different personal information of user corresponding Exercise data type.Alternatively, some specific body signs may be concentrated and be appeared in some specific crowds, for example, It for signs such as bowlegs, splayfoots, generally occurs from young group, therefore, when the object that needs are studied When for older group (e.g. adult), the exercise data for obtaining the signs such as characterization bowlegs, splayfoot can not be considered Type.Alternatively, may focus mostly on the accident being likely to occur in some movements in specific season.Such as in movement The case where tumble, is mainly in winter, and main cause may be that climate influences, and ground is wet and slippery, and user is careless during the motion The probability of tumble is larger.Therefore, when summer carrying out data acquisition, it can not consider the exercise data class for obtaining characterization tumble state Type.
It should be noted that above content is by way of example only, in practical applications, required acquisition can be adjusted as needed Exercise data type.For example, can be according to the healthy historical information (medical record information for extracting the user in the personal information of user Deng), the data acquired needed for being determined according to healthy historical information are acceleration information or acceleration information and angular velocity data two Person；Alternatively, extracting the healthy historical information of user from personal information, institute is determined according to healthy historical information and environmental information The data that need to be acquired are acceleration information or both acceleration information and angular velocity data；Alternatively, determining institute according to environmental information The data that need to be acquired are acceleration information or both acceleration information and angular velocity data.
Step S12：The actual motion data of user are acquired according to exercise data type.In the personal information according to user And/or after environmental information has determined the exercise data type to be obtained, the actual motion of user can be obtained according to the type Data.
Optionally, in some embodiments of the invention, the sole that the intelligence that can be worn by user has enough obtains practical Exercise data.As shown in Fig. 2, 5 regions (MFF, LFF, MMF, LMF, HEEL) of the sole are uniform-distribution with pressure monitoring power generation Integrated soft sensing technology is made of, the work of elastic sensing element elastic sensing element, displacement sensing element, power generation module group Be make to be acted on some area and be converted to by measuring pressure displacement or strain based on Wheatstone bridge pressure resistance type electrostrictive strain Signal.
The actual motion data of above-mentioned steps S12 acquisition may include user or so sole MFF, LFF, LMF, HEEL tetra- Pressure data, each pressure data of the region (no MMF) in multiple directions of motion account for the specific gravity of gross pressure, acceleration information, Angular velocity data and corresponding time data etc..
Optionally, in some embodiments of the invention, which includes acceleration information.Such as Fig. 3 A institute Show, step S13, analyzes actual motion data, determine the motion state of user, may particularly include：
Step S131：According to acceleration information, the acceleration change information in multiple directions of motion is obtained；
Step S132：Judge whether user remains static according to acceleration change information；
Step S133：When user is not in stationary state, the motion state of user is judged according to acceleration change information Belong to shuttling movement state or non-cyclic motion state.
It can be good at distinguishing the stationary state and motion state of human body behavior using acceleration information, and can be good at Distinguish shuttling movement state and non-cyclic motion state.
Optionally, multiple direction includes the both direction of the first dimension x along sole length direction, along shoe sole width side To the second dimension y both direction and the third dimension z perpendicular to plane where sole both direction.
Above-mentioned steps S12 acquisition acceleration information can be using the 3-axis acceleration sensor on sole, according to for example (frequency of people's walking is generally in 110 steps/minute for the sample frequency of 76Hz, 88Hz, 100Hz, 105Hz, 120Hz or 150Hz (1.8Hz), frequency when running do not exceed 5Hz, select any of the above-described kind of sample frequency that can accelerate in accurately reaction Degree variation and system effectiveness, energy consumption etc. obtain preferable counterbalance effect), acquire above-mentioned first dimension x, the second dimension y and The acceleration information of each dimension both direction in third dimension z.
General acceleration is assured that user is not stationary state when being not zero.In addition, according to acceleration change information The frequency occurred to the peak value of track counts.In horizontal movement, vertical and two acceleration that advance can be in general user Existing cyclically-varying.In the movement that foot is received in walking, since single foot contacts to earth center of gravity upwards, vertical direction acceleration is in forward direction Increased trend continues forward later, and decentralization bipod bottoms out, and acceleration is opposite.Horizontal acceleration reduces when receiving foot, Increase when taking a step.It may be seen that vertical and generation of advancing acceleration and time substantially one are just in walking movement Chord curve, and have a peak value in certain point, wherein the acceleration change of vertical direction is maximum.
A variety of shuttling movements are counted in the manner described above, shuttling movement state can be determined in some dimension direction On acceleration at cyclically-varying, therefore above-mentioned steps S133 can distinguish shuttling movement state according to this rule and non-follow Ring motion state.
In practical applications, the shuttling movement state of human body behavior and acyclic can be distinguished well using acceleration information Motion state.But similar motor behavior is just compared and is difficult to distinguish.Also, it is clear that acceleration information is particularly suited for direction Movement differentiate, and for fall detection, period of motion link, splayfoot etc., can not directly be sentenced by acceleration information Not, then it needs to differentiate using angular speed.Therefore, in some embodiments of the invention, can be carried out in conjunction with angular velocity data Analysis and distinguishing.Specifically, angular velocity data can be acquired with the gyroscope on sole.As shown in Figure 3B, step S13 is also wrapped It includes：
Step S134：If the motion state of user belongs to shuttling movement state, according to the acceleration change information With angular speed change information, judge the motion state of user belong to go upstairs, go downstairs, level walking or running；
Step S135：If the motion state of user belongs to non-cyclic motion state, believed according to the acceleration change Breath and angular speed change information, judge that the motion state of user belongs to and sit down, squat down, stand up, jump or fall.
At this point, in conjunction with acceleration information and angular velocity data refinement differentiation can be carried out to similar movement.Also, benefit With information threshold method, the different motion link of non-cyclic motion state can be distinguished well.And fallen and moved by identification, energy Enough carry out tumble early warning.
It is further described below by taking fall detection as an example below：
Falling has the feature of biggish acceleration peak value and angular speed peak value, this is because can be with very fast during falling down Speed and the collision of low gesture object, thus the acceleration peak value and angular speed peak value that generate than walking in daily routines, go upstairs Most of general process are big.Since human motion action process has complexity and randomness, sentence using only acceleration information The generation of disconnected falling over of human body behavior can bring very big erroneous judgement.So the embodiment of the present invention uses SVMAAnd SVMWThe letter combined Threshold method is ceased, tumble can be accurately distinguished and generates the lesser low-intensity movement of SVM peak value.
Specifically, corresponding acceleration signal vector mould threshold value of falling can use SVMAT=20m/s2, angular velocity signal vector Mould threshold value can use SVMWT=4rad/s.
After determining the motion state of user, it can further judge whether the motion state of user belongs to normal state. As described above, which may include pressure data, can distinguish morbid state and normal state using pressure data, but The effect determined in conjunction with motion state is more preferable.
For example, by medical files and experiments have shown that：Normal person and rheumatoid arthritis metatarsalgia patient are compared Compared with discovery, when static state is stood, the maximum pressure distribution of two groups of people's front foots does not find notable difference, but when walking, foot disease exists Phalanx leaves the maximum pressure in face of ground and is all concentrated on the outside of front foot mostly, and normal foot leaves the maximum pressure in face of ground in phalanx It is all concentrated in the middle part of front foot mostly；Plantar grade pressurization time phase of diabetes patient rises appreciably than normal person, and its front foot Contact time is short compared with what normal person came, and the process of contacting to earth is a quick transient process.
The user movement condition detection method of the embodiment of the present invention, due to can personal information according to user and locating ring Border information screens the exercise data type of required acquisition, can be into reduce the collection capacity to user movement data One step reduces the calculation amount analyzed the exercise data.The user movement condition detection method can effectively reduce wearable set Standby power consumption, reduces the consumption of electricity, so that extending the sustainable of the wearable device uses the time.
Optionally, in some embodiments of the invention, as shown in fig. 4 a and fig. 4b, the user movement condition detection method After above-mentioned steps S13, it may also include：Step S14 determines the health status of user according to the actual motion data of user. Specifically, the detailed process of step S14 includes：
Step S141, the gait trained according to actual motion data and in advance deviate model, determine the gait of user Deviate the degree of normal sample crowd.
Step S142, if the degree that the gait of user deviates normal sample crowd is greater than preset threshold, according to user's Gait deviates the degree and actual motion data of normal sample crowd, judges that the motion state of user belongs to normal state or disease Otherwise state judges that the motion state of user belongs to normal state.
It is very big that lasting big data training subdivision calculation amount is carried out in the embodiment of the present invention, with wherein plantar pressure data For, sample rate 100Hz, each vola acquires 6 directional pressure values of 3000 points, everyone original data volume per second is 360 Ten thousand, more than data mining i.e. 3,600,000 dimensions, huge operand accordingly is brought to subsequent data processing.
In order to reduce the calculation amount of data processing, in the embodiment of the present invention, data are dropped by step S141 first Dimension.The data that the degree that step S142 only deviates normal sample crowd to the gait of user is greater than preset threshold carry out pathology areas Point, to reduce calculation amount, improve computational efficiency.
In addition, in the embodiment of the present invention former problem can also be converted to dual problem processing, to further decrease complexity Degree.
Optionally, which includes the N class parameter value in n region of user's sole, and n and N are to be greater than or wait In 1 integer；
Above-mentioned steps S141, the gait trained according to actual motion data and in advance deviate model, determine user's The process that gait deviates the degree of normal sample crowd specifically includes：
Determine that the gait of the user deviates the degree x of normal sample crowd using following formula：
Wherein, qjiFor the i-th class parameter value in j-th of region of user's sole,For the normal sample crowd's shoes being obtained ahead of time The average value of the N class parameter in j-th of region at bottom, 1≤i≤N, 1≤j≤n.
Specifically, above-mentioned n region may include tetra- regions MFF, LFF, LMF, HEEL as shown in Figure 2, above-mentioned N class ginseng Numerical value such as may include acceleration, angular speed, pressure value.
Wherein, above-mentioned sample population is theoretically normal population.At this point, by determining that user's gait deviates normal population Degree can screen away normal users, only further discriminate between in the presence of the possible user of morbid state.
Optionally, the detailed process of above-mentioned steps S142 includes：
According to first pass through in advance SVM algorithm determine every kind of motion state under every kind of morbid state corresponding weight set and Ill threshold value determines the motion state of user corresponding weight set and ill threshold value under every kind of morbid state；Wherein weight Set includes the corresponding weighted value of class parameter every in N class parameter and the corresponding weighted value of x；
According to actual motion data, x and the motion state of user, corresponding weight set is carried out under every kind of morbid state Weighted calculation obtains the weighted value under every kind of morbid state；
Weighted value under every kind of morbid state is compared with corresponding ill threshold value, if at least one weighted value is greater than morbid state Threshold value, it is determined that the motion state of user belongs to morbid state, otherwise, it determines the motion state of user belongs to normal state.
Here, by analyzing performance of the different motion state under different morbid state, it can determine different motion shape The weighted value of parameter of the state under different morbid state.Such as when normal person's standing and walking, left and right plantar pressure surge pressure distribution It is essentially identical；And diabetic and critical person, range of motion become smaller and front foot/metapedes pressure are caused to significantly increase, and pressure It is unevenly distributed weighing apparatus.Therefore it is standing under walking states, the weight of diabetes corresponding pressure value is big.
At this point, carrying out ill differentiation by the motion state to user, it is able to carry out diabetes, cerebral apoplexy, children eight The early warning of the various diseases such as word foot, Parkinson, and realize recovering aid treatment etc..
Optionally, in some embodiments of the invention, above-mentioned steps S142 carries out the normal state of user and point of morbid state The corresponding weight set of analysis and ill threshold value, can be determined by following steps：
Obtain actual motion data of the sample population sole in presetting multiple dimensions on each dimension direction；
According to the actual motion data of sample population, gait temporal signatures and gait frequency domain character are extracted；
Fusion treatment is carried out to gait temporal signatures and the gait frequency domain character, obtains the fused sample population Gait feature collection；
Using SVM algorithm to the gait feature collection of the sample population according to the normal state and disease under different motion states State is classified, and determines every kind of motion state corresponding weight set and ill threshold value under every kind of morbid state.
Specifically, classify using SVM classifier to gait sample (gait feature collection).It is assumed that having been registered in database M class (M is the integer more than or equal to 1) gait sample, by new gait sample input SVM classifier training, according to input Which kind of that new gait sample belongs in M class be value determine, if having exceeded the range of M class, as new classification M+1 class, Then classifier is updated.
Wherein, the gait sample of ill crowd can be carried out to emphasis calculating, such as extract left and right foot same point, same foot respectively Then 1000 groups of the pressure value in four regions extracts gait temporal signatures and gait frequency domain character, according to the step of ill crowd State feature accurately determines weight set.
Specifically, above-mentioned that fusion treatment is carried out to gait temporal signatures and the gait frequency domain character, it obtains fused The step of gait feature collection of the sample population, including：
According to the actual motion data of sample population, every class parameter is obtained in presetting multiple dimensions on each dimension direction Change curve；The key point of the change curve of every class parameter is obtained using difference algorithm；It extracts the parameter value at key point, drive Impetus and braking momentum, and according to parameter value, driving momentum and the braking momentum at key point, obtain gait temporal signatures； According to key point, waveform alignment is carried out using change curve of the linear interpolation method to every class parameter；Using wavelet packet decomposition algorithm Gait frequency domain character is extracted from the change curve after waveform alignment.
In practical applications, each region active force of sole is related to movement gait, and time-frequency can characterize gait cycle, variation The global features such as rate and acceleration, frequency domain can characterize the minutias such as spectral property.WAVELET PACKET DECOMPOSITION, difference algorithm difference can be used Frequency domain, temporal signatures are extracted from the pressure data of four regions of sole, three dimensions, to identify movement shape using SVM algorithm State and normal state and morbid state.
Wherein, mainly include for the extraction process of temporal signatures：First-order difference algorithm detection front-rear direction (x can be used Axis), the wave crest point and trough point of vertical direction (z-axis) curve, as the key point of force profile, and by vertical direction curve Reference point of the trough point as force profile；Then occur with the pressure value of the key point of vertical direction curve, pressure value Phase, adjacent key point active force change rate and momentum (including driving momentum and braking momentum), corresponding front-rear direction it is bent The pressure value at key point, driving momentum (0 point or more of power and the integral of time are occupy on force-time curve) and system on line The whole gait temporal signatures of impetus (occuping the integral of power below and time on force-time curve at 0 point of) characterization.
Extraction process for frequency domain character mainly includes：Key point in active force elder generation in a vertical direction curve can be incited somebody to action The alignment of active force waveform, to improve, frequency domain character is comparative and classification capacity.Specifically first active force is tieed up with linear interpolation algorithm Number normalizes to same value, and the trough after normalizing on active force vertical direction force curve is gone out by first-order difference algorithm search Point carries out reference for trough point as key point, then with linear interpolation method by the left and right directions (y-axis) in active force, front and back Direction and the alignment of vertical direction curve waveform, the active force after being aligned.Again with L layers of wavelet packet decomposition algorithm from active force Extract whole gait frequency domain character.
Optionally, it is above-mentioned using SVM algorithm to the gait feature collection of the sample population according to different motion states Under normal state and morbid state classify, and determine every kind of motion state corresponding weight set and disease under every kind of morbid state The process of state threshold value can be and first select minimum from multiple wavelet packets of the gait frequency domain character of extraction with fuzzy C-mean algorithm method Wavelet packets set, then sorted based on fuzzy membership with fuzzy C-mean algorithm method select from the set picked out it is minimum optimal WAVELET PACKET DECOMPOSITION coefficient obtains minimum optimal gait frequency domain character subset, then combines with gait temporal signatures, obtains fused Gait feature collection.
Optionally, in some embodiments of the invention, as shown in Figure 4 C, carry out user's in S142 through the above steps After the analysis of normal state and morbid state, it may also include the Optimization Steps to weight set and ill threshold value, specifically, optimization step Suddenly include：
Step S143, to judge the motion state of user belong to normal state or morbid state judging result verify.
Specifically deviateing model according to actual motion data and updated gait, the gait of user is redefined Deviate the degree of normal sample crowd；It is according to the sample people for belonging to normal state screened again that updated gait, which deviates model, The model that the data of group obtain；
If the degree that the gait of the user redefined deviates normal sample crowd is greater than preset threshold, according to again true The gait of fixed user deviates the degree and actual motion data of normal sample crowd, and the motion state for rejudging user belongs to Normal state or morbid state；
Last judging result is verified according to the judging result rejudged.
After being verified by step S143, step S144 is executed, it is true to SVM algorithm is first passed through in advance according to verification result Every kind of fixed motion state corresponding weight set and ill threshold value under every kind of morbid state optimize.With sample size Increase, SVM classifier can adaptively be continued to optimize perfect, improve the execution efficiency of algorithm.
Wherein, SVM classifier can be sampled calculating for no abnormal sample population.Searching exceptional sample When, it may be bigger than normal due to wherein some regional standard difference, another regional standard difference is less than normal, situations such as just offseting, causes not It notes abnormalities, therefore carries out random sampling verifying again.New sample is inputted every time, according to cross-validation method principle, calculates SVM points Class device discrimination.
It is SVM classifier to sample using SVM classifier fitness function to the characteristic value of abnormal not found sample Divide accuracy.Parallel implementation is simulated by keeping the interaction between multiple groups and properly control group, from And even if not using parallel computer, it can also improve the execution efficiency of algorithm.
It further, is the accuracy for guaranteeing actual motion data collected, the user movement shape of the embodiment of the present invention State detection method may also include：Denoising is carried out to actual motion data using Wavelet Transform Threshold method.
In practical applications, the electromagnetic interference in collection process in circuit is main interference source, and electromagnetic interference is high frequency Noise；And human motion is mainly the low frequency signal within 50Hz, the embodiment of the present invention selects wavelet transform threshold method, With band-pass filtering function, calculating speed is fast.It can specifically judge to detection plus threshold value and cadence to filter, that is to say, that phase For the time interval of adjacent two steps at least more than 0.11,0.14,0.17,0.2,0.23,0.27 second, filter high frequency noise can be in standard It really reacts acceleration change and system effectiveness, energy consumption etc. and obtains best counterbalance effect.
In addition, can carry out wavelet decomposition to the pressure data for collecting four regions, handle high-frequency wavelet coefficient, is small The wavelet transform function of three steps of reconstructed wave, by the pressure time-domain signal discretization in four regions, by multi-frequency ingredient Mixed signal decomposes different frequency range, and then the different characteristic according to each seed signal on frequency domain is handled by frequency band；Then, base Removal noise is used in the non_monitor algorithm of matrix and retains the information most represented.Finally, further using supervision algorithm Improve resolution capability.Obtain the high gait data of signal-to-noise ratio.
In embodiments of the present invention, it not only can refer to the personal letter of user when determining the exercise data type to be acquired Breath and/or environmental information screen data.When analyzing actual motion data, the individual of user equally can refer to Information and/or environmental information.It as shown in Figure 4 C, should the mistake based on the novel carry out health status judgement of personal information and/or environment Journey mainly includes：Step S145：Health status range to be detected is determined according to personal information and/or environmental information；Step S146：According to health status range, acceleration information and in advance the gait that trains deviates model, determines that the gait of user is inclined Degree from normal sample crowd；If user gait deviate normal sample crowd degree be greater than preset threshold, according to The gait at family deviates the degree and actual motion data of normal sample crowd, judge the motion state of user belong to normal state or Otherwise morbid state judges that the motion state of user belongs to normal state.
In some embodiments of the invention, it for the judgement of health status, needs to calculate by neural network deep learning Method, combined training model carries out posture judgement, and further progress health status judges.But works as and use neural network deep learning Algorithm carries out lasting big data and trains subdivision calculation amount very big, correspondingly brings huge fortune to subsequent data processing Calculation amount.And for the judgement of some of health status, can first be determined according to userspersonal information and/or environmental information may Health status range, be then based on personal information and/or environmental information and determine whether only to acquire with the health status range The acceleration information of user analyzes the health status of user, obtains to deviate model in conjunction with the gait trained in advance The health status of user is further segmented without acquiring angular velocity data again, can be greatly reduced to exercise data processing Calculation amount extends it and persistently uses the time to effectively reduce the electric quantity consumption of corresponding wearable device, improves continuation of the journey energy Power.
It is illustrated below in conjunction with concrete application example.
In practical applications, many injurys gained in sports or disease may be that concentration is mainly in specific environment or weather.Example Such as, for rheumatic arthritis, disease symptom be affected by climate change it is larger, often weather turn it is cold or rainy before there is joint The symptoms such as pain.Therefore, when the personal information by user knows its medical history with rheumatic arthritis, according to the user Actual motion data when being analyzed, then environmental factor can be taken into account.(such as less than when judging that current environment is colder 10 degrees Celsius) or current season belongs to autumn and winter or current weather belonged to when cloudy day, rainy day, in root Its acceleration change information is obtained according to the acceleration information of user movement, thus judge that user belongs to shuttling movement state, and Further it can determine whether out that user is presently at walking, running or abnormal walking states according to the acceleration change information.Its In, abnormal walking states include that sole mops floor that (i.e. the friction of sole and ground is larger, and is not belonging to appearance of normally walking for walking State).At this point, in conjunction with the personal information (medical history of rheumatic arthritis) of user, current environmental information, (weather turns cold or rainy It is preceding etc.), when judging that user is in abnormal walking states in conjunction with the gait deviation model trained in advance, determine that the user belongs to wind The case where wet arthritis breaks out.
In some embodiments, the abnormal walking states of user can also only be combined with its personal information, or will used The abnormal walking states at family are only combined with environmental information, can equally make above-mentioned judgement.
It can be seen that the movement analyzed by the personal information of user and/or environmental information and according to acceleration information State combines, and can carry out the judgement of the health status of user (on such as according to acceleration information combination neural network algorithm During described in the step S141 and step S142 stated, which is only acceleration information), without combining angle Speed data does further refinement to the training pattern of neural network algorithm, therefore, can greatly reduce and be carried out based on exercise data The operand of analysis improves its cruise duration to reduce the power consumption of the wearable device.
If can not determine that the possible health status of the user detects according to the personal information of user and/or environmental information When range (for example, the health of the user, no passing medical history provides reference), then also need to carry out using in conjunction with angular velocity data The neural network algorithm of subdivision is more detailed motion state analysis and health status analysis (step S141 as escribed above And described in step S142 during, which is acceleration information and angular velocity data).
Method through the embodiment of the present invention carries out the analysis of the motion state and health status of user, is according to movement number According to the primary motor data of type acquisition user, personal portrait model is established in conjunction with personal information and/or environmental information；According to mould Type determines whether that acquiring collateral motion data establishes second level artificial intelligence model.It can personal information according to user and locating ring Border information finely screens the exercise data type of required acquisition, analysis, by the multistage model for including in a model, thus Collection capacity, calculation amount are reduced, the consumption of electricity is effectively reduced.
The embodiment of the present invention also provides a kind of user movement condition checkout gear, optionally, in some implementations of the invention In example, which, which can be, is set in the wearable intelligence foot tool that user is worn, and is e.g. arranged In the sole having enough.As shown in figure 5, the user movement condition checkout gear mainly includes：Data obtaining module 51, reality Exercise data acquisition module 52 and moving state determining module 53 etc..
Wherein, which is used to obtain the personal information and/or environmental information of user, according to personal information And/or environmental information determines the required exercise data type acquired；Detailed content can be found in the step S11 of above method embodiment Associated description.
Actual motion data acquisition module 52 is used to acquire the actual motion data of user according to exercise data type；In detail Content can be found in the associated description of the step S12 of above method embodiment.
Moving state determining module 53 determines the motion state of user for analyzing actual motion data；Detailed content can Referring to the associated description of the step S13 of above method embodiment.
Optionally, in some embodiments of the invention, which includes acceleration information.As shown in fig. 6, The moving state determining module 53 includes：
Acceleration change acquisition of information submodule 531, for according to acceleration information, obtaining adding in multiple directions of motion Velocity variations information；Detailed content can be found in the associated description of the step S131 of above method embodiment.
Shuttling movement judging submodule 532, for judging whether user remains static according to acceleration change information； When user is not in stationary state, according to acceleration change information judge user motion state belong to shuttling movement state or Person's non-cyclic motion state.Detailed content can be found in the associated description of the step S132 and step S133 of above method embodiment.
In practical applications, the shuttling movement state of human body behavior and acyclic can be distinguished well using acceleration information Motion state.But similar motor behavior is just compared and is difficult to distinguish.Also, it is clear that acceleration information is particularly suited for direction Movement differentiate, and for fall detection, period of motion link, splayfoot etc., can not directly be sentenced by acceleration information Not, then it needs to differentiate using angular speed.Therefore, in some embodiments of the invention, can be carried out in conjunction with angular velocity data Analysis and distinguishing.Specifically, angular velocity data can be acquired with the gyroscope on sole.As shown in fig. 6, the motion state determines mould Block further includes：Motion state judging submodule 533 is for executing following steps：If the motion state of user belongs to shuttling movement State, motion state judging submodule 533 judge the movement shape of user according to acceleration change information and angular speed change information State belong to go upstairs, go downstairs, level walking or running；If the motion state of user belongs to non-cyclic motion state, fortune State judging submodule 533 is moved according to acceleration change information and angular speed change information, judges that the motion state of user belongs to It sits down, squat down, stand up, jump or falls.Detailed content can be found in the step S134 and step S135 of above method embodiment Associated description.
The user movement condition checkout gear of the embodiment of the present invention can be believed according to the personal information and locating environment of user Breath screens the exercise data type of required acquisition, so that the collection capacity to user movement data is reduced, it can be further Reduce the calculation amount analyzed the exercise data.The user movement condition checkout gear can effectively reduce wearable device Power consumption, reduces the consumption of electricity, so that extending the sustainable of the wearable device uses the time.
Optionally, in some embodiments of the invention, as shown in fig. 7, the user movement condition checkout gear can also wrap Health status determining module 54 is included, the health status of user is determined for the actual motion data according to user, to user's Health status provides warning information.Detailed content can be found in the associated description of the step S14 of above method embodiment.
Specifically, which includes：Gait departure degree determines submodule, for according to practical fortune Dynamic data and the gait trained in advance deviate model, determine that the gait of user deviates the degree of normal sample crowd；In detail Content can be found in the associated description of the step S141 of above method embodiment.
Health status determines submodule, if the degree that the gait of user deviates normal sample crowd is greater than preset threshold, is good for Health state determines that submodule deviates the degree and actual motion data of normal sample crowd according to the gait of user, judges user's Motion state belongs to normal state or morbid state, otherwise, judges that the motion state of user belongs to normal state；Detailed content can be found in State the associated description of the step S142 of embodiment of the method.
Optionally, in some embodiments of the invention, carrying out user's by above-mentioned health status determining module 54 After the analysis of normal state and morbid state, which may also include：
Authentication module 55, for judge the motion state of user belong to normal state or morbid state judging result test Card；Detailed content can be found in the associated description of the step S143 of above method embodiment.
Optimization module 56, for according to verification result to first pass through in advance SVM algorithm determine every kind of motion state at every kind Corresponding weight set and ill threshold value optimize under morbid state；Detailed content can be found in the step of above method embodiment The associated description of S144.
What health status determining module 54, authentication module 55 shown in Fig. 7 and optimization module 56 were indicated with dotted line frame The reason is that, being equally for the considerations of reducing power consumption, reduction battery consumption, which determines mould in practical applications Block 54, authentication module 55 and optimization module 56 can be the computing platform for being set to cloud, pass through the intelligence foot worn in user The communication module being arranged in tool, it is strong that the computing platform in actual motion data transmission to the cloud of the user that will acquire carries out user The analytical calculation etc. of health state, to be further reduced the intelligence, tool is in use to the consumption of battery enough, to extend Its cruise duration.
In some embodiments of the invention, it for the judgement of health status, needs to calculate by neural network deep learning Method, combined training model carries out posture judgement, and further progress health status judges.But works as and use neural network deep learning Algorithm carries out lasting big data and trains subdivision calculation amount very big, correspondingly brings huge fortune to subsequent data processing Calculation amount.And for the judgement of some of health status, can first be determined according to userspersonal information and/or environmental information may Health status range, be then based on personal information and/or environmental information and determine whether only to acquire with the health status range The acceleration information of user analyzes the health status of user, obtains to deviate model in conjunction with the gait trained in advance The health status of user is further segmented without acquiring angular velocity data again, can be greatly reduced to exercise data processing Calculation amount extends it and persistently uses the time to effectively reduce the electric quantity consumption of corresponding wearable device, improves continuation of the journey energy Power.
In this embodiment, the motion state judging submodule 533 is for executing following steps：If the movement shape of user State belongs to shuttling movement state, and motion state judging submodule 533 judges the motion state of user according to acceleration change information Belong to walking, running or abnormal walking states.
Correspondingly, which further includes：Health status range determination submodule, for according to a People's information and/or environmental information determine health status range to be detected；The healthy shape of the health status determining module 54 at this time State judging submodule is then used for according to health status range, acceleration information and in advance the gait that trains deviates model, really The gait for determining user deviates the degree of normal sample crowd；If the degree that the gait of user deviates normal sample crowd is greater than default Threshold value then deviates the degree and actual motion data of normal sample crowd according to the gait of user, judges the motion state of user Belong to normal state or morbid state, otherwise, judges that the motion state of user belongs to normal state.
Optionally, in embodiments of the present invention, not only it can refer to user when determining the exercise data type to be acquired Personal information and/or environmental information data are screened.When analyzing actual motion data, use equally can refer to The personal information and/or environmental information at family.Also, motion state analysis is carried out based on the personal information and/or environmental information, with And the health status of user is analyzed, the calculation amount to exercise data processing can be greatly reduced, to effectively reduce phase The electric quantity consumption for the wearable device answered extends it and persistently uses the time, improves cruising ability.
It is illustrated below in conjunction with concrete application example.
In practical applications, many injurys gained in sports or disease may be that concentration is mainly in specific environment or weather.Example Such as, for rheumatic arthritis, disease symptom be affected by climate change it is larger, often weather turn it is cold or rainy before there is joint The symptoms such as pain.Therefore, when the personal information by user knows its medical history with rheumatic arthritis, according to the user Actual motion data when being analyzed, then environmental factor can be taken into account.(such as less than when judging that current environment is colder 10 degrees Celsius) or current season belongs to autumn and winter or current weather belonged to when cloudy day, rainy day, in root Its acceleration change information is obtained according to the acceleration information of user movement, thus judge that user belongs to shuttling movement state, and Further it can determine whether out that user is presently at walking, running or abnormal walking states according to the acceleration change information.Its In, abnormal walking states include that sole mops floor that (i.e. the friction of sole and ground is larger, and is not belonging to appearance of normally walking for walking State).At this point, in conjunction with the personal information (medical history of rheumatic arthritis) of user, current environmental information, (weather turns cold or rainy It is preceding etc.), when judging that user is in abnormal walking states in conjunction with the gait deviation model trained in advance, determine that the user belongs to wind The case where wet arthritis breaks out.
In some embodiments, the abnormal walking states of user can also only be combined with its personal information, or will used The abnormal walking states at family are only combined with environmental information, can equally make above-mentioned judgement.
It can be seen that the movement analyzed by the personal information of user and/or environmental information and according to acceleration information State combines, and can carry out the judgement of the health status of user (on such as according to acceleration information combination neural network algorithm During described in the step S141 and step S142 stated, which is only acceleration information), without combining angle Speed data does further refinement to the training pattern of neural network algorithm, therefore, can greatly reduce and be carried out based on exercise data The operand of analysis improves its cruise duration to reduce the power consumption of the wearable device.
If can not determine that the possible health status of the user detects according to the personal information of user and/or environmental information When range (for example, the health of the user, no passing medical history provides reference), then the health status determining module 54 also needs to adopt With the neural network algorithm and angular velocity data being finely divided in conjunction with angular velocity data, more detailed motion state point is done (during described in step S141 and step S142 as escribed above, which is to add for analysis and health status analysis Speed data and angular velocity data).
Device through the embodiment of the present invention carries out the analysis of the motion state and health status of user, is according to movement number According to the primary motor data of type acquisition user, personal portrait model is established in conjunction with personal information and/or environmental information；According to mould Type determines whether that acquiring collateral motion data establishes second level artificial intelligence model.It can personal information according to user and locating ring Border information finely screens the exercise data type of required acquisition, analysis, by the multistage model for including in a model, thus Collection capacity, calculation amount are reduced, the consumption of electricity is effectively reduced.
The embodiment of the invention also provides a kind of wearable devices, as shown in figure 8, the wearable device may include processing Device 81 and memory 82, wherein processor 81 can be connected with memory 82 by bus or other modes, to pass through in Fig. 8 For bus connection.In a preferred embodiment, the wearable device can for one intelligence foot tool, but the present invention not as Limit.
Processor 81 can be central processing unit (Central Processing Unit, CPU).Processor 81 can be with For other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit (Application Specific Integrated Circuit, ASIC), field programmable gate array (Field- Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic, The combination of the chips such as discrete hardware components or above-mentioned all kinds of chips.
Memory 82 is used as a kind of non-transient computer readable storage medium, can be used for storing non-transient software program, non- Transient computer executable program and module, as the display device for mounting on vehicle key screen method in the embodiment of the present invention is corresponding Program instruction/module is (for example, data obtaining module shown in fig. 5 51, actual motion data acquisition module 52 and motion state are true Cover half block 53).Non-transient software program, instruction and the module that processor 81 is stored in memory 82 by operation, thus Execute the various function application and data processing of processor, i.e. user movement state-detection in realization above method embodiment Method.
Memory 82 may include storing program area and storage data area, wherein storing program area can storage program area, Application program required at least one function；It storage data area can the data etc. that are created of storage processor 81.In addition, storage Device 82 may include high-speed random access memory, can also include non-transient memory, for example, at least a magnetic disk storage Part, flush memory device or other non-transient solid-state memories.In some embodiments, it includes relative to place that memory 82 is optional The remotely located memory of device 81 is managed, these remote memories can pass through network connection to processor 81.The reality of above-mentioned network Example includes but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
One or more of modules are stored in the memory 82, when being executed by the processor 81, are executed Such as the user movement condition detection method in Fig. 1-Fig. 4 C illustrated embodiment.
Above-mentioned wearable device detail can correspond to refering to fig. 1 that corresponding correlation is retouched into embodiment shown in Fig. 4 C It states and is understood with effect, details are not described herein again.
It is that can lead to it will be understood by those skilled in the art that realizing all or part of the process in above-described embodiment method Computer program is crossed to instruct relevant hardware and complete, the program can be stored in a computer-readable storage medium In, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, the storage medium can for magnetic disk, CD, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), flash memory (Flash Memory), hard disk (Hard Disk Drive, abbreviation：) or solid state hard disk HDD (Solid-State Drive, SSD) etc.；The storage medium can also include the combination of the memory of mentioned kind.
Although being described in conjunction with the accompanying the embodiment of the present invention, those skilled in the art can not depart from the present invention Spirit and scope in the case where various modifications and variations can be made, such modifications and variations are each fallen within by appended claims institute Within the scope of restriction.

Claims (24)

1. a kind of user movement condition detection method, which is characterized in that including：
The personal information and/or environmental information for obtaining user, acquisition needed for being determined according to the personal information and/or environmental information Exercise data type；
The actual motion data of user are acquired according to the exercise data type；
The actual motion data are analyzed, determine the motion state of the user.
2. user movement condition detection method according to claim 1, which is characterized in that the personal information includes：With At least one of the gender information at family, height information, weight information, age information；The environmental information includes：Temperature information And at least one of season information.
3. user movement condition detection method according to claim 1 or 2, which is characterized in that according to the personal information And/or environmental information determines the required exercise data type acquired, including：
The healthy historical information that the user is extracted from the personal information is adopted needed for being determined according to the healthy historical information The data integrated is acceleration information or both acceleration informations and angular velocity data；Or
The healthy historical information that the user is extracted from the personal information, according to the healthy historical information and environmental information The data acquired needed for determining are acceleration information or both acceleration information and angular velocity data；Or
The data acquired needed for being determined according to the environmental information are acceleration information or acceleration information and angular velocity data two Person.
4. user movement condition detection method according to claim 3, which is characterized in that the actual motion data include Acceleration information；
The analysis actual motion data, determine the motion state of the user, including：
According to the acceleration information, the acceleration change information in multiple directions of motion is obtained；
Judge whether user remains static according to the acceleration change information；
When user is not in stationary state, judge that the motion state of user belongs to circulation fortune according to the acceleration change information Dynamic state or non-cyclic motion state.
5. user movement condition detection method according to claim 4, which is characterized in that if the motion state category of user In shuttling movement state, then judge that the motion state of user belongs to walking, running or exception according to the acceleration change information Walking states.
6. user movement condition detection method according to claim 4, which is characterized in that the actual motion data are also wrapped Include angular velocity data；
The analysis actual motion data, determine the motion state of the user, further include：
If the motion state of user belongs to shuttling movement state, according to the acceleration change information and angular speed variation letter Breath, judge the motion state of user belong to go upstairs, go downstairs, level walking or running；
If the motion state of user belongs to non-cyclic motion state, changed according to the acceleration change information and angular speed Information judges that the motion state of user belongs to and sits down, squats down, stands up, jumps or fall.
7. the user movement condition detection method according to any one of claim 3-6, which is characterized in that further include：
The health status of the user is determined according to the actual motion data of the user.
8. user movement condition detection method according to claim 7, which is characterized in that the reality according to the user Border exercise data determines the health status of the user, including：
Health status range to be detected is determined according to the personal information and/or environmental information；
According to the health status range, acceleration information and in advance the gait that trains deviates model, determines the user Gait deviate normal sample crowd degree；
If the degree that the gait of the user deviates normal sample crowd is greater than preset threshold, the gait according to the user is inclined Degree and the actual motion data from normal sample crowd, judge that the motion state of the user belongs to normal state or disease Otherwise state judges that the motion state of the user belongs to normal state.
9. user movement condition detection method according to claim 8, which is characterized in that when personal can not being believed according to described It is described to be determined according to the actual motion data of the user when breath and/or environmental information determine health status range to be detected The health status of the user further includes：
According to the acceleration information, angular velocity data and in advance the gait that trains deviates model, determines the user's The degree of gait deviation normal sample crowd；
If the degree that the gait of the user deviates normal sample crowd is greater than preset threshold, the gait according to the user is inclined Degree and the actual motion data from normal sample crowd, judge that the motion state of the user belongs to normal state or disease Otherwise state judges that the motion state of the user belongs to normal state.
10. user movement condition detection method according to claim 8 or claim 9, which is characterized in that further include：
To judge the motion state of the user belong to normal state or morbid state judging result verify；
According to verification result to first pass through in advance SVM algorithm determine every kind of motion state under every kind of morbid state corresponding weight Set and ill threshold value optimize.
11. user movement condition detection method according to claim 10, which is characterized in that described pair judges the user Motion state belong to normal state or morbid state judging result verified, including：
Deviate model according to the actual motion data and updated gait, the gait for redefining the user deviates just The degree of normal sample population；It is according to the sample population for belonging to normal state screened again that the updated gait, which deviates model, The obtained model of data；
If the degree that the gait of the user redefined deviates normal sample crowd is greater than the preset threshold, according to weight The gait of the user newly determined deviates the degree and the actual motion data of normal sample crowd, rejudges the use The motion state at family belongs to normal state or morbid state；
Last judging result is verified according to the judging result rejudged.
12. a kind of user movement condition checkout gear, which is characterized in that including：
Data obtaining module, for obtaining the personal information and/or environmental information of user, according to the personal information and/or ring The exercise data type that border information acquires needed for determining；
Actual motion data acquisition module, for acquiring the actual motion data of user according to the exercise data type；
Moving state determining module determines the motion state of the user for analyzing the actual motion data.
13. user movement condition checkout gear according to claim 12, which is characterized in that the personal information includes： At least one of the gender information of user, height information, weight information, age information；The environmental information includes：Temperature letter At least one of breath and season information.
14. user movement condition checkout gear according to claim 12 or 13, which is characterized in that the acquisition of information mould Block is specifically used for：
The healthy historical information that the user is extracted from the personal information is adopted needed for being determined according to the healthy historical information The data integrated is acceleration information or both acceleration informations and angular velocity data；Or
The healthy historical information that the user is extracted from the personal information, according to the healthy historical information and environmental information The data acquired needed for determining are acceleration information or both acceleration information and angular velocity data；Or
The data acquired needed for being determined according to the environmental information are acceleration information or acceleration information and angular velocity data two Person.
15. user movement condition checkout gear according to claim 13, which is characterized in that the actual motion data packet Include acceleration information；
The moving state determining module includes：
Acceleration change acquisition of information submodule, for obtaining the acceleration in multiple directions of motion according to the acceleration information Spend change information；
Shuttling movement judging submodule, for judging whether user remains static according to the acceleration change information；When When user is not in stationary state, judge that the motion state of user belongs to shuttling movement state according to the acceleration change information Or non-cyclic motion state.
16. user movement condition checkout gear according to claim 15, which is characterized in that the motion state determines mould Block further includes：
Motion state judging submodule, if the motion state of user belongs to shuttling movement state, motion state judgement Module judges that the motion state of user belongs to walking, running or abnormal walking states according to the acceleration change information.
17. user movement condition checkout gear according to claim 15, which is characterized in that the actual motion data are also Including angular velocity data；
The moving state determining module further includes：
Motion state judging submodule, if the motion state of user belongs to shuttling movement state, motion state judgement Module judges that the motion state of user belongs to and goes upstairs, downstairs according to the acceleration change information and angular speed change information Ladder, level walking or running；
If the motion state of user belongs to non-cyclic motion state, the motion state judging submodule is according to the acceleration Change information and angular speed change information judge that the motion state of user belongs to and sit down, squat down, stand up, jump or fall.
18. user movement condition checkout gear described in any one of 4-17 according to claim 1, which is characterized in that further include：
Health status determining module determines the health status of the user for the actual motion data according to the user.
19. user movement condition checkout gear according to claim 18, which is characterized in that the health status determines mould Block includes：
Health status range determination submodule, for determining health to be detected according to the personal information and/or environmental information State range；
Health status judging submodule, for according to the health status range, acceleration information and the step that trains in advance State deviates model, determines that the gait of the user deviates the degree of normal sample crowd；
If the degree that the gait of the user deviates normal sample crowd is greater than preset threshold, the gait according to the user is inclined Degree and the actual motion data from normal sample crowd, judge that the motion state of the user belongs to normal state or disease Otherwise state judges that the motion state of the user belongs to normal state.
20. user movement condition checkout gear according to claim 19, which is characterized in that the health status determines mould Block further includes：
Gait departure degree determines submodule, for training according to the acceleration information, angular velocity data and in advance Gait deviates model, determines that the gait of the user deviates the degree of normal sample crowd；
Health status determines submodule, if the degree that the gait of the user deviates normal sample crowd is greater than preset threshold, institute It states health status and determines degree and the actual motion number of the submodule according to the gait of user deviation normal sample crowd According to judging that the motion state of the user belongs to normal state or morbid state, otherwise, judge that the motion state of the user belongs to just Normality.
21. user movement condition checkout gear described in 9 or 20 according to claim 1, which is characterized in that further include：
Authentication module, for judge the motion state of the user belong to normal state or morbid state judging result test Card；
Optimization module, for according to verification result to first pass through in advance SVM algorithm determine every kind of motion state under every kind of morbid state Corresponding weight set and ill threshold value optimize.
22. user movement condition checkout gear according to claim 21, which is characterized in that the authentication module is specifically used In：
Deviate model according to the actual motion data and updated gait, the gait for redefining the user deviates just The degree of normal sample population；It is according to the sample population for belonging to normal state screened again that the updated gait, which deviates model, The obtained model of data；
If the degree that the gait of the user redefined deviates normal sample crowd is greater than the preset threshold, according to weight The gait of the user newly determined deviates the degree and the actual motion data of normal sample crowd, rejudges the use The motion state at family belongs to normal state or morbid state；
Last judging result is verified according to the judging result rejudged.
23. a kind of wearable device, which is characterized in that including：
Memory and processor communicate with each other connection, are stored in the memory between the memory and the processor Computer instruction, the processor is by executing the computer instruction, thereby executing any one of such as claim 1-11 institute The user movement condition detection method stated.
24. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has computer to refer to It enables, the computer instruction is for making the computer execute such as user movement state of any of claims 1-11 Detection method.
CN201810556612.7A 2018-05-31 2018-05-31 User motion state detection method and device and wearable device Active CN108831527B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810556612.7A CN108831527B (en) 2018-05-31 2018-05-31 User motion state detection method and device and wearable device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810556612.7A CN108831527B (en) 2018-05-31 2018-05-31 User motion state detection method and device and wearable device

Publications (2)

Publication Number Publication Date
CN108831527A true CN108831527A (en) 2018-11-16
CN108831527B CN108831527B (en) 2021-06-04

Family

ID=64146783

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810556612.7A Active CN108831527B (en) 2018-05-31 2018-05-31 User motion state detection method and device and wearable device

Country Status (1)

Country Link
CN (1) CN108831527B (en)

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109829439A (en) * 2019-02-02 2019-05-31 京东方科技集团股份有限公司 The calibration method and device of a kind of pair of head motion profile predicted value
CN110010224A (en) * 2019-03-01 2019-07-12 出门问问信息科技有限公司 User movement data processing method, device, wearable device and storage medium
CN110123335A (en) * 2019-05-21 2019-08-16 首都医科大学宣武医院 Information processing method, device and system
CN110180158A (en) * 2019-07-02 2019-08-30 乐跑体育互联网（武汉）有限公司 A kind of running state identification method, system and terminal device
CN110558991A (en) * 2019-07-30 2019-12-13 福建省万物智联科技有限公司 Gait analysis method
CN110960222A (en) * 2019-12-17 2020-04-07 心核心科技(北京)有限公司 Motion type detection method and device
CN111382641A (en) * 2018-12-29 2020-07-07 西安思博探声生物科技有限公司 Body state recognition method and motion guidance system of motion sensing game
CN112380946A (en) * 2020-11-09 2021-02-19 上海泗科智能科技有限公司 Fall detection method and device based on end-side AI chip
CN112634489A (en) * 2020-12-09 2021-04-09 众安在线财产保险股份有限公司 Vehicle state determination method, device and system based on mobile terminal
CN112699744A (en) * 2020-12-16 2021-04-23 南开大学 Fall posture classification identification method and device and wearable device
CN112764545A (en) * 2021-01-29 2021-05-07 重庆子元科技有限公司 Virtual character motion synchronization method and terminal equipment
CN112967427A (en) * 2021-02-08 2021-06-15 遥相科技发展(北京)有限公司 Method and system for unlocking by using wearable device
CN113143251A (en) * 2021-01-28 2021-07-23 胤迈医药科技(上海)有限公司 Household wearable device based on stride monitoring
TWI782885B (en) * 2022-04-25 2022-11-01 國立臺灣海洋大學 Posture and food intake correlation detection system for rheumatoid arthritis
US20230133858A1 (en) * 2021-11-01 2023-05-04 Unitedhealth Group Incorporated Movement prediction machine learning models
CN116746910A (en) * 2023-06-15 2023-09-15 广州医科大学附属脑科医院 Gait monitoring method and device based on wearable equipment and wearable equipment

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103218906A (en) * 2013-04-23 2013-07-24 中国科学院深圳先进技术研究院 Falling data acquiring and analyzing platform
US20130346014A1 (en) * 2009-02-23 2013-12-26 Imetrikus, Inc. Dba Numera Identifying a Type of Motion of an Object
CN105530865A (en) * 2013-09-11 2016-04-27 皇家飞利浦有限公司 Fall detection system and method
CN106909800A (en) * 2017-04-12 2017-06-30 佛山市量脑科技有限公司 A kind of Intelligent insole data handling system
CN106901444A (en) * 2017-04-12 2017-06-30 佛山市丈量科技有限公司 A kind of physiology monitor Intelligent insole
CN106971059A (en) * 2017-03-01 2017-07-21 福州云开智能科技有限公司 A kind of wearable device based on the adaptive health monitoring of neutral net
CN107753026A (en) * 2017-09-28 2018-03-06 古琳达姬（厦门）股份有限公司 For the intelligent shoe self-adaptive monitoring method of backbone leg health

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130346014A1 (en) * 2009-02-23 2013-12-26 Imetrikus, Inc. Dba Numera Identifying a Type of Motion of an Object
CN103218906A (en) * 2013-04-23 2013-07-24 中国科学院深圳先进技术研究院 Falling data acquiring and analyzing platform
CN105530865A (en) * 2013-09-11 2016-04-27 皇家飞利浦有限公司 Fall detection system and method
CN106971059A (en) * 2017-03-01 2017-07-21 福州云开智能科技有限公司 A kind of wearable device based on the adaptive health monitoring of neutral net
CN106909800A (en) * 2017-04-12 2017-06-30 佛山市量脑科技有限公司 A kind of Intelligent insole data handling system
CN106901444A (en) * 2017-04-12 2017-06-30 佛山市丈量科技有限公司 A kind of physiology monitor Intelligent insole
CN107753026A (en) * 2017-09-28 2018-03-06 古琳达姬（厦门）股份有限公司 For the intelligent shoe self-adaptive monitoring method of backbone leg health

Cited By (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111382641A (en) * 2018-12-29 2020-07-07 西安思博探声生物科技有限公司 Body state recognition method and motion guidance system of motion sensing game
CN109829439A (en) * 2019-02-02 2019-05-31 京东方科技集团股份有限公司 The calibration method and device of a kind of pair of head motion profile predicted value
CN110010224A (en) * 2019-03-01 2019-07-12 出门问问信息科技有限公司 User movement data processing method, device, wearable device and storage medium
CN110123335A (en) * 2019-05-21 2019-08-16 首都医科大学宣武医院 Information processing method, device and system
CN110180158A (en) * 2019-07-02 2019-08-30 乐跑体育互联网（武汉）有限公司 A kind of running state identification method, system and terminal device
CN110558991B (en) * 2019-07-30 2022-05-20 福建省万物智联科技有限公司 Gait analysis method
CN110558991A (en) * 2019-07-30 2019-12-13 福建省万物智联科技有限公司 Gait analysis method
CN110960222A (en) * 2019-12-17 2020-04-07 心核心科技(北京)有限公司 Motion type detection method and device
CN112380946B (en) * 2020-11-09 2022-12-16 苏州爱可尔智能科技有限公司 Fall detection method and device based on end-side AI chip
CN112380946A (en) * 2020-11-09 2021-02-19 上海泗科智能科技有限公司 Fall detection method and device based on end-side AI chip
CN112634489A (en) * 2020-12-09 2021-04-09 众安在线财产保险股份有限公司 Vehicle state determination method, device and system based on mobile terminal
CN112699744A (en) * 2020-12-16 2021-04-23 南开大学 Fall posture classification identification method and device and wearable device
CN113143251A (en) * 2021-01-28 2021-07-23 胤迈医药科技(上海)有限公司 Household wearable device based on stride monitoring
CN112764545A (en) * 2021-01-29 2021-05-07 重庆子元科技有限公司 Virtual character motion synchronization method and terminal equipment
CN112764545B (en) * 2021-01-29 2023-01-24 重庆子元科技有限公司 Virtual character motion synchronization method and terminal equipment
CN112967427A (en) * 2021-02-08 2021-06-15 遥相科技发展(北京)有限公司 Method and system for unlocking by using wearable device
CN112967427B (en) * 2021-02-08 2022-12-27 深圳市机器时代科技有限公司 Method and system for unlocking by using wearable device
US20230133858A1 (en) * 2021-11-01 2023-05-04 Unitedhealth Group Incorporated Movement prediction machine learning models
TWI782885B (en) * 2022-04-25 2022-11-01 國立臺灣海洋大學 Posture and food intake correlation detection system for rheumatoid arthritis
CN116746910A (en) * 2023-06-15 2023-09-15 广州医科大学附属脑科医院 Gait monitoring method and device based on wearable equipment and wearable equipment
CN116746910B (en) * 2023-06-15 2024-05-28 广州医科大学附属脑科医院 Gait monitoring method and device based on wearable equipment and wearable equipment

Also Published As

Publication number Publication date
CN108831527B (en) 2021-06-04

Similar Documents

Publication Publication Date Title
CN108831527A (en) A kind of user movement condition detection method, device and wearable device
CN108244744A (en) A kind of method of moving state identification, sole and footwear
Quaid et al. Wearable sensors based human behavioral pattern recognition using statistical features and reweighted genetic algorithm
Cuzzolin et al. Metric learning for Parkinsonian identification from IMU gait measurements
Xia et al. A dual-modal attention-enhanced deep learning network for quantification of Parkinson’s disease characteristics
Yoneyama et al. Accelerometry-based gait analysis and its application to Parkinson's disease assessment—part 1: detection of stride event
CN106887115A (en) Old people falling monitoring device and falling risk assessment method
CN105023022A (en) Tumble detection method and system
CN108514421A (en) The method for promoting mixed reality and routine health monitoring
KR20190105867A (en) System and Method for Analyzing Foot Pressure Change and Gait Pattern
Guo et al. Human activity recognition by fusing multiple sensor nodes in the wearable sensor systems
Mahoney et al. Methodology and validation for identifying gait type using machine learning on IMU data
Malshika Welhenge et al. Human activity classification using long short-term memory network
Wang et al. Recognizing parkinsonian gait pattern by exploiting fine-grained movement function features
CN109805935A (en) A kind of intelligent waistband based on artificial intelligence hierarchical layered motion recognition method
Chakraborty et al. Pathological gait detection based on multiple regression models using unobtrusive sensing technology
Pippa et al. Feature Selection Evaluation for Light Human Motion Identification in Frailty Monitoring System.
Santoyo-Ramón et al. A study on the impact of the users’ characteristics on the performance of wearable fall detection systems
Luqian et al. Human activity recognition using time series pattern recognition model-based on tsfresh features
Zheng et al. SVM-based gait analysis and classification for patients with Parkinson’s disease
KR20210022375A (en) Apparatus and method for identifying individuals by performing discriminant analysis for various detection information
Patel et al. Machine learning prediction of tbi from mobility, gait and balance patterns
Liu et al. Preimpact fall detection for elderly based on fractional domain
Sowmiya et al. A hybrid approach using bidirectional neural networks for human activity recognition
CN106446778A (en) Method for identifying human motions based on accelerometer

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant