CN109166624A - A kind of behavior analysis method, device, server, system and storage medium - Google Patents
A kind of behavior analysis method, device, server, system and storage medium Download PDFInfo
- Publication number
- CN109166624A CN109166624A CN201811117507.XA CN201811117507A CN109166624A CN 109166624 A CN109166624 A CN 109166624A CN 201811117507 A CN201811117507 A CN 201811117507A CN 109166624 A CN109166624 A CN 109166624A
- Authority
- CN
- China
- Prior art keywords
- data
- behavior
- period
- activity recognition
- behavioural
- 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.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 123
- 238000003860 storage Methods 0.000 title claims abstract description 23
- 230000003542 behavioural effect Effects 0.000 claims abstract description 151
- 230000000694 effects Effects 0.000 claims abstract description 74
- 241001269238 Data Species 0.000 claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 15
- 206010000117 Abnormal behaviour Diseases 0.000 claims abstract description 11
- 230000008569 process Effects 0.000 claims abstract description 8
- 230000006399 behavior Effects 0.000 claims description 167
- 230000001133 acceleration Effects 0.000 claims description 60
- 230000007613 environmental effect Effects 0.000 claims description 26
- 238000004590 computer program Methods 0.000 claims description 18
- 230000005540 biological transmission Effects 0.000 claims description 17
- 238000004422 calculation algorithm Methods 0.000 claims description 16
- 230000003068 static effect Effects 0.000 claims description 8
- 238000012706 support-vector machine Methods 0.000 claims description 6
- 235000013399 edible fruits Nutrition 0.000 claims description 2
- 230000006870 function Effects 0.000 description 11
- 238000005457 optimization Methods 0.000 description 10
- 238000012545 processing Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 230000003340 mental effect Effects 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 108010074864 Factor XI Proteins 0.000 description 1
- 208000028017 Psychotic disease Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000002490 cerebral effect Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000000474 nursing effect Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
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
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a kind of behavior analysis method, device, server, system and computer readable storage medium, method includes: the behavioral data and corresponding time of the act parameter that real-time reception intelligent wearable device is transmitted；Every preset time period obtains all behavioral datas in the period according to the time of the act parameter, and pre-processes to all behavioral datas, to generate behavioural characteristic data；The period corresponding behavior type is obtained by the Activity recognition model pre-established according to the behavioural characteristic data；According to the behavior type and the corresponding period, by the Behavior law table pre-established, the Activity recognition analysis result for corresponding to the period is generated；Wherein, the Behavior law table is stored with corresponding behavior type of each period；The Activity recognition analysis result includes normal behaviour result and abnormal behaviour result.The present invention, which realizes, nurses the intelligence of patient with phychlogical problems.
Description
Technical field
The present invention relates to field of computer technology more particularly to a kind of behavior analysis method, device, server, system with
And computer readable storage medium.
Background technique
Phrenoblabia refers to that cerebral function activity gets muddled, and leads to the cerebrations such as cognition, emotion, behavior and will
The general name of different degrees of obstacle.Currently, China has 17.5% people to have phrenoblabia, severe mental disturbances patient morbidity is
1%, more than 70 ancestor's severe mental disturbances patient's troublemaking cases just occur for 2017 Guangdong Province Nian Dan, cause tens of people dead, seriously
It is stable to influence Local Society.
In the implementation of the present invention, inventor has found: prevention and treatment of the current social for severe mental disturbances patient
Journey, usually by the long hospitalisation of mental hospital, still, due to high medical expenses, part family can not undertake it
The high expense that long hospitalisation generates, patient with phychlogical problems can only nurse at home, can frequently result in due to nursing not
When the generation for leading to sufferer troublemaking cases, therefore, urgent need establishes severe mental disturbances patient's socialized service system supervisor
System.
Summary of the invention
In view of the above-mentioned problems, the purpose of the present invention is to provide a kind of behavior analysis method, device, server, system with
And computer readable storage medium, the behavior of real-time monitoring patient with phychlogical problems, it realizes and the intelligence of patient with phychlogical problems is nursed.
In a first aspect, first embodiment of the invention provides a kind of behavior analysis method, comprising the following steps:
The behavioral data of real-time reception intelligent wearable device transmission and corresponding time of the act parameter；
Every preset time period obtains all behavioral datas in the period according to the time of the act parameter, and right
All behavioral datas are pre-processed, to generate behavioural characteristic data；
The period, it is corresponding to be obtained by the Activity recognition model pre-established according to the behavioural characteristic data
Behavior type；
According to the behavior type and the corresponding period, pass through the Behavior law table pre-established, generation pair
The Activity recognition of period described in Ying Yu analyzes result；Wherein, the Behavior law table is stored with corresponding row of each period
For type；The Activity recognition analysis result includes normal behaviour result and abnormal behaviour result.
In the first implementation of first aspect, the behavioral data of real-time reception intelligent wearable device transmission with
And corresponding time of the act parameter, specifically:
Resultant acceleration data, the position data, environmental data, sign data of the transmission of intelligent wearable device described in real-time reception
And corresponding time of the act parameter；Wherein, the resultant acceleration data intelligent wearable device according to acquiring in real time
Three-dimensional acceleration data calculates acquisition；If resultant acceleration is a, if three-dimensional acceleration is respectively ax、ay、az, then
It is described every pre- in second of implementation of first aspect according to the first implementation of first aspect
If the period, all behavioral datas in the period are obtained according to the time of the act parameter, and to all behavior numbers
According to being pre-processed, to generate behavioural characteristic data, specifically:
Every preset time period, obtained according to the time of the act parameter all resultant acceleration data in the period,
Position data, environmental data and sign data；
The resultant acceleration characteristic in the period is calculated according to all resultant acceleration data；Wherein, the row
Data are characterized including at least any one in the mean value of all resultant acceleration data, standard deviation, maximum value, minimum value
Or it is multiple；
According to the resultant acceleration characteristic, position data, environmental data and sign data, behavioural characteristic number is generated
According to.
It is described according to institute in the third implementation of first aspect according to second of implementation of first aspect
Behavioural characteristic data are stated, by the Activity recognition model pre-established, obtain the period corresponding behavior type, specifically
Are as follows:
Using the behavioural characteristic data as the input value of the Activity recognition model, with from the Activity recognition model from
Obtain the period corresponding behavior type；Wherein, the behavior type includes static, walking and running.
According to the third implementation of first aspect, in the 4th kind of implementation of first aspect, the behavior is known
The establishment process of other model the following steps are included:
Obtain the sample data for corresponding to the intelligent wearable device；Wherein, when the sample data includes each default
Between resultant acceleration data, position data, environmental data, sign data and the period corresponding behavior type in section；Institute
Stating behavior type includes static, walking and running；
The resultant acceleration data, position data, environmental data and sign data are pre-processed, to generate sample
Characteristic；
The sample characteristics data are clustered according to the behavior type, it is right to obtain each behavior type institute
The sample characteristics data answered；
According to the behavior type and corresponding sample characteristics data, it is trained by algorithm of support vector machine, with
Generate the Activity recognition model.
In the 5th kind of implementation of first aspect, further includes:
By the Activity recognition analysis result be sent to the associated associated terminal of the intelligent wearable device so that described
Associated terminal shows the Activity recognition analysis result.
Second aspect, the embodiment of the invention provides a kind of behavioural analysis devices, comprising the following steps:
Behavioral data acquiring unit, behavioral data and corresponding behavior for the transmission of real-time reception intelligent wearable device
Time parameter；
Pretreatment unit is used for every preset time period, the institute in the period is obtained according to the time of the act parameter
There is behavioral data, and all behavioral datas are pre-processed, to generate behavioural characteristic data；
Behavior type acquiring unit, for according to the behavioural characteristic data, by the Activity recognition model pre-established,
Obtain the period corresponding behavior type；
Activity recognition analytical unit is used for according to the behavior type and the corresponding period, by building in advance
Vertical Behavior law table generates the Activity recognition analysis result for corresponding to the period；Wherein, the Behavior law table storage
There is corresponding behavior type of each period；The Activity recognition analysis result includes normal behaviour result and abnormal behaviour knot
Fruit.
The third aspect the embodiment of the invention provides a kind of behavioural analysis server, including processor, memory and is deposited
The computer program executed by the processor is stored up in the memory and is configured as, the processor executes the calculating
The behavior analysis method as described in any one of first aspect is realized when machine program.
Fourth aspect, the embodiment of the invention provides a kind of computer readable storage medium, the computer-readable storage
Medium includes the computer program of storage, wherein controls the computer-readable storage medium in computer program operation
Equipment executes the behavior analysis method as described in any one of second aspect where matter.
5th aspect, the embodiment of the invention provides a kind of behavior analysis systems, including the behavior as described in the third aspect
Analysis server, at least one intelligent wearable device and at least one and the associated associated terminal of the intelligent wearable device；
The behavioral data for acquiring behavioral data in real time, and is transferred to the behavior by the intelligent wearable device
Analysis server；
The behavioural analysis server, the behavioral data for the transmission of real-time reception intelligent wearable device；
The behavioural analysis server, is also used to every preset time period, obtains all behavioral datas in the period,
And all behavioral datas are pre-processed, to generate behavioural characteristic data；
The behavioural analysis server is also used to pass through the Activity recognition pre-established according to the behavioural characteristic data
Model obtains the behavior type in the period；
The behavioural analysis server is also used to according to the behavior type and the corresponding period, by pre-
The Behavior law table first established generates the Activity recognition analysis result for corresponding to the period；Wherein, the Behavior law table
It is stored with corresponding behavior type of each period；The Activity recognition analysis result includes normal behaviour result and abnormal row
For result；
The behavioural analysis server, be also used to by the Activity recognition analysis result be sent to it is described intelligence wearing set
Standby associated associated terminal；
The associate device, for receiving and showing the Activity recognition analysis result.
Above embodiments have the following beneficial effects:
The behavioral data transmitted by real-time reception intelligent wearable device and corresponding time of the act parameter, and every
Preset time period obtains all behavioral datas in the period according to the time of the act parameter, and to all behaviors
Data are pre-processed, and to generate behavioural characteristic data, further according to the behavioural characteristic data, are known by the behavior pre-established
Other model obtains the period corresponding behavior type, finally according to the behavior type and the corresponding period,
By the Behavior law table pre-established, the Activity recognition analysis for corresponding to the period is generated as a result, passing through Activity recognition
Model identifies the behavioral data of patient to determine that user carries out in the behavior of the period, and in conjunction with patient behavior rule
Identify the abnormal conditions of patient behavior, the behavior of real-time monitoring patient with phychlogical problems is known by the safety to patient with phychlogical problems
The intelligence of patient with phychlogical problems Shi Xian not nursed, avoid due to manually nurse it is inconsiderate to patient with phychlogical problems and other people
It damages, while also reducing the energy and cost of nurse.
Detailed description of the invention
In order to illustrate more clearly of technical solution of the present invention, attached drawing needed in embodiment will be made below
Simply introduce, it should be apparent that, the accompanying drawings in the following description is only some embodiments of the present invention, general for this field
For logical technical staff, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is the flow diagram for the behavior analysis method that first embodiment of the invention provides.
Fig. 2 is the structural schematic diagram for the behavioural analysis device that second embodiment of the invention provides.
Fig. 3 is the structural schematic diagram for the behavioural analysis server that third embodiment of the invention provides.
Fig. 4 is the structural schematic diagram for the behavior analysis system that fifth embodiment of the invention provides.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Referring to Fig. 1, first embodiment of the invention provides a kind of behavior analysis method, it can be by behavioural analysis server
It executes, and the following steps are included:
S11, the behavioral data of real-time reception intelligent wearable device transmission and corresponding time of the act parameter.
In embodiments of the present invention, the behavior analysis method is integrated on the behavioural analysis server, by the row
It is executed for Analysis server.
In embodiments of the present invention, the intelligent wearable device is configured to target patient and is started, to pass through
State the behavioral data that intelligent wearable device acquires the target patient in real time, and by the behavioral data of the target data and right
The time of the act parameter answered is sent to the behavioural analysis server, so that the behavioural analysis server real-time reception is intelligent
The behavioral data of wearable device transmission and corresponding time of the act parameter, it should be noted that the present invention is for the intelligence
The concrete form of wearable device does not do any restriction, can be specifically arranged according to actual conditions, for example, the intelligence wearing is set
Standby can be Intelligent bracelet etc..
It in embodiments of the present invention, specifically, at least include acceleration transducer, GPS in the intelligent wearable device
Module, Temperature Humidity Sensor, heart rate sensor etc., to pass through institute after being worn to the target patient and starting
The processing module (such as MCU module) that stating has in intelligent wearable device obtains the three-dimensional acceleration data, position data, temperature
The sign datas such as the environmental datas such as humidity, heart rate, in order to avoid the influence in direction, the processing module root of the intelligent wearable device
Resultant acceleration data, the then wireless transmission by having in the intelligent wearable device are calculated according to the three-dimensional acceleration data
Module in real time by the sign datas such as environmental datas, the hearts rate such as the resultant acceleration data, position data, temperature and humidity and acquisition with
The corresponding time of the act parameter of upper data is sent to the behavioural analysis server, it should be noted that the intelligence wearing is set
Standby upper acceleration transducer, GPS module, Temperature Humidity Sensor, heart rate sensor and wireless transport module, respectively with it is described
Processing module connection, the resultant acceleration number that then intelligent wearable device described in the behavioural analysis server real-time reception is transmitted
According to, position data, environmental data, sign data and corresponding time of the act parameter；Wherein, the resultant acceleration data are institute
It states intelligent wearable device and acquisition is calculated according to the three-dimensional acceleration data acquired in real time；If resultant acceleration is a, if three-dimensional accelerate
Degree is respectively ax、ay、az, then
S12, every preset time period obtain all behavioral datas in the period according to the time of the act parameter,
And all behavioral datas are pre-processed, to generate behavioural characteristic data.
In embodiments of the present invention, specifically, the behavioural analysis server every preset time period, according to the behavior
Time parameter obtains all resultant acceleration data, position data, environmental data and sign data in the period, needs
Bright, the preset time period is corresponding with the time of the act parameter of the intelligent wearable device, and the intelligence wearing is set
The standby behavioral data according to acquisition, may within the unit time, as acquire in 1 second and send in real time N behavioral data (N >=
1), because intelligent wearable device acquisition speed is extremely fast, and person's development speed and behavior speed is not in real life
Have and take action in seconds, thus according to a behavioral data determine user behavior be it is inappositely, in the application, then
The behavioural analysis server every preset time period obtains all conjunctions in the period according to the time of the act parameter and adds
Speed data, position data, environmental data and sign data, such as all behavior numbers obtained in 1 minute every 1 minute
According to being obtained described in 11 points 11 minutes~11: 12/according to all time of the act parameters on 11 points of 12 minutes time points
The collected behavioral data of intelligent wearable device, then the behavioural analysis server is according to all resultant acceleration data meters
The resultant acceleration characteristic in the period is calculated, the behavioural characteristic data include at least all resultant acceleration data
It is mean value, standard deviation, maximum value, any one or more in minimum value, finally according to the resultant acceleration characteristic, position
Data, environmental data and sign data generate behavioural characteristic data.
S13 obtains the period pair by the Activity recognition model pre-established according to the behavioural characteristic data
The behavior type answered.
In embodiments of the present invention, specifically, the behavioural analysis server is using the behavioural characteristic data as described in
The input value of Activity recognition model, it is described with from the Activity recognition model from obtaining period corresponding behavior type
Behavior type includes static, walking and runs, what the Activity recognition model was established based on algorithm of support vector machine.
S14 is raw by the Behavior law table pre-established according to the behavior type and the corresponding period
Result is analyzed at the Activity recognition for corresponding to the period；Wherein, it is corresponding to be stored with each period for the Behavior law table
Behavior type；The Activity recognition analysis result includes normal behaviour result and abnormal behaviour result.
In embodiments of the present invention, the behavioural analysis server is according to the behavior type and the corresponding time
Section, is compared processing by the Behavior law table pre-established, to judge whether the behavior type meets in the period
Behavior law, behavior type and corresponding time of the act parameter of the Behavior law table according to the target patient of record
Further analysis obtains, and the Behavior law table is stored with corresponding behavior type of each period, if the behavior judges
Server judges not meeting Behavior law in the behavior type of the period, then confirms that the target patient is deposited in the period
In abnormal behaviour, abnormal behaviour is generated as a result, if judging to meet Behavior law in the behavior type of the period, then it is assumed that institute
It is normal in the period behavior to state target patient, generates normal behaviour result.
In conclusion first embodiment of the invention provides a kind of behavior analysis method, intelligently dressed by real-time reception
The behavioral data of equipment transmission and corresponding time of the act parameter, and in every preset time period, according to the time of the act
Parameter obtains all behavioral datas in the period, and pre-processes to all behavioral datas, to generate behavior spy
Data are levied, the period, it is corresponding to be obtained by the Activity recognition model pre-established further according to the behavioural characteristic data
Behavior type, it is raw by the Behavior law table pre-established finally according to the behavior type and the corresponding period
It analyzes at the Activity recognition for corresponding to the period as a result, being identified by behavioral data of the Activity recognition model to patient
To determine that user in the behavior of the period, and carries out in conjunction with patient behavior rule the abnormal conditions of identification patient behavior, in real time
The behavior of monitoring psychotic disorders patient is realized by the safety identification to patient with phychlogical problems and is seen to the intelligence of patient with phychlogical problems
Shield, avoid due to manually nurse it is inconsiderate to patient with phychlogical problems and other people damage, while also reducing nurse
Energy and cost.
In order to facilitate the understanding of the present invention, some currently preferred embodiments of the present invention will be done and will further be retouched below
It states.
Preferably, on the basis of first embodiment of the invention, the establishment process of the Activity recognition model includes following
Step:
Obtain the sample data for corresponding to the intelligent wearable device；Wherein, when the sample data includes each default
Between resultant acceleration data, position data, environmental data, sign data and the period corresponding behavior type in section；Institute
Stating behavior type includes static, walking and running.
The resultant acceleration data, position data, environmental data and sign data are pre-processed, to generate sample
Characteristic.
The sample characteristics data are clustered according to the behavior type, it is right to obtain each behavior type institute
The sample characteristics data answered.
According to the behavior type and corresponding sample characteristics data, it is trained by algorithm of support vector machine, with
Generate the Activity recognition model.
In embodiments of the present invention, the behavioural analysis server carries out dressing first the patient of the intelligent wearable device
Sample data acquisition, the sample data includes resultant acceleration data, position data, environment number in each preset time period
Primary data analysis processing is carried out according to, sign data and the period corresponding behavior type, and to the sample data,
Such as vacancy value is carried out to fill up mean value, unusual Value Data is removed, has which feature that there is cluster in judgement sample data
Negative consequence, and these characteristics are separately saved, it is not input in clustering algorithm, the behavioural analysis server is to described
Resultant acceleration data, position data, environmental data and sign data are pre-processed, to generate sample characteristics data acquisition sample
Notebook data, wherein resultant acceleration characteristic is calculated according to the resultant acceleration data, including the equal of the resultant acceleration data
Value, standard deviation, maximum value, minimum value, then according to the resultant acceleration characteristic, position data, environmental data and body
Data are levied, generate behavioural characteristic data, such as be defined as { xi,yi, wherein i=1,2 ..., l, x ∈ Rn, y={+1, -1 }, l are
Sample number, n are sample characteristics number, and x corresponds to the resultant acceleration data, position data, ring in each preset time period
Border data, sign data, y correspond to the period corresponding behavior type, and the behavioural analysis server is according to the behavior
Type clusters the sample characteristics data, to obtain sample characteristics data corresponding to each behavior type, leads to
Clustering algorithm optimization is crossed, keeps the separability between two subclasses as strong as possible, generates optimal Binary decision tree construction, final foundation
The structure trains sub-classifier, comprising: S01: using whole training sample sets as initial root node, calling and clusters in root node
Original training sample merging is divided into two classes, forms two child nodes by algorithm optimization；S02: judge whether the child node is only
There are a classes, if into S04, if not then entering S03；S03: continuing the child node to call clustering algorithm optimization, will
It is further subdivided into two child nodes, into S02.；S04: the node is leaf node, and algorithm terminates；Wherein, the clustering algorithm
Optimization specifically includes: S001: the learning rate of random initializtion cluster centre and position (cluster centre)；S002: according to closest
Rule divides data, according to the calculation formula of fitness, calculates the fitness value of each cluster centre, more new samples letter
The individual extreme value of breath；S003: cluster centre sets 20% possibility and randomly selects position, and finds global extremum and global extremum
Position；S004: if the member for reaching cluster no longer changes, 2 i.e. optimal cluster centres of the position of Optimal cluster centers are exported；
If not up to termination condition returns to S002；Cluster optimization algorithm needs to preset the number of cluster, and the number of the cluster is i.e. poly-
The type number of class, cluster is behavior type in this application, and the number of cluster corresponds to the type number of behavior type, a sample
Represent the cluster centre of each cluster, sample XiIt indicates are as follows: Xi={ Ci1,Ci1,…,Cij, in formula: CijIt indicates representated by i-th of sample
J-th of classification classification center, then each cluster centre represents the classification of a kind of pair of data set, and entire cluster point represents pair
A variety of splitting schemes of data set；The fitness function of cluster centre in algorithm are as follows:
In formula: jeFor the sum of within-cluster variance, NCFor the number of cluster, information P is acquiredmBelong to cluster centre CijThe classification of representative.Then it fits
The sum of the higher within-cluster variance of central point of response is smaller, i.e., the similitude in class is higher, and the cluster centre is an instruction
Practice some sample of collection, which is set as a sample point at random at the beginning, the sample be (location information, sign information,
Environmental information, action message, goal behavior) form a vector, in next step carry out algorithm in iteration, carry out cluster centre
It updates, the position sample points for keeping cluster most intensive are updated to cluster centre point；The last behavioural analysis server is according to
Behavior type and corresponding sample characteristics data, the sample characteristics data are as output valve, and the behavior type is as pre-
The output valve of survey, is trained by algorithm of support vector machine, to generate the Activity recognition model, when linear separability, and branch
Holding vector machine algorithm classification optimal planar can indicate are as follows: wx+b=0.At this point, the class interval of two kinds of information categories is 2/ | | w
| |, then when | | w | | when being minimum value, the class interval of two kinds of information is maximum, then has following constrained optimization problem:When linearly inseparable, fuzzy factor ξ is introducedi, i=1,2 ..., l are above-mentioned
Constrained optimization problem then indicates are as follows:C is constraint factor, C in formula
More big then easier inhibition mistake classification.After finding out the optimization problem by method of Lagrange multipliers, it can be deduced that optimum cluster
Function:Wherein a is Lagrange coefficient；The behavioural analysis server will training sample
When notebook data is trained test, pass through the affiliated behavior type of characteristic x in optimum cluster function training of judgement sample.Again
According to Kuhn-Tucker condition, the solution of optimization problem then needs to meet: ai(yi(wx+b) -1)=0；When the sample number of acquisition
When according to for Nonlinear Classification problem, support vector machines is according to kernel function K (xi·xj) sample data x be mapped to some higher-dimension sky
Between H, further by original optimization problem linear partition in higher dimensional space.Then, Optimal Clustering can indicate are as follows:
Preferably, on the basis of first embodiment of the invention, the behavior analysis method further include:
By the Activity recognition analysis result be sent to the associated associated terminal of the intelligent wearable device so that described
Associated terminal shows the Activity recognition analysis result.
In embodiments of the present invention, the behavioural analysis server is after getting Activity recognition analysis result,
By the Activity recognition analysis result be sent to the associated associated terminal of the intelligent wearable device so that the associated terminal
Receive and show Activity recognition analysis as a result, if the behavioural analysis result be abnormal behaviour as a result, if the behavior point
Analysis server generate warning reminding and by the alarm deduct a percentage be sent to the associated associated terminal of the intelligent wearable device, with
Just it reminds in time, guarantees the safety of patient.
Referring to Fig. 2, second embodiment of the invention provides a kind of behavioural analysis device, comprising the following steps:
Behavioral data acquiring unit 11, behavioral data and corresponding row for the transmission of real-time reception intelligent wearable device
For time parameter.
Pretreatment unit 12 is used for every preset time period, is obtained in the period according to the time of the act parameter
All behavioral datas, and all behavioral datas are pre-processed, to generate behavioural characteristic data.
Behavior type acquiring unit 13, for passing through the Activity recognition mould pre-established according to the behavioural characteristic data
Type obtains the period corresponding behavior type.
Activity recognition analytical unit 14 is used for according to the behavior type and the corresponding period, by preparatory
The Behavior law table of foundation generates the Activity recognition analysis result for corresponding to the period；Wherein, the Behavior law table is deposited
Contain corresponding behavior type of each period；The Activity recognition analysis result includes normal behaviour result and abnormal behaviour
As a result.
In the first implementation of second embodiment, the behavioral data acquiring unit 11 is specifically included:
Resultant acceleration data, the position data, environmental data, sign data of the transmission of intelligent wearable device described in real-time reception
And corresponding time of the act parameter；Wherein, the resultant acceleration data intelligent wearable device according to acquiring in real time
Three-dimensional acceleration data calculates acquisition；If resultant acceleration is a, if three-dimensional acceleration is respectively ax、ay、az, then
The first implementation according to the second embodiment, it is described pre- in second of implementation of second embodiment
Processing unit 12 specifically includes:
Behavioral data obtains module, is used for every preset time period, obtains the period according to the time of the act parameter
Interior all resultant acceleration data, position data, environmental data and sign data.
Characteristic computing module, for calculating the resultant acceleration in the period according to all resultant acceleration data
Characteristic；Wherein, the behavioural characteristic data include at least mean value, standard deviation, the maximum of all resultant acceleration data
It is any one or more in value, minimum value.
Behavioural characteristic data generation module, for according to the resultant acceleration characteristic, position data, environmental data with
And sign data, generate behavioural characteristic data.
Second of implementation according to the second embodiment, in the third implementation of second embodiment, the row
It is specifically included for type acquiring unit 13:
Using the behavioural characteristic data as the input value of the Activity recognition model, with from the Activity recognition model from
Obtain the period corresponding behavior type；Wherein, the behavior type includes static, walking and running.
The third implementation according to the second embodiment, in the 4th kind of implementation of second embodiment, the row
For identification model establishment process the following steps are included:
Sample data acquiring unit, for obtaining the sample data for corresponding to the intelligent wearable device；Wherein, the sample
Notebook data include resultant acceleration data in each preset time period, position data, environmental data, sign data and this when
Between the corresponding behavior type of section；The behavior type includes static, walking and running.
Sample pre-treatment unit, for the resultant acceleration data, position data, environmental data and sign data into
Row pretreatment, to generate sample characteristics data.
Sample clustering unit, it is every to obtain for being clustered according to the behavior type to the sample characteristics data
Sample characteristics data corresponding to one behavior type.
Model training unit, for passing through supporting vector according to the behavior type and corresponding sample characteristics data
Machine algorithm is trained, to generate the Activity recognition model.
In the 5th kind of implementation of second embodiment, further includes:
As a result transmission unit, it is associated with the intelligent wearable device for being sent to Activity recognition analysis result
Associated terminal, so that the associated terminal shows the Activity recognition analysis result.
It should be noted that the apparatus embodiments described above are merely exemplary, wherein described be used as separation unit
The unit of explanation may or may not be physically separated, and component shown as a unit can be or can also be with
It is not physical unit, it can it is in one place, or may be distributed over multiple network units.It can be according to actual
It needs that some or all of the modules therein is selected to achieve the purpose of the solution of this embodiment.In addition, device provided by the invention
In embodiment attached drawing, the connection relationship between module indicate between them have communication connection, specifically can be implemented as one or
A plurality of communication bus or signal wire.Those of ordinary skill in the art are without creative efforts, it can understand
And implement.
It is the schematic diagram for the behavioural analysis server that third embodiment of the invention provides referring to Fig. 3.As shown in figure 3, the row
It include: at least one processor 11, such as CPU for Analysis server, at least one network interface 14 or other users interface
13, memory 15, at least one communication bus 12, communication bus 12 is for realizing the connection communication between these components.Wherein,
User interface 13 optionally may include USB interface and other standards interface, wireline interface.Network interface 14 optionally can be with
Including Wi-Fi interface and other wireless interfaces.Memory 15 may include high speed RAM memory, it is also possible to further include it is non-not
Stable memory (non-volatilememory), for example, at least a magnetic disk storage.Memory 15 optionally can wrap
The storage device of aforementioned processor 11 is located remotely from containing at least one.
In some embodiments, memory 15 stores following element, executable modules or data structures, or
Their subset or their superset:
Operating system 151 includes various system programs, for realizing various basic businesses and hardware based of processing
Business；
Program 152.
Specifically, processor 11 executes row described in above-described embodiment for calling the program 152 stored in memory 15
For Analysis server, such as step S11 shown in FIG. 1.Alternatively, being realized when the processor execution computer program above-mentioned
The function of each module/unit in each Installation practice, such as behavioral data acquiring unit.
Illustratively, the computer program can be divided into one or more module/units, one or more
A module/unit is stored in the memory, and is executed by the processor, to complete the present invention.It is one or more
A module/unit can be the series of computation machine program instruction section that can complete specific function, and the instruction segment is for describing institute
State implementation procedure of the computer program in the behavioural analysis server.
The behavioural analysis server may include, but be not limited only to, processor, memory.Those skilled in the art can be with
Understand, the schematic diagram is only the example of behavioural analysis server, does not constitute the restriction to behavioural analysis server, can be with
Including than illustrating more or fewer components, perhaps combining certain components or different components, such as behavioural analysis clothes
Being engaged in device can also be including input-output equipment, network access equipment, bus etc..
Alleged processor 11 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng the processor 11 is the control centre of the behavioural analysis server, utilizes various interfaces and the entire behavior of connection
The various pieces of Analysis server.
The memory 15 can be used for storing the computer program and/or module, the processor 11 by operation or
Computer program and/or the module stored in the memory is executed, and calls the data being stored in memory, is realized
The various functions of the behavioural analysis server.The memory 15 can mainly include storing program area and storage data area,
In, storing program area can application program needed for storage program area, at least one function (such as sound-playing function, image
Playing function etc.) etc.；Storage data area, which can be stored, uses created data (such as audio data, phone directory according to mobile phone
Deng) etc..In addition, memory may include high-speed random access memory, it can also include nonvolatile memory, such as firmly
Disk, memory, plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital,
SD) block, flash card (Flash Card), at least one disk memory, flush memory device or other volatile solid-states
Part.
Fourth embodiment of the invention provides a kind of computer readable storage medium, the behavioural analysis server set at
If module/unit is realized in the form of SFU software functional unit and when sold or used as an independent product, can store
In one computer-readable storage medium.Based on this understanding, the present invention realize above-described embodiment method in whole or
Part process can also instruct relevant hardware to complete by computer program, and the computer program can be stored in
In one computer readable storage medium, the computer program is when being executed by processor, it can be achieved that above-mentioned each embodiment of the method
The step of.Wherein, the computer program includes computer program code, and the computer program code can be source code shape
Formula, object identification code form, executable file or certain intermediate forms etc..The computer-readable medium may include: that can take
Any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic disk, CD, computer with the computer program code are deposited
Reservoir, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access
Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It should be noted that the computer-readable medium
The content for including can carry out increase and decrease appropriate according to the requirement made laws in jurisdiction with patent practice, such as in certain departments
Method administrative area does not include electric carrier signal and telecommunication signal according to legislation and patent practice, computer-readable medium.
Referring to Fig. 4, fifth embodiment of the invention provides a kind of behavior analysis system, including as described in 3rd embodiment
Behavioural analysis server 21, at least one intelligent wearable device 22 and at least one is associated with the intelligent wearable device
Associated terminal 23.
The behavioral data for acquiring behavioral data in real time, and is transferred to the row by the intelligent wearable device 22
For Analysis server 21.
The behavioural analysis server 21, the behavioral data transmitted for real-time reception intelligent wearable device 22.
The behavioural analysis server 21, is also used to every preset time period, obtains all behavior numbers in the period
According to, and all behavioral datas are pre-processed, to generate behavioural characteristic data.
The behavioural analysis server 21 is also used to be known according to the behavioural characteristic data by the behavior pre-established
Other model, obtains the behavior type in the period.
The behavioural analysis server 21 is also used to be passed through according to the behavior type and the corresponding period
The Behavior law table pre-established generates the Activity recognition analysis result for corresponding to the period；Wherein, the Behavior law
Table is stored with corresponding behavior type of each period；The Activity recognition analysis result includes normal behaviour result and exception
Behavior outcome.
The behavioural analysis server 21 is also used to for Activity recognition analysis result being sent to and dress with the intelligence
The associated associated terminal 23 of equipment 22.
The associate device 23, for receiving and showing the Activity recognition analysis result.
Preferably, the behavioural analysis server 21 is also used to judge the Activity recognition analysis result for abnormal row
When for result, warning reminding is sent with the associated associated terminal 23 of the intelligent wearable device 22 to described.
The associate device 23, is also used to receive and show the warning reminding.
The above is a preferred embodiment of the present invention, it is noted that for those skilled in the art
For, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also considered as
Protection scope of the present invention.
Claims (10)
1. a kind of behavior analysis method, which comprises the following steps:
The behavioral data of real-time reception intelligent wearable device transmission and corresponding time of the act parameter；
Every preset time period obtains all behavioral datas in the period according to the time of the act parameter, and to described
All behavioral datas are pre-processed, to generate behavioural characteristic data；
The period corresponding behavior is obtained by the Activity recognition model pre-established according to the behavioural characteristic data
Type；
According to the behavior type and the corresponding period, by the Behavior law table pre-established, generation corresponds to
The Activity recognition of the period analyzes result；Wherein, the Behavior law table is stored with corresponding behavior class of each period
Type；The Activity recognition analysis result includes normal behaviour result and abnormal behaviour result.
2. behavior analysis method according to claim 1, which is characterized in that the real-time reception intelligent wearable device transmission
Behavioral data and corresponding time of the act parameter, specifically:
Intelligent wearable device described in real-time reception transmission resultant acceleration data, position data, environmental data, sign data and
Corresponding time of the act parameter；Wherein, the resultant acceleration data are the intelligent wearable device according to the three-dimensional acquired in real time
Acceleration information calculates acquisition；If resultant acceleration is a, if three-dimensional acceleration is respectively ax、ay、az, then
3. behavior analysis method according to claim 2, which is characterized in that the every preset time period, according to described
Time of the act parameter obtains all behavioral datas in the period, and pre-processes to all behavioral datas, with life
At behavioural characteristic data, specifically:
Every preset time period obtains all resultant acceleration data in the period, position according to the time of the act parameter
Data, environmental data and sign data；
The resultant acceleration characteristic in the period is calculated according to all resultant acceleration data；Wherein, the behavior is special
Levy data include at least the mean values of all resultant acceleration data, standard deviation, maximum value, in minimum value any one or it is more
It is a；
According to the resultant acceleration characteristic, position data, environmental data and sign data, behavioural characteristic data are generated.
4. behavior analysis method according to claim 3, which is characterized in that it is described according to the behavioural characteristic data, lead to
The Activity recognition model pre-established is crossed, the period corresponding behavior type is obtained, specifically:
Using the behavioural characteristic data as the input value of the Activity recognition model, from the Activity recognition model from acquisition
Period corresponding behavior type；Wherein, the behavior type includes static, walking and running.
5. behavior analysis method according to claim 4, which is characterized in that the establishment process packet of the Activity recognition model
Include following steps:
Obtain the sample data for corresponding to the intelligent wearable device；Wherein, the sample data includes each preset time period
Interior resultant acceleration data, position data, environmental data, sign data and the period corresponding behavior type；The row
It include static, walking and running for type；
The resultant acceleration data, position data, environmental data and sign data are pre-processed, to generate sample characteristics
Data；
The sample characteristics data are clustered according to the behavior type, to obtain corresponding to each behavior type
Sample characteristics data；
It according to the behavior type and corresponding sample characteristics data, is trained by algorithm of support vector machine, to generate
The Activity recognition model.
6. behavior analysis method according to claim 1, which is characterized in that further include:
By the Activity recognition analysis result be sent to the associated associated terminal of the intelligent wearable device so that the association
Terminal shows the Activity recognition analysis result.
7. a kind of behavioural analysis device, which comprises the following steps:
Behavioral data acquiring unit, behavioral data and corresponding time of the act for the transmission of real-time reception intelligent wearable device
Parameter；
Pretreatment unit is used for every preset time period, all rows in the period is obtained according to the time of the act parameter
For data, and all behavioral datas are pre-processed, to generate behavioural characteristic data；
Behavior type acquiring unit, for being obtained according to the behavioural characteristic data by the Activity recognition model pre-established
Period corresponding behavior type；
Activity recognition analytical unit, for passing through what is pre-established according to the behavior type and the corresponding period
Behavior law table generates the Activity recognition analysis result for corresponding to the period；Wherein, the Behavior law table is stored with often
One period corresponding behavior type；The Activity recognition analysis result includes normal behaviour result and abnormal behaviour result.
8. a kind of behavioural analysis server, including processor, memory and storage in the memory and be configured as by
The computer program that the processor executes, the processor are realized when executing the computer program as in claim 1 to 6
Behavior analysis method described in any one.
9. a kind of computer readable storage medium, which is characterized in that the computer readable storage medium includes the calculating of storage
Machine program, wherein equipment where controlling the computer readable storage medium in computer program operation is executed as weighed
Benefit require any one of 1 to 6 described in behavior analysis method.
10. a kind of behavior analysis system, which is characterized in that including behavioural analysis server as claimed in claim 8, at least one
A intelligent wearable device and at least one and the associated associated terminal of the intelligent wearable device；
The behavioral data for acquiring behavioral data in real time, and is transferred to the behavioural analysis by the intelligent wearable device
Server；
The behavioural analysis server, the behavioral data for the transmission of real-time reception intelligent wearable device；
The behavioural analysis server, is also used to every preset time period, obtains all behavioral datas in the period, and right
All behavioral datas are pre-processed, to generate behavioural characteristic data；
The behavioural analysis server, is also used to according to the behavioural characteristic data, by the Activity recognition model pre-established,
Obtain the behavior type in the period；
The behavioural analysis server is also used to according to the behavior type and the corresponding period, by building in advance
Vertical Behavior law table generates the Activity recognition analysis result for corresponding to the period；Wherein, the Behavior law table storage
There is corresponding behavior type of each period；The Activity recognition analysis result includes normal behaviour result and abnormal behaviour knot
Fruit；
The behavioural analysis server is also used to for Activity recognition analysis result being sent to and close with the intelligent wearable device
The associated terminal of connection；
The associate device, for receiving and showing the Activity recognition analysis result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811117507.XA CN109166624A (en) | 2018-09-21 | 2018-09-21 | A kind of behavior analysis method, device, server, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811117507.XA CN109166624A (en) | 2018-09-21 | 2018-09-21 | A kind of behavior analysis method, device, server, system and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109166624A true CN109166624A (en) | 2019-01-08 |
Family
ID=64880346
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811117507.XA Pending CN109166624A (en) | 2018-09-21 | 2018-09-21 | A kind of behavior analysis method, device, server, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109166624A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109961090A (en) * | 2019-02-28 | 2019-07-02 | 广州杰赛科技股份有限公司 | A kind of behavior classification method and system based on intelligent wearable device |
| CN110211693A (en) * | 2019-06-03 | 2019-09-06 | 深圳市儿童医院 | A kind of motor function recovery situation automated after gait analysis assessment HIBD treatment |
| CN112002419A (en) * | 2020-09-17 | 2020-11-27 | 吾征智能技术(北京)有限公司 | Disease auxiliary diagnosis system, equipment and storage medium based on clustering |
| CN113008231A (en) * | 2021-04-30 | 2021-06-22 | 东莞市小精灵教育软件有限公司 | Motion state identification method and system, wearable device and storage medium |
| CN115913980A (en) * | 2022-12-06 | 2023-04-04 | 沸蓝建设咨询有限公司 | A data multi-terminal access control system |
| CN116226527A (en) * | 2023-03-03 | 2023-06-06 | 中浙信科技咨询有限公司 | Digital community treatment method for realizing behavior prediction through resident big data |
| CN117151959A (en) * | 2023-10-16 | 2023-12-01 | 广东紫慧旭光科技有限公司 | Real-time video analysis method, system and storage medium for city management |
| CN118779710A (en) * | 2024-09-09 | 2024-10-15 | 杭州泽进科技有限公司 | A method and system for constructing multimodal heterogeneous vital sign data |
| CN119652557A (en) * | 2024-11-07 | 2025-03-18 | 海南大学 | Network situation awareness method and system based on user behavior analysis |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080139899A1 (en) * | 2005-05-04 | 2008-06-12 | Menachem Student | Remote Monitoring System For Alzheimer Patients |
| CN105608654A (en) * | 2015-12-19 | 2016-05-25 | 刘国正 | Intelligent wearable terminal based child behavior monitoring and developing method and system |
| CN106683340A (en) * | 2016-12-15 | 2017-05-17 | 歌尔股份有限公司 | A user behavior monitoring method and wearable device |
| CN108108743A (en) * | 2016-11-24 | 2018-06-01 | 百度在线网络技术（北京）有限公司 | Abnormal user recognition methods and the device for identifying abnormal user |
| CN108256540A (en) * | 2016-12-28 | 2018-07-06 | 中国移动通信有限公司研究院 | A kind of information processing method and system |
| CN108282533A (en) * | 2018-01-29 | 2018-07-13 | 百度在线网络技术（北京）有限公司 | intelligent monitoring method, device, wearable device and server |
-
2018
- 2018-09-21 CN CN201811117507.XA patent/CN109166624A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080139899A1 (en) * | 2005-05-04 | 2008-06-12 | Menachem Student | Remote Monitoring System For Alzheimer Patients |
| CN105608654A (en) * | 2015-12-19 | 2016-05-25 | 刘国正 | Intelligent wearable terminal based child behavior monitoring and developing method and system |
| CN108108743A (en) * | 2016-11-24 | 2018-06-01 | 百度在线网络技术（北京）有限公司 | Abnormal user recognition methods and the device for identifying abnormal user |
| CN106683340A (en) * | 2016-12-15 | 2017-05-17 | 歌尔股份有限公司 | A user behavior monitoring method and wearable device |
| CN108256540A (en) * | 2016-12-28 | 2018-07-06 | 中国移动通信有限公司研究院 | A kind of information processing method and system |
| CN108282533A (en) * | 2018-01-29 | 2018-07-13 | 百度在线网络技术（北京）有限公司 | intelligent monitoring method, device, wearable device and server |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109961090A (en) * | 2019-02-28 | 2019-07-02 | 广州杰赛科技股份有限公司 | A kind of behavior classification method and system based on intelligent wearable device |
| CN110211693A (en) * | 2019-06-03 | 2019-09-06 | 深圳市儿童医院 | A kind of motor function recovery situation automated after gait analysis assessment HIBD treatment |
| CN112002419B (en) * | 2020-09-17 | 2023-09-26 | 吾征智能技术(北京)有限公司 | A cluster-based disease auxiliary diagnosis system, equipment and storage medium |
| CN112002419A (en) * | 2020-09-17 | 2020-11-27 | 吾征智能技术(北京)有限公司 | Disease auxiliary diagnosis system, equipment and storage medium based on clustering |
| CN113008231A (en) * | 2021-04-30 | 2021-06-22 | 东莞市小精灵教育软件有限公司 | Motion state identification method and system, wearable device and storage medium |
| WO2022227202A1 (en) * | 2021-04-30 | 2022-11-03 | 东莞市小精灵教育软件有限公司 | Motion state recognition method and system, and wearable device and storage medium |
| CN115913980A (en) * | 2022-12-06 | 2023-04-04 | 沸蓝建设咨询有限公司 | A data multi-terminal access control system |
| CN115913980B (en) * | 2022-12-06 | 2023-07-28 | 沸蓝建设咨询有限公司 | A data multi-terminal access control system |
| CN116226527A (en) * | 2023-03-03 | 2023-06-06 | 中浙信科技咨询有限公司 | Digital community treatment method for realizing behavior prediction through resident big data |
| CN116226527B (en) * | 2023-03-03 | 2024-06-07 | 中浙信科技咨询有限公司 | Digital community treatment method for realizing behavior prediction through resident big data |
| CN117151959A (en) * | 2023-10-16 | 2023-12-01 | 广东紫慧旭光科技有限公司 | Real-time video analysis method, system and storage medium for city management |
| CN117151959B (en) * | 2023-10-16 | 2024-04-16 | 广东紫慧旭光科技有限公司 | Real-time video analysis method, system and storage medium for city management |
| CN118779710A (en) * | 2024-09-09 | 2024-10-15 | 杭州泽进科技有限公司 | A method and system for constructing multimodal heterogeneous vital sign data |
| CN119652557A (en) * | 2024-11-07 | 2025-03-18 | 海南大学 | Network situation awareness method and system based on user behavior analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109166624A (en) | A kind of behavior analysis method, device, server, system and storage medium | |
| US11615876B2 (en) | Predictive model for substance monitoring and impact prediction | |
| Lutze et al. | A smartwatch software architecture for health hazard handling for elderly people | |
| CN106845644B (en) | Heterogeneous network for learning user and mobile application contact through mutual relation | |
| CN108549276B (en) | Method and system for intelligently and interactively controlling water production equipment | |
| CN109669837A (en) | Equipment state method for early warning, system, computer installation and readable storage medium storing program for executing | |
| CN107193836B (en) | Identification method and device | |
| CN109918279A (en) | Electronic device, method and storage medium based on daily record data identification user's abnormal operation | |
| CN114444705A (en) | Model updating method and device | |
| CN106777973A (en) | The automatic method for formulating training plan, device and server | |
| CN110401567A (en) | The processing method of alarm data, calculates equipment, medium at device | |
| CN107256427A (en) | Medical knowledge drawing generating method, device and diagnostic data obtain system, method | |
| CN109324902A (en) | Method for adjusting operating frequency of mobile terminal, mobile terminal and storage medium | |
| CN110414778A (en) | Case assignment method and device | |
| CN107734202B (en) | Breakpoint calling-out method, electronic device and computer readable storage medium | |
| CN110111815A (en) | Animal anomaly sound monitoring method and device, storage medium, electronic equipment | |
| CN109657916A (en) | A kind of Fire risk assessment method, device and server | |
| CN108111399A (en) | Method, apparatus, terminal and the storage medium of Message Processing | |
| CN109035094A (en) | Teaching method, device and terminal device based on artificial intelligence | |
| Varghese et al. | Ai based caregiver for dementia patients | |
| Wilson et al. | Domain adaptation under behavioral and temporal shifts for natural time series mobile activity recognition | |
| CN107122464A (en) | A kind of aid decision-making system and method | |
| CN116936119A (en) | Blood bank intelligent scheduling management system and method | |
| CN110210425A (en) | Face identification method, device, electronic equipment and storage medium | |
| CN113056756B (en) | Sleep recognition method, device, storage medium and electronic equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190108 |
|
| RJ01 | Rejection of invention patent application after publication |