CN108281203A - A kind of prediction technique and device of abnormal behaviour - Google Patents
A kind of prediction technique and device of abnormal behaviour Download PDFInfo
- Publication number
- CN108281203A CN108281203A CN201810169092.4A CN201810169092A CN108281203A CN 108281203 A CN108281203 A CN 108281203A CN 201810169092 A CN201810169092 A CN 201810169092A CN 108281203 A CN108281203 A CN 108281203A
- Authority
- CN
- China
- Prior art keywords
- data
- monitored person
- person
- walking states
- prediction
- 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
Links
- 206010000117 Abnormal behaviour Diseases 0.000 title claims abstract description 86
- 238000000034 method Methods 0.000 title claims abstract description 53
- 230000003542 behavioural effect Effects 0.000 claims abstract description 45
- 230000005484 gravity Effects 0.000 claims description 53
- 230000035772 mutation Effects 0.000 claims description 48
- 230000006399 behavior Effects 0.000 claims description 25
- 230000005021 gait Effects 0.000 claims description 20
- 230000002159 abnormal effect Effects 0.000 claims description 15
- 238000004891 communication Methods 0.000 claims description 11
- 238000009434 installation Methods 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 8
- 238000013481 data capture Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 10
- 230000007613 environmental effect Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 7
- 230000008859 change Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000000474 nursing effect Effects 0.000 description 4
- 241000209094 Oryza Species 0.000 description 3
- 235000007164 Oryza sativa Nutrition 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 235000009566 rice Nutrition 0.000 description 3
- RTZKZFJDLAIYFH-UHFFFAOYSA-N Diethyl ether Chemical compound CCOCC RTZKZFJDLAIYFH-UHFFFAOYSA-N 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000036438 mutation frequency Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Development Economics (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Emergency Alarm Devices (AREA)
- Alarm Systems (AREA)
Abstract
This application discloses a kind of prediction technique of abnormal behaviour and device, the method includes:Acquisition is monitored the behavioral activity data of person;By analyzing the behavioral activity data to generate walking states data, the walking states data reflect the walking states of the monitored person;It is monitored whether person is abnormal behavior according to described in the walking states data prediction.This automatic Prediction mode to abnormal behaviour can find the abnormal behaviour of monitored person in time, not only reduce artificial nurse cost, it is thus also avoided that artificial nurse can not be achieved 24 hours one day sedulous nurse problems.
Description
Technical field
This application involves field of computer technology more particularly to the prediction techniques and device of a kind of abnormal behaviour.
Background technology
With the aging of population, effective nurse of the elderly will be as the social concern of a getting worse.It is existing
It is by artificial round-the-clock nurse in nursing old people mode, still, artificial nursing cost is higher, moreover, artificial nursing is not
It may realize sedulous nurse in 24 hours in one day, the elderly's unusual condition (such as tumble etc.) can not be found in time by existing
Situation to which the unusual condition that can not occur in time to the elderly is handled, and then can not ensure the person peace of the elderly
Entirely.
Invention content
The main purpose of the embodiment of the present application is to provide a kind of prediction technique and device of abnormal behaviour, can be in time
It was found that the abnormal behaviour of monitored person.
The embodiment of the present application provides a kind of prediction technique of abnormal behaviour, including:
Acquisition is monitored the behavioral activity data of person;
Walking states data are generated by analyzing the behavioral activity data, the walking states data reflect described
The walking states of monitored person;
It is monitored whether person is abnormal behavior according to described in the walking states data prediction.
Optionally, the acquisition is monitored the behavioral activity data of person, including:
Using at least one infrared sensor, the behavioral activity data of the monitored person are acquired.
Optionally, described to utilize at least one infrared sensor, the behavioral activity data for being monitored person are acquired, including:
According to the installation site of at least one infrared sensor, determine the monitored person location information and/or
Center of gravity information;
Correspondingly, described by analyzing the behavioral activity data to generate walking states data, including:
By analyzing the location information and/or center of gravity information, to generate walking states data.
Optionally, the walking states data include following one or more data:
The paces frequency of the monitored person;
Reflect the successional data of gait of the monitored person;
Reflect the data of the paces amplitude of variation of the monitored person;
Reflect the data of the gravity center shift amplitude of the monitored person.
Optionally, described that whether behavior is abnormal according to monitored person described in the walking states data prediction, including:
Determine that the mutation probability of each item data in the walking states data, the mutation probability characterize respective items
The frequency of mutation of the data in preset period of time;
According to the mutation probability of each item data, predict that the monitored person is abnormal the probability of behavior;
Judge whether the probability predicted is more than predetermined probabilities threshold value;
If so, the prediction monitored person is abnormal behavior;If it is not, then predicting monitored person's no exceptions
Behavior.
Optionally, the prediction monitored person is abnormal after behavior, further includes:
According to the walking states data, the abnormal behaviour type of prediction monitored person's generation.
Optionally, the method further includes:
According to the virtual condition of the abnormal behaviour type and the monitored person, the determination side of the mutation probability is adjusted
The size of formula and/or the predetermined probabilities threshold value.
Optionally, the prediction monitored person is abnormal after behavior, further includes:
Warning information is sent at least one default communication apparatus.
The embodiment of the present application also provides a kind of prediction meanss of abnormal behaviour, including:
Behavioral data collecting unit, the behavioral activity data for acquiring monitored person;
It walks data capture unit, it is described for passing through the analysis behavioral activity data to generate walking states data
Walking states data reflect the walking states of the monitored person;
Abnormal behaviour predicting unit, for being monitored whether person is abnormal according to described in the walking states data prediction
Behavior.
Optionally, the behavioral data collecting unit includes:
First data acquisition unit acquires the behavior of the monitored person for utilizing at least one infrared sensor
Activity data.
Optionally, the first data acquisition unit includes:
Second data acquisition unit, described according to the installation site of at least one infrared sensor, determining
The location information and/or center of gravity information of monitored person;
Correspondingly, the walking data capture unit includes:
Walking data acquisition subelement analyzes the location information and/or center of gravity information, to generate walking shape for passing through
State data.
Optionally, the walking states data include following one or more data:
The paces frequency of the monitored person;
Reflect the successional data of gait of the monitored person;
Reflect the data of the paces amplitude of variation of the monitored person;
Reflect the data of the gravity center shift amplitude of the monitored person.
Optionally, the abnormal behaviour predicting unit includes:
Mutation probability determination subelement, the mutation probability for determining each item data in the walking states data,
The mutation probability characterizes the frequency of mutation of the corresponding item data in preset period of time;
Abnormal determine the probability subelement predicts the monitored person for the mutation probability according to each item data
It is abnormal the probability of behavior;
Abnormal behaviour predicts subelement, and whether the probability for judging to predict is more than predetermined probabilities threshold value;If so, pre-
It surveys the monitored person and is abnormal behavior;If it is not, then predicting monitored person's no exceptions behavior.
Optionally, described device further includes:
Behavior type predicting unit, after being abnormal behavior in the prediction monitored person, according to described
Walking states data, the abnormal behaviour type that the prediction monitored person occurs.
Optionally, described device further includes:
Trigger condition adjustment unit is adjusted for the virtual condition according to the abnormal behaviour type and the monitored person
The size of the method for determination of the whole mutation probability and/or the predetermined probabilities threshold value.
Optionally, described device further includes:
Warning information transmission unit, after being abnormal behavior in the prediction monitored person, at least one
A default communication apparatus sends warning information.
The embodiment of the present application also provides a kind of prediction meanss of abnormal behaviour, which is characterized in that including:Processor is deposited
Reservoir, system bus;
The processor and the memory are connected by the system bus;
The memory includes instruction, described instruction for storing one or more programs, one or more of programs
The processor is set to execute method described in any one of the above embodiments when being executed by the processor.
The embodiment of the present application also provides a kind of computer readable storage medium, deposited in the computer readable storage medium storing program for executing
Instruction is contained, when described instruction is run on the terminal device so that the terminal device executes the prediction of above-mentioned abnormal behaviour
Any implementation method of method.
The prediction technique and device of a kind of abnormal behaviour provided by the embodiments of the present application acquire the behavioral activity for being monitored person
Data;By analyzing the behavioral activity data to generate walking states data, the walking states data reflect the quilt
The walking states of human observer;It is monitored whether person is abnormal behavior according to described in the walking states data prediction.As it can be seen that this
Kind can find the abnormal behaviour of monitored person, not only reduce and manually see in time to the automatic Prediction mode of abnormal behaviour
Protect cost, it is thus also avoided that artificial nurse can not be achieved 24 hours one day sedulous nurse problems.
Description of the drawings
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is the application
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 is a kind of one of flow diagram of prediction technique of abnormal behaviour provided by the embodiments of the present application;
Fig. 2 is the two of a kind of flow diagram of the prediction technique of abnormal behaviour provided by the embodiments of the present application;
Fig. 3 is a kind of composition schematic diagram of the prediction meanss of abnormal behaviour provided by the embodiments of the present application;
Fig. 4 is a kind of hardware architecture diagram of the prediction meanss of abnormal behaviour provided by the embodiments of the present application.
Specific implementation mode
To keep the purpose, technical scheme and advantage of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
In attached drawing, technical solutions in the embodiments of the present application is clearly and completely described, it is clear that described embodiment is
Some embodiments of the present application, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art
The every other embodiment obtained without making creative work, shall fall in the protection scope of this application.
The embodiment of the present application provides a kind of prediction technique of abnormal behaviour, and the behavioral activity number of person is monitored by acquisition
According to, for example the behavioral activity data of the elderly are acquired, to analyze the walking states of the elderly, to which basis divides walking states
Analysis is as a result, to predict whether the behavior of the elderly exception occurs, to realize a kind of automatic nurse mode.Using this automatic
The artificial nurse cost to the elderly can be greatly reduced in nurse mode, furthermore, it is possible to may quickly go out to the elderly in time
Existing abnormal behaviour is precisely predicted, such as tumble etc., so as to effectively reduce the potential risk that the elderly is likely to occur,
And then it overcomes in artificial nurse it is not possible that 24 hours one day sedulous nurse defects.
The embodiment of the present application is specifically introduced below.
It is a kind of flow diagram of the prediction technique of abnormal behaviour provided by the embodiments of the present application, the prediction referring to Fig. 1
Method includes the following steps:
S101:Acquisition is monitored the behavioral activity data of person.
Can be handicapped old it should be noted that the present embodiment does not limit the specific identity of the monitored person
Year people can also be the patient for suffering from disease.
Wherein, the behavioral activity data are the relevant data of behavioral activity with the monitored person.It needs to illustrate
That the behavioral activity data are really one group of time series data, so as to be based on the time series data to monitored person into
Row behavior prediction.
It can be under the premise of protecting individual privacy, using the sensor-based system including one or more sensors, to acquire
The behavioral activity data of monitored person.Therefore, in a kind of embodiment of the application, step S101 can specifically include:Profit
With at least one infrared sensor, the behavioral activity data for being monitored person are acquired.
It in the present embodiment, can for the monitoring of environmental (such as in family, nursing home rooms etc.) being monitored residing for person
With according to the deployment scenarios of the monitoring of environmental, monitored frequent activities region and sensor sense of the person in the monitoring of environmental
Know the factors such as the size in region, multiple infrared sensors are installed in the monitoring of environmental, more than specific installation site can combine
Several combined factors consider, are capable of the behavioral activity of the comprehensive monitoring monitored person as possible.For example, can be by each infrared sensing
Device is deployed in the positions such as roof, wall side, is installed on the infrared sensor of different location by these to acquire the behavior of monitored person
Activity data, and these collected data are stored in database, carry out data analysis will pass through subsequent step.
It further, specifically can be according at least one infrared sensing in the above-mentioned specific implementation of S101
The installation site of device determines the location information and/or center of gravity information of monitored person.That is, for the behavioral activity data, it can
With the center of gravity information of location information and/or monitored person including monitored person, and location information and/or center of gravity information are to be based on
The installation site of the infrared sensor of monitored person is perceived and determination, next, carried out to location information and center of gravity information
It illustrates.
Wherein, the location information can be monitored relative position of the person in monitoring of environmental, and the relative position can
To be position section.
Specifically, it may be predetermined that the space size of the monitoring of environmental, and with a vertex in the monitoring of environmental
Position (such as one in four, roof vertex) is origin coordinates, for example origin coordinates is (0,0), in this way, the monitoring of environmental
Interior other vertex positions and vertex can come relative to this origin coordinates (0,0) with the position coordinates of external position
The relative coordinate of definition.
Based on this, the position of each infrared sensor can be measured in advance, to define each infrared sensor in the prison
Survey the relative coordinate in environment.In this way, when acquisition is monitored the location information of person, it can be defeated according to the signal of infrared sensor
Artificial situation determines monitored person by which infrared sensor covering perception, then, according to the infrared sensing for perceiving monitored person
The relative coordinate of device, to infer the physical location where monitored person.For example, when monitored person is simultaneously by sensors A and sensing
The two infrared sensors of device B perceive simultaneously, it is possible to determine what monitored person intersected in sensors A and sensor B
In overlay area, so as to according to the relative coordinate of sensors A and sensor B, specific being covered determine residing for monitored person
Cover area.
Wherein, the center of gravity information can be that basis is inferred mounted on the sensing results of the infrared sensor of different height
The height of C.G. information of the monitored person gone out, and the elevation information can be a height section.
Specifically, the center of gravity height for being monitored person can be determined based on the fuse information of multiple sensors.Example
Such as, it is assumed that between the position height of sensors A covering is 1.2 meters to 2 meters, the position height of sensor B coverings is 0 meter to 1.3
Between rice, if sensors A and sensor B perceive monitored person simultaneously, being monitored the center of gravity of person at this time should be 1.2
Rice is between 1.3 meters;If only sensor B perceives monitored person, 1.2 should be less than by being monitored the center of gravity of person at this time
Rice.
S102:By analyzing the behavioral activity data to generate walking states data, wherein the walking states data
Reflect the walking states of the monitored person.
When the behavioral activity data include the location information and/or center of gravity information of monitored person, correspondingly, S102 tools
Body may include:By analyzing the location information and/or center of gravity information, to generate walking states data.
In the present embodiment, can chronologically-based acquisition behavioral activity data, to be monitored person paces frequency,
The characteristics such as gait continuity, paces amplitude of variation, gravity center shift amplitude are extracted and are arranged, to form the walking
Status data.
Therefore, in a kind of embodiment of the application, the walking states data may include in following 4 item data
It is one or more:
1st:The paces frequency of the monitored person.
The paces frequency refers to the step number that monitored person is walked in preset duration, for example, it is per minute walk how many step.
In the process of walking due to monitored person, center of gravity is periodically variable, therefore, can be based on the weight referred in above-mentioned steps
Heart information knows the gravity center shift situation of monitored person in the process of walking, and then determines monitored person institute in preset duration
The step number walked, for example, it is per minute walk 20 steps.
2nd:Reflect the successional data of gait of the monitored person.
As an example, reflect the successional data of the gait, whether steady, the paces if can refer to paces frequency
The relevant explanation of frequency may refer to described in the 1st, and details are not described herein.For example, if monitored person walked 30 at first 1 minute
Step, and 15 steps have been walked within following 1 minute, illustrate that the variation of paces frequency is apparent, then it represents that paces frequency is unstable, to indicate
It is poor to state gait continuity;If monitored person walked 30 steps at first 1 minute, and had walked within following 1 minute 28 steps, illustrate paces
Frequency changes unobvious, then it represents that paces frequency is more steady, to indicate that the gait continuity is preferable.
As another example, reflect the successional data of the gait, whether steady, the step of paces distance can be referred to
It refers to the distance or be pre-determined distance has walked how many step that monitored person is walked using default step number to cut down distance, for example 10 steps are walked
It is over 7 meters.For example, if monitored person has walked 7 meters in preceding 10 step, then 10 steps have walked 2 meters, illustrate that often walking walked distance becomes
Change apparent, then it represents that paces are apart from unstable, to indicate that the gait continuity is poor;If monitored person walks in preceding 10 step
7 meters, then 10 steps walked 6 meters, illustrate often to walk walked distance change unobvious, then it represents that paces distance is steady, to table
Show that the gait continuity is preferable.
Wherein, in the process of walking due to monitored person, center of gravity is periodically variable, therefore, can be based on above-mentioned
The center of gravity information referred in step knows the gravity center shift situation of monitored person in the process of walking, and then determines monitored person
The step number walked in preset duration;And the distance that monitored person is walked, it can be according to the location information referred in above-mentioned steps
To determine.
3rd:Reflect the data of the paces amplitude of variation of the monitored person.
As an example, the paces amplitude of variation can refer to the paces frequency referred in above-mentioned 1st or the 2nd
The amplitude of variation of rate, referred to herein as cadence change.Specifically, step number and duration can determine the frequency of paces, according to each
The statistical result of period (monitored person is under walking states), for example a step number was counted to monitored person in every 1 minute, by this
Statistical result calculates once averagely cadence size, can calculate cadence delta data in this way.For example, if monitored person is preceding
1 minute average cadence is 30 steps/minute, and following 1 minute average cadence is 16 steps/minute, then it represents that cadence changes
It is 14 to be worth (decreasing value).
As another example, the paces amplitude of variation can refer to the paces distance referred in above-mentioned 2nd
Amplitude of variation, referred to herein as step change.Specifically, step number and distance can determine that step size (walked by i.e. average often step
Distance), according to the statistical result of each distance segment (monitored person under walking states), for example, monitored person often walk 3 meters it is right
Monitored person counts a step number, calculates an average stride size by this statistical result, can calculate step change in this way
Data.For example, if monitored person in preceding 3 meters of average stride is 0.5 meter/step, rear 3 meters of average stride be 0.2 meter/
Step, then it represents that step change value (decreasing value) is 0.3.
4th:Reflect the data of the gravity center shift amplitude of the monitored person.
The gravity center shift amplitude can refer to the amplitude of monitored person center of gravity height variation in the process of walking.Since people exists
In walking process, center of gravity is periodically variable, therefore, can be known and supervised based on the center of gravity information of above-mentioned monitored person
The gravity center shift amplitude of survey person in the process of walking.For example, if monitored person did not surpassed in front and back 1 minute gravity center shift amplitude
Cross positive and negative 0.5 meter, then it represents that gravity center shift amplitude is normal, otherwise indicates that gravity center shift amplitude is abnormal.
S103:It is monitored whether person is abnormal behavior according to described in the walking states data prediction.
It, can be according to the mutation frequency of each item data in the walking states data after generating the walking states data
Rate, to predict whether monitored person is abnormal behavior.
In this way, as shown in Fig. 2, in a kind of embodiment of the application, step S103 can specifically include following steps:
S201:Determine that the mutation probability of each item data in the walking states data, the mutation probability characterize
The frequency of mutation of the corresponding item data in preset period of time.
In the present embodiment, if the walking states data include above-mentioned 1st item data, i.e., the step of the described monitored person
Cut down frequency, then it, specifically can be according to the statistical result of the past paces frequency data it needs to be determined that the mutation probability Pr1 of paces frequency
It is calculated with current pace frequency data.As an example, mutation probability Pr1 can be according to the paces in a period of time
The mutation number of frequency calculates, for example, current time start (such as 15 minutes) for the previous period in, paces frequency
The case where mutation, occurs 3 times, then Pr1=3%.
In the present embodiment, if the walking states data include above-mentioned 2nd item data, that is, reflect the monitored person
The successional data of gait specifically can be continuous according to the past gait then it needs to be determined that the successional mutation probability Pr2 of gait
The statistical result and current gait continuity data of property data calculates.As an example, mutation probability Pr2 can basis
The successional mutation number of gait calculates in a period of time, for example, current time start (ratio for the previous period
Such as 15 minutes) in, the case where gait continuity is mutated, occurs 3 times, then Pr2=3%.
In the present embodiment, if the walking states data include above-mentioned 3rd item data, that is, reflect the monitored person
The data of paces amplitude of variation specifically can be according to the past paces then it needs to be determined that the mutation probability Pr3 of paces amplitude of variation
The statistical result and current pace amplitude of variation data of amplitude of variation calculates.As an example, mutation probability Pr3 can be with
Calculated according to the mutation number of the paces amplitude of variation in a period of time, for example, current time start the last period
The case where time (such as 15 minutes) is interior, and paces amplitude of variation is mutated occurs 3 times, then Pr3=3%.
In the present embodiment, if the walking states data include above-mentioned 4th item data, that is, reflect the monitored person
The data of gravity center shift amplitude specifically can walk weight according to the past then it needs to be determined that the mutation probability Pr4 of gravity center shift amplitude
The statistical result of heart amplitude of variation and current gravity center shift amplitude data calculate.As an example, mutation probability Pr4 can
To be calculated according to the mutation number of the gravity center shift amplitude in a period of time, for example, current time start it is previous
The case where section time (such as 15 minutes) is interior, gravity center shift amplitude hit occurs 3 times, then Pr4=3%.
S202:According to the mutation probability of each item data, predict that the monitored person is abnormal the probability of behavior.
Above-mentioned mutation probability parameter is input in the abnormal behaviour prediction model pre-established, can be predicted monitored
Person is abnormal the probability P r of behavior, specific as follows:
Pr=1- (1-Pr1) * (1-Pr2) * (1-Pr3) * (1-Pr4) * 100%
It should be noted that for the walking states data data item not to be covered, the corresponding mutation probability of data item
Value is 1.
S203:Judge whether the probability predicted is more than predetermined probabilities threshold value;If so, the prediction monitored person occurs
Abnormal behaviour;If it is not, then predicting monitored person's no exceptions behavior.
A probability threshold value can be set, when probability P r is more than the probability threshold value, it is different just to judge that the monitored person occurs
Chang Hangwei just judges that the monitored person is not abnormal behavior conversely, when probability P r is not more than the probability threshold value.Wherein,
The probability threshold value can also be adjusted according to counting empirically determined according to the actual conditions for being monitored person.
Further, when S103 or step S203 through the above steps predict the monitored person be abnormal behavior it
Afterwards, the present embodiment can also predict which class abnormal behaviour the monitored person has occurred, therefore, in a kind of embodiment party of the application
In formula, can also include:According to the walking states data, the abnormal behaviour type of prediction monitored person's generation.
In the present embodiment, each item number for being included about the walking states data for being introduced in step S102
According to that is, about related datas such as paces frequency, gait continuity, paces amplitude of variation, gravity center shift amplitudes, can utilizing wherein
One item data or multinomial data, to predict abnormal behaviour type that monitored person is likely to occur.
For example, can judge the whether suddenly quickening or unexpected of its paces from the paces amplitude of variation data of monitored person
Slow down;If paces are accelerated suddenly, the abnormal behaviour type for being monitored person can be " may fall down ";If paces are put suddenly
Slow, the abnormal behaviour type for being monitored person can be " may fall in a swoon ".
On this basis, it can be predicted further combined with the gravity center shift amplitude data of monitored person.Specifically, may be used
To combine specific time of origin, judge whether its gravity center of human body declines suddenly from the gravity center shift amplitude data of monitored person;
If center of gravity declines suddenly and above-mentioned judgement show that paces are accelerated suddenly, the abnormal behaviour type of monitored person can be " to fall
";If center of gravity is without decline suddenly and above-mentioned judgement show that paces are accelerated suddenly, the abnormal behaviour type for being monitored person can
Think " falling down not successfully ";If center of gravity declines suddenly and above-mentioned judgement show that paces slow down suddenly, it is monitored the exception of person
Behavior type can be " falling in a swoon ";If center of gravity is without decline suddenly and above-mentioned judgement show that paces slow down suddenly, it is monitored
The abnormal behaviour type of person can be " state of mind is not good enough ".
Further, when S103 or step S203 through the above steps predict the monitored person be abnormal behavior it
Afterwards, warning function can be triggered, specifically can send warning information at least one default communication apparatus.Wherein, described default
Communication apparatus can be the communication apparatus of guardian or emergency contact, for example, if the monitoring of environmental residing for monitored person is
Family, then the default communication apparatus can be the household of monitored person or the mobile phone of neighbours;If the prison residing for monitored person
It is hospital or home for destitute to survey environment, and the default communication apparatus can be household or the relevant person in charge of monitored person.Wherein, institute
It can indicate that the prompt message of abnormal behaviour, such as word and/or voice messaging has occurred in monitored person to state warning information,
On the basis of this, specific abnormal behaviour type can also be provided.
Further, after predicting the abnormal behaviour type that the monitored person occurs, due to the abnormal behaviour class
Type is prediction result, the prediction result may accurately may also be inaccurate, therefore, the practical letter of the feedbacks such as guardian can be obtained
Breath, to determine whether prediction result and the virtual condition of the monitored person are consistent, to realize forecasting system parameter self
Study and adjusting and optimizing, that is, the actual conditions based on monitored person, adjustment send out the trigger condition and parameter of early warning.
It therefore, can be according to the abnormal behaviour type and the monitored person in a kind of embodiment of the application
Virtual condition, adjust the method for determination of the mutation probability and/or the size of the predetermined probabilities threshold value.For example, when being supervised
The cadence of survey person from 10 step per minute variation be 14 step per minute, although occur it is this variation be monitored person actually do not occur it is different
It often occurs as can come by adjusting the corresponding mutation probability method of determination of the data and/or the size of the predetermined probabilities threshold value
Avoid the triggering of warning information.
To sum up, the prediction technique of a kind of abnormal behaviour provided by the embodiments of the present application acquires the behavioral activity for being monitored person
Data;By analyzing the behavioral activity data to generate walking states data, the walking states data reflect the quilt
The walking states of human observer;It is monitored whether person is abnormal behavior according to described in the walking states data prediction.As it can be seen that this
Kind can find the abnormal behaviour of monitored person, not only reduce and manually see in time to the automatic Prediction mode of abnormal behaviour
Protect cost, it is thus also avoided that artificial nurse can not be achieved 24 hours one day sedulous nurse problems.
It is a kind of composition schematic diagram of the prediction meanss of abnormal behaviour provided by the embodiments of the present application, the prediction referring to Fig. 3
Device 300 includes:
Behavioral data collecting unit 301, the behavioral activity data for acquiring monitored person;
Walking data capture unit 302, for passing through the analysis behavioral activity data to generate walking states data, institute
State the walking states that walking states data reflect the monitored person;
Abnormal behaviour predicting unit 303, for being monitored whether person occurs according to described in the walking states data prediction
Abnormal behaviour.
In a kind of embodiment of the application, the behavioral data collecting unit 301 includes:
First data acquisition unit acquires the behavior of the monitored person for utilizing at least one infrared sensor
Activity data.
In a kind of embodiment of the application, the first data acquisition unit includes:
Second data acquisition unit, described according to the installation site of at least one infrared sensor, determining
The location information and/or center of gravity information of monitored person;
Correspondingly, the walking data capture unit 302 includes:
Walking data acquisition subelement analyzes the location information and/or center of gravity information, to generate walking shape for passing through
State data.
In a kind of embodiment of the application, the walking states data include following one or more data:
The paces frequency of the monitored person;
Reflect the successional data of gait of the monitored person;
Reflect the data of the paces amplitude of variation of the monitored person;
Reflect the data of the gravity center shift amplitude of the monitored person.
In a kind of embodiment of the application, the abnormal behaviour predicting unit 303 includes:
Mutation probability determination subelement, the mutation probability for determining each item data in the walking states data,
The mutation probability characterizes the frequency of mutation of the corresponding item data in preset period of time;
Abnormal determine the probability subelement predicts the monitored person for the mutation probability according to each item data
It is abnormal the probability of behavior;
Abnormal behaviour predicts subelement, and whether the probability for judging to predict is more than predetermined probabilities threshold value;If so, pre-
It surveys the monitored person and is abnormal behavior;If it is not, then predicting monitored person's no exceptions behavior.
In a kind of embodiment of the application, described device 300 further includes:
Behavior type predicting unit, after being abnormal behavior in the prediction monitored person, according to described
Walking states data, the abnormal behaviour type that the prediction monitored person occurs.
In a kind of embodiment of the application, described device 300 further includes:
Trigger condition adjustment unit is adjusted for the virtual condition according to the abnormal behaviour type and the monitored person
The size of the method for determination of the whole mutation probability and/or the predetermined probabilities threshold value.
In a kind of embodiment of the application, described device 300 further includes:
Warning information transmission unit, after being abnormal behavior in the prediction monitored person, at least one
A default communication apparatus sends warning information.
It is a kind of hardware architecture diagram of the prediction meanss of abnormal behaviour provided by the embodiments of the present application, institute referring to Fig. 4
It includes memory 401 and receiver 402 to state device 400, and is connect respectively with the memory 401 and the receiver 402
Processor 403, the memory 401 is for storing batch processing instruction, and the processor 403 is for calling the memory
The program instruction of 401 storages executes following operation:
Acquisition is monitored the behavioral activity data of person;
Walking states data are generated by analyzing the behavioral activity data, the walking states data reflect described
The walking states of monitored person;
It is monitored whether person is abnormal behavior according to described in the walking states data prediction.
In a kind of embodiment of the application, the processor 403 is additionally operable to the journey for calling the memory 401 to store
Sequence instruction execution operates as follows:
Using at least one infrared sensor, the behavioral activity data of the monitored person are acquired.
In a kind of embodiment of the application, the processor 403 is additionally operable to the journey for calling the memory 401 to store
Sequence instruction execution operates as follows:
According to the installation site of at least one infrared sensor, determine the monitored person location information and/or
Center of gravity information;
By analyzing the location information and/or center of gravity information, to generate walking states data.
In a kind of embodiment of the application, the walking states data include following one or more data:
The paces frequency of the monitored person;
Reflect the successional data of gait of the monitored person;
Reflect the data of the paces amplitude of variation of the monitored person;
Reflect the data of the gravity center shift amplitude of the monitored person.
In a kind of embodiment of the application, the processor 403 is additionally operable to the journey for calling the memory 401 to store
Sequence instruction execution operates as follows:
Determine that the mutation probability of each item data in the walking states data, the mutation probability characterize respective items
The frequency of mutation of the data in preset period of time;
According to the mutation probability of each item data, predict that the monitored person is abnormal the probability of behavior;
Judge whether the probability predicted is more than predetermined probabilities threshold value;
If so, the prediction monitored person is abnormal behavior;If it is not, then predicting monitored person's no exceptions
Behavior.
In a kind of embodiment of the application, the processor 403 is additionally operable to the journey for calling the memory 401 to store
Sequence instruction execution operates as follows:
According to the walking states data, the abnormal behaviour type of prediction monitored person's generation.
In a kind of embodiment of the application, the processor 403 is additionally operable to the journey for calling the memory 401 to store
Sequence instruction execution operates as follows:
According to the virtual condition of the abnormal behaviour type and the monitored person, the determination side of the mutation probability is adjusted
The size of formula and/or the predetermined probabilities threshold value.
In a kind of embodiment of the application, the processor 403 is additionally operable to the journey for calling the memory 401 to store
Sequence instruction execution operates as follows:
Warning information is sent at least one default communication apparatus.
In some embodiments, the processor 403 can be central processing unit (Central Processing
Unit, CPU), the memory 401 can be the interior of random access memory (Random Access Memory, RAM) type
Portion's memory, the receiver 402 can include General Physics interface, and the physical interface can be that ether (Ethernet) connects
Mouth or asynchronous transfer mode (Asynchronous Transfer Mode, ATM) interface.The processor 403, receiver 402
One or more independent circuits or hardware can be integrated into memory 401, such as:Application-specific integrated circuit (Application
Specific Integrated Circuit, ASIC).
Further, the embodiment of the present application also provides a kind of computer readable storage medium, the computer is readable to deposit
Instruction is stored in storage media, when described instruction is run on the terminal device so that the terminal device executes above-mentioned exception
Any implementation method of the prediction technique of behavior.
As seen through the above description of the embodiments, those skilled in the art can be understood that above-mentioned implementation
All or part of step in example method can add the mode of required general hardware platform to realize by software.Based on such
Understand, substantially the part that contributes to existing technology can be in the form of software products in other words for the technical solution of the application
It embodies, which can be stored in a storage medium, such as ROM/RAM, magnetic disc, CD, including several
Instruction is used so that a computer equipment (can be the network communications such as personal computer, server, or Media Gateway
Equipment, etc.) execute method described in certain parts of each embodiment of the application or embodiment.
It should be noted that each embodiment is described by the way of progressive in this specification, each embodiment emphasis is said
Bright is all difference from other examples, and just to refer each other for identical similar portion between each embodiment.For reality
For applying device disclosed in example, since it is corresponded to the methods disclosed in the examples, so description is fairly simple, related place
Referring to method part illustration.
It should also be noted that, herein, relational terms such as first and second and the like are used merely to one
Entity or operation are distinguished with another entity or operation, without necessarily requiring or implying between these entities or operation
There are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant are intended to contain
Lid non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also include other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or equipment including the element.
The foregoing description of the disclosed embodiments enables professional and technical personnel in the field to realize or use the application.
Various modifications to these embodiments will be apparent to those skilled in the art, as defined herein
General Principle can in other embodiments be realized in the case where not departing from spirit herein or range.Therefore, the application
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest range caused.
Claims (11)
1. a kind of prediction technique of abnormal behaviour, which is characterized in that including:
Acquisition is monitored the behavioral activity data of person;
By analyzing the behavioral activity data to generate walking states data, the walking states data reflect described supervised
The walking states of survey person;
It is monitored whether person is abnormal behavior according to described in the walking states data prediction.
2. according to the method described in claim 1, it is characterized in that, it is described acquisition be monitored person behavioral activity data, including:
Using at least one infrared sensor, the behavioral activity data of the monitored person are acquired.
3. according to the method described in claim 2, it is characterized in that, described utilize at least one infrared sensor, acquisition to be supervised
The behavioral activity data of survey person, including:
According to the installation site of at least one infrared sensor, the location information and/or center of gravity of the monitored person are determined
Information;
Correspondingly, described by analyzing the behavioral activity data to generate walking states data, including:
By analyzing the location information and/or center of gravity information, to generate walking states data.
4. method according to any one of claims 1 to 3, which is characterized in that the walking states data include following one
Item or multinomial data:
The paces frequency of the monitored person;
Reflect the successional data of gait of the monitored person;
Reflect the data of the paces amplitude of variation of the monitored person;
Reflect the data of the gravity center shift amplitude of the monitored person.
5. according to the method described in claim 4, it is characterized in that, described supervised according to described in the walking states data prediction
Whether survey person is abnormal behavior, including:
Determine that the mutation probability of each item data in the walking states data, the mutation probability characterize corresponding item data
The frequency of mutation in preset period of time;
According to the mutation probability of each item data, predict that the monitored person is abnormal the probability of behavior;
Judge whether the probability predicted is more than predetermined probabilities threshold value;
If so, the prediction monitored person is abnormal behavior;If it is not, then predicting monitored person's no exceptions row
For.
6. method according to claim 1 or 5, which is characterized in that the prediction monitored person is abnormal behavior
Later, further include:
According to the walking states data, the abnormal behaviour type of prediction monitored person's generation.
7. according to the method described in claim 6, it is characterized in that, the method further includes:
According to the virtual condition of the abnormal behaviour type and the monitored person, the method for determination of the mutation probability is adjusted
And/or the size of the predetermined probabilities threshold value.
8. method according to claim 1 or 5, which is characterized in that the prediction monitored person is abnormal behavior
Later, further include:
Warning information is sent at least one default communication apparatus.
9. a kind of prediction meanss of abnormal behaviour, which is characterized in that including:
Behavioral data collecting unit, the behavioral activity data for acquiring monitored person;
Walking data capture unit, for passing through the analysis behavioral activity data to generate walking states data, the walking
Status data reflects the walking states of the monitored person;
Abnormal behaviour predicting unit, for being monitored whether person is abnormal row according to described in the walking states data prediction
For.
10. a kind of prediction meanss of abnormal behaviour, which is characterized in that including:Processor, memory, system bus;
The processor and the memory are connected by the system bus;
The memory includes instruction for storing one or more programs, one or more of programs, and described instruction works as quilt
The processor makes the processor execute the method as described in any one of claim 1-8 when executing.
11. a kind of computer readable storage medium, which is characterized in that it is stored with instruction in the computer readable storage medium storing program for executing,
When described instruction is run on the terminal device so that the terminal device perform claim requires 1-8 any one of them methods.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810169092.4A CN108281203B (en) | 2018-02-28 | 2018-02-28 | Method and device for predicting abnormal behavior |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810169092.4A CN108281203B (en) | 2018-02-28 | 2018-02-28 | Method and device for predicting abnormal behavior |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108281203A true CN108281203A (en) | 2018-07-13 |
CN108281203B CN108281203B (en) | 2021-10-22 |
Family
ID=62808721
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810169092.4A Active CN108281203B (en) | 2018-02-28 | 2018-02-28 | Method and device for predicting abnormal behavior |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108281203B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109118081A (en) * | 2018-08-08 | 2019-01-01 | 成都保源酷码科技有限公司 | A kind of operation safety supervisory systems and method based on image procossing mode |
CN109492595A (en) * | 2018-11-19 | 2019-03-19 | 浙江传媒学院 | Behavior prediction method and system suitable for fixed group |
CN111243369A (en) * | 2020-01-16 | 2020-06-05 | 西安科技大学 | Container type fire-fighting hidden danger accident recurrence experience training system |
CN115065585A (en) * | 2022-04-29 | 2022-09-16 | 北京达佳互联信息技术有限公司 | Business abnormity monitoring method and device, electronic equipment and storage medium |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1874497A (en) * | 2006-05-30 | 2006-12-06 | 浙江工业大学 | Household safe and security equipment for solitary old person based on omnibearing computer vision |
FR2929427A1 (en) * | 2008-03-26 | 2009-10-02 | Univ Rennes I Etablissement Pu | METHOD FOR ASSESSING HEALTH AND / OR FORM, DEVICE AND CORRESPONDING COMPUTER PROGRAM PRODUCT |
CN102811343A (en) * | 2011-06-03 | 2012-12-05 | 南京理工大学 | Intelligent video monitoring system based on behavior recognition |
CN103577810A (en) * | 2013-11-13 | 2014-02-12 | 汕头大学 | Intelligent nursing method |
US20140221784A1 (en) * | 2003-08-11 | 2014-08-07 | Bodymedia, Inc. | System for monitoring and presenting health, wellness, nutrition and fitness data with feedback and coaching engine |
CN105286874A (en) * | 2015-11-03 | 2016-02-03 | 长安大学 | System and method for predicting tumble risk of old people |
CN105989695A (en) * | 2015-02-15 | 2016-10-05 | 中国移动通信集团公司 | Guarding object movement risk evaluation method and device |
CN106683340A (en) * | 2016-12-15 | 2017-05-17 | 歌尔股份有限公司 | User behavior monitoring method and wearable equipment |
CN106919892A (en) * | 2015-12-25 | 2017-07-04 | 中国移动通信集团公司 | Behavior monitoring method and device |
CN107174255A (en) * | 2017-06-15 | 2017-09-19 | 西安交通大学 | Three-dimensional gait information gathering and analysis method based on Kinect somatosensory technology |
-
2018
- 2018-02-28 CN CN201810169092.4A patent/CN108281203B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140221784A1 (en) * | 2003-08-11 | 2014-08-07 | Bodymedia, Inc. | System for monitoring and presenting health, wellness, nutrition and fitness data with feedback and coaching engine |
CN1874497A (en) * | 2006-05-30 | 2006-12-06 | 浙江工业大学 | Household safe and security equipment for solitary old person based on omnibearing computer vision |
FR2929427A1 (en) * | 2008-03-26 | 2009-10-02 | Univ Rennes I Etablissement Pu | METHOD FOR ASSESSING HEALTH AND / OR FORM, DEVICE AND CORRESPONDING COMPUTER PROGRAM PRODUCT |
CN102811343A (en) * | 2011-06-03 | 2012-12-05 | 南京理工大学 | Intelligent video monitoring system based on behavior recognition |
CN103577810A (en) * | 2013-11-13 | 2014-02-12 | 汕头大学 | Intelligent nursing method |
CN105989695A (en) * | 2015-02-15 | 2016-10-05 | 中国移动通信集团公司 | Guarding object movement risk evaluation method and device |
CN105286874A (en) * | 2015-11-03 | 2016-02-03 | 长安大学 | System and method for predicting tumble risk of old people |
CN106919892A (en) * | 2015-12-25 | 2017-07-04 | 中国移动通信集团公司 | Behavior monitoring method and device |
CN106683340A (en) * | 2016-12-15 | 2017-05-17 | 歌尔股份有限公司 | User behavior monitoring method and wearable equipment |
CN107174255A (en) * | 2017-06-15 | 2017-09-19 | 西安交通大学 | Three-dimensional gait information gathering and analysis method based on Kinect somatosensory technology |
Non-Patent Citations (1)
Title |
---|
仇森: ""人体步态分析的多传感器数据融合研究"", 《中国博士学位论文全文数据库(信息科技辑)》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109118081A (en) * | 2018-08-08 | 2019-01-01 | 成都保源酷码科技有限公司 | A kind of operation safety supervisory systems and method based on image procossing mode |
CN109118081B (en) * | 2018-08-08 | 2021-07-16 | 成都保源酷码科技有限公司 | Operation safety supervision system and method based on image processing mode |
CN109492595A (en) * | 2018-11-19 | 2019-03-19 | 浙江传媒学院 | Behavior prediction method and system suitable for fixed group |
CN111243369A (en) * | 2020-01-16 | 2020-06-05 | 西安科技大学 | Container type fire-fighting hidden danger accident recurrence experience training system |
CN115065585A (en) * | 2022-04-29 | 2022-09-16 | 北京达佳互联信息技术有限公司 | Business abnormity monitoring method and device, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN108281203B (en) | 2021-10-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108281203A (en) | A kind of prediction technique and device of abnormal behaviour | |
CN106485871B (en) | System and method for providing early prediction and prediction of false alarms by applying statistical inference models | |
CN108965826B (en) | Monitoring method, monitoring device, processing equipment and storage medium | |
JP7288688B2 (en) | Systems and methods for identifying vaping and bullying | |
US7552030B2 (en) | System and method for learning patterns of behavior and operating a monitoring and response system based thereon | |
US8606913B2 (en) | Method for adaptively building a baseline behavior model | |
CN108614989B (en) | A kind of old man's intelligent monitor method, system and medium based on WiFi | |
US20120019353A1 (en) | Systems and Methods for Automatically Activating Monitoring Systems | |
EP2096610A1 (en) | Remote monitoring thresholds | |
CN103530978A (en) | Special population-oriented danger sensing and alarming system | |
CN109920192A (en) | Fire alarm method, system and computer readable storage medium | |
WO2015127491A1 (en) | Monitoring system | |
KR20130039625A (en) | Method and apparatus for circadian life pattern modeling and anomaly detection for living alone | |
US8471712B2 (en) | Detecting abnormal time intervals | |
US11984009B2 (en) | Fall detection | |
CN105959184A (en) | Smart indoor air purification system | |
CN106092133A (en) | Start the decision method of guest mode, device | |
CN111466918A (en) | Abnormal behavior detection method and device, computer equipment and storage medium | |
JP7127301B2 (en) | ABNORMAL SENSOR DETECTION METHOD, ABNORMAL SENSOR DETECTION SYSTEM AND INFORMATION PROCESSING DEVICE | |
GB2608639A (en) | Threat assessment system | |
CN114730518A (en) | System and method for monitoring individuals | |
KR20210099720A (en) | Artificial Intelligence-based Method and system for sensing falling accident using acceleration sensor and gyro sensor | |
WO2017109910A1 (en) | Electronic device, determination method, and determination program | |
US11950900B2 (en) | Method and system for frailty detection | |
KR20110065927A (en) | System and method for chenking user's health by means of iptv, and apparatusapplied to the same |
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 |