CN106919892A - Behavior monitoring method and device - Google Patents
Behavior monitoring method and device Download PDFInfo
- Publication number
- CN106919892A CN106919892A CN201510997343.4A CN201510997343A CN106919892A CN 106919892 A CN106919892 A CN 106919892A CN 201510997343 A CN201510997343 A CN 201510997343A CN 106919892 A CN106919892 A CN 106919892A
- Authority
- CN
- China
- Prior art keywords
- parameter
- sensor
- monitored
- behavior
- testing result
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Emergency Alarm Devices (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a kind of behavior monitoring method and device, methods described includes：It is determined that when the first sensor being arranged in the first space detects the action of object to be monitored, triggering second sensor is detected to the first parameter in first space, obtains the testing result of first parameter；Testing result no less than first parameter obtained in the time period of the first setting duration is compared with reference to testing result, when comparison result characterizes degree of fitting reaches given threshold, determines that the first behavior of the object to be monitored occurs；When determining that the first behavior of the object to be monitored occurs duration more than the second setting duration, outputting alarm information.
Description
Technical field
The present invention relates to behavior monitoring technology, more particularly to a kind of behavior monitoring method and device.
Background technology
Technology based on video monitoring more than existing Human bodys' response technology is realized, gathered by video equipment
Data are analyzed by data using image processing algorithm, so that the behavior of identifying user.Known by video
It is inadequate that the mode of other user behavior can cause privacy of user to be protected, and image processing algorithm is complicated, and hardware cost is high,
To realize the identification of careful behavior, it is necessary to lay substantial amounts of video monitoring equipment, also, video identification is used
The recognition accuracy of family behavior is low, and easily light is influenceed by building structure and within doors for the validity of recognition result.
In view of the foregoing, Video Supervision Technique is difficult to be advised greatly in the application of real Human bodys' response
The popularization of mould.
The content of the invention
In order to solve the above technical problems, the embodiment of the invention provides a kind of behavior monitoring method and device.
A kind of behavior monitoring method, methods described includes：
It is determined that when the first sensor being arranged in the first space detects the action of object to be monitored, triggering the
Two sensors detect to the first parameter in first space, obtain the detection knot of first parameter
Really；
By no less than the testing result of first parameter obtained in the time period of the first setting duration and reference
Testing result is compared, and when comparison result characterizes degree of fitting reaches given threshold, is determined described to be monitored
First behavior of object occurs；
When determining that the first behavior of the object to be monitored occurs duration more than the second setting duration, outputting alarm
Information.
In the embodiment of the present invention, methods described also includes：
It is no less than in the time period of the first setting duration described, it is determined that the first biography being arranged in second space
When sensor detects the action of object to be monitored, determine that the object to be monitored does not occur the first behavior, make institute
State second sensor and stop detection work.
In the embodiment of the present invention, methods described also includes：
When comparison result characterizes degree of fitting is not up to given threshold, continue to obtain the detection of first parameter
As a result, and continue will be no less than first setting duration time period in obtain first parameter detection knot
Fruit is compared with reference to testing result, and comparison result characterizes degree of fitting and is not up to given threshold all the time, and
It is determined that the first sensor being arranged in other spaces is not detected by the action of object to be monitored all the time, when continuing
When length is more than the 3rd setting duration, outputting alarm information.
In the embodiment of the present invention, methods described also includes：
In setting cycle, when the first behavior of the object to be monitored occurs, second sensor pair is triggered
The first parameter in first space is detected；
Using the testing result of the first parameter in the setting cycle as training sample, calculated using supervised learning
Least square integration method in method is fitted to the testing result of the first parameter in the setting cycle, obtains
The first parameter described in the first behavior generating process of the object to be monitored in first space anaplasia at any time
The tendency information of change, the tendency information that first parameter is changed over time is used as the reference testing result.
In the embodiment of the present invention, the first sensor includes passive infrared pir sensor；
The second sensor includes humidity sensor.
A kind of behavior monitoring device, described device includes：First determining unit, trigger element, acquiring unit,
Comparison unit, judging unit and output unit, wherein：
First determining unit, whether the first sensor for determining to be arranged in the first space detects is waited to supervise
The action of object is surveyed, when detecting the action of the object to be monitored, the trigger element is triggered；
Trigger element, detects for triggering second sensor to the first parameter in first space；
Acquiring unit, the testing result of first parameter for obtaining the second sensor；
Comparison unit, for by no less than first parameter obtained in the time period of the first setting duration
Testing result is compared with reference to testing result, when comparison result characterizes degree of fitting reaches given threshold,
Determine that the first behavior of the object to be monitored occurs；
Judging unit, the first behavior for judging the object to be monitored occurs whether duration sets more than second
Timing is long, and the output unit is triggered during more than the described second setting duration；
Output unit, for outputting alarm information.
In the embodiment of the present invention, described device also includes：Second determining unit and stop element, wherein：
Second determining unit, for being no less than in the time period of the first setting duration described, it is determined that being arranged at
When first sensor in second space detects the action of object to be monitored, the object to be monitored is determined not
There is the first behavior, trigger the stop element；
Stop element, for making the second sensor stop detection work.
In the embodiment of the present invention, described device also includes：3rd determining unit；
When the comparison result of the comparison unit characterizes degree of fitting is not up to given threshold, continue to trigger described
Acquiring unit obtains the testing result of first parameter, and continue to trigger the comparing unit will be no less than the
The testing result of first parameter obtained in the time period of one setting duration is compared with reference to testing result
It is right, and comparison result characterizes degree of fitting and is not up to given threshold all the time, and it is true by the 3rd determining unit
Surely the first sensor being arranged in other spaces is not detected by the action of object to be monitored, duration all the time
During more than the 3rd setting duration, the output unit outputting alarm information is triggered.
In the embodiment of the present invention, described device also includes：
Training unit, in setting cycle, when the first behavior of the object to be monitored occurs, touching
Hair second sensor is detected to the first parameter in first space；By in the setting cycle
The testing result of one parameter as training sample, using the least square integration method in supervised learning algorithm to institute
The testing result for stating the first parameter in setting cycle is fitted, and obtains the first row of the object to be monitored
The tendency information that the first parameter described in generating process in the first space is changed over time, by described first
The tendency information that parameter is changed over time is used as the reference testing result.
In the embodiment of the present invention, the first sensor includes passive infrared pir sensor；
The second sensor includes humidity sensor.
Behavior monitoring method and device provided in an embodiment of the present invention, by pir sensor etc. to be monitored right
As being detected, to determine whether object to be monitored is located in setting space, when detecting object to be monitored position
When setting in space, the behavior that unlatching other sensors treat monitoring object is detected, is treated when detecting
During certain behavior of monitoring object, the duration to the behavior is detected, defeated when beyond given threshold
Go out corresponding warning information.Corresponding warning information can be exported to specific object, such as with object to be monitored
Related user.The technical scheme of the embodiment of the present invention recognizes the behavior of object to be monitored using non-intruding mode,
The privacy of object to be monitored is protected, and is detected using the behavior that sensor treats monitoring object, reduced
The difficulty and system deployment cost of recognizer, and improve identification certainty.
Brief description of the drawings
Fig. 1 is the schematic flow sheet of the behavior monitoring method of the embodiment of the present invention one；
Fig. 2 is the structural representation of the behavior monitoring system of the embodiment of the present invention；
Fig. 3 is the schematic flow sheet of the behavior monitoring method of the embodiment of the present invention two；
Fig. 4 is the behavioral parameters statistics schematic diagram of the object to be monitored of the embodiment of the present invention；
Fig. 5 is the structure composition schematic diagram of the behavior monitoring device of the embodiment of the present invention.
Specific embodiment
The characteristics of in order to more fully hereinafter understand the embodiment of the present invention and technology contents, below in conjunction with the accompanying drawings
Realization to the embodiment of the present invention is described in detail, appended accompanying drawing purposes of discussion only for reference, is not used for
Limit the embodiment of the present invention.
Fig. 1 is the schematic flow sheet of the behavior monitoring method of the embodiment of the present invention one, as shown in figure 1, originally showing
The behavior monitoring method of example is comprised the following steps：
Step 101：It is determined that the first sensor being arranged in the first space detects the action of object to be monitored
When, triggering second sensor is detected to the first parameter in first space, obtains first ginseng
Several testing results.
In the embodiment of the present invention, first sensor is sensed including passive infrared (PIR, Passive InfraRed)
Device etc.；Second sensor is including humidity sensor etc..
First space can be including toilet, bathroom etc..Object to be monitored includes handicapped old man, disease
The objects such as people.Because object to be monitored is handicapped, it is necessary to be supervised into the behavior in particular space to it
Survey, it is to avoid occur unexpected.Belong to the place of secret due to Spatial General 6 R to be monitored, if first-class using imaging
Mode is monitored, it will causing the right of privacy of object to be monitored can not be effectively ensured.Therefore, the present invention is real
Apply in example by way of sensor is set, the monitoring of monitoring object is treated in realization.
The embodiment of the present invention, after object to be monitored is detected into bathroom or toilet, opens humidity sensor
Device is treated monitoring object and is detected, when detecting object to be monitored and such as being had a bath, will be to be monitored right
The bathing duration of elephant is detected, when the bathing duration for detecting object to be monitored exceeds given threshold, will
Outputting alarm information.
Step 102：By no less than the detection of first parameter obtained in the time period of the first setting duration
Result is compared with reference to testing result, when comparison result characterizes degree of fitting reaches given threshold, it is determined that
First behavior of the object to be monitored occurs.
In the embodiment of the present invention, the testing result of the first parameter got by second sensor, to ensure
The accuracy of object behavior to be monitored detection, it is necessary to obtain the testing result of the first parameter in a period of time,
And the testing result of the first parameter in a period of time is compared with reference to testing result, work as comparison result
When sign degree of fitting reaches given threshold, determine that the corelation behaviour of the object to be monitored occurs.Such as determine to use
After family enters bathroom, reference data of the humidity data in a few minutes of collection before is intended
Close, work as coefficient R2>When 70%, then judge that user is having a bath.Work as coefficient R2<When 70%, then sentence
Determine user do not having a bath.In the embodiment of the present invention, given threshold can be set according to actual conditions,
Could be arranged to 60%, 65%, 75%, 80%, 85% etc..
In the embodiment of the present invention, it is no less than in the time period of the first setting duration described, it is determined that being arranged at
When first sensor in two spaces detects the action of object to be monitored, determine that the object to be monitored is not sent out
Raw first behavior, makes the second sensor stop detection work.When it is determined that object to be monitored is had a bath
, it is necessary to close the testing equipment of the relevant parameters such as depth transducer during etc. behavior to be monitored.
In setting cycle, when the first behavior of the object to be monitored occurs, second sensor pair is triggered
The first parameter in first space is detected；
Using the testing result of the first parameter in the setting cycle as training sample, calculated using supervised learning
Least square integration method in method is fitted to the testing result of the first parameter in the setting cycle, obtains
The first parameter described in the first behavior generating process of the object to be monitored in first space anaplasia at any time
The tendency information of change, the tendency information that first parameter is changed over time is used as the reference testing result.
The first parameter that behavior of the embodiment of the present invention by treating monitoring object is produced is counted, and forms training number
According to obtain the accuracy of the reference testing result of object to be monitored as far as possible, to be accurately judged to wait to supervise
Survey whether object there occurs behavior to be monitored.
Step 103：It is defeated when determining that the first behavior of object to be monitored occurs duration more than the second setting duration
Go out warning information.
In the embodiment of the present invention, when it is determined that the first behavior of object to be monitored that duration occurs is more long and exceeded not
During reasonable duration, by outputting alarm information.Warning information can be exported directly, it is also possible to third party such as 999
Center, guardian of object to be monitored etc. send.
In the embodiment of the present invention, methods described also includes：
When comparison result characterizes degree of fitting is not up to given threshold, continue to obtain the detection of first parameter
As a result, and continue will be no less than first setting duration time period in obtain first parameter detection knot
Fruit is compared with reference to testing result, and comparison result characterizes degree of fitting and is not up to given threshold all the time, and
It is determined that the first sensor being arranged in other spaces is not detected by the action of object to be monitored all the time, when continuing
When length is more than the 3rd setting duration, outputting alarm information.I.e. when object to be monitored is entered in the first space,
But there is no behavior to be detected, and the duration that object to be monitored is stopped in the first space is not beyond conforming to
The duration of reason, will equally understand outputting alarm information.
Below by way of example, the essence of embodiment technical scheme that the present invention is furture elucidated.
Fig. 2 is the structural representation of the behavior monitoring system of the embodiment of the present invention, as shown in Fig. 2 of the invention
The behavior monitoring system of embodiment include humidity sensor, pir sensor, processing terminal, memory,
Application server and alarm object output such as PC, cell-phone customer terminal or 999 centers etc..The embodiment of the present invention is only
Related description is carried out with the structure shown in Fig. 2, is not intended to limit the scope of the present invention.It is of the invention real
Apply in example, will be monitoring behavior so that whether user has a bath, determine user behavior whether beyond unreasonable duration.
The function of each several part component is described as follows in the behavior monitoring system of the embodiment of the present invention：
Humidity sensor, for measuring the relative humidity in air.As humidity sensor be mountable to bathroom or
Toilet.
Whether pir sensor, passive type Infrared Detectors, detectable human body has activity.Sensed by PIR
Device, can monitor whether user enters corresponding monitored area.
Processing terminal, gathers sensing data and transfers data to storage server and application server.This
In inventive embodiments, memory can also be storage server, or be arranged at the storage device in processing terminal
Deng.Business device is deposited, the bathing of historical data and application server transmission for storing each monitoring sensor starts
Time, the information such as end time and bathing duration, and this historical data is transmitted to application server for having a bath
The foundation of unusual determination.Application server, for judging whether monitored target is being washed according to sensing data
Bath, and by the long alarm threshold value of the excavation setting bathtime to historical data.The time-out if user has a bath,
Abnormal information of having a bath then is notified guardian to user etc..PC or cell-phone customer terminal, apply for receiving
The bathing information and abnormal information of server transmission simultaneously notify user.
Fig. 3 is the schematic flow sheet of the behavior monitoring method of the embodiment of the present invention two, as shown in figure 3, originally showing
The behavior monitoring method of example includes following process step：
Detect bathroom pir sensor whether have by nobody to someone signal saltus step event.
If being occurred to the signal saltus step event of someone by nobody, humidity sensor in bathroom is gathered and stored
Data.
In humidity data gatherer process, there is PIR signal to be mutated thing in the event of other rooms of house
Part occurs, then judge that user leaves bathroom, does not there is the behavior of bathing.
In the embodiment of the present invention, behavior monitoring usually is carried out to solitary old man or patient, and working as interior has
, it is necessary to be monitored to user behavior during many people.
In humidity data gatherer process, there is PIR signal to be mutated if there are no other rooms of house
Event occurs, then judge that user also in bathroom, does not leave.
The numerical value of humidity sensor is adopted as the training sample of machine learning during collection user's bathing in 30 days
Data are fitted with the least square integration method in supervised learning algorithm, bathroom is wet during being had a bath
Tendency chart and equation that degree is changed over time, as shown in Figure 4.
After judging that user enters bathroom, learn before the humidity data in a few minutes that will be gathered
The model for obtaining is fitted, and checks fitting result, works as coefficient R2>When 70%, then judge that user exists
Have a bath.Work as coefficient R2<When 70%, then judge that user is not having a bath.
User have a bath when, when bathroom pir sensor by someone become nobody signal saltus step event occur when,
If the pir sensor in other rooms of house is occurred by the unmanned signal saltus step event for becoming someone, user is judged
Bathing terminates.
The 30 days time of each user's bathing of statistics, normal distribution fitting is carried out, chooses confidential interval 95%,
So as to set the alarm threshold value of time-out of having a bath.
In the embodiment of the present invention, when it is determined that user does not occur bathing behavior, and its time for staying in bathroom is not
Rational length is not had a bath in bathroom such as and has treated 15 minutes, then same outputting alarm information, to be monitored to facilitate
The guardian of user takes corresponding measure in time, prevents object to be monitored from occurring unexpected.
Fig. 5 is the structure composition schematic diagram of the behavior monitoring device of the embodiment of the present invention, as shown in figure 5, this
The behavior monitoring device of inventive embodiments includes：First determining unit 50, trigger element 51, acquiring unit
52nd, comparison unit 53, judging unit 54 and output unit 55, wherein：
First determining unit 50, whether the first sensor for determining to be arranged in the first space detects is treated
The action of monitoring object, when detecting the action of the object to be monitored, triggers the trigger element 51；
Trigger element 51, examines for triggering second sensor to the first parameter in first space
Survey；
Acquiring unit 52, the testing result of first parameter for obtaining the second sensor；
Comparison unit 53, for by no less than first parameter obtained in the time period of the first setting duration
Testing result with compare with reference to testing result, when comparison result characterizes degree of fitting reaches given threshold,
Determine that the first behavior of the object to be monitored occurs；
Whether there is duration more than second in judging unit 54, the first behavior for judging the object to be monitored
Setting duration, the output unit is triggered during more than the described second setting duration；
Output unit 55, for outputting alarm information.
On the basis of the behavior monitoring device shown in Fig. 5, the behavior monitoring device of the embodiment of the present invention is also wrapped
Include：Second determining unit (not shown in Fig. 5) and stop element (not shown in Fig. 5), wherein：
Second determining unit, for being no less than in the time period of the first setting duration described, it is determined that being arranged at
When first sensor in second space detects the action of object to be monitored, the object to be monitored is determined not
There is the first behavior, trigger the stop element；
Stop element, for making the second sensor stop detection work.
On the basis of the behavior monitoring device shown in Fig. 5, the behavior monitoring device of the embodiment of the present invention is also wrapped
Include：3rd determining unit (not shown in Fig. 5)；
When the comparison result of the comparison unit 53 characterizes degree of fitting is not up to given threshold, continue to trigger institute
State acquiring unit 52 and obtain the testing result of first parameter, and continue to trigger the general of the comparing unit 53
The testing result of first parameter obtained in the time period no less than the first setting duration is tied with reference to detection
Fruit is compared, and comparison result characterizes degree of fitting and is not up to given threshold all the time, and true by the described 3rd
Order unit determines that the first sensor being arranged in other spaces is not detected by the action of object to be monitored all the time,
When duration is more than the 3rd setting duration, the outputting alarm information of output unit 55 is triggered.
On the basis of the behavior monitoring device shown in Fig. 5, the behavior monitoring device of the embodiment of the present invention is also wrapped
Include：Training unit (not shown in Fig. 5), in setting cycle, when the first of the object to be monitored
When behavior occurs, triggering second sensor is detected to the first parameter in first space；Will be described
The testing result of the first parameter in setting cycle as training sample, using the minimum in supervised learning algorithm
Two product algorithms are fitted to the testing result of the first parameter in the setting cycle, wait to supervise described in acquisition
Survey the trend letter that the first parameter described in the first behavior generating process of object in the first space is changed over time
Breath, the tendency information that first parameter is changed over time is used as the reference testing result.
In the embodiment of the present invention, the first sensor includes passive infrared pir sensor；
The second sensor includes humidity sensor.
It will be appreciated by those skilled in the art that above-mentioned each unit realizes that function can refer to foregoing embodiments
The associated description of behavior monitoring method and understand.The function of above-mentioned each unit can be by running in processing module
Program and realize, can also be realized by specific logic circuit.
Between technical scheme described in the embodiment of the present invention, in the case where not conflicting, can be in any combination.
In several embodiments provided by the present invention, it should be understood that disclosed method and smart machine,
Can realize by another way.Apparatus embodiments described above are only schematical, for example,
The division of the unit, only a kind of division of logic function, can there is other division side when actually realizing
Formula, such as：Multiple units or component can be combined, or be desirably integrated into another system, or some features can
To ignore, or do not perform.In addition, the coupling or straight each other of shown or discussed each part
Connect coupling or communication connection can be the INDIRECT COUPLING or communication connection of equipment or unit by some interfaces,
Can be electrical, machinery or other forms.
It is above-mentioned as separating component illustrate unit can be or may not be it is physically separate, as
The part that unit shows can be or may not be physical location, you can positioned at a place, also may be used
To be distributed on multiple NEs；Part or all of unit therein can be according to the actual needs selected
Realize the purpose of this embodiment scheme.
In addition, each functional unit in various embodiments of the present invention can be fully integrated into a second processing list
In unit, or each unit is individually as a unit, it is also possible to two or more unit collection
Into in a unit；Above-mentioned integrated unit can both be realized in the form of hardware, it would however also be possible to employ hard
Part adds the form of SFU software functional unit to realize.
The above, specific embodiment only of the invention, but protection scope of the present invention is not limited to
This, any one skilled in the art the invention discloses technical scope in, can readily occur in
Change or replacement, should all be included within the scope of the present invention.
Claims (10)
1. a kind of behavior monitoring method, it is characterised in that methods described includes：
It is determined that when the first sensor being arranged in the first space detects the action of object to be monitored, triggering the
Two sensors detect to the first parameter in first space, obtain the detection knot of first parameter
Really；
By no less than the testing result of first parameter obtained in the time period of the first setting duration and reference
Testing result is compared, and when comparison result characterizes degree of fitting reaches given threshold, is determined described to be monitored
First behavior of object occurs；
When determining that the first behavior of the object to be monitored occurs duration more than the second setting duration, outputting alarm
Information.
2. behavior monitoring method according to claim 1, it is characterised in that methods described also includes：
It is no less than in the time period of the first setting duration described, it is determined that the first biography being arranged in second space
When sensor detects the action of object to be monitored, determine that the object to be monitored does not occur the first behavior, make institute
State second sensor and stop detection work.
3. behavior monitoring method according to claim 1 and 2, it is characterised in that methods described is also wrapped
Include：
When comparison result characterizes degree of fitting is not up to given threshold, continue to obtain the detection of first parameter
As a result, and continue will be no less than first setting duration time period in obtain first parameter detection knot
Fruit is compared with reference to testing result, and comparison result characterizes degree of fitting and is not up to given threshold all the time, and
It is determined that the first sensor being arranged in other spaces is not detected by the action of object to be monitored all the time, when continuing
When length is more than the 3rd setting duration, outputting alarm information.
4. behavior monitoring method according to claim 1, it is characterised in that methods described also includes：
In setting cycle, when the first behavior of the object to be monitored occurs, second sensor pair is triggered
The first parameter in first space is detected；
Using the testing result of the first parameter in the setting cycle as training sample, calculated using supervised learning
Least square integration method in method is fitted to the testing result of the first parameter in the setting cycle, obtains
The first parameter described in the first behavior generating process of the object to be monitored in first space anaplasia at any time
The tendency information of change, the tendency information that first parameter is changed over time is used as the reference testing result.
5. the behavior monitoring method according to any one of Claims 1-4, it is characterised in that described
One sensor includes passive infrared pir sensor；
The second sensor includes humidity sensor.
6. a kind of behavior monitoring device, it is characterised in that described device includes：First determining unit, triggering
Unit, acquiring unit, comparison unit, judging unit and output unit, wherein：
First determining unit, whether the first sensor for determining to be arranged in the first space detects is waited to supervise
The action of object is surveyed, when detecting the action of the object to be monitored, the trigger element is triggered；
Trigger element, detects for triggering second sensor to the first parameter in first space；
Acquiring unit, the testing result of first parameter for obtaining the second sensor；
Comparison unit, for by no less than first parameter obtained in the time period of the first setting duration
Testing result is compared with reference to testing result, when comparison result characterizes degree of fitting reaches given threshold,
Determine that the first behavior of the object to be monitored occurs；
Judging unit, the first behavior for judging the object to be monitored occurs whether duration sets more than second
Timing is long, and the output unit is triggered during more than the described second setting duration；
Output unit, for outputting alarm information.
7. behavior monitoring device according to claim 6, it is characterised in that described device also includes：
Second determining unit and stop element, wherein：
Second determining unit, for being no less than in the time period of the first setting duration described, it is determined that being arranged at
When first sensor in second space detects the action of object to be monitored, the object to be monitored is determined not
There is the first behavior, trigger the stop element；
Stop element, for making the second sensor stop detection work.
8. the behavior monitoring device according to claim 6 or 7, it is characterised in that described device is also wrapped
Include：3rd determining unit；
When the comparison result of the comparison unit characterizes degree of fitting is not up to given threshold, continue to trigger described
Acquiring unit obtains the testing result of first parameter, and continue to trigger the comparing unit will be no less than the
The testing result of first parameter obtained in the time period of one setting duration is compared with reference to testing result
It is right, and comparison result characterizes degree of fitting and is not up to given threshold all the time, and it is true by the 3rd determining unit
Surely the first sensor being arranged in other spaces is not detected by the action of object to be monitored, duration all the time
During more than the 3rd setting duration, the output unit outputting alarm information is triggered.
9. behavior monitoring device according to claim 6, it is characterised in that described device also includes：
Training unit, in setting cycle, when the first behavior of the object to be monitored occurs, touching
Hair second sensor is detected to the first parameter in first space；By in the setting cycle
The testing result of one parameter as training sample, using the least square integration method in supervised learning algorithm to institute
The testing result for stating the first parameter in setting cycle is fitted, and obtains the first row of the object to be monitored
The tendency information that the first parameter described in generating process in the first space is changed over time, by described first
The tendency information that parameter is changed over time is used as the reference testing result.
10. the behavior monitoring device according to any one of claim 6 to 9, it is characterised in that described
First sensor includes passive infrared pir sensor；
The second sensor includes humidity sensor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510997343.4A CN106919892B (en) | 2015-12-25 | 2015-12-25 | Behavior monitoring method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510997343.4A CN106919892B (en) | 2015-12-25 | 2015-12-25 | Behavior monitoring method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106919892A true CN106919892A (en) | 2017-07-04 |
| CN106919892B CN106919892B (en) | 2020-07-07 |
Family
ID=59455737
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510997343.4A Active CN106919892B (en) | 2015-12-25 | 2015-12-25 | Behavior monitoring method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106919892B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108281203A (en) * | 2018-02-28 | 2018-07-13 | 泰康保险集团股份有限公司 | A kind of prediction technique and device of abnormal behaviour |
| CN108494856A (en) * | 2018-03-21 | 2018-09-04 | 耘申信息科技（上海）有限公司 | A kind of management method and system of space service condition |
| CN110765967A (en) * | 2019-10-30 | 2020-02-07 | 腾讯科技（深圳）有限公司 | Action recognition method based on artificial intelligence and related device |
| CN111306803A (en) * | 2020-03-01 | 2020-06-19 | 苏州淘喜网络科技有限公司 | Water source supply control system and method based on big data |
| CN113357771A (en) * | 2021-05-28 | 2021-09-07 | 青岛海尔空调器有限总公司 | Air conditioner control method based on movable wearable device and movable wearable device |
| CN116110193A (en) * | 2023-03-29 | 2023-05-12 | 中国铁塔股份有限公司 | Intelligent nursing method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103325080A (en) * | 2013-06-21 | 2013-09-25 | 电子科技大学 | Gerocamium intelligent nursing system and method based on Internet of Things technology |
| CN104112331A (en) * | 2014-01-07 | 2014-10-22 | 芜湖美的厨卫电器制造有限公司 | Method and system for performing safety alarm via water heater, and water heater |
| CN104376694A (en) * | 2013-08-13 | 2015-02-25 | 联想(北京)有限公司 | Monitoring method, electronic device and system |
| CN204576766U (en) * | 2015-03-26 | 2015-08-19 | 郭天铭 | Be exclusively used in the overtime reminiscences in toilet |
| CN105046883A (en) * | 2015-08-14 | 2015-11-11 | 上海正苒智能科技有限公司 | Monitoring and alarming system and method |
-
2015
- 2015-12-25 CN CN201510997343.4A patent/CN106919892B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103325080A (en) * | 2013-06-21 | 2013-09-25 | 电子科技大学 | Gerocamium intelligent nursing system and method based on Internet of Things technology |
| CN104376694A (en) * | 2013-08-13 | 2015-02-25 | 联想(北京)有限公司 | Monitoring method, electronic device and system |
| CN104112331A (en) * | 2014-01-07 | 2014-10-22 | 芜湖美的厨卫电器制造有限公司 | Method and system for performing safety alarm via water heater, and water heater |
| CN204576766U (en) * | 2015-03-26 | 2015-08-19 | 郭天铭 | Be exclusively used in the overtime reminiscences in toilet |
| CN105046883A (en) * | 2015-08-14 | 2015-11-11 | 上海正苒智能科技有限公司 | Monitoring and alarming system and method |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108281203A (en) * | 2018-02-28 | 2018-07-13 | 泰康保险集团股份有限公司 | A kind of prediction technique and device of abnormal behaviour |
| CN108281203B (en) * | 2018-02-28 | 2021-10-22 | 泰康保险集团股份有限公司 | Method and device for predicting abnormal behavior |
| CN108494856A (en) * | 2018-03-21 | 2018-09-04 | 耘申信息科技（上海）有限公司 | A kind of management method and system of space service condition |
| CN108494856B (en) * | 2018-03-21 | 2022-03-11 | 耘申信息科技（上海）有限公司 | Space use condition management method and system |
| CN110765967A (en) * | 2019-10-30 | 2020-02-07 | 腾讯科技（深圳）有限公司 | Action recognition method based on artificial intelligence and related device |
| CN110765967B (en) * | 2019-10-30 | 2022-04-22 | 腾讯科技（深圳）有限公司 | Action recognition method based on artificial intelligence and related device |
| CN111306803A (en) * | 2020-03-01 | 2020-06-19 | 苏州淘喜网络科技有限公司 | Water source supply control system and method based on big data |
| CN113357771A (en) * | 2021-05-28 | 2021-09-07 | 青岛海尔空调器有限总公司 | Air conditioner control method based on movable wearable device and movable wearable device |
| CN116110193A (en) * | 2023-03-29 | 2023-05-12 | 中国铁塔股份有限公司 | Intelligent nursing method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106919892B (en) | 2020-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106919892A (en) | Behavior monitoring method and device | |
| US8138882B2 (en) | Securing premises using surfaced-based computing technology | |
| Dahmen et al. | Smart secure homes: a survey of smart home technologies that sense, assess, and respond to security threats | |
| CN105354956B (en) | The cloud computing platform and method analyzed based on data mining and big data | |
| CA2438834A1 (en) | Real-time spatio-temporal coherence estimation for autonomous mode identification and invariance tracking | |
| CN107422643A (en) | Smart home monitoring method and system based on vibration detection | |
| KR101069001B1 (en) | Apparatus and method for detecting falldown | |
| JP2021119469A (en) | Monitoring system | |
| EP1968023A2 (en) | System and method for premises monitoring using weight detection | |
| CN105608838A (en) | Monitoring system and method | |
| CN105632058A (en) | Intelligent alarm method and alarm system based on human body infrared characteristic human body identification | |
| CN106796746A (en) | Activity monitoring approach and system | |
| CN107146386A (en) | A kind of anomaly detection method and device, user equipment | |
| CN107067640A (en) | A kind of intellectual communityintellectualized village's safety protecting method and system | |
| US20160117918A1 (en) | Intrusion sensor for monitoring an entrance to a building to be monitored, and method | |
| CN106599802A (en) | Intelligent corridor monitoring system based on cloud technology | |
| CN115984767A (en) | Abnormity early warning method and system based on real-time analysis of monitoring picture | |
| CN105151938A (en) | Elevator video monitoring device and method | |
| CN110942541A (en) | Control system and control method of anti-following linkage door | |
| CN113326492A (en) | Air conditioning system control method and device, electronic equipment and storage medium | |
| JP6604199B2 (en) | Vibration analysis system, vibration analysis apparatus, and vibration analysis method | |
| CN205451392U (en) | Monitor system | |
| KR20220113631A (en) | Dangerous situation detection device and dangerous situation detection method | |
| CN104809840A (en) | Intrusion detection method and system based on multiple sensors | |
| CN108648417A (en) | Raspberry Pi old man based on deep learning falls down detecting system |
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 |