CN110136832A - A kind of cognitive ability assessment system and method based on the elderly's daily behavior - Google Patents
A kind of cognitive ability assessment system and method based on the elderly's daily behavior Download PDFInfo
- Publication number
- CN110136832A CN110136832A CN201910421469.5A CN201910421469A CN110136832A CN 110136832 A CN110136832 A CN 110136832A CN 201910421469 A CN201910421469 A CN 201910421469A CN 110136832 A CN110136832 A CN 110136832A
- Authority
- CN
- China
- Prior art keywords
- user
- behavior
- server
- cognitive ability
- client
- 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
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B21/00—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant
- G01B21/22—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring angles or tapers; for testing the alignment of axes
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
- G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Alarm Systems (AREA)
- Emergency Alarm Devices (AREA)
Abstract
The present invention relates to a kind of cognitive ability assessment systems and method based on the elderly's daily behavior, the system includes server and several behavior sensors, wherein, the server acquires the behavioral data with the daily behavior of user-association several behavior sensors in the living space for being deployed in user in a manner of implicitly perceiving；The server is scored according at least to the cognitive ability of the behavioral data assessment user of the daily behavior with user-association with the cognitive ability for obtaining user, the present invention realizes the behavioral data long term monitoring to old man by cognition technology, and then assessment of the realization to old man's cognitive ability, without the cognitive ability for continually assessing user by cognitive disorder Screening Scale, mitigate bothering for the daily life to user, reduces the labor intensity of medical staff.
Description
Technical field
The present invention relates to the building field of database, the machine learning being related in artificial intelligence field, more particularly to it is a kind of
Cognitive ability assessment system and method based on the elderly's daily behavior.
Background technique
The assessment for the cognitive ability of old man relies primarily on cognitive disorder Screening Scale at present, by staff to old
People evaluates and tests, and then realizes and assess the cognitive ability of old man.But there are the following problems for traditional scale assessment, pays a return visit
Time interval is longer, it is difficult to realize regular return visit；The assessment time is longer, requires staff high, it is difficult to realize a wide range of general
And；The low old man of education level is difficult to complete most of evaluation and test content etc..
Design a kind of cognition assessment system in patent of invention CN106327049A, including information module, test module and point
Analyse module；Information module is used for the data according to object, obtains the medical information to match with test module, and foundation is completely recognized
Know assessment database；Test module obtains the recognition tests data of object by test, includes following five submodules: attention
With execution functional test module, recall tests module, mathematics and computing capability test module, language testing module, movement and row
For control and scenario test module；The cognition that the medical information and test module that analysis module is obtained according to information module obtain
Test data determines the cognition assessment result of object.But the invention, which measures realization cognition there is still a need for staff, to be commented
Estimate, staff is required high, it is difficult to realize automation.Moreover, the cognitive ability decline of old man is one and slowly is difficult to feel
The process examined can not react old man by a cognitive ability scoring that cognitive disorder Screening Scale is assessed twice well
Cognitive ability variation, and as previously mentioned, since cognitive disorder Screening Scale evaluation process exists, time-consuming, to work
The old man that personnel requirement is high, education level is low is difficult to complete most of the problems such as evaluating and testing content, continually passes through cognitive disorder
The cognitive ability variation that Screening Scale is assessed is difficult operation.
Therefore, it is necessary to be improved to the prior art.
In addition, the inevitable difference of those skilled in the art and examination department that one side is understood by applicant；Separately
On the one hand due to having studied lot of documents and patent when inventor makes the present invention, but length limit do not enumerate in detail it is all
Details and content, however this feature of the invention absolutely not for not having these prior arts, present invention have been provided with existing skill
All features of art, and applicant retains foundation guidelines for examination relevant regulations and increases related existing skill in the background technology at any time
The right of art.
Summary of the invention
For the deficiencies of the prior art, the present invention provides a kind of, and the cognitive ability based on the elderly's daily behavior assesses system
System and method.Since the cognitive ability decline of user can be embodied among the daily behavior of old man, the present invention passes through perception
Technology realizes the behavioral data long term monitoring to old man, and then realizes the assessment to old man's cognitive ability.Without continually passing through
Cognitive disorder Screening Scale assesses the cognitive ability of user, mitigates bothering for the daily life to user, reduces medical staff's
Labor intensity.
According to a preferred embodiment, a kind of cognitive ability assessment system based on the elderly's daily behavior, the system
Including server and several behavior sensors, wherein if the server is by described in being deployed in the living space of user
Dry behavior sensor acquires the behavioral data with the daily behavior of user-association in a manner of implicitly perceiving；The server is at least
The cognitive ability of user is assessed according to the behavioral data of the daily behavior with user-association to obtain the cognitive ability scoring of user.
According to a preferred embodiment, the cognitive ability that the server periodically compares the corresponding user of current period is commented
Divided the cognitive ability scoring of user corresponding with a upper period, and the server scores under ring ratio in the cognitive ability of user
Drop generates the first warning information when being more than default activation threshold value.
According to a preferred embodiment, the server is according to the cognitive ability of following scoring formula assessment user to obtain
Cognitive ability to user scores:
Wherein, server assessment user cognitive ability with obtain user cognitive ability scoring before, select it is daily
Standard Task X of the corresponding behavioral data of most n behaviors as the cognitive ability for evaluating user is triggered, X=is expressed as
{X1,X2,…,Xn, T is the set that ordinary people completes the standard time of each task in the n task, is expressed as T={ T1,
T2,…,Tn, TiIt is the standard time that ordinary people completes i-th task in the n task, t is that user completes in the n task
The set of the average time of each task is expressed as t={ t1,t2,…,tn, tiIt is that user completes i-th task in the n task
Average time, α is the set that user completes the task completeness of each task in the n task, αiIndicate that user completes the n
The task completeness of i-th task in task, w are the set of the weight of each task in the n task, wiIndicate the n task
In i-th task weight.
According to a preferred embodiment, the behavioral data band with the daily behavior of user-association of the collection of server
Having time attribute, the server is obtained will be with user with foundation time attribute after the behavioral data of the daily behavior of user-association
The behavioral data of associated daily behavior is stored into time series database, and the server is independently established for each user to close therewith
The Hidden Markov Model for being used to predict its behavior of connection, the server use the row related with user in time series database
For the trained Hidden Markov Model with the user-association of data, server is according to the Hidden Markov Model with the user-association
It predicts the predictive behavior of user, and is deviated in the agenda of user and predictive behavior and the deviation will lead to known wind
The second warning information is generated in the case where danger and/or known loss.
According to a preferred embodiment, the system also includes the first client, the first client communication connection
In the server, first client obtains several behavior sensings being arranged in living space as trunking
The behavioral data of device acquisition, the server are asked after generating the second warning information to first client transmission risk verifying
It asks, first client end response is sounded an alarm in the risk checking request, and the alarm is only capable of by user
By can just be released after the verifying of at least two living things feature recognitions in one client, first client is sounded all clear
Afterwards to the server send risk wrong report feedback or risk release feedback, the server in response to risk report by mistake feedback or
Person's risk releases feedback and deletes the second warning information.
According to a preferred embodiment, the system also includes photographic device, the photographic device is communicatively coupled to
One client, the photographic device can be set to outside the access door for passing in and out the living space, and the photographic device is for acquiring the
One photo group and the second photo group, the first photo group are shot before access door is opened, and the second photo group is
Until access door continues to shoot during preset time after closing after introduction is opened, first client is from the camera shooting
Device obtains the first photo group and the second photo group, and first client the first photo group and the second photo group are come
Determine personnel's variable condition in the living space, and first client end response is in the personnel in the living space
Variable condition determines the receiving mode of the personnel accommodated in living space, and the receiving mode includes one of following mode:
Have in living space and the user of only one people of user stays alone mode；Have in living space other staff in addition to the user or
The only guest mode of other staff；With the vacant mode of nobody in living space；Wherein, the first client analyzes institute
The touching originator for the behavioral data that several behavior sensors acquire during guest mode is stated, first client is in guest mode
Retention can not determine the corresponding row of touching originator in the case that the touching originator of the corresponding behavioral data of period acquisition can not determine
For data, and only it can determine that touching originator is the behavior number of user for what several behavior sensors acquired during guest mode
According to being sent to server.Preferably, the length of preset time can be by producer and/or user setting.For example, preset time can be with
It is 1~5s.Specifically, for example, preset time can be 2s, 3s or 4s.I.e., it is assumed that preset time is 2s, the second photo group
The photo shot in a period of 2s after being opened including access door to after closing.
According to a preferred embodiment, several sensors include at least and are installed on going out on access door for identification
Enter the angular displacement sensor of door opening and closing state, the angular displacement sensor for entering and leaving door opening and closing state for identification is communicatively coupled to
The photographic device, the angular displacement sensor for entering and leaving door opening and closing state for identification are configured as in access door towards open
The electric signal for indicating that access door is opened, the photographic device actively are sent to the photographic device immediately when direction rotates 3 °~5 °
Several photos are shot in 1s as the first photo group after receiving the electric signal of access door opening, the access door for identification is opened
The angular displacement sensor of off status is configured as in the case where access door turns to access door towards the direction of closing and completely closes
The electric signal for indicating that access door is closed just is sent to the photographic device, the photographic device is after the completion of the first photo group is shot
Continue to be used as the second photo group during preset time after several photos are continuously shot until receiving the electric signal of access door closing.
According to a preferred embodiment, the system also includes Intelligent bracelet and identification module, server is every
A user distributes a unique identity and simultaneously the identity is stored in Intelligent bracelet, and the Intelligent bracelet is to limited
Communication range in send carry identity electromagnetic wave, each behavior sensor is provided with carries identity for identification
Electromagnetic wave identification module, with detect user wearing Intelligent bracelet to identify behavior sensor acquisition behavior number
According to touching originator, when the first client determines that the receiving mode of the personnel accommodated in living space is the solitary mode of user, institute
It states the behavioral data of the first client reception behavior features sensor acquisition and identification module is not worn user is not detected
The touching originator default definition that behavioral data is collected in the case where wearing Intelligent bracelet is user；In the first client end response in described
Personnel's variable condition in living space determines the receiving mode of the personnel accommodated in living space by the solitary Mode change of user
When for guest mode, the first client instruction user wears the Intelligent bracelet, and the first client reception behavior features pass
Sensor acquisition behavioral data and only by identification module detect user wear Intelligent bracelet in the case where acquire
To behavioral data be determined as triggering person be user behavioral data.
According to a preferred embodiment, the predefined action sequence for meeting user behavior habit is prestored in the server
With the time span of scheduled specific behavior, after the server generates the first warning information, the server is based on the received
Behavior sequence and predefined action sequence phase of the user in current period are analyzed with the behavioral data of the daily behavior of user-association
The accuracy of ratio obtains the first confidence level, and the server divides with the behavioral data of the daily behavior of user-association based on the received
The time span of corresponding specific behavior of the user in current period is analysed compared with the time span of scheduled specific behavior
Second confidence level, the server memory have preset first confidence threshold value and the second confidence threshold value, first confidence
It spends threshold value and is greater than the second confidence threshold value, the server is greater than the first confidence threshold value and the second confidence level in the first confidence level
Determine that first warning information is invalid when greater than the second confidence threshold value, the server is less than or equal to the in the first confidence level
One confidence threshold value and the second confidence level are less than or equal to directly confirm that the first warning information is effective when the second confidence threshold value, described
Server is less than or equal to the first confidence threshold value in the first confidence level and the second confidence level is less than or equal in the second confidence threshold value
One of condition the first warning information is labeled as to the first warning information to be verified when setting up, server waits the first visitor
Next period that family end is sent believes with the behavioral data of the daily behavior of user-association to verify first early warning to be verified
Breath is only assessed when server scores according to the cognitive ability of corresponding user of next period with next period toward the first two period
Corresponding user cognitive ability scoring compared to decrease beyond default activation threshold value when confirm that the first warning information is effective, in institute
Server is stated first warning information is sent to by the other staff other than user when confirming that the first warning information is effective
The second client held.
According to a preferred embodiment, a kind of cognitive ability appraisal procedure based on the elderly's daily behavior, this method
The cognitive ability of user is assessed using foregoing system, which includes server and several behavior sensors, wherein
The server is acquired in a manner of implicitly perceiving several behavior sensors in the living space for being deployed in user
With the behavioral data of the daily behavior of user-association；Behavior number of the server according at least to the daily behavior with user-association
According to the cognitive ability of assessment user to obtain the cognitive ability scoring of user.
Detailed description of the invention
Fig. 1 is the module diagram of a preferred embodiment of system of the invention.
Reference signs list
100: the first client, 200: the second client 300: server
400: behavior sensor 500: photographic device 600: Intelligent bracelet
700: identification module
Specific embodiment
It is described in detail with reference to the accompanying drawing.
Firstly, in invention using to part term be defined:
Implicit perception can refer to that behavior sensor is coupled in the article of living space or on article to touch in user
The behavior of perception user obtains behavioral data when moving or operate these articles.In other words, implicit perception is to carry out day in user
The behavior on article touched by the meeting being coupled in living space by the daily behavior of user during Chang Hangwei passes
Sensor implicitly obtains the perception of the behavioral data of user.This implicitly to perceive initiatively goes test different from user,
User is without deliberately removing triggering behavior sensor when implicit perception, but triggers row in passing during completing daily behavior
Corresponding behavioral data is obtained for sensor.The set-up mode and measurement method of behavior sensor will not bother the daily of user
Behavior.That is, acquisition and user-association in the living space that several behavior sensors are set to user in a manner of interruption-free user
Daily behavior behavioral data.Article for example may include at least one of all kinds of doors, all kinds of switches and all kinds of apparatus.Tool
Body, article may include that interior door, window door, access door, refrigerator doors, door for microwave oven, wardrobe door, water tap, lamp are opened
At least one of pass, hearth switch, power switch, cup for rinsing mouth and washbowl.
Time series database can refer to time series databases.Time series databases are mainly used for referring to that the processing band time marks
Sign and (change according to the sequence of time, i.e. the time serializes) data of time attribute in other words.Band time tag or time belong to
The data of property are also referred to as time series data.
Embodiment 1
Present embodiment discloses a kind of cognitive ability assessment systems based on the elderly's daily behavior, in other words, Yi Zhongji
In the cognitive ability assessment system of user's daily behavior, the system based on time series database assessment cognitive ability a kind of in other words,
The system for assessing cognitive ability a kind of in other words.The system is adapted for carrying out each method and step that the present invention records, to reach
To expected technical effect.In the case where not causing conflict or contradictory situation, the entirety of the preferred embodiment of other embodiments
And/or partial content can be used as the supplement of the present embodiment.
According to a preferred embodiment, referring to attached drawing 1, which may include that server 300 and/or several behaviors pass
Sensor 400.Server 300 can be by several behavior sensors 400 for being set to or be deployed in the living space of user
The behavioral data of acquisition and the daily behavior of user-association.In other words, server 300 can be empty by being deployed in the inhabitation of user
Interior several behavior sensors 400 acquire the behavioral data with the daily behavior of user-association in a manner of implicitly perceiving.It is excellent
Selection of land, behavior sensor 400 may include angular transducer, door status switch sensor, laser sensor, water flow sensor,
In microswitch sensor, pressure sensor, temperature sensor, humidity sensor, intelligent switch and angular transducer at least
One.Server 300 can assess the cognitive ability of user according to the behavioral data of the daily behavior with user-association to obtain
The cognitive ability of user scores.Preferably, server 300 passes through several behavior sensors for being set in the living space of user
400 acquire the behavioral data with the daily behavior of user-association in a manner of implicitly perceiving.Preferably, living space refers to user
Living environment.For example, living space may include at least one of bedroom, parlor, kitchen and lavatory.The present invention uses this
Mode at least can be realized following advantageous effects: first, it is possible to reduce continually assess cognitive ability to the daily of user
Behavior is bothered；Second, the difficulty for persistently obtaining the cognitive ability scoring of user is reduced, to observe the cognitive ability of user for a long time
Variation.
According to a preferred embodiment, server 300 can periodically compare the cognition energy of the corresponding user of current period
The cognitive ability scoring of power scoring user corresponding with a upper period.Server 300 can be in the cognitive ability of user scoring ring
Warning information is generated when than decreaseing beyond default activation threshold value.Preferably, the first warning information can be sent to by server 300
Second client.Preferably, the cognitive ability that server 300 periodically compares the corresponding user of current period scored and a upper period
The compares cycle of the cognitive ability scoring of corresponding user can be artificial settings.Preferably, default activation threshold value can be with people
For setting.For example, default activation threshold value for example can be 5%~60%.I.e., it is assumed that server 300 compares use by the period of day
The cognitive ability at family scores, and default activation threshold value is set to 10%.It is 50 points when the cognitive ability of the previous day user scores, it is modern
The cognitive ability scoring of its user is 38 points, then the cognitive ability scoring ring of user has been more than 10%, has then serviced than decline 24%
Device 300 generates warning information.Preferably, server 300 periodically relatively the cognitive ability scoring of the corresponding user of current period with
The compares cycle of the cognitive ability scoring of upper period corresponding user can have multiple cycle lengths period different from each other.
For example, server 300 can be configured as at least one of day, week, the moon, season and year as the period.For example, server
300 can be configured as the cognitive ability scoring for carrying out more corresponding user using day as the period.For another example, server 300 can be with
It is configured as taking day and week as the cognitive ability scoring for carrying out more corresponding user the period.That is, server 300 both more adjacent two
The cognitive ability scoring of corresponding user in it, also the cognitive ability of corresponding user scores in more adjacent two weeks.Preferably,
Server 300 can periodically compare the cognitive ability of the corresponding user of current period at least two compares cycles different from each other
The cognitive ability scoring of scoring user corresponding with a upper period.Server 300 can be in the cognitive ability of user scoring ring ratio
Warning information is generated when decreaseing beyond default activation threshold value.Different compares cycles can correspond to default triggering different from each other
Threshold value.The corresponding default activation threshold value of compares cycle with longer cycle length can be smaller.For example, server 300 compares
In more adjacent two days when the cognitive ability scoring of corresponding user, corresponding default activation threshold value can be 15%.Server 300
In more adjacent two weeks when the cognitive ability scoring of corresponding user, corresponding default activation threshold value can be 10%.Preferably,
Cycle length can refer to duration contained by a cycle.The present invention at least can be realized following Advantageous effect using this mode
Fruit: first, the present invention, which is regularly handled the behavioral data of the collected user of sensor by server 300, to be compared, with anti-
The variation of the cognitive ability of user is fed out, and server 300 decrease beyond default touching in the cognitive ability scoring ring ratio of user
Warning information is generated when sending out threshold value, the problem of there may be rapid decreases to recognize the cognitive ability level of user；Second,
If constantly going to evaluate the cognitive ability of user daily using existing cognitive disorder Screening Scale, this is almost not
It is in the cards, and the present invention utilizes the cognition energy of the behavioral data evaluation user of the daily collected user abundant of sensor
Power can obtain the cognitive ability of user within the period of different cycle lengths in such a way that multiple periods periodically compare
Variation and timely early warning；Third, in general it is assumed that the cognitive ability of user slowly reduces at any time, then time span is bigger, answers
It is the corresponding default touching of compares cycle with longer cycle length in a conventional manner when cognitive ability reduces more
Hair threshold value is bigger, and still, the present inventor thinks, since cycle length is bigger, data volume is also bigger, and the one of reaction
The scoring of a cognitive ability is also just truer, and error is also smaller, and therefore, the present invention breaks routine, and allowing in server 300 will have more
The corresponding default activation threshold value of the compares cycle of long cycle length is arranged smaller, for example, server 300 more adjacent two days
In corresponding user cognitive ability scoring when, corresponding default activation threshold value is 19%, in server 300 more adjacent two weeks
When the cognitive ability scoring of corresponding user, corresponding default activation threshold value is 16%, the more two neighboring season of server 300
In corresponding user cognitive ability scoring when, corresponding default activation threshold value be 13%, the more two neighboring season of server 300
In degree when the cognitive ability scoring of corresponding user, corresponding default activation threshold value is 10%, to reduce system wrong report, allows this hair
Bright warning information is more acurrate.
According to a preferred embodiment, which may include the first client, Intelligent bracelet 600 and identification mould
At least one of block 700.Server 300 can distribute a unique identity for each user and by the identity
It is stored in Intelligent bracelet 600.Intelligent bracelet 600 can be carried by user.Intelligent bracelet 600 can be to limited communication
The electromagnetic wave for carrying identity is sent in range.Each behavior sensor 400 can be furnished with identification module 700, with
The association user for the behavioral data that identification behavior sensor 400 acquires.It is mobile so that it communicates model with user in Intelligent bracelet 600
It encloses when covering corresponding identification module 700, corresponding identification module 700 is according to the electricity with identity of acquisition
Magnetic wave identifies the identity of user relevant to the collected behavioral data of behavior sensor 400 and generates the letter for having time attribute
Breath.Corresponding first client associate is in the user identified with respective identity.
According to a preferred embodiment, which may include several cameras.Several cameras can be set into
The periphery of the door of the living space of user out.System can be according to the people in the image recognition living space that several cameras acquire
The case where member.System can be ignored and be affected in the case where behavioral data has to be influenced by addition to the user other people
Behavioral data.
According to a preferred embodiment, server 300 can be according to the cognitive ability of following scoring formula assessment user
To obtain the cognitive ability scoring of user:Preferably, cognition of the server 300 in assessment user
Before ability is to obtain the cognitive ability scoring of user, it can choose the corresponding behavioral data of the most n behaviors of daily triggering and make
For the Standard Task X of the cognitive ability for evaluating user, it is expressed as X={ X1,X2,…,Xn}.T can be ordinary people and complete to be somebody's turn to do
The set of the standard time of each task, is expressed as T={ T in n tasks1,T2,…,Tn}。TiIt can be ordinary people and complete the n
The standard time of i-th task in task.T can be the set that user completes the average time of each task in the n task, table
It is shown as t={ t1,t2,…,tn}。tiIt can be the average time that user completes i-th task in the n task.α can be use
Complete the set of the task completeness of each task in the n task in family.αiIt can indicate that user completes in the n task i-th
The task completeness of task.W can be the set of the weight of each task in the n task.wiIt can indicate in the n task
The weight of i tasks.For example, being more than not close the door the regular hour, being at this moment particularly likely that user forgets after user opens the door
Note is closed the door, and the task completeness that switch gate event is completed reduces, the cognitive ability being calculated by cognitive ability scoring formula
Therefore scoring will reduce, if the event of switch gate is one of most n behaviors of the daily triggering of user, can be used use
In the cognitive ability of evaluation user, forget that the number of switch gate is more, cognitive ability scoring is lower.For another example, user is in wash vegetables
During just Guan Shui for a long time, will lead to and complete the event of wash vegetables event and be far more than the time for normally completing wash vegetables, pole has
It may be that user forgets Guan Shui, it, can quilt if the event of switch tap is one of most n behaviors of the daily triggering of user
Using the cognitive ability for evaluating user, the cognitive ability scoring of calculating can also be reduced.The present invention uses the daily triggering of user
The cognitive ability of user is evaluated in most n behaviors, it is possible to reduce is caused because of very few as the derived data evaluated
A small number of, accidental data cause excessive interference to the evaluation of the cognitive ability of user.Preferably, different user is different
Habit, for example, some users may be accustomed to open access door be not related to divulge information.For another example, some users may be accustomed to not making
Taste is dissipated with the door of micro-wave oven is opened when micro-wave oven for a long time.It in using the present invention, can be first of the invention to instruction manual
The code of points of cognitive ability, to allow user can be avoided due to not knowing code of points because personal habits make some cause
There is the event of relatively large deviation in scoring.And after user knows these rules, one can be deliberately made when carrying out some behaviors
A little movements can also embody the cognitive ability of user to obtain higher cognitive ability scoring.Preferably, n may be greater than equal to 1
Integer.N can be by being manually set, for example, being set as 1,2,3 or 4.It, can be according in the living space of user when setting
Depending on the quantity of the behavior sensor of setting, behavior sensor is more, and the value of n can be set bigger.
According to a preferred embodiment, what server 300 acquired can with the behavioral data of the daily behavior of user-association
To have time attribute.It can be according to time attribute after the acquisition of server 300 and the behavioral data of the daily behavior of user-association
The behavioral data of daily behavior with user-association is stored into time series database.Server 300 can be only for each user
It is vertical to establish the Hidden Markov Model for being used to predict its behavior being associated.Server 300 can be used in time series database
The trained Hidden Markov Model with the user-association of behavioral data related with user.Server 300 can according to this
The predictive behavior of the Hidden Markov Model prediction user of user-association.Server can go in the agenda of user and prediction
To deviate and generating the second warning information in the case that the deviation will lead to known risk and/or known loss.
According to a preferred embodiment, system may include the first client 100, the communication connection of the first client 100
In server 300.First client 100 can be used as trunking and obtain several behavior sensors being arranged in living space
The behavioral data of 400 acquisitions.Server 300 is verified after the second warning information can be generated to the first client 100 transmission risk
Request.First client 100 can be sounded an alarm in response to risk checking request.Alarm is only capable of by user in the first client
By can just be released after the verifying of at least two living things feature recognitions on 100.First client 100 can be with after sounding all clear
Risk wrong report feedback is sent to server 300 or risk releases feedback.Server 300 can in response to risk report by mistake feedback or
Person's risk releases feedback and deletes the second warning information.
According to a preferred embodiment, system may include photographic device 500.Photographic device 500 can communicate to connect
In the first client 100.Photographic device 500 can be set to outside the access door of disengaging living space.Photographic device 500 can be used for
Acquire the first photo group and the second photo group.First photo group can be shooting before access door is opened.Second photo group can
To be after access door is opened until continuing to shoot during preset time after access door closing.First client 100 can be with
The first photo group and the second photo group are obtained from photographic device 500.First client 100 can compare the first photo group and second
Photo group determines personnel's variable condition in living space.First client 100 can be in response to the personnel in living space
Variable condition determines the receiving mode of the personnel accommodated in living space.Receiving mode may include one of following mode:
Have in living space and the user of only one people of user stays alone mode；Have in living space other staff in addition to the user or
The only guest mode of other staff；With the vacant mode of nobody in living space.First client 100 can analyze
The touching originator for the behavioral data that several behavior sensors 400 acquire during guest mode.First client 100 can be in visitor
Retention can not determine the corresponding of touching originator in the case that the touching originator of the corresponding behavioral data acquired during mode can not determine
Behavioral data, and only by several behavior sensors 400 acquired during guest mode can determine that touching originator be user row
Server 300 is sent to for data.
Preferably, the length of preset time can be by producer and/or user setting.For example, preset time can be 1~
5s.Specifically, for example, preset time can be 2s, 3s or 4s.I.e., it is assumed that preset time is 2s, and the second photo group includes
The photo that introduction is shot in a period of 2s after opening to after closing.The present invention at least can be realized following beneficial skill using this mode
Art effect: first, in general, the prior art is to pass through 500 collector of photographic device in setting photographic device 500 outdoors
Feature carries out feature identification, and with determination, whether corresponding personnel have the permission entered, but be not related to judgement of the invention
The receiving mode of personnel in living space, the present invention can both guarantee the authenticity of behavioral data using which, can also be with
Reduce the trouble of old man's operation.Although old man can also be allowed to operate in the first client 100 to reject false behavior number
According to still, since the elderly operates there are not yet done and be difficult to the case where operating smart machine, the present invention is in order to simplify the system
The elderly is bothered, the operating procedure of old man is reduced with exhausting one's ability；Second, the photographic device 500 setting, will not outdoors
The related photo of life privacy for collecting old man, avoids old man from resentment occur.
According to a preferred embodiment, several behavior sensors may include being installed on going out on access door for identification
Enter the angular displacement sensor of door opening and closing state.The angular displacement sensor for entering and leaving door opening and closing state for identification can be communicatively coupled to
Photographic device 500.The angular displacement sensor for entering and leaving door opening and closing state for identification can be configured as in access door towards open
The electric signal for indicating that access door is opened actively is sent to photographic device 500 immediately when direction rotates 3 °~5 °.Photographic device 500 is received
Several photos can be shot in 1s as the first photo group after the electric signal opened to access door.Door switch is entered and left for identification
The angular displacement sensor of state, which can be configured as, turns to the case where access door completely closes in the direction of access door towards closing
Lower ability sends the electric signal for indicating that access door is closed to photographic device 500.Photographic device 500 can have been shot in the first photo group
Continue to shine during preset time as second after several photos are continuously shot after until receiving the electric signal of access door closing
Piece group.The present invention at least can be realized following advantageous effects using this mode: discrepancy door switch for identification of the invention
The angular displacement sensor of state is communicatively coupled to photographic device 500, and the first photo group and second that photographic device 500 acquires
The time of photo group and the switch state of access door are related, so that the first photo group and the second photo group that the present invention is shot are general
Rate is related with personnel's variable condition in living space, without shooting excessive useless photo, such as when access door is not opened
Passerby passes by the photo before access door, can reduce the calculation amount of the first client 100, moreover it is possible to enable the first client 100
Enough receiving modes for efficiently and accurately analyzing the personnel accommodated in living space.
According to a preferred embodiment, the system this may include Intelligent bracelet 600 and/or identification module 700.
Server 300 can distribute a unique identity for each user and the identity is stored in Intelligent bracelet 600
In.Intelligent bracelet 600 can send the electromagnetic wave for carrying identity into limited communication range.Each behavior sensor
400 can be equipped with the identification module 700 for the electromagnetic wave for carrying identity for identification, to detect the intelligence of user's wearing
Energy bracelet 600 is to identify the touching originator for the behavioral data that behavior sensor 400 acquires.It determines and lives in the first client 100
When the receiving mode for the personnel that space content is received is user's solitary mode, the first client 100 can receive behavior sensor 400
The behavioral data of acquisition and identification module 700 is adopted in the case where user is not detected and does not wear Intelligent bracelet 600
Integrate the touching originator default definition of behavioral data as user.
The personnel accommodated in living space are determined in response to personnel's variable condition in living space in the first client 100
Receiving mode when by the solitary Mode change of user being guest mode, the first client 100 can indicate that user wears intelligent hand
Ring 600.Determine the personnel's accommodated in living space in response to personnel's variable condition in living space in the first client 100
Receiving mode by the solitary Mode change of user be guest mode when, the first client 100 can receive behavior sensor 400 acquisition
Behavioral data and only by identification module 700 detect user wear Intelligent bracelet 600 in the case where collect
Behavioral data be determined as triggering person be user behavioral data.The present invention at least can be realized following beneficial using this mode
Technical effect: first, under the solitary mode of user, user can not carry Intelligent bracelet 600, make user freer；Second,
In the life process of user, due to a variety of causes such as kith and kin drop in, maintenance personnel's to maintain equipment or water, electricity and gas company table look-up, occupy
It is inevitable for firmly entering other staff in space, and under guest mode, user can carry Intelligent bracelet 600, to there is him
It is still only obtained in the case that people is in living space by the behavioral data of user's triggering and evaluates the cognitive ability of user, thus
It avoids the collected behavioral data triggered by other people and mistakenly evaluates the cognitive ability of user, improve cognition energy of the invention
The accuracy of power evaluation；Third is reduced in the case where guest mode because user and visitor trigger different behavior sensings simultaneously
The first warning information and/or the second warning information reported by mistake caused by device 400.
According to a preferred embodiment, the predefined action for meeting user behavior habit can be prestored in server 300
The time span of sequence and scheduled specific behavior.After server 300 generates the first warning information, server 300 can basis
Received behavior sequence and predefined action with the behavioral data analysis user of the daily behavior of user-association in current period
The accuracy that sequence is compared obtains the first confidence level.Server 300 can based on the received with the daily behavior of user-association
Behavioral data analyzes the time span of corresponding specific behavior of the user in current period and the time of scheduled specific behavior
The second confidence level that length is compared.Can there be preset first confidence threshold value and the second confidence threshold value in server 300.
First confidence threshold value can be greater than the second confidence threshold value.Server 300 can be greater than the first confidence level in the first confidence level
Threshold value and the second confidence level determine that the first warning information is invalid when being greater than the second confidence threshold value.Server 300 can be first
Confidence level is less than or equal to the first confidence threshold value and the second confidence level is less than or equal to directly confirmation first when the second confidence threshold value
Warning information is effective.Server 300 can be less than or equal to the first confidence threshold value in the first confidence level and the second confidence level is less than
The first warning information is labeled as to the first early warning to be verified when setting up equal to one of condition in the second confidence threshold value
Information.The behavior with the daily behavior of user-association in next period that server 300 can wait the first client 100 to send
Data verify first warning information to be verified.Only when server 300 is according to the cognition energy of corresponding user of next period
It is decrease beyond compared with the cognitive ability scoring for the corresponding user that power scoring is assessed when next period toward the first two period default
Confirm that the first warning information is effective when activation threshold value.Server 300 can be when confirming that the first warning information is effective by first
Warning information is sent to the second client 200 held by the other staff other than user.The present invention uses this mode at least
It can be realized following advantageous effects: first, the present invention is by the first confidence level of setting compared with the first confidence threshold value
And second confidence level the wrong report of the first warning information is reduced compared with the second confidence threshold value, improve of the invention first
The accuracy of warning information；Second, because the time span of the behavior of user occurs compared to behavior sequence because of potential factor
A possibility that fluctuation, is bigger, therefore preset first confidence threshold value is greater than the second confidence threshold value in server 300, as a result,
To be further reduced the wrong report of the first warning information.
According to a preferred embodiment, the holder of the second client 200 for example can be medical staff or this hair
The network operator of bright system.First warning information can be sent to the second client 200 by server 300, relevant to allow
Personnel recognize the change of the cognitive ability of user.Preferably, after the second client 200 receives the first warning information, the second visitor
Family end 200 can indicate that its holder goes to the living space of user to recognize using MoCA scale and/or MMSE scale user
The ability of knowing is evaluated to obtain the scene scoring of reflection user cognition ability, recognizes when scene scoring is lower than corresponding preset fraction
Determine user be no longer appropriate for it is solitary.As a result, so as to scene accurately cognitive ability is dropped to be not suitable for it is solitary, it is solitary to generate phase
The cognitive ability of the user for the risk answered is judged, and intervenes the solitary behavior of this kind of user in time.For example, will use
Family is sent to the home for destitute for having nursing staff's colonization, or its family members is notified to look after user, to prevent cognitive ability
The risk that the user of degradation is solitary and generates.
Embodiment 2
Present embodiment discloses a kind of cognitive ability appraisal procedures based on the elderly's daily behavior, in other words, Yi Zhongji
In the cognitive ability appraisal procedure of user's daily behavior, the method based on time series database assessment cognitive ability a kind of in other words,
The method for assessing cognitive ability a kind of in other words.This method can by system of the invention and/or other alternative zero
Component is realized.For example, realizing method of the invention by using each components in system of the invention.It is not causing to conflict
Or in contradictory situation, the entirety and/or partial content of the preferred embodiment of other embodiments can be used as the present embodiment
Supplement.
According to a preferred embodiment, system of the invention is can be used to assess the cognitive ability of user in this method.
According to a preferred embodiment, this method be may comprise steps of in 1, step 2, step 3 and step 4 extremely
It is one few.This method may include information collection step, expert knowledge library construction step, and data processing step and cognitive ability are commented
Estimate and warning step.Data collection steps are made of sensor and server, old man's movement at sensor collection each moment
Sensing data is integrated in information, server collection；Information knowledge library construction step includes to original feature to higher level
The storage of classification and classification data；Data processing step includes the behavior prediction classifier carried out to the information based on classification storage
Building, which use Hidden Markov Model as disaggregated model；Cognitive ability appraisal procedure includes the behavior to obtaining
It scores, the result for decreaseing beyond threshold value to scoring carries out early warning.
Step 1: acquisition basic information constructs sensor information data set, including sensor device information table and sensor
Data information table.Sensor device information table describes the basic information of various kinds of sensors, attribute include: sensor name,
MAC Address, effect description, sensor type, data unit, installation site.MAC Address is unique as sensor device information
Mark.Sensor data information table describes the information content that sensor collection arrives, and attribute includes: sensor device, data
Content, uplink time.
By disposing sensor in the room, it upload the data to cloud server when sensor is triggered, takes
Business device stores data, and according to the uplink time of data, data are periodically carried out filing storage and data processing.
Step 2: building expert knowledge library knows the priori of relationship between sensor and behavior by expertise offer
Know to increase the precision of behavior prediction, and then increases the precision of cognition early warning.By constructing behavior, sensor and attribute
Between relation information table, be not based entirely on rule behavior prediction.Expert knowledge library mainly includes that sensor row is table, is passed
Sensor behavior table includes attribute: behavior title, behavior definition, triggering article, trigger sensor, triggered time and position lead to
Artificial common sense is crossed, the behavior basic to daily life is defined, and decomposition behavior acts triggered article to specific movement
It is associated with sensor, i.e., behavior is limited between several sensors that behavior may trigger, row is improved by above-mentioned rule
For the accuracy rate of prediction.Bottom sensor is sorted out according to classification to each behavior for table by sensor row, and will
This behavior is stored in expert knowledge library the relationship of the multi-to-multi of sensor.
Step 3: behavior prediction analysis uses Hidden Markov for the timing implied in sensor and behavioral data
Model comes according to sensor data predictive behavior.Hidden Markov Model introduces an implicit variable, and thinks state in data
Change be as and only as caused by the implicit variable at previous time point and this implicit variable, but this implicit variable can not be by
Observer directly observes and obtains.In Hidden Markov Model, by implying transfer matrix, initial state probabilities square between variable
The emission matrix that battle array corresponds to behavior with hidden variable solves the behavior at the time point to be predicted.It is carried out using Hidden Markov Model
When Activity recognition as, behavior regarded to the hidden variable of sensor, sensing data is observable and behavioral data is hiding
's.
According to a preferred embodiment, the present invention uses the data training Hidden Markov Model being collected into advance.And
Behavior prediction was carried out using Hidden Markov Model to the sensing data that this day is collected into for the period with 24 hours.It will give below
Markov model training and the step of the process of prediction out:
To Hidden Markov Model defined variable:
| Variable name | Variable is explained |
| T | Data sequence length |
| A | Transfer matrix between state hidden variable |
| B | Emission matrix |
| π | Initial state probabilities matrix |
| N | The number of hidden variable value |
| Q={ q0,q1,…,qN-1} | Hidden variable possible values set |
| I=(i1,i2,…iT-1) | Hidden variable sequence |
| O=(O0,O1,…,OT-1) | The data sequence observed |
The element value for defining the i-th row jth column of matrix A is also by i-th of state qiIt is transferred to j-th of state qjProbability
For aij:
aij=P (qj|qi)
It is q that the value for defining the row k jth column of matrix B, which is also in state,jWhen, observe the probability of data k:
bj(k)=P (k | qj)
So far, Markov model λ=(A, B, π) building complete, but A and B be all it is unknown, use is presented below
The process and formula of viterbi algorithm solution Hidden Markov Model.
Viterbi algorithm want be maximumlly hidden variable sequence after given observation data probability, it may be assumed that
max P(I|O)
Viterbi algorithm definition
Then recurrence formula can be obtained by above-mentioned formula:
Define Ψt(i)=argmax1≤j≤Nδt-1(j)aji, then the process of viterbi algorithm is as follows:
Input: model λ=(A, B, π) observes data sequence O=(o0,o1,…,oT-1)
Output: hidden variable sequence I=(i0,i1,…,iT-1)
Initialize local state:
δ0=πibi(o0), i=0,1 ..., N-1
Ψ0..., (i)=0, i=0,1 N-1
Dynamic Programming recursion t=1,2 is carried out ..., the local state at T-1 moment:
Calculate the maximum Ψ of moment TT(i), Ψ at this timeTIt (i) is the hidden variable state most possibly occurred at the t=T moment
I=(i is obtained using Ψ (i) backtracking0,i1,…,iT-1):
it=Ψt+1(it+1)
When being predicted using Hidden Markov Model, regard sensing data as observation sequence, i.e. O=(o0,
o1,…,oT-1), regard behavior as hidden variable, i.e. I=(i0,i1,…,iT-1).When can acquire each using viterbi algorithm
Carve corresponding behavior.
Step 4: by identifying obtained behavioural information, assessing cognitive ability and realizing early warning.The decline of cognitive ability exists
Incorrect important step is skipped or executed to the mistake that behavior is shown as in daily life when completing a certain activity,
So that this activity loses the meaning realized originally.The mistake of these behaviors, which may include, to be forgotten to close coal gas, keeps refrigerator doors
It is prolonged to open, or take a long time to complete a certain simple work.
The present invention selects the most n behaviors of daily triggering as Standard Task X, is expressed as X={ X1,X2,…,Xn, test
Standard time T of the time as this behavior that common people complete the n task is obtained, T={ T is expressed as1,T2,…,Tn, it is false
If everyone task completion time is t={ t1,t2,…,tn, task completeness is α={ α1,α2,…,αn, according to each
The importance of task determines that its weight is w={ w1,w2,…,wn, the scoring formula of cognitive ability is as follows:
Pass through the quality by cognitive ability score normalization, completed to quantify activity.According to daily score information, when
The cognitive ability scoring of user decrease beyond threshold value 10% and generates warning information.
According to a preferred embodiment, behavior sensor device information table describes the basis letter of each class behavior sensor
Breath, attribute are as shown in the table:
| Serial number | Symbol | Attribute information |
| 1 | Device Name | Sensor name |
| 2 | MAC address | MAC Address |
| 3 | Device Info | Effect description |
| 4 | Device Type | Sensor type |
| 5 | Data Unit | Data unit |
| 6 | Location | Installation site |
According to a preferred embodiment, sensor device collects data and transfers data to server.Server carries out
It is stored as sensor data information, shown in attribute following table:
| Serial number | Symbol | Attribute information |
| 1 | Device ID | Sensor device |
| 2 | Data | Data content |
| 3 | Time | Uplink time |
Following deployment is carried out to general house type house for the basis movement for detecting people according to a preferred embodiment:
It include communication gate and communication module inside behavior sensor device according to a preferred embodiment.Not simultaneous interpretation
Sensor transfers information to the first client by communication module.Communication module can be wire communication module or wireless communication
Module.Wireless communication module for example can be bluetooth module or ZigBee module.First client is by connecting WIFI for institute
There is data forwarding to server.The a variety of behavior sensors of system compatible only need to pass when there is new behavior sensor access
The data of sensor are set as the communication protocol that current system determines.Behavior sensor is only when having behavior to generate triggering
Transmit data, it is possible to reduce the transmission of data volume.
According to a preferred embodiment, communications protocol format is defined as follows shown in table:
According to a preferred embodiment, after data storage to server end, since data volume is big, in daily evening
Ten two points of timings carry out the filing of data, and the data that the collection on the same day obtains are arranged, and are packaged storage.
According to a preferred embodiment, by the behavior sensor-of expertise building, that behavior corresponds to table is as follows:
It should be noted that above-mentioned specific embodiment is exemplary, those skilled in the art can disclose in the present invention
Various solutions are found out under the inspiration of content, and these solutions also belong to disclosure of the invention range and fall into this hair
Within bright protection scope.It will be understood by those skilled in the art that description of the invention and its attached drawing are illustrative and are not
Constitute limitations on claims.Protection scope of the present invention is defined by the claims and their equivalents.
Claims (10)
1. a kind of cognitive ability assessment system based on the elderly's daily behavior, which is characterized in that the system includes server
(300) and several behavior sensors (400),
Wherein, the server (300) by several behavior sensors (400) for being deployed in the living space of user with
The mode implicitly perceived acquires the behavioral data with the daily behavior of user-association；
The server (300) according at least to the daily behavior with user-association behavioral data assessment user cognitive ability with
Obtain the cognitive ability scoring of user.
2. the system as claimed in claim 1, which is characterized in that periodically relatively current period is corresponding for the server (300)
The score cognitive ability of user corresponding with a upper period of the cognitive ability of user scores, and the server (300) with
The cognitive ability scoring ring ratio at family generates the first warning information when decreaseing beyond default activation threshold value.
3. the system as described in one of preceding claims, which is characterized in that the server (300) is according to following scoring formula
The cognitive ability of user is assessed to obtain the cognitive ability scoring of user:
Wherein, server (300) assessment user cognitive ability with obtain user cognitive ability scoring before, select it is daily
Standard Task X of the corresponding behavioral data of most n behaviors as the cognitive ability for evaluating user is triggered, X=is expressed as
{X1,X2,…,Xn, T is the set that ordinary people completes the standard time of each task in the n task, is expressed as T={ T1,
T2,…,Tn, Ti is the standard time that ordinary people completes i-th task in the n task, and t is that user completes in the n task
The set of the average time of each task is expressed as t={ t1,t2,…,tn, ti is that user completes i-th task in the n task
Average time, α is the set that user completes the task completeness of each task in the n task, and α i indicates that user completes the n
The task completeness of i-th task in task, w are the set of the weight of each task in the n task, and wi indicates the n task
In i-th task weight.
4. the system as described in one of preceding claims, which is characterized in that the server (300) acquires and user-association
The behavioral data of daily behavior have time attribute, the server (300) obtains the row with the daily behavior of user-association
For the behavioral data of the daily behavior with user-association is stored the clothes into time series database according to time attribute after data
Business device (300) is that each user independently establishes the Hidden Markov Model for being used to predict its behavior being associated, the service
Device (300) uses the trained Hidden Markov mould with the user-association of behavioral data related with user in time series database
Type, the predictive behavior of server (300) basis and the Hidden Markov Model prediction user of the user-association, and in the reality of user
Second is generated in the case that border behavior and predictive behavior deviate and the deviation will lead to known risk and/or known loss
Warning information.
5. the system as described in one of preceding claims, which is characterized in that the system also includes the first client (100),
First client (100) is communicatively coupled to the server (300), and first client (100) is used as trunking
The behavioral data for several behavior sensor (400) acquisitions being arranged in living space is obtained, the server (300) is raw
Risk checking request, the first client (100) response are sent to first client (100) at after the second warning information
It is sounded an alarm in the risk checking request, and the alarm is only capable of being passed through extremely on the first client (100) by user
Can just be released after the verifying of few two living things feature recognitions, first client (100) sound all clear after to the clothes
Be engaged in device (300) send risk wrong report feedback or risk release feedback, the server (300) in response to risk report by mistake feedback or
Person's risk releases feedback and deletes the second warning information.
6. the system as described in one of preceding claims, which is characterized in that the system also includes photographic device (500), institutes
It states photographic device (500) to be communicatively coupled to the first client (100), the photographic device (500) can be set to and pass in and out the inhabitation
Outside the access door in space, the photographic device (500) is for acquiring the first photo group and the second photo group, the first photo group
It is to be shot before access door is opened, the second photo group is after access door is opened until access door is persistently preset after closing
It is shot during time, first client (100) obtains the first photo group and second from the photographic device (500) and shines
Piece group, first client (100) the first photo group and the second photo group determine in the living space
Personnel's variable condition, and first client (100) is determined in response to personnel's variable condition in the living space and is occupied
The receiving mode for the personnel that firmly space content is received, the receiving mode includes one of following mode:
Have in living space and the user of only one people of user stays alone mode；
There is the guest mode of other staff or only other staff in addition to the user in living space；With
The vacant mode of nobody in living space；
Wherein, the first client (100) analyzes the behavior number that several behavior sensors (400) acquire during guest mode
According to touching originator, the touching originator for the corresponding behavioral data that first client (100) acquires during guest mode can not
Retention can not determine the corresponding behavioral data of touching originator in the case where determination, and only by several behavior sensors (400)
What is acquired during guest mode can determine that touching originator is that the behavioral data of user is sent to server (300).
7. the system as described in one of preceding claims, which is characterized in that several sensors are included at least and are installed on out
The angular displacement sensor for entering and leaving door opening and closing state for identification in introduction, the angle position for entering and leaving door opening and closing state for identification
Displacement sensor is communicatively coupled to the photographic device (500), the angular displacement sensor for entering and leaving door opening and closing state for identification
It is configured as actively sending to the photographic device (500) immediately when access door rotates 3 °~5 ° towards open direction and represent
The electric signal for opening of geting started, the photographic device (500) shoot several photos after receiving the electric signal that access door is opened in 1s
As the first photo group, the angular displacement sensor for entering and leaving door opening and closing state for identification is configured as in access door towards closing
Direction turn in the case that access door completely closes and just to send the electricity for indicating that access door is closed to the photographic device (500)
Signal, the photographic device (500) are continuously shot several photos until receiving access door pass after the completion of the first photo group is shot
Continue to be used as the second photo group during preset time after the electric signal closed.
8. the system as described in one of preceding claims, which is characterized in that the system also includes Intelligent bracelet (600) and bodies
Part identification module (700), server (300) are that each user distributes a unique identity and stores the identity
In Intelligent bracelet (600), the Intelligent bracelet (600) sends the electromagnetism for carrying identity into limited communication range
Wave, each behavior sensor (400) are provided with the identification module (700) for carrying the electromagnetic wave of identity for identification,
To detect the Intelligent bracelet (600) of user's wearing to identify the touching originator of the behavioral data of behavior sensor (400) acquisition,
It is described when the first client (100) determines that the receiving mode of the personnel accommodated in living space is the solitary mode of user
First client (100) reception behavior features sensor (400) acquisition behavioral data and identification module (700) is not being examined
Measuring and collecting the touching originator default definition of behavioral data in the case that user does not wear Intelligent bracelet (600) is user；
The people accommodated in living space is determined in response to personnel's variable condition in the living space in the first client (100)
When the receiving mode of member by the solitary Mode change of user is guest mode, first client (100) instruction user wears institute
It states Intelligent bracelet (600), the behavioral data of the first client (100) reception behavior features sensor (400) acquisition and only general
Collected behavioral data is really in the case where detecting Intelligent bracelet (600) that user wears for identification module (700)
It is set to the behavioral data that touching originator is user.
9. the system as described in one of preceding claims, which is characterized in that prestored in the server (300) and meet user
The time span of the predefined action sequence and scheduled specific behavior of behavioural habits, the server (300) generate the first early warning
After information, the server (300) is based on the received with the behavioral data of the daily behavior of user-association analysis user current
The accuracy that behavior sequence in period is compared with predefined action sequence obtains the first confidence level, server (300) basis
Received corresponding specific behavior of the behavioral data analysis user in current period with the daily behavior of user-association when
Between second confidence level of the length compared with the time span of scheduled specific behavior, have in the server (300) preset
First confidence threshold value and the second confidence threshold value, first confidence threshold value are greater than the second confidence threshold value, the service
Described in device (300) determines when the first confidence level is greater than the first confidence threshold value and the second confidence level is greater than the second confidence threshold value
First warning information is invalid,
The server (300) is less than or equal to the first confidence threshold value in the first confidence level and the second confidence level is less than or equal to second
Directly confirm that the first warning information is effective when confidence threshold value,
The server (300) is less than or equal to the first confidence threshold value in the first confidence level and the second confidence level is less than or equal to second
First warning information is labeled as the first warning information to be verified when setting up by one of condition in confidence threshold value, is serviced
What device (300) waited the first client (100) next period for sending tests with the behavioral data of the daily behavior of user-association
First warning information to be verified is demonstrate,proved, only when server (300) scores according to the cognitive ability of corresponding user of next period
Default firing level is decrease beyond compared with the cognitive ability scoring of the corresponding user assessed when next period toward the first two period
Confirm that the first warning information is effective when value,
The server (300) confirm the first warning information it is effective when by first warning information be sent to by user with
The second client (200) that outer other staff are held.
10. a kind of cognitive ability appraisal procedure based on the elderly's daily behavior, which is characterized in that this method uses such as right 1
The cognitive ability of user is assessed to system described in one of 9, which includes server (300) and several behavior sensors
(400),
Wherein, the server (300) by several behavior sensors (400) for being deployed in the living space of user with
The mode implicitly perceived acquires the behavioral data with the daily behavior of user-association；
The server (300) according at least to the daily behavior with user-association behavioral data assessment user cognitive ability with
Obtain the cognitive ability scoring of user.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910421469.5A CN110136832B (en) | 2019-05-20 | 2019-05-20 | Cognitive ability assessment system and method based on daily behaviors of old people |
| CN202210362582.2A CN114974577A (en) | 2019-05-20 | 2019-05-20 | Patient cognitive ability analysis and early warning system and method based on behavior prediction |
| CN202210356940.9A CN114724714A (en) | 2019-05-20 | 2019-05-20 | Patient cognitive ability monitoring system and method based on user space |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910421469.5A CN110136832B (en) | 2019-05-20 | 2019-05-20 | Cognitive ability assessment system and method based on daily behaviors of old people |
Related Child Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210356940.9A Division CN114724714A (en) | 2019-05-20 | 2019-05-20 | Patient cognitive ability monitoring system and method based on user space |
| CN202210362582.2A Division CN114974577A (en) | 2019-05-20 | 2019-05-20 | Patient cognitive ability analysis and early warning system and method based on behavior prediction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110136832A true CN110136832A (en) | 2019-08-16 |
| CN110136832B CN110136832B (en) | 2022-04-15 |
Family
ID=67571819
Family Applications (3)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910421469.5A Active CN110136832B (en) | 2019-05-20 | 2019-05-20 | Cognitive ability assessment system and method based on daily behaviors of old people |
| CN202210356940.9A Pending CN114724714A (en) | 2019-05-20 | 2019-05-20 | Patient cognitive ability monitoring system and method based on user space |
| CN202210362582.2A Pending CN114974577A (en) | 2019-05-20 | 2019-05-20 | Patient cognitive ability analysis and early warning system and method based on behavior prediction |
Family Applications After (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210356940.9A Pending CN114724714A (en) | 2019-05-20 | 2019-05-20 | Patient cognitive ability monitoring system and method based on user space |
| CN202210362582.2A Pending CN114974577A (en) | 2019-05-20 | 2019-05-20 | Patient cognitive ability analysis and early warning system and method based on behavior prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (3) | CN110136832B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110472891A (en) * | 2019-08-26 | 2019-11-19 | 上海蔚来汽车有限公司 | It is powered on service ability or the assessment or management method of resource, system and storage medium |
| CN110502303A (en) * | 2019-08-20 | 2019-11-26 | 银康(中山)科技有限公司 | Method, apparatus, electronic device and storage medium for evaluating ability of elderly person |
| CN110752033A (en) * | 2019-08-30 | 2020-02-04 | 康美健康云服务有限公司 | Informationization method and system for cognitive assessment and readable storage medium |
| CN111128383A (en) * | 2019-12-30 | 2020-05-08 | 成都麦杰康科技有限公司 | Information processing method, information processing device, electronic equipment and storage medium |
| CN113962444A (en) * | 2021-09-29 | 2022-01-21 | 湖北美和易思教育科技有限公司 | Student quality literacy prediction system based on reinforcement learning |
| CN114521270A (en) * | 2019-09-30 | 2022-05-20 | 松下知识产权经营株式会社 | Cognitive level assessment system, cognitive level assessment method, and program |
| CN115019964A (en) * | 2021-06-11 | 2022-09-06 | 合肥工业大学 | Cognitive ability evaluation system and method based on digital biomarker |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1564219A (en) * | 2004-03-25 | 2005-01-12 | 浙江工业大学 | Household security device for lonely living edged people |
| CN104881591A (en) * | 2015-06-25 | 2015-09-02 | 贾建平 | Cognitive disorder data processing method and system |
| CN106092133A (en) * | 2016-05-27 | 2016-11-09 | 北京灵龄科技有限责任公司 | Start the decision method of guest mode, device |
| CN107004062A (en) * | 2014-12-19 | 2017-08-01 | 皇家飞利浦有限公司 | For assessing the personal equipment, system and method for performing one or more movable abilities |
| CN107886103A (en) * | 2016-09-29 | 2018-04-06 | 日本电气株式会社 | For identifying the method, apparatus and system of behavior pattern |
| CN108348194A (en) * | 2015-09-15 | 2018-07-31 | 联邦科学和工业研究机构 | Mobility monitors |
| US20190057777A1 (en) * | 2017-08-15 | 2019-02-21 | Totemic Labs, Inc. | System and method for processing wireless backscattered signal using artificial intelligence processing for activities of daily life |
| CN109473173A (en) * | 2018-09-30 | 2019-03-15 | 华中科技大学 | A kind of the elderly's Cognitive deficiency assessment system and device based on video |
| CN109752963A (en) * | 2019-01-02 | 2019-05-14 | 沈阳工程学院 | A kind of house security system based on Internet of Things |
-
2019
- 2019-05-20 CN CN201910421469.5A patent/CN110136832B/en active Active
- 2019-05-20 CN CN202210356940.9A patent/CN114724714A/en active Pending
- 2019-05-20 CN CN202210362582.2A patent/CN114974577A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1564219A (en) * | 2004-03-25 | 2005-01-12 | 浙江工业大学 | Household security device for lonely living edged people |
| CN107004062A (en) * | 2014-12-19 | 2017-08-01 | 皇家飞利浦有限公司 | For assessing the personal equipment, system and method for performing one or more movable abilities |
| CN104881591A (en) * | 2015-06-25 | 2015-09-02 | 贾建平 | Cognitive disorder data processing method and system |
| CN108348194A (en) * | 2015-09-15 | 2018-07-31 | 联邦科学和工业研究机构 | Mobility monitors |
| CN106092133A (en) * | 2016-05-27 | 2016-11-09 | 北京灵龄科技有限责任公司 | Start the decision method of guest mode, device |
| CN107886103A (en) * | 2016-09-29 | 2018-04-06 | 日本电气株式会社 | For identifying the method, apparatus and system of behavior pattern |
| US20190057777A1 (en) * | 2017-08-15 | 2019-02-21 | Totemic Labs, Inc. | System and method for processing wireless backscattered signal using artificial intelligence processing for activities of daily life |
| CN109473173A (en) * | 2018-09-30 | 2019-03-15 | 华中科技大学 | A kind of the elderly's Cognitive deficiency assessment system and device based on video |
| CN109752963A (en) * | 2019-01-02 | 2019-05-14 | 沈阳工程学院 | A kind of house security system based on Internet of Things |
Non-Patent Citations (3)
| Title |
|---|
| SUNLEE BANG等: "Toward real time detection of the basic living activity in home using a wearable sensor and smart home sensors", 《2008 30TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY》 * |
| 姚小慧: "基于隐式感知的老人日常活动识别系统", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 张明园等: "《精神科评定量表手册》", 30 September 2015, 湖南科学技术出版社 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110502303A (en) * | 2019-08-20 | 2019-11-26 | 银康(中山)科技有限公司 | Method, apparatus, electronic device and storage medium for evaluating ability of elderly person |
| CN110472891A (en) * | 2019-08-26 | 2019-11-19 | 上海蔚来汽车有限公司 | It is powered on service ability or the assessment or management method of resource, system and storage medium |
| CN110472891B (en) * | 2019-08-26 | 2023-10-17 | 上海蔚来汽车有限公司 | Method, system and storage medium for evaluating or managing power-up service capability or resource |
| CN110752033A (en) * | 2019-08-30 | 2020-02-04 | 康美健康云服务有限公司 | Informationization method and system for cognitive assessment and readable storage medium |
| CN114521270A (en) * | 2019-09-30 | 2022-05-20 | 松下知识产权经营株式会社 | Cognitive level assessment system, cognitive level assessment method, and program |
| CN111128383A (en) * | 2019-12-30 | 2020-05-08 | 成都麦杰康科技有限公司 | Information processing method, information processing device, electronic equipment and storage medium |
| CN115019964A (en) * | 2021-06-11 | 2022-09-06 | 合肥工业大学 | Cognitive ability evaluation system and method based on digital biomarker |
| CN113962444A (en) * | 2021-09-29 | 2022-01-21 | 湖北美和易思教育科技有限公司 | Student quality literacy prediction system based on reinforcement learning |
| CN113962444B (en) * | 2021-09-29 | 2024-08-13 | 武汉美和易思数字科技有限公司 | Student literacy prediction system based on reinforcement learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114724714A (en) | 2022-07-08 |
| CN114974577A (en) | 2022-08-30 |
| CN110136832B (en) | 2022-04-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110136832A (en) | A kind of cognitive ability assessment system and method based on the elderly's daily behavior | |
| Jung et al. | Human-in-the-loop HVAC operations: A quantitative review on occupancy, comfort, and energy-efficiency dimensions | |
| CN100355228C (en) | Anomalous detecting device and anomalous detection system | |
| Suryadevara et al. | Smart homes | |
| CN109891436A (en) | Security system and its control method based on deep learning neural network | |
| US10482901B1 (en) | System and method for beep detection and interpretation | |
| US11531082B2 (en) | Device location network | |
| US11544924B1 (en) | Investigation system for finding lost objects | |
| JP2020115312A (en) | Model generation device, model generation method, model generation program, model generation system, inspection system, and monitoring system | |
| US20240314604A1 (en) | Mesh network connection quality | |
| Matsui et al. | Easy-to-deploy living activity sensing system and data collection in general homes | |
| JP2018180826A (en) | Residence information management device, and residence information management system | |
| US11550276B1 (en) | Activity classification based on multi-sensor input | |
| US11624519B2 (en) | Carbon monoxide purge system for a property | |
| Sansano-Sansano et al. | Multimodal Sensor Data Integration for Indoor Positioning in Ambient‐Assisted Living Environments | |
| Niu et al. | Integrating environmental sensing and BLE-based location for improving daily activity recognition in OPH | |
| US11544505B1 (en) | Semi-supervised learning based on clustering objects in video from a property | |
| US11823452B2 (en) | Video analytics evaluation | |
| Wilhelm | Activity-monitoring in Private Households for Emergency Detection: A Survey of Common Methods and Existing Disaggregable Data Sources. | |
| Miao et al. | The analysis of student grades based on collected data of their Wi-Fi behaviors on campus | |
| CN106919947B (en) | method and device for recognizing eating behavior of user | |
| KR101955939B1 (en) | Method and apparatus for recognizing activities through spatial filtering and machine learning | |
| US20230039967A1 (en) | Airborne pathogen detection through networked biosensors | |
| US20230081909A1 (en) | Training an object classifier with a known object in images of unknown objects | |
| US20230044233A1 (en) | Fast user enrollment for facial recognition using face clustering |
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 |