CN104200613A - Silent alarming method and silent alarming device - Google Patents
Silent alarming method and silent alarming device Download PDFInfo
- Publication number
- CN104200613A CN104200613A CN201410482801.6A CN201410482801A CN104200613A CN 104200613 A CN104200613 A CN 104200613A CN 201410482801 A CN201410482801 A CN 201410482801A CN 104200613 A CN104200613 A CN 104200613A
- Authority
- CN
- China
- Prior art keywords
- user
- study
- value
- interruption
- state
- 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
Landscapes
- Alarm Systems (AREA)
- Emergency Alarm Devices (AREA)
Abstract
The invention provides a silent alarming method and a silent alarming device, and is applicable to the field of monitoring of special crowds. The silent alarming method comprises the following steps of learning a user using mode; judging whether the user is in a movement state or not through preset dynamic state induction equipment, preset static state induction equipment and the learned user using mode; and giving an alarm when the user is not in the movement state. By the method and the device, the probability of false alarm on monitoring of old people can be reduced.
Description
Technical field
The invention belongs to special population monitoring field, relate in particular to a kind of without sound alarm method and device.
Background technology
At present, Wearable equipment and object sensor are widely used in the elderly's activity monitoring.But all have certain defect when both use separately, Wearable sensor advantage is to detect in time extremely, if old man wears, supposes that battery does not exhaust, movable information that should real-time perception old man.But shortcoming is old man to have a poor memory, and often can forget and put on, or sensor in use electric weight exhaust, and old man forgets charging.These all can cause system to send wrong alerting signal.And if at this moment the staff of service centre intervenes (as: phone) in inappropriate time (as: having a rest and time for eating meals), will cause unnecessary creating disturbances to old man client and children thereof.In addition, if telephone interview is not answered, just need to set out attendant visits and visits, due to Wearable sensor misinformation probability higher (client forget wear or forget charging cause), service centre just needs the configuration attendant more than actual demand, cause service centre's manpower, the significantly rising of the costs such as traffic.The advantage of object sensor is that sensor is directly placed on the conventional object of old man, does not exist the problem of forgetting.But it is relatively poor that shortcoming is its real-time, because the elderly can use all the time.
Summary of the invention
It is a kind of without sound alarm method and device that the object of the embodiment of the present invention is to provide, and is intended to solve existing Wearable equipment or the object sensor high problem of rate of false alarm in the time using separately.
The embodiment of the present invention is achieved in that a kind of without sound alarm method, and described method comprises the steps:
Study user uses pattern;
By default dynamic sensing apparatus and state induction equipment, and described study to user use pattern, judge that whether user is in active state;
When user is during in inactive state, send warning.
Further, described dynamic sensing apparatus is the Wearable equipment with acceleration transducer; Described state induction equipment is the object sensor with acceleration transducer.
Further, described by default dynamic sensing apparatus and state induction equipment, and described study to user use pattern, judge whether user comprises in active state:
Calculate the interior maximal value of all axial acceleration absolute values of acceleration transducer sum of Wearable equipment of a Preset Time or the maximal value of all axial acceleration absolute values of acceleration transducer of Wearable equipment as the first detected value A1; Calculate the interior maximal value of all axial acceleration absolute value sums of object sensor of described Preset Time or the maximal value of all axial acceleration absolute values of object sensor as the second detected value A2;
When described the first detected value A1 is less than or equal to default threshold value a1, and described the second detected value A2 is less than or equal to default threshold value a2, according to described study to user use mode decision current time whether in user's activity time section, be to judge that user is in inactive state.
Further, described study is used pattern also to comprise:
The study of user's interruption-free time, and be added in described user's use pattern.
Further, the study of described user's interruption-free time comprises:
Interruption-free state sample gathers;
Extract the feature of the interruption-free state sample of described collection;
Carry out sorter training according to the feature of described extraction, obtain described user's interruption-free time.
The present invention also proposes a kind of without sound warning device, and described device comprises:
Study module, uses pattern for learning user;
Judge module, for by default dynamic sensing apparatus and state induction equipment, and described study to user use pattern, judge that whether user is in active state;
Alarm module, for when user is during in inactive state, sends warning.
Further, described dynamic sensing apparatus is the Wearable equipment with acceleration transducer; Described state induction equipment is the object sensor with acceleration transducer.
Further, described judge module comprises:
Computing unit, for calculating the maximal value of all axial acceleration absolute values of acceleration transducer sum of Wearable equipment in a Preset Time or the maximal value of all axial acceleration absolute values of acceleration transducer of Wearable equipment as the first detected value A1; Calculate the interior maximal value of all axial acceleration absolute value sums of object sensor of described Preset Time or the maximal value of all axial acceleration absolute values of object sensor as the second detected value A2;
Identifying unit, for being less than or equal to default threshold value a1 as described the first detected value A1, and described the second detected value A2 is less than or equal to default threshold value a2, according to described study to user use mode decision current time whether in user's activity time section, be to judge that user is in inactive state.
Further, described study module also for:
The study of user's interruption-free time, and be added in described user's use pattern.
Further, described study module comprises:
Collecting unit, gathers for interruption-free state sample;
Extraction unit, for extracting the feature of interruption-free state sample of described collection;
Training unit, for carrying out sorter training according to the feature of described extraction, obtains described user's interruption-free time.
The embodiment of the present invention propose a kind of dynamic sensing apparatus as Wearable sensor and state induction equipment as object sensor combine without sound alarm method and device, because above-mentioned two kinds of sensors are all, by built-in acceleration transducer, the motion of human body or object is carried out to perception, there is motion perception advantage accurately compared with pyroelectric sensor, camera, therefore greatly reduce disadvantaged group as the probability of the false alarm of old man's monitoring.Use in the learning process of pattern user, increased adaptive learning method, improved system user is used in different time, age, health the adaptability of patterns of change.Formulate corresponding service centre counter-measure according to two kinds of different alarm condition of sensor simultaneously, and propose the recognition methods that user exempts from section interference time the cost providing without sound alert service has been provided, improve user's experience, improved service quality and user satisfaction.
Brief description of the drawings
Fig. 1 is the system construction drawing without the application of sound alarm method that the embodiment of the present invention one provides;
Fig. 2 is the process flow diagram without sound alarm method that the embodiment of the present invention one provides;
Fig. 3 is the process flow diagram without determining step in sound alarm method that the embodiment of the present invention one provides;
Fig. 4 is another process flow diagram without sound alarm method that the embodiment of the present invention one provides;
Fig. 5 is the process flow diagram without sound alarm method learning step that the embodiment of the present invention one provides;
Fig. 6 is the structural drawing without sound warning device that the embodiment of the present invention two provides;
Fig. 7 is the structural drawing without judge module in sound warning device that the embodiment of the present invention two provides;
Fig. 8 is the structural drawing without sound warning device learning module that the embodiment of the present invention two provides.
Embodiment
In order to make object of the present invention, technical scheme and advantage clearer, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
embodiment mono-
The embodiment of the present invention one proposes a kind of without sound alarm method, is applied to the server in system as shown in Figure 1, this system comprise server, mobile terminal, external or in the dynamic sensing apparatus established if Wearable equipment, state induction equipment are as object sensor.The embodiment of the present invention describes as an example of Wearable equipment and object sensor example, other similar devices also can be applicable to the embodiment of the present invention, Wearable equipment is by elders wear, object sensor is fixed on the conventional object of old man, and Wearable equipment and object sensor are mainly made up of acceleration transducer, MCU, wireless communication module and the supply module of diaxon or three axles.As shown in Figure 2, the method for the embodiment of the present invention one comprises step:
S1, study user use pattern.For economizing on resources, avoid system frequently to detect user's active state, the embodiment of the present invention is introduced user's use pattern, and the use pattern of introducing user can reduce the probability of error detection.
Before user's use pattern, first must learn user's use pattern.Using initial a period of time (as one month) of Wearable equipment or object sensor user is the pattern learning phase.During this period of time, estimation object/person body in each time period (as: each hour) in moving type probability of state.With the pattern learning phase of 30 days, 8 to 9 time periods were example, if in these 30 days, had 29 days wearing sensors or object sensor output active signal, 8 to 9 points, and human body is 29/30=96.67% in moving type probability of state.
Because user's use pattern may change along with the variation in season, month, therefore in follow-up use procedure, system by automatically to the user in different months use pattern learn to obtain activity condition probability P (A|M) based on month wherein M represent month, A deputy activity.Consider impact use pattern being caused along with the growth of user's age or the variation of physical qualification simultaneously.System is upgraded P by finishing in every month the rear conditional probability to this month
update(A|M)=b*P
old(A|M)+(1-b) * P
new(A|M).Wherein upgrade weight b by the monthly Lookup protocol of reporting the result of visit to user according to customer acceptance center.If this month user's use patterns of change is owing to going away, the physical function impermanency influence factor causing of suddenling change causes, and b value is larger, as: 0.9～1.0; If this month user's use patterns of change is that b value is less because physical function sudden change (as: occurring affecting the disease of mobility) causes, as: 0.0～0.1; If this moon does not have emergency case, b can value 0.5, to adapt to successional use patterns of change.
S2, by default dynamic sensing apparatus and state induction equipment, and study to user use pattern, judge that whether user is in active state.As shown in Figure 3, specifically can comprise step:
In S11, calculating one Preset Time, the maximal value of all axial acceleration absolute values of acceleration transducer sum of Wearable equipment or the maximal value of all axial acceleration absolute values of acceleration transducer of Wearable equipment are as the first detected value A1; Calculate the interior maximal value of all axial acceleration absolute value sums of object sensor of Preset Time or the maximal value of all axial acceleration absolute values of object sensor as the second detected value A2.
S12, be less than or equal to default threshold value a1 as the first detected value A1, and the second detected value A2 is less than or equal to default threshold value a2, and according to study to user use mode decision current time whether in user's activity time section, be to judge that user is in inactive state.Threshold value a1 and threshold value a2 are for presetting, the mode of setting is: by object sensor and Wearable equipment static placement a period of time as one hour, calculate the average of the acceleration quadratic sum of the acceleration transducer of object sensor and Wearable equipment in static process, using the average of the acceleration quadratic sum of object sensor (also can get the maximal value of each axial acceleration absolute value of object sensor) as threshold value a1, using the average of the quadratic sum of the acceleration of the acceleration transducer of Wearable equipment (also can get the maximal value of each axial acceleration absolute value of sensor) as threshold value a2.Contrast the first detected value A1 and threshold value a1, contrast the second detected value A2 and threshold value a2, as the first detected value A1 is less than or equal to threshold value a1, and the second detected value A2 is less than or equal to threshold value a2, further according to study to user whether use mode decision to obtain the current time period be that activity time of user is when section, just deducibility goes out user in abnormal inactive state, and carries out next step.
S3, when user is during in inactive state, send warning.
That reports to the police sends and can be completed by object sensor, Wearable equipment or server.If Wearable equipment sends alerting signal, object sensor shows that User Activity is normal, shows that user may forget to wear Wearable sensor or Wearable sensor battery exhausts or breaks down.At this moment, remind and wear Wearable equipment or remind charging note automatically to send.After certain hour as still without response, enter the artificial treatment patterns such as phone.If Wearable sensor and object sensor all send alerting signal, enter one-level early warning, carry out phone inquiry, reply as nothing, expatriate personnel visit.If two kinds of sensors all do not send alerting signal, show normally, without taking measures.If Wearable sensor does not send alerting signal, object sensor sends alerting signal, illustrates that object sensor may break down, and will enter object sensor maintenance flow process.Alerting signal output determination methods in this measure is as follows: suppose that perceptron is P at the movable probability of certain time period, if current slot perceptron does not have active signal output, and P is greater than certain threshold value as 30% perceptron output alarm signal.This threshold value has determined the susceptibility of system, generally should adjust according to practice.
As shown in Figure 4, the embodiment of the present invention one also can comprise step:
The study of S4, user's interruption-free time, and be added in user's use pattern.
Experience in order to improve user, avoid user to cause unnecessary creating disturbances to, user's interruption-free time can be set, in user's interruption-free time, user does not receive the Human disturbances such as phone.As Wearable equipment, object sensor or server send warning, need to check whether the current time period of living in disturb the period for exempting from, be to wait for exempting to disturb the period to finish.Here the interruption-free time period to user is carried out to automatic learning, learning method as shown in Figure 5, comprising:
S31, interruption-free state sample gather.Gather user's (for example: have a rest and have dinner) Wearable sensor reading sample within the interruption-free period.
S32, feature extraction.Disturb the reading sample of period inner sensor to be divided into n the period (n value can be estimated optimal value by cross validation) by exempting from.Calculate each period sensor reading sample average and variance.Specific features extracting method is not limited to this, also can adopt the amplitude equalizing value that the sensing data reading in the period is carried out to each frequency band of the statistics of Fourier variation in short-term as feature, and n characteristics of time interval series connection obtained to proper vector.Extract the sensor reading feature of normal period by identical method simultaneously.
S33, sorter training.Carry out the sorter training (exempting to disturb period and normal period) of two classes according to the sample characteristics obtaining.Sorter can adopt the methods such as support vector machine, artificial neural network and random forest.
S34, the judgement of interruption-free time period.When obtaining after the Wearable sensor reading of a day, be multiple continuous time periods by the sensor reading cutting of this day, duration is identical with the interruption-free period duration average of training use.According to extracting sensor reading feature.And input sorter and adjudicate.When Wearable sensor is worn or when running down of battery there is no reading owing to forgetting, adjudicate according to the interference time section average exempted from of front m (as: 5) day.
The embodiment of the present invention one propose without sound alarm method, because above-mentioned two kinds of sensors are all, by built-in acceleration transducer, the motion of human body or object is carried out to perception, there is the low and motion perception advantage accurately of cost compared with pyroelectric sensor, camera.Use in the learning process of pattern user, increased adaptive learning method, improved system user is used in different time, age, health the adaptability of patterns of change.Simultaneously can take phase counter-measure according to two kinds of different alarm condition of sensor, and propose the recognition methods that user exempts from section interference time the cost providing without sound alert service has been provided, improve user's experience, improve service quality and user satisfaction.
embodiment bis-
The embodiment of the present invention two proposes one without sound warning device, and this device can be server, can be also cloud platform, preferably cloud platform.Cloud platform can configure required hardware resource flexibly according to the number of customer volume and calculated amount.Amazon, Alibaba, the companies such as Sina all provide basic cloud platform service.Wearable equipment or object sensor push data into cloud platform by http protocol or udp protocol.Can be by Apache http server software receiving sensor data be installed on cloud platform, carry out data analysis processing, to service centre provide web application service show in real time the geriatric state of use equipment, to outworker's mobile terminal or children's mobile terminal PUSH message (can adopt MQTT to realize).
As shown in Figure 6, the device of the embodiment of the present invention two comprises:
Study module 30, uses pattern for learning user.
Judge module 10, for by default dynamic sensing apparatus and state induction equipment, and study to user use pattern, judge that whether user is in active state; Above-mentioned dynamic sensing apparatus can be Wearable equipment, and state induction equipment can be object sensor, and other similar devices also can be applicable to the embodiment of the present invention, and the embodiment of the present invention describes as an example of Wearable equipment and object sensor example.
Alarm module 20, for when user is during in inactive state, sends warning.
Further, as shown in Figure 7, judge module 10 comprises computing unit 11, calculates the interior maximal value of all axial acceleration absolute values of acceleration transducer sum of Wearable equipment of a Preset Time or the maximal value of all axial acceleration absolute values of acceleration transducer of Wearable equipment as the first detected value A1; Calculate the interior maximal value of all axial acceleration absolute value sums of object sensor of Preset Time or the maximal value of all axial acceleration absolute values of object sensor as the second detected value A2; Identifying unit 12, when the first detected value A1 is less than or equal to default threshold value a1, and the second detected value A2 is less than or equal to default threshold value a2, according to study to user use mode decision current time whether in user's activity time section, be to judge that user is in inactive state.
For economizing on resources, avoid system frequently to detect user's active state, the embodiment of the present invention is introduced user's use pattern, and the use pattern of introducing user can reduce the probability of error detection.Before user's use pattern, first study module 30 is learnt user's use pattern, and using initial a period of time (as one month) of Wearable equipment or object sensor user is the pattern learning phase.During this period of time, estimation object/person body in each time period (as: each hour) in moving type probability of state.With the pattern learning phase of 30 days, 8 to 9 time periods were example, if in these 30 days, had 29 days wearing sensors or object sensor output active signal, 8 to 9 points, and human body is 29/30=96.67% in moving type probability of state.
Because user's use pattern may change along with the variation in season, month, therefore in follow-up use procedure, study module 30 by automatically to the user in different months use pattern learn to obtain activity condition probability P (A|M) based on month wherein M represent month, A deputy activity.Consider impact use pattern being caused along with the growth of user's age or the variation of physical qualification simultaneously.System is upgraded P by finishing in every month the rear conditional probability to this month
update(A|M)=b*P
old(A|M)+(1-b) * P
new(A|M).Wherein upgrade weight b by the monthly Lookup protocol of reporting the result of visit to user according to customer acceptance center.If this month user's use patterns of change is owing to going away, the physical function impermanency influence factor causing of suddenling change causes, and b value is larger, as: 0.9～1.0; If this month user's use patterns of change is that b value is less because physical function sudden change (as: occurring affecting the disease of mobility) causes, as: 0.0～0.1; If this moon does not have emergency case, b can value 0.5, to adapt to successional use patterns of change.
When judge module 10 judges, threshold value a1 and threshold value a2 are for presetting, the mode of setting is: by object sensor and Wearable equipment static placement a period of time as one hour, calculate the average of the acceleration quadratic sum of the acceleration transducer of object sensor and Wearable equipment in static process, using the average of the acceleration quadratic sum of object sensor (also can get the maximal value of each axial acceleration absolute value of object sensor) as threshold value a1, using the average of the quadratic sum of the acceleration of the acceleration transducer of Wearable equipment (also can get the maximal value of each axial acceleration absolute value of sensor) as threshold value a2.The first detected value A1 and threshold value a1 that identifying unit 12 comparing calculation unit 11 calculate, contrast the second detected value A2 and threshold value a2, as the first detected value A1 is less than or equal to threshold value a1, and the second detected value A2 is less than or equal to threshold value a2, further according to study to user whether use mode decision to obtain the current time period be activity time of user when section, just deducibility goes out user in abnormal inactive state.
Alarm module 20 can send warning by Wearable equipment, object sensor or server, when user is during in active state, may be that Wearable equipment sends alerting signal and object sensor shows that User Activity is normal, show that user may forget to wear Wearable sensor or Wearable sensor battery exhausts or breaks down.At this moment, remind and wear Wearable equipment or remind charging note automatically to send.After certain hour as still without response, enter the artificial treatment patterns such as phone.Only have Wearable sensor and object sensor all to send alerting signal, enter one-level early warning, carry out phone inquiry, reply as nothing, expatriate personnel visit.If two kinds of sensors all do not send alerting signal, show normally, without taking measures.If Wearable sensor does not send alerting signal, object sensor sends alerting signal, illustrates that object sensor may break down, and will enter object sensor maintenance flow process.Alerting signal output determination methods in this measure is as follows: suppose that perceptron is P at the movable probability of certain time period, if current slot perceptron does not have active signal output, and P is greater than certain threshold value as 30% perceptron output alarm signal.This threshold value has determined the susceptibility of system, generally should adjust according to practice.
Study module 30 also can further arrange user's interruption-free time, avoids user to cause unnecessary creating disturbances to.In user's interruption-free time, user does not receive the Human disturbances such as phone.As Wearable equipment, object sensor or server send warning, need to check whether the current time period of living in disturb the period for exempting from, be to wait for exempting to disturb the period to finish.As shown in Figure 8, study module 30 can comprise collecting unit 31, gathers for interruption-free state sample, gathers user's (for example: have a rest and have dinner) Wearable sensor reading sample within the interruption-free period; Extraction unit 32, for extracting the feature of interruption-free state sample of collection, disturbs the reading sample of period inner sensor to be divided into n the period (n value can be estimated optimal value by cross validation) by exempting from.Calculate each period sensor reading sample average and variance.Specific features extracting method is not limited to this, also can adopt the amplitude equalizing value that the sensing data reading in the period is carried out to each frequency band of the statistics of Fourier variation in short-term as feature, and n characteristics of time interval series connection obtained to proper vector.Extract the sensor reading feature of normal period by identical method simultaneously; Training unit 33, for carrying out sorter training according to the feature of extracting, obtains user's the interruption-free time.Carry out the sorter training (exempting to disturb period and normal period) of two classes according to the sample characteristics obtaining.Sorter can adopt the methods such as support vector machine, artificial neural network and random forest.When obtaining after the Wearable sensor reading of a day, be multiple continuous time periods by the sensor reading cutting of this day, duration is identical with the interruption-free period duration average of training use.According to extracting sensor reading feature.And input sorter and adjudicate.When Wearable sensor is worn or when running down of battery there is no reading owing to forgetting, adjudicate according to the interference time section average exempted from of front m (as: 5) day.
The embodiment of the present invention two propose without sound warning device, because above-mentioned two kinds of sensors are all, by built-in acceleration transducer, the motion of human body or object is carried out to perception, there is the low and motion perception advantage accurately of cost compared with pyroelectric sensor, camera.Use in the learning process of pattern user, increased adaptive learning method, improved system user is used in different time, age, health the adaptability of patterns of change.Simultaneously can take phase counter-measure according to two kinds of different alarm condition of sensor, and propose the recognition methods that user exempts from section interference time the cost providing without sound alert service has been provided, improve user's experience, improve service quality and user satisfaction.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, all any amendments of doing within the spirit and principles in the present invention, be equal to and replace and improvement etc., within all should being included in protection scope of the present invention.
Claims (10)
1. without a sound alarm method, it is characterized in that, described method comprises the steps:
Study user uses pattern;
By default dynamic sensing apparatus and state induction equipment, and described study to user use pattern, judge that whether user is in active state;
When user is during in inactive state, send warning.
2. as claimed in claim 1ly it is characterized in that without sound alarm method, described dynamic sensing apparatus is the Wearable equipment with acceleration transducer; Described state induction equipment is the object sensor with acceleration transducer.
3. as claimed in claim 2ly it is characterized in that without sound alarm method, described by default dynamic sensing apparatus and state induction equipment, and described study to user use pattern, judge whether user comprises in active state:
Calculate the interior maximal value of all axial acceleration absolute values of acceleration transducer sum of Wearable equipment of a Preset Time or the maximal value of all axial acceleration absolute values of acceleration transducer of Wearable equipment as the first detected value A1; Calculate the interior maximal value of all axial acceleration absolute value sums of object sensor of described Preset Time or the maximal value of all axial acceleration absolute values of object sensor as the second detected value A2;
When described the first detected value A1 is less than or equal to default threshold value a1, and described the second detected value A2 is less than or equal to default threshold value a2, according to described study to user use mode decision current time whether in user's activity time section, be to judge that user is in inactive state.
4. as claimed in claim 1ly it is characterized in that without sound alarm method, described study is used pattern also to comprise:
The study of user's interruption-free time, and be added in described user's use pattern.
5. as claimed in claim 4ly it is characterized in that without sound alarm method, the study of described user's interruption-free time comprises:
Interruption-free state sample gathers;
Extract the feature of the interruption-free state sample of described collection;
Carry out sorter training according to the feature of described extraction, obtain described user's interruption-free time.
6. without a sound warning device, it is characterized in that, described device comprises:
Study module, uses pattern for learning user;
Judge module, for by default dynamic sensing apparatus and state induction equipment, and described study to user use pattern, judge that whether user is in active state;
Alarm module, for when user is during in inactive state, sends warning.
7. as claimed in claim 6ly it is characterized in that without sound warning device, described dynamic sensing apparatus is the Wearable equipment with acceleration transducer; Described state induction equipment is the object sensor with acceleration transducer.
8. as claimed in claim 7ly it is characterized in that without sound warning device, described judge module comprises:
Computing unit, for calculating the maximal value of all axial acceleration absolute values of acceleration transducer sum of Wearable equipment in a Preset Time or the maximal value of all axial acceleration absolute values of acceleration transducer of Wearable equipment as the first detected value A1; Calculate the interior maximal value of all axial acceleration absolute value sums of object sensor of described Preset Time or the maximal value of all axial acceleration absolute values of object sensor as the second detected value A2;
Identifying unit, for being less than or equal to default threshold value a1 as described the first detected value A1, and described the second detected value A2 is less than or equal to default threshold value a2, according to described study to user use mode decision current time whether in user's activity time section, be to judge that user is in inactive state.
9. as claimed in claim 6ly it is characterized in that without sound warning device, described study module also for:
The study of user's interruption-free time, and be added in described user's use pattern.
10. as claimed in claim 9ly it is characterized in that without sound warning device, described study module comprises:
Collecting unit, gathers for interruption-free state sample;
Extraction unit, for extracting the feature of interruption-free state sample of described collection;
Training unit, for carrying out sorter training according to the feature of described extraction, obtains described user's interruption-free time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410482801.6A CN104200613B (en) | 2014-09-19 | 2014-09-19 | Silent alarming method and silent alarming device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410482801.6A CN104200613B (en) | 2014-09-19 | 2014-09-19 | Silent alarming method and silent alarming device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104200613A true CN104200613A (en) | 2014-12-10 |
| CN104200613B CN104200613B (en) | 2017-05-17 |
Family
ID=52085898
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410482801.6A Active CN104200613B (en) | 2014-09-19 | 2014-09-19 | Silent alarming method and silent alarming device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104200613B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105787504A (en) * | 2016-01-15 | 2016-07-20 | 北京中科天合科技有限公司 | Method and system for identifying human body behaviors |
| CN105915682A (en) * | 2016-06-27 | 2016-08-31 | 深圳市嘉兰图设计股份有限公司 | Alarm clock with alarm function and an emergency alarm method employing the alarm clock |
| CN105931428A (en) * | 2016-06-30 | 2016-09-07 | 北京小米移动软件有限公司 | Alarming method and apparatus |
| CN107360330A (en) * | 2017-08-31 | 2017-11-17 | 努比亚技术有限公司 | Method for early warning and mobile terminal |
| CN107561448A (en) * | 2017-07-24 | 2018-01-09 | 歌尔股份有限公司 | The battery electric quantity alarm method and earphone of earphone |
| CN108091103A (en) * | 2017-12-12 | 2018-05-29 | 中国联合网络通信集团有限公司 | A kind of mobile terminal and its driving method |
Citations (4)
| 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 |
| CN202331717U (en) * | 2011-11-24 | 2012-07-11 | 福建师范大学 | Intelligent home wireless warning device for old persons |
| CN202394339U (en) * | 2011-12-30 | 2012-08-22 | 成都市神州伴侣家庭服务有限公司 | Activity-free condition detecting alarm |
| 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 |
-
2014
- 2014-09-19 CN CN201410482801.6A patent/CN104200613B/en active Active
Patent Citations (4)
| 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 |
| CN202331717U (en) * | 2011-11-24 | 2012-07-11 | 福建师范大学 | Intelligent home wireless warning device for old persons |
| CN202394339U (en) * | 2011-12-30 | 2012-08-22 | 成都市神州伴侣家庭服务有限公司 | Activity-free condition detecting alarm |
| 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 |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105787504A (en) * | 2016-01-15 | 2016-07-20 | 北京中科天合科技有限公司 | Method and system for identifying human body behaviors |
| CN105787504B (en) * | 2016-01-15 | 2020-07-07 | 北京中科天合科技有限公司 | Human behavior recognition method and system |
| CN105915682A (en) * | 2016-06-27 | 2016-08-31 | 深圳市嘉兰图设计股份有限公司 | Alarm clock with alarm function and an emergency alarm method employing the alarm clock |
| CN105931428A (en) * | 2016-06-30 | 2016-09-07 | 北京小米移动软件有限公司 | Alarming method and apparatus |
| CN107561448A (en) * | 2017-07-24 | 2018-01-09 | 歌尔股份有限公司 | The battery electric quantity alarm method and earphone of earphone |
| CN107360330A (en) * | 2017-08-31 | 2017-11-17 | 努比亚技术有限公司 | Method for early warning and mobile terminal |
| CN107360330B (en) * | 2017-08-31 | 2020-03-17 | 努比亚技术有限公司 | Early warning method, mobile terminal and storage medium |
| CN108091103A (en) * | 2017-12-12 | 2018-05-29 | 中国联合网络通信集团有限公司 | A kind of mobile terminal and its driving method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104200613B (en) | 2017-05-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104200613A (en) | Silent alarming method and silent alarming device | |
| US10485452B2 (en) | Fall detection systems and methods | |
| Fang et al. | Developing a mobile phone-based fall detection system on android platform | |
| CN102707305B (en) | Tumble detecting and positioning system and method | |
| CN104334075B (en) | Biometric attributes abnormality detection system with adjustment notice | |
| US11468984B2 (en) | Device, method and application for establishing a current load level | |
| Berrocal et al. | Rich contextual information for monitoring the elderly in an early stage of cognitive impairment | |
| CN107548500A (en) | Event anomalies based on user's routine model | |
| CN103914948A (en) | Senior citizen nursing system based on intelligent mobile terminal and nursing method thereof | |
| CN105913614A (en) | Method and device of monitoring tumbling, intelligent wearable device and tumbling alarm system | |
| CN114446026B (en) | Article forgetting reminding method, corresponding electronic equipment and device | |
| Sharma et al. | Passive WiFi CSI sensing based machine learning framework for COVID-Safe occupancy monitoring | |
| CN108401415A (en) | monitoring method and monitoring device | |
| US20200005618A1 (en) | Anomaly notification system and anomaly notification method | |
| CN109947037A (en) | A kind of monitoring of living environment and method for early warning | |
| CN212694560U (en) | Intelligent Internet of things area management system | |
| KR101766438B1 (en) | A mobile device for detecting abnormal activity and system including the same for supporting management of members in a group | |
| KR102536176B1 (en) | Method of healing uncontact smartphone addiction based on chatbot | |
| US11717217B2 (en) | Stress monitor and stress-monitoring method | |
| US9373089B2 (en) | Intelligent electronic monitoring system | |
| JP2023038803A (en) | Data collection device, data collection system and data collection method | |
| US20230109079A1 (en) | Data collection system, data collection method. and data collection device | |
| US20230108162A1 (en) | Data collection system, data collection device, data acquisition device, and data collection method | |
| KR20190010984A (en) | A module for detecting abnormal activity and system including the same | |
| US11868405B2 (en) | Information processor, information processing method, and recording medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 518000 Guangdong province Shenzhen City Guangming Street million Daiheng high tech Industrial Park No. 5 Building 5 floor Applicant after: Shenzhen City Zhongzhi Kechuang Robot Co., Ltd. Address before: 518000 Guangdong province Shenzhen City Guangming Street million Daiheng high tech Industrial Park No. 5 Building 5 floor Applicant before: Shenzhen Kesong Electronic Co., Ltd. |
|
| COR | Change of bibliographic data | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 518000 Guangdong province Shenzhen City Guangming Street million Daiheng high tech Industrial Park No. 5 Building 5 floor Applicant after: CIIC Kechuang robot Co Ltd Address before: 518000 Guangdong province Shenzhen City Guangming Street million Daiheng high tech Industrial Park No. 5 Building 5 floor Applicant before: Shenzhen City Zhongzhi Kechuang Robot Co., Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PP01 | Preservation of patent right | ||
| PP01 | Preservation of patent right |
Effective date of registration: 20190327 Granted publication date: 20170517 |