WO2015136839A1 - 生活行動推定装置、およびプログラム - Google Patents
生活行動推定装置、およびプログラム Download PDFInfo
- Publication number
- WO2015136839A1 WO2015136839A1 PCT/JP2015/000646 JP2015000646W WO2015136839A1 WO 2015136839 A1 WO2015136839 A1 WO 2015136839A1 JP 2015000646 W JP2015000646 W JP 2015000646W WO 2015136839 A1 WO2015136839 A1 WO 2015136839A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- probability
- living
- estimation
- unit
- behavior
- 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.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/046—Forward inferencing; Production systems
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
- G08B21/0407—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons based on behaviour analysis
- G08B21/0423—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons based on behaviour analysis detecting deviation from an expected pattern of behaviour or schedule
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
- G08B21/0438—Sensor means for detecting
- G08B21/0484—Arrangements monitoring consumption of a utility or use of an appliance which consumes a utility to detect unsafe condition, e.g. metering of water, gas or electricity, use of taps, toilet flush, gas stove or electric kettle
Definitions
- the present invention relates to a living behavior estimation device and a program, and more particularly to a living behavior estimation device and program for estimating a living behavior from the usage status of resources in a house.
- a living behavior estimation device that estimates a living behavior of a resident based on an operating state of an electric device used in a house (see Document 1 [International Publication No. 2013/157175]).
- a rule group is set that concludes a behavior classification that classifies living behavior on the condition of a device classification assigned to distinguish the type for each electrical equipment and an operation state for each electrical equipment. ing.
- an operation state an event such as operation start or operation stop
- the behavior estimation device extracts the behavior category by applying the device category and the operation state of the electrical device to the rule group.
- An object of the present invention is to provide a living behavior estimation device in which the estimation accuracy of living behavior is improved as compared with the conventional configuration, and a program for realizing the living behavior estimation device by a computer.
- the living behavior estimation apparatus includes an acquisition unit, a device operation detection unit, a storage unit, a behavior estimation unit, and an output unit.
- the said acquisition part is comprised so that the data regarding the usage condition of the resource in the apparatus which belongs to the said division may be acquired for every some division in a house.
- the device operation detection unit is configured to detect an operation state indicating whether the device is operating or stopped for each of the categories from data regarding the resource usage status for each of the categories acquired by the acquisition unit.
- the storage unit is configured to previously store a prior probability, a first conditional probability, and a second conditional probability.
- the prior probability is a probability that a plurality of types of living activities set in advance occur each day.
- the first conditional probability is a probability that the device belonging to the category is operating or stopped under a condition in which each of the plurality of types of living behavior occurs.
- the second conditional probability is a probability that the living behavior occurs in each of a plurality of time zones obtained by dividing a day into a plurality of times under the condition in which each of the plurality of types of living behavior occurs. is there.
- the behavior estimation unit is configured to determine the prior probability, the first conditional probability, and the second condition based on an operation state of the device for each of the categories detected by the device operation detection unit at an estimation time point.
- the probability of occurrence of each of the plurality of types of living behavior at the estimated time is obtained based on Bayes' theorem using the attached probability.
- the said action estimation part is comprised so that it may estimate that the living action with the said relatively high generation probability has generate
- the program of the form according to the present invention is a program for causing a computer to function as any one of the above-described living behavior estimation devices.
- the recording medium that records the program may be a computer-readable recording medium.
- the living behavior estimation apparatus estimates the living behavior of a resident (that is, a user) based on the usage status of resources in the devices in each of the plurality of categories set in the house.
- the division is a spatial division in the house and is a classification related to the use in the house. That is, the division is a concept including a place such as a room in a house and a use of the place.
- the resources used in the house include water as well as energy such as electricity and gas.
- the living behavior estimation apparatus described below determines the operating state of the electrical device from the usage state of the power by the electrical device belonging to the category, and estimates the living behavior of the resident based on the operating state of the electrical device.
- the following living behavior estimation apparatus estimates which living behavior the living behavior of the resident at the time of estimation corresponds to among a plurality of preset lifestyle behaviors.
- three states a home state, a going-out state, and a sleep state, are distinguished as living behavior, and the living behavior at the estimated time is estimated.
- the home state refers to a state in which a resident is in the house and is not sleeping.
- the living behavior estimation device can also detect a change in living behavior as an event performed by a resident.
- the living activity estimation device is a bedtime event when changing from home to sleep, a wake-up event when changing from sleep to home, an outing event when changing from home to going out, and a home from going out If it changes to, it is detected as a homecoming event.
- a distribution board 2 installed in a house accommodates one main breaker 21 and a plurality of branch breakers 22.
- the trunk line L1 from the main breaker 21 is branched into branch lines L2 by a plurality of branch breakers 22, respectively, and power is supplied to the electrical equipment 3 connected to the plurality of branch lines L2.
- one electrical device 3 is connected to each branch line L2, but a plurality of electrical devices 3 may be connected to the branch line L2.
- an outlet that is, a receptacle into which the plug of the electric device 3 is inserted may be connected to the branch line L2.
- each room for example, a living room, a kitchen, a bedroom, etc.
- Each branch line L2 is connected to an electrical device 3 in the same section.
- a plurality of branch lines L2 may correspond to one section.
- the electrical device 3 connected to the branch line L2 of the living room is referred to as an electrical device 31
- the electrical device 3 connected to the kitchen branch line L2 is referred to as an electrical device 32
- the electrical device 3 is referred to as an electrical device 33.
- the living behavior estimation apparatus acquires power data used for each branch line L2.
- the power data acquired for each branch line L2 is referred to as power data.
- a power sensor 23 that detects power for each branch line L2 is provided on the load side of each branch breaker 22.
- the power sensor 23 detects the current flowing through the branch line L2 and the line voltage of the branch line L2.
- a Rogowski coil is used to detect the current.
- the output of each power sensor 23 is output to the communication unit 24, and is output from the communication unit 24 to the living behavior estimation apparatus 1.
- the unit for acquiring the power data of the electrical device 3 can be set variously as required.
- This unit may be selected from the trunk line L1, the electric circuit further branched from the branch line L2, the outlet connected to the branch line L2, and the individual electric equipment connected to the branch line L2.
- a power sensor may be provided in an outlet provided on the branch line L2, and power data detected by the power sensor provided in the outlet may be collected by the communication unit 24 and output to the living behavior estimation apparatus 1.
- the communication unit 24 may collect power data detected by a power sensor provided in the electrical device 3 and output it to the living behavior estimation apparatus 1.
- the living behavior estimation apparatus 1 is configured with a device that realizes the function described below as a main hardware element by executing a program.
- a typical example of this type of device is a microcomputer including a processor and a memory. Therefore, in addition to a dedicated device, a program that realizes the functions described below can be executed by a device such as a general-purpose computer, a tablet terminal, or a smartphone, thereby functioning as the living behavior estimation device 1.
- the program may be provided through a telecommunication line such as the Internet or a mobile communication network, or may be provided as a computer-readable recording medium.
- the recording medium is selected from an optical disk, a hard disk, a nonvolatile semiconductor memory, and the like.
- the living behavior estimation apparatus 1 includes an estimation unit 10 (behavior estimation unit), an acquisition unit 12, a detection unit 16 (equipment operation detection unit), and a storage unit 17, as shown in FIG.
- the living behavior estimation apparatus 1 according to the present embodiment further includes an input unit 18 and an update unit 19.
- the living behavior estimation apparatus 1 of the present embodiment further includes a communication unit 11 (communication interface unit), a built-in clock 13, a history storage unit 14, and a registration unit 15.
- the communication unit 11 communicates with the communication unit 24 in the distribution board 2.
- the communication unit 11 receives the power data of each branch line L2 measured every predetermined measurement time (for example, 1 second, 1 minute) from the communication unit 24, and outputs the received power data to the acquisition unit 12. To do.
- the acquisition unit 12 obtains the amount of power per unit time based on the power data input from the communication unit 11 at every predetermined measurement time.
- the unit time is an integral multiple of the measurement time, and is set in a range of, for example, about 30 seconds to 10 minutes.
- the power sensor 23 measures the power value for each divided time obtained by subdividing the measurement time, and the communication unit 24 transmits the average value of the measured power value for each divided time to the living behavior estimation apparatus 1. Also good.
- the acquisition unit 12 can obtain the amount of power by multiplying the average power value input from the communication unit 24 by the measurement time.
- segmentation time based on the electric power value measured by the electric power sensor 23 may be transmitted to the living action estimation apparatus 1 from the communication unit 24.
- the built-in clock 13 measures the date and time.
- the built-in clock 13 is constituted by a real time clock.
- the history storage unit 14 records the amount of power for each branch line L2 obtained by the acquisition unit 12 together with a time stamp using the date and time counted by the built-in clock 13. That is, the history storage unit 14 stores time-series data of electric energy for each branch line L2.
- the capacity of the history storage unit 14 is determined so that time series data of several hours of power can be stored at the shortest, and preferably time series data of one year or more can be stored. Determined.
- the registration unit 15 registers information for distinguishing the electrical equipment 3 in the house in association with information for distinguishing the system of the branch line L2.
- the registration unit 15 not only associates the electrical device 3 with the branch line L2, but also sets information for distinguishing the electrical device 3 in the estimation unit 10 in association with information representing a section in the house.
- information indicating the division in the house is referred to as division information.
- This classification information is, for example, information set in advance when the living behavior estimation apparatus 1 is installed.
- the division information of the electric device 3 connected to each branch line L2 is information regarding the place and application where the electric device 3 is used, and is transmitted from the communication unit 24 of the distribution board 2 to the communication unit 11, for example.
- the registration unit 15 registers the classification information of the electrical equipment 3 connected to each branch line L2 in the estimation unit 10 based on the classification information received by the communication unit 11.
- the classification information of the electrical equipment 3 connected to the branch line L2 is registered in the estimation unit 10.
- categories such as a living room, a kitchen, a dining room, a bathroom, and a bedroom are registered in the estimation unit 10 as the category information of the electrical device 3.
- the classification information of the electrical equipment 3 may be changed.
- the registration unit 15 does not need to set the classification information for all the electric devices 3, and the classification information is necessary for the electric devices 3 connected to each of the plurality of branch lines L ⁇ b> 2 that are necessary for estimating the living behavior. You only have to set it.
- the acquisition part 12 should just acquire the data showing the use condition of a resource, ie, electric power data in this embodiment, about the some branch line L2 to which attention is paid.
- the power data of the branch line L2 to which this type of electrical device 3 is connected is It is not used to estimate living behavior.
- the amount of power for each branch line L2 is input from the history storage unit 14 to the detection unit 16. Based on the change in the amount of power obtained by the acquisition unit 12, the detection unit 16 detects the operating state (whether it is operating or stopped) of the electrical device 3 connected to the corresponding branch line L2. Although there is the electrical device 3 that consumes standby power even when the operation is stopped, in this embodiment, the state that consumes the standby power is regarded as being stopped as the operation state.
- the detection unit 16 determines whether the electrical device connected to the branch line L2 is operating or on standby by comparing the amount of power for each branch line L2 with a predetermined threshold value. Therefore, the detection unit 16 sets a threshold value used for determining the operation state from the amount of power recorded in the history storage unit 14 for each branch line L2. That is, the detection unit 16 minimizes the threshold used for determining the operation state within a range that satisfies the condition that the time during which the power amount of the target branch line L2 continues to be equal to or less than the threshold exceeds the predetermined maintenance time. Set to value. Thus, the threshold value set by the detection unit 16 becomes the peak value of standby power for each branch line L2.
- the storage unit 17 accumulates, as prior probabilities, the probability that each of a plurality of types of living behaviors set in advance (at home, going out, sleeping) in the present day will occur.
- This prior probability may use the value of the occurrence probability of each living behavior from the result of estimating the living behavior in the target house for a predetermined period, or for groups with similar occupation, age and residential area of the resident, A value obtained statistically in advance may be used.
- the storage unit 17 also has a probability that the electrical device 3 belonging to each category is operating or stopped under the conditions in which three types of living behaviors of sleep state, home state, and outing state are generated. (First conditional probability) is accumulated. This probability is obtained from the result of collecting the operation state of the electrical device 3 detected by the detection unit 16 and the living behavior of the resident for a predetermined period, and is accumulated in the storage unit 17. For each category to which the electric device 3 belongs, the probability of whether it is operating or stopped under each of the three types of living behaviors of sleep state, home state, and outing state is obtained in advance, and this value is stored in the storage unit. 17 may be accumulated.
- FIG. 2 is a pie chart showing the ratio of whether the electrical device 31 in the room is operating (on) or stopped (off) under the condition that the living behavior such as the sleep state occurs.
- the probability of operation is B1 (%).
- FIG. 3 is a pie chart showing the ratio of whether the electrical appliance 32 in the kitchen is operating or stopped under the condition that a living behavior such as a sleep state occurs. In the illustrated example, the probability of operating is 0. (%). That is, in the example of FIG. 3, the electrical device 32 is stopped (off).
- FIG. 4 is a pie chart showing the ratio of whether the electrical device 33 in the bedroom is operating or stopped under the condition that the living behavior such as the sleeping state is occurring. In the illustrated example, the probability of operating is 100. (%). That is, in the example of FIG. 4, the electrical device 33 is in operation (on).
- the storage unit 17 stores the life in each of a plurality of time zones obtained by dividing a day into a plurality of times under the conditions in which three types of living behaviors, that is, a home state, a going-out state, and a sleeping state are generated.
- the probability that the action will occur (second conditional probability) is obtained and stored in advance.
- a case where one day is divided into four time zones will be described as an example. That is, the time zone T1 is from 0 o'clock to 6 o'clock, the time zone T 2 is from 6 o'clock to 12 o'clock, the time zone T 3 is from 12 o'clock to 18 o'clock, and the time zone T 4 is from 18 o'clock to 24 o'clock.
- FIG. 5 shows, as a pie chart, the probability that a living behavior such as a sleep state occurs in each of the four time zones T1, T2, T3, and T4.
- the probability that the living behavior of the sleeping state occurs in the time zone T1 is A1 (%)
- the probability that it occurs in the time zone T2 is A2 (%)
- the probability that it occurs in the time zone T3 is 0%
- the time The probability of occurrence in band T4 is A4 (%).
- the probability that a living behavior called a sleep state will occur is 0%, so the probability for the time zone T3 does not appear in the pie chart of FIG.
- the transition probability of the next living behavior is registered in advance for each of the three types of living behaviors, that is, the home state, the going-out state, and the sleeping state. This transition probability is obtained by counting the living behavior at the next estimated time from the living behavior estimated at a certain point of time based on the result of estimating the living behavior every predetermined period, Accumulated in the unit 17.
- FIG. 6 is a state transition diagram in the case where there are three types of living behaviors: a home state, a going-out state, and a sleeping state.
- the probability of transition from the home state to the home state is C1 (%), the probability of transition from the home state to the going-out state is C2 (%), and the probability of transition from the home state to the sleep state is C3 (%). It is.
- the probability of transition from the outing state to the outing state is C4 (%), the probability of transitioning from the outing state to the sleeping state is C5 (%), and the probability of transitioning from the outing state to the home state is C6 (%).
- the probability of transition from the sleep state to the sleep state is C7 (%), the probability of transition from the sleep state to the home state is C8 (%), and the probability of transition from the sleep state to the going-out state is C9 (%).
- the event which changes from a going-out state to a sleeping state and the event which changes from a sleeping state to a going-out state generally do not occur easily.
- the probability C9 of transition to the state is zero.
- the input unit 18 includes a user interface having an operation unit for performing an input operation and a display unit for displaying input contents.
- a user interface having an operation unit for performing an input operation and a display unit for displaying input contents.
- the update unit 19 Based on the feedback information input to the input unit 18, the update unit 19 obtains at least one of the prior probability, the first conditional probability, and the second conditional probability accumulated in the storage unit 17. Update. The update process of the storage unit 17 by the update unit 19 will be described later.
- the operation state of the electric device 3 detected by the detection unit 16 for each branch line L2 is input to the estimation unit 10 as fact information.
- the estimation unit 10 is input as fact information which time zone of the time zones T1, T2, T3, and T4 is included from the time information at the estimation time point. Therefore, the estimation unit 10 uses the fact information about the operating state of the electrical device 3 at the estimated time point and the fact information about the time zone including the estimated time point as input information for the Bayesian network. Since the input information for the Bayesian network is information that has been confirmed as facts, it is hereinafter referred to as confirmed information.
- the fixed information is a general term for input information to the Bayesian network, and includes a plurality of fact information.
- the estimation unit 10 reads the prior probability, the first conditional probability, and the second conditional probability from the storage unit 17 based on the confirmation information. Furthermore, the estimation unit 10 calculates the probability that each living behavior occurs at the estimation time point based on Bayes' theorem by obtaining a joint probability of the first conditional probability and the second conditional probability.
- FIG. 7 shows the relationship between the transition of the power value P1 consumed by the electrical device 31, the transition of the power value P2 consumed by the electrical device 32, the transition of the power value P3 consumed by the electrical device 33, and the living behavior of the resident. It is the graph which illustrated about one day.
- the power value P1 consumed by the electric appliance 31 in the room is displayed by a solid line
- the power value P2 consumed by the electric appliance 32 in the kitchen is displayed by a broken line
- the power value P3 consumed by the electric appliance 33 in the bedroom is It is shown with a dashed-dotted line.
- the estimation unit 10 estimates the living behavior at 17:00 in the example of FIG. 7, the estimation unit 10 reads the operation state of the electrical devices 31, 32, and 33 at 17:00 from the detection unit 16 as first fact information. .
- the electrical device 31 in the room is operating, the electrical device 32 in the kitchen is stopped, and the electrical device 33 in the bedroom is stopped at 17:00.
- the estimation part 10 calculates
- the calculation process in which the estimation unit 10 calculates the occurrence probability of each living behavior (at home state, outing state, sleeping state) at 17:00 will be described with reference to the Bayesian network shown in FIG. FIG. 8 shows the life behavior to be calculated, the probability (first conditional probability) that the electrical devices 31, 32, and 33 are operating or stopped in the state where the life behavior to be calculated is generated, and the determination It is the figure which described as a graphical model the relationship with the probability (2nd conditional probability) that the living action of operation object will occur in the time slot
- the estimation unit 10 reads the prior probability that the home state will occur within one day from the storage unit 17.
- the estimation unit 10 reads, from the storage unit 17, the probabilities that the operation states of the electrical devices 31, 32, and 33 detected by the detection unit 16 occur under the home state. For example, taking the operation state at 17:00 in FIG. 7 as an example, the estimation unit 10 determines from the storage unit 17 the probability that the electric device 31 is operating and the electric devices 32 and 33 are stopped under the home state. read out. In addition, the estimation unit 10 reads from the storage unit 17 the probability that a home state will occur in a time zone including the determination time (a time zone T3 from 12:00 to 18:00 if 17:00).
- the estimation part 10 calculates
- the estimation unit 10 determines that a living action with a relatively high probability is currently occurring. . Note that the estimation unit 10 may determine that a living action having a relatively high probability and a significant difference compared to the occurrence probability of other living actions is currently occurring. Then, when estimating the living behavior occurring at the estimation time point, the estimating unit 10 outputs the estimation result or the occurrence probability of each living behavior.
- the estimation unit 10 can estimate the living behavior of the resident from the operating state of the electrical device 3 throughout the day by periodically performing the above-described estimating operation of the living behavior (for example, every few minutes). . Moreover, the estimation part 10 can detect the change of living behavior as an event. For example, the estimation unit 10 is a wake-up event when the sleep state ends, a go-out event that is the start time of the go-out state from the home state, and a start time of the home state that is the start time of the go-out state from the go-out state. Detect as a homecoming event.
- the estimation unit 10 may use the transition probability accumulated in the storage unit 17 for the probability inference of living behavior.
- a calculation process in the case where the estimation unit 10 obtains the occurrence probability of the living behavior at a certain time in combination with the transition probability from the living behavior one time before will be described with reference to the Bayesian network shown in FIG.
- FIG. 9 shows the life behavior to be calculated, the life behavior one point before, and the probability that the electrical devices 31, 32, and 33 are operating or stopped in a state where the life behavior to be calculated is generated. It is the figure which described the relationship with the probability that the living action of calculation object will occur in the time slot
- the estimating unit 10 When estimating the living behavior at a certain time, the estimating unit 10 reads the operating state of the electric devices 31, 32, 33 at the estimated time from the detecting unit 16 as first fact information. Moreover, the estimation part 10 calculates
- the estimation unit 10 when obtaining the occurrence probability of the home state, the estimation unit 10 reads from the storage unit 17 the prior probability that the home state will occur within one day. Further, the estimating unit 10 stores the transition probability that the living behavior transitions to the home state when the living behavior one time before (previous estimated time) is any of the home state, the outing state, and the sleep state. Read from. Furthermore, the estimation unit 10 reads from the storage unit 17 the probabilities that the operation states of the electrical devices 31, 32, and 33 detected by the detection unit 16 occur under the home state.
- the estimation unit 10 applies the probability read from the storage unit 17 to the corresponding node of the Bayesian network, and obtains the joint probability, thereby obtaining the probability that the home state occurs at the estimation time point. Moreover, the estimation part 10 calculates
- the living behavior is estimated using the transition probability, the possibility of estimating a living behavior having a low probability of occurrence in daily life is reduced, so that the estimation accuracy of the living behavior is improved. For example, since the transition probability of becoming a sleep state next to the out-of-going state or the transition probability of going out after the sleep state is low in daily life, the possibility that such a living behavior is estimated is reduced.
- the user of the living behavior estimation apparatus 1 inputs feedback information indicating a mismatch between the estimation result of the living behavior and the actual living behavior (true value) to the living behavior estimation apparatus 1, and the storage unit 17. It is also preferable to update the probability information stored in the.
- the estimation part 10 of the living behavior estimation apparatus 1 transmits the estimation result of the living behavior to the portable terminal possessed by the guardian who is going out, and the guardian grasps the living behavior of the child from the outside. An explanation will be given.
- the estimating unit 10 of the living behavior estimation apparatus 1 periodically estimates the living behavior.
- the estimation unit 10 estimates that a return home event has occurred when the child returns from a state in which all the residents are out, and sends a push notification, for example, by e-mail to the portable terminal owned by the guardian.
- the living behavior estimation apparatus 1 includes a communication unit that can be connected to an electric communication line such as the Internet or a mobile communication network.
- the estimation unit 10 transmits an e-mail notifying the occurrence of the return home event from the communication unit to a pre-registered email address of the mobile terminal.
- the parent who has received the push notification from the living behavior estimation apparatus 1 calls the telephone in the house or the mobile phone possessed by the child and confirms the fact of the return home and the return home time, Can determine whether the estimation result of the living behavior estimation apparatus 1 is correct.
- the guardian is expected not to input feedback information to the living behavior estimation device 1.
- the update unit 19 does not update various probability data stored in the storage unit 17, but there is no problem because a correct estimation result is obtained.
- the guardian is expected to input feedback information to the living behavior estimation device 1 and update various probability data stored in the storage unit 17.
- the living behavior estimation device 1 estimates that a homecoming event has occurred and sends an e-mail notifying the homecoming event to a portable terminal possessed by the parent, the guardian who has gone out confirms with the child As a result, the case where the child has not come home will be described as an example.
- the guardian (resident) confirms the fact that the child has not come home when the living behavior estimation apparatus 1 estimates that he / she has returned home, and confirms the time when the child has actually returned home, and operates the input unit 18 after returning home, Enter the actual return time.
- the update unit 19 performs an update process on the storage unit 17 based on the feedback information input from the input unit 18. For example, if the estimation unit 10 estimates that the return home event has occurred at 16:00, but the actual return home event is at 17:00, the guardian may return the actual return home When the event is 17:00, the event is input using the input unit 18.
- the update unit 19 is the first operating in the outing state for the electrical device 3 that is detected as operating in the outing state.
- the conditional probability is updated to increase by a predetermined amount.
- the updating unit 19 updates the electrical equipment 3 that is detected to be stopped under the outing condition so as to increase the first conditional probability of being stopped under the outing condition by a predetermined amount.
- the update unit 19 determines the first conditional probability that the electrical device 3 detected as operating under the home state is operating under the home state. Update to lower only the fixed amount. The update unit 19 updates the electrical device 3 detected as being stopped under the home state so as to lower the first conditional probability of being stopped under the home state by a predetermined amount.
- the updating unit 19 updates the prior probability that the going-out state will occur within a day by a predetermined amount, and further, the going-out state is generated in each of the plurality of time zones T1, T2, T3, T4. Change the conditional probability of 2. Further, the update unit 19 updates the prior probability that the home state will occur within a day by a predetermined amount, and further the home state occurs in each of a plurality of time zones T1, T2, T3, and T4. Change the second conditional probability.
- the guardian does not receive a home event notification from the living behavior estimation device 1 when he / she calls the telephone in the house or the mobile phone held by the child and confirms that the child has returned home, Check the actual return time from the child. Then, the guardian operates the input unit 18 after returning home, and inputs the actual return time.
- the update unit 19 performs an update process on the storage unit 17 based on the feedback information input from the input unit 18. For example, if the estimation unit 10 still estimates that the user has gone out at 15 o'clock even though he / she has actually returned home at 15:00, the guardian will be in the wrong state after 15 o'clock, and the actual return event will be at 15 o'clock. Is input using the input unit 18.
- the update unit 19 uses the first conditional probability that the electric device 3 that has been detected to be operating under the outing state is operating under the outing state. Is updated by a predetermined amount. In addition, the updating unit 19 reduces the first conditional probability that the electrical device 3 that has been detected to be stopped under the outing state by a predetermined amount is stopped under the outing state. Update.
- the update unit 19 uses the first conditional probability that the electrical device 3 that has been detected to be operating under the home state is operating under the home state. Update to be higher by a predetermined amount. In addition, the update unit 19 increases the first conditional probability that the electrical device 3 that has been detected to be stopped under the home state is stopped by a predetermined amount under the home state. Update.
- the updating unit 19 updates the prior probability that the home state will occur in one day by a predetermined amount, and further the home state is generated in each of the plurality of time zones T1, T2, T3, and T4. Change the conditional probability of 2. Further, the updating unit 19 updates the prior probability that the outing state will occur within one day by a predetermined amount, and the outing state occurs in each of the plurality of time zones T1, T2, T3, and T4. Change the second conditional probability.
- the updating unit 19 updates the probability data related to the feedback information among the probability data stored in the storage unit 17 based on the feedback information input from the input unit 18.
- the estimation accuracy of can be improved.
- the estimation unit 10 detects a change in the estimation result of the living behavior as an event, and records a pattern in which this event occurs in one day.
- the estimation unit 10 may detect an abnormality in the living behavior when the occurrence timing of the event detected after the pattern is recorded deviates from the pattern.
- FIG. 11 shows the frequency distribution of the estimated return time, and the frequency distribution of the estimated return time is a normal distribution with the average value at time t1.
- the estimation unit 10 determines from the history of the estimated return home time that the estimated return home time when the occurrence of the return home event is detected is a predetermined range including the average value t1 (for example, from time t2 to time t3). It is determined that an abnormality has occurred in the living behavior.
- the estimating unit 10 determines that an abnormality has occurred in the living behavior, for example, a push notification that causes the communication unit to transmit an e-mail notifying that an abnormality has occurred in the living behavior to the portable terminal possessed by the guardian I do.
- the resident return event is recorded every day on weekdays. However, the resident return event may be recorded every day of the week when the rhythm of the resident's life is the same.
- the abnormality of the wakeup event may be notified by detecting the abnormality of the wakeup event.
- the estimation unit 10 may record a pattern in which a resident's wake-up event is repeated every day, and may detect an abnormality in living behavior because the wake-up event occurs out of the pattern. Applicable to.
- the living behavior estimation apparatus 1 of the present embodiment includes the acquisition unit 12, the detection unit 16 (equipment operation detection unit), the storage unit 17, and the estimation unit 10 (behavior estimation unit).
- the acquisition unit 12 is configured to acquire data relating to the resource usage status in a device (in this embodiment, the electric device 3) belonging to the category for each of the plurality of categories in the house.
- the detection unit 16 is configured to detect an operation state indicating whether the device is operating or stopped for each category from the data regarding the resource usage status for each category acquired by the acquisition unit 12.
- the storage unit 17 is configured to store in advance a prior probability, a first conditional probability, and a second conditional probability. Prior probabilities are probabilities that multiple types of living behavior will occur each day.
- the first conditional probability is a probability that a device belonging to a category is operating or stopped under a condition in which each of a plurality of types of living behaviors occurs.
- the second conditional probability is a probability that the living behavior occurs in each of a plurality of time zones obtained by dividing the day into a plurality of times under the condition in which each of the plurality of types of living behavior occurs.
- the estimation unit 10 uses the prior probabilities, the first conditional probabilities, and the second conditional probabilities based on the operation states of the devices for each category detected by the detection unit 16 at the estimation time.
- the probability of occurrence of each of a plurality of types of living behavior is calculated based on Bayes' theorem.
- the estimation part 10 is comprised so that it may estimate that the living action with a relatively high probability of occurrence has occurred at the estimated time.
- the estimation unit 10 uses the operation state of the device at the time of estimation as input information, and uses a plurality of types of living behaviors using the prior probability, the first conditional probability, and the second conditional probability accumulated in the storage unit 17. Is calculated based on Bayes' theorem. Therefore, it is possible to evaluate which living behavior is more likely to occur from the probability of occurrence of multiple types of living behavior, and to accurately estimate the living behavior at the estimated time compared to the conventional example Can be estimated.
- the device is an electrical device 3, and a distribution board 2 in the house and a plurality of branch lines L2 are connected.
- Each of the plurality of branch lines L2 is connected to at least one electric device 3 among the plurality of electric devices 3 belonging to the plurality of sections.
- Each of the plurality of branch lines L2 feeds power from the distribution board 2 to at least one electrical device 3 connected thereto.
- the acquisition unit 12 is also preferably configured to acquire power data for each branch line L2.
- the detection unit 16 determines the amount of power for each branch line L2 acquired by the acquisition unit 12 for each section. It is possible to detect whether the electrical equipment 3 in the category is operating or stopped.
- the storage unit 17 stores in advance the transition probability of the next living behavior among the plurality of types of living behavior after the occurrence of the living behavior for each of the plurality of types of living behavior. It may be configured as follows. And it is preferable that the estimation part 10 is comprised so that a transition probability may be included in the calculation of the probability of occurrence of each of a plurality of types of living behaviors at the estimated time. Since there is a living action with a low probability of occurring next in a state where a certain living action is occurring, the estimation accuracy of the living action is improved by using the transition probability for estimating the living action.
- the living behavior estimation apparatus 1 may further include an input unit 18 and an update unit 19.
- the input unit 18 receives feedback information indicating a mismatch between the estimation result of the estimation unit 10 and the living behavior actually performed by the user at the estimation time.
- the update unit 19 updates at least one of the prior probability, the first conditional probability, and the second conditional probability accumulated in the storage unit 17 based on the feedback information received by the input unit 18. .
- the update unit 19 updates the probability information accumulated in the storage unit 17 based on the feedback information, so that the estimation accuracy of the living behavior can be improved.
- the plurality of types of living behavior include a home state, a going-out state, and a sleep state.
- the living behavior of the resident can be estimated by being classified into a home state, a going-out state, and a sleep state.
- the living behaviors to be estimated by the estimating unit 10 are not limited to the home state, the outing state, and the sleeping state. For example, even if the living behavior in the house is estimated in more detail, such as a meal state or a bathing state. Good.
- the estimation unit 10 periodically detects a change in the estimation result of the living behavior as an event, and records a pattern in which the event occurs in one day (a pattern repeated every day).
- the estimation unit 10 may be configured to detect an abnormality in living behavior when the timing at which an event detected after the pattern is recorded deviates from the pattern. From the result of obtaining the resource usage status by the device for each category, the estimation unit 10 can estimate the living behavior and further detect abnormalities in the living behavior.
- the program according to the present embodiment is a program for causing a computer to function as the above-described living behavior estimation apparatus 1.
- the program may be recorded on a computer-readable recording medium, and the computer may execute the program recorded on the recording medium or may be executed by the computer after the program recorded on the recording medium is installed in the computer.
- the program may be provided through a telecommunication line such as the Internet.
- the case where the device that consumes the resource is an electric device has been described as an example.
- the operating state of the gas device may be determined from the gas usage status.
- the use status of the gas is acquired from a flow rate detected by a flow rate sensor provided in the gas flow path or information detected by various sensors provided in the gas device.
- the operation state of the water use device may be determined from the water use status.
- the use status of water is acquired from, for example, a flow rate detected by a flow rate sensor provided in the flow path of water or information detected by various sensors provided in the water utilization device.
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Emergency Management (AREA)
- Gerontology & Geriatric Medicine (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Economics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Social Psychology (AREA)
- Psychology (AREA)
- Psychiatry (AREA)
- Computational Linguistics (AREA)
- Mathematical Analysis (AREA)
- Probability & Statistics with Applications (AREA)
- Algebra (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Telephonic Communication Services (AREA)
- Alarm Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Description
Claims (7)
- 取得部と、機器動作検出部と、記憶部と、行動推定部とを備え、
前記取得部は、住宅内の複数の区分ごとに、前記区分に属する機器での資源の使用状況に関するデータを取得するように構成され、
前記機器動作検出部は、前記取得部が取得した前記複数の区分ごとの資源の使用状況に関するデータから前記複数の区分ごとに前記区分に属する前記機器が動作中か停止中かを示す動作状態を検出するように構成され、
前記記憶部は、予め設定された複数種類の生活行動が1日のうちでそれぞれ発生する事前確率と、前記複数種類の生活行動の各々が発生している条件のもとで前記区分に属する前記機器が動作中又は停止中である第1の条件付き確率と、前記複数種類の生活行動の各々が発生している条件のもとで、その生活行動が1日を複数に分割した複数の時間帯の各々で発生する第2の条件付き確率と、を予め蓄積するように構成され、
前記行動推定部は、推定時点において前記機器動作検出部によって検出された前記複数の区分ごとの前記機器の動作状態をもとに、前記事前確率と前記第1の条件付き確率と前記第2の条件付き確率とを用いて、推定時点において前記複数種類の生活行動のそれぞれが発生する発生確率をベイズの定理に基づいて求め、前記発生確率が相対的に高い生活行動が前記推定時点において発生していると推定するように構成された
ことを特徴とする生活行動推定装置。 - 前記機器は電気機器であり、
前記住宅内の分電盤と、複数の分岐線が接続されており、
前記複数の分岐線のそれぞれは、前記複数の区分に属する複数の前記電気機器のうち少なくとも1つの電気機器と接続されており、
前記複数の分岐線のそれぞれは、前記分電盤から、前記接続された少なくとも1つの前記電気機器に給電を行い、
前記取得部は、前記分岐線ごとに電力データを取得するように構成されたことを特徴とする請求項1記載の生活行動推定装置。 - 前記記憶部は、前記複数種類の生活行動の各々について、当該生活行動の発生後、前記複数種類の生活行動のうち次に発生する生活行動の遷移確率を予め蓄積するように構成され、
前記行動推定部は、前記推定時点において前記複数種類の生活行動の各々が発生する発生確率の演算に前記遷移確率を含めるように構成されたことを特徴とする請求項1又は2の何れかに記載の生活行動推定装置。 - 前記行動推定部の推定結果と、前記推定時点で実際に利用者によって行われた生活行動との不一致を示すフィードバック情報を受け付ける入力部と、
前記入力部で受け付けた前記フィードバック情報をもとに、前記記憶部に蓄積された前記事前確率と前記第1の条件付き確率と前記第2の条件付き確率のうちの少なくとも1つを更新する更新部とを備えたことを特徴とする請求項1~3の何れか1項に記載の生活行動推定装置。 - 前記複数種類の生活行動は、在宅状態、外出状態、睡眠状態を含むことを特徴とする請求項1~4の何れか1項に記載の生活行動推定装置。
- 前記行動推定部は、前記生活行動の推定結果の変化を事象として定期的に検出し、前記事象が1日のうちで発生するパターンを記録し、前記パターンの記録後に検出された事象の発生するタイミングが前記パターンからずれている場合には前記生活行動の異常を検知するように構成されたことを特徴とする請求項1~5の何れか1項に記載の生活行動推定装置。
- コンピュータを、請求項1~6の何れか1項に記載の生活行動推定装置として機能させるためのプログラム。
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| EP15762341.4A EP3118780A4 (en) | 2014-03-11 | 2015-02-12 | Lifestyle behavior estimating device, and program |
| US15/122,327 US20160371593A1 (en) | 2014-03-11 | 2015-02-12 | Living activity inference device, and program |
| JP2016507290A JPWO2015136839A1 (ja) | 2014-03-11 | 2015-02-12 | 生活行動推定装置、およびプログラム |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2014-048001 | 2014-03-11 | ||
| JP2014048001 | 2014-03-11 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2015136839A1 true WO2015136839A1 (ja) | 2015-09-17 |
Family
ID=54071302
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2015/000646 Ceased WO2015136839A1 (ja) | 2014-03-11 | 2015-02-12 | 生活行動推定装置、およびプログラム |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US20160371593A1 (ja) |
| EP (1) | EP3118780A4 (ja) |
| JP (1) | JPWO2015136839A1 (ja) |
| WO (1) | WO2015136839A1 (ja) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2018026006A (ja) * | 2016-08-10 | 2018-02-15 | オムロン株式会社 | 見守り装置、見守り方法、および見守りプログラム |
| JP2018147316A (ja) * | 2017-03-07 | 2018-09-20 | 東海警備保障株式会社 | 住戸セキュリティシステム |
| JP2019220100A (ja) * | 2018-06-22 | 2019-12-26 | 株式会社Nttドコモ | 推定装置 |
| JP2022165117A (ja) * | 2021-04-19 | 2022-10-31 | 沖電気工業株式会社 | データ分析装置、データ分析方法、プログラムおよびデータ分析システム |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9721208B2 (en) * | 2012-04-19 | 2017-08-01 | Panasonic Intellectual Property Management Co., Ltd. | Living activity inference device, program, and computer-readable recording medium |
| EP3353567A4 (en) * | 2015-09-21 | 2019-04-17 | Saab AB | DETECTION OF OBJECTS IN IMAGES |
| US11690561B2 (en) * | 2018-03-09 | 2023-07-04 | Panasonic Intellectual Property Management Co., Ltd. | Cognitive function evaluation system |
| WO2020261624A1 (ja) * | 2019-06-27 | 2020-12-30 | パナソニックIpマネジメント株式会社 | 情報管理システム、情報管理装置および情報管理方法 |
| CN110579807B (zh) * | 2019-09-06 | 2021-07-23 | 合创汽车科技有限公司 | 生命体探测方法、装置、计算机设备和存储介质 |
| FR3104303B1 (fr) * | 2019-12-04 | 2022-07-15 | Electricite De France | Procédés et dispositifs pour la surveillance d’évolutions d’habitudes de vie |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008112267A (ja) * | 2006-10-30 | 2008-05-15 | Hitachi Ltd | 電力使用量による生活見守り方法およびシステム |
| JP2011043984A (ja) * | 2009-08-21 | 2011-03-03 | Central Res Inst Of Electric Power Ind | 電力需要家居住者の生活状況推定方法およびシステム並びに生活状況推定用プログラム |
| WO2013058820A1 (en) * | 2011-10-21 | 2013-04-25 | Nest Labs, Inc. | User-friendly, network connected learning thermostat and related systems and methods |
| WO2013157175A1 (ja) * | 2012-04-19 | 2013-10-24 | パナソニック株式会社 | 生活行動推定装置、プログラム、コンピュータ読み取り可能な記録媒体 |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3996428B2 (ja) * | 2001-12-25 | 2007-10-24 | 松下電器産業株式会社 | 異常検知装置及び異常検知システム |
| US20040030531A1 (en) * | 2002-03-28 | 2004-02-12 | Honeywell International Inc. | System and method for automated monitoring, recognizing, supporting, and responding to the behavior of an actor |
| US20060123150A1 (en) * | 2004-11-24 | 2006-06-08 | Sharp Kabushiki Kaisha | Electronic apparatus and status information presenting apparatus |
| US7710824B1 (en) * | 2007-09-18 | 2010-05-04 | Sprint Communications Company L.P. | Location monitoring and sonar determination of presence |
| US8417481B2 (en) * | 2008-09-11 | 2013-04-09 | Diane J. Cook | Systems and methods for adaptive smart environment automation |
| US7917580B2 (en) * | 2009-06-05 | 2011-03-29 | Creative Technology Ltd | Method for monitoring activities of a first user on any of a plurality of platforms |
| KR101611287B1 (ko) * | 2009-11-13 | 2016-04-11 | 엘지전자 주식회사 | 지능형 계측 기기 |
| GB2491109B (en) * | 2011-05-18 | 2014-02-26 | Onzo Ltd | Identification of a utility consumption event |
-
2015
- 2015-02-12 JP JP2016507290A patent/JPWO2015136839A1/ja not_active Withdrawn
- 2015-02-12 EP EP15762341.4A patent/EP3118780A4/en not_active Withdrawn
- 2015-02-12 US US15/122,327 patent/US20160371593A1/en not_active Abandoned
- 2015-02-12 WO PCT/JP2015/000646 patent/WO2015136839A1/ja not_active Ceased
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008112267A (ja) * | 2006-10-30 | 2008-05-15 | Hitachi Ltd | 電力使用量による生活見守り方法およびシステム |
| JP2011043984A (ja) * | 2009-08-21 | 2011-03-03 | Central Res Inst Of Electric Power Ind | 電力需要家居住者の生活状況推定方法およびシステム並びに生活状況推定用プログラム |
| WO2013058820A1 (en) * | 2011-10-21 | 2013-04-25 | Nest Labs, Inc. | User-friendly, network connected learning thermostat and related systems and methods |
| WO2013157175A1 (ja) * | 2012-04-19 | 2013-10-24 | パナソニック株式会社 | 生活行動推定装置、プログラム、コンピュータ読み取り可能な記録媒体 |
Non-Patent Citations (1)
| Title |
|---|
| See also references of EP3118780A4 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2018026006A (ja) * | 2016-08-10 | 2018-02-15 | オムロン株式会社 | 見守り装置、見守り方法、および見守りプログラム |
| JP2018147316A (ja) * | 2017-03-07 | 2018-09-20 | 東海警備保障株式会社 | 住戸セキュリティシステム |
| JP2019220100A (ja) * | 2018-06-22 | 2019-12-26 | 株式会社Nttドコモ | 推定装置 |
| JP7112896B2 (ja) | 2018-06-22 | 2022-08-04 | 株式会社Nttドコモ | 推定装置 |
| JP2022165117A (ja) * | 2021-04-19 | 2022-10-31 | 沖電気工業株式会社 | データ分析装置、データ分析方法、プログラムおよびデータ分析システム |
Also Published As
| Publication number | Publication date |
|---|---|
| US20160371593A1 (en) | 2016-12-22 |
| EP3118780A4 (en) | 2017-03-22 |
| JPWO2015136839A1 (ja) | 2017-04-06 |
| EP3118780A1 (en) | 2017-01-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2015136839A1 (ja) | 生活行動推定装置、およびプログラム | |
| CA2864739C (en) | Method and system for forecasting power requirements using granular metrics | |
| Kleiminger et al. | Occupancy detection from electricity consumption data | |
| Monacchi et al. | GREEND: An energy consumption dataset of households in Italy and Austria | |
| US20150268281A1 (en) | System and method for monitoring, analyzing and acting upon electricity patterns | |
| JP5928916B2 (ja) | 行動管理装置、行動管理方法およびプログラム | |
| JP6190309B2 (ja) | 消費電力量に基づいて生活パターンを推定する装置、プログラム及び方法 | |
| JP6297876B2 (ja) | 消費電力量に基づいて生活行動パターンを抽出する装置、プログラム及び方法 | |
| JP6197258B2 (ja) | 行動予測装置、プログラム | |
| CN102565525A (zh) | 功耗遵守监测系统和方法 | |
| JP6308465B2 (ja) | 給電制御装置、給電制御システム、プログラム | |
| JP2018107751A (ja) | 宅内構成員の異常状態判断方法及びサーバ | |
| JP6190301B2 (ja) | 消費電力量から推定された生活行動を比較評価可能な装置、プログラム及び方法 | |
| JP6410191B2 (ja) | 行動管理装置、行動管理方法およびプログラム | |
| JPWO2017104237A1 (ja) | 情報処理装置、その情報処理方法、およびプログラム | |
| JP2015089163A (ja) | 行動評価装置、行動評価システム、行動評価方法、プログラム | |
| JP5984095B2 (ja) | 行動管理装置、行動管理方法およびプログラム | |
| Reinhardt et al. | Can smart plugs predict electric power consumption? A case study | |
| US10811901B2 (en) | System and method to determining efficiency of a smart appliance and providing feedback based of efficiencies of similar smart appliances in a smart grid network | |
| CN113447711A (zh) | 具有老人用电异常报警功能的智能电表及其报警方法 | |
| EP2991235A1 (en) | Method of monitoring and corresponding electronic device, computer readable program product and computer readable storage medium | |
| JP5715394B2 (ja) | エネルギー管理情報報知システム及びエネルギー管理情報報知方法 | |
| JP5452558B2 (ja) | 見守りシステム、見守り装置及び見守り方法 | |
| JP2020160932A (ja) | 電力予測方法及び電力予測システム | |
| JP5633069B2 (ja) | 使用電力量に基づく健康維持状態推定装置及び推定方法 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 15762341 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 2016507290 Country of ref document: JP Kind code of ref document: A |
|
| REEP | Request for entry into the european phase |
Ref document number: 2015762341 Country of ref document: EP |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2015762341 Country of ref document: EP |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 15122327 Country of ref document: US |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |