JP2013131096A - Danger determination system, danger determination method and danger determination program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a danger determination system capable of automatically determining whether or not a target person is in danger at home.SOLUTION: A histogram generation section 31 generates daily histograms concerning power consumption at home, the power consumption which is acquired at a fixed time interval for each day during a specified period in the past and accumulated in a power data storage section 21. A data filtering section 32 selects a day including the lowest power consumption from among the histograms, and calculates a degree of separation between a low consumption class and a high consumption class separated by a discriminant analysis method for each day to select a day on which the degree of separation becomes the largest. Then a threshold value calculation section 33 takes a threshold value of the day on which the degree of separation becomes the largest as the maximal value for power consumption of appliances under automatic operation and a value calculated based on the minimal power consumption of the day including the lowest power consumption as the minimal value for the power consumption of the appliances under automatic operation, and sets the threshold value and the calculated value as a first threshold value and a second threshold value, respectively, used for determining whether or not a person is in danger.

Description

  The present invention relates to a dangerous state determination system, a dangerous state determination method, and a dangerous state determination program, and in particular, a dangerous state determination for monitoring an elderly person living alone by using the result of acquiring power consumption in the house. The present invention relates to a system, a dangerous state determination method, and a dangerous state determination program.

  In recent years, in view of the increase in the number of elderly living alone, Non-Patent Document 1 “Self-living elderly monitoring system-Demonstration test in Sabae City” (Electric Power Research Institute, Research Report R09014) and Non-Patent Document 2 System for watching elderly living alone from their usage (Part 2) -Method using cumulative frequency distribution of changes in total load current- "(Electric Power Research Institute, Research Report R05013) and Non-Patent Document 3 As described in “Emergency Call Service for Apartment Houses” (Safety Center Co., Ltd.) and others, development of a watching system for watching a single person living alone from a remote location is in progress. Although many of these monitoring systems do not require urgency, they consider not only the need to monitor the normal activities of the elderly living alone, but also the safety confirmation for the elderly living alone. Has been.

Central Research Institute of Electric Power, “Self-existing Elderly Monitoring System-Demonstration Test in Sabae City”, Research Report R09014, May 2010, http://criepi.denken.or.jp/jp/kenkikaku/report/ download / uUtRMCXDU9WjHMJ9GfExmbe6q6tfrQqk / report.pdf Central Research Institute of Electric Power Industry, “System for watching elderly living alone from the use of electricity (Part 2)-Method using cumulative frequency distribution of total load current change”, Research report R05013, June 2006, http: //criepi.denken.or.jp/jp/kenkikaku/report/leaflet/R05013.pdf Safety Center Co., Ltd. “Emergency call service for collective housing for elderly people”, http://azc.azbil.com/service/jutaku/shikumi.html

  Non-Patent Document 1, Non-Patent Document 2, and the like describe a technique for estimating the amount of human activity in the home from fluctuations in the current flowing through each device in the home.

  However, the person in charge and family members who refer to the output result of the estimated amount of human activity are appropriately determined as to whether or not the current state of the human being in the house is a dangerous state. The mechanism for determining whether or not a person in the house is in a dangerous state is not automated, and it is impossible to avoid the occurrence of human error.

  Here, the “dangerous state” means a state in which a person living at home cannot act for some reason, for example, a state of being seriously injured or suffering from a serious sudden illness or being unconscious. It means that you have fallen into the state of.

  The present invention has been made in view of such circumstances, and a dangerous state determination system and a dangerous state determination method capable of automatically determining whether or not a human state in a target house is in a dangerous state. It is an object of the present invention to provide a dangerous state determination program.

  The present invention comprises the following technical means in order to solve the above-mentioned problems.

  The first technical means is a dangerous state determination system for determining a human dangerous state in a target house, and a predetermined time interval for power consumption per day in a predetermined period in the house in the past. Applying a discriminant analysis method (Discriminant Analysis Method) to the means for obtaining the histogram, the means for generating the histogram for the power consumption per day in the acquired home, and the generated daily histogram, Means for calculating the degree of separation to be separated into two classes of a low consumption class with low power consumption and a high consumption class with large power consumption for each day, and selecting a day on which the calculated degree of separation is maximized; Deriving a threshold for separation into the two classes on the selected day, and the device automatically driving the derived threshold without any human operation. Considering it as the maximum value of power consumption in the state of automatic driving, the power consumption is the smallest in each of the means for setting as a first threshold for determining a human dangerous state and the generated daily histogram. Means for extracting the minimum power consumption for each day, selecting the minimum power consumption with the smallest power consumption from the extracted daily minimum power consumption, and the device based on the selected minimum power consumption Means for calculating a minimum value of power consumption in the state of automatic driving and setting the calculated minimum value of power consumption as a second threshold for determining a human dangerous state; Features.

  In the dangerous state determination system according to the first technical means, the second technical means is configured to determine the dangerous state of the person in the house on the latest date in the past or the selected day, and A state in which power data relating to power consumption is acquired, and each of the acquired power data is sequentially compared with the first threshold and the second threshold in time series, and the acquired power data does not exceed the first threshold Or means for calculating, as a dangerous state determination result indicating a human dangerous state in the house, a determination result that determines whether or not the state that does not decrease below the second threshold continues beyond a predetermined limit time Is further provided.

  A third technical means is a dangerous state determination method for determining a human dangerous state in a target house, and a predetermined time interval for power consumption per day in a predetermined period in the house in the past. Applying a discriminant analysis method to the acquired histogram for the power consumption for each day in the home acquired, and the generated histogram for each day, Calculating a degree of separation for each day into two classes, a low-consumption class with low power consumption and a high-consumption class with large power consumption, and selecting a day on which the calculated degree of separation is maximized; A threshold for separating the two classes on the selected day is derived, and the device automatically operates the derived threshold without any human operation. It is assumed that the power consumption amount is the maximum value in the state of automatic device operation, and is set as a first threshold value for determining a human dangerous state. Extracting the smallest daily minimum power consumption, selecting the smallest power consumption with the smallest power consumption from the extracted daily minimum power consumption, and based on the selected minimum power consumption, Calculating a minimum value of power consumption in the automatic device operation state, and setting the calculated minimum value of power consumption as a second threshold value for determining a human dangerous state; It is characterized by being.

  In the dangerous state determination method according to the third technical means, when a fourth technical means determines the human dangerous state in the home on the latest past day or a selected date, A state in which power data relating to power consumption is acquired, and each of the acquired power data is sequentially compared with the first threshold and the second threshold in time series, and the acquired power data does not exceed the first threshold Or calculating a determination result that determines whether or not the state that does not decrease below the second threshold continues beyond a predetermined limit time as a dangerous state determination result that indicates a human dangerous state in the house It further has these.

  The fifth technical means, in the dangerous state determination method according to the fourth technical means, when calculating the dangerous state determination result, sequentially compares the acquired power data and the threshold for each time, If the state where the power data does not exceed the first threshold or does not decrease below the second threshold continues beyond the limit time, it is determined that the person in the house is in a dangerous state On the other hand, if the state where the power data does not exceed the first threshold or does not decrease below the second threshold does not continue beyond the limit time, the person in the house is in a dangerous state. It is determined that there is not, and the determined result is calculated as a binary dangerous state determination result.

  Sixth technical means, in the dangerous state determination method according to the fourth technical means, when calculating the dangerous state determination result, sequentially compares the acquired power data and the threshold for each time, A risk state determination comprising a ratio of a duration time during which the power data does not exceed the first threshold value or a state where the power data does not decrease below the second threshold value to the limit time is a numerical ratio indicating the degree of a human dangerous state It is calculated as a result.

  A seventh technical means calculates the dangerous state determination method according to any one of the third to sixth technical means based on the minimum power consumption selected from the daily minimum power consumption. When setting the minimum value of power consumption in the state of automatic device operation as the second threshold, the value of the selected minimum power consumption itself is set in advance for the selected minimum power consumption. The value obtained by adding the power margin is regarded as the minimum value of the power consumption in the automatic device operation state, and is set as the second threshold value.

  The eighth technical means is characterized in that the dangerous state determination method according to any one of the third to seventh technical means is a dangerous state determination program implemented as a program executable by a computer. .

  According to the dangerous state determination system, the dangerous state determination method, and the dangerous state determination program of the present invention, it is possible to automatically determine the dangerous state of a person living in the home based on the power consumption of the device installed in the home. In addition, the following effects can be obtained.

  First, it is not necessary to manually set initial values for calculating the first threshold value and the second threshold value for determining whether or not a human is in a dangerous state in the target home, Since the first threshold value and the second threshold value can be obtained directly and automatically from the power time series data, it causes a problem that the first threshold value and the second threshold value fluctuate depending on the setting of the initial value. There is no.

  Second, first and second threshold values for determining whether or not a person is in a dangerous state in the target house can be directly and automatically obtained from past power time series data in the house. Therefore, the user does not need knowledge or experience regarding the setting of the first threshold value and the second threshold value when operating the dangerous state determination system.

  Third, since the past power time-series data in the home is used for the automatic calculation of the first threshold and the second threshold for determining the presence or absence of a human dangerous state in the target home, It is possible to calculate and set an optimum value for each.

It is a block block diagram which shows an example of the internal structure of the dangerous state determination system by this invention. It is a graph which shows an example of the histogram of the power consumption for one day produced | generated in the histogram production | generation part of the threshold value calculation part of the dangerous state determination system of FIG. It is explanatory drawing for demonstrating the calculation method of the discriminant analysis method applied in the data filtering part of the threshold value calculating part of the dangerous state determination system of FIG. It is a graph for demonstrating a mode when the 1st threshold value and 2nd threshold value for determining the presence or absence of a dangerous state are set in the threshold value calculation part of the threshold value calculation part of the dangerous state determination system of FIG. It is a flowchart which shows an example of the whole operation | movement of the dangerous state determination system of FIG. It is a flowchart which shows an example of operation | movement in the data filtering part of the threshold value calculating part of the dangerous state determination system of FIG. It is a flowchart for demonstrating an example of the operation | movement in the dangerous state determination part of the dangerous state determination system of FIG.

  Hereinafter, an example of a preferred embodiment of a dangerous state determination system, a dangerous state determination method, and a dangerous state determination program according to the present invention will be described in detail with reference to the drawings. In the following description, the dangerous state determination system and the dangerous state determination method according to the present invention will be described. However, the dangerous state determination method may be implemented as a dangerous state determination program that can be executed by a computer. Furthermore, it goes without saying that the dangerous state determination program may be recorded on a computer-readable recording medium.

(Features of the present invention)
Prior to the description of the embodiments of the present invention, an outline of the features of the present invention will be described first. The present invention obtains the power consumption in the target home, and thus the dangerous state of a person living in the home (for example, a health hazard, a serious injury, a serious illness, a sleeping state or unconsciousness) The main feature is that it is automatically estimated whether or not the user has fallen into a state where he / she cannot act). Note that current consumption may be used instead of power consumption.

  Specifically, in order to determine the dangerous state of a person living at home, the first threshold that can be regarded as the maximum value of the power consumption of automatic device operation related to the device in the home and the device automatic operation Two power thresholds, the second threshold that can be regarded as the minimum value of power consumption, are calculated directly and automatically from past power time-series data, set in advance, and targeted The measurement result of the power consumption of the device in the home does not exceed the first threshold that can be regarded as the maximum value of the power consumption of automatic device operation, or the minimum value of the power consumption of automatic device operation If any of the conditions that do not decrease below the second threshold that can be considered as a duration for the determination of the dangerous state continues for a predetermined limit time , The person in the house falls into danger Determining that it shall have been mainly characterized.

Here, when calculating the first threshold value that can be regarded as the maximum value of the power consumption of the automatic device operation, the power time series of the past N days (N: number of products manufactured) arbitrarily determined Generate histograms for daily power consumption from the data, and use the discriminant analysis method for each of the generated daily power consumption histograms. Separation metric (Separation Metrics) σ _b ² / σ _w ² (σ _b ² : Between-Class Variance), σ _w ² : In-class variance (Within-Class Variance)) is calculated every day and the threshold value of the day when the calculated degree of separation σ _b ² / σ _w ² is maximized is derived. Related to electrical equipment installed in Is regarded as the maximum value of the power consumption during automatic operation, is set as the first threshold for determining the presence or absence of one of the hazardous condition of the human that home to home.

  On the other hand, when calculating the second threshold value that can be regarded as the minimum value of the power consumption of automatic device operation, the power time-series data of N days (N: number of products manufactured) arbitrarily determined, Generate a histogram for power consumption for each day, extract the minimum power consumption for each generated power consumption histogram for each day, and extract the minimum power consumption for each day The minimum electric power consumption is extracted as the minimum electric power consumption in N days from the inside, and further, the automatic equipment related to the electric equipment installed in the target house based on the extracted minimum electric power consumption By calculating the minimum value of power consumption during operation, the second value for determining the presence or absence of the other dangerous state of the person living in the home is calculated based on the calculated minimum value of power consumption during automatic operation of the device. As a threshold Set to.

  In other words, two power consumptions, the maximum value of power consumption and the minimum value of power consumption by automatic operation of the device in the house, from time series data of power for the past N days arbitrarily determined in the target house The amount is automatically calculated and set as a first threshold value and a second threshold value for determining the presence or absence of a dangerous state of a person living in the house, and the power consumption amount in the house is determined by a predetermined time limit. If the state that does not exceed the first threshold continues or the state that does not decrease below the second threshold continues until the threshold is exceeded, the person in the house is in a dangerous state that cannot operate the device. The main feature of the present invention is that it is determined that the object has fallen.

  Normal human life is in units of one day (24 hours). Unless you stay up all night or at a home party, you usually stay home for 24 hours, for going out or going to bed. Since humans perform operations to stop the operation of devices in the home, the power consumption consumed by the devices in the home decreases to the minimum level of power consumption during automatic operation of the device, and except when the user stays outside. Usually, within 24 hours, when a person staying at home performs an operation to start the operation of the device at home, the power consumption consumed by the device at home is the maximum value of automatic device operation. A state exceeding.

  Accordingly, when, for example, 24 hours is set as the predetermined limit time, the state where the maximum power consumption of the automatic operation of the device has not been exceeded for more than 24 hours has continued. Except for the above, it can be estimated that the person in the house is in a dangerous state where the operation for starting the device cannot be performed at all within 24 hours. On the contrary, the fact that the state where the power consumption does not decrease below the minimum value of automatic operation for more than 24 hours continues means that people in the house are not staying overnight or at home parties, etc. It can be estimated that within 24 hours, the device is in a dangerous state in which it is impossible to perform any operation to stop the device that was in operation. Here, the frequency of occurrences of conditions that are different from normal times such as overnight stays, overnight stays, home parties, etc. is very low in normal life, and when such a condition occurs, some prior notice is given to a person at home. In many cases, it reaches the parties involved in the management of dangerous situations, so there is a special problem even if it does not automatically detect and exclude conditions different from those described above. Can be regarded as not.

  Note that the automatic device operation related to the electric device refers to an operation state of a device that automatically consumes power even if a human does not perform an operation in normal home life.

  For example, a refrigerator can be unplugged by a person, but usually does not pull out the outlet. Therefore, the refrigerator consumes power for cooling even in the state of automatic operation where no human operation is performed. The amount is generated.

  In the case of a television, normally, for a person who turns off the power of the television with the remote control, turning off the power with the remote control is a human operation. Although the power consumption changes, even after the power is turned off (OFF) by the remote controller, the standby power consumed is the power consumption in the automatic device operation state. To put it simply, humans turn off the power of devices in their homes when they go out according to their lifestyles, but the operating state of devices that operate and consume power when they go out is It corresponds to “automatic operation”.

  In the present invention, the present invention relates to a technique for determining whether or not a person at home is in a dangerous state, and whether or not the corresponding person is at home or is away from home. It is preferable that it can be confirmed reliably. However, as for the determination technique of whether the user is away from home or not, even if the existing technique is applied as it is, it does not affect the feasibility of the present invention. For example, the sensor function described in Non-Patent Document 3 is provided. Even if the key holder is used, there is no problem in realizing the present invention.

(Configuration example of dangerous state determination system according to the present invention)
Next, an embodiment of the present invention will be described with reference to FIG. 1 as an example of the internal configuration of the dangerous state determination system according to the present invention. FIG. 1 is a block diagram showing an example of the internal configuration of a dangerous state determination system according to the present invention. Although FIG. 1 shows a case where each block is configured by hardware logic, in some cases, all or a part of each block shown in FIG. 1 is realized as a program executable by a computer. You may do it.

  As shown in FIG. 1, the dangerous state determination system 100 is installed in a house, acquires the occurrence state of power consumption due to the operation of human equipment in the house, determines the dangerous state of the person, and determines It has a function of outputting the result to the outside, and includes at least a power data input unit 1, a storage unit 2, a threshold value calculation unit 3, a determination unit 4, and a dangerous state output unit 5. Further, the storage unit 2 includes at least a power data storage unit 21, the threshold value calculation unit 3 includes at least a histogram generation unit 31, a data filtering unit 32, and a threshold value calculation unit 33, and the determination unit 4 includes a dangerous state determination unit 41. At least.

  The power data input unit 1 has a function of acquiring power data obtained from a power sensor or the like, that is, power consumption as numerical information. In the following description, the power data acquisition interval in the power data input unit 1 is set to be one minute, but is not limited to one minute, and may be an arbitrary time interval appropriately determined in advance.

  The storage unit 2 has a function of storing various types of information (data, programs, etc.). The power data storage unit 21 of the storage unit 2 arbitrarily determines power data acquired by the power data input unit 1 in advance. In addition, it has a function of sequentially storing over a specific period.

  The threshold value calculation unit 3 uses two threshold values, a first threshold value and a second threshold value, as threshold values for determining the presence / absence of the human dangerous state based on the state of power consumption generated by the operation of the human device at home. The histogram generation unit 31 of the threshold value calculation unit 3 has a function for automatically calculating and setting, and the histogram generation unit 31 of the threshold value calculation unit 3 calculates 1 from the power data within an arbitrarily specified specific period stored in the power data storage unit 21. It has a function of generating a histogram relating to power consumption every day. The histogram displays power (power consumption) in a natural logarithm on the horizontal axis, and displays the frequency of occurrence of each power (power consumption) on the vertical axis.

  FIG. 2 is a graph illustrating an example of a histogram of power consumption for one day generated by the histogram generation unit 31 of the threshold value calculation unit 3 of the dangerous state determination system 100 of FIG. In FIG. 2, power data for one day acquired every minute and stored in the power data storage unit 21, that is, 1,440 pieces of power data are set in a predetermined power unit (for example, 0.1 W unit). This is an example in which the frequency of occurrence (number of times) in each power interval is displayed as a histogram, sorted in order of increasing power consumption from low power consumption to high power consumption.

  That is, in this embodiment, in order to determine a human dangerous state, a method of rearranging power data as a generally used histogram is applied as a method of analyzing power data. In the example of the power data histogram shown in FIG. 2, power data acquired every minute is shown as an example. However, when generating a histogram, it is not limited to every minute, and is appropriate in advance. The unit may be an arbitrary time interval determined in.

  In addition, when the arbitrarily defined specific period is N days (N: positive integer), N histograms are created for each day. The N days of the specific period is appropriately about 30 days, but is not limited to 30 days, and may be a period arbitrarily determined arbitrarily. Moreover, although the case where the predetermined power unit as the interval for dividing the power data is 0.1 W, for example, is shown, it may be divided by any power unit.

In addition, the data filtering unit 32 of the threshold value calculation unit 3 calculates the N threshold values generated by the histogram generation unit 31 in order to calculate a first threshold value that is one threshold value for determining a human dangerous state (the specific identification). For each histogram of a period of N days, the separation metric in the Discriminant Analysis Method (Separation Metrics) σ _b ² / σ _w ² (σ _b ² : Between-Class Variance ), Σ _w ² : Within-Class Variance), and has a function of selecting a day on which the value of the degree of separation σ _b ² / σ _w ² is maximum. The discriminant analysis method is a technique for defining two classes for a certain data group and calculating a threshold value where the degree of separation between the two defined classes is the largest. This is a technique frequently used in the field for binarization of image shading.

The calculation method of the discriminant analysis method will be further described with reference to FIG. FIG. 3 is an explanatory diagram for explaining a calculation method of the discriminant analysis method applied in the data filtering unit 32 of the threshold value calculation unit 3 of the dangerous state determination system 100 of FIG. 1. For each of the histograms, a calculation method is described in which binarization is performed by the first threshold t ₁ into two classes, a class with a large power consumption (high consumption class) and a small class (low consumption class).

In other words, as shown in FIG. 3A, the daily power consumption illustrated in FIG. 2 generated in the histogram generation unit 31 is a class with a large power consumption (high consumption class) by the first threshold t ₁ . And the case of separation into two classes, a small class (low consumption class).

Here, as shown in FIG. 3A, the number of power data in the low consumption class is ω ₁ , the average is m ₁ , the variance is σ ₁ , the number of power data in the high consumption class is ω ₂ , the average is m ₂ , When the variance is σ ₂ , the number of power data of the entire power data is ω _t1 , the average is m _t1 , and the variance is σ _t1 , the intra-class variance σ _w ² is as shown in FIG. (1)

と表すことができる。

It can be expressed as.

Further, the interclass variance σ _b ² is expressed by the following equation (2) as shown in FIG.

と表すことができる。

It can be expressed as.

Here, the total variance σ _t1 is

として表すことができる。したがって、２つのクラスの分離度は、図３（Ｂ）に示すように、クラス間分散σ_ｂ ^２とクラス内分散σ_ｗ ^２との比で与えられ、次の式（３）

Can be expressed as Therefore, as shown in FIG. 3B, the degree of separation between the ^two classes is given by the ratio between the inter-class variance σ _b ² and the intra-class variance σ _w ^2, and the following equation (3)

となり、この分離度σ_ｂ ^２/σ_ｗ ^２が最大になる日の第１閾値ｔ_１を求めれば、電力消費量を利用して、人間の活動状態を（活動しているか否かを）推定するために用いることが可能な２つのクラスに、電力消費量を分離することができる。

If the first threshold value t ₁ on the day when the degree of separation σ _b ² / σ _w ² becomes maximum is obtained, the human activity state (whether or not it is active) is estimated using the power consumption. The power consumption can be separated into two classes that can be used to:

That is, the power consumption belonging to the low consumption class and the power consumption belonging to the high consumption class in the histogram of FIG. It can be separated into two classes: the case of automatic operation of consumed equipment and the case where power consumption is increased by human operation. FIG. 4 shows a state in which the first threshold value t ₁ and the second threshold value t ₂ for determining the presence or absence of a dangerous state are set in the threshold value calculation unit 33 of the threshold value calculation unit 3 of the dangerous state determination system 100 of FIG. FIG. 3 is a graph for explaining, and the pattern of the power consumption of the day shown as the histogram of FIG. 2 is the separation degree σ _b ² / σ _w as the first threshold t _{1 in} a specific period (for example, N days). ^This is shown as a case where the histogram is a day when ² is the maximum and the power consumption used when setting the second threshold value t ₂ described later is the minimum.

As shown in the histogram of FIG. 4, among the histograms for each day within the specific period, the histogram for the day selected as the histogram for the day with the maximum first threshold t ₁ is obtained using the discriminant analysis method. According to the first threshold value t ₁ , there are two classes, namely, the case of automatic operation in which power is automatically consumed regardless of human operation in the house, and the case where power consumption is increased by human operation. separated, in the power consumption of the home belonging to the low class to the left of the first threshold value t ₁ is delimited lines indicated was presumed that human the home has not performed an operation for starting the operation of the device, the in power consumption of home belonging to the right of the high consumption class of separators which first threshold t ₁ indicates, it is a human of the home is presumed to be making operation for starting the operation of the equipment.

As a specific numerical example, in the case of the histogram shown in FIG. 4, for example, the case where power data for one day is acquired every minute and stored in the power data storage unit 21 of the storage unit 2 is shown. Since one day is 24 hours and 24 hours corresponds to 1,440 minutes, 1,440 pieces of power data are accumulated. Also, of the N days in the specific period, for example, the day on which the histogram relating to the power consumption in FIG. 4 is obtained is the day when the degree of separation σ _b ² / σ _w ^{2 of the two} classes is maximized by the discriminant analysis method. Is determined, the first threshold value t ₁ that is the threshold value of the day is calculated as the first threshold value t ₁ for determining whether or not a future person in the house is in a dangerous state. .

That is, as described above, the threshold value calculation unit 33 of the threshold value calculation unit 3 is based on the daily histogram for a specific period (N days) generated by the histogram generation unit 31 with respect to the power data of the input day. The first threshold value t ₁ obtained by the discriminant analysis method using the histogram of the day selected as the day with the highest degree of separation σ _b ² / σ _w ² in the data filtering unit 32 is used as a human operation in the house. The first threshold value t _1, which is one threshold value for determining the dangerous state of the person in the house, is considered to give the maximum value of the automatic device operation that automatically consumes power even when there is no power. Set as.

That is, when the two classes of “power consumption by automatic operation of equipment” and “increase of power consumption by human operation” are clearly separated, the first threshold value t ₁ obtained by the discriminant analysis method is Considering that this is the maximum value of the power consumption of automatic device operation that automatically consumes power when there is no human operation, power consumption exceeding the first threshold t ₁ occurs. In this case, it can be estimated that the person in the target house is in an active state where some operation of the electric device is performed.

Here, the state where the power consumption in the home does not exceed the first threshold t ₁ continues, and a human being in the home starts operating the device after a predetermined limit time, for example, one day (24 hours). The situation in which no operation is performed is a situation that does not occur in a normal state unless a situation that rarely occurs, such as when a person staying outside the house stays out. Therefore, when the state where the power consumption does not exceed the first threshold t ₁ continues beyond a predetermined limit time, it is dangerous that a person in the house cannot perform an operation to start the operation of the device. It can be determined that it is in a state.

  In addition, the data filtering unit 32 of the threshold value calculation unit 3 generates N threshold values generated by the histogram generation unit 31 in order to calculate the second threshold value, which is another threshold value for determining the dangerous state of the person in the house. The minimum value of the power consumption is acquired in each of the histograms (when the specific period is N days), and the power of the minimum value of each power consumption for each N days (that is, the minimum power consumption for each day) It has a function to select the day with the smallest consumption.

The threshold calculation unit 33 of the threshold calculation unit 3 uses the power of the data filtering unit 32 based on the daily histogram for a specific period (for N days) generated by the histogram generation unit 31 with respect to the input power data for the day. Using the histogram of the day selected as the day with the smallest amount of consumption as input data, the minimum value of power consumption on that day is given, and the minimum value at the time of automatic operation when the person in the house is not operating the device Based on the selected minimum value of power consumption, the second threshold value t ₂ , which is another threshold value for determining whether or not the person in the house is in a dangerous state, is calculated. To set.

Here, the power consumption of the home is continuously the state does not decrease to a second threshold value t ₂ below, beyond a predetermined limit time for example one day (24 hours), the human of the house stops the operation of the equipment The situation in which no operation is performed is a situation that does not occur in a normal state except for a special event such as a special event such as a home party held all night. Therefore, the state in which power consumption is not reduced to the second threshold value t ₂ or less, when not continue beyond the limits time previously arbitrarily set, the more home human can not be operated to stop the operation of the equipment It can be determined that the vehicle is in a dangerous state.

Further, the dangerous state determination unit 41 acquires the latest latest power data (power time-series data) in the past or power data (power time-series data) on an arbitrarily designated date from the power data storage unit 21 and acquires it. compared respectively power data (power time-series data) first threshold t ₁ and the second threshold value t ₂ set in chronological order threshold calculating unit 33 sequentially, the acquired power data (power time-series data) , when the state does not exceed the first threshold t ₁ had continued beyond the limit time previously determined are those human the home is experiencing start operation dangerous that they can not state of operation of the equipment a judgment, or, if the acquired power data (power time-series data), the state does not decrease to the second threshold value t ₂ less had continued beyond the limit time previously determined is human the home Luck It is determined that the machine is in such a dangerous state that it cannot be stopped.

Conversely, when the duration of the state that does not exceed the first threshold t ₁ is less than or equal to the limit time, or when the duration of the state that does not fall below the second threshold t _{2 is} less than or equal to the limit time It is determined that the person in the house is not in a dangerous state. Here, the limit time is preferably one day (24 hours), which is a normal unit of human life, but is not limited to this, and an arbitrary period may be selected. .

The determination result is output to the dangerous state output unit 5 as a binary dangerous state determination result indicating the presence or absence of a human dangerous state in the target house. Alternatively, out of the total number of data of power data (power time-series data) acquired as the power consumption of the day selected as the day for determining the dangerous state, the number of data that does not continuously exceed the first threshold t ₁ or the ratio of the number of data does not decrease continuously to the second threshold value t ₂ or less, as a risk status decisions made of (numbers not necessarily binary) numerical percentage indicating the degree of human dangerous conditions in a house, dangerous situation You may make it output with respect to the output part 5. FIG.

Incidentally, based on the minimum value of the power consumption selected as providing the minimum value of the time equipment automatic operation, when calculating the second threshold t _2, the second threshold value the minimum value itself of the selected power consumption t ₂ may be set to, in such a case, even though actually the state of the device automatic operation only, the same power as the value set in the second threshold value t ₂ as the minimum value at the time of equipment automatic operation It may not be consumed.

Specifically, a value set in the second threshold value t ₂ as the minimum power consumption during equipment automatic operation at a particular period, for example, N days example 50 W, and sets the example 24 hours as a limit time In such a case, even if the minimum value for a certain day (24 hours) is reduced to only 51 W even when only the automatic device operation is performed, it may occur depending on the environmental conditions. When such a case occurs, there is a possibility that a person in the house may erroneously determine that the person is in a dangerous state even though the person is not in a dangerous state.

Therefore, when calculating the second threshold t ₂ , as shown in FIG. 4, the minimum power consumption itself at the time of automatic operation of the device for a specific period, for example, N days is not used as the second threshold t ₂ , but the specific period for example it is desirable to set a value obtained by adding a certain amount or more power margin previously arbitrarily determined for minimum power consumption during equipment automatic operation in N days as a second threshold value t _2. For example, 20 W or 30 W corresponding to one low wattage bulb is an appropriate power amount as a power margin of a certain amount or more that is arbitrarily determined. There is no middle power consumption between the first threshold t ₁ and the minimum power consumption (= e ^{(a + b) / 2} , or = (e ^a + e ^b ) / 2, where e ^{a is} the first threshold t ₁ , E ^b : minimum power consumption) or an appropriate arbitrary value between the first threshold t ₁ and the minimum power consumption can be selected.

Further, the dangerous state output unit 5 of the dangerous state determination system 100 determines the determination result determined by the dangerous state determination unit 41 (determination result indicating whether or not a person in the house is in a dangerous state or not). data hazard state judging result of the binary, or, it did not decrease continuously the acquired data number or the second threshold value t ₂ power data not continuously exceeds the first threshold t ₁ and less is The ratio of the number to the total number of acquired power data is an external device (registered in advance) as a dangerous state determination result consisting of a numerical ratio (a numerical value not limited to two) indicating the degree of dangerous state of the person in the house. Device).

(Operation example of the dangerous state determination system according to the present invention)
Next, an example of the operation of the dangerous state determination system 100 according to the present invention shown in FIG. 1 will be described with reference to the flowcharts of FIGS. FIG. 5 is a flowchart showing an example of the overall operation of the dangerous state determination system 100 of FIG. 1, and shows an example of the dangerous state determination method according to the present invention.

FIG. 6 is a flowchart illustrating an example of the operation in the data filtering unit 32 of the threshold value calculation unit 3 of the dangerous state determination system 100 in FIG. In the flowchart of FIG. 6, power consumption during a specific period (N days) in which two threshold values, a first threshold value t ₁ and a second threshold value t ₂ , for estimating the presence / absence of a human dangerous state in the home are determined. It is calculated based on In other words, the threshold on the day when the degree of separation when separating into two classes, the low consumption class and the high consumption class, is regarded as the maximum value of power consumption during automatic operation of the equipment, Calculated by setting as a certain first threshold t ₁ and calculating the minimum value of power consumption during automatic operation of the device based on the minimum value of power consumption on the day when the power consumption is minimized shows the operation for setting the minimum value of the power consumption amount during equipment automatic operation as the second threshold value t ₂ is the other threshold.

  FIG. 7 is a flowchart for explaining an example of the operation in the dangerous state determination unit 41 of the dangerous state determination system 100 of FIG. 1, and the risk of human in the house based on the power consumption in the target house. The operation | movement which determines a state is illustrated.

  First, an example of the overall operation of the dangerous state determination system 100 of FIG. 1 will be described using the flowchart shown in FIG.

  In the flowchart of FIG. 5, first, power time series data (time) obtained by converting power consumption obtained in a time series from a power sensor or the like in the home through the input interface in the power data input unit 1 into numerical information. Obtained as power consumption data arranged in series) (step S1). Note that the power time-series data acquisition interval can be arbitrarily set, and can be set, for example, every minute. The power time series data acquired by the power data input unit 1 is sequentially stored in the power data storage unit 21 of the storage unit 2 for a specific period (for example, N days) arbitrarily set in advance (step) S2).

Next, the first threshold value t ₁ and the second threshold value t _2, which are threshold values used for determination of the dangerous state, using the power time-series data for a specific period (for example, N days) stored in the power data storage unit 21. The human dangerous state of the day is determined using the power time-series data of the past latest date or an arbitrarily selected date stored in the power data storage unit 21. It is determined whether or not (step S3). Using the acquired power time-series data for a specific period (for example, N days), that is, power consumption, an operation is performed to calculate the first threshold t ₁ and the second threshold t ₂ that are thresholds used for determination of the dangerous state. If (YES in step S3), and then proceeds to step S4, whereas, it was determined not to be the case performs an operation of calculating the first threshold t ₁ and the second threshold value t ₂ is a threshold value used for determination of the dangerous state In such a case (NO in step S3), it is determined whether or not a person is in a dangerous state using the power time series data acquired on the latest day or an arbitrarily selected day. As a result, the process proceeds to step S7.

In step S3, when performing an operation for calculating a first threshold t ₁ and the second threshold value t ₂ is a threshold value used for determination of the dangerous state by using the electric power time-series data obtained (YES in step S3), and first, 2 as shown in FIG. 2 based on the power data for an arbitrarily determined specific period (for example, N days) stored in the power data storage unit 21 by the histogram generation unit 31 of the threshold value calculation unit 3. A histogram relating to daily power consumption is generated (step S4). As described above, the histogram shows each power consumption when the power consumption is arranged in a predetermined power interval (for example, 0.1 W) in order of increasing power consumption from the low power consumption to the high power consumption. Each occurrence frequency (frequency distribution) is shown every day. Here, when the specific period is N days, for example, N histograms are generated regarding the power consumption.

When the histogram regarding the power consumption for each day is generated, first, N pieces of the values generated by the histogram generation unit 31 (the above-mentioned) are used to calculate the first threshold value t ₁ that gives the maximum value of the power consumption during the automatic operation of the device. The discriminant analysis method is applied to each of the histograms in the case where the specific period is N days) in the data filtering unit 32 of the threshold value calculation unit 3, and the separation degree σ _b ² / σ _w ² (σ _b ² : class By calculating the inter-class variance, σ _w ² : intra-class variance, the power data is filtered, and the day on which the value of the degree of separation σ _b ² / σ _w ² is maximized is selected (step S5).

That is, as described above, the separation degree σ _b ² / σ _w ² is the degree of clarity of separation (separation when separating into two classes of the low consumption class and the high consumption class in each power consumption amount for each day. The degree of separation σ _b ² / σ _w ² is maximized, and it is most clearly separated into two classes, a low consumption class and a high consumption class It means that.

Further, the two classes of the low consumption class and the high consumption class often appear as “in the case of power consumption by automatic operation of equipment” and “in the case of increase in power consumption by human operation”, respectively. Therefore, selecting the day with the maximum value of the separation degree σ _b ² / σ _w ² automatically consumes power when there is no human operation due to the threshold value obtained by the discriminant analysis method. The day when the power can be most clearly separated is selected into two classes, that is, the case of automatic operation of the device and the case where power is consumed by human operation.

Next, to calculate the second threshold value t ₂ which gives the minimum value of the power consumption during equipment automatic operation, a histogram of the N generated by the histogram generation unit 31 (if the specific time period is N date) In each case, after selecting a value with the smallest power consumption, a histogram of the day showing the smallest power consumption is selected from the minimum power consumption for each day (step S5).

That is, the data filtering unit 32 of the threshold value operation unit 3, a histogram of the power consumption to be used for the calculation of two thresholds between the first threshold value t ₁ for determining human hazardous condition and the second threshold value t ₂ Assuming that only two histograms are extracted, the histogram of the day with the clearest separation of the two classes and the histogram of the day with the lowest power consumption, the separation of the two classes is not clear histogram of day to be not used for the calculation of the first threshold t ₁ and filtered, and the histogram of the other days of power consumption has become smallest value is filtered by the second threshold value t ₂ It is not used for calculation. The detailed operation regarding the data filtering process by the data filtering unit 32 will be further described later with reference to the flowchart of FIG.

Thereafter, using the histogram of the day selected by the data filtering unit 32 as input data, the threshold value obtained by the discriminant analysis method is automatically calculated in the target specific period without any human operation in the target house. Is set as a first threshold t ₁ for determining the dangerous state of the person in the house, in the threshold calculation unit 33, assuming that the maximum value of the power consumption of the automatic operation of the device consumed is given, In the target specific period, the minimum power consumption of the day when the power consumption is the smallest is the automatic power consumption of the device that is automatically consumed in the specific period without any human operation in the house. as the minimum value of the power consumption is given, the threshold calculating unit 33 sets as the second threshold value t ₂ for determining a dangerous condition of the house human Step S6).

As described above, it was obtained when the two classes of “power consumption by automatic operation of the device” and “increase of power consumption by human operation” are most clearly separated by the discriminant analysis method in the data filtering unit 32. the second threshold value t ₂ is obtained if that is the first threshold value t ₁ and the minimum power consumption, respectively, the power consumption of the equipment automatic operation to automatically consume power when no human operator is It can be considered that the maximum value and the minimum value are shown, and can be set as a threshold value for estimating a human dangerous state. Note that the second threshold t ₂ is not the minimum power consumption itself within the specific period, but the minimum power consumption, as described above, in order to more reliably determine the state in which the operation device is not stopped. it is desirable to set a value obtained by adding a power margin to a predetermined arbitrarily for the power consumption as a second threshold value t _2.

By using the two threshold values of the first threshold value t ₁ and the second threshold value t ₂ , a state in which the power consumption does not exceed the first threshold value t ₁ is a limit that is determined in advance as a duration for determining the dangerous state. If the operation continues beyond a certain time (for example, 24 hours), some dangerous state has occurred in which the person in the target house cannot start the operation of the device within the limit time. and can be determined, also a state in which power consumption is not reduced to the second threshold value t ₂ or less, beyond the limit time (e.g. 24 hours), if continues, in該限field time This shows that it is possible to determine that some dangerous state that cannot be performed by the person in the target house can stop the operation of the device during operation.

Next, in step S3, by using the electric power time-series data obtained, if it is determined that it is not a case performs an operation of calculating the first threshold t ₁ and the second threshold value t ₂ is a threshold value used for determination of the dangerous state (NO in step S3), using the power time-series data of the latest acquired date or arbitrarily selected date, whether or not a person is in a dangerous state in the target house, the dangerous state determination result The process proceeds to step S7. First, based on the acquired power time series data, the dangerous state determination unit 41 determines whether or not a person in the house is in a dangerous state.

That is, in the dangerous state determination unit 41, and the power time-series data of the latest date or optionally selected day acquired, the first threshold t ₁ and the second threshold value t ₂ set by the threshold calculating unit 33 in step S6 Are sequentially compared in time series. As a comparison result, when the acquired power time series data does not exceed the first threshold value t ₁ and continues for a predetermined limit time (for example, 24 hours), the limit time elapses. In the meantime, it is determined that the person in the house is in a dangerous state where the operation of starting the device cannot be performed at all. In addition, when the acquired power time-series data does not decrease below the second threshold t ₂ and continues beyond the limit time (for example, 24 hours), the time until the limit time elapses. In addition, it is determined that the person in the house is in a dangerous state where the operation for stopping the operation of the device cannot be performed at all.

On the other hand, when the state does not decrease to the state or the second threshold value t ₂ below which does not exceed the first threshold value t ₁ is, did not have to continue beyond the predetermined limit time (e.g. 24 hours), the time limit It is determined that a person in the house is performing some operation on the device until the time elapses, and the person in the house is not in a dangerous state. The determined result is sent to the dangerous state output unit 5 as a binary dangerous state determination result indicating the presence or absence of the dangerous state of the person in the house (step S7).

State In the dangerous state determination unit 41, rather than as a dangerous state judging results of two values indicating the presence or absence of hazardous condition, in some cases, which did not exceed the first threshold value t ₁ of the power time-series data obtained duration or percentage of the time limit for the duration of the state that has not been reduced to the second threshold value t ₂ following, the proportions numerical value indicating a degree of danger state of the home of the person (numbers not limited to binary) It may be calculated as a dangerous state determination result and sent to the dangerous state output unit 5. Detailed operations related to the dangerous state determination process in the dangerous state determination unit 41 will be further described later with reference to the flowchart of FIG.

  Dangerous state determination result comprising a binary dangerous state determination result that determines the presence or absence of a human dangerous state from the dangerous state determination unit 41 or a percentage value (a numerical value that is not limited to binary) that indicates the degree of the human dangerous state in the house Is transmitted, the dangerous state output unit 5 sends a binary dangerous state determination result transmitted from the dangerous state determination unit 41 to an external device registered in advance via the output interface or A dangerous state determination result consisting of a ratio numerical value (a numerical value not limited to binary) is output (step S8).

By performing the above operations, it is possible to automatically estimate the maximum and minimum power consumption values for automatic operation of the equipment in the target home based on past power data (power consumption data). becomes available, also the maximum value and the minimum value of the power consumption of the estimated equipment automatic operation, as a first threshold t ₁ and the second threshold value t ₂ specific for determining the presence or absence of human dangerous conditions in the premises In this state, the acquired power data (power consumption data) of the latest day or the power data (power consumption data) of an arbitrarily selected day does not exceed the specific first threshold value t ₁ or the second threshold value. A limit time (for example, 24 hours) arbitrarily determined in advance as a duration for determining whether or not a dangerous state has occurred is a time during which the state that has not decreased below t ₂ continues. When the time limit is exceeded, it is possible to determine that the person in the house is in a dangerous state that cannot perform any operation on the device until the limit time elapses.

Next, with reference to the flowchart of FIG. 6, in order to calculate the first threshold value determining human hazardous condition t ₁ and a second threshold value t _2, Nursing power consumption and maximum and minimum in the state of the device automatic operation The number of days that can be deceived is calculated based on power time-series data (power consumption data arranged in time series) for a specific period of a plurality of predetermined past days, for example, N days (N: positive integer). An example of the operation of the data filtering unit 32 will be described.

  In the flowchart of FIG. 6, first, for example, power time-series data acquired every minute for a predetermined period of N days, that is, data related to time-series power consumption acquired every minute is stored in the power data. The histogram generation unit 31 converts the read power time-series data for N days read from the unit 21 into a histogram relating to the power consumption for each day and sends the histogram to the data filtering unit 32. (Step S21).

The data filtering unit 32 that has received N histograms corresponding to N days from the histogram generation unit 31 first uses a discriminant analysis method for each of the N histograms in order to calculate the first threshold value t _1. Thus, the degree of separation σ _b ² / σ _w ² between the two classes of the low consumption class and the high consumption class is calculated (step S22).

Thereafter, the data filtering unit 32 compares the N separation degrees σ _b ² / σ _w ² in each of the N histograms corresponding to N days, and the separation degree σ _b ² / σ _w ² becomes the largest. The day corresponding to the histogram is selected and output to the threshold value calculation unit 33. In the threshold value calculation unit 33, on the day selected by the data filtering unit 32, the threshold value that is separated into the two classes of the low consumption class and the high consumption class is automatically supplied with power in a state where the human is not operating. calculated as being given the maximum value of the power consumption in devices automatic operation to be consumed, it sets the calculated threshold value as a first threshold value t ₁ (step S23).

Furthermore, in order to calculate the second threshold t ₂ , the data filtering unit 32 extracts each day's minimum power consumption in which the power consumption is minimum in each of the N histograms corresponding to N days. The smallest daily minimum power consumption is selected from the extracted N daily minimum power consumptions as the day for giving the minimum power consumption during the N days, and is output to the threshold calculation unit 33. To do. In the threshold calculation unit 33, the daily minimum power consumption of the day selected by the data filtering unit 32 is the minimum power consumption during the N days, and the minimum value of the power consumption in the automatic device operation is given. and in that the regarded that is set as a second threshold value _{t 2} (step S24). Here, as the second threshold t ₂ to be set, as described above, the minimum power consumption itself selected by the data filtering unit 32 may be used, but the frequency of erroneous determination regarding the dangerous state is further reduced. Therefore, it is desirable to use a value obtained by adding a predetermined power margin to the minimum power consumption.

  Next, an example of detailed operations relating to the determination of the dangerous state in the dangerous state determination unit 41 will be described using the flowchart of FIG.

  In the flowchart of FIG. 7, a specific time interval of the latest day to be calculated or an arbitrarily selected day among the power time series data (power consumption data arranged in time series) accumulated in the power data storage unit 21 The power time-series data acquired every time (for example, every minute) is read for a time longer than a limit time (for example, 24 hours) set in advance as a continuation time used for determination of the dangerous state (step S31). When the limit time is set to 24 hours, not only the latest day or an arbitrarily selected day, but also the previous day or the next day, including the power time series data, the number of power data more than 24 hours Read only the predetermined number of data.

Thereafter, first, the power data (power consumption data) sequentially extracted from the read power time-series data in time-series order and the first threshold value t ₁ set by the threshold calculation unit 33 are compared in order. (Step S32).

Number of data sequentially retrieved power data from the power time-series data read out from the power data storage unit 21 (power consumption data) does not exceed the first threshold value t ₁ is continuously, the number of data corresponding to the limit time duration If it exceeds (YES in step S32), it is determined that the person in the house is in a dangerous state where the operation of starting the device cannot be performed at all for the limit time (step S35).

On the other hand, when the number of data whose power data (power consumption data) does not continuously exceed the first threshold t ₁ does not exceed the number of data corresponding to the limit time (NO in step S32), then, comparing the second threshold value t ₂ of time-sequentially retrieved power data (power consumption data) and the threshold value calculation unit 33 is set to the acquired time sequence in the order (step S33).

Data number data does not drop to the second threshold value t ₂ less continuously sequentially extracted power data from the read power time series data from the power data storage unit 21 (power consumption data) is, corresponding to the limit time duration Is exceeded (YES in step S33), it is determined that the person in the house is in a dangerous state that cannot stop the operation of the device at all for the limit time (step S35). .

On the other hand, when the power data (power consumption data) number of data does not decrease to a second threshold value t ₂ following in succession it has not exceeded the number of data corresponding to the limit time duration (NO in step S33) A person in the house has started operating the equipment or stopped operating the equipment at any timing of the limit time, and the person in the house is in a dangerous state. (Step S34).

As the nuclear, using the power consumption home device consumes of interest, it calculates a first threshold value determining human hazardous condition t ₁ and a second threshold value t _2, and the most recent day or any power time-series data for the selected day, the state does not decrease to the state or the second threshold value t ₂ less does not exceed the first threshold value t ₁ is greater than the limit time arbitrarily defined as the duration for the determination of the dangerous state If it continues, it is possible to automatically determine that the person in the house is in a dangerous state.

  In the flowchart of FIG. 7, a case is described in which whether or not a person in the house is in a dangerous state is calculated as a binary dangerous state determination result. You may make it calculate the dangerous state determination result which consists of the ratio numerical value (numerical value which is not restricted to 2 value) which shows the grade of a state.

For example, even if the duration state does not fall state or the second threshold value t ₂ less does not exceed the first threshold value t ₁ continues was kept within the limits hours, then shows the calculation results of Equation, You may make it output as a dangerous state determination result which consists of a ratio numerical value which shows the grade of a dangerous state.

Dangerous state determination result = (state in which the first threshold value t ₁ set by the threshold value calculation unit 33 is not exceeded)
Or the duration for which the state that does not decrease below the second threshold t ₂ continues
Longest maximum duration) / (limit time)
In other words, by extracting the longest duration state not lowered to the first threshold value t ₁ of the state or the second threshold value t ₂ less does not exceed the threshold value calculation unit 33 is set lasted longest, the percentage of the time limit, You may make it calculate as a dangerous state determination result which consists of a numerical ratio (numerical value which is not restricted to 2 value) which shows the grade of a dangerous state.

In addition, a binary dangerous state determination result indicating whether or not a person in the house is in a dangerous state and a dangerous state determination result including a numerical ratio indicating the degree of the dangerous state are calculated, and the person falls into the dangerous state. when outputting information indicating the degree of information or hazardous condition indicating that is, indicating which if any of the one state not lowered to the second threshold value t ₂ below or state that does not exceed the first threshold value t ₁ Information may be output as detailed information.

(Description of the effect of this embodiment)
As described in detail above, in the present embodiment, not only can the human dangerous state staying in the house be automatically determined based on the power consumption of the device installed in the house, Further, the following effects can be obtained.

First, it is not necessary to set an initial value for calculating the first threshold t ₁ and the second threshold value t ₂ determines whether a human in the house has fallen at risk of interest manually, the it is possible to determine the past power time-series data direct and automatically from the first threshold t ₁ and the second threshold value t ₂ in a house, the first threshold t ₁ and the second threshold value by setting how the initial value t ₂ is not able to cause the problem of change.

Second, the first threshold t ₁ and the second threshold t ₂ for determining whether or not a person is in a dangerous state in the target house are directly and automatically determined from past power time series data in the house. it is possible to ask the, when operation of the hazardous condition determination system 100, the user does not require knowledge and experience about the first threshold t ₁ and the second threshold value t ₂ set.

Third, since the past power time-series data in the home is used for the automatic calculation of the first threshold t ₁ and the second threshold t ₂ for determining the presence or absence of a human dangerous state in the target home, the user It is possible to calculate and set an optimum value for each and every season.

DESCRIPTION OF SYMBOLS 1 ... Electric power data input part, 2 ... Memory | storage part, 3 ... Threshold calculation part, 4 ... Determination part, 5 ... Danger state output part, 21 ... Electric power data storage part, 31 ... Histogram generation part, 32 ... Data filtering part, 33 ... threshold value calculation unit, 41 ... danger state determination unit, 100 ... danger state determination system.

Claims (8)

  A dangerous state determination system for determining a human dangerous state in a target house, and means for acquiring power consumption per day in a predetermined period in the house at a predetermined time interval A means for generating a histogram relating to the power consumption for each day in the house and a discriminant analysis method applied to the generated histogram for each day to reduce power consumption and low power consumption. A degree of separation that is separated into two classes, that is, a class and a high-consumption class that consumes a large amount of power, is calculated every day, and means for selecting a day on which the calculated degree of separation is maximized; Deriving thresholds for separation into two classes, and converting the derived thresholds into automatic device operation states in which devices are automatically operated without human operation Means for setting as a first threshold value for determining a human dangerous state, and the minimum power for each day with the smallest power consumption in each of the generated histograms for each day Means for selecting the minimum power consumption with the smallest power consumption from the extracted daily minimum power consumption, and the state of the automatic operation of the equipment based on the selected minimum power consumption. And a means for calculating a minimum value of the power consumption amount at the time and setting the calculated minimum value of the power consumption amount as a second threshold value for determining a human dangerous state. State determination system.   The dangerous state determination system according to claim 1, wherein when determining the dangerous state of the person in the house on the latest past day or a selected day, power data relating to the power consumption in the house on the day is acquired. Each of the acquired power data is sequentially compared with the first threshold and the second threshold in time series, and the acquired power data does not exceed the first threshold or does not decrease below the second threshold. Is further provided with means for calculating a determination result for determining whether or not it has continued beyond a predetermined limit time as a dangerous state determination result indicating a human dangerous state in the house. Hazardous state judgment system.   A dangerous state determination method for determining a human dangerous state in a target home, the step of acquiring power consumption per day for a predetermined period in the past in the home at a predetermined time interval, and A step of generating a histogram relating to the daily power consumption in the house, and applying a discriminant analysis method to the generated daily histogram to reduce power consumption and low power consumption. A separation degree that is separated into two classes of a class and a high consumption class with a large amount of power consumption is calculated every day, and a day on which the calculated separation degree is maximized is selected. Deriving thresholds for separation into two classes, automatic device operation where the devices are automatically operated without human operation Considering it as the maximum value of power consumption in the state, setting as a first threshold value for determining a human dangerous state, and the minimum of each day with the smallest power consumption in each of the generated daily histograms Extracting power consumption, selecting a minimum power consumption with the smallest power consumption from the extracted daily minimum power consumption, and based on the selected minimum power consumption, Calculating a minimum value of power consumption in a state, and setting the calculated minimum value of power consumption as a second threshold for determining a human dangerous state; How to judge dangerous situations.   4. The method for determining a dangerous state according to claim 3, wherein when determining the dangerous state of the person in the house on the latest past day or a selected day, power data relating to the power consumption in the house on the day is acquired. Each of the acquired power data is sequentially compared with the first threshold and the second threshold in time series, and the acquired power data does not exceed the first threshold or does not decrease below the second threshold. Is characterized by further comprising a step of calculating a determination result for determining whether or not the predetermined limit time has been exceeded as a dangerous state determination result indicating a human dangerous state in the house. How to judge dangerous situations.   5. The risk condition determination method according to claim 4, wherein when the risk condition determination result is calculated, the power data at each acquired time and the threshold value are sequentially compared, and the power data exceeds the first threshold value. In the case where the person in the house is in a dangerous state, while the power data is not in the first threshold. When a state that does not exceed one threshold value or a state that does not decrease below the second threshold value does not continue beyond the limit time, it is determined that a person in the house is not in a dangerous state. A dangerous state determination method, wherein a result is calculated as a binary dangerous state determination result.   5. The risk condition determination method according to claim 4, wherein when the risk condition determination result is calculated, the power data at each acquired time and the threshold value are sequentially compared, and the power data exceeds the first threshold value. A risk characterized in that a ratio of a duration time during which no state or a state that does not decrease below the second threshold continues to the limit time is calculated as a dangerous state determination result including a numerical ratio indicating the degree of a human dangerous state State determination method.   7. The danger state determination method according to claim 3, wherein the power consumption amount in the automatic operation state of the device calculated based on the minimum power consumption amount selected from the daily minimum power consumption amounts. When the minimum value is set as the second threshold, the value of the selected minimum power consumption itself or a value obtained by adding a predetermined power margin to the selected minimum power consumption is used as the device. A dangerous state determination method, wherein the second threshold value is set as a minimum value of power consumption in an automatic driving state.   A dangerous state determination program, wherein the dangerous state determination method according to claim 3 is implemented as a program executable by a computer.

Images