JP7601820B2 - Estimation system, computer program, and estimation method - Google Patents

Description

The present disclosure relates to an estimation system, a computer program, and an estimation method.

Conventionally, there is known a technique for estimating the power consumption of each of multiple devices used in a residence based on the power measured at the main of a distribution board (see, for example, Patent Document 1). There is also known a technique for estimating the attributes of a corresponding user based on the power consumption (see, for example, Patent Document 2).

JP 2013-213825 A JP 2015-162229 A

Conventionally, technology for estimating user characteristics using power consumption as an indicator has been based on the total power consumption in a residence. With this conventional technology, user characteristics are estimated based on time series data of total power consumption with low time resolution, so it is not possible to estimate detailed user characteristics with high accuracy.

Therefore, according to one aspect of the present disclosure, it is desirable to provide a technology that can estimate detailed characteristics of residents in a residence with higher accuracy than conventional methods based on the residence's electricity consumption.

According to one aspect of the present disclosure, an estimation system is provided. The estimation system includes an acquisition unit and an estimation unit. The acquisition unit is configured to acquire, as power information, information indicating the power consumption of each of a plurality of devices used in the residence of the household, determined by monitoring the power supplied through the electrical wiring in the residence of the household.

The estimation unit is configured to estimate the lifestyle of the household based on the power consumption of each device indicated by the power information acquired by the acquisition unit. The lifestyle estimation includes at least one of estimating the lifestyle of the household that is correlated with the power consumption and estimating the lifestyle behavior.

This estimation system estimates the lifestyle of the people living in the home, i.e., the detailed characteristics of the household, particularly the living conditions or behavior, with greater accuracy than ever before, by estimating the lifestyle based on the power consumption of multiple devices in the home.

According to an aspect of the present disclosure, the acquisition unit may acquire, as the power information, information indicating the amount of power consumption of each device per predetermined time period.
According to an aspect of the present disclosure, the acquisition unit may further acquire, as the power information, information indicating a total amount of power consumption per predetermined hour used in the residence determined by the power monitoring. In this case, the estimation unit may perform lifestyle estimation based on the total amount of power consumption per predetermined hour and the power consumption of each device per predetermined hour indicated by the power information.

Lifestyle estimation based on total consumption and the power consumption of individual devices allows for more accurate estimation of the household's lifestyle. For example, there may be cases where it is difficult to determine the power consumption of every device in a residence. In such cases, by taking into account total consumption, it is possible to perform lifestyle estimation while indirectly taking into account the usage of devices whose power consumption cannot be captured individually.

According to one aspect of the present disclosure, the acquisition unit may further acquire, as the power information, information indicating the total remaining power consumption other than the power consumption of a plurality of devices included in the total consumption for each specified time period, which is determined as other consumption by power monitoring.

The estimation unit may perform lifestyle estimation based on the total consumption per specified hour, the power consumption of each device per specified hour, and other consumption per specified hour, which are indicated by the power information. By performing lifestyle estimation that takes into account the usage status of devices whose power consumption cannot be captured individually, it is possible to accurately estimate the lifestyle of a household.

According to one aspect of the present disclosure, the acquisition unit may further acquire, as the power information, information indicating stationary or non-stationary components as components included in the total consumption determined by monitoring the power. The estimation unit may perform lifestyle estimation based on the total consumption and components for each predetermined time period indicated by the power information and the power consumption of each device for each predetermined time period.

The stationary component is likely to be associated with the static lifestyle of the household. The non-stationary component is likely to be associated with the dynamic lifestyle of the household. Therefore, lifestyle estimation that takes into account the stationarity or non-stationarity of electricity consumption makes it possible to estimate the lifestyle of the household with higher accuracy.

According to one aspect of the present disclosure, the estimation unit may perform lifestyle estimation by inputting features of electricity consumption in a household into a machine learning model based on the electricity consumption of each device, and obtaining an estimated value regarding the lifestyle of the household as an output of the machine learning model. The machine learning model may be a machine learning model constructed based on a group of training data indicating a correspondence between the features of electricity consumption for each household and the lifestyle of the household for a plurality of households. By using the machine learning model, it is possible to estimate the lifestyle with high accuracy without manually analyzing the correspondence.

According to one aspect of the present disclosure, the estimation unit may calculate, for each of the multiple devices, one or more of the maximum, minimum, and average power consumption of the corresponding device within a corresponding time segment for each predefined time segment, as an actual value based on time series data of the power consumption of the corresponding device over a predetermined period of time. The estimation unit may also perform lifestyle estimation based on the actual values for each time segment of the multiple devices. Lifestyle estimation based on such organization of time series data allows for lifestyle estimation to be performed with low load and high accuracy.

According to one aspect of the present disclosure, the estimation unit may calculate, for each of the multiple devices, one or more of the number of times the corresponding device is used, the usage time of the corresponding device, and the usage rate of the corresponding device relative to the multiple devices, as the usage amount based on the time series data of the power consumption of the corresponding device. Furthermore, the estimation unit may perform a lifestyle estimation of the household based on the calculated usage amount of each of the multiple devices in addition to the power consumption of each device. By using the usage amount in the estimation, a more accurate lifestyle estimation may be achieved.

According to one aspect of the present disclosure, estimating living conditions may include at least one of estimating household composition, estimating lifestyle, and estimating life events.

According to one aspect of the present disclosure, the estimation unit can estimate the living situation by estimating a lifestyle of a household from among a plurality of predetermined lifestyles.
According to one aspect of the present disclosure, the estimation unit may estimate a lifestyle related to at least one of entertainment, meals, work, and housework as a lifestyle of a household.

According to one aspect of the present disclosure, the estimation unit can estimate the living activities of a household by estimating the current living activities of the household or predicting the future living activities of the household based on time series data of the power consumption of each device.

According to one aspect of the present disclosure, estimating or predicting daily activities may include estimating or predicting at least one of activities related to going out, eating, and sleeping.

According to one aspect of the present disclosure, the estimation system may include a selection unit and a distribution unit. The selection unit may be configured to select information content to be distributed to an information terminal associated with the household based on information related to at least one of the living situation and living behavior of the household obtained by the lifestyle estimation. The distribution unit may be configured to transmit the information content selected by the selection unit to the information terminal.

By distributing information content using these lifestyle estimation results, it becomes more likely that information content that is of great interest to consumers can be provided to them.

According to one aspect of the present disclosure, the estimation system may include a data output unit configured to output household characteristic data describing information about at least one of the living conditions and living activities of the household estimated by the estimation unit in association with a household identifier.

The identifier may be a terminal ID for advertisement delivery issued to an information terminal used by the household or a cookie ID issued to a browser. Such data output may provide useful information to, for example, devices or companies that deliver advertisements.

According to one aspect of the present disclosure, another estimation system may be provided that includes an acquisition unit, an estimation unit, and a data output unit. In this estimation system, the acquisition unit may be configured to acquire, as the power information, information indicating the amount of power consumption related to the power consumed by the household in the residence.

The estimation unit may be configured to perform household lifestyle estimation, including at least one of estimating the household lifestyle conditions and estimating the lifestyle behavior of the household that are correlated with the power consumption, based on the power consumption indicated by the power information acquired by the acquisition unit.

The data output unit may be configured to output household characteristic data that describes information about at least one of the living conditions and living activities of the household estimated by the estimation unit in association with a household identifier. The identifier may be a terminal ID or a cookie ID for advertisement delivery.

This type of estimation system configuration can also provide useful information to devices or companies that deliver advertisements or collect consumer information, for example.

According to one aspect of the present disclosure, the data output unit may output characteristic data for a plurality of customers so as to transmit household characteristic data to a system that manages a customer database that stores characteristic data for each customer in association with a corresponding customer identifier.

According to one aspect of the present disclosure, the other estimation system may include an update unit. The update unit may be configured to update a database including characteristic data for each of a plurality of households. The update unit may update the database so that the database stores, as characteristic data for a household that is the subject of lifestyle estimation, characteristic data that describes information regarding at least one of the living situation and living behavior of the household estimated by the estimation unit in association with a household identifier. The identifier may be a terminal ID for advertisement delivery issued to an information terminal used by the household or a cookie ID issued to the browser. With such a configuration of the estimation system, a database that is useful for advertisement delivery can be constructed.

According to one aspect of the present disclosure, there may be provided yet another estimation system including an acquisition unit, an estimation unit, and an update unit. In this estimation system, the acquisition unit may be configured to acquire, as the power information, information indicating the amount of power consumption related to the power consumed by the household in the residence.

The estimation unit may be configured to perform household lifestyle estimation, including at least one of estimating the household lifestyle conditions and estimating the lifestyle behavior of the household that are correlated with the power consumption, based on the power consumption indicated by the power information acquired by the acquisition unit.

The update unit may be configured to update a database that includes characteristic data for each of a plurality of households. The update unit may update the database so that the database stores, as characteristic data for a household that is the subject of lifestyle estimation, characteristic data that describes information regarding at least one of the living situation and living behavior of the household estimated by the estimation unit in association with a household identifier. The identifier may be a terminal ID or a cookie ID for advertisement delivery.

According to one aspect of the present disclosure, a computer program may be provided for causing a computer to realize at least some of the functions of the estimation system described above. For example, a computer program may be provided for causing a computer to realize the functions of the acquisition unit and the estimation unit in the estimation system described above.

According to one aspect of the present disclosure, a computer program may be provided for causing a computer to realize the functions of the acquisition unit, the estimation unit, the selection unit, and the distribution unit in the estimation system described above.

According to one aspect of the present disclosure, a computer program may be provided for causing a computer to realize the functions of the acquisition unit, the estimation unit, and the data output unit in the estimation system described above.

According to one aspect of the present disclosure, a computer program may be provided for causing a computer to realize the functions of the acquisition unit, the estimation unit, and the update unit in the estimation system described above.

According to one aspect of the present disclosure, there may be provided an estimation method executed by a computer, comprising: acquiring information indicating the power consumption of each of a plurality of devices used by a household in the residence, determined by monitoring the power supplied through electrical wiring in the household's residence; and making a lifestyle estimation of the household based on the power consumption of each device indicated by the acquired information, wherein the lifestyle estimation includes at least one of estimating the household's living conditions and estimating the living behavior of the household that are correlated with the power consumption.

According to one aspect of the present disclosure, there may be provided an estimation method executed by a computer, the estimation method including: acquiring information indicating power consumption related to power consumed by a household in a residence; making a household lifestyle estimation including at least one of estimating a household lifestyle situation and/or estimating a lifestyle behavior of the household that is correlated with the power consumption based on the power consumption indicated by the acquired information; and outputting household characteristic data describing information regarding at least one of the estimated household lifestyle situation and lifestyle behavior in association with a household identifier. The identifier may be a terminal ID or a cookie ID for advertisement delivery.

According to one aspect of the present disclosure, there may be provided an estimation method executed by a computer, the estimation method including: acquiring information indicating power consumption related to power consumed by a household in a residence; performing a household lifestyle estimation including at least one of estimating a household's lifestyle situation and estimating lifestyle behavior that is correlated with the amount of power consumption based on the amount of power consumption indicated by the acquired information; and updating a database that includes characteristic data for each of a plurality of households, the database being updated so that the database stores, as the characteristic data for the household that is the subject of the lifestyle estimation, characteristic data that describes information regarding at least one of the estimated household's lifestyle situation and lifestyle behavior in association with a household identifier. The identifier may be a terminal ID or a cookie ID for advertisement delivery.

1 is a block diagram illustrating a configuration of an information processing system according to a first embodiment. FIG. 2 is a diagram illustrating a configuration of power analysis data. 11 is a flowchart showing a lifestyle estimation process executed by a processor. 13 is a diagram showing a configuration of power consumption feature data input to an estimation model. FIG. FIG. 2 is a diagram showing a configuration of lifestyle estimation data output from an estimation model. FIG. 13 is a diagram illustrating segment definitions for each category related to lifestyle. FIG. 2 is a diagram illustrating a configuration of a user management database. 11 is a flowchart showing a model construction process executed by a processor. FIG. 9A is a flowchart showing a data providing process executed by a processor, and FIG. 9B is a diagram explaining that data provided from the information processing system is associated with customer data in a customer management system through an advertising identifier. 11 is a flowchart illustrating a first advertisement delivery process executed by a processor. 11 is a flowchart illustrating a second advertisement delivery process executed by the processor. FIG. 13 is an explanatory diagram regarding estimation of a lifestyle in a modified example. 13 is a flowchart showing a behavior estimation process executed by a processor in the second embodiment. FIG. 14A is a diagram showing a configuration of behavior estimation data output from a behavior estimation model, and FIG. 14B is an explanatory diagram relating to behavior estimation. 13 is a flowchart showing a life event estimation process executed by a processor in a third embodiment. FIG. 13 is a diagram showing the configuration of household life event estimation data output from the life event estimation model.

Exemplary embodiments of the present disclosure will now be described with reference to the drawings.
[First embodiment]
The information processing system 1 of this embodiment is a system configured to estimate the life of a household within a residence, in particular the living conditions and living activities that are correlated with power consumption, based on information on the power consumed in the residence.

This information processing system 1 includes a processor 11, a memory 13, a storage 15, and a communication interface 19. The processor 11 is configured to execute processing according to a computer program stored in the storage 15. The memory 13 is used as a working area when the processor 11 executes processing.

The storage 15 includes a hard disk drive or solid state drive, and stores computer programs and various data used when the processor 11 executes processes. The communication interface 19 is connected to a wide area network.

For example, the information processing system 1 is configured to be able to communicate through the communication interface 19 with a cloud server 20, a customer management system 30 of a company that uses the services provided by the information processing system 1, a distribution server 40 for advertising, and a web server 50 that provides various information to users.

The cloud server 20 is configured to analyze the power measurement data acquired from each of a plurality of households using the analysis unit 21 (see FIG. 2 ) and provide the generated power analysis data to the information processing system 1. The function of the analysis unit 21 is realized, for example, by a processor (not shown) in the cloud server 20 executing processing according to a computer program.

Each household's power measurement data is transmitted from a meter 110 installed in the corresponding household's residence to a cloud server 20 via a communication device 140 in the residence and the wide area network.

The meter 110 for each household is provided on the main side of a distribution board 100 provided in the residence of the corresponding household, which is surrounded by a dashed line in FIG. 1. In the distribution board 100, the electrical wiring extending from the main side is branched off at a branch circuit 120. The electrical wiring within the residence extending from the branch circuit 120 is connected to wiring sockets for each of the multiple rooms.

The meter 110 is installed upstream of the branch circuit 120 in the distribution board 100, and measures the power supplied from the main side to the residence at a point before the branch. In other words, the meter 110 measures the power supplied to the residence by monitoring the power supplied through the electrical wiring in the household's residence at a point upstream before the electrical wiring branches.

The meter 110 is configured to measure the power consumption, which is the amount of power consumed within the residence during a given period of time, at each given time interval, and provide the measured power consumption for each given period of time to the cloud server 20 as time-series power measurement data. The given period of time is, for example, one minute.

The amount of power consumption per given time indicated by this power measurement data is the sum of the power consumption in the residence, including the power consumption of multiple devices 150 used by the household in the residence, i.e., the total consumption. The power branched off from the branch circuit 120 is supplied through the electrical wiring in the residence, and further through power taps installed in each room in the residence, to multiple devices 150 connected to the power taps.

The multiple devices 150 are electric or electronic devices. Examples of the multiple devices 150 include a refrigerator, a microwave oven, a washing machine, a TV receiver, and an air conditioner (hereinafter referred to as an "air conditioner"). There may be multiple devices of the same type in a residence. For example, there may be multiple TV receivers in a residence. In the following, multiple devices of the same type are conceptually treated as one device.

The analysis unit 21 of the cloud server 20 shown in FIG. 2 determines, for each household, the power consumption per given time of each of the multiple devices 150, i.e., the power consumption per device, from the power consumption per given time indicated by the power measurement data provided from the meter 110 of the corresponding household, and generates power analysis data that explains the determined power consumption per device in chronological order. The power analysis data is held in the cloud server 20, and is provided from the cloud server 20 to the information processing system 1 in response to a request from the information processing system 1.

The structure of the generated power analysis data is illustrated in FIG. 2. According to this example, the power analysis data has records for each meter ID, each measurement date and time, and each classification, which describe the power consumption for a specified time period of the household identified by the meter ID at the corresponding date and time and for the corresponding classification. The power consumption for a specified time period means the amount of power consumed during the specified time period. The records are arranged in chronological order in the power analysis data, for example, for each meter ID.

The meter ID here means the identification code of the meter 110. The measurement date and time means the date and time when the corresponding power consumption occurred. The measurement date and time is recorded in the record with the smallest unit being minutes. The classification indicates the type of power consumption described in the corresponding record.

The analysis unit 21 records the total consumption of the corresponding household in the specified time period (total amount of electricity consumed in the residence) as a record describing the amount of electricity consumed in the specified time period. The analysis unit 21 further generates, for each of the multiple devices 150, a record describing the amount of electricity consumed in the specified time period of the corresponding device 150.

The analysis unit 21 further generates a record that describes the remaining power consumption that could not be separated into the power consumption by device from the total consumption as other consumption. The other consumption corresponds to the total power consumption of one or more devices 150 of unknown type used in the residence other than the multiple devices 150 whose individual power consumption has been determined. Hereinafter, the one or more other devices 150 are conceptually regarded as one device and are simply referred to as "other devices". The power consumption of the other devices, i.e., the other consumption, is obtained by subtracting the sum of the power consumption by device from the total consumption.

If a record describes "total consumption," the record describes a classification code indicating that the power consumption is total consumption. If a record describes the power consumption of one device 150, the record describes a classification code that can identify the corresponding one device 150. If a record describes "power consumption" of other devices, the record describes a classification code indicating that the power consumption is the power consumption of other devices.

The processor 11 of the information processing system 1 executes the lifestyle estimation process shown in FIG. 3 for each household, thereby estimating the lifestyle of the corresponding household based on the power analysis data of the corresponding household stored in the cloud server 20. The lifestyle estimation process is executed for each household at predetermined intervals.

When the lifestyle estimation process is started, the processor 11 acquires from the cloud server 20 power analysis data representing the power consumption of the target household for each predetermined time period within a target period as the power analysis data to be used for the lifestyle estimation (S110). The target household here refers to the household whose lifestyle is to be estimated, and the target period refers to the measurement period of the power consumption to be used for the lifestyle estimation.

Then, based on the acquired power analysis data, the processor 11 calculates the characteristic quantities for each time segment related to the total consumption per specified hour as the characteristic quantities related to the power consumption of the target household in the target period (S120). The time segments referred to here are time segments defined by subdividing one week.

Specifically, a time segment is defined by dividing a week into a combination of days of the week and time periods. In other words, a time segment is a combination of days of the week and time periods. A time period is defined, for example, by dividing a 24-hour period into one-hour units. For example, examples of time segments include the time period from 7:00 to 8:00 on Monday, and the time period from 13:00 to 14:00 on Wednesday.

The characteristic quantities for one hour segment regarding the total consumption per specified hour are the maximum, minimum, and average values regarding the total consumption for the specified hour in all time periods corresponding to that hour segment in the target period. That is, in S120, the processor 11 calculates, for each hour segment, the maximum, minimum, and average values of the total consumption for the specified hour in the target household and the corresponding hour segment as the characteristic quantities regarding the total consumption per specified hour, based on the power analysis data for the corresponding household and the target period acquired in S110.

Furthermore, for each of the multiple devices 150 and other devices, the processor 11 calculates a characteristic value for each time segment relating to the power consumption of the corresponding device per specified time period (S130).

The characteristic quantities calculated here for one time segment of the corresponding device are the maximum, minimum, and average values for the power consumption of the corresponding device for a specified time period in all time periods that fall within that time segment of the target period. That is, in S130, based on the power analysis data for the corresponding household and the target period acquired in S110, the processor 11 calculates, for each device, the maximum, minimum, and average values for the power consumption of the corresponding device in the target household for a specified time period for each time segment as characteristic quantities for the power consumption of the corresponding device per specified time period.

Furthermore, for each of the multiple devices 150 and other devices, the processor 11 calculates a feature quantity related to the usage amount of the corresponding device during the target period (S140). Examples of the feature quantity here include the number of times the device is used during the target period, the usage time, and the usage rate.

The number of uses can be determined, for example, from the change in power consumption in response to turning the corresponding device on/off. The usage time can be determined from the time during which the corresponding device consumes power exceeding its standby power. The usage rate can be calculated as the ratio of the number of uses or usage time of the corresponding device to the total number of uses or usage time of all devices for which the number of uses or usage time are calculated during the target period.

In S140, the processor 11 can calculate at least one of the number of uses, the usage time, and the usage rate as the above-mentioned characteristic amount for each device.

Furthermore, the processor 11 calculates the steady-state power consumption, which is the amount of power steadily consumed during the target period regardless of day or night, from the time change of the total consumption in the power analysis data, as one characteristic amount related to the household's power consumption (S150). Instead of the steady-state power consumption, the non-steady-state power consumption for each predetermined time period calculated by subtracting the steady-state power consumption from the total consumption may be used in subsequent processing.

Then, the processor 11 generates array data in which the feature quantities calculated in S120 to S150 are arranged as input data for the estimation model. Hereinafter, this array data will be referred to as power consumption feature data (S160). The feature quantities included in the power consumption feature data correspond to actual values related to power consumption.

The processor 11 inputs the electricity consumption characteristic data generated in S160 into a lifestyle estimation model, which is an estimation model constructed in advance to estimate the lifestyle of the household, and obtains from the lifestyle estimation model lifestyle estimation data of the corresponding household that is output from the lifestyle estimation model in response to the input (S170). This estimation model is, for example, a machine learning model, and can be constructed by machine learning using training data. Examples of estimation models include neural networks.

Figure 4 shows an example of the configuration of power consumption characteristic data input to the lifestyle estimation model. Figure 5 shows an example of the configuration of lifestyle estimation data output from the lifestyle estimation model.

The power consumption characteristic data illustrated in FIG. 4 includes characteristic quantities for each time segment related to the total consumption per specified time. Furthermore, the power consumption characteristic data includes characteristic quantities related to a refrigerator, microwave oven, rice cooker, induction cooker, washing machine, vacuum cleaner (corded), TV receiver, air conditioner, and heater as characteristic quantities of multiple devices 150. A heater here refers to a device that includes a heating wire, such as a dryer or electric kettle. Furthermore, the power consumption characteristic data includes characteristic quantities of other devices.

The power consumption characteristic data includes, as features of each device, features for each time segment related to the power consumption of the device per given time period, and features related to the usage amount of the device. The power consumption characteristic data further includes, as a feature, the steady-state power consumption amount during the target period.

The lifestyle estimation data illustrated in FIG. 5 includes, for each lifestyle category, identification information (e.g., segment number) of the segment to which the target household is estimated to belong. Examples of categories include demographic attributes, diet, work, leisure, sleep, and housework.

For each category, a segment is defined, as shown in Figure 6, but is not limited to this. Training data is prepared according to this segment definition, and a lifestyle estimation model is constructed by machine learning based on the training data. The lifestyle estimation data output from the lifestyle estimation model describes the identification information of the segment to which the target household belongs for each category.

According to the example in FIG. 6, the demographic attribute categories define a "children" segment for households with children, a "elderly" segment for households with elderly people, and a "pets" segment for households with pets. These segments represent household composition.

In the food category, the "home cooking" segment is defined as households that cook a lot at home, the "delivery" segment is defined as households that make a lot of use of food delivery services, and the "eating out" segment is defined as households that eat out a lot.

In the work category, the "dual income" segment is defined as dual-income households, the "single income" segment is defined as single income households, and the "telework" segment is defined as teleworking households.

In the leisure category, the "indoor type", "outdoor type", and "travel type" segments are defined. Leisure corresponds to the example of entertainment. In the sleep category, the "early bed type", "night owl type", and "reversed day and night type" segments are defined.

When the lifestyle estimation data is acquired in S170, the processor 11 registers the acquired lifestyle estimation data in the management data of the target household existing in the user management database 15A stored in the storage 15 (S180). After that, the lifestyle estimation process shown in FIG. 3 is terminated.

As shown in FIG. 7, the management data includes a household ID, which is an identification code for the household, a meter ID, which is an identification code for the meter 110 installed in the household, and an advertising identifier linked to the household's information terminal 60, and the lifestyle estimation data is associated with the household ID, meter ID, and advertising identifier and registered in the user management database 15A. With this registration, the user management database 15A is updated to store the lifestyle estimation data in association with the household's advertising identifier.

The advertising identifier is registered in the management data for the purpose of delivering advertisements to information terminals 60 owned by members of the household (e.g., the head of the household). The advertising identifier is information for identifying the destination of the advertisement.

Specifically, the advertising identifier may be a terminal ID unique to an information terminal 60 such as a smartphone that is assigned to the information terminal 60 and used for delivering advertisements. Alternatively, the advertising identifier may be a cookie ID issued to the browser of the information terminal 60, or an email address for sending advertising content to the information terminal 60 by email. The advertising content corresponds to information content for advertising.

The advertising ID and cookie ID can be obtained from the information terminal 60 that is the access source, for example, when accepting registration for advertisement distribution from a household through the web server 50, or when obtaining permission to collect power information using the meter 110 and use the collected data. The email address can be obtained through input from the user when the user registers.

In addition, the advertising identifier can be obtained from the household's information terminal 60 or members of the household in various situations during the process of using services through the information processing system 1 of this embodiment and collecting power information.

For simplicity, the above describes an example in which the lifestyle estimation process is performed for each household, but the lifestyle estimation process may be performed in parallel for multiple households. Processor 11 can use matrices or the like to simultaneously perform lifestyle estimation for multiple households.

Next, details of the model construction process executed by the processor 11 to construct a lifestyle estimation model will be described with reference to FIG. 8. When an instruction to execute the model construction process is input from an administrator of the information processing system 1 via an operation device of the information processing system 1 (not shown), the processor 11 can execute the model construction process shown in FIG. 8.

Prior to executing the model construction process, the administrator acquires from the cloud server 20 power analysis data equivalent to the power analysis data acquired in S110 as data on the power consumption of multiple households that are cooperative with the survey as a panel. In addition, the administrator acquires questionnaire data on lifestyles from these multiple households. Based on this power data and questionnaire data, the administrator can generate power consumption characteristic data and lifestyle estimation data for each household.

This lifestyle estimation data is correct answer data based on the questionnaire data. The administrator creates a combination of each household's electricity consumption characteristic data and lifestyle estimation data as teacher data showing the correspondence between the electricity consumption characteristics of the corresponding household and their lifestyle, and stores this in storage 15.

When the processor 11 starts the model construction process, it reads out from the storage 15 a group of training data that has been stored in advance in the storage 15 (S210). The processor 11 then constructs a lifestyle estimation model by machine learning using the group of training data that has been read out (S220).

Then, the processor 11 stores the constructed lifestyle estimation model, specifically the parameters that define the estimation model, in the storage 15 (S230). The processor 11 then ends the model construction process.

The processor 11 can utilize the lifestyle estimation model stored in the storage 15 to estimate the lifestyle of each household for multiple households that are not part of the panel in the lifestyle estimation process shown in FIG. 3, and can associate the lifestyle estimation data with the advertising identifier of the corresponding household and store it in the storage 15 (S180).

Next, the details of the data provision process executed by the processor 11 using the lifestyle estimation data associated with the advertising identifier will be described with reference to Figures 9A and 9B. When the processor 11 receives a data request from an external system through the communication interface 19, it executes the data provision process shown in Figure 9A. An example of the external system is a customer management system 30 of a company that uses the data provision service provided by the information processing system 1.

When the data provision process starts, the processor 11 obtains the requested lifestyle estimation data from the user management database 15A in the storage 15. A data request from an external system is made by specifying an advertising identifier. For each of the one or more specified advertising identifiers, the processor 11 obtains lifestyle estimation data for the household associated with the corresponding advertising identifier from the user management database 15A (S310).

Then, the processor 11 associates each of the acquired lifestyle estimation data with the corresponding advertising identifier, and transmits the compiled data to the data requester via the communication interface 19 (S320). As a result, the processor 11 outputs the household characteristic data with the advertising identifier. The processor 11 then terminates the data provision process.

When the external system that requests the data is a customer management system 30 that manages a CRM (Customer Relationship Management) database, which is a customer database, the customer management system 30 can link the lifestyle estimation data with advertising identifiers provided by the information processing system 1 with customer data with advertising identifiers that it holds, using the advertising identifier as a clue, as shown in FIG. 9B.

The CRM database is a customer database that stores customer data, which is characteristic data for each customer, in association with the corresponding customer's identifier for multiple customers. Therefore, the lifestyle estimation data provision service realized in the information processing system 1 of this embodiment is very useful for enriching the customer data of companies that use the service.

Next, the details of the first advertisement delivery process executed by the processor 11 using the lifestyle estimation data associated with the advertisement identifier will be described with reference to FIG. 10. When a predetermined condition is satisfied, the processor 11 executes the first advertisement delivery process shown in FIG. 10.

The processor 11 can execute the first advertisement delivery process, for example, on the condition that the delivery cycle of the advertising content or a specified delivery time has arrived. Alternatively, the processor 11 can execute the first advertisement delivery process when a delivery instruction is input via an operation device of the information processing system 1 (not shown).

When the first advertisement delivery process is started, the processor 11 selects a target household from a group of households registered as targets for delivery of advertisement content (S410). The processor 11 then determines the lifestyle of the target household by referring to the lifestyle estimation data of the relevant household registered in the user management database 15A (S420).

Here, the lifestyle determination can be achieved by referring to the segment to which a particular category belongs among the multiple categories whose segments are described in the lifestyle estimation data. For example, if the advertising content to be delivered is related to food, the processor 11 can determine the segment to which the food category belongs by referring to the lifestyle estimation data.

For example, the processor 11 can determine the segment to which a pre-specified category belongs by referring to the lifestyle estimation data. Alternatively, the first advertisement delivery process may be executed for each category. For each category, a group of households to which the advertisement is to be delivered may be defined, and advertising content may be prepared for each category and for each segment.

After completing the processing in S420, the processor 11 selects, from among a plurality of pre-prepared advertising contents, the advertising content associated with the segment to which the processing target household belongs determined in S420 as the content to be distributed (S430).

In the next step S440, the processor 11 determines the advertising identifier of the household being processed by referring to the user management database 15A, and delivers the advertising content selected in S430 to the information terminal 60 corresponding to the advertising identifier. The processor 11 can make a delivery request to the distribution server 40, and deliver the advertising content to the information terminal 60 via the distribution server 40.

By repeatedly executing the processes of S410 to S440, the processor 11 delivers advertising content according to the segment to which the household belongs to to all households registered as targets for advertising content delivery. Then, when the delivery of advertising content to all households is completed (Yes in S450), the first advertising delivery process is terminated.

Here, for the sake of simple explanation and easy understanding, an example has been described in which content to be distributed is selected for each household, and the selected advertising content is distributed. However, it goes without saying that after selecting advertising content to be distributed to each of a plurality of households, a process of distributing the advertising content to each of the plurality of households may be executed. A distribution request to distribution server 40 may be an advertisement submission to distribution server 40.

In addition, the processor 11 can execute a second advertisement delivery process shown in FIG. 11 instead of or in addition to the first advertisement delivery process. The processor 11 can execute the second advertisement delivery process when a predetermined condition is satisfied. For example, the processor 11 can execute the second advertisement delivery process when a delivery instruction is input via an operation device of the information processing system 1 (not shown).

When the second advertisement delivery process is started, the processor 11 acquires delivery target information (S510). The delivery target information may be, for example, information that specifies a delivery destination by a combination of a lifestyle category and a segment. The delivery target information may be input from a delivery instruction source.

In the next step S520, the processor 11 determines a group of households belonging to a specified segment in the category specified in the distribution target information by referring to a group of lifestyle estimation data in the user management database 15A.

In the next step S530, the processor 11 distributes the advertising content specified by the distribution instruction source to the group of households identified in S520. At this time, the processor 11 identifies a group of advertising identifiers corresponding to the group of identified households, and distributes the advertising content to the group of information terminals 60 having these advertising identifiers. The distribution can be performed through the distribution server 40, similar to the processing in S440.

According to the information processing system 1 of this embodiment described above, lifestyle estimation based on the power consumption of multiple devices 150 in a residence makes it possible to estimate the lifestyle of the people living in the residence, i.e., the household, with higher accuracy than conventional methods.

According to this embodiment, since lifestyle estimation is performed based on the total consumption, the power consumption by device, and the power consumption of other devices, it is possible to appropriately consider the power consumption of devices of unknown types that cannot be separated by device. Furthermore, according to this embodiment, lifestyle estimation is performed while considering the stationary component of power consumption, so it is possible to realize a highly accurate lifestyle estimation.

Furthermore, in this embodiment, in order to prevent an excessive increase in input data to the estimation model that accompanies handling of power consumption by device, the power consumption is converted into statistical values for each time segment, and these statistical values are used to generate input data to the estimation model. Furthermore, taking advantage of the fact that people's daily activities show cyclical behavior according to the calendar, the time segments are defined by dividing one week into segments. Therefore, according to this embodiment, it is possible to realize highly accurate lifestyle estimation while suppressing the processing load on the processor 11.

In addition, in this embodiment, the lifestyle estimation data estimated by the estimation model is associated with an advertising identifier. The lifestyle estimation data with the advertising identifier can be used meaningfully for advertisement delivery and enrichment of customer data.

In the above embodiment, the types of lifestyles are defined by defining multiple segments for each lifestyle category. However, lifestyles may also be defined for each category by clustering a group of lifestyles in the corresponding category into multiple clusters.

Each lifestyle category can be subdivided by multiple parameters. For example, a lifestyle related to "meals" can be subdivided by multiple parameters, such as the type of food eaten, the place where the meal is eaten, the type of cook, and the frequency of eating out, as shown in FIG. 12. Clustering here corresponds to classifying lifestyles subdivided using multiple parameters into a small number of clusters. In this way, multiple clusters can be defined for each lifestyle category.

In this case, instead of estimating the segment to which the household belongs for each category, the processor 11 can estimate a cluster that corresponds to the household's lifestyle.

[Second embodiment]
The information processing system 1 of the second embodiment is configured such that the processor 11 executes the behavior estimation process shown in Fig. 13 in addition to the process described in the first embodiment. In the following, as the configuration of the information processing system 1 of the second embodiment, the details of the behavior estimation process executed by the processor 11 will be selectively described. The configuration of the information processing system 1 and the peripheral configuration of the information processing system 1 that are not mentioned in this embodiment may be understood to be the same as those of the first embodiment.

The processor 11 executes the behavior estimation process shown in FIG. 13 for each household, thereby estimating the behavior of the corresponding household from characteristics related to electricity consumption. The behavior to be estimated includes the daily activities of the household members within the residence and behavior related to entering and leaving the residence, which may have a correlation with electricity consumption. The processor 11 can periodically and repeatedly execute the behavior estimation process for each household.

When the behavior estimation process starts, the processor 11 acquires from the cloud server 20 power analysis data that represents the power consumption of the target household in a time series during a target period that is a predetermined past period including the present (S710). The target household here refers to the household whose behavior is to be estimated.

The processor 11 then generates power time series data that explains the changes in power consumption during the target period based on the acquired power analysis data (S720). As shown in FIG. 14A, the power time series data has array data that arranges the power consumption of multiple devices 150 and other devices at the corresponding date and time for each point in time of a specified time interval during the target period. The power time series data is configured as data in which this array data is arranged in chronological order. The power consumption is the power consumption for a specified period of time (e.g., one minute).

In the next step S730, the processor 11 inputs the power time series data generated in S720 into a behavior estimation model, and obtains behavior estimation data of the target household from the behavior estimation model as output data of the behavior estimation model. This estimation model is a mathematical model for estimating household behavior, and is constructed, for example, by machine learning using training data. Examples of estimation models include neural networks.

As shown in FIG. 14A, the behavior estimation data has a behavior flag for each type of behavior for multiple types of behavior to be estimated, which indicates with 1 or 0 whether the corresponding type of behavior has been performed. In other words, the behavior flag indicates with 1 or 0 an estimated value regarding whether the corresponding behavior has been performed. Examples of types of behavior include behaviors that may occur within a residence in daily life, such as taking a break, eating, doing laundry, cleaning, cooking, using SNS, watching mass media, bathing, sleeping, being at home, and going out. In another example, instead of the behavior flag, a score indicating the possibility of performing the corresponding behavior may be used, for example a score corresponding to the probability of the behavior, which may range from a value of 0 to a value of 1.

The behavior estimation data may represent, for example, whether or not the target household is performing each type of behavior at the present time (e.g., the time indicated by the black circle in FIG. 14B), which corresponds to the end point of the target period. Alternatively, the behavior estimation data may represent, as a predicted value, whether or not the target household is performing each type of behavior at a point in the near future, a certain time period from the present (e.g., the time indicated by the white circle in FIG. 14B).

In the next step S740, the processor 11 determines, based on the acquired behavior estimation data, whether the behavior estimation model has estimated that the target household is currently performing or will perform a specific type of behavior in the near future. The specific type of behavior may be one or more of the multiple types of behavior estimated by the behavior estimation model.

If the processor 11 determines that the household is currently performing a specific type of behavior or is estimated to perform the behavior in the near future, it makes a positive judgment in S740 and delivers advertising content corresponding to the specific type of behavior to the target household (S750).

That is, the processor 11 delivers advertising content to the information terminal 60 corresponding to the advertising identifier of the target household by referencing the user management database 15A. The processor 11 can deliver advertising content to the information terminal 60 via the distribution server 40.

When multiple types of behavior are set as a specific type of behavior, the processor 11 can select, from among the multiple advertising contents, advertising content corresponding to the type of behavior that is currently being performed or will be performed in the near future as the target for delivery, and deliver the selected advertising content.

On the other hand, if the household is not estimated to be currently performing or to be performing a particular type of behavior in the near future, the processor 11 makes a negative judgment in S740 and terminates the behavior estimation process without delivering the advertising content to the target household.

By repeatedly executing the behavior estimation process described above, the processor 11 can deliver the advertising content to the household's information terminal 60 when the household performs an action related to the advertising content, or when there is a high possibility that the household will perform the action in the near future. Alternatively, the processor 11 can switch the type of advertising content to be delivered in response to a change in the household's behavior.

The execution cycle of the behavior estimation process may be the same time interval as the acquisition period of the power analysis data used for behavior estimation (i.e., the target period described above), or may be a shorter time interval as shown in FIG. 14B.

Moreover, the specific type of behavior can be selected from among multiple types of behavior according to selection conditions set by an administrator of the information processing system 1. The processor 11 can select the specific type of behavior from among multiple types of behavior that can be estimated by the behavior estimation model, depending on the type of advertising content prepared for delivery.

Alternatively, each advertising content may have a delivery condition that specifies which of multiple types of behavior should be treated as the specific type of behavior. Processor 11 can execute the processes of S740 and S750 in accordance with the delivery condition.

In addition, prior to repeated execution of the behavior estimation process, the processor 11 can acquire training data for the behavior estimation model (S210), construct the behavior estimation model by machine learning using the training data (S220), and store parameters that define the constructed behavior estimation model in the storage 15 (S230), in the same manner as the model construction process of the first embodiment (see FIG. 8).

As training data, behavioral history data that explains whether or not multiple types of behaviors are performed over time can be obtained from multiple households corresponding to the panel. The training data can be created based on the power time series data and behavioral history data for each household corresponding to the panel. In other words, training data corresponding to the input and output of the behavior estimation model to be constructed can be created from the power time series data and behavioral history data for each household corresponding to the panel, and stored in storage 15.

According to the information processing system 1 of the second embodiment described above, current or near-future daily living activities can be estimated with high accuracy, and content delivery in response to changes in daily living activities can be realized, thereby realizing the delivery of highly appealing content.

[Third embodiment]
In the information processing system 1 of the third embodiment, the processor 11 is configured to further execute a life event estimation process shown in Fig. 15. In the following, as the configuration of the information processing system 1 of the third embodiment, the details of the life event estimation process executed by the processor 11 will be selectively described. The configuration of the information processing system 1 and the peripheral configuration of the information processing system 1 that are not mentioned in this embodiment may be understood to be the same as those of the first or second embodiment.

The processor 11 executes the life event estimation process shown in FIG. 15 for each household, thereby estimating the life events of the corresponding household from characteristics related to electricity consumption. The life events to be estimated are life events that may have a correlation with electricity consumption within the residence. The processor 11 can periodically and repeatedly execute the life event estimation process for each household.

When the life event estimation process is started, the processor 11 acquires power analysis data representing the power consumption of the target household during a target period, which is a relatively long past period including the present, such as one year, from the cloud server 20 (S810). The target household here refers to the household for which life events are to be estimated.

The processor 11 then generates long-term time series data that describes the changes in power consumption during the target period based on the acquired power analysis data (S820). As shown in FIG. 16, the long-term time series data has array data that arrays feature amounts of power consumption of the multiple devices 150 and other devices for each month in the target period, and is configured as data in which the array data for each month is arranged in chronological order. The feature amount may be the total power consumption of the corresponding device for the corresponding month. Alternatively, the feature amount may be a combination of the maximum, minimum, and average power consumption per specified time of the corresponding device for the corresponding month. Examples of the specified time include one minute, one hour, and one day.

In the next step S830, the processor 11 inputs the long-term time series data generated in S820 into a life event estimation model, and obtains life event estimation data of the target household from the life event estimation model as output data of the life event estimation model. This estimation model may also be a machine learning model such as a neural network, similar to the lifestyle estimation model and the behavior estimation model.

The life event estimation data shown in FIG. 16 has an event flag for each type of life event that indicates, with 1 or 0, whether or not a corresponding type of life event has occurred for multiple types of life events to be estimated.

An event flag is an estimate of whether or not a corresponding life event will occur. Examples of life events include marriage, pregnancy, childbirth, moving, and employment. Moving in this case includes the moving of some household members. In another example, instead of an event flag, a score indicating the likelihood of the corresponding life event occurring may be used, for example a score corresponding to the probability of occurrence with a possible range of values from 0 to 1.

Next, in S840, the processor 11 determines whether a specific type of life event has occurred in the target household based on the acquired life event estimation data. The specific type of life event may be one or more of the multiple types of life events estimated by the life event estimation model.

When the processor 11 determines that a specific type of life event has occurred in the target household (Yes in S840), it delivers advertising content corresponding to the specific type of life event to the target household (S850). That is, the processor 11 delivers the advertising content to the information terminal 60 corresponding to the advertising identifier of the target household.

When multiple types of life events are set as a specific type of life event, the processor 11 can select, from among the multiple advertising contents, advertising content that corresponds to the type of life event that is currently occurring as the target for delivery, and deliver the selected advertising content.

On the other hand, if the processor 11 determines that a specific type of life event will not occur in the target household (No in S840), it terminates the life event estimation process without delivering the advertising content to the target household.

By repeatedly executing the life event estimation process described above, the processor 11 can deliver advertising content to the household's information terminal 60 when the household is experiencing a life event related to the advertising content. Alternatively, the processor 11 can switch the type of advertising content to be delivered in response to changes in the household's life events.

The specific type of life event may be selected from among multiple types of life events according to selection conditions set by an administrator of the information processing system 1. According to another example, the processor 11 may select the specific type of life event from among multiple types of life events according to the type of advertising content prepared for delivery.

Alternatively, each advertising content may have a distribution condition that specifies which of multiple types of life events should be treated as the specific type of life event. Processor 11 may execute the processes of S840 and S850 in accordance with the distribution condition.

In addition, the life event estimation model can be constructed by machine learning prior to repeated execution of the life event estimation process. For example, training data regarding the input and output of the life event estimation model is prepared based on information provided by multiple households corresponding to a panel, and the life event estimation model can be constructed by machine learning based on the prepared training data.

According to the information processing system 1 of the third embodiment described above, a consumer's life events can be estimated from changes in power consumption, and content can be delivered in response to the occurrence of a life event, thereby enabling the delivery of highly appealing content.

[Other embodiments]
The present disclosure is not limited to the above-described embodiment, and can adopt various aspects.

For example, the idea of associating an advertising identifier with output data of an estimation model to be useful for ad delivery and enriching customer data is not limited to technology that estimates a user's living situation or daily activities based on the power consumption of each device. In other words, this idea may be applied to technology that estimates a user's living situation or daily activities based on total consumption. In other words, the above idea can also be applied to systems that do not separate power consumption by device.

The functions of one component in the above embodiments may be distributed among multiple components. The functions of multiple components may be integrated into one component. Part of the configuration of the above embodiments may be omitted. At least part of the configuration of the above embodiments may be added to or substituted for the configuration of another of the above embodiments. All aspects included in the technical ideas identified from the wording of the claims are embodiments of the present disclosure.

1...information processing system, 11...processor, 13...memory, 15...storage, 15A...user management database, 19...communication interface, 20...cloud server, 21...analysis unit, 30...customer management system, 40...distribution server, 50...web server, 60...information terminal, 100...distribution board, 110...measuring instrument, 120...branch circuit, 150...equipment.

Claims (35)

an acquisition unit configured to acquire, as power information, information indicating the power consumption of each of a plurality of devices used by the household in the residence, the information being determined by monitoring the power supplied through an electrical wiring in the residence of the household;
an estimation unit configured to estimate a lifestyle of the household based on the power consumption of each of the devices indicated by the power information acquired by the acquisition unit;
The lifestyle estimation includes at least one of estimating a lifestyle situation of the household correlated with the power consumption and estimating a lifestyle activity of the household,
the estimation unit calculates, for each of the plurality of devices, one or more of a usage count of the corresponding device, a usage time of the corresponding device, and a usage rate of the corresponding device with respect to the plurality of devices, based on time series data of the power consumption of the corresponding device;
The estimation unit is an estimation system that performs a lifestyle estimation of the household based further on the usage amount of each of the plurality of devices . The estimation system according to claim 1 , wherein estimating the living situation includes at least one of estimating a household composition, estimating a lifestyle, and estimating a life event. an acquisition unit configured to acquire, as power information, information indicating the power consumption of each of a plurality of devices used by the household in the residence, the information being determined by monitoring the power supplied through an electrical wiring in the residence of the household;
an estimation unit configured to estimate a lifestyle of the household based on the power consumption of each of the devices indicated by the power information acquired by the acquisition unit;
wherein the lifestyle estimation includes estimating life events of the household as a lifestyle condition of the household correlated with the amount of electricity consumption. The estimation system according to claim 3 , wherein the life events include at least one of marriage, pregnancy, childbirth, moving of some household members, and employment. The estimation system according to claim 3 or 4, wherein the lifestyle estimation includes estimating a lifestyle activity of the household that is correlated with the amount of power consumption. The estimation unit performs the lifestyle estimation by inputting a group of features related to the household into a machine learning model and obtaining an estimated value related to the lifestyle of the household as an output of the machine learning model;
the set of feature amounts includes feature amounts related to power consumption of each of the devices and feature amounts related to usage of each of the devices,
The estimation system according to claim 1 or claim 2 , wherein the machine learning model is constructed based on a group of training data indicating a correspondence between a group of the features for each household and lifestyles of a plurality of households. the estimation unit performs the lifestyle estimation by inputting features of the power consumption in the household into a machine learning model based on the power consumption of each of the devices and acquiring an estimated value regarding the lifestyle of the household as an output of the machine learning model;
The estimation system according to any one of claims 3 to 5, wherein the machine learning model is constructed based on a group of teacher data indicating a correspondence between the feature amount of the electricity consumption for each household and lifestyle of a plurality of households. The estimation unit is
For each of the plurality of devices, calculate, as an actual value, one or more of a maximum consumption amount, a minimum consumption amount, and an average consumption amount of the corresponding device within a corresponding time segment for each predefined time segment based on time series data of the corresponding device's power consumption during a predetermined period;
The estimation system according to any one of claims 1 to 7 , wherein the lifestyle estimation is performed based on the performance values for each time segment of each of the plurality of devices. the estimation unit is configured to calculate, for each of the plurality of devices, one or more of a maximum consumption amount, a minimum consumption amount, and an average consumption amount of power of the corresponding device within a corresponding time segment for each predefined time segment, as an actual value , based on time series data of power consumption of the corresponding device within a predetermined period of time;
The estimation system according to claim 6 , wherein the feature amount relating to the power consumption of each of the devices includes a performance value of the corresponding device for each time segment . The estimation system according to claim 1 , wherein the acquisition unit acquires, as the power information, information indicating power consumption of each of the devices for each predetermined time period. The acquisition unit further acquires, as the power information, information indicating a total consumption amount of power used in the residence per predetermined time period determined by the power monitoring, and
The estimation system according to claim 10 , wherein the estimation unit performs the lifestyle estimation based on the total power consumption for each of the predetermined hours and the power consumption of each of the devices for each of the predetermined hours, both of which are indicated by the power information. the acquiring unit further acquires, as the power information, information indicating a total of remaining power consumption other than the power consumption of the plurality of devices included in the total consumption for each predetermined time period, the remaining power consumption being determined as other consumption by the power monitoring;
The estimation system according to claim 11 , wherein the estimation unit performs the lifestyle estimation based on the total consumption for each specified hour, the power consumption of each of the devices for each specified hour, and the other consumption for each specified hour , all of which are indicated by the power information. The acquisition unit further acquires, as the power information, information indicating a steady component or a non-steady component as a component included in the total consumption amount determined by monitoring the power,
The estimation system according to claim 11 , wherein the estimation unit performs the lifestyle estimation based on the total consumption amount and the components for each of the predetermined hours, which are indicated by the power information, and the power consumption amount of each of the devices for each of the predetermined hours. The estimation system according to claim 1 , 2 , or 6 , wherein the estimation unit estimates the living situation by estimating a living style of the household from a plurality of predetermined living styles. The estimation system according to claim 14 , wherein the estimation unit estimates a lifestyle related to at least one of entertainment, food, work, and housework as the lifestyle of the household. The estimation system of claim 1, claim 2, claim 5, or claim 6, wherein the estimation unit estimates the living activities of the household by estimating the current living activities of the household based on time series data of the power consumption of each of the devices, or by predicting the future living activities of the household. The estimation system according to claim 16 , wherein the estimating or predicting the living behavior includes estimating or predicting at least one of behaviors related to going out, eating, and sleeping. A selection unit configured to select information content to be delivered to an information terminal associated with the household based on information regarding at least one of a living situation and a living activity of the household obtained by the life estimation;
a delivery unit configured to transmit the information content selected by the selection unit to the information terminal;
The estimation system according to claim 1 , claim 2 , claim 5 , or claim 6 , comprising: The estimation system of claim 1, claim 2, claim 5, or claim 6, further comprising a data output unit configured to output characteristic data of the household that describes information regarding at least one of the living conditions and living activities of the household estimated by the estimation unit in association with an identifier of the household, wherein the identifier is a terminal ID for advertising delivery issued to an information terminal used by the household or a cookie ID issued to a browser. an acquisition unit configured to acquire information indicating an amount of power consumption related to power consumed by a household within a residence as power information;
an estimation unit configured to perform a lifestyle estimation of the household, including at least one of estimating a lifestyle situation of the household correlated with the power consumption and estimating a lifestyle activity of the household, based on the power information acquired by the acquisition unit;
a data output unit configured to output characteristic data of the household that describes information on at least one of the living situation and the living activity of the household estimated by the estimation unit in association with an identifier of the household;
wherein the identifier is a terminal ID for advertisement delivery issued to an information terminal used by the household or a cookie ID issued to a browser,
The power information includes information indicating the power consumption of each of a plurality of devices used by the household in the residence,
the estimation unit calculates, for each of the plurality of devices, one or more of a usage count of the corresponding device, a usage time of the corresponding device, and a usage rate of the corresponding device with respect to the plurality of devices, based on time series data of the power consumption of the corresponding device;
The estimation unit is an estimation system that performs a lifestyle estimation of the household based further on the usage amount of each of the plurality of devices . an acquisition unit configured to acquire information indicating an amount of power consumption related to power consumed by a household within a residence as power information;
an estimation unit configured to perform a lifestyle estimation of the household, the lifestyle estimation including at least estimating a lifestyle situation of the household that is correlated with the amount of power consumption, based on the power information acquired by the acquisition unit;
a data output unit configured to output characteristic data of the household that describes information about the living conditions of the household estimated by the estimation unit in association with an identifier of the household;
wherein the identifier is a terminal ID for advertisement delivery issued to an information terminal used by the household or a cookie ID issued to a browser,
The estimation system includes estimating life events of the household as a living condition of the household that is correlated with the electricity consumption . The estimation system according to any one of claims 19 to 21, wherein the data output unit outputs the characteristic data for the household to a system that manages a customer database that stores characteristic data for each customer in association with the identifier of the corresponding customer for a plurality of customers . An estimation system as described in claim 1, claim 2, claim 5, or claim 6, comprising an update unit configured to update a database containing characteristic data for each household related to a plurality of households, the update unit updating the database so that the database stores characteristic data describing information regarding at least one of the living conditions and living activities of the household estimated by the estimation unit in association with an identifier of the household as characteristic data of the household that is the subject of the lifestyle estimation, the identifier being a terminal ID for advertising delivery issued to an information terminal used by the household or a cookie ID issued to a browser. an acquisition unit configured to acquire information indicating an amount of power consumption related to power consumed by a household within a residence as power information;
an estimation unit configured to perform a lifestyle estimation of the household, including at least one of estimating a lifestyle situation of the household correlated with the power consumption and estimating a lifestyle activity of the household, based on the power information acquired by the acquisition unit;
an update unit configured to update a database including characteristic data for each of a plurality of households, the update unit updating the database so that the database stores characteristic data describing information on at least one of the living situation and living activities of the household estimated by the estimation unit in association with an identifier of the household as the characteristic data of the household that is the subject of the lifestyle estimation;
wherein the identifier is a terminal ID for advertisement delivery issued to an information terminal used by the household or a cookie ID issued to a browser,
The power information includes information indicating the power consumption of each of a plurality of devices used by the household in the residence,
the estimation unit calculates, for each of the plurality of devices, one or more of a usage count of the corresponding device, a usage time of the corresponding device, and a usage rate of the corresponding device with respect to the plurality of devices, based on time series data of the power consumption of the corresponding device;
The estimation unit is an estimation system that performs a lifestyle estimation of the household based further on the usage amount of each of the plurality of devices . an acquisition unit configured to acquire information indicating an amount of power consumption related to power consumed by a household within a residence as power information;
an estimation unit configured to perform a lifestyle estimation of the household, the lifestyle estimation including at least estimating a lifestyle situation of the household that is correlated with the amount of power consumption, based on the power information acquired by the acquisition unit;
an update unit configured to update a database including characteristic data for each of a plurality of households, the update unit updating the database so that the database stores characteristic data describing information about the living conditions of the households estimated by the estimation unit in association with an identifier of the household as the characteristic data of the households that are the subject of the lifestyle estimation;
wherein the identifier is a terminal ID for advertisement delivery issued to an information terminal used by the household or a cookie ID issued to a browser,
The estimation system includes estimating life events of the household as a living condition of the household that is correlated with the electricity consumption . A computer program for causing a computer to realize functions as the acquisition unit and the estimation unit in the estimation system according to any one of claims 1 to 17 . A computer program for causing a computer to realize functions of the acquisition unit, the estimation unit, the selection unit, and the delivery unit in the estimation system according to claim 18 . A computer program for causing a computer to realize the functions of the acquisition unit, the estimation unit, and the data output unit in the estimation system according to any one of claims 19 to 22 . A computer program for causing a computer to realize functions of the acquisition unit, the estimation unit, and the update unit in the estimation system according to any one of claims 23 to 25 . 1. A computer-implemented estimation method comprising:
obtaining information relating to a plurality of devices used by a household within the dwelling, the information being indicative of the power consumption of each of the devices, the information being determined by monitoring the power supplied through an electrical wiring in the dwelling of the household;
performing a lifestyle estimation of the household based on the power consumption of each of the devices indicated by the acquired information;
The lifestyle estimation includes at least one of estimating a lifestyle situation of the household correlated with the power consumption and estimating a lifestyle activity of the household;
The estimation method includes calculating, for each of the plurality of devices, one or more of the number of times the corresponding device is used, the usage time of the corresponding device, and the utilization rate of the corresponding device among the plurality of devices as a usage amount based on time series data of the power consumption of the corresponding device, and performing a lifestyle estimation of the household based further on the usage amount of each of the plurality of devices . 1. A computer-implemented estimation method comprising:
obtaining information relating to a plurality of devices used by a household within the dwelling, the information being indicative of the power consumption of each of the devices, the information being determined by monitoring the power supplied through an electrical wiring in the dwelling of the household;
performing a lifestyle estimation of the household based on the power consumption of each of the devices indicated by the acquired information;
wherein the lifestyle estimation includes estimating life events of the household as a lifestyle condition of the household correlated with the amount of electricity consumption. 1. A computer-implemented estimation method comprising:
Obtaining information indicating an amount of electricity consumed by a household within a residence as electricity information ;
performing a lifestyle estimation of the household, the lifestyle estimation including at least one of estimating a lifestyle situation of the household correlated with the amount of power consumption and estimating a lifestyle activity of the household based on the acquired power information ;
and outputting characteristic data of the household that describes information on at least one of the estimated living situation and living behavior of the household in association with an identifier of the household, the identifier being a terminal ID for advertisement delivery issued to an information terminal used by the household or a cookie ID issued to a browser,
The power information includes information indicating the power consumption of each of a plurality of devices used by the household in the residence,
The estimation method includes calculating, for each of the plurality of devices, one or more of the number of times the corresponding device is used, the usage time of the corresponding device, and the utilization rate of the corresponding device among the plurality of devices as a usage amount based on time series data of the power consumption of the corresponding device, and performing a lifestyle estimation of the household based further on the usage amount of each of the plurality of devices . 1. A computer-implemented estimation method comprising:
obtaining information indicative of electricity consumption related to electricity consumed by a household within a residence;
performing a lifestyle estimation of the household, the lifestyle estimation including at least estimating a lifestyle situation of the household that is correlated with the amount of power consumption based on the amount of power consumption indicated by the acquired information;
and outputting characteristic data of the household that describes information about the estimated living situation of the household in association with an identifier of the household, the identifier being a terminal ID for advertisement delivery issued to an information terminal used by the household or a cookie ID issued to a browser,
The lifestyle estimation method includes estimating life events of the household as a lifestyle condition of the household that is correlated with the electricity consumption . 1. A computer-implemented estimation method comprising:
Obtaining information indicating an amount of electricity consumed by a household within a residence as electricity information ;
performing a lifestyle estimation of the household, the lifestyle estimation including at least one of estimating a lifestyle situation of the household correlated with the amount of power consumption and estimating a lifestyle activity of the household based on the acquired power information ;
updating a database that includes characteristic data for each of a plurality of households, so that the database stores characteristic data describing information on at least one of the estimated living situation and living behavior of the household in association with an identifier of the household as the characteristic data of the household that is the subject of the lifestyle estimation, the identifier being a terminal ID for advertisement delivery issued to an information terminal used by the household or a cookie ID issued to a browser;
The power information includes information indicating the power consumption of each of a plurality of devices used by the household in the residence,
The estimation method includes calculating, for each of the plurality of devices, one or more of the number of times the corresponding device is used, the usage time of the corresponding device, and the utilization rate of the corresponding device among the plurality of devices as a usage amount based on time series data of the power consumption of the corresponding device, and performing a lifestyle estimation of the household based further on the usage amount of each of the plurality of devices . 1. A computer-implemented estimation method comprising:
obtaining information indicative of electricity consumption related to electricity consumed by a household within a residence;
performing a lifestyle estimation of the household, the lifestyle estimation including at least estimating a lifestyle situation of the household that is correlated with the amount of power consumption based on the amount of power consumption indicated by the acquired information;
updating a database that includes characteristic data for each of a plurality of households, so that the database stores characteristic data describing information on the estimated living conditions of the household in association with an identifier of the household as the characteristic data of the household that is the subject of the lifestyle estimation, the identifier being a terminal ID for advertisement delivery issued to an information terminal used by the household or a cookie ID issued to a browser;
The lifestyle estimation method includes estimating life events of the household as a lifestyle condition of the household that is correlated with the electricity consumption .

Images