JP7332865B2 - Information processing method, information processing device, and program - Google Patents

Description

The present disclosure relates to an information processing method, an information processing device, and a program.

2. Description of the Related Art Conventionally, there is known a technique for recommending energy-saving operation settings of a device to a user (see Patent Document 1, for example).

JP 2009-259125 A

However, the prior art may not be able to determine appropriate operating settings for equipment. An object of the present disclosure is to provide technology that can determine appropriate settings for a device.

In an information processing method according to a first aspect of the present disclosure, an information processing apparatus includes data sets acquired from a plurality of devices, information indicating a situation when each device is operated, and a criterion for determining whether or not the operation setting according to the situation when the first device is operated is the energy-saving operation setting, based on a data set including a combination with information on power consumption when the first device is operated; A process for inferring power consumption is executed. This allows determination of the appropriate settings for the device.

Further, a second aspect of the present disclosure is the information processing apparatus according to the first aspect, wherein the information indicating the situation when each device is operated includes outside temperature and installation of each device. include at least one of the number of people in the room

Further, a third aspect of the present disclosure is the information processing device according to the first or second aspect, wherein the information indicating the situation when each device is operated includes At least one of the date and time of the event and the illuminance in the room where each device is installed is included.

Further, a fourth aspect of the present disclosure is the information processing apparatus according to any one of the first to third aspects, wherein the information indicating the situation when each device is operated includes outside air humidity, solar radiation At least one of quantity, type of weather, indoor temperature, indoor humidity, heat load, indoor floor area, and type of indoor use is included.

Further, a fifth aspect of the present disclosure is the information processing device according to any one of the first to fourth aspects, wherein in the process of inferring the reference power consumption, Machine learning using linear regression or nonlinear regression is performed based on the obtained data set, and using the result of the machine learning, the situation when the first device is operated is input, and power consumption as a reference to infer

Further, a sixth aspect of the present disclosure is the information processing apparatus according to any one of the first to fifth aspects, wherein in the process of inferring the reference power consumption, when each of the devices is operated A representative value of the power consumption when each device is operated is inferred as a reference power consumption for each situation.

Further, a seventh aspect of the present disclosure is the information processing apparatus according to any one of the first to sixth aspects, wherein information indicating a situation when each device is operated and Based on a data set that includes a combination of the inferred standard power consumption and the operation settings when the equipment is operated, the process of inferring the operation settings according to the situation when the equipment is operated is executed. do.

Further, an eighth aspect of the present disclosure is the information processing apparatus according to the seventh aspect, wherein in the process of inferring the operation setting, the power consumption as a reference inferred for the first device is set to the first Infer the operating settings, modified according to the current power consumption of the appliance.

Further, a ninth aspect of the present disclosure is the information processing apparatus according to the eighth aspect, wherein when the current power consumption of the device is greater than the reference power consumption inferred for the situation of the device, Execute processing for notifying the user of information that recommends the inferred operation settings.

Further, a tenth aspect of the present disclosure is the information processing apparatus according to any one of the first to ninth aspects, wherein a data set for each of a plurality of devices, wherein when each device is operated Machine learning based on a data set containing a combination of time transition of information indicating the status of each device and time transition information of power consumption when each device is operated, and the result of machine learning and the operation of the device Based on the time transition of the situation at the time of operation, the time transition of the power consumption of the device is inferred. Execute processing to notify information that recommends a predetermined setting.

Further, according to an eleventh aspect of the present disclosure, the information processing apparatus includes data sets respectively acquired from a plurality of devices, including information indicating a situation when each device is operated and Consumption that serves as a criterion for determining whether the operation setting according to the situation when the first device is operated is the energy-saving operation setting based on the data set including the combination with the information on the power consumption when the first device is operated It has an inference unit that infers power.

Further, in a twelfth aspect of the present disclosure, the program is a data set obtained by a computer from a plurality of devices, and includes information indicating a situation when each device is operated and Based on the data set including the combination with the power consumption information when the first device is operated, it is a criterion for determining whether or not the operation setting corresponding to the situation when the first device is operated is the energy saving operation setting. Execute processing for inferring power consumption.

It is a figure which shows an example of the system configuration|structure of the information processing system which concerns on embodiment. It is a figure which shows an example of the hardware constitutions of the information processing apparatus which concerns on embodiment. It is a figure which shows an example of the functional block diagram of the information processing apparatus which concerns on embodiment. 6 is a flowchart showing an example of processing during learning of the information processing apparatus according to the embodiment; It is a figure which shows an example of the log|history of the driving condition memorize|stored in driving condition DB which concerns on embodiment. 7 is a flowchart showing an example of processing during inference of the information processing apparatus according to the embodiment; It is a figure explaining an example of the notification screen of the recommended operation setting which concerns on embodiment.

Hereinafter, each embodiment will be described with reference to the drawings. In the present specification and drawings, constituent elements having substantially the same functional configuration are denoted by the same reference numerals, thereby omitting redundant description.

<System configuration>
First, the system configuration of the information processing system 1 will be described. FIG. 1 is a diagram showing an example of a system configuration of an information processing system 1 according to an embodiment. As shown in FIG. 1, the information processing system 1 includes an information processing device 10, a device 20A (an example of a “first device”), a device 20B, and a device 20C (hereinafter, when there is no need to distinguish between them, terminal 30A, terminal 30B, and terminal 30C (hereinafter simply referred to as "terminal 30" when there is no need to distinguish between them). The number of information processing apparatuses 10, devices 20, and terminals 30 is not limited to the example in FIG.

The information processing device 10 and the equipment 20, and the information processing device 10 and the terminal 30 are, for example, the Internet, a wireless LAN (Local Area Network), a mobile phone network such as LTE (Long Term Evolution) and 5G, a LAN, and a signal. They may be communicatively connected via a network NW such as a line. The device 20 may be installed, for example, in residences, offices, public facilities, and the like. The information processing device 10 may be, for example, a server on the cloud. Further, the information processing device 10 may be accommodated in, for example, the device 20 (for example, an indoor unit housing of an air conditioner).

The information processing apparatus 10 is a data set acquired from each of the plurality of devices 20, and includes information indicating the state when the device 20 is operated and information on power consumption when the device 20 is operated. Power consumption (reference power consumption) that serves as a reference for determining whether or not the operation setting of the device 20A or the like is the energy-saving operation setting according to the situation when the device 20A or the like is operated, based on the data set including the combination. infer.

In addition, the information processing apparatus 10 includes data sets acquired from each of the plurality of devices 20, and includes information indicating the situation when the device 20 is operated, the inferred reference power consumption, and the An energy-saving operation setting for the device 20A or the like is inferred based on the data set including the combination with the actual operation setting. In addition, the information processing device 10 notifies the user of the device 20A or the like of the inferred operation settings.

The device 20 is, for example, various devices such as an air conditioner (air conditioner), a refrigerator, a water heater, and lighting, and has an IoT (Internet of Things) device that transmits various types of measured information to the information processing device 10. You may

The terminal 30 is, for example, a terminal such as a smart phone, a mobile phone, a tablet, or a personal computer used by the user of the device 20 .

It should be noted that the user of each device 20 has previously registered in the information processing apparatus 10 the IDs and communication addresses of the devices 20 and terminals 30 that he/she uses. information such as operation settings can be notified to each terminal 30 of the user of each device 20 .

<Hardware Configuration of Information Processing Device 10, Device 20, and Terminal 30>
Next, hardware configurations of the information processing device 10, the device 20, and the terminal 30 of the information processing system 1 according to the embodiment will be described. Since the information processing device 10, the device 20, and the terminal 30 have the same hardware configuration, only the hardware configuration of the information processing device 10 will be described here.

FIG. 2 is a diagram showing an example of the hardware configuration of the information processing device 10 according to the embodiment. As shown in FIG. 2 , the information processing apparatus 10 has a CPU (Central Processing Unit) 101 , a ROM (Read Only Memory) 102 and a RAM (Random Access Memory) 103 . The CPU 101, ROM 102, and RAM 103 form a so-called computer. The information processing apparatus 10 also has an auxiliary storage device 104 , a display device 105 , an operation device 106 , an I/F (Interface) device 107 and a drive device 108 . Each piece of hardware of the information processing apparatus 10 is interconnected via a bus 109 .

The CPU 101 is an arithmetic device that executes various programs (for example, machine learning programs, etc.) installed in the auxiliary storage device 104 . ROM 102 is a non-volatile memory. The ROM 102 functions as a main memory device and stores various programs and data necessary for the CPU 101 to execute various programs installed in the auxiliary memory device 104 . Specifically, the ROM 102 stores boot programs such as BIOS (Basic Input/Output System) and EFI (Extensible Firmware Interface).

A RAM 103 is a volatile memory such as a DRAM (Dynamic Random Access Memory) or an SRAM (Static Random Access Memory). The RAM 103 functions as a main storage device and provides a work area that is expanded when various programs installed in the auxiliary storage device 104 are executed by the CPU 101 .

The auxiliary storage device 104 stores various programs and information used when various programs are executed.

The display device 105 is a display device that displays various information. The operation device 106 is an operation device for receiving various operations. The I/F device 107 is a communication device that communicates with external equipment.

A drive device 108 is a device for setting a recording medium 110 . The recording medium 110 here includes media for optically, electrically or magnetically recording information such as CD-ROMs, flexible disks, and magneto-optical disks. The recording medium 110 may also include a semiconductor memory or the like that electrically records information, such as a ROM or a flash memory.

Various programs to be installed in the auxiliary storage device 104 are installed by, for example, setting the distributed recording medium 110 in the drive device 108 and reading the various programs recorded in the recording medium 110 by the drive device 108. be done. Alternatively, various programs installed in the auxiliary storage device 104 may be installed by being downloaded from a network (not shown).

<Functional configuration>
Next, with reference to FIG. 3, the functional configuration of the information processing system 1 according to the embodiment will be described. FIG. 3 is a diagram showing an example of functional blocks of the information processing device 10 according to the embodiment.

<<Information processing device 10>>
The information processing device 10 has a driving situation DB 111 , an acquisition unit 11 , a training data generation unit 12 , a learning unit 13 , a training data generation unit 14 , a learning unit 15 , an inference unit 16 , an inference unit 17 , and a notification unit 18 . Each of these units may be realized, for example, by cooperation of one or more programs installed in the information processing apparatus 10, the CPU 101, the ROM 102, the RAM 103, and the like of the information processing apparatus 10. FIG.

The acquisition unit 11 acquires information about the operating status of each of the plurality of devices 20 and records the information in the operating status DB 111 .

Based on the information acquired by the acquisition unit 11, the training data generation unit 12 generates training data for learning (machine learning) the reference power consumption corresponding to the situation when the device 20 is operated. Based on the training data generated by the training data generation unit 12, the learning unit 13 learns the reference power consumption corresponding to the situation when the device 20 is operated.

Based on the information acquired by the acquisition unit 11, the training data generation unit 14 generates training data for learning operation settings according to the situation when the device 20 is operated and the reference power consumption. Based on the training data generated by the learning unit 15 and the training data generation unit 14, the operation setting corresponding to the situation when the device 20 is operated and the reference power consumption is learned.

The inference unit 16 infers the reference power consumption for the current state of the device 20A based on the information about the current operating state of the device 20A acquired by the acquisition unit 11 and the learning result of the learning unit 13 .

Based on the information indicating the current status of the device 20A, the learning result of the operation setting by the learning unit 15, and the reference power consumption for the current status of the device 20A inferred by the inference unit 16, the inference unit 17 Infer the operation setting of the equipment 20A that saves energy in the environment.

The notification unit 18 notifies the user of the device 20A of the operation setting of the device 20A inferred by the inference unit 17 .

<Processing>
A case where the device 20 is an air conditioner (air conditioner) will be described below as an example, but the technology disclosed herein can be applied to various devices 20 such as refrigerators, water heaters, and lighting, for example.

≪Processing during learning≫
An example of processing during learning of the information processing system 1 according to the embodiment will be described with reference to FIGS. 4 and 5 . FIG. 4 is a flowchart showing an example of processing during learning of the information processing apparatus 10 according to the embodiment. FIG. 5 is a diagram showing an example of a history of driving situations stored in the driving situation DB 111 according to the embodiment.

(Acquisition of training data)
In step S<b>101 , the acquisition unit 11 of the information processing device 10 acquires information regarding the operating status of each of the plurality of devices 20 . Here, the acquisition unit 11 of the information processing device 10 may acquire information about the current operating status of each device 20 from each device 20 at intervals of a predetermined time (for example, one hour), for example. Alternatively, the history of information on the operating status of each device 20 may be acquired from each device 20 at predetermined time intervals (for example, once a day). The acquisition unit 11 of the information processing apparatus 10 may acquire, for example, a history of information related to the operating status of each device 20 accumulated in an external server.

Here, the information about the operating status includes, for example, the device ID that is the ID of the device 20, the date and time when the device 20 was operated, information indicating the surrounding environment when the device 20 was operated (for example, the date and time), Information on power consumption when the device is operated and operation settings when the device is operated may be included.

Subsequently, the acquisition unit 11 of the information processing device 10 records the acquired information about the driving situation in the driving situation DB 111 (step S102).

In the example of FIG. 5, in the operating status DB 111, a set (record) of information indicating the surrounding environment when the device 20 is operated, power consumption, and operation settings is associated with the device ID and the date and time. remembered. Also, the device type is stored in association with the device ID.

The information indicating the surrounding environment when the device 20 is operated includes, for example, the outside temperature, the number of people in the room, the illuminance in the room, the humidity in the outside air, the amount of solar radiation, the type of weather, the temperature in the room, the humidity in the room, the heat load, and the temperature in the room. and the type of indoor use, etc. may be included.

The outdoor temperature is the temperature outside the building in which the device 20 is installed. The outside air temperature may be measured, for example, by a temperature sensor provided in the air conditioner outdoor unit of the equipment 20 .

The number of people in the room is the number of people in the room where the device 20 is installed. The number of people in the room may be measured by the device 20 based on information detected by, for example, a radiation temperature sensor provided in the air conditioner indoor unit of the device 20 or by a camera or the like.

The illuminance in the room is the illuminance in the room where the device 20 is installed. The illuminance in the room may be measured by, for example, an illuminance sensor provided in the air conditioner indoor unit of the device 20 .

The outside air humidity is the humidity outside the building where the device 20 is installed. The outside air humidity may be measured by, for example, a humidity sensor provided in the air conditioner outdoor unit of the device 20 .

The amount of insolation is the amount of insolation outside the building in which the device 20 is installed. The amount of solar radiation may be measured by, for example, a solar radiation sensor (pyranometer) provided in the outdoor unit of the air conditioner of the device 20 .

The type of weather is the type of weather in the area where the device 20 is installed. Weather types may include, for example, types such as sunny, cloudy, rainy, and snowy. The type of weather is based on, for example, information on the region where the device 20 is installed, which is preset in the device 20, and information on the type of weather in each region at each date and time obtained from a server such as the Meteorological Agency. may be determined.

The indoor temperature and indoor humidity are the temperature and humidity in the room where the device 20 is installed, respectively. The indoor temperature and indoor humidity may be measured by, for example, a temperature sensor and a humidity sensor provided in the air conditioner indoor unit of the device 20, respectively.

The heat load is, for example, the amount of heat flowing in and out of the room (room) in which the device 20 is installed, and the amount of heat generated in the room. For example, if the room in which the device 20 is installed has a lot of air exchange due to the inflow and outflow of outside air or a ventilation fan, if the ceiling is high, or if the building has low heat insulation such as a wooden building, the heat load becomes larger. The heat load may be a value estimated by the device 20 or the like based on the history of information regarding the operating status of the device 20 . Alternatively, the value of the air conditioning capacity (horsepower) of the device 20 may be used as the heat load.

The indoor floor area is the indoor floor area where the device 20 is installed. The floor area of the room may be stored in the device 20 in advance by, for example, setting operation by each user.

The indoor usage type is the indoor usage type (industry) in which the device 20 is installed. The types of indoor use may include, for example, types such as home use, office use (general office use), beauty parlor use, restaurant use, and server room use. The indoor use type may be stored in advance in the device 20 by, for example, setting operation by each user.

Power consumption is power consumption when the device 20 is operated. The power consumption is the total value (cumulative value) of power consumed per predetermined time period on each day. The power consumption may be calculated by the device 20 based on the power actually consumed per predetermined period of time.

The operation setting is the operation setting when the equipment 20 is operated. The operation settings may include, for example, settings related to the operation of the device 20 that are set by the user by operating the remote control of the device 20 or the like. The operation settings may include, for example, an operation mode, a set temperature, and a set air volume. The operation modes may include, for example, automatic operation, cooling operation, heating operation, dehumidifying operation, and air blowing operation.

The device type is the type of the device 20, and may include, for example, types such as air conditioners, refrigerators, water heaters, and lighting. The device type item may be set in advance for each device 20 .

(Learning of standard power consumption)
Subsequently, the training data generation unit 12 of the information processing device 10 learns the reference power consumption corresponding to the surrounding environment when the device 20 is operated based on the data set recorded in the operating situation DB 111. training data is generated (step S103). Note that the reference power consumption is, for example, power consumption that serves as a reference for determining whether or not the operation setting of the device 20 according to the surrounding environment when the device 20 is operated is the energy-saving operation setting.

Here, the training data generation unit 12 of the information processing device 10 selects at least one item (first item) and power consumption may be used as training data for learning the reference power consumption. In this case, the training data generation unit 12 of the information processing device 10 receives, for example, at least one item of information included in information indicating the surrounding environment when the device 20 is operated, and uses power consumption as correct data. , a combination (set) of the input and the correct data may be used as training data for learning the reference power consumption.

Next, based on the generated training data, the learning unit 13 of the information processing device 10 determines whether the operation setting of the device 20 according to the surrounding environment when the device 20 is operated is the energy-saving operation setting. Machine learning is performed on the reference power consumption for determining whether or not (step S104).

Here, the learning unit 13 of the information processing device 10 may machine-learn a regression problem for inferring power consumption based on an input, for example, by supervised learning. Note that the regression problem is, for example, a problem of predicting continuous values. As a result, the average power consumption in each ambient environment and each operation setting of each device 20 used by each user is used as a criterion for determining whether or not the operation setting saves energy in each ambient environment of the device 20A. power consumption. Therefore, for example, the request for unreasonable energy saving that impairs the user's comfort beyond a certain level is reduced. In addition, for example, if public awareness of energy conservation is increasing, it is possible to request energy conservation in line with public perception.

In this case, the learning unit 13 of the information processing device 10 may perform machine learning using, for example, linear regression. In this case, the learning unit 13 of the information processing apparatus 10 uses, for example, power consumption as an objective variable (response variable, dependent variable), and at least one item included in the information indicating the surrounding environment when the device 20 is operated. may be used as explanatory variables (input variables, independent variables) and machine learning may be performed using the method of least squares or the like.

Also, the learning unit 13 of the information processing device 10 may perform machine learning using, for example, nonlinear regression. In this case, the learning unit 13 of the information processing device 10 is, for example, a recurrent neural network (RNN), a general regression neural network (General Regression Neural Network), a random forest (Random Forest), or Machine learning using a support vector machine (SVM) or the like may be performed.

Further, the learning unit 13 of the information processing apparatus 10 calculates, for example, a representative value of the power consumption when the device 20 is operated for each surrounding environment when the device 20 is operated, and each calculated representative The value may be machine-learned to be the reference power consumption for each surrounding environment when the device 20 is operated. Note that the learning unit 13 of the information processing device 10 may calculate, for example, an average value, a median value, a most frequent value, or the like as the representative value. Further, the learning unit 13 of the information processing device 10 may calculate an average value such as an average value, median value, and most frequent value as the representative value.

(learning driving settings)
Subsequently, the training data generation unit 14 of the information processing device 10 performs operation according to the surrounding environment and the reference power consumption when the device 20 is operated, based on the data set recorded in the operation situation DB 111. Training data for learning the setting is generated (step S105).

Here, the training data generation unit 14 of the information processing device 10 selects at least one item (second items), power consumption, and operation settings of the device 20 may be used as training data for learning the operation settings. Note that the first item and the second item described above may be the same or different.

In this case, the training data generation unit 14 of the information processing device 10 receives, for example, at least one item of information included in the information indicating the surrounding environment when the device 20 is operated and the power consumption, and Twenty operating settings may be used as correct data, and a combination (set) of the input and the correct data may be used as training data for learning the operating settings.

Subsequently, based on the generated training data, the learning unit 15 of the information processing device 10 machine-learns the operation setting according to the ambient environment and the reference power consumption when the device 20 is operated (step S106). Here, the learning unit 15 of the information processing device 10 may perform machine learning of a classification problem for inferring driving settings based on inputs, for example, by supervised learning. Note that the classification problem is, for example, a problem of predicting discrete values. In this case, the learning unit 15 of the information processing device 10 uses, for example, logistic regression, random forest, boosting, support vector machine (SVM), or neural network. Machine learning using, etc. may be performed. This makes it possible to infer optimal operation settings for the device 20 according to the environment around the device 20 and the reference power consumption.

≪Processing during inference≫
Next, an example of inference processing of the information processing apparatus 10 according to the embodiment will be described with reference to FIGS. 6 and 7. FIG. FIG. 6 is a flowchart illustrating an example of processing during inference by the information processing apparatus 10 according to the embodiment. FIG. 7 is a diagram illustrating an example of a recommended operation setting notification screen according to the embodiment. An example of performing inference with respect to the device 20A will be described below.

In step S201, the acquisition unit 11 of the information processing device 10 acquires information about the current operating status of the device 20A. Here, the acquisition unit 11 of the information processing device 10 may acquire information about the current operating status of the device 20A from the device 20A at predetermined time intervals (for example, one hour), for example.

Subsequently, the inference unit 16 of the information processing apparatus 10 determines the current operating status of the device 20A based on the obtained information about the current operating status of the device 20A and the learning result of the reference power consumption obtained by the processing in step S104 of FIG. A reference power consumption for the surrounding environment is inferred (step S202). Here, the inference unit 16 of the information processing apparatus 10 receives the information of the first item used when learning the reference power consumption among the items included in the information indicating the current surrounding environment of the device 20A. , the learning result of the reference power consumption is used to infer the current reference power consumption of the device 20A.

Further, the inference unit 16 of the information processing device 10 may infer the current reference power consumption of the device 20A, for example, based on each result learned by each method described above. In this case, the inference unit 16 of the information processing apparatus 10 infers the current reference power consumption of the device 20A based on each result learned by each method described in the process of step S104 in FIG. 4, for example. Then, the inference unit 16 of the information processing device 10 may infer the average value of the inferred values or the like as the current reference power consumption of the device 20A.

Subsequently, the inference unit 17 of the information processing device 10 determines whether or not to recommend the energy-saving operation settings to the user A of the device 20A (step S203). Here, the inference unit 17 of the information processing device 10 sets the energy-saving operation settings based on, for example, the current power consumption of the device 20A and the reference power consumption inferred for the current surrounding environment of the device 20A. may be determined whether to recommend In this case, for example, when the current power consumption of the device 20A is greater than the inferred reference power consumption by a predetermined threshold or more, the inference unit 17 of the information processing apparatus 10 determines that an energy-saving operation setting is recommended. If it is not greater than a predetermined threshold, it may be determined that it is not recommended.

If it is determined not to recommend (NO in step S203), the inference unit 17 of the information processing device 10 ends the process and does not execute the following process.

If it is determined to be recommended (YES in step S203), the inference unit 17 of the information processing device 10 receives information indicating the current surrounding environment of the device 20A, the driving setting learning result obtained by the processing of step S106 in FIG. Based on the reference power consumption for the current surrounding environment of the device 20A, which was inferred in the process of step S202, an operation setting that saves energy in the environment is inferred (step S204). Here, the inference unit 17 of the information processing device 10 selects the information of the second item used when learning the driving setting, among the items included in the information indicating the current surrounding environment of the device 20A, and the reference Power consumption is used as an input, and the learning result of the operation setting is used to infer the operation setting. As a result, it is possible to infer an operation setting in which the power consumption value in the current surrounding environment of the device 20A approximately matches the reference power consumption value in the environment.

In the process of step S204, the inference unit 17 of the information processing apparatus 10 corrects the reference power consumption value for the current surrounding environment of the device 20A, which was inferred in the process of step S202, and sets the corrected value as the reference power consumption. may be used. In this case, the inference unit 17 of the information processing apparatus 10 may infer the operation settings by inputting a value obtained by lowering the inferred reference power consumption value by a predetermined amount (for example, 5%). As a result, it is possible to infer an operation setting in which the power consumption value in the current surrounding environment of the device 20A is lower than the reference power consumption value in the environment by a predetermined amount.

Further, the inference unit 17 of the information processing apparatus 10 corrects the value of the reference power consumption based on, for example, the current value of the power consumption of the device 20A and the value of the inferred reference power consumption, and converts the corrected value to It may be used as a reference power consumption. In this case, the inference unit 17 of the information processing apparatus 10, for example, increases the inferred reference power consumption value as the ratio between the current power consumption value of the device 20A and the inferred reference power consumption value increases. An operation setting may be inferred from a value increased by a predetermined amount as an input. In this case, for example, when the current power consumption value of the device 20A is 1.2 times the inferred reference power consumption value, the inference unit 17 of the information processing apparatus 10 sets the reference power consumption value to It may be used after being corrected to a value 1.1 times the average value of the values. As a result, for example, when the user A of the device 20A prefers to perform cooling with a relatively low set temperature, or prefers to operate with a relatively low set air volume, relatively energy saving can be achieved. Even if the user A prefers an operation setting that does not satisfy the above conditions, it is possible to infer an energy-saving operation setting that relatively reduces the decrease in comfort for the user A.

Subsequently, the notification unit 18 of the information processing device 10 notifies the user A of the device 20A of information recommending the inferred operation setting (step S205). Here, the notification unit 18 of the information processing device 10 transmits the inferred driving setting information to the terminal 30A, which is a pre-registered notification destination for the user A, for example.

In the example of FIG. 7 , the notification unit 18 of the information processing apparatus 10 displays the reference power consumption 702 inferred for the current surrounding environment of the device 20A, the current surrounding environment of the device 20A, and the current surrounding environment of the device 20A on the notification content display screen 701. and the current power consumption 704 of the device 20A are displayed on the terminal 30A. Further, the reference power consumption 705 corrected in the process of step S204, the inferred operation setting information 706, and the "AI collective setting" button 707 are displayed on the terminal 30A.

When the "AI collective setting" button 707 is pressed, the terminal 30A transmits a control signal (remote control command) via wireless communication such as a wireless LAN, and changes various settings included in the inferred operation settings to the device 20A. may be reflected in

Note that the notification unit 18 of the information processing device 10 changes the operation setting of the device 20A to the inferred operation setting, for example, when automatic operation by AI (Artificial Intelligence) is permitted by the user A's setting operation. You may make it control. In this case, the notification unit 18 of the information processing device 10 may transmit the control signal to the device 20A via the terminal 30A, or may transmit the control signal to the device 20A without the terminal 30A.

<Modification 1>
The information processing apparatus 10 predicts the transition of power consumption in the future based on the time-series data such as the outside air temperature acquired from the device 20A. It may be recommended. As a result, for example, in the midsummer, when power shortage is expected in the early afternoon, it is possible to recommend energy saving in the morning.

In this case, the training data generation unit 12 of the information processing device 10 generates a data set for each of the plurality of devices 20, which is a time transition (at each point in time) of information indicating the surrounding environment when each device 20 is operated. , time-series data) and information on the time transition of power consumption when each device 20 is operated may be used as training data for learning the time transition of the reference power consumption. In this case, the training data generation unit 12 of the information processing device 10 receives, for example, the temporal transition of information of at least one item included in the information indicating the surrounding environment when the device 20 is operated, and calculates the power consumption. A combination of the input and the correct data may be used as the training data for learning the reference power consumption, with the time transition as the correct data.

Based on the training data, the learning unit 13 of the information processing device 10 machine-learns the temporal transition of the reference power consumption. In this case, the learning unit 13 of the information processing device 10 may perform machine learning using, for example, a recurrent neural network (RNN).

Then, in the process of step S203 in FIG. 7, the inference unit 17 of the information processing apparatus 10, based on the result of the machine learning and the time-series data of the surrounding environment of the device 20A at each point in time up to the present, A value calculated by inferring future (or later) changes in the power consumption of the device 20A, and calculating the total value of the future power consumption of the device 20A within a predetermined time period (for example, within three hours) based on the inferred changes. is equal to or greater than the threshold, it is determined that the user A of the device 20A is recommended to use the energy-saving operation setting.

Then, in the process of step S204 in FIG. 7, the inference unit 17 of the information processing apparatus 10 converts the value of the reference power consumption for the current surrounding environment of the device 20A, inferred in the process of step S202, into the calculated future predetermined power consumption value. It is corrected based on the total value of power consumption within the time period, and the corrected value is used as the reference power consumption. In this case, the inference unit 17 of the information processing apparatus 10 may correct the value of the reference power consumption so that the amount of decrease in the inferred reference power consumption value increases as the total value increases.

<Modification 2>
Each functional unit of the information processing device 10 may be realized by cloud computing configured by one or more computers, for example. At least part of the processing of each functional unit of the information processing apparatus 10 described above may be executed by the device 20 . In this case, for example, the device 20 is provided with the inference unit 16 and the inference unit 17, and each trained model generated by the learning unit 13 and the learning unit 15 is distributed to the inference unit 16 and the inference unit 17 of each device 20. may Further, the information processing device 10 and the device 20 may be configured as an integrated device.

Although the embodiments have been described above, it will be appreciated that various changes in form and detail may be made without departing from the spirit and scope of the claims.

1 information processing system 10 information processing device 111 driving situation DB
11 acquisition unit 12 training data generation unit 13 learning unit 14 training data generation unit 15 learning unit 16 inference unit 17 inference unit 18 notification unit

Claims (11)

The information processing device
Based on a data set obtained from each of a plurality of devices and containing a combination of information indicating the status when each device is operated and information on power consumption when each device is operated a process of inferring power consumption as a reference for determining whether or not the operation setting according to the situation when the first device is operated is an energy-saving operation setting;
a data set containing a combination of information indicating a situation when each device is operated, power consumption as a reference inferred for the first device, and operation settings when each device is operated; a process of inferring recommended operating settings according to current conditions in which the first device is operated, based on the
A method of processing information that performs The information indicating the situation when each device is operated includes at least one of the outdoor temperature and the number of people in the room where each device is installed.
The information processing method according to claim 1 . The information indicating the situation when each device was operated includes at least one of the date and time when each device was operated and the illuminance in the room where each device was installed.
The information processing method according to claim 1 or 2. The information indicating the situation when each device is operated includes outside air humidity, amount of solar radiation, type of weather, indoor temperature, indoor humidity, heat load, indoor floor area, type of indoor use, and type of device. includes at least one
The information processing method according to any one of claims 1 to 3. In the process of inferring the reference power consumption,
Machine learning using linear regression or nonlinear regression is performed based on the data sets respectively obtained from the plurality of devices, and the current situation in which the first device is operated is calculated using the results of the machine learning. as an input to infer the standard power consumption,
The information processing method according to any one of claims 1 to 4. In the process of inferring the reference power consumption,
Inferring a representative value of power consumption when each device is operated as a reference power consumption for each situation when each device is operated;
The information processing method according to any one of claims 1 to 5. In the process of inferring the operation setting, the reference power consumption inferred for the first device is corrected according to the current power consumption of the first device, and the operation setting is inferred.
The information processing method according to claim 1 . If the current power consumption of the device is greater than the reference power consumption inferred for the status of the device, executing a process of notifying the user of information recommending the inferred operation settings;
The information processing method according to claim 1 or 7 . The information processing device
A data set for each of a plurality of devices, which is a combination of time transition of information indicating the state when each device is operated and information on time transition of power consumption when each device is operated machine learning based on a dataset containing
Based on the result of machine learning and the time transition of information indicating the situation when the equipment is operated, the time transition of the power consumption of the equipment after the inference is inferred, and the inferred power consumption of the equipment is calculated after the inference. If the threshold value is exceeded within a predetermined time, a process of notifying information that recommends a predetermined setting regarding the operation of the device is executed.
The information processing method according to any one of claims 1 to 8 . Based on a data set obtained from each of a plurality of devices and containing a combination of information indicating the status when each device is operated and information on power consumption when each device is operated to infer the power consumption that serves as a criterion for determining whether or not the operation setting corresponding to the situation when the first device is operated is the energy-saving operation setting, and to determine the situation when each device is operated. The first device is operated based on a data set that includes a combination of the indicated information, the reference power consumption inferred for the first device, and the operation setting when each device is operated. An information processing device having an inference unit that infers recommended driving settings according to the current situation . to the computer,
Based on a data set obtained from each of a plurality of devices and containing a combination of information indicating the status when each device is operated and information on power consumption when each device is operated a process of inferring power consumption as a reference for determining whether or not the operation setting according to the situation when the first device is operated is an energy-saving operation setting;
a data set containing a combination of information indicating a situation when each device is operated, power consumption as a reference inferred for the first device, and operation settings when each device is operated; a process of inferring recommended operating settings according to current conditions in which the first device is operated, based on the
program to run.

Images