Information processing system

Abstract

An information processing system that can infer the attributes of a user using a washing machine is provided. The information processing system according to the embodiment has an acquisition unit and an inference unit. The acquisition unit acquires data related to the state of the washing machine. The inference unit uses a learned model generated by machine learning to infer the attributes of the user of the washing machine based on the data acquired by the acquisition unit.

Description

Technical Field

[0001] Embodiments of the present invention relate to an information processing system. Background Art

[0002] In recent years, home appliances equipped with a wireless communication function and capable of connecting to the Internet have been spreading. Such a technical field is generally called IoT (Internet of Things), and is attracting attention in various industrial fields, not limited to the field of home appliances. For example, manufacturers of home appliances have launched services that can remotely confirm the status of home appliances or remotely operate home appliances through an application on a smartphone (hereinafter referred to as a "home appliance application").

[0003] Prior Art Documents:

[0004] Patent Documents:

[0005] Patent Document 1: International Publication No. 2014 / 097589

[0006] Patent Document 2: Japanese Unexamined Patent Application Publication No. 2019-063381

[0007] Patent Document 3: Japanese Unexamined Patent Application Publication No. 2019-096975

[0008] Patent Document 4: Japanese Unexamined Patent Application Publication No. 2019-154481

[0009] However, since conventional services start from user operations such as remotely confirming the status of home appliances or remotely operating home appliances by the user, the frequency of user operations of the home appliance application is high, and the convenience for the user is not necessarily high. Therefore, there is a need for a home appliance application that can control home appliances according to the attributes of the user. To provide such a home appliance application, it is necessary to infer the attributes of the user without relying on the user's setting behavior. Summary of the Invention

[0010] The problem to be solved by the present invention is to provide an information processing system that can infer the attributes of a user who uses a washing machine.

[0011] The information processing system according to the embodiment has an acquisition unit and an inference unit. The acquisition unit acquires data related to the state of the washing machine. The inference unit uses a learned model generated by machine learning to infer the attributes of the user of the washing machine based on the data acquired by the acquisition unit.

[0012] Effects of the Invention:

[0013] The present invention can infer the attributes of a user who uses a washing machine. Brief Description of the Drawings

[0014] Figure 1 This is a diagram showing the overall structure of the information processing system according to the embodiment.

[0015] Figure 2 This is an external view showing an example of the structure of the washing machine according to the embodiment.

[0016] Figure 3 This is a cross-sectional view showing an example of the structure of the washing machine according to the embodiment.

[0017] Figure 4 This is a block diagram showing an example of the structure related to the control of the washing machine according to the embodiment.

[0018] Figure 5 This is a diagram showing a specific example of the image inside the tub of the washing machine according to the embodiment.

[0019] Figure 6 This is a block diagram showing an example of the structure of the server according to the embodiment.

[0020] Figure 7 This is a diagram showing a specific example of the data D used to generate the input information for estimating the number of users in the information processing system according to the embodiment.

[0021] Figure 8 This is a diagram showing a first specific example of the temperature change around the washing machine according to the embodiment.

[0022] Figure 9 This is a diagram showing a second specific example of the temperature change around the washing machine according to the embodiment.

[0023] Figure 10 This is a diagram showing a specific example of the user registration information according to the embodiment.

[0024] Figure 11 This is a diagram showing the process flow of the processing in the washing machine according to the embodiment.

[0025] Figure 12 This is a diagram showing the process flow of the processing in the server according to the embodiment.

[0026] Mark Explanation:

[0027] 1... Information processing system, 100... Washing machine, 1A... Opening, 1B... Washing machine main body, 1D... Door, 1DL... Door handle, 4... Switch, 5... Operation panel, 6... Display unit, 7... Drum motor, 8... Power supply unit, 9... Drain valve unit, 10... Water inlet valve unit, 11... Drying unit, 13... Rotating tub, 14... Water tub, 17... Supplementary liquid storage unit, 17A... Opening, 23... Water supply port, 24... Water intake port, 26... Detergent and fabric softener input unit, 26F... Cover surface, 30... Pump, 31, 32... Tanks, 34... Cover, 601... Door switch, 602... Detergent remaining amount sensor, 603... Fabric softener remaining amount sensor, 604... Power detection unit, 605... Water level sensor, 606... Bubble sensor, 607... Weight sensor, 608... Stain sensor, 609... Water temperature sensor, 610... In-tub camera, 611... Surrounding temperature and humidity sensor, 612... Outside air temperature sensor, 613... Lint filter switch, 70... Wireless module, 80... Control unit, 81... Cleaning control unit, 82... Storage unit, 83... Information recording unit, 84... Information output unit, 200... Server, 201... Information acquisition unit, 202... Information conversion unit, 203... Learning unit, 204... Estimation unit, 205... Information recording unit, 206... Information output unit, 207... Storage unit, 300... Terminal device, 300a... Display device. Detailed implementation manners

[0028] Hereinafter, the information processing system of the implementation manner will be described with reference to the drawings. In the following description, the same reference numerals are added to the structures having the same or similar functions. And sometimes the repeated description of these structures is omitted. The so-called "based on XX" means "at least based on XX", and it can also include the case of being based on other elements in addition to XX. The so-called "based on XX" is not limited to the case of directly using XX, and it can also include the case of being based on the result of arithmetic operation and processing of XX. The so-called "XX or YY" is not limited to the case of either XX or YY, and it can also include the case of both XX and YY. This is the same when the number of selected elements is three or more. "XX" and "YY" are arbitrary elements (for example, arbitrary information).

[0029] (First implementation manner)

[0030] <1. Overall structure of the information processing system>

[0031] Figure 1FIG. is a diagram showing the overall configuration of the information processing system 1 according to an embodiment. The information processing system 1 includes, for example, a washing machine 100, a server 200, and a terminal device 300 configured in each household. Among them, in this specification, the so-called "information processing system" may refer only to the server 200 without including the washing machine 100 and the terminal device 300. Regarding the network NW described later, depending on the situation, for example, the Internet, a cellular network, a Wi-Fi network, LPWA (Low Power Wide Area), WAN (Wide Area Network), LAN (Local Area Network), other public lines, dedicated lines, etc. may be used.

[0032] The washing machine 100 is arranged in the residence of the user U. The washing machine 100 can communicate with the server 200 via a wireless router R arranged in the residence of the user U and the network NW, for example. Figure 1 The number of the washing machines 100 shown is one, but it is not limited thereto, and there may be multiple washing machines. The structure of the washing machine 100 will be described in detail later.

[0033] The server 200 is composed of one or more server devices SD (such as cloud servers). The server 200 may also be referred to as a "server system". The server 200 may also include an information processing unit that performs edge computing and fog computing, such as an information processing unit included in a router in the network NW. The server 200 will be described in detail later.

[0034] The terminal device 300 is a device such as a personal computer and can communicate with the server 200 via the network NW. The terminal device 300 includes a display device 300a such as a liquid crystal display or an organic EL (Electro Luminescence) display. Among them, the terminal device 300 and the server device SD may also be integrally provided in one device.

[0035] <2. Washing Machine>

[0036] <2.1 Overall Structure of Washing Machine>

[0037] Figure 2 FIG. is an external view showing a structural example of the washing machine 100. In addition, Figure 3 FIG. is a cross-sectional view showing a structural example of the washing machine 100. Figure 3 Shows Figure 2 The cross-section of the washing machine 100 along the line F2 - F2 in Figure 2 and Figure 3As shown, the washing machine 100 is a drum - type washing and drying machine with a drying function, but this does not limit the washing machine of the present embodiment to a drum - type. The washing machine 100 can also be a vertical washing and drying machine. The washing machine 100 is configured to include a wireless module 70 so as to be able to connect to a network.

[0038] The washing machine 100 includes, for example, a washing machine main body 1B, a door 1D, a switch 4, and an operation panel 5. In addition, in the washing machine 100, the side of the door 1D is set as the front side of the washing machine 100, and the side opposite to the surface where the door 1D is located is set as the rear side of the washing machine 100. In Figure 1 the XYZ - axis coordinate system is adopted, the +X - axis is defined as the horizontal direction along the front surface of the washing machine 100, the +Y - axis is defined as the depth direction, and the +Z - axis is defined as the vertical direction upward. The description of the XYZ - axis coordinate system is the same in the following figures.

[0039] The washing machine main body 1B forms the outer shell of the washing machine 100 and is formed in a rectangular box shape with a smoothly inclined front surface. An opening 1A is provided in the central part of the front surface of the washing machine main body 1B. The opening 1A communicates with a rotary tub 13 ( Figure 2 ) provided inside the washing machine main body 1B. Laundry is put into the rotary tub 13 through this opening 1A. The door 1D is provided so as to be able to open and close the opening 1A. The door 1D is opened by operating a door handle 1DL provided near the opening 1A. In addition, a door switch 601, which is a sensor for detecting the opening and closing of the door, is provided at the opening and closing part of the door 1D.

[0040] At the upper left part of the front surface of the washing machine main body 1B, a detergent and softener input part 26 ( Figure 3 ) is provided, which can slide back and forth to move in and out. When the detergent and softener input part 26 is accommodated inside the washing machine main body 1B, the cover surface 26F of the detergent and softener input part 26 is formed with the same inclination as the inclination of the front surface of the washing machine main body 1B. In the detergent and softener input part 26, a detergent box (not shown) is provided for the user to input detergent or softener during each washing operation. The user pulls out the detergent and softener input part 26, injects the detergent or softener measured by the user himself / herself, accumulates it in the detergent box, and then accommodates the detergent and softener input part 26 inside the washing machine main body 1B. Then, when the washing machine 100 starts a washing operation, the detergent or softener injected and accumulated in the detergent box is put into a water tub 14 ( Figure 3 ) at a specified timing during the process of executing the washing operation control. In addition, in the detergent box, a detergent remaining amount sensor 602 and a softener remaining amount sensor 603, which are sensors for detecting the remaining amounts of detergent and softener in the box, are provided.

[0041] On the upper surface of the washing machine main body 1B, a water supply port 23, an opening 17A, and a lid 34 are provided. The water supply port 23 is connected to the faucet of a water pipe of a water supply source, i.e., a tap water pipe, through a water supply pipe (not shown). Moreover, the water from the faucet of the tap water pipe is supplied into the tub 14 provided inside the washing machine main body 1B through the water supply pipe, the water supply port 23, and an inlet valve unit 10 described later.

[0042] A lid 34 that can be freely opened and closed is arranged at the opening 17A. For example, Figure 1 the lid 34 shown is in an open state. The opening 17A is used to replenish a cleaning treatment agent into a replenishing liquid storage portion 17 provided inside the washing machine main body 1B. Detergent, fabric softener, bleach, and a mixed solution thereof are an example of the cleaning treatment agent. In the following description, a case where detergent is used as the first cleaning treatment agent and fabric softener is used as the second cleaning treatment agent is exemplified. However, it is not limited thereto, and for example, bleach or a mixed solution may be used in the same manner instead of the above example, or bleach or a mixed solution may be used in addition to the above example.

[0043] For example, the replenishing liquid storage portion 17 includes a pump 30 ( Figure 3 ), and tanks 31 and 32. The tanks 31 and 32 are containers having a liquid receiving port (not shown) at the upper part. The tanks 31 and 32 separately store detergent or fabric softener injected into the inside from the liquid receiving port for each tank. A pump 30 is provided in the liquid flow path from the inside of the tanks 31 and 32 to the tub 14. When the pump 30 is driven, the cleaning treatment agent in the tanks 31 and 32 is injected into the tub 14. For example, a control unit 80 (described later in Figure 4 ) determines the timing for driving the pump 30 according to the cleaning operation program selected by the user. In addition, the case of two tanks is exemplified with reference to the tanks 31 and 32, but the number of tanks is not limited, and it may be one, or three or more.

[0044] The operation panel 5 accepts various settings related to the operation of the washing machine 100. For example, as Figure 2 shown, the operation panel 5 is provided on the front side of the upper surface of the washing machine main body 1B. The operation panel 5 includes, for example, a display unit 6 and switches 4. The display unit 6 is formed as a so-called touch operation panel, for example, and includes a touch sensor composed of a capacitive switch. The display unit 6 includes, for example, a liquid crystal display device or the like. The display unit 6 displays an image including a plurality of display screens related to cleaning operation control on its display surface. For example, the operation panel 5 accepts the operation of the user instructing the switching of the control mode (start of other control modes) of the cleaning operation control of the washing machine 100, and displays the setting content based on the operation and the current operation status.

[0045] The switch 4 is the power switch of the washing machine 100. On the power supply side of the switch 4, there is a power cord (not shown), through which power is supplied from the outside. In addition, on the load side of the switch 4, a power supply unit (not shown) that supplies the power supplied from the outside to each functional unit of the washing machine 100 is connected.

[0046] Specifically, the power supply unit converts the alternating current supplied from the outside into direct current, and supplies the stabilized voltage to each functional unit of the washing machine 100. For example, the power supply unit includes a detection unit (the power supply detection unit 604 described later) for the direct current voltage (not shown), and supplies the detection result to the control unit 80. For example, if the state is such that a direct current voltage lower than a specified threshold voltage is output from the power supply unit, the power supply unit outputs a reset request to the control unit 80. If the direct current voltage exceeding the specified threshold voltage is output from the power supply unit when the power is turned on through the switch 4, the power supply unit reverses the detection result and cancels the reset request to the control unit 80. The washing machine 100 performs the initialization process based on the control unit 80 from when the reset request is canceled, and then becomes a state capable of performing various controls including communication control and washing control. The operation of turning on the power through the switch 4 is an example of an operation (washing operation start operation) for starting the washing operation. The washing machine 100 starts the washing operation after detecting the washing operation start operation. The washing machine 100 stipulates this sequence in such a way that the actual washing operation starts from when the washing operation start operation is detected. However, there is no limit to the time difference between the two. Figure 4 In addition, the washing machine 100 is connected to a drum motor 7, a drain valve unit 9, a water inlet valve unit 10, a drying unit 11, and a pump 30 (automatic dosing mechanism). Detailed descriptions are omitted respectively, but the drum motor 7 rotates the rotary tub 13 provided in the washing machine main body 1B. The drain valve unit 9 includes a drain valve (not shown), a drain pump, and a drain valve motor, and drains the water in the water tub 14 to the outside of the machine. The water inlet valve unit 10 includes a water inlet valve (not shown), a bath water pump, and a bath water pump motor, opens and closes the communication between the water supply port 23 or the bath water intake port 24 and the inside of the water tub 14, and supplies water to the water tub 14.

[0047] The drying unit 11 includes a compressor, a fan, a fan motor, and an exhaust baffle motor (not shown), and constitutes a heat pump unit for drying the laundry. The pump 30 doses the detergent or softener stored in the tanks 31 and 32 in a timed manner according to the control of the control unit 80. The control unit 80 includes a drive circuit for driving each part. The drum motor 7, the drain valve unit 9, the drying unit 11, the water inlet valve unit 10, and the pump 30 are controlled via the control unit 80.

[0048] <2.2 Configuration of the Sensor Group and Control Unit of the Washing Machine>

[0049]

[0050] ​Figure 4 is a block diagram showing an example of a structure related to the control of the washing machine 100. As Figure 4 shown, the washing machine 100 includes a wireless module 70 for communicably connecting itself to other communication devices, a control unit 80 for causing its own device to function as a washing machine, and a sensor group SU for acquiring various information required for the control of the washing machine. The control unit 80 is communicably connected to the sensor group SU through a communication line inside the washing machine 100 and is wirelessly communicably connected to the server 200 via the wireless module 70. The wireless module 70 wirelessly communicates with the server 200 via the wireless router R.

[0051] The control unit 80 is configured to include a processor such as a CPU (Central Processing Unit), memories such as SRAM (Static Random Access Memory) and DRAM (Dynamic Random Access Memory), and auxiliary storage devices such as an SSD (Solid State Drive) and an HDD (Hard Disk Drive). The control unit 80 functions as a device including a washing control unit 81, a storage unit 82, an information recording unit 83, and an information output unit 84 by reading a program stored in the auxiliary storage device onto the memory and executing it through the processor. In addition, all or part of the functions of the control unit 80 may be implemented by hardware (circuit unit; including circuits) such as an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), or an FPGA (Field Programmable Gate Array), or may be implemented by the cooperative operation of software and hardware.

[0052] The cleaning control unit 81 has a function of controlling the operations of the drum motor 7, the drain valve unit 9, the water inlet valve unit 10, the drying unit 11, and the pump 30 according to the input operations to the operation panel 5 and the detection results of the sensor group SU in order for its own device to function as a washing machine. The cleaning control unit 81 may also be configured to perform control based on the cleaning method set by the user U in addition to the control based on the cleaning method preset for the washing machine 100. For example, the cleaning method of the user U is set by using the operation panel 5 of the washing machine 100 or an application installed in the terminal device 300 (hereinafter referred to as the "cleaning application"). Hereinafter, the cleaning method selectable during the use of the washing machine 100 is referred to as a "cleaning program", and the program set by the user U through the cleaning application in the cleaning program is referred to as an "application program".

[0053] The storage unit 82 stores the identification information I1 and the status information I2. The identification information I1 represents the device ID assigned to each washing machine 100 for identifying the washing machine 100. The status information I2 is time-series information indicating the status of the washing machine 100.

[0054] The information recording unit 83, for example, refers to a timer (not shown), correlates the information indicating the status of the washing machine 100 with the date and time information, and adds it to the status information I2 in the storage unit 82. The "status of the washing machine 100" includes, for example, the on (ON) / off (OFF) state of the power supply of the washing machine 100, the operating states of the drum motor 7, the water inlet valve unit 10, the drain valve unit 9, the drying unit 11, and the pump 30. In addition, the "status of the washing machine 100" may also include the status of the items washed by the washing machine 100. The date and time information includes information indicating the day of the week and the time.

[0055] Furthermore, the information recording unit 83 correlates the information indicating the detection results of the sensor group SU with the date and time information, and adds it to the status information I2 in the storage unit 82. Here, in addition to the above-described door switch 601, detergent level sensor 602, fabric softener level sensor 603, and power detection unit 604, the washing machine 100 further includes a water level sensor 605, a bubble sensor 606, a weight sensor 607, a dirt sensor 608, a water temperature sensor 609, an in-barrel camera 610, a surrounding temperature and humidity sensor 611, an outside air temperature sensor 612, and a lint filter switch 613 as the sensor group SU.

[0056] The water level sensor 605 is a sensor that measures the water level of the water injected into the water storage tub 14. The bubble sensor 606 is a sensor that detects the bubbles generated inside the water storage tub 14. Bubbles are mainly generated during the execution of the washing process due to the agitation of the detergent or fabric softener inside the water storage tub 14. According to the degree of foaming, it is possible to detect an excess or deficiency of the detergent or fabric softener. The weight sensor 607 is a sensor that measures the weight of the water storage tub 14. According to the weight of the water storage tub 14, it is possible to detect the amount of water injected and the amount of laundry to be cleaned. The dirt sensor 608 is a sensor that detects the dirt of the water inside the water storage tub 14. According to the vibration state of the water storage tub 14, it is possible to detect the state of the laundry inside the water storage tub 14. The water temperature sensor 609 is a sensor that measures the temperature of the water injected into the water storage tub 14.

[0057] The in-tub camera 610 is a camera that photographs the inside of the water storage tub 14 of the washing machine 100. For example, Figure 5 FIG. is a specific example showing an image (hereinafter referred to as "in-tub image") obtained by photographing the inside of the water storage tub 14 of the washing machine 100 with the in-tub camera 610. The detection results of the sensor group SU are the detection results of the above various sensors and switches. Regarding this information, the original data can be recorded, or it can be recorded in a state after necessary calculations (processing).

[0058] The ambient temperature and humidity sensor 611 is a sensor that detects the temperature and humidity near the washing machine 100. The outside air temperature sensor 612 is a sensor that measures the outside air temperature of the installation location of the washing machine 100. When the washing machine 100 is installed outdoors, the measured temperature of the outside air temperature sensor 612 is the same as the measured temperature of the ambient temperature and humidity sensor 611, so the outside air temperature sensor 612 can also be omitted. The power supply detection unit 604 has the function of detecting the DC voltage as described above. Through this function, the power supply detection unit 604 can detect the frequency of the external power supply connected to the washing machine 100.

[0059] The information output unit 84 transmits the status information I2 stored in the storage unit 82 to the server 200 via the wireless module 70. The information output unit 84 transmits the status information I2 to the server 200 at a predetermined cycle, for example. At this time, the information output unit 84 transmits the status information I2 to the server 200 in association with the identification information I1 stored in the storage unit 82. The identification information I1 is a device ID assigned to each washing machine 100 to identify the washing machine 100. The status information I2 and the identification information I1 are an example of the data transmitted from the washing machine 100 to the server 200. Hereinafter, the status information I2 and the identification information I1 are collectively referred to as "data D".

[0060] Alternatively, instead of the above structure, the information recording unit 83 may be omitted, and the information output unit 84 may transmit the operating state of the washing machine 100 and the detection results of the sensor group SU to the server 200 in real time. In this case, the server 200 may also establish the correspondence between the operating state of the washing machine 100 and the detection results of the sensor group SU and the date-time information.

[0061] <3. Server>

[0062] Figure 6 FIG. is a block diagram showing a structural example of the server 200. The server 200 includes, for example, an information acquisition unit 201, an information conversion unit 202, a learning unit 203, an estimation unit 204, an information recording unit 205, and an information output unit 206. These functional units are implemented by a hardware processor such as a CPU included in the server 200 executing a program (software). However, all or part of these functional units may also be implemented by hardware (circuit unit; including circuits) such as ASIC, PLD, or FPGA, or may be implemented by the cooperation of software and hardware.

[0063] Furthermore, the server 200 has a storage unit 207. The storage unit 207 is implemented, for example, by a combination of RAM, ROM, HDD, flash memory, or a plurality of them. In the storage unit 207, stored information I11, user registration information I12, learning model L, estimation model (learned model) M, and user attribute information I13 are stored.

[0064] The information acquisition unit 201 acquires the data D (received) transmitted from the washing machine 100. In addition, when learning the estimation model M, the information acquisition unit 201 collects the data D from a plurality of washing machines 100 used in a plurality of households respectively. The information acquisition unit 201 stores the acquired data D as the stored information I11 in the storage unit 207. For example, regarding each washing machine 100, the information acquisition unit 201 stores the data D for a specified period (e.g., 3 months). The information acquisition unit 201 is an example of the "acquisition unit".

[0065] The information conversion unit 202 generates input information to be input to the estimation model M, which will be described later, based on the storage information I11 storing the data D of each washing machine 100 and the learning model L. The learning model L is a model representing an algorithm for performing machine learning. The estimation model M is a learned model generated by learning using the storage information I11 of the learning model L, and is a model for estimating the attributes of the user U. For example, as an example of the attributes of the user U, (a) the number of users of the washing machine 100, (b) gender, (c) age, (d) housing type, (e) installation location, (f) employment type, (g) presence or absence of marriage, (h) residential area, etc. can be cited. However, the attributes of the estimated user U only need to be matters that can be estimated from the storage information I11 regarding the user U, and may be matters other than those listed above.

[0066] (a. Input information for estimating the number of users)

[0067] For example, the information conversion unit 202 generates one or more of the following listed information based on the storage information I11 as input information (hereinafter referred to as "input information for estimating the number of users") to be input to the estimation model M for estimating the attribute regarding the number of users. These information have a correlation with the number of users at least from the viewpoints described below. Therefore, one or more of the following listed information can be used as the input information of the estimation model M that outputs the attribute regarding the number of users.

[0068] · Information about the model type of the washing machine 100

[0069] · Information about the number of cleaning times of the washing machine 100

[0070] · Information about the amount of laundry washed by the washing machine 100

[0071] · Information about the cleaning time of the washing machine 100

[0072] · Information about the continuous operation of the washing machine 100

[0073] · Information about the dirt of the laundry washed by the washing machine 100

[0074] · Information about the cleaning frequency of the lint filter in the washing machine 100

[0075] · Information about the cleaning program of the washing machine 100

[0076] · Information about the setting of the timer reservation of the washing machine 100

[0077] · Information about the use of bath water in the washing machine 100

[0078] · Information on the change of the reserved time in the washing machine 100

[0079] · Information on the type of clothing to be washed by the washing machine 100

[0080] · Information on the time from the end of washing in the washing machine 100 until the clothes are taken out

[0081] For example, it is considered that generally, the manufacturer of washing machines line up models with functions corresponding to the number of people using the washing machines. Therefore, users select and purchase a model corresponding to the number of people they envision using from the models available. Thus, it is considered that the washing machine 100 is highly likely to be used by a number of users corresponding to its model type.

[0082] In addition, generally, the load applied to the washing machine 100 tends to be larger as the number of people using the washing machine 100 (for example, the number of cohabiting family members of the user) increases. Therefore, various index values indicating the magnitude of the load applied to the washing machine 100 are correlated with the number of users of the washing machine 100. Here, as index values indicating the magnitude of the load applied to the washing machine 100, examples include "the number of washing times of the washing machine 100", "the amount of clothes washed by the washing machine 100", "the washing program of the washing machine 100", "the washing time of the washing machine 100", "the continuous operation of the washing machine 100", "the dirtiness of the clothes washed by the washing machine 100", "the cleaning frequency of the lint filter in the washing machine 100", etc.

[0083] Figure 7 It is a diagram showing a specific example of the data D used in the generation of the input information for estimating the number of users. The data D is time-series data representing the detection results of the sensor group SU. In Figure 7 "The number of washing times of the washing machine 100" can be detected, for example, based on the output of the door switch 601. In addition, "the amount of clothes washed by the washing machine 100" can be detected, for example, based on the output of the weight sensor 607 or the water level sensor 605. In addition, "the washing time of the washing machine 100" and "the continuous operation of the washing machine 100" can be detected, for example, based on the output of the door switch 601 or the weight sensor 607. In addition, "the dirtiness of the clothes washed by the washing machine 100" can be detected, for example, based on the output of the dirt sensor 608. In addition, "the cleaning frequency of the lint filter in the washing machine 100" can be detected based on the output of the lint filter switch 613.

[0084] In addition, generally, the method of using the washing machine 100 tends to change depending on whether the person using the washing machine 100 is a single person or a family. Here, as index values related to the method of using the washing machine 100, "setting of the timer reservation of the washing machine 100", "use of bath water in the washing machine 100", "change of the reservation time of the washing machine 100", etc. can be cited. For example, a user who uses the washing machine 100 alone is considered to have a large change in life pattern, so it is considered that the frequency of changing the reservation time of the timer is relatively high. On the other hand, a user who uses the washing machine 100 as a family is considered to have a small change in life pattern, so it is considered that the frequency of changing the reservation time of the timer is relatively low.

[0085] In addition, it is generally considered that the user who uses bath water while using washing machine 100 is likely to be a family member who uses washing machine 100. Information related to "washing program of washing machine 100", "setting of timer reservation of washing machine 100", "use of bath water in washing machine 100", and "change of reservation time of washing machine 100" can be detected based on the history information of operation input performed on operation panel 5.

[0086] Furthermore, generally, the types of clothes washed by washing machine 100 more directly reflect the family composition of the user. For example, for the family composition of a user who washes smaller clothes, it is considered that the possibility of the family being a family with children is high, and it is considered that the number of people using washing machine 100 is high. Furthermore, generally, it is considered that a short time from the end of washing by washing machine 100 to the removal of clothes is high, indicating a high possibility of a large amount of washing, and it is considered that the user is likely to use washing machine 100 as a family. "Types of clothes washed by washing machine 100" can be determined, for example, based on the image in the tub (refer to Figure 5 The “time from the end of washing in the washing machine 100 to the time when the laundry is taken out” can be detected based on the output of the door switch 601 or the weight sensor 607, for example.

[0087] The information conversion unit 202 generates information such as "information related to the load applied to the washing machine 100", "information related to the time from the end of washing in the washing machine 100 to the removal of the clothes", "information related to the types of clothes washed by the washing machine 100", "information related to the washing program of the washing machine 100", "information related to the setting of the timer reservation of the washing machine 100", "information related to the use of bath water in the washing machine 100", and "information related to the change of the reservation time of the washing machine 100" obtained based on such data D as input information for estimating the number of users.

[0088] In addition, as other examples of attributes related to the number of users of the washing machine 100, the family structure of the user can be cited. For example, when it is presumed that the number of users of the washing machine 100 is one person, the family structure of this user can be considered a single-person household. In addition, for example, when it is presumed that the number of users of the washing machine 100 is two people and they are of the same generation, the family structure of this user can be considered a family consisting only of a couple. In this case, in order to presume the age or age group of the user, the input information for age presumption described later can also be included in the input information for number presumption.

[0089] In addition, for example, when it is presumed that the number of users of the washing machine 100 is multiple people and includes children and adults, the family structure of this user can be considered a family of parents and children. In this case, in order to presume the presence or absence of children, information such as the input information for age presumption and the input information for employment mode presumption described later can also be included in the input information for number presumption.

[0090] In addition, in this case, when it is presumed that the adults include adults in the child-rearing age group and elderly adults, the family structure of this user can be considered a three-generation family. In this case, in order to presume the age group of the adults, information such as the input information for age presumption and the input information for employment mode presumption described later can also be included in the input information for number presumption.

[0091] (b. Input Information for Presuming Gender)

[0092] For example, the information conversion unit 202 generates one or more of the following-listed information based on the accumulated information I11 as input information (hereinafter referred to as "gender presumption input information") to be input to the presumption model M for presuming attributes related to the gender of the user U. These information have a correlation with the gender of the user U at least from the viewpoints described below. Therefore, one or more of the following-listed information can be used as input information for the presumption model M that outputs attributes related to the gender of the user U.

[0093] · Information related to the types of clothes washed by the washing machine 100

[0094] · Information related to the washing program of the washing machine 100

[0095] · Information related to the brand of detergent or fabric softener used in the washing machine 100

[0096] · Information related to the physical characteristics of the user U of the washing machine 100

[0097] "The types of clothes washed by washing machine 100" more directly reflects the gender of its user. For example, it is possible to determine whether the clothes washed by washing machine 100 are for male or female based on the use, size, pattern, color, shape (an example of the type of clothes), etc. of the clothes. In addition, generally, it is considered that women have a stronger tendency to consider the load on the laundry compared to men. For example, it is considered that "fashionable clothes washing", which is one of the "washing programs of washing machine 100", has a tendency to be more favored by women than men. In addition, such female preferences are sometimes also reflected in the detergents or fabric softeners used. Therefore, when the use of a specific brand of detergent or fabric softener is detected, there is a possibility of inferring the gender of the user. "Information related to the brand of detergent or fabric softener used in washing machine 100" can be determined, for example, through user registration information I12.

[0098] In addition, it is considered that "the physical characteristics of user U" show a tendency related to the gender of user U of washing machine 100. For example, men tend to be taller than women. In addition, men's hands or arms tend to be thicker than women's hands or arms. In addition, compared to men, women are more likely to wear jewelry on their hands or arms, and in most cases, it can be known from the appearance whether the jewelry is for women or men.

[0099] Specifically, the physical characteristics of user U of washing machine 100 can be obtained, for example, using the image data inside the tub of washing machine 100. For example, the hands of user U that put the laundry in and out are sometimes captured in the image inside the tub of washing machine 100. Therefore, the information conversion unit 202 detects the hands of the person captured in the image inside the tub through image recognition processing, and identifies the attributes of the detected hands (for example, size, thickness, presence or absence of ornaments, etc.). The image data inside the tub is a form of data D. In this case, the image recognition processing only needs to be able to identify the hands of the person captured in the image inside the tub, and any method can be used.

[0100] For example, in the image recognition processing, the following method can be adopted, that is: based on various feature amounts obtained using the pixel values of the image data, the presence and attributes of a person's hands are identified. Therefore, the information conversion unit 202 generates information representing the recognition result of a person's hands based on the image recognition processing as input information for gender inference. In addition, since it is considered that the pixel values of the image data contain information representing the characteristics of the subject, the information conversion unit 202 can also generate the image data itself as input information for gender inference.

[0101] (c. Input information for age inference)

[0102] For example, the information conversion unit 202 generates one or more pieces of information listed below based on the stored information I11 as input information (hereinafter referred to as "input information for age estimation") to be input to the estimation model M for estimating attributes related to the age of the user U. These pieces of information have a correlation with the age of the user U at least from the viewpoints described below. Therefore, one or more pieces of information listed below can be used as input information for the estimation model M that outputs attributes related to the age of the user U.

[0103] · Information related to the model of the washing machine 100

[0104] · Information related to the number of washings of the washing machine 100

[0105] · Information related to the types of clothes washed by the washing machine 100

[0106] · Information related to the washing program of the washing machine 100

[0107] · Information related to the continuous operation of the washing machine 100

[0108] · Information related to the washing time of the washing machine 100

[0109] · Information related to the brand of detergent or fabric softener used in the washing machine 100

[0110] · Information related to the timer reservation setting of the washing machine 100

[0111] · Information related to the dirtiness of the clothes washed by the washing machine 100

[0112] · Information related to the use of bath water in the washing machine 100

[0113] · Information related to the cleaning frequency of the lint filter in the washing machine 100

[0114] · Information related to the time from the end of washing of the washing machine 100 to the time when the clothes are taken out

[0115] The model of the washing machine 100 may show differences in the preferences of users according to age or age group. For example, it is considered that young users have a stronger tendency to choose a relatively new type of washing machine, i.e., a drum washing machine, and older users have a stronger tendency to choose a vertical washing machine.

[0116] In addition, for example, it is considered that the elderly have a lower probability of washing less than young people and thus a smaller load on the washing machine 100. In addition, for the same reason, it is considered that the elderly are less likely to run the washing machine 100 continuously than young people. In addition, since the elderly have a tendency to start activities early in the morning compared to young people, it is considered that the time to start the opening and closing of the washing machine 100 is earlier than that of young people. In addition, it is considered that the elderly have less changes in their life patterns on weekdays and weekends than young people. On the other hand, it is considered that the life patterns of salaried workers or students change on weekdays and weekends. Furthermore, it is considered that in the case of students, unlike salaried workers, even if the life patterns are different every day on weekdays, they have a tendency to repeat the same life pattern when viewed from the span of 1 week. In addition, sometimes the difference in preferences based on age groups is reflected according to the brands of detergents and softeners used in washing. Similarly, sometimes the difference in preferences based on age groups is reflected in the functions of the washing machine 100 used. For example, it is considered that the elderly are less likely to use the drying function than young people. For example, the use of the drying function can be determined based on the history information of the washing program being washed.

[0117] Therefore, the information conversion unit 202 generates "information related to the load applied to the washing machine 100", "information related to the types of clothes washed by the washing machine 100", "information related to the washing program of the washing machine 100", "information related to the continuous operation of the washing machine 100", "information related to the washing time of the washing machine 100", and "information related to the brand of detergent or softener used in the washing machine 100" as input information for age estimation.

[0118] (d. Input information for estimating attributes related to housing type)

[0119] For example, the information conversion unit 202 generates one or more of the following information based on the accumulated information I11 as input information to be input into the estimation model M for estimating the attributes related to the housing style (hereinafter referred to as "input information for estimating the housing style"). These information have a correlation with the housing style at least from the viewpoint described below. Therefore, one or more of the following information can be used as input information of the estimation model M that outputs the attributes related to the housing style.

[0120] Information about the temperature and humidity around the washing machine 100

[0121] Information on the outside temperature of the installation location of the washing machine 100

[0122] Figure 8 1 is a diagram showing a first specific example of temperature changes at the installation position of the washing machine 100.Figure 8 As shown, it is considered that the "temperature or humidity around the washing machine 100" shows a tendency to change in indoor and outdoor temperatures corresponding to the setting position. For example, compared with a single-family house, an apartment has a tendency for smaller indoor temperature changes. Specifically, information related to the temperature of the setting position of the washing machine 100 can be obtained based on the detection results of the ambient temperature and humidity sensor 611 included in the accumulated information I11. Therefore, the information conversion unit 202 generates information representing the temperature of the setting position of the washing machine 100 as input information for estimating the housing type.

[0123] In addition, compared with a single-family house, an apartment is less affected by the external air temperature, so it has a tendency for the indoor temperature change to be smaller regardless of time periods, seasons, etc. Since the indoor temperature change is greatly affected by the outdoor temperature, in order to more accurately determine the cause of the indoor temperature change, the "external air temperature at the setting position of the washing machine 100" can also be included in the input information for estimating the housing type. In addition, in addition to the temperature change, an apartment has a tendency for a smaller indoor humidity change compared with a single-family house. Therefore, similar to the temperature change, the "humidity around the washing machine 100" can also be included in the input information for estimating the housing type.

[0124] (e. Input information for estimating attributes related to the setting position of the washing machine 100)

[0125] For example, the information conversion unit 202 generates one or more of the following-listed information based on the accumulated information I11 as input information (hereinafter referred to as "setting position estimation input information") input to the estimation model M for estimating attributes related to the setting position of the washing machine 100. These information have a correlation with the setting position of the washing machine 100 at least in the viewpoints described below. Therefore, one or more of the following-listed information can be used as input information for the estimation model M that outputs attributes related to the setting position of the washing machine 100.

[0126] · Information related to the temperature or humidity around the washing machine 100

[0127] · Information related to the external air temperature at the setting position of the washing machine 100

[0128] For example, when the washing machine 100 is installed outdoors such as on a balcony or a roof, the temperature change around the washing machine 100 is the same as the change in the external air temperature. Therefore, it is considered that there is a high possibility of determining whether the setting position of the washing machine 100 is outdoors or indoors based on the temperature change around the washing machine 100. In addition, when the washing machine 100 is installed indoors, the temperature change around the washing machine 100 sometimes reflects the characteristics of the room.

[0129] Figure 9 This is a diagram showing a second specific example of the temperature change in the room where the washing machine 100 is installed. For example, in a studio apartment or the like, the washing machine 100 is sometimes installed near the kitchen, and a stove is installed near this installation location. Also, it is considered that when a stove is installed near the washing machine 100, the temperature near the washing machine 100 rises at the time of using the stove. In addition, since the stove is more likely to be used during the meal time, when the temperature near the washing machine 100 rises frequently during the meal time, the possibility that the installation location of this washing machine 100 is the kitchen is higher. Thus, it is considered that there is a correlation between "the temperature around the washing machine 100" and the attributes regarding the installation location of the washing machine 100. Therefore, the information conversion unit 202 generates "information related to the temperature or humidity around the washing machine 100" and "information related to the outside air temperature at the installation location of the washing machine 100" as input information for installation location estimation.

[0130] In addition, it is considered that when the washing machine 100 is installed indoors, "the humidity around the washing machine 100" exhibits humidity changes corresponding to the use of the space of the installation location. For example, when the washing machine 100 is installed near the kitchen, there is a tendency for the humidity to temporarily increase due to the steam generated during cooking. In addition, even in a space other than the kitchen, when using this space, there is also a tendency for the humidity to temporarily increase due to the exhalation of users or beverages, etc. In addition, the degree of the tendency for the humidity to temporarily increase sometimes varies depending on the use of this space, and this tendency is manifested by characteristics such as the amount of humidity change and the time period of humidity change. Therefore, the information conversion unit 202 generates information indicating the humidity around the washing machine 100 as input information for installation location estimation.

[0131] (f. Input information for estimating employment pattern)

[0132] For example, the information conversion unit 202 generates one or more of the following listed information based on the accumulated information I11 as input information (hereinafter referred to as "input information for employment pattern estimation") input to the estimation model M for estimating attributes related to the employment pattern of the user U. These information have a correlation with the employment pattern of the user U at least from the viewpoints described below. Therefore, one or more of the following listed information can be used as input information for the estimation model M that outputs attributes related to the employment pattern of the user U.

[0133] · Information related to the types of clothes washed by the washing machine 100

[0134] · Information related to the weekly usage cycle (hereinafter referred to as "washing cycle") of the washing machine 100

[0135] · Information related to the change of the reserved time of the washing machine 100

[0136] · Information related to the presence or absence of the terminal device 300 around the washing machine 100

[0137] For example, it is considered that the living pattern of the user U exhibits attributes such as the working style and working time period of the user U. In addition, the usage pattern of the washing machine 100 exhibits a part of the living pattern of the user U, and the change pattern of the load applied to the washing machine 100 exhibits the usage pattern of the washing machine 100. For example, when the working style of the user U is part-time, it is characterized by a relatively short time interval (e.g., less than a few hours) from the temporary end of the use of the washing machine 100 to the next start. When the working style of the user U is full-time, it is characterized by a relatively long time interval (e.g., more than 10 hours) from the temporary end of the use of the washing machine 100 to the next start.

[0138] In addition, for example, the working time period of the user U, as the time period from the temporary end of the use of the washing machine 100 to the next start, is reflected in the usage pattern of the washing machine 100. For example, the living pattern of the user U with a working time from 9:00 am to 20:00 pm is reflected in the usage pattern of the washing machine 100 where the use of the washing machine 100 is temporarily ended before 9:00 am on weekdays and restarted after 20:00 pm. In addition, the living pattern of the user U with a working time from 21:00 at night to 6:00 am the next day is reflected in the usage pattern of the washing machine 100 where the use of the washing machine 100 is temporarily ended before 21:00 at night on weekdays and restarted after 6:00 am the next day.

[0139] In addition, for example, when the user is a student, the living pattern of the user U is reflected in the usage pattern where the washing machine 100 is sometimes used in different patterns every day of the weekday but is used in a roughly same pattern repetition on a weekly basis. In addition, the living pattern of the user can be inferred based on whether the user is at the user's residence or not. For example, the presence or absence of the user can be inferred based on the presence or absence of a user terminal (e.g., smartphone, tablet, laptop, etc.) around the washing machine 100. In addition, the presence or absence of the user terminal around the washing machine 100 can be inferred based on the location information of the user terminal, or can be inferred based on whether the user terminal exists on the same subnet as the washing machine 100.

[0140] (f. Input information for inferring the marital status of the user U of the washing machine 100)

[0141] For example, the information transformation unit 202 generates one or more pieces of information listed below based on the accumulated information I11, as input information (hereinafter referred to as "input information for marriage presumption") to be input to the presumption model M for presuming attributes related to the presence or absence of marriage (married / unmarried) of the user U. These pieces of information have a correlation with the presence or absence of the user U's marriage at least from the viewpoints described below. Therefore, one or more pieces of information from the following-listed pieces of information can be used as the input information for the presumption model M that has an attribute related to the presence or absence of the user U's marriage as the output information.

[0142] · Information related to the number of cleaning times of the washing machine 100

[0143] · Information related to the types of clothes washed by the washing machine 100

[0144] · Information related to the cleaning program of the washing machine 100

[0145] · Information related to the cleaning time of the washing machine 100

[0146] · Information related to the continuous operation of the washing machine 100

[0147] · Information related to the time from the end of cleaning of the washing machine 100 until the clothes are taken out

[0148] · Information related to the timer reservation setting of the washing machine 100

[0149] · Information related to the dirtiness of the clothes washed by the washing machine 100

[0150] · Information related to the use of bath water in the washing machine 100

[0151] · Information related to the cleaning frequency of the lint filter of the washing machine 100

[0152] It is considered that the "load applied to the washing machine 100" shows a tendency related to the presence or absence of the user U's marriage. For example, when either men's clothes or women's clothes are accommodated in the water tub 14 of the washing machine 100, it is considered that the possibility of the user U being unmarried is relatively high. When both men's clothes and women's clothes are accommodated in the water tub 14, it is considered that the possibility of the user U being married is relatively high. In addition, when both adult clothes and children's clothes are accommodated in the water tub 14, it is also considered that the possibility of the user U being married is relatively high.

[0153] Therefore, the information conversion unit 202 generates information representing the recognition result of the clothing based on the image recognition process as the input information for marriage presumption. In addition, since it is considered that information representing the characteristics of the subject is included in each pixel value of the image data, the information conversion unit 202 can also generate the image data itself as the input information for marriage presumption.

[0154] In addition, it is considered that the "physical characteristics of the user U of the washing machine 100" also show a tendency related to the presence or absence of the marriage of the user U. For example, as the physical characteristics showing a tendency related to the presence or absence of marriage, the presence or absence of wearing a wedding ring can be cited. When it is recognized by the image recognition process that the user U's hand captured in the image inside the water tub is wearing a wedding ring, it is considered that the possibility that the user U is married is high.

[0155] Therefore, the information conversion unit 202 generates information representing the recognition result of the physical characteristics based on the image recognition process as the input information for marriage presumption. In addition, since it is considered that information representing the characteristics of the subject is included in each pixel value of the image data, the information conversion unit 202 can also generate the image data itself as the input information for marriage presumption.

[0156] (h. Input information for presumptive determination of the place of residence)

[0157] For example, the information conversion unit 202 generates one or more pieces of information listed below based on the stored information I11 as the input information (hereinafter referred to as "input information for place of residence presumption") input to the presumption model M for presumptive determination of the attribute related to the place of residence of the user U. These pieces of information have a correlation with the place of residence of the user U at least from the viewpoints described below. Therefore, one or more pieces of information listed below can be used as the input information for the presumption model M that outputs the attribute related to the place of residence of the user U.

[0158] · Information related to the temperature or humidity around the washing machine 100

[0159] · Information related to the frequency of the external power supply of the washing machine 100

[0160] It is considered that the "temperature around the washing machine 100" shows a tendency related to the residential area of the user U. For example, when the washing machine 100 is installed indoors, it is considered that the temperature around the washing machine 100 changes relatively with respect to the outside air temperature, and the outside air temperature shows different distributions corresponding to the region. Therefore, it is considered that the temperature around the washing machine 100 reflects the climate of the residential area of the user U. In addition, it is considered that the "humidity around the washing machine 100" also shows a tendency related to the residential area of the user U. Furthermore, it is considered that the combination of the "temperature around the washing machine 100" and the "humidity around the washing machine 100" characterizes the climate of the residential area in more detail.

[0161] Therefore, the information conversion unit 202 generates information representing the temperature around the washing machine 100 as input information for residential area estimation. Alternatively, the information conversion unit 202 may obtain temperature information of each region from the server of the meteorological agency, and use the comparison result between the obtained temperature information of each region and the detection result of the ambient temperature and humidity sensor 611 as input information for residential area estimation.

[0162] In addition, the water used by the user U during washing sometimes has properties unique to its residential area (such as soft water or hard water, etc.). Therefore, when it is possible to measure the water quality of the water used by the washing machine 100, there is a possibility of estimating the residential area of the user based on the measured water quality. Therefore, when there is a water quality sensor that measures the water quality of the water used by the washing machine 100, the information conversion unit 202 may also generate information related to the water quality of the water used by the washing machine 100 as input information for residential area estimation.

[0163] In addition, the "information related to the frequency of the external power supply" is information indicating whether the AC frequency of the external power supply connected to the washing machine 100 is 50 Hz or 60 Hz, etc. This information is derived, for example, based on the detection result of the power supply detection unit 604 included in the data D. Here, the frequency of the commercial power supply in eastern Japan is 50 Hz, and the frequency of the commercial power supply in western Japan is 60 Hz.

[0164] Next, the learning unit 203 will be described. The learning unit 203 generates a prediction model M for predicting the attributes of the user U as a learned model by applying the above various input information to the learning model L of machine learning. The prediction model M is learned to output a prediction result of the attributes of the user U of the washing machine 100 when information related to the washing machine 100 is input.

[0165] In the present embodiment, the learning unit 203 generates a presumption model MA for presuming attributes related to the number of users, a presumption model MB for presuming attributes related to gender, a presumption model MC for presuming attributes related to age, a presumption model MD for presuming attributes related to the housing type, a presumption model ME for presuming attributes related to the installation location, a presumption model MF for presuming attributes related to the employment type, a presumption model MG for presuming attributes related to the presence or absence of marriage, and a presumption model MH for presuming attributes related to the residential area, as the presumption model M for presuming the attributes of the user U.

[0166] In addition, "learning" as used in this specification may represent either unsupervised learning or supervised learning. Hereinafter, the case of generating the presumption model M through supervised learning will be mainly described, but the presumption model M may also be generated through unsupervised learning. For example, the learning unit 203 applies various presumption input information generated by the information transformation unit 202 and the user registration information I12 as training data to the learning model L, and learns the correlation between the various presumption input information and the user registration information I12, thereby generating the presumption models MA to MH as learned models. In the learning model L, for example, a neural network, reinforcement learning, deep learning, etc. can be used, but the learning model L is not limited thereto. The learning model L may also generate a regression curve or a classifier as the learning result of the above-mentioned correlation. For example, SVM (Support Vector Machine), Decision Tree, Random Forest, k-Nearest Neighbor algorithm, etc. may be used as the learning model L other than the neural network.

[0167] Figure 10 It is a diagram showing a specific example of the user registration information I12. In the user registration information I12, for each identification information (user ID) of each user U, the number of users of the washing machine 100 owned by the user, the installation location, the gender, age, employment type, presence or absence of marriage, residential area, housing type (housing mode) of the house where the user lives, the brands of fabric softener and detergent used, etc. can be cited. However, the attributes of the user U to be presumed may be matters that can be presumed for the user U based on the accumulated information I11, and may also be matters other than those listed above. The learning unit 203 can learn the correlation between the respective attributes of the user U and the various presumption input information by performing machine learning using, as training data, data obtained by associating the respective attributes of such a user U with the various presumption input information related to them.

[0168] In addition, the correspondence between each attribute of the user U and various input information for estimation can be established manually or mechanically. For example, it can also be that the learning unit 203 calculates the strength of the correlation between each attribute and various input information for estimation, and establishes the correspondence between the various input information for estimation and the attribute with the strongest correlation to generate training data.

[0169] The estimation unit 204 uses the estimation model M obtained by the learning unit 203 to estimate the user attributes of the user U of the washing machine 100 (hereinafter referred to as "the washing machine 100 to be judged") that is the object of judgment of the user attributes based on the data D received from the washing machine 100 to be judged. Here, the so-called "estimation" includes not only judging the most likely one attribute candidate, but also the case of outputting the respective probabilities of multiple attribute candidates (for example, the possibility that the number of users is 1 person: 10%, the possibility that the number of users is 2 people: 20%, the possibility that the number of users is 3 people: 50%, the possibility that the number of users is 4 or more people: 20%).

[0170] The estimation unit 204 inputs various input information for estimation based on the data D obtained from the washing machine 100 to be judged into the estimation model M, and obtains the estimation result of the user attributes of the user U of the washing machine 100 to be judged as the output information of the estimation model M. In the present embodiment, the estimation unit 204 inputs the above-mentioned input information for estimating the number of users, input information for estimating gender, input information for estimating age, input information for estimating the housing type, input information for estimating the installation location, input information for estimating the employment type, input information for estimating marriage, and input information for estimating the residential area as the input information based on the data D obtained from the washing machine 100 to be judged into the corresponding estimation models MA to MH respectively, and outputs the estimation results of (a) the number of users of the washing machine 100, (b) gender, (c) age, (d) housing type, (e) installation location, (f) employment type, (g) presence or absence of marriage, and (h) residential area as the output information of the estimation models MA to MH.

[0171] The information recording unit 205 stores the user attributes estimated by the estimation unit 204 as user attribute information I13 in the storage unit 207.

[0172] The information output unit 206 sends the user attribute information I13 obtained through the above processing to the terminal device 300. Thereby, the user attribute information I13 can be used for product development and service provision.

[0173] <4. Process flow>

[0174] Next, the process flow will be described.

[0175] Figure 11It is a diagram showing the process of processing in the washing machine 100. First, the control unit 80 determines whether the power supply of the washing machine 100 is turned on (ON) (S101). When the power supply of the washing machine 100 is turned off (OFF), the control unit 80 stands by until the power supply of the washing machine 100 is turned on.

[0176] On the other hand, when the power supply of the washing machine 100 is turned on (S101: Yes), the control unit 80 sends the detection results detected by the sensor group SU to the server 200 at a predetermined cycle or in real time (S102).

[0177] Next, the control unit 80 determines whether the power supply of the washing machine 100 is turned off (S103). When the power supply of the washing machine 100 is turned on (S103: No), the control unit 80 repeats the process of S102. On the other hand, when the power supply of the washing machine 100 is turned off (S103: Yes), the control unit 80 ends a series of processes. And the washing machine 100 repeats the above processes (S101 to S103) for a predetermined period, for example.

[0178] Figure 12 It is a diagram showing the process of processing in the server 200. As a prerequisite, the data D sent from the washing machine 100 is acquired by the information acquisition unit 201 and stored as the stored information I11.

[0179] First, the information conversion unit 202 generates the above various input information for estimation based on the stored information I11 (S201). Next, the estimation unit 204 inputs the generated various input information for estimation to the estimation models MA to MH respectively, and thus obtains an estimation result related to the attributes of the user U as output information (S202). Next, the information output unit 206 causes the terminal device 300 to output information indicating the estimation result related to the attributes of the user U estimated by the estimation unit 204.

[0180] <5. Function>

[0181] As a comparative example, consider collecting the attribute information of the user U by inputting information such as gender, age, number of users, and residential area in a questionnaire survey or on the Internet. However, in these cases, there are situations where the input is cumbersome and users are reluctant to input information. In addition, there are also situations where the information input by users does not match the actual situation. In addition, it is also difficult to confirm the detailed usage status with users in the form of a questionnaire survey.

[0182] On the other hand, in the present embodiment, the information processing system 1 includes an information acquisition unit 201 and an estimation unit 204. The information acquisition unit 201 acquires the data D transmitted from the washing machine 100, and the estimation unit 204 uses the estimation model M obtained by machine learning to estimate the attributes of the user U of the washing machine 100 based on various input information for estimation obtained from the data D acquired by the information acquisition unit 201. With such a configuration, even without the input of the user U, the attributes of the user U can be estimated based on the usage results of the washing machine 100 by the user U. Thereby, it is possible to reduce the burden of collecting the attribute information of the user U.

[0183] In addition, a server 200 communicably connected via a network may be used. In this case, each functional unit provided in the server 200 may be separately installed in a plurality of information processing devices. For example, the learning unit 203 and the estimation unit 204 may be separately installed in different information processing devices.

[0184] In the above-described embodiment, the case where the server 200 estimates information related to the attributes of the user of the washing machine 100 through machine learning of accumulated information has been described. However, the washing machine 100 may be configured to not only estimate the attributes of the user at a specified timing but also accumulate the estimation results and estimate the attributes of the user related to the changes based on the accumulated estimation results. For example, the server 200 may estimate the change in the family composition of the user based on the change in the number of users. For example, when the number of users increases from one to two, the server 200 may estimate that the user's marital status has changed from unmarried to married.

[0185] According to at least one of the embodiments described above, by having an acquisition unit that acquires data related to the state of the washing machine and an estimation unit that uses a learned model generated by machine learning to estimate the attributes of the user of the washing machine based on the data acquired by the acquisition unit, it is possible to estimate the attributes of the user using the washing machine without relying on the user's setting behavior.

[0186] Several embodiments of the present invention have been described, but these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other ways, and various omissions, substitutions, and changes can be made without departing from the gist of the invention. These embodiments and their modifications are included in the scope and gist of the invention, and similarly, are included in the invention described in the claims and its equivalent scope.

Claims

1. An information processing system, wherein: Comprising: A washing machine, having an in-tub camera for photographing the interior of the water tub of the washing machine and a sensor group for detecting various matters related to the washing machine; A storage unit that stores user registration information registered by the user of the washing machine for the use of the washing machine; An acquisition unit that acquires data related to the state of the washing machine based on the image data photographed by the in-tub camera, the output of the sensor group, or the user registration information; and An estimation unit that uses a learned model generated by machine learning to estimate the attributes of the user of the washing machine based on the data acquired by the acquisition unit, The data includes any one or more of the following information: information related to the model of the washing machine, information related to the dirt of the clothes washed by the washing machine, information related to the cleaning frequency of the lint filter of the washing machine, information related to the washing program used in the washing machine, information related to the setting of the timer reservation, information related to the use of bath water, information related to the change of the reservation time, information related to the type of clothes washed by the washing machine, or information related to the time from the end of washing to the time when the clothes are taken out. The estimation unit estimates the attribute related to the number of users of the washing machine as the attribute of the user.

2. An information processing system, wherein: Comprising: A washing machine, having an in-tub camera for photographing the interior of the water tub of the washing machine and a sensor group for detecting various matters related to the washing machine; A storage unit that stores user registration information registered by the user of the washing machine for the use of the washing machine; An acquisition unit that acquires data related to the state of the washing machine based on the image data photographed by the in-tub camera, the output of the sensor group, or the user registration information; and An estimation unit that uses a learned model generated by machine learning to estimate the attributes of the user of the washing machine based on the data acquired by the acquisition unit, The data includes any one or more of the following information: information related to the model of the washing machine, information related to the washing program used in the washing machine, information related to the brand of the detergent or softener used in the washing machine, information related to the timer reservation setting of the washing machine, information related to the dirt of the clothes washed by the washing machine, information related to the use of bath water in the washing machine, information related to the cleaning frequency of the lint filter in the washing machine, or information related to the time from the end of washing to the time when the clothes are taken out. The estimation unit estimates the attribute related to the age of the user as the attribute of the user.

3. An information processing system, wherein: Comprising: A washing machine, having an in-tub camera for photographing the interior of the water tub of the washing machine and a sensor group for detecting various matters related to the washing machine; A storage unit that stores user registration information registered by the user of the washing machine for the use of the washing machine; An acquisition unit that acquires data related to the state of the washing machine based on the image data captured by the in-tub camera, the output of the sensor group, or the user registration information; and A presumption unit that uses a learned model generated by machine learning to presume the attributes of the user of the washing machine based on the data acquired by the acquisition unit, The data includes any one or more of information related to the temperature around the washing machine, information related to the humidity around the washing machine, or information related to the external temperature at the installation location of the washing machine, The presumption unit presumes an attribute related to the user's housing style as the attribute of the user.

4. An information processing system, wherein It includes: A washing machine having an in-tub camera for photographing the inside of the tub of the washing machine and a sensor group for detecting various matters related to the washing machine; A storage unit that stores user registration information registered by the user of the washing machine for using the washing machine; An acquisition unit that acquires data related to the state of the washing machine based on the image data captured by the in-tub camera, the output of the sensor group, or the user registration information; and A presumption unit that uses a learned model generated by machine learning to presume the attributes of the user of the washing machine based on the data acquired by the acquisition unit, The data includes any one or more of information related to the temperature around the washing machine, information related to the humidity around the washing machine, or information related to the external temperature at the installation location of the washing machine, The presumption unit presumes an attribute related to the installation location of the washing machine as the attribute of the user.

5. An information processing system, wherein It includes: A washing machine having an in-tub camera for photographing the inside of the tub of the washing machine and a sensor group for detecting various matters related to the washing machine; A storage unit that stores user registration information registered by the user of the washing machine for using the washing machine; An acquisition unit that acquires data related to the state of the washing machine based on the image data captured by the in-tub camera, the output of the sensor group, or the user registration information; and A presumption unit that uses a learned model generated by machine learning to presume the attributes of the user of the washing machine based on the data acquired by the acquisition unit, The data includes any one or more of information related to the type of clothes washed by the washing machine, information related to the change of the reservation time, and information related to the presence or absence of a user terminal around the washing machine, The presumption unit presumes an attribute related to the user's employment style as the attribute of the user.

6. An information processing system, wherein It includes: A washing machine having an in-tub camera for photographing the inside of the tub of the washing machine and a sensor group for detecting various matters related to the washing machine; A storage unit that stores user registration information registered by the user of the washing machine for using the washing machine; An acquisition unit that acquires data related to the state of the washing machine based on the image data captured by the in-tub camera, the output of the sensor group, or the user registration information; and A presumption unit that uses a learned model generated by machine learning to presume the attributes of the user of the washing machine based on the data acquired by the acquisition unit, The data includes any one or more pieces of information related to the type of laundry being washed in the washing machine, information related to the washing program selected in the washing machine, information related to the time from the end of washing to when the laundry is taken out, information related to the timer reservation setting of the washing machine, information related to the dirtiness of the laundry being washed in the washing machine, information related to the use of bath water in the washing machine, and information related to the cleaning frequency of the lint filter in the washing machine. The presumption unit presumes an attribute related to the presence or absence of the user's marriage as the attribute of the user.

7. An information processing system, wherein it includes: A washing machine having an in-tub camera that captures the inside of the washing tub of the washing machine and a sensor group for detecting various matters related to the washing machine; A storage unit that stores user registration information registered by the user of the washing machine for the use of the washing machine; An acquisition unit that acquires data related to the state of the washing machine based on the image data captured by the in-tub camera, the output of the sensor group, or the user registration information; and A presumption unit that uses a learned model generated by machine learning to presume the attributes of the user of the washing machine based on the data acquired by the acquisition unit, The data includes any one or more pieces of information related to the temperature around the washing machine, information related to the humidity around the washing machine, or information related to the frequency of the external power supply of the washing machine. The presumption unit presumes an attribute related to the residential area of the user as the attribute of the user.

Images