CN113729546A

CN113729546A - Information processing system

Info

Publication number: CN113729546A
Application number: CN202110263542.8A
Authority: CN
Inventors: 金山将也; 丸谷裕树; 中川达也; 泷川正史
Original assignee: Toshiba Lifestyle Products and Services Corp
Current assignee: Toshiba Lifestyle Products and Services Corp
Priority date: 2020-05-29
Filing date: 2021-03-11
Publication date: 2021-12-03
Also published as: JP2021189726A

Abstract

Provided is an information processing system capable of reducing the burden of collecting attribute information of a user. An information processing system according to an embodiment includes an acquisition unit and an estimation unit. The acquisition unit acquires data transmitted from the electric vacuum cleaner. The estimating unit estimates the attribute of the user of the electric vacuum cleaner based on the input information obtained from the data acquired by the acquiring unit, using a model learned as an estimation result that outputs the attribute of the user when the information on the electric vacuum cleaner is input.

Description

Information processing system

Technical Field

Embodiments of the present invention relate to an information processing system.

Background

There is known an electric vacuum cleaner that receives data relating to a cleaning operation unit from an external device via a communication interface and performs control based on the received data.

Further, it is sometimes desired to collect attribute information of a user for product development, service provision, or the like. In this case, the user needs to be requested to complete a questionnaire, registration on the network, or the like, and the burden of collecting information may be large.

Patent document 1: japanese patent laid-open publication No. 2019-000442

Disclosure of Invention

An object of the present invention is to provide an information processing system capable of reducing the burden of collecting attribute information of a user.

An information processing system according to an embodiment includes an acquisition unit and an estimation unit. The acquisition unit acquires data transmitted from the electric vacuum cleaner. The estimating unit estimates the attribute of the user of the electric vacuum cleaner based on the input information obtained from the data acquired by the acquiring unit, using a model learned as an estimation result that outputs the attribute of the user when the information on the electric vacuum cleaner is input.

The invention has the following effects:

according to the present invention, the attribute of the user of the electric vacuum cleaner can be estimated.

Drawings

Fig. 1 is a diagram showing an overall configuration of an information processing system according to a first embodiment.

Fig. 2 is a perspective view showing an example of the electric vacuum cleaner according to the first embodiment.

Fig. 3 is a block diagram showing the configuration of a sensor and a control unit of the electric vacuum cleaner according to the first embodiment.

Fig. 4 is a diagram conceptually showing a part of data transmitted from the electric vacuum cleaner in the first embodiment.

Fig. 5 is a block diagram showing the configuration of the server according to the first embodiment.

Fig. 6 is a diagram showing an example of the content of the user registration information according to the first embodiment.

Fig. 7 is a diagram showing an example of an estimation model relating to unsupervised learning according to the first embodiment.

Fig. 8 is a diagram showing an example of an estimation model relating to supervised learning in the first embodiment.

Fig. 9 is a diagram showing an example of the contents of the user attribute information according to the first embodiment.

Fig. 10 is a flowchart showing a process flow of the electric vacuum cleaner according to the first embodiment.

Fig. 11 is a flowchart showing a processing flow of the server according to the first embodiment.

Fig. 12 is a block diagram showing a configuration of a server according to the second embodiment.

Fig. 13 is a block diagram showing a configuration of a server according to the third embodiment.

Description of the labeling:

100, 100A, 100B … electric vacuum cleaner, 200 … server, 201 … information acquisition unit (acquisition unit), 202 … information conversion unit, 203 … learning unit, 204 … user attribute estimation unit (estimation unit), M … estimation model.

Detailed Description

Hereinafter, an information processing system according to an embodiment will be described with reference to the drawings. In the following description, structures having the same or similar functions are denoted by the same reference numerals. Moreover, a repetitive description of these configurations may be omitted. By "based on XX", it is meant "based on at least XX", and it is also possible to include cases where the base is based on other elements in addition to XX. "based on XX" is not limited to the case of using XX directly, and may include a case of using the result of performing an operation or processing on XX. "XX or YY" is not limited to one of XX and YY, and may include both XX and YY. The same applies to the case where the number of selected elements is 3 or more. "XX" and "YY" are arbitrary elements (for example, arbitrary information).

(first embodiment)

< 1. overall Structure of information processing System >

Fig. 1 is a diagram showing an overall configuration of an information processing system (user information collection system) 1 according to an embodiment. The information processing system 1 includes, for example, an electric vacuum cleaner 100, a server 200, and a terminal device 300, which are disposed in each home. However, in the present specification, the "information processing system" may refer to only the server 200 without including the electric vacuum cleaner 100 and the terminal device 300. The Network NW described later may use, for example, the internet, a cellular Network, a Wi-Fi Network, an LPWA (Low Power Wide Area), a WAN (Wide Area Network), a LAN (Local Area Network), another public line, a private line, or the like, depending on the situation.

The electric vacuum cleaner 100 is disposed in the house of the user U. The electric vacuum cleaner 100 can communicate with the server 200 via a wireless router R and a network NW disposed in the house of the user U, for example. Details of the electric vacuum cleaner 100 will be described later.

The server 200 includes 1 or more server devices SD (e.g., cloud servers). The server 200 may also be referred to as a "server system". The server 200 may include an information processing unit that performs edge calculation and fog calculation, such as an information processing unit included in a router in the network NW. Details of the server 200 will be described later.

The terminal 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 (lcd) or an organic EL display (Electro Luminescence). Note that the terminal device 300 and the server device SD may be provided integrally in 1 device.

< 2. electric vacuum cleaner

< 2.1 integral Structure of electric vacuum cleaner

Fig. 2 is a perspective view showing an example of the electric vacuum cleaner 100. The electric vacuum cleaner 100 of the present embodiment is a so-called stick (stick) type electric vacuum cleaner, and is a cordless type electric vacuum cleaner incorporating a battery 15. The electric vacuum cleaner 100 includes, for example, a cleaner main body 10, an extension pipe 20, and a head (suction port body) 30.

The cleaner body 10 includes, for example, a body case 11, a handle (grip) 12, a dust collecting device 13, an electric blower 14, a battery 15, a circuit board 16, and a communication module 17 (see fig. 3).

The main body case 11 forms an outer contour of the cleaner main body 10. The main body case 11 accommodates an electric blower 14, a battery 15, a circuit board 16, a communication module 17, and the like. The main body case 11 has an extension pipe connecting portion 11a to which one end of an extension pipe 20 described later is connected.

A handle 12 is provided at an upper rear end portion of the main body case 11. The handle 12 is a portion to be held by the user U when the electric vacuum cleaner 100 is used to clean a floor surface (a surface to be cleaned). The handle 12 has an operation knob 12a operated by the user U.

The dust collecting device 13 is detachably mounted to the main body case 11. The dust collector 13 is a device for separating dust contained in air sucked into the cleaner body 10 by the operation of an electric blower 14 described later. For example, the dust collecting device 13 is a centrifugal separation type dust collecting device including a separating section 13a and a filter 13 b. The separating portion 13a centrifugally separates (whirls) dust contained in the sucked air from the air. The filter 13b separates (filters and separates) a small amount of dust remaining in the air having passed through the separating unit 13 a. However, the dust collector 13 is not limited to a centrifugal separation type dust collector, and may be a filter type dust collector including a dust collection paper bag or the like.

The electric blower 14 includes a motor called a fan motor or a main motor, and a turbine rotated by the motor, and is driven to generate a negative pressure. The electric blower 14 sucks in dust-containing air from a suction port 31a of a head 30 described later to the dust collecting device 13 by the generated negative pressure, and exhausts the air from which dust is separated in the dust collecting device 13 to the outside of the electric vacuum cleaner 100.

The battery 15 is a power supply unit that supplies electric power to the electric blower 14, a brush motor 34, and the like, which will be described later. The circuit board 16 includes a printed wiring board provided with a wiring pattern, and a plurality of electronic components mounted on the printed wiring board. The circuit board 16 implements a control unit 80 (see fig. 3) that controls the operation of the electric vacuum cleaner 100. The communication module 17 includes, for example, a high-frequency circuit and an antenna, and is capable of wireless communication with the router R.

Further, an air blowing attachment 18 is detachably attached to the cleaner body 10. The air blowing attachment 18 is a nozzle connected to the exhaust air passage of the cleaner body 10. When the air blowing attachment 18 is attached, the user U can perform cleaning by using the exhaust air blown out from the air blowing attachment 18. The air blowing accessory 18 is an example of "accessories".

Next, the extension pipe 20 will be explained. The extension pipe 20 is formed in a long shape, for example, and has a first end 20a and a second end 20 b. The first end 20a of the extension pipe 20 is air-tightly connected to the extension pipe connection part 11a of the cleaner body 10. The second end 20b of the extension tube 20 is hermetically connected to the head 30. Inside the extension pipe 20, a connection wiring for electrically connecting the cleaner body 10 and the head 30 is provided.

Next, the header 30 will be explained. The head 30 is a part that moves along the ground. The head 30 has, for example, a head housing 31, a connection pipe 32, a rotary brush 33, a brush motor 34, and a lamp 35.

The head case 31 is formed long in the lateral direction, i.e., is formed long in the left-right direction. The head housing 31 accommodates a brush motor 34. The head case 31 has a suction port 31a at a lower portion facing the floor surface. The suction port 31a is an opening through which dust on the floor is sucked by driving the electric blower 14.

The connection pipe 32 is a part for hermetically connecting the head case 31 and the second end 20b of the extension pipe 20, and is rotatably connected to the head case 31. By connecting the head housing 31 and the extension pipe 20 by the connection pipe 32, an air passage is formed from the suction port 31a of the head housing 31 to the cleaner body 10 through the extension pipe 20.

The rotary brush 33 is provided at the suction port 31a and arranged along the floor surface. The rotary brush 33 is rotatably provided with respect to the head housing 31. The rotating brush 33 plays a role of floating dust from the floor surface, raising the front end of pile of a carpet or the like, and the like. The brush motor 34 is connected to the rotary brush 33 via a rotation drive mechanism (not shown) and drives (rotates) the rotary brush 33. The lamp 35 is provided in the head case 31, and is turned on in accordance with a detection result of an illuminance sensor 65 described later when the head 30 is inserted into a dark place (a bed, a sofa, a gap in furniture, or the like).

Here, various accessories 36 can be detachably attached to the second end 20b of the extension pipe 20 in place of the head 30. The accessories 36 include, for example, a gap nozzle 36A, a round brush 36A, and a bed cleaning head 36C. Instead of the extension pipe 20, the accessories 36 may be detachably attached to the extension pipe connecting portion 11a of the main body case 11.

< 2.2 construction of sensor group and control part of electric vacuum cleaner >

Fig. 3 is a block diagram showing the configuration of the sensor group and the control unit 80 of the electric vacuum cleaner 100. The electric vacuum cleaner 100 includes, for example, an electric blower current detection unit 41, a power supply detection unit 42, a remaining battery level detection unit 43, a battery temperature sensor 44, a main body acceleration sensor 45, a main body gyro sensor 46, a grip force detection unit 47, a dust sensor 48, a camera 49, a dust collector detection switch 50, an air blowing accessory detection switch 51, a brush motor current detection unit 61, an encoder 62, a head acceleration sensor 63, a head gyro sensor 64, an illuminance sensor 65, an extension pipe angle sensor 66, and an accessory detection switch 67. Hereinafter, they are sometimes collectively referred to as "sensor group SU". However, the electric vacuum cleaner 100 does not need to include all of these sensors, switches, and the like.

The electric blower current detection unit 41 includes a shunt resistor and the like, and detects a current value of a current flowing from the battery 15 to the motor of the electric blower 14. The current value of the current flowing to the motor of the electric blower 14 is proportional to the load of the electric blower 14. For example, when the filter 13b is clogged and the load on the electric blower 14 increases, the current value detected by the electric blower current detection unit 41 increases. Therefore, the electric blower current detection unit 41 can be said to be a detection unit that detects a load of the electric blower 14 (for example, clogging of the filter 13 b). From another point of view, when the head 30 is lifted from the ground and the load on the electric blower 14 is reduced, the current value detected by the electric blower current detecting unit 41 is reduced. Therefore, electric blower current detection unit 41 may be said to be a detection unit that detects the state of head 30 with respect to the ground (e.g., the top and bottom of head 30).

When the electric vacuum cleaner 100 is connected to an external commercial power supply (e.g., a household outlet) for charging, the power supply detection unit 42 detects that the electric vacuum cleaner is connected to the commercial power supply and whether the ac frequency of the commercial power supply is 50Hz or 60 Hz.

The remaining battery level detecting unit 43 detects the remaining capacity of the battery 15 based on the voltage of the battery 15. The battery temperature sensor 44 is provided adjacent to the battery 15 and detects the temperature of the battery 15. The temperature of the battery 15 immediately after the start of the operation of the electric vacuum cleaner 100 is substantially the same as the temperature (room temperature) of the environment around the electric vacuum cleaner 100. Therefore, the battery temperature sensor 44 may be said to be a detection unit that detects the room temperature of the house of the user U. In addition, the electric vacuum cleaner 100 may have a sensor dedicated to detecting the room temperature, which is different from the battery temperature sensor 44.

The main body acceleration sensor 45 is provided in the cleaner main body 10 and detects acceleration of the cleaner main body 10. The main body gyro sensor 46 is provided in the cleaner main body 10 and detects an angular velocity of the cleaner main body 10.

The grip force detector 47 includes a pressure-sensitive sensor provided in the handle 12, and detects a force (grip force) of the user gripping the handle 12 and/or a position (grip position) of the handle 12 gripped by the user U. Here, generally, the gripping force of a male is larger than that of a female in most cases. Further, the grip position is an element showing a habit different depending on the user U.

The dust sensor 48 is provided in, for example, an intake air passage of the cleaner body 10. The dust sensor 48 includes, for example, a light emitting portion and a light receiving portion that are arranged separately on the left and right inner surfaces of the intake air passage, and detects dust that has been sucked in by blocking light that travels from the light emitting portion toward the light receiving portion with dust that has passed through the intake air passage. For example, the debris sensor 48 determines that debris is being sucked while light from the light emitting section toward the light receiving section is blocked. On the other hand, the debris sensor 48 determines that debris is not being sucked while light from the light emitting section toward the light receiving section is not blocked. The debris sensor 48 (or the control unit 80 of the electric vacuum cleaner 100, or the information conversion unit 202 of the server 200 described later) measures the amount of debris sucked based on the ratio of the time for which debris is sucked to the time for which debris is not sucked (in other words, the time for which debris is sucked during the operation time).

The camera 49 is provided, for example, in the dust collecting device 13 of the cleaner body 10, and photographs the dust accumulated in the dust collecting device 13. Alternatively, the camera 49 may be provided on the head 30 to photograph the garbage (e.g., garbage immediately before being sucked by the head 30) present in front of the head 30. The camera 49 may be provided in the air intake passage of the cleaner body 10 to photograph the dust sucked by the vacuum cleaner 100. The camera 49 is a detection unit that detects the type of garbage. The phrase "the type of the garbage detected by the camera 49" means that, for example, the type of the garbage is determined by performing image recognition (for example, pattern matching or image recognition using a neural network) by the control unit 80 of the electric vacuum cleaner 100 or the information conversion unit 202 of the server 200 described later on the captured image data captured by the camera 49.

The dust collection device detection switch 50 is provided at a position adjacent to the dust collection device 13, and detects a state of attachment/detachment of the dust collection device 13 to/from the cleaner body 10. The air blowing accessory detection switch 51 is provided at a position adjacent to the air blowing accessory 18 when the air blowing accessory 18 is attached to the cleaner body 10, and detects an attachment state of the air blowing accessory 18 to the cleaner body 10.

The brush motor current detection unit 61 includes a shunt resistor and the like, and detects a current value of the current flowing from the battery 15 to the brush motor 34. The current value of the current flowing to the brush motor 34 is proportional to the load of the brush motor 34. For example, when the floor surface is a carpet and the load of the electric blower 14 is increased, the current value detected by the brush motor 34 is increased. Therefore, the brush motor current detection unit 61 can be said to be a detection unit that detects the type of floor (floor/floor mat/carpet, etc.).

The encoder 62 is provided on the rotary brush 33 (or the brush motor 34) and detects the rotational speed of the rotary brush 33 (or the brush motor 34). For example, when the floor surface is a carpet and the rotation speed of the rotary brush 33 is decreased, the rotation speed detected by the encoder 62 is decreased. Therefore, the encoder 62 can also be said to be a detection section that detects the floor type (floor/mat/carpet, etc.). The detection unit for detecting the floor type may be a detection unit that irradiates light to the floor surface and detects the floor type based on the characteristics of the reflected light, instead of the brush motor current detection unit 61 or the encoder 62, or in addition to the brush motor current detection unit 61 or the encoder 62.

The head acceleration sensor 63 is provided in the head 30 and detects the acceleration of the head 30. The head gyro sensor 64 is provided in the head 30 and detects an angular velocity of the head 30.

The illuminance sensor 65 is provided in the head 30, and detects that the illuminance is equal to or less than a predetermined amount when the head 30 is inserted into a dark place (under a bed or a sofa, or a gap in furniture). When the illuminance sensor 65 detects that the illuminance is equal to or less than the predetermined amount, the control unit 80, which will be described later, turns on the lamp 35 to illuminate a dark place.

The extension pipe angle sensor 66 is provided in the connection pipe 32 of the head 30, and detects an angle (angle α in fig. 2) of the extension pipe 20 with respect to the head 30. For example, when the user using the electric vacuum cleaner 100 is tall, the angle of the extension pipe 20 with respect to the head 30 becomes large. On the other hand, when the user using the electric vacuum cleaner 100 is low in height, the angle of the extension pipe 20 with respect to the head 30 becomes small. Therefore, the extension pipe angle sensor 66 may be said to be a detection unit that detects the height of the user. Here, the height of a male is generally higher than that of a female in many cases.

The accessory detection switch 67 is provided at the second end 20b of the extension pipe 20 and/or the extension pipe connection part 11a of the cleaner body 10, and detects the attachment state of the accessory 36 to the second end 20b of the extension pipe 20 or the extension pipe connection part 11a of the cleaner body 10. Further, the control unit 80, which will be described later, detects the state of current supply to the object in a state where the attachment of the object is detected by the accessory detection switch 67. When the attached object is energized, the control unit 80 determines that the object is the head 30. On the other hand, when the attached object is not energized, the control unit 80 determines that the object is the accessory 36. In the following description, the "detection result of the accessory detection switch 67" is used to include the detection result of the energization state by the control unit 80. Further, the accessory detection switch 67 can also detect the type of the accessory 36 (the gap nozzle 36A, the round brush 36B, or the bed cleaning head 36C).

Next, the control unit 80 will be explained. The control unit 80 includes, for example, an operation receiving unit 81, a motor control unit 82, an information recording unit 83, and an information output unit 84. These functional units are realized by executing a program (software) by a hardware processor such as a CPU (Central Processing Unit) mounted in the electric vacuum cleaner 100. However, all or a part of these functional units may be realized by hardware (Circuit units, 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 realized by cooperation of software and hardware.

Further, the control unit 80 includes a storage unit 85. The storage unit 85 is implemented by, for example, a RAM (Random Access Memory), a ROM (Read Only Memory), an HDD (Hard Disk Drive), a flash Memory, or a combination of a plurality of these. The storage unit 85 stores identification information I1 and status information I2.

The operation receiving unit 81 receives an operation of the electric vacuum cleaner 100 by the user U in response to an operation of the operation knob 12a of the electric vacuum cleaner 100 by the user U. The operation of the user U received by the operation receiving unit 81 is, for example, turning on/off of the power supply of the electric vacuum cleaner 100, an operation mode (weak/strong/automatic, etc.) of the electric blower 14, and turning on/off of the rotation of the rotary brush 33.

The motor control unit 82 supplies electric power from the battery 15 to the electric blower 14 in response to the operation of the user U received by the operation receiving unit 81, and drives the electric blower 14. Similarly, the motor control unit 82 supplies electric power from the battery 15 to the brush motor 34 to drive the brush motor 34 in accordance with the operation of the user U received by the operation receiving unit 81.

The information recording unit 83 refers to, for example, a control command output from the motor control unit 82 and a timer, not shown, and adds the state information I2 of the storage unit 85 to the operation state of the electric vacuum cleaner 100 in association with date and time information. The "operation state of the electric vacuum cleaner 100" includes, for example, a state in which the power supply of the electric vacuum cleaner 100 is turned on/off, an operation mode of the electric blower 14, and the like. The date and time information includes information indicating the day of the week and the time of day. Further, the information recording unit 83 associates the detection result of the sensor group SU with date and time information, and adds the result to the state information I2 in the storage unit 85. The detection result of the sensor group SU is the detection result of the above-described various sensors and switches. The information may be recorded as raw data or in a state where necessary calculation (processing) is performed.

The information output unit 84 transmits the status information I2 stored in the storage unit 85 to the server 200 via the communication module 17. 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 85. The identification information I1 is an appliance ID assigned to each electric vacuum cleaner 100 in order to identify the electric vacuum cleaner 100. The state information I2 and the identification information I1 are examples of data transmitted from the electric vacuum cleaner 100 to the server 200. Hereinafter, the state information I2 and the identification information I1 are collectively referred to as "data D".

Instead of the above configuration, the information recording unit 83 may be omitted, and the information output unit 84 may transmit the operation state of the vacuum cleaner 100 and the detection result of the sensor group SU to the server 200 in real time. In this case, the server 200 may be configured to correlate the operation state of the electric vacuum cleaner 100, the detection result of the sensor group SU, and the date and time information.

Fig. 4 is a diagram conceptually showing a part of the data D transmitted from the electric vacuum cleaner 100. Fig. 4 shows an example of data D obtained at both the husband of the office worker and the wife of the housewife. Note that "operating time of the electric vacuum cleaner" in the drawing is actually an index calculated by the server 200 in the present embodiment, but is shown in fig. 4 for ease of illustration.

As can be seen from data D shown in fig. 4, cleaning was performed on monday afternoon, wednesday afternoon, friday afternoon, which are weekdays, and sunday morning, which is a holiday. Further, it was found that the height of the user who cleaned on sunday morning was higher than the height of the user who cleaned on monday afternoon, wednesday afternoon, and friday afternoon, and that the grip of the user who cleaned on sunday afternoon was higher than the grip of the user who cleaned on monday afternoon, wednesday afternoon, and friday afternoon. By analyzing these pieces of information, it can be estimated that there are at least 2 family members including males and females, and there is a high possibility that there are males who take a break on saturday and females who are not-in-person or are part-time.

< 3. Server >

Fig. 5 is a block diagram showing the configuration of the server 200. The server 200 includes, for example, an information acquisition unit 201, an information conversion unit 202, a learning unit 203, a user attribute estimation unit 204, an information recording unit 205, and an information output unit 206. These functional units are realized by executing a program (software) by a hardware processor such as a CPU included in the server 200. However, all or a part of these functional units may be realized by hardware (circuit unit; including circuit) such as ASIC, PLD, or FPGA, or may be realized by cooperation of software and hardware.

Further, the server 200 has a storage unit 207. The storage section 207 is realized by, for example, a RAM, a ROM, an HDD, a flash memory, or a combination of a plurality of them. The storage unit 207 stores the accumulation information I11, the user registration information I12, the estimation model (learning model) M, and the user attribute information I13.

The information acquisition unit 201 acquires (obtains) data D transmitted from the electric vacuum cleaner 100. When learning the estimation model M, the information acquisition unit 201 collects data D from a plurality of electric vacuum cleaners 100 used in a plurality of households. The information acquisition unit 201 accumulates the acquired data D in the storage unit 207 as accumulation information I11. The information acquisition unit 201 accumulates data D for a predetermined period (for example, 3 months) for each electric vacuum cleaner 100, for example. The information acquisition unit 201 is an example of an "acquisition unit".

The information conversion unit 202 generates input information to be input to an estimation model M described later, based on the accumulation information I11 in which the data D of each electric vacuum cleaner 100 is accumulated. The estimation model M is a model for estimating attributes of the user U (the category of the family (for example, the scale of the family), the presence or absence of children, the presence or absence of pets, sex, age, employment pattern, the presence or absence of marital marriage, the house type (for example, the size of the house), the floor type of a room, the living area, and the like).

(a. input information for estimating attribute of family)

The information conversion unit 202 generates, for example, 1 or more pieces of information from the information I11, which is input to the estimation model M for estimating the attribute of the family, among information on the operation time of the electric vacuum cleaner 100, information on the time until a predetermined amount of dust is accumulated in the electric vacuum cleaner 100, information on the time until the operation of the electric vacuum cleaner 100 is resumed after the operation is ended, information on the number of times the power of the electric vacuum cleaner 100 is turned on/off, information on the number of times the head 30 of the electric vacuum cleaner 100 is lifted, information on the day and hour period in which the electric vacuum cleaner 100 is used, information on the angle of the extension pipe 20 of the electric vacuum cleaner 100 with respect to the head 30, information on the gripping force or the gripping position of the handle 12 by the user U of the electric vacuum cleaner 100, and information on the number of electric vacuum cleaners 100 in the same house (hereinafter, referred to as "information on" 1 or more pieces of information "input to the estimation model M for estimating the attribute of the family (hereinafter, referred to as" information on the attribute of the family " Input information for estimation of co-living family). The number of people in the same household can be regarded as the number of users U who use the electric vacuum cleaner 100 (the number of users).

The "information on the operation time" is an average value or a maximum value of the operation time of the electric vacuum cleaner 100 in each cleaning 1 time, an integrated value of the operation time of the electric vacuum cleaner 100 in the predetermined period (for example, 3 months), or the like. The "cleaning at 1 time" is calculated as the same cleaning at 1 time if the time until the power supply is turned on next is within a predetermined time (for example, within 10 minutes) even when the power supply of the electric vacuum cleaner 100 is turned off. The "operation time" is a time during which the power source of the electric vacuum cleaner 100 is turned on (i.e., a time during which the electric blower 14 is rotated). The average value, the maximum value, or the integrated value is calculated based on, for example, "the operation state of the electric vacuum cleaner" and date and time information included in the data D. Here, in general, the larger the number of people who live in the same house, the larger the house or the house with the larger number of rooms. The average value, the maximum value, or the integrated value described above tends to be larger as the house is larger and/or the number of rooms is larger.

The "information on the time until the dust is accumulated by the predetermined amount" is an average value of a time interval (see T1 in fig. 4) from when the dust collecting device detection switch 50 detects the start of removal of the dust collecting device 13 at a certain point in time to when the same removal is detected next, an average value of a time from when (for example, when the dust collecting device detection switch 50 detects the removal of the dust collecting device 13) until the dust detected by the dust sensor 48 reaches the predetermined amount, or the like. These average values are calculated from, for example, the detection result of the dust collecting device detection switch 50, the detection result of the dust sensor 48, the date and time information, and the like included in the data D. The removal of the dust collecting device 13 from the cleaner body 10 can be considered as the time when the dust is accumulated in the dust collecting device 13 and the accumulated dust is discarded by the user U. Here, generally, the larger the number of people who live in a house, the larger the amount of garbage generated. The average value is shorter as the amount of generated garbage is larger.

"information on the time from the end of the operation to the restart of the operation" is an average value of the time interval (see T2 in fig. 4) from the end of a certain cleaning to the start of the next cleaning, and the like. The average value is calculated from "the operating state of the electric vacuum cleaner" and date and time information included in the data D, for example. Here, generally, the larger the number of people who live in a house, the larger the amount of generated garbage, and the more frequent the cleaning. Further, as the number of people living in the house increases, the number of times of cleaning is performed at a timing desired by each individual person also increases, and the frequency of cleaning increases. The average value is shorter as the frequency of cleaning increases. The "information on the time from the end of the operation to the restart of the operation" can be information for estimating the presence of the user U having a tendency that the cleaning time is shorter 1 time or the presence of the user U having a tendency that the cleaning time is longer 1 time. In other words, "information on the time from the end of the operation to the restart of the operation" is information useful for estimating the number of people using the electric vacuum cleaner 100.

The "information on the number of times of turning on/off the power supply" refers to an average value or a maximum value of the number of times of turning on/off the power supply of the electric vacuum cleaner 100 every 1 cleaning, an integrated value of the number of times of turning on/off the power supply of the electric vacuum cleaner 100 in the predetermined period (for example, 3 months), or the like. These average values, maximum values, or integrated values are calculated from "the operation state of the electric vacuum cleaner" and date and time information included in the data D, for example. Here, in general, the number of furniture and the like increases as the number of households increases, and the number of rooms increases, so that the number of times of turning on/off the power of the electric vacuum cleaner 100 increases. The "information on the number of times of power supply on/off" can be information for estimating the presence of the user U having a tendency that the cleaning time is short 1 time or the presence of the user U having a tendency that the cleaning time is long 1 time (or the presence of the user U frequently stopping the power supply or the presence of the user U not frequently stopping the power supply). In other words, "information on the number of times the power supply is turned on/off" is information useful for estimating the number of people using the electric vacuum cleaner 100.

The "number of times the head is lifted" is an average value or a maximum value of the number of times the head 30 is lifted every 1 cleaning, an integrated value of the number of times the head 30 is lifted in the predetermined period (for example, 3 months), or the like. These average values, maximum values, or integrated values are calculated from, for example, the detection results of the electric blower current detection unit 41, the detection results of the head acceleration sensor 63, the detection results of the head gyro sensor 64, date and time information, and the like included in the data D. Here, in general, the more the number of households, the more furniture and the like, the more rooms, and the more the house type including stairs, and therefore, the number of times the head 30 is lifted up increases.

The "information on the used day and time period" includes, for example, information indicating whether the week in which the electric vacuum cleaner 100 is used is monday through friday or saturday, sunday, and holiday, and information indicating which of morning, day, and night the time period in which the electric vacuum cleaner 100 is used is. In addition, the "information on the time zone" in the present specification may be information indicating the time itself. These pieces of information are derived from "the operating state of the electric vacuum cleaner" and date and time information included in the data D, for example. Here, generally, the larger the number of people who live in a family, the more the number of cases including a professional, a non-employment senior citizen, and a student. In the case of a professional woman, a non-employment elderly person, or a student, there are many opportunities to perform cleaning in the morning and daytime of a workday. In other words, the week and the period of time in which the electric vacuum cleaner 100 is used have different tendencies depending on whether the user U is a house-specific task, a co-working task, or a single-person living alone. That is, "information on the day of the week and the period of use" is information useful for estimating the number of people using the electric vacuum cleaner 100.

The "information on the angle of the extension pipe with respect to the head" is, for example, information indicating whether or not the difference between the average value of the angle of the extension pipe 20 with respect to the head 30 in a certain cleaning and the average value of the angle of the extension pipe 20 with respect to the head 30 in other cleaning exceeds a predetermined amount. This information is derived from, for example, the detection result of the extension pipe angle sensor 66 and the date and time information included in the data D. Here, in general, if the number of people who live in a family is 2 or more, the possibility of including males and females is high. When men and women are included in the family, the angle of the extension tube 20 with respect to the head 30 may be different by more than a predetermined amount. That is, "information on the angle of the extension pipe with respect to the head" is information useful for estimating the number of people using the electric vacuum cleaner 100.

The "information on the user's grip on the handle" is, for example, information indicating whether or not the difference between the average value (or the grip position) of the user's grip in a certain cleaning and the average value (or the grip position) of the user's grip in another cleaning exceeds a predetermined amount. This information is derived from, for example, the detection result of the grasping force detecting unit 47 and the date and time information included in the data D. Here, in general, if the number of people in the family is 2 or more, the possibility that men and women are included in the family is high. When a male and a female are included in the family, the difference in gripping force of the user may exceed a predetermined amount. Further, if the number of people in the same household is 2 or more, the possibility that the user who grips the handle 12 at a different grip position exists becomes high. That is, "information on the user's grip on the handle" is information useful for estimating the number of users of the electric vacuum cleaner 100.

The "information on the number of electric vacuum cleaners in the same house" is information indicating whether or not there are 2 or more electric vacuum cleaners 100 in the house of the user U, for example. This information is derived from, for example, identification information I1 (device ID) of the electric vacuum cleaner 100 included in the data D and user registration information I12 stored in the storage unit 207. Here, in general, if the number of the electric vacuum cleaners 100 is 2 or more, there is a high possibility that the preference for the type of the electric vacuum cleaner 100 (the type such as a stick/pot/floor cleaning robot, the type such as a suction type-oriented lightweight type), differs depending on a plurality of people living together. In other words, when there are 2 or more electric vacuum cleaners 100, there is a high possibility that the number of people in the same house is 2 or more. That is, "information on the number of electric vacuum cleaners in the same house" is information useful for estimating the number of users of the electric vacuum cleaner 100.

Here, the number of persons who live in the house (or the number of persons who use the electric vacuum cleaner 100) is an attribute indicating the home configuration of the user U. Further, by adding the number of persons in the same house (or the number of persons using the electric vacuum cleaner 100) and the presence or absence of children and/or attributes regarding age, which will be described later, attributes indicating a more detailed house structure can be estimated.

For example, when it is estimated that the user U of the electric vacuum cleaner 100 is 1 person, the home structure of the user U can be considered as a single family (single family). For example, when it is estimated that the number of people who live at home is 2 and the age group is a fellow person, the family structure of the user U can be considered as a couple-only family.

For example, in a case where it is estimated that the number of persons who live in the family is a plurality of persons and includes children and adults, the family structure of the user U can be considered as a family of parents and children (a family of two generations in the same hall, a child-bearing age group). In this case, in order to estimate the presence or absence of a child, the "input information for estimating a family of a living person" may include information such as "input information for estimating a child" described later, "input information for estimating an age," and "input information for estimating a employment mode.

For example, when it is estimated that adults include adults of childbearing age and elderly adults, the family structure of the user U can be considered as a family of a three-generation lobby. In this case, in order to estimate the age group of an adult, the "input information for estimating a family of a living being" may include information such as "input information for estimating a child" described later, "input information for estimating an age", and "input information for estimating a employment form".

Fig. 6 is a diagram showing an example of the content of the user registration information I12. In the user registration information I12, a user ID, an apparatus ID of the electric vacuum cleaner 100, model information of the electric vacuum cleaner 100, and a model type of the electric vacuum cleaner 100 are registered in association with each other. The user registration information I12 is obtained by, for example, registration by the user at the time of product purchase. The information conversion unit 202 refers to the user ID based on the identification information I1 (device ID) included in the data D received from the electric vacuum cleaner 100, and acquires information indicating the number of electric vacuum cleaners 100 registered in association with the same user ID.

(b. input information for estimating presence or absence of child or pet)

The description is continued with reference back to fig. 5. For example, the information conversion unit 202 generates information regarding the type of garbage sucked by the electric vacuum cleaner 100 based on the accumulated information I11 as input information (hereinafter referred to as "input information for estimation of children") to be input to the estimation model M for estimating the presence or absence of children and/or pets of the user U. For example, the information conversion unit 202 performs pattern matching on the captured data captured by the camera 49 or image recognition using a neural network or the like, thereby generating information on the type of garbage. The "information on the category of garbage" is information indicating whether or not a specific category of garbage exists in excess of a predetermined amount. Here, in general, when children and children are present in the same household, the amount of sebum-containing garbage increases. In addition, when a pet is present, litter containing hair of the pet increases. "sebum-containing litter" and/or "litter of pets" are examples of the particular types of litter described above.

(c. input information for estimating gender)

For example, the information conversion unit 202 generates, as input information (hereinafter referred to as "sex estimation input information") to be input to the estimation model M for estimating the sex of the user U, 1 or more of information on the angle of the extension pipe 20 of the electric vacuum cleaner 100 with respect to the head 30, information on the gripping force of the user U of the electric vacuum cleaner 100 on the handle 12, information on the acceleration acting on the electric vacuum cleaner 100, information on the number of times the filter of the electric vacuum cleaner 100 is clogged, and information on the type of garbage sucked by the electric vacuum cleaner 100, based on the accumulated information I11. In addition, "information on the angle of the extension pipe with respect to the head", "information on the gripping force of the user on the handle", and "information on the type of the attracted trash" are as described above. Here, in general, when the user U is a woman, the garbage often contains long hair.

The "information on acceleration" is an average value, a maximum value, or the like of the acceleration applied to the cleaner body 10 for the predetermined period (for example, 3 months). These average values and maximum values are calculated from the detection results of the subject acceleration sensor 45 included in the data D, for example. Here, in general, when the user U is a male, the acceleration acting on the cleaner body 10 becomes higher than when the user U is a female.

The "information on the number of times of filter clogging" is, for example, the number of times that the load of the electric blower 14 becomes equal to or more than a predetermined value and the filter clogging is reported to the user U (for example, a not-shown warning lamp is turned on by the control of the control unit 80) from a certain time (for example, a time when the removal of the dust collecting device 13 is detected by the dust collecting device detection switch 50) in the predetermined period (for example, 3 months). The number of times is calculated from, for example, the detection result of the electric blower current detection unit 41 included in the data D and the date and time information. Here, in general, when the user U is a female, the number of times the filter is clogged increases because the garbage contains long hairs increases compared to when the user U is a male.

(d. input information for estimating age)

For example, the information conversion unit 202 derives information indicating the model of the electric vacuum cleaner 100 from the accumulation information I11 as input information (hereinafter referred to as "input information for age estimation") to be input to the estimation model M for estimating the age of the user U. This information is derived from, for example, identification information I1 (device ID) of the electric vacuum cleaner 100 included in the data D and user registration information I12 stored in the storage unit 207. Here, generally, the elderly tend to prefer a lighter model than a model in which suction is important. In addition, elderly people tend to prefer a canister over a stick. In addition, elderly people tend to prefer a filter type (dust collection paper bag type) as a dust collection method rather than a centrifugal separation type. Further, the human model may be different depending on each age group such as 20 age group, 30 age group, and 40 age group. The information indicating the model of the electric vacuum cleaner 100 is an example of "information that can specify the model".

(e. input information for estimating employment mode)

For example, the information conversion unit 202 generates information on the day of the week and the period of time during which the electric vacuum cleaner 100 is used, as input information (hereinafter referred to as "input information for estimating the employment mode") to be input to the estimation model M for estimating the employment mode (full-time/part-time/non-employment) of the user U, based on the accumulated information I11. The "information on the week and the period used" is as described above.

(f. input information for estimating house type)

For example, the information conversion unit 202 generates, as input information (hereinafter referred to as "home type estimation input information") to be input to the estimation model M for estimating the home type of the user U, 1 or more pieces of information among information relating to the operation time of the electric vacuum cleaner 100, information relating to the number of reconnections of the electric vacuum cleaner 100, which is a wired type, to an external power supply (commercial power supply), information relating to accessories attached to and detached from the electric vacuum cleaner 100, information relating to the lighting state of a lamp provided on the head of the electric vacuum cleaner 100, and information relating to the number of electric vacuum cleaners 100 in the same home, based on the accumulated information I11. The "information on the operation time" and the "information on the number of electric vacuum cleaners in the same house" are as described above. Here, in general, when 2 or more electric vacuum cleaners 100 are provided, there is a high possibility that the house is large and the number of rooms is large.

The "information on the number of reconnection times to the external power supply" is an average value or a maximum value of the number of reconnection times to the external power supply per 1 cleaning, an integrated value of the number of reconnection times in the above-mentioned predetermined period (for example, 3 months), or the like. The "number of reconnection to an external power supply" is, for example, the number of times the plug of the electric vacuum cleaner 100 is inserted into and removed from a household outlet. The number of times is calculated from, for example, the detection result of the power supply detecting unit 42 and the date and time information included in the data D. Here, generally, the larger the room is and the larger the number of rooms is, the larger the number of reconnection times is.

The "information on the attached/detached accessory" is information indicating the number of times the accessory 36 or the air blowing accessory 18 is attached during the predetermined period (for example, 3 months). The attachment of the accessories 36 or the air supply accessories 18 is derived from, for example, the detection result of the accessory detection switch 67, the detection result of the air supply accessory detection switch 51, the date and time information, and the like included in the data D. Here, in general, the larger the house is, the more places to be cleaned with accessories 36 or air blowing accessories 18 increase in many cases.

The "information on the lighting state of the lamp" is an average value or a maximum value of the number of lighting times of the lamp 35 in every 1 cleaning, an integrated value of the number of lighting times of the lamp 35 in the above-described predetermined period (for example, 3 months), or the like. These average values, maximum values, or integrated values are calculated from, for example, the detection results of the illuminance sensor 65 and the date and time information included in the data D. Here, in general, the larger the house is, the more furniture and the like are, and the more dark cleaning places need to be lighted up by the light 35 are increased in many cases.

(g. input information for estimating ground type)

For example, the information conversion unit 202 generates, as input information (hereinafter referred to as "input information for estimating the floor type") to be input to the estimation model M for estimating the floor type of the room, 1 or more pieces of information among information on the load state of the brush motor 34 of the electric vacuum cleaner 100, information on the acceleration acting on the head 30 of the electric vacuum cleaner 100, and information on the detection result of the debris sensor 48, based on the accumulation information I11.

The "information on the load state of the brush motor" is information indicating a temporal change in the load state of the brush motor 34, and the like. This information is derived from, for example, the detection result of the brushed motor current detection unit 61 and the date and time information included in the data D. Here, in general, in a carpet, a floor mat, or a floor, the load applied to the brush motor 34 is highest at the carpet, the floor mat is next highest, and the floor is lowest.

The "information on the acceleration acting on the head" is information indicating a temporal change in the acceleration acting on the head 30, and the like. This information is derived from, for example, the detection result of the head acceleration sensor 63 and the date and time information included in the data D. Here, in general, in a carpet, a floor mat, a floor, the resistance against the head 30 is highest at the carpet, the floor mat is next highest, and the floor is lowest. Therefore, the head 30 moves smoothly on the floor, and the acceleration of the head 30 tends to increase. On the other hand, the head 30 is difficult to move smoothly on the carpet, and the acceleration of the head 30 is likely to be small.

The "information on the detection result of the dust sensor" is, for example, information indicating the time at which the dust sensor 48 detects dust in time series. This information is derived from, for example, the detection result of the garbage sensor 48 and the date and time information included in the data D. Here, generally, garbage is obtained over the entire carpet, and on the other hand, on the floor, garbage is easily collected in the corner of a room. Therefore, in the floor cleaning, the time when the garbage is not sufficiently obtained and the time when the garbage is intensively obtained are represented in the detection result of the garbage sensor 48.

(h. input information for estimating residential area)

For example, the information conversion unit 202 derives 1 or more pieces of information among the information on the temperature detected by the electric vacuum cleaner 100 and the information on the frequency of the external power supply connected to the electric vacuum cleaner 100, as input information (hereinafter referred to as "living area estimation input information") input to the estimation model M for estimating the living area of the user U, based on the storage information I11.

The "information on temperature" is information indicating the temperature of the battery 15 immediately after the start of the operation of the electric vacuum cleaner 100 every 1 cleaning, and the like. This information is derived from, for example, the detection result of the battery temperature sensor 44 and the date and time information included in the data D. As described above, the temperature of the battery 15 immediately after the start of the operation of the electric vacuum cleaner 100 can be regarded as being substantially the same as the room temperature. Here, the server 200 may acquire the air temperature information of each place from the server of the weather hall, and use the result of comparison between the acquired air temperature information of each place and the detection result of the battery temperature sensor 44 as the living area estimation input information. With this configuration, the area where the house of the user U is located can be estimated from the comparison information between the air temperature and the room temperature in each area.

The "information on the frequency of the external power supply" is information indicating whether the ac frequency of the external power supply connected to the electric vacuum cleaner 100 is 50Hz or 60Hz, or the like. This information is derived from, for example, the detection result of the power supply detecting unit 42 included in the data D. Here, the frequency of the commercial power supply in east japan is 50Hz, and the frequency of the commercial power supply in west japan is 60 Hz.

Next, the learning unit 203 will be explained. The learning unit 203 generates the estimation model M by machine learning based on the various input information described above. The estimation model M learns the estimation result of the attribute of the user U who outputs the electric vacuum cleaner 100 when the information on the electric vacuum cleaner 100 is input.

In the present embodiment, the learning unit 203 generates an estimation model MA for estimating attributes related to the family (for example, the scale of the family or the family structure), an estimation model MB for estimating attributes related to the presence or absence of children or pets, an estimation model MC for estimating attributes related to the gender, an estimation model MD for estimating attributes related to the age, an estimation model ME for estimating attributes related to the employment pattern, an estimation model MF for estimating attributes related to the house (for example, the house type), an estimation model MG for estimating attributes related to the floor type of the room, and an estimation model MH for estimating attributes related to the living area, as estimation models M for estimating attributes of the user U. In the present specification, "learning" may also refer to either unsupervised learning or supervised learning. Hereinafter, an example of generating the estimation model M by unsupervised learning and an example of generating the estimation model M by supervised learning will be described. The estimation model M is not limited to the neural network, and may be a model based on a mathematical expression and a threshold value.

First, unsupervised learning will be explained. For example, the learning unit 203 generates the estimation model M by clustering the various input information described above. The clustering method is, for example, the K-means method, but other methods may be employed.

Fig. 7 is a diagram showing an example of the estimation model M obtained by unsupervised learning. Specifically, fig. 7 shows an example of an estimation model MA for estimating an attribute related to the family of the user U. In the example shown in fig. 7, the "information on the operation time" and the "information on the time until garbage accumulation" obtained by the information conversion unit 202 are given as 2 pieces of input information (parameters X1 and X2), and the number of clusters is set to 3 (single family, core family, and large family). That is, the first group G1, which has a relatively short operation time and a relatively long time to accumulate garbage, is classified as a single family, the third group G3, which has a relatively long operation time and a relatively short time to accumulate garbage, is classified as a large family, and the second group G2 located therebetween is classified as a core family. In the present specification, the term "family" is used in a sense of expanding the family, with respect to the expression of the core family. A single person may also be considered a "single family". The core family may also be considered as a "generation 2 co-located family". Big family can also be regarded as "family in 3 generations".

As described above, the information processing apparatus performs clustering based on 1 or more pieces of input information (for example, 2 or more pieces of input information) among the above-described information on the operation time of the electric vacuum cleaner 100, information on the time until a predetermined amount of dust is accumulated in the interior of the electric vacuum cleaner 100, information on the time from the end of the operation of the electric vacuum cleaner 100 to the restart of the operation, information on the number of times the power of the electric vacuum cleaner 100 is turned on/off, information on the number of times the head 30 of the electric vacuum cleaner 100 is lifted, information on the day and week in which the electric vacuum cleaner 100 is used, information on the angle of the extension pipe 20 with respect to the head 30 of the electric vacuum cleaner 100, information on the gripping force (or gripping position) of the user with respect to the handle 12 of the electric vacuum cleaner 100, and information on the number of electric vacuum cleaners 100 in the same house, thereby, an estimation model MA for estimating the attribute relating to the co-resident family of the user U is derived. Alternatively, the estimation model M may be derived by clustering 1 input information included in the various information, or may be derived by clustering 3 or more input information included in the various information.

Here, the user U includes a user who performs cleaning carefully and a user who performs cleaning roughly with priority given to time. Therefore, if attributes such as the number of people in a family and the size of a house are estimated only from information on the operation time of the electric vacuum cleaner 100, the estimation accuracy may not be easily improved. However, for example, by complementarily using 2 or more pieces of input information such as "the operation time of the electric vacuum cleaner 100" and "the information on the time until garbage is accumulated", it is possible to estimate that the user U is a type of user who performs cleaning carefully and the number of people in the same house is small (or the house is small) even when the operation time of the electric vacuum cleaner 100 is long and that the user U is a type of user who performs cleaning roughly with priority in time and the number of people in the same house is large (or the house is large) even when the operation time of the electric vacuum cleaner 100 is short. By using 2 or more (more specifically, 3 or more) pieces of input information in this way, the estimation accuracy can be further improved.

Several examples of the input information have been described above, but the input information is not limited to the above examples. The input information is information included in the data D received from the electric vacuum cleaner 100, and various information that cannot be described as a specific example can be appropriately used.

Next, other estimation models MB to MH will be described. By clustering the above-described information on the type of garbage sucked by the electric vacuum cleaner 100 as input information, an estimation model MB for estimating the attribute of the presence or absence of children or pets is derived. The number of clusters is set to 2 (presence or absence of children or pet, for example).

The estimation model MC for estimating the attribute of the sex is derived by clustering, as input information, information of 1 or more (for example, 2 or more) of the above-described information on the angle of the extension pipe 20 with respect to the head 30 of the electric vacuum cleaner 100, information on the gripping force of the user on the handle 12 of the electric vacuum cleaner 100, information on the acceleration acting on the electric vacuum cleaner 100, and information on the number of times the filter of the electric vacuum cleaner 100 is clogged. The number of clusters was set to 2 (male/female).

The information indicating the model of the electric vacuum cleaner 100 and the like are clustered as input information to derive an estimation model MD for estimating attributes related to age. The number of clusters is set to, for example, 3 (young person/child bearing age group/elderly).

The estimation model ME for estimating the attribute of the employment pattern is derived by clustering the information on the week and the period of time in which the electric vacuum cleaner 100 is used, as the input information. The number of clusters is set to, for example, 3 (full-time/part-time/non-employment).

The estimation model MF for estimating the attribute of the house is derived by clustering, as input information, information of 1 or more (for example, 2 or more) of the above-described information on the operation time of the electric vacuum cleaner 100, information on the number of reconnection times of the electric vacuum cleaner 100 as a wired type to an external power supply, information on accessories attached to and detached from the electric vacuum cleaner 100, information on the lighting state of a lamp provided on the head of the electric vacuum cleaner 100, and information on the number of electric vacuum cleaners 100 in the same house. The number of clusters is set to, for example, 3 (large-sized house/medium-sized house/small-sized house).

The estimation model MG for estimating the attribute of the floor type of the room is derived by clustering 1 or more (for example, 2 or more) pieces of information among the above-described information on the load state of the brush motor 34 of the electric vacuum cleaner 100, information on the acceleration acting on the head 30 of the electric vacuum cleaner 100, and information on the detection result of the debris sensor 48 as input information. The number of clusters is set to 3 (floor/mat/carpet), for example.

The estimation model MH for estimating the attribute of the residential area is derived by clustering 1 or more (for example, 2 or more) pieces of information such as the above-described information on the temperature detected by the electric vacuum cleaner 100 and the information on the frequency of the external power supply connected to the electric vacuum cleaner 100 as input information. The number of clusters is set to 9 (north sea/northeast/east china warfare/east/northeast/west/china/four country/kyushou) or 2 (east japan/west japan), for example.

On the other hand, fig. 8 is a diagram showing an example of the estimation model M used in supervised learning. The estimation model M used in supervised learning is composed of a neural network including an input layer, a hidden layer (intermediate layer), and an output layer. The estimation model M is learned by adjusting weighting coefficients between nodes included in the input layer, the hidden layer, and the output layer by deep learning using training data or the like. The training data is, for example, data in which the various input information collected from the electric vacuum cleaner 100 of the user who assists the questionnaire and the user who registers on the network (hereinafter referred to as "specific user") is associated with accurate data of the user attribute registered by the specific user through the questionnaire or registered on the network.

In the present embodiment, the output information of the estimation model M in the supervised learning corresponds to the classification of various clusters described in the unsupervised learning. For example, the estimation model MA for estimating the attribute relating to the family of the same house learns that: using, as input information, information of 1 or more (for example, 2 or more) of information on the operation time of the electric vacuum cleaner 100, information on the time until a predetermined amount of dust has accumulated in the interior of the electric vacuum cleaner 100, information on the time from the end of the operation of the electric vacuum cleaner 100 to the restart of the operation, information on the number of times the power supply of the electric vacuum cleaner 100 is turned on/off, information on the number of times the head 30 of the electric vacuum cleaner 100 is lifted, information on the day and time period in which the electric vacuum cleaner 100 is used, information on the angle of the extension pipe 20 with respect to the head 30 of the electric vacuum cleaner 100, information on the gripping force (or gripping position) of the handle 12 of the electric vacuum cleaner 100 by the user, and information on the number of the electric vacuum cleaners 100 in the same house, an estimation result indicating that the user is a single person, a core home, or a large home is output as the output information. Note that a part or all of the input information is not limited to the information calculated or derived by the information conversion unit 202, and may be data D itself (for example, time-series data indicating the detection results of the sensor group SU) received from the electric vacuum cleaner 100. This is also true for the other estimation models MB to MH.

The user attribute estimating unit 204 estimates the user attribute of the user U of the determination target cleaning machine 100 from the data D received from the electric vacuum cleaner 100 (hereinafter referred to as "determination target cleaning machine 100") as the determination target of the user attribute using the estimation model M obtained by the learning unit 203. Here, "estimation" includes not only the case of determining the most likely 1 attribute candidate but also the case of outputting the probabilities (for example, the single-person probability: 13%, the core-family probability: 65%, and the big-family probability: 22%) of the plurality of attribute candidates.

The user attribute estimating unit 204 inputs, to the estimation model M, input information based on the data D obtained from the determination target cleaning machine 100, and obtains an estimation result of the user attribute of the user U of the determination target cleaning machine 100 as output information of the estimation model M. In the present embodiment, the user attribute estimating unit 204 inputs the above-described input information for estimating the family, the input information for estimating children and the like, the input information for estimating the gender, the input information for estimating the age, the input information for estimating the employment mode, the input information for estimating the house type, the input information for estimating the ground type, and the input information for estimating the living area to the corresponding estimation models MA to MG as the input information based on the data D obtained from the determination target cleaning machine 100, and outputs the type of the family (for example, the scale or the family structure of the family), the presence of children, the presence of pets, the gender, the age, the employment type, the house type, the ground type, and the estimation result of the living area of the user U of the determination target cleaning machine 100 as the output information of the estimation models MA to MG.

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

Fig. 9 is a diagram showing an example of the contents of the user attribute information I13. In the user attribute information I13, for example, a user ID, a category of a family, the presence or absence of a child, the presence or absence of a pet (not shown), a sex, an age, a employment style, a house type (for example, the size of a house), a floor type (not shown), a living area (not shown), and the like are registered in association with each other.

The information output unit 206 transmits the user attribute information I13 obtained by the above-described processing to the terminal device 300. Thus, the user attribute information I13 can be used for product development and service provision.

< 4. flow of processing

Next, the flow of the processing will be described.

Fig. 10 is a diagram showing a flow of processing of the electric vacuum cleaner 100. First, the control unit 80 determines whether or not the power of the electric vacuum cleaner 100 is ON (ON) (S101). When the power of the electric vacuum cleaner 100 is OFF (OFF), the control unit 80 stands by until the power of the electric vacuum cleaner 100 is turned on.

On the other hand, when the power of the electric vacuum cleaner 100 is turned on (yes in S101), the control unit 80 transmits the detection result detected by the sensor group SU to the server 200 at a predetermined cycle or in real time (S102).

Next, the control unit 80 determines whether or not the power of the electric vacuum cleaner 100 is turned off (S103). When the power of the electric vacuum cleaner 100 is turned on (no in S103), the control unit 80 repeats the process of S102. On the other hand, when the power of the electric vacuum cleaner 100 is turned off (S103: YES), the control unit 80 ends the series of processing. The electric vacuum cleaner 100 repeats the above-described processing for a predetermined period of time (S101 to S103), for example.

Fig. 11 is a diagram showing a flow of processing of server 200. As a premise, data D transmitted from the electric vacuum cleaner 100 to the server 200 is acquired by the information acquisition unit 201 and stored as storage information I11.

First, the information conversion unit 202 derives the various input information described above from the accumulation information I11 (S201). Next, the user attribute estimation unit 204 obtains the estimation result of the user attribute as output information by inputting the various types of input information derived to the estimation models MA to MH, respectively (S202). Next, the information output unit 206 outputs the user attribute estimated by the user attribute estimation unit 204 to the terminal device 300.

< 5. Effect >

As a comparative example, it is conceivable to collect attribute information of a user by inputting information such as sex, age, and family composition or time of cleaning on a questionnaire or a network. However, in these cases, the user may have trouble inputting the information, and the information input by the user may not match the actual information. Further, it is difficult to confirm the detailed usage status to the user in the form of a questionnaire.

On the other hand, in the present embodiment, the information processing system 1 includes an information acquisition unit 201 that acquires data D transmitted from the electric vacuum cleaner 100, and a user attribute estimation unit 204 that estimates an attribute of the user U of the electric vacuum cleaner 100 from input information obtained from the data D acquired from the information acquisition unit 201 using the machine-learned model M. With this configuration, even if there is no input from the user U, the attribute of the user U can be estimated from the result of use of the electric vacuum cleaner 100 by the user U. This can reduce the burden of collecting attribute information of the user U.

(second embodiment)

Next, a second embodiment will be explained. The second embodiment is different from the first embodiment in that the electric vacuum cleaner 100A is a canister type. The configuration other than the following description is the same as that of the first embodiment.

Fig. 12 is a diagram showing a configuration of a server 200 according to the second embodiment. In the present embodiment, the electric vacuum cleaner 100A is a canister type electric vacuum cleaner. The electric vacuum cleaner 100A includes a main body landing detector 71 and a cable pull-out amount detector 72 as detectors included in the sensor group SU. The main body contact detection unit 71 includes, for example, a switch that contacts the floor surface when the electric vacuum cleaner 100A is positioned on the floor surface, and detects whether the electric vacuum cleaner 100A is in contact with the floor surface or floating. The cable drawing amount detection unit 72 includes, for example, an encoder that detects the amount of rotation of a reel around which the cable is wound, and detects the length of the cable drawn from the electric vacuum cleaner 100A (the amount of drawing of the cable). The detection results of the body grounding detection portion 71 and the cable pull-out amount detection portion 72 are transmitted to the server 200 as a part of the data D.

In the present embodiment, for example, the information conversion unit 202 includes information on the usage mode of the electric vacuum cleaner 100A as 1 piece of input information for estimating the sex. The "information on the usage pattern" is information indicating whether cleaning is performed in a state where the cleaner body 10 of the electric vacuum cleaner 100A is grounded on the floor surface or in a state where the cleaner body 10 of the electric vacuum cleaner 100A is lifted up from the floor surface by the user U, or the like. This information is derived from, for example, "the operating state of the electric vacuum cleaner 100A" included in the data D, the detection result of the body contact detecting unit 71 (or the detection result of the head acceleration sensor 63), date and time information, and the like. Here, in general, when the user U is a male, cleaning is often performed in a state where the cleaner body 10 of the electric vacuum cleaner 100A is lifted from the floor surface, as compared with a case where the user U is a female.

In the present embodiment, for example, the information conversion unit 202 includes information relating to the movement of the cleaner body 10 of the electric vacuum cleaner 100A as 1 of the input information for estimating the house type. The cleaner body 10 is a portion having wheels and placed on the floor. The cleaner body 10 is an example of a "main body". The "information on the movement of the cleaner body 10" is an average value or a maximum value of the distance traveled by the cleaner body 10 of the electric vacuum cleaner 100A per 1 cleaning, or an integrated value of the distance traveled by the cleaner body 10 of the electric vacuum cleaner 100A in the predetermined period (for example, 3 months). The average value, the maximum value, or the integrated value is calculated from, for example, the detection result of the subject acceleration sensor 45, the detection result of the subject gyro sensor 46, date and time information, and the like included in the data D. Here, in general, the movement of the head 30 of the canister type electric vacuum cleaner 100A is generally the same in both a small room and a large room, but in many cases, the moving distance of the cleaner body 10 is short in a small room and the moving distance of the cleaner body 10 is long in a large room.

In the present embodiment, for example, the information conversion unit 202 includes information on the amount of cable drawn out of the electric vacuum cleaner 100A as 1 of the input information for estimating the house type. The "information on the drawn-out amount of the cable" is an average value or a maximum value of the drawn-out amount of the cable of the electric vacuum cleaner 100A per 1 cleaning, or an integrated value of the drawn-out amount of the cable of the electric vacuum cleaner 100A in the predetermined period (for example, 3 months). The average value, the maximum value, or the integrated value is calculated from, for example, the detection result of the cable drawing amount detecting unit 72 and the date and time information included in the data D. Here, in general, the cable of the electric vacuum cleaner 100A is often drawn out less frequently when the room is small and is drawn out longer when the room is large.

In the present embodiment, the user attribute estimating unit 204 estimates the sex of the user U based on the information on the usage mode of the electric vacuum cleaner 100A. The user attribute estimation unit 204 may estimate the age of the user U based on information on the usage mode of the electric vacuum cleaner 100A. That is, the elderly tend to lift the cleaner body 10 of the electric vacuum cleaner 100A and perform cleaning less frequently than the young.

In the present embodiment, the user attribute estimation unit 204 estimates the house type (e.g., the size of a room) of the user U based on information on the movement of the cleaner body 10 of the electric vacuum cleaner 100A and/or information on the amount of cable drawn out of the electric vacuum cleaner 100A. The user attribute estimation unit 204 may estimate the attribute (the number of people) of the living family based on the information on the movement of the cleaner body 10 of the electric vacuum cleaner 100A and/or the information on the amount of cable drawn out of the electric vacuum cleaner 100A.

With such a configuration, as in the first embodiment, the load of collecting the attribute information of the user U can be reduced.

(third embodiment)

Next, a third embodiment will be explained. The third embodiment is different from the first embodiment in that the electric vacuum cleaner 100B is a sweeping robot. The configuration other than the following description is the same as that of the first embodiment.

Fig. 13 is a diagram showing a configuration of a server 200 according to the third embodiment. In the present embodiment, the electric vacuum cleaner 100B is a sweeping robot that travels automatically to collect waste. The electric vacuum cleaner 100B includes a map generation unit 75, a fall prevention sensor 76, and an illuminance sensor 65 as detection units included in the sensor group SU. The map generation unit 75 generates map information of the room based on the result of the automatic travel of the electric vacuum cleaner 100B. The drop prevention sensor 76 is a sensor for detecting whether there is no level difference (for example, a step) in front of the electric vacuum cleaner 100B in the traveling direction. The illuminance sensor 65 detects that the illuminance is equal to or less than a predetermined amount when the electric vacuum cleaner 100B enters below the bed, as in the first embodiment. The map information generated by the map generation unit 75, the detection result of the falling prevention sensor 76, and the detection result of the illuminance sensor 65 are transmitted to the server 200 as a part of the data D.

In the present embodiment, for example, the information conversion unit 202 includes information on the map generated by the map generation unit 75 of the electric vacuum cleaner 100B, and 1 of the input information for estimating a living family. The "information on the map" is information indicating the number of rooms in the house, the size of each room, and the like.

In the present embodiment, for example, the information conversion unit 202 includes information on the week and the time period in which the electric vacuum cleaner 100B is operated, and 1 of the input information for estimating the employment mode. This information is derived from, for example, "the operating state of the electric vacuum cleaner 100B" and date and time information included in the data D. Here, in general, the user U often performs cleaning by the electric vacuum cleaner 100B as a cleaning robot while the user U is out of the house. Therefore, the week and the period of operation of the electric vacuum cleaner 100B can be regarded as the time when the user U is not at home (the time in operation).

In the present embodiment, for example, the information conversion unit 202 includes information on the detection result of the drop prevention sensor 76 of the electric vacuum cleaner 100B as 1 of the input information for estimating the house type. The "information on the detection result of the drop prevention sensor 76" is information indicating whether or not there is a level difference that can be regarded as a step. In the case where there is a difference in height that can be regarded as a step, the possibility of the house being large increases.

In the present embodiment, for example, the information conversion unit 202 includes information relating to the detection result of the illuminance sensor 65 provided in the electric vacuum cleaner 100B as input information (hereinafter referred to as "input information for marital estimation") to be input to the estimation model M for estimating an attribute relating to the presence or absence of marital (marriage/nonmarriage). The "information on the detection result of the illuminance sensor 65" is information indicating the size of an area in which the illuminance is continuously equal to or less than a predetermined amount. The size of the area in which the illuminance is continuously equal to or less than the predetermined amount can be regarded as the size of the bed placed in the house of the user U. Therefore, if the size of the area in which the illuminance is continuously equal to or less than the predetermined amount is the size of the single bed, the possibility of losing the right is increased. In addition, when the number of areas in which the illuminance is continuously equal to or less than the predetermined amount is 2 or more, the possibility of marrying (the possibility of having 2 or more beds) is increased.

In the present embodiment, the user attribute estimation unit 204 estimates the type of the family (single family, core family, or major family) based on the information on the map generated by the map generation unit 75. The user attribute estimation unit 204 estimates attributes related to employment style based on information related to the week and the period of operation of the electric vacuum cleaner 100B.

In the present embodiment, the user attribute estimation unit 204 estimates the attribute relating to the house type from the information relating to the detection result of the drop prevention sensor 76. Further, the user attribute estimation unit 204 estimates an attribute relating to the presence or absence of marital based on the information relating to the detection result of the illuminance sensor 65.

According to at least one embodiment described above, by providing an acquisition unit that acquires data transmitted from an electric vacuum cleaner, and an estimation unit that estimates an attribute of a user of the electric vacuum cleaner from the data acquired by the acquisition unit using a model learned by a machine, it is possible to reduce a burden of collecting attribute information of the user.

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 may be implemented in various other forms, and various omissions, substitutions, and changes may be made without departing from the spirit of the invention. These embodiments and modifications are included in the scope and gist of the invention, and are also included in the invention described in the claims and the equivalent scope thereof.

Claims

1. An information processing system in which, among other things,

the disclosed device is provided with:

an acquisition unit that acquires data transmitted from the electric vacuum cleaner; and

an estimating unit that estimates an attribute of a user of the electric vacuum cleaner based on input information obtained from the data acquired by the acquiring unit, using a model learned as a result of output of an estimation result of the attribute of the user when information related to the electric vacuum cleaner is input.

2. The information processing system of claim 1,

the input information includes: information on an operation time of the electric vacuum cleaner, information on a time until a predetermined amount of dust is accumulated in the electric vacuum cleaner, information on a time from the end of the operation of the electric vacuum cleaner to the restart of the operation, information on the number of times the power of the electric vacuum cleaner is turned on/off, information on the number of times the head of the electric vacuum cleaner is lifted up, information on a day of the week and a time period in which the electric vacuum cleaner is used, information on an angle of an extension pipe with respect to the head of the electric vacuum cleaner, information on a gripping force or a gripping position of a handle of the electric vacuum cleaner by a user, information on the number of the electric vacuum cleaners in the same house, or information on a map generated by the electric vacuum cleaner as a cleaning robot,

the estimation unit estimates an attribute relating to a family as the attribute of the user.

3. The information processing system of claim 2,

the estimation unit estimates the attribute of the living home based on information on an operation time of the electric vacuum cleaner and information on a time until a predetermined amount of dust is accumulated in the electric vacuum cleaner.

4. The information processing system according to any one of claims 1 to 3,

the input information includes information on the type of the garbage sucked by the electric vacuum cleaner,

the estimation unit estimates an attribute relating to the presence or absence of a child or a pet as the attribute of the user.

5. The information processing system according to any one of claims 1 to 4,

the input information includes: information on an angle of an extension pipe with respect to a head of the electric vacuum cleaner, information on a gripping force of a user with respect to a handle of the electric vacuum cleaner, information on an acceleration acting on the electric vacuum cleaner, information on a number of times a filter of the electric vacuum cleaner is clogged, information on a type of dust sucked by the electric vacuum cleaner, or information on a usage mode of the canister type electric vacuum cleaner,

the estimation unit estimates an attribute relating to gender as the attribute of the user.

6. The information processing system according to any one of claims 1 to 5,

the input information includes information that can determine a model of the electric vacuum cleaner,

the estimating unit estimates an attribute relating to age as the attribute of the user.

7. The information processing system of any one of claims 1 to 6,

the input information includes: information on the week and the period in which the electric vacuum cleaner is used, or information on the week and the period in which the electric vacuum cleaner as a cleaning robot operates,

the estimation unit estimates an attribute relating to a employment mode as the attribute of the user.

8. The information processing system according to any one of claims 1 to 7,

the input information includes information on a detection result of an illuminance sensor provided in the electric cleaner as the cleaning robot,

the estimation unit estimates an attribute relating to the presence or absence of a marital as the attribute of the user.

9. The information processing system according to any one of claims 1 to 8,

the input information includes: information on an operation time of the electric vacuum cleaner, information on a number of reconnections of the wired type of the electric vacuum cleaner to an external power source, information on accessories attached to or detached from the electric vacuum cleaner, information on a lighting state of a lamp provided on a head of the electric vacuum cleaner, information on the number of the electric vacuum cleaners in the same house, information on a movement of a main body of the canister type of the electric vacuum cleaner, information on a drawn amount of a cable of the canister type of the electric vacuum cleaner, information on a map generated by the electric vacuum cleaner as a cleaning robot, or information on a detection result of a fall prevention sensor of the electric vacuum cleaner as a cleaning robot,

the estimation unit estimates an attribute relating to the house as the attribute of the user.

10. The information processing system according to any one of claims 1 to 9,

the input information includes: information on a load state of a brush motor of the electric vacuum cleaner, information on an acceleration acting on a head of the electric vacuum cleaner, or information on a detection result of a dust sensor provided in the electric vacuum cleaner,

the estimating unit estimates an attribute relating to a floor type of a room as the attribute of the user.

11. The information processing system according to any one of claims 1 to 10,

the input information includes: information on the temperature detected by the electric vacuum cleaner or information on the frequency of an external power supply connected to the electric vacuum cleaner,

the estimation unit estimates an attribute of the residential area as the attribute of the user.