CN113669983A - Information processing system - Google Patents
Information processing system Download PDFInfo
- Publication number
- CN113669983A CN113669983A CN202110154628.7A CN202110154628A CN113669983A CN 113669983 A CN113669983 A CN 113669983A CN 202110154628 A CN202110154628 A CN 202110154628A CN 113669983 A CN113669983 A CN 113669983A
- Authority
- CN
- China
- Prior art keywords
- refrigerator
- user
- information
- attribute
- processing system
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000010365 information processing Effects 0.000 title claims abstract description 30
- 238000010801 machine learning Methods 0.000 claims abstract description 7
- 238000007710 freezing Methods 0.000 claims description 34
- 230000008014 freezing Effects 0.000 claims description 34
- 238000001816 cooling Methods 0.000 claims description 28
- 235000013305 food Nutrition 0.000 claims description 18
- 239000000463 material Substances 0.000 claims description 17
- 238000006243 chemical reaction Methods 0.000 description 31
- 238000001514 detection method Methods 0.000 description 26
- 238000003860 storage Methods 0.000 description 23
- 238000010586 diagram Methods 0.000 description 20
- 238000012545 processing Methods 0.000 description 20
- 235000013311 vegetables Nutrition 0.000 description 18
- 230000008859 change Effects 0.000 description 17
- 238000009434 installation Methods 0.000 description 13
- 239000003507 refrigerant Substances 0.000 description 10
- 238000005057 refrigeration Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 6
- 238000000034 method Methods 0.000 description 5
- 230000000875 corresponding effect Effects 0.000 description 4
- 235000012054 meals Nutrition 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 238000010411 cooking Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005401 electroluminescence Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000012356 Product development Methods 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 235000013361 beverage Nutrition 0.000 description 1
- 235000021152 breakfast Nutrition 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 238000003892 spreading Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
- F25D11/00—Self-contained movable devices, e.g. domestic refrigerators
- F25D11/02—Self-contained movable devices, e.g. domestic refrigerators with cooling compartments at different temperatures
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
- F25D23/00—General constructional features
- F25D23/02—Doors; Covers
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
- F25D29/00—Arrangement or mounting of control or safety devices
- F25D29/005—Mounting of control devices
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
- F25D2400/00—General features of, or devices for refrigerators, cold rooms, ice-boxes, or for cooling or freezing apparatus not covered by any other subclass
- F25D2400/36—Visual displays
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
- F25D2500/00—Problems to be solved
- F25D2500/06—Stock management
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Physics & Mathematics (AREA)
- Mechanical Engineering (AREA)
- Thermal Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Cold Air Circulating Systems And Constructional Details In Refrigerators (AREA)
- Devices That Are Associated With Refrigeration Equipment (AREA)
Abstract
Provided is an information processing system capable of estimating attributes of a user who uses a refrigerator. An information processing system according to an embodiment includes an acquisition unit and an estimation unit. The acquisition unit acquires data relating to the state of the refrigerator. The estimation unit estimates attributes of a user of the refrigerator based on the data acquired by the acquisition unit, using a learned model generated by machine learning.
Description
Technical Field
Embodiments of the present invention relate to an information processing system.
Background
In recent years, a home appliance which is equipped with a wireless communication function and can be connected to the internet has been spreading. Such a technical field is generally called IoT (Internet of Things), and is not limited to the field of home appliances, and is attracting attention in various industries. For example, manufacturers of home appliances are developing services capable of remotely confirming the states of home appliances from applications of smartphones (hereinafter, referred to as "home appliance applications") or remotely operating home appliances.
Prior art documents:
patent documents:
patent document 1: japanese patent laid-open publication No. 2017-120178
Patent document 2: japanese patent laid-open publication No. 2019-78506
Patent document 3: republishing WO2017/179188 publication
Patent document 4: japanese patent laid-open publication No. 2011-33325
Disclosure of Invention
However, since the conventional service starts with a user operation such as a user remotely checking the state of the home appliance or remotely operating the home appliance, the frequency of the user operating the home appliance application is high, and the service is not always convenient for the user. Accordingly, it is desirable to provide a home appliance application capable of controlling a home appliance according to an attribute of a user. In order to provide such home appliance applications, it is necessary to estimate the attributes of the user without depending on the setting behavior of the user.
An object of the present invention is to provide an information processing system capable of estimating attributes of a user using a refrigerator.
An information processing system according to an embodiment includes an acquisition unit and an estimation unit. The acquisition unit acquires data relating to the state of the refrigerator. The estimation unit estimates an attribute of a user of the refrigerator based on the data acquired by the acquisition unit, using a learned model generated by machine learning.
The invention has the following effects:
the invention can estimate the attribute of the user using the refrigerator.
Drawings
Fig. 1 is a diagram showing an overall configuration of an information processing system (user information collection system) according to an embodiment.
Fig. 2 is an external view showing a configuration example of the refrigerator according to the embodiment.
Fig. 3 is a sectional view showing a configuration example of a refrigerator according to the embodiment.
Fig. 4 is a block diagram showing a configuration example related to control of the refrigerator according to the embodiment.
Fig. 5 is a diagram showing a specific example of an in-box image of a refrigerator according to the embodiment.
Fig. 6 is a block diagram showing a configuration example of a server according to the embodiment.
Fig. 7 is a diagram showing a specific example of data D used for generating input information for estimating the number of people to be used in the information processing system according to the embodiment.
Fig. 8 is a diagram showing a first specific example of a temperature change in the interior of a building in which the refrigerator according to the embodiment is installed.
Fig. 9 is a diagram showing a second specific example of a temperature change in the interior of a building in which the refrigerator according to the embodiment is installed.
Fig. 10 is a diagram showing a specific example of the user registration information according to the embodiment.
Fig. 11 is a diagram showing a flow of processing in the refrigerator according to the embodiment.
Fig. 12 is a diagram showing a flow of processing in the server according to the embodiment.
Description of the reference symbols
1 … … information processing system, 100 … … refrigerator, 10 … … refrigerator compartment, 11 … … refrigerator compartment door, 12 … … refrigerator compartment door switch, 13 … … refrigerator cooler, 14 … … refrigerator cooling fan, 15 … … refrigerator cooling compartment, 20 … … vegetable compartment, 21 … … vegetable compartment door, 22 … … vegetable compartment door switch, 30 … … freezer compartment, 31 … … freezer compartment door, 32 … … freezer compartment door switch, 33 … … refrigerator cooler, 34 … … refrigerator cooling fan, 35 … … refrigerator cooling compartment, 40 … … compartment, 41 … … ice making compartment door, 42 … … ice making compartment door switch, 51 … … compressor, 52 … … refrigerant switching valve, 53 … … damper 531 … … refrigerator cooling damper, 532 … … refrigerator cooling damper, 533 … … communication, 54 … … ice making tray motor, 55 … … water supply motor, 61 … … refrigerator compartment temperature sensor, 62 … … vegetable compartment temperature sensor, 63 … … freezing chamber temperature sensor, 64 … … ice making chamber temperature sensor, 65 … … camera in box, 66 … … human body detection sensor, 67 … … ambient temperature sensor, 68 … … ambient humidity sensor, 69 … … power detection unit, 70 … … wireless module, 80 … … control unit, 81 … … freezing cycle control unit, 82 … … storage unit, 83 … … information recording unit, 84 … … information output unit, 200 … … server, 201 … … information acquisition unit, 202 … … information conversion unit, 203 … … learning unit, 204 … … estimation unit, 205 … … information recording unit, 206 … … information output unit, 207 … … storage unit, 300 … … terminal device, 300a … … display device.
Detailed Description
Hereinafter, an information processing system according to an embodiment will be described with reference to the drawings. In the following description, the same reference numerals are given to structures having the same or similar functions. Moreover, a repetitive description of these configurations may be omitted. "based on XX" means "based on at least XX", and can also include cases based on other elements in addition to XX. "based on XX" is not limited to the case of directly using XX, and may include a case based on a result of performing an operation or processing on XX. "XX or YY" is not limited to either XX or YY, and may include both XX and YY. The same applies to the case where three or more selected elements are used. "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, a refrigerator 100, a server 200, and a terminal device 300, which are disposed in each home. In the present specification, the "information processing system" may mean only the server 200 without including the refrigerator 100 and the terminal device 300. The Network NW described later may be, 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 refrigerator 100 is disposed in the residence of the user U. The refrigerator 100 can communicate with the server 200 via a wireless router R and a network NW disposed in the residence of the user U, for example. The refrigerator 100 will be described in detail later.
The server 200 is configured by 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 or fog calculation, such as an information processing unit included in a router in the network NW. The server 200 will be described in detail 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 or an organic EL (Electro Luminescence) display. Note that the terminal device 300 and the server device SD may be provided integrally in one device.
< 2. refrigerator >
< 2.1 Overall Structure of refrigerator
Fig. 2 is an external view showing a configuration example of the refrigerator 100. Refrigerator 100 includes, for example, refrigerating compartment 10, vegetable compartment 20, freezing compartment 30, and ice-making compartment 40 as storage compartments, and refrigerating compartment door 11, vegetable compartment door 21, freezing compartment door 31, and ice-making compartment door 41 as doors for opening and closing the storage compartments. The refrigerating compartment door 11, the vegetable compartment door 21, the freezing compartment door 31, and the ice-making compartment door 41 are provided with a refrigerating compartment door switch 12, a vegetable compartment door switch 22, a freezing compartment door switch 32, and an ice-making compartment door switch 42 as sensors for detecting the open/closed states thereof. Further, a human body detection sensor 66 for detecting the approach of the user U is provided on the outer surface of the refrigerator 100.
Fig. 3 is a sectional view showing a configuration example of the refrigerator 100. Fig. 3 is a sectional view taken along line a-a in fig. 2. Fig. 3 shows a so-called dual cooling type refrigerator having two cooling mechanisms as an example of the refrigerator 100. The refrigerator 100 includes, for example, a refrigerating cooler 13, a freezing cooler 33, a refrigerating cooling fan 14, a freezing cooling fan 34, a compressor 51, a refrigerant switching valve 52, a damper 53, an ice tray motor 54, and a water supply motor 55 as components for realizing a freezing cycle.
The compressor 51 is a device that compresses a refrigerant that circulates through a refrigeration cycle as a heat exchange medium. The refrigerating cooler 13 is an evaporator that cools air in the refrigerating and cooling chamber 15 by heat exchange with a refrigerant. The air cooled by the refrigerating cooler 13 is supplied to the refrigerating chamber 10 or the vegetable chamber 20 through the communicating portion 533 by the rotation of the refrigerating cooling fan 14. Similarly, the freezing cooler 33 is an evaporator that cools air in the freezing and cooling chamber 35 by heat exchange with the refrigerant. The air cooled by the freezing cooler 33 is supplied to the freezing compartment 30 or the ice making compartment 40 via the communication portion 533 by the rotation of the freezing cooling fan 34.
The refrigerant switching valve 52 is a valve that switches a flow path of the refrigerant so that the refrigerant is sent to one or both of the refrigerating cooler 13 and the freezing cooler 33. The refrigerating cooling damper 531 adjusts the flow rate of air flowing between the refrigerating cooling chamber 15 and the refrigerating chamber 10 through the communicating portion 533. Freezing/cooling damper 532 is a device for adjusting the flow rate of air flowing between freezing/cooling chamber 35 and freezing chamber 30 through communication portion 533. The ice-making tray motor 54 is a motor for rotating the ice-making tray in order to move the ice generated in the ice-making chamber 40 to the receiving tray. The water supply motor 55 is a motor for supplying water stored in the water supply tank in the ice making chamber 40 to the ice making tray.
< 2.2 Structure of sensor group and control part of refrigerator
Fig. 4 is a block diagram showing a configuration example related to control of the refrigerator 100. As shown in fig. 4, the refrigerator 100 includes a wireless module 70 for communicably connecting itself to another communication device, a control unit 80 for causing itself to function as a refrigeration cycle apparatus, and a sensor group SU for acquiring various information necessary for controlling the refrigeration cycle. The controller 80 is communicably connected to the sensor group SU via a communication line inside the refrigerator 100, and is wirelessly communicable with the server 200 via the wireless module 70. The wireless module 70 wirelessly communicates with the server 200 via the wireless router R.
The control Unit 80 includes, for example, a processor such as a CPU (Central Processing Unit), a Memory such as an SRAM (Static Random Access Memory) or a DRAM (Dynamic Random Access Memory), and an auxiliary storage device such as an SSD (Solid State Drive) or an HDD (Hard Disk Drive). The control unit 80 reads a program stored in the auxiliary storage device by the processor onto the memory and executes the program, thereby functioning as a device including the refrigeration cycle control unit 81, the storage unit 82, the information recording unit 83, and the information output unit 84. All or part of the functions of the control unit 80 may be realized by hardware (including a Circuit unit) 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.
The refrigeration cycle controller 81 functions to control the operations of the refrigerating cooling fan 14, the freezing cooling fan 34, the compressor 51, the refrigerant switching valve 52, the damper 53, the ice tray motor 54, and the water supply motor 55 based on the temperature of the refrigerating compartment 10, the temperature of the vegetable compartment 20, the temperature of the freezing compartment 30, and the temperature of the ice compartment 40, because the refrigerator 100 functions as a refrigeration cycle device. The refrigeration cycle controller 81 may be configured to perform control based on the setting of the user U in addition to control based on the temperature of each storage room.
The storage unit 82 stores identification information I1 and status information I2. The identification information I1 indicates an equipment ID given to each refrigerator 100 in order to identify the refrigerator 100. The state information I2 is time-series information indicating the state of the refrigerator 100.
Information recording unit 83 refers to a timer, not shown, for example, and adds information indicating the state of refrigerator 100 and date and time information to state information I2 in storage unit 82 in association with each other. The "state of the refrigerator 100" includes, for example, a state of turning on/off the power supply of the refrigerator 100, and an operation state of the compressor 51, the refrigerant switching valve 52, the refrigerating cooling fan 14, the freezing cooling fan 34, and the like. The "state of the refrigerator 100" may include a state of articles stored in the refrigerator 100. The date and time information includes information indicating the day of the week and the time of day.
Further, the information recording unit 83 adds information indicating the detection result of the sensor group SU to the state information I2 in the storage unit 82 in association with the date and time information. Here, refrigerator 100 includes, as sensor group SU, a refrigerating compartment temperature sensor 61, a vegetable compartment temperature sensor 62, a freezing compartment temperature sensor 63, an ice-making compartment temperature sensor 64, an in-box camera 65, a human body detection sensor 66, an ambient temperature sensor 67, an ambient humidity sensor 68, and a power supply detection unit 69, in addition to refrigerating compartment door switch 12, vegetable compartment door switch 22, freezing compartment door switch 32, and ice-making compartment door switch 42 described above. The refrigerating compartment temperature sensor 61, the vegetable compartment temperature sensor 62, the freezing compartment temperature sensor 63, and the ice compartment temperature sensor 64 are temperature sensors for measuring the indoor temperatures of the refrigerating compartment 10, the vegetable compartment 20, the freezing compartment 30, and the ice compartment 40, respectively.
The in-box camera 65 is a camera that photographs the inside of the refrigerator 100. For example, fig. 5 is a diagram showing a specific example of an image (hereinafter, referred to as an "in-box image") obtained by taking an image of the inside of the refrigerator 100 by the in-box camera 65. Is an example provided to photograph the inside of the refrigerating compartment 10. The in-box camera 65 may be provided to photograph the inside of the vegetable compartment 20, the freezing compartment 30, or the ice making compartment 40 as necessary. In addition, a plurality of in-box cameras 65 may be provided inside refrigerator 100 to photograph the inside of a plurality of storage rooms. The detection results of the sensor group SU are the detection results of the various sensors or switches described above. The information may be recorded as raw data or in a state where a desired operation (processing) is performed.
The human body detection sensor 66 is a sensor that detects a person near the refrigerator 100. The human body detection sensor 66 may detect a human body by infrared rays, or may detect a human body based on an image obtained by photographing the vicinity of the refrigerator 100.
The ambient temperature sensor 67 is a sensor that detects the temperature near the refrigerator 100. The ambient humidity sensor is a sensor that detects humidity in the vicinity of the refrigerator 100. The power detection unit 69 is a sensor that detects the frequency of the external power supply connected to the refrigerator 100.
The information output unit 84 transmits the status information I2 stored in the storage unit 82 to the server 200 via the wireless module 70. The information output unit 84 transmits the status information I2 to the server 200 at a predetermined cycle, for example. At this time, the information output unit 84 associates the status information I2 with the identification information I1 stored in the storage unit 82 and transmits the information to the server 200. The identification information I1 is an equipment ID given to each refrigerator 100 in order to identify the refrigerator 100. The state information I2 and the identification information I1 are examples of data transmitted from the refrigerator 100 to the server 200. Hereinafter, the status information I2 and the identification information I1 are collectively referred to as "data D".
Instead of the above configuration, information recording unit 83 may be omitted, and information output unit 84 may transmit the operation state of refrigerator 100 and the detection result of sensor group SU to server 200 in real time. In this case, the server 200 may associate the operating state of the refrigerator 100, the detection result of the sensor group SU, and the date and time information.
< 3. Server >
Fig. 6 is a block diagram showing a configuration example of server 200. The server 200 includes, for example, an information acquisition unit 201, an information conversion unit 202, a learning unit 203, an estimation unit 204, an information recording unit 205, and an information output unit 206. These functional units are realized by executing a program (software) by a hardware processor such as a CPU included in the server 200. All or part of these functional units may be realized by hardware (including a circuit unit) such as an 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 learning model L, the estimation model (learned model) M, and the user attribute information I13.
The information conversion unit 202 generates input information to be input to an estimation model M, which will be described later, based on the accumulated information I11 in which the data D of each refrigerator 100 is accumulated and the learning model L. The learning model L is a model showing an algorithm for performing mechanical learning. The estimation model M is a learned model generated by learning using the accumulated information I11 of the learning model L, and is a model for estimating the attribute of the user U. Examples of the attributes of the user U include (a) the number of people using the refrigerator 100, (b) sex, (c) age, (d) residence mode, (e) installation location, (f) employment mode, (g) presence or absence of marital, and (h) residence area. The estimated attribute of the user U may be something other than the above-mentioned items as long as the user U can estimate the attribute based on the accumulated information I11.
(a. input information for estimating the number of users)
The information conversion unit 202 generates, for example, one or more pieces of information among the following pieces of information, as input information (hereinafter, referred to as "input information for estimating the number of people used") to be input to the estimation model M for estimating the attribute related to the number of people used, based on the accumulated information I11. These pieces of information have a correlation with the number of users at least from the viewpoint described below. Therefore, one or more pieces of information among the pieces of information listed below can be used as input information of the estimation model M in which the attribute relating to the number of people used is used as output information.
Information related to model of refrigerator 100
Information related to the kind of door of the refrigerator 100
Information on the number of times of opening and closing of the door of the refrigerator 100
Information on the opening/closing timing of the door of refrigerator 100
Information related to the opening and closing times of the doors of the refrigerator 100
Information on the in-cabinet temperature of the refrigerator 100
Information relating to the operation of the compressor 51 of the refrigerator 100
Information related to the operation of the cooling fan of the refrigerator 100
Information related to the operation of the ice maker of the refrigerator 100
Information related to quick freezing action of the refrigerator 100
For example, generally, since a manufacturer of a refrigerator arranges models having functionality according to the number of persons using the refrigerator in a row (line up), a user selects a model according to the number of persons who use the refrigerator from the arranged models. Therefore, it is considered that the refrigerator 100 is highly likely to be used by users of the number of persons corresponding to the model. In such a model arrangement corresponding to the number of users, in many cases, the number of models is designed according to the number of users in the gate section as the number of users increases. Therefore, it is considered that the refrigerator 100 is highly likely to be used by the user of the number of persons corresponding to the kind of the door.
In general, the load applied to refrigerator 100 tends to increase as the number of people using refrigerator 100 (e.g., the number of people in the family of the user) increases. Therefore, various index values indicating the magnitude of the load applied to the refrigerator 100 have a correlation with the number of people using the refrigerator 100. Here, the index value indicating the magnitude of the load applied to refrigerator 100 includes "the number of times of opening and closing the door of refrigerator 100", "the opening and closing timing of the door of refrigerator 100", "the opening and closing time of the door of refrigerator 100", "the internal temperature of refrigerator 100", "the operating state of compressor 51 of refrigerator 100", "the operating state of cooling fan of refrigerator 100", "the state of ice making operation of refrigerator 100", "the state of quick freezing operation of refrigerator 100", and the like.
Fig. 7 is a diagram showing a specific example of data D for generating input information for estimating the number of people to be used. The data D is time-series data representing the detection results of the sensor groups SU. In fig. 7, it can be known that the use timing of the refrigerator 100 is detected by the human body detection sensor 66. Further, it is known that the storage room used at each use timing is detected by on/off of the door switch of each storage room. It is also known that the load varies at each use timing according to the temperature of each storage room, and the operating conditions of the compressor 51, the refrigerating cooling fan 14, and the freezing cooling fan 34.
The information conversion unit 202 generates, as the input information for estimating the number of people to be used, information such as "the number of times the door of the refrigerator 100 is opened and closed", "the opening and closing timing of the door of the refrigerator 100", "the opening and closing time of the door of the refrigerator 100", "the internal temperature of the refrigerator 100", "the operating state of the compressor 51 of the refrigerator 100", "the operating state of the cooling fan of the refrigerator 100", "the state of the ice making operation of the refrigerator 100", "the state of the quick freezing operation of the refrigerator 100", and the like, which are acquired based on the data D.
In addition, as another example of the attribute related to the number of persons using refrigerator 100, a home structure of the user may be cited. For example, if it is estimated that the user of refrigerator 100 is 1 person, the family structure of the user can be considered as a single family. For example, if the number of people using refrigerator 100 is 2 and it is estimated that the age group is a fellow person, the family structure of the user can be considered as a family of only couples. In this case, in order to estimate the age or age group of the user, the age estimation input information described later may be included in the number-of-people estimation input information.
Further, for example, in a case where the number of persons using the refrigerator 100 is a plurality of persons, and it is estimated that children and adults are included therein, it can be considered that the family structure of the user is a family of parents and children. In this case, information such as age estimation input information or employment style estimation input information described later may be included in the population estimation input information in order to estimate the presence or absence of children.
In this case, when it is estimated that an adult of the childbearing age group and an old adult are included in the family, the family structure of the user can be considered as a 3 rd generation family. In this case, in order to estimate the age group of the adult, information such as age estimation input information or employment style estimation input information described later may be included in the number-of-people estimation input information.
(b. input information for estimating gender)
The information conversion unit 202 generates, for example, one or more pieces of information among the following pieces of information, as input information (hereinafter referred to as "sex estimation input information") to be input to the estimation model M for estimating the attribute related to the sex of the user U, based on the accumulated information I11. These pieces of information have a correlation with the gender of the user U at least in the viewpoint described below. Therefore, one or more pieces of information among the pieces of information listed below can be used as input information of the estimation model M in which an attribute relating to the sex of the user U is used as output information.
Information related to food materials stored in the cabinet of the refrigerator 100
Information relating to physical characteristics of user U of refrigerator 100
It is considered that the tendency relating to the gender of the user U is exhibited in "the food materials stored in the cabinet of the refrigerator 100". For example, since women tend to cook more frequently than men, if the user of refrigerator 100 is a woman, it is considered that there is a high possibility that a large amount of fresh food is stored in the refrigerator 100. In addition, women tend to eat more vegetables than men, so in the case where the user of the refrigerator 100 is a woman, it is considered that there is a high possibility that a large amount of vegetables are stored in the refrigerator 100.
Specifically, the information conversion unit 202 executes image recognition processing for recognizing the photographed food material with respect to an in-box image (for example, see fig. 5) of the refrigerator 100 photographed by the in-box camera 65. The in-box image data is a form of data D. In this case, the image recognition processing may be performed by any method as long as the food material captured in the in-box image can be recognized.
For example, in the image recognition process, the following method can be used: the presence or absence and the type of the food material are identified based on various feature amounts obtained using each pixel value of the image data. Therefore, the information conversion unit 202 generates information indicating the result of recognition of the food material by the image recognition processing as the input information for estimating the gender. Further, since it is considered that information indicating the feature of the subject is included in each pixel value of the image data, the information conversion unit 202 may generate the image data itself as the input information for estimating the sex.
Further, it is considered that in the "physical characteristics of the user U", a tendency relating to the gender of the user U of the refrigerator 100 is exhibited. For example, men tend to be taller than women. In addition, the male hand or arm tends to be larger and thicker than the female hand or arm. Further, women often wear the jewelry item on their hands or arms as compared with men, and in addition, the jewelry item is mostly visible from the outside of the body for women or men.
Specifically, the information related to the physical characteristics of the user U of the refrigerator 100 can be acquired using, for example, the detection result of the human body detection sensor 66 or the in-box image data of the refrigerator 100. For example, when the human body detection sensor 66 detects a person having a height equal to or greater than a predetermined height, the detection result of the human body detection sensor 66 can be used as information indicating whether or not the height of the user U of the refrigerator 100 is equal to or greater than the predetermined height. Further, for example, the hand of the user U who accesses the food material may be photographed in the in-box image of the refrigerator 100. Therefore, the information conversion unit 202 detects the hand of the person captured in the in-box image by the image recognition processing, and recognizes the attribute (for example, the size, thickness, presence or absence of an accessory, and the like) of the detected hand.
The information conversion unit 202 generates information indicating the recognition result of the hand attribute by the image recognition processing as input information for estimating the gender. Further, since it is considered that information indicating the feature of the subject is included in each pixel value of the image data, the information conversion unit 202 may generate the image data itself as the input information for estimating the sex.
(c. input information for estimating age)
The information conversion unit 202 generates, for example, one or more pieces of information among the following pieces of information, as input information (hereinafter referred to as "input information for age estimation") to be input to the estimation model M for estimating an attribute related to the age of the user U, based on the accumulated information I11. These pieces of information have a correlation with the age of the user U at least in the viewpoint described below. Therefore, one or more pieces of information among the pieces of information listed below can be used as input information of the estimation model M in which an attribute relating to the age of the user U is used as output information.
Information on the opening/closing timing of the door of refrigerator 100
Information on the in-cabinet temperature of the refrigerator 100
It is considered that the "opening and closing timing of the door of refrigerator 100" tends to be correlated with the age of user U. For example, an older person tends to move earlier in the morning than a young person, and therefore it is considered that the time at which opening and closing of refrigerator 100 is started is earlier than the young person. Further, in the case where the door of the refrigerator is opened and closed periodically from about 6 to about 8 am, it is considered that the possibility that the user will have a box meal in addition to the preparation of breakfast is high. Further, it is considered that the possibility that a family of the generation having students among children is required is high.
Specifically, the opening/closing timing of the door of refrigerator 100 can be obtained based on accumulated information I11 in which the on/off states of refrigerating compartment door switch 12, vegetable compartment door switch 22, freezing compartment door switch 32, and ice-making compartment door switch 42 are recorded. For example, when the switch is turned on when each door is closed and turned off when each door is opened, the timing at which each switch changes from the on state to the off state or the timing at which each switch changes from the off state to the on state is detected, whereby the timing at which the user opens the door can be obtained.
Therefore, information conversion unit 202 generates information indicating the timing at which the user opens and closes the door of refrigerator 100 as input information for estimating age. Further, since the "internal temperature of the refrigerator 100" is likely to change greatly in the opening and closing timing of the refrigerating chamber door 11, the information conversion unit 202 may be configured to recognize the opening and closing timing of the refrigerating chamber door 11 from the change in the internal temperature of the refrigerator 100.
(d. input information for estimating attribute relating to residence mode)
The information conversion unit 202 generates, for example, one or more pieces of information among the following pieces of information, as input information (hereinafter referred to as "input information for estimating a residence system") to be input to the estimation model M for estimating an attribute related to the residence system, based on the accumulated information I11. These pieces of information have a correlation with the residence mode at least in the viewpoint described below. Therefore, one or more pieces of information among the following pieces of information can be generated as input information of the estimation model M in which the attribute relating to the residence system is used as output information.
Information relating to the temperature inside the building in which the refrigerator 100 is installed
Information related to humidity inside the building in which the refrigerator 100 is installed
Fig. 8 is a diagram showing a first example of a temperature change in the interior of a building in which refrigerator 100 is installed. As shown in fig. 8, it is considered that "the temperature inside the building in which refrigerator 100 is installed" shows a tendency of a temperature change in the room according to the type of the building. For example, an apartment tends to have a smaller indoor temperature change than a house of an independent house. Specifically, information relating to the temperature inside the building in which refrigerator 100 is installed can be acquired based on the detection result of ambient temperature sensor 67 included in accumulated information I11. Therefore, information conversion unit 202 generates information indicating the temperature inside the building in which refrigerator 100 is installed as input information for estimating the residence system.
Further, since apartments are less susceptible to the influence of outside air temperature than houses of individual houses, there is a tendency that the temperature change inside the building is less dependent on the time of day, season, or the like. Since the indoor temperature change is not substantially affected by the outdoor temperature, the "temperature outside the building where refrigerator 100 is installed" may be included in the input information for estimating the residence system in order to more accurately determine the cause of the indoor temperature change. In addition to the temperature change, the apartment tends to have a smaller change in indoor humidity than the house of the independent house. Therefore, "humidity inside the building where refrigerator 100 is installed" may be included in the input information for estimating the residence system, similarly to the temperature change.
(e. input information for estimating the attribute relating to the setting position of the refrigerator 100)
The information conversion unit 202 generates, for example, one or more pieces of information among the following pieces of information, as input information (hereinafter referred to as "input information for estimating installation position") to be input to the estimation model M for estimating the attribute related to the installation position of the refrigerator 100, based on the accumulated information I11. These pieces of information have a correlation with the set position of the refrigerator 100 at least in a viewpoint explained below. Therefore, one or more pieces of information among the pieces of information listed below can be used as input information of the estimation model M in which the attribute relating to the installation position of the refrigerator 100 is used as output information.
Information relating to the temperature inside the building in which the refrigerator 100 is installed
Information related to humidity inside the building in which the refrigerator 100 is installed
Fig. 9 is a diagram showing a second example of a temperature change in the interior of a building in which refrigerator 100 is installed. Generally, refrigerator 100 is installed in a kitchen, and a cooking range is often installed near the installation position. Further, in the case where a range is provided near the refrigerator 100, it is considered that the temperature near the refrigerator 100 rises at the use timing of the range. Further, since the range is highly likely to be used during a meal, in a case where the frequency of temperature rise in the vicinity of the refrigerator 100 during the meal is high, the refrigerator 100 is highly likely to be set in the place of the kitchen. In this way, it is considered that there is a correlation between "the temperature inside the building where the refrigerator 100 is provided" and the attribute regarding the installation place of the refrigerator 100. Therefore, information conversion unit 202 generates information indicating the temperature inside the building in which refrigerator 100 is installed as input information for estimating the installation position.
In addition, it is considered that in "humidity inside a building where the refrigerator 100 is provided", humidity change according to the use of a space inside the building is exhibited. For example, in a general kitchen, as an installation place of the refrigerator 100, humidity tends to temporarily increase due to steam generated during cooking. In addition, even in a space other than a kitchen, humidity tends to temporarily increase due to exhalation of a user, beverages, or the like when the space is used. The degree of the tendency to temporarily increase the humidity may vary depending on the use of the space, and the tendency appears as a characteristic such as the amount of change in the humidity or the period of change in the humidity. Specifically, information relating to the humidity inside the building in which refrigerator 100 is installed can be acquired based on the detection result of ambient humidity sensor 68 included in accumulated information I11. Therefore, information conversion unit 202 generates information indicating the humidity inside the building in which refrigerator 100 is installed as input information for estimating the installation position.
(f. input information for estimating employment mode)
The information conversion unit 202 generates, for example, one or more pieces of information among the following pieces of information, as input information (hereinafter referred to as "input information for estimating the employment style") to be input to the estimation model M for estimating the attribute related to the employment style of the user U, based on the accumulated information I11. These pieces of information have a correlation with the employment pattern of the user U at least in the viewpoint described below. Therefore, one or more pieces of information among the pieces of information listed below can be used as input information of the estimation model M in which the attribute relating to the employment mode of the user U is used as output information.
Information on the number of times of opening and closing of the door of the refrigerator 100
Information on the opening/closing timing of the door of refrigerator 100
Information related to the opening and closing times of the doors of the refrigerator 100
Information on the in-cabinet temperature of the refrigerator 100
Information relating to the operation of the compressor 51 of the refrigerator 100
Information related to the operation of the fan of the refrigerator 100
Information related to the operation of the ice maker of the refrigerator 100
Information related to quick freezing action of the refrigerator 100
For example, it is considered that attributes such as the work mode or the work period of the user U appear in the life pattern (pattern) of the user U. Further, a part of the life pattern of the user U appears in the use pattern of the refrigerator 100, and the use pattern of the refrigerator 100 appears in the variation pattern of the load applied to the refrigerator 100. For example, when the operation mode of user U is part-time, the time interval from the end of the use of refrigerator 100 to the restart thereof is short (for example, less than several hours), and when the operation mode of user U is full-time, the time interval from the end of the use of refrigerator 100 to the restart thereof is long (for example, 10 hours or more).
Further, for example, the working period of the user U is a period from the temporary end of the use of the refrigerator 100 to the restart thereof, and the life pattern thereof appears in the use pattern of the refrigerator 100. For example, the life pattern of the user U, which has the operating time from 9 am to 20 am, appears as the usage pattern of the refrigerator 100, in which the use of the refrigerator 100 is temporarily ended before 9 am of the working day and the use of the refrigerator 100 is restarted after 20 am. Further, the life pattern of the user U who sets the operation time from the night 21 to the next morning 6 appears as the use pattern of the refrigerator 100 in which the use of the refrigerator 100 is temporarily ended before the night 21 of the working day and the use of the refrigerator 100 is restarted after the next morning 6.
Further, for example, in the case where the user is a student, the life pattern of the user U appears as a usage pattern in which the refrigerator 100 is used repeatedly in almost the same pattern every week, although the refrigerator 100 is sometimes used in different patterns every day of the working day.
(g. input information for estimating presence/absence of marriage of user U of refrigerator 100)
The information conversion unit 202 generates, for example, one or more pieces of information among the following pieces of information, as input information (hereinafter referred to as "input information for marital estimation") to be input to the estimation model M for estimating an attribute related to the presence or absence of marital (marriage/nonmarriage) of the user U, based on the accumulated information I11. These pieces of information have a correlation with the presence or absence of the marriage of the user U at least from the viewpoint described below. Therefore, one or more pieces of information among the following pieces of information can be used as input information of the estimation model M in which an attribute relating to the presence or absence of the marital of the user U is used as output information.
Information related to food materials stored in the cabinet of the refrigerator 100
Information relating to physical characteristics of user U of refrigerator 100
It is considered that "food materials stored in the refrigerator 100" tend to be related to the presence or absence of marriage of the user U. For example, in the case where one of the masculine-preferred food material and the feminine-preferred food material is stored in the box of the refrigerator 100, it is considered that the user U is highly likely to be unmarried, and in the case where both the masculine-preferred food material and the feminine-preferred food material are stored in the box, it is considered that the user U is highly likely to be married. Further, even when the food materials preferred by adults and children are stored in the box, it is considered that the possibility of the user being married by U is high.
Therefore, the information conversion unit 202 generates information indicating the result of the identification of the food material by the image recognition processing as input information for marital estimation. Further, since it is considered that information indicating the feature of the subject is included in each pixel value of the image data, the information conversion unit 202 may generate the image data itself as input information for marital estimation.
Further, it is considered that the "physical characteristics of the user U of the refrigerator 100" also shows a tendency related to the presence or absence of marriage of the user U. For example, as a physical feature indicating a tendency related to the presence or absence of marriage, the presence or absence of wearing of a wedding ring can be cited. When it is recognized by the image recognition processing that the user U photographed in the in-box image wears the wedding ring on the hand, it is considered that the possibility that the user U is marred is high.
Therefore, the information conversion unit 202 generates information indicating the recognition result of the physical feature by the image recognition processing as input information for marital estimation. Further, since it is considered that information indicating the feature of the subject is included in each pixel value of the image data, the information conversion unit 202 may generate the image data itself as input information for marital estimation.
(h. input information for estimating residential area)
The information conversion unit 202 generates, for example, one or more pieces of information among the following pieces of information, as input information (hereinafter referred to as "living area estimation input information") to be input to the estimation model M for estimating the attribute related to the living area of the user U, based on the accumulated information I11. These pieces of information have a correlation with the living area of the user U at least from the viewpoint described below. Therefore, one or more pieces of information among the following pieces of information can be used as input information of the estimation model M in which the attribute related to the living area of the user U is used as output information.
Information relating to the temperature inside the building in which the refrigerator 100 is installed
Information related to humidity inside the building in which the refrigerator 100 is installed
Information relating to the frequency of the external power supply
It is considered that "the temperature inside the building where refrigerator 100 is installed" shows a tendency related to the living area of user U. For example, it is considered that the temperature inside a building in which the refrigerator 100 is installed changes relatively to the outside air temperature, and the outside air temperature shows a distribution that differs depending on the region. Therefore, it is considered that the temperature inside the building where the refrigerator 100 is installed reflects the climate of the residential area of the user U. It is also considered that "humidity inside the building where refrigerator 100 is installed" also tends to be related to the living area of user U. Further, it is considered that the combination of "the temperature inside the building where the refrigerator 100 is provided" and "the humidity inside the building where the refrigerator 100 is provided" gives more detailed characteristics to the climate of the residential area.
Therefore, information conversion unit 202 generates information indicating the temperature inside the building in which refrigerator 100 is installed as input information for estimating the living area. The information conversion unit 202 may acquire the air temperature information of each place from the server of the weather bureau, and may use the result of comparison between the acquired air temperature information of each place and the detection result of the ambient temperature sensor 67 as the living area estimation input information.
Further, "information related to the frequency of the external power supply" is information indicating whether the ac frequency of the external power supply to which the refrigerator 100 is connected is 50Hz or 60Hz, or the like. This information is derived based on, for example, the detection result of the power source detection unit 69 included in the data D. Here, the frequency of the commercial power supply in eastern japan is 50Hz, and the frequency of the commercial power supply in western japan is 60 Hz.
Next, the learning unit 203 will be described. The learning unit 203 applies the various input information described above to the learning model L of the machine learning, thereby generating an estimation model M for estimating the attribute of the user U as a learned model. When information related to refrigerator 100 is input, estimation model M learns to output an estimation result of an attribute of user U of refrigerator 100.
In the present embodiment, the learning unit 203 generates, as the estimation model M for estimating the attribute of the user U, an estimation model MA for estimating the attribute related to the number of people used, an estimation model MB for estimating the attribute related to gender, an estimation model MC for estimating the attribute related to age, an estimation model MD for estimating the attribute related to the housing system, an estimation model ME for estimating the attribute related to the installation location, an estimation model MF for estimating the attribute related to the employment system, an estimation model MG for estimating the attribute related to the presence or absence of marital, and an estimation model MH for estimating the attribute related to the housing area.
In addition, "learning" in this specification may mean either unsupervised learning or supervised learning. In the following, the description will be given mainly of the case where the estimation model M is generated by supervised learning, but the estimation model M may be generated by unsupervised learning. For example, the learning unit 203 applies the various types of input information for estimation and the user registration information I12 generated by the information conversion unit 202 as training data to the learning model L to learn the relationship between the various types of input information for estimation and the user registration information I12, thereby generating the estimation models MA to MH as learned models. For example, a neural network, reinforcement learning, deep learning, or the like can be used as the learning model L, but the learning model L is not limited thereto. The learning model L may also generate a regression curve or classifier as a result of learning the above-described relationship. For example, SVM (Support Vector Machine), Decision Tree (Decision Tree), random forest, k-neighborhood method, or the like may be used as the learning model L other than the neural network.
Fig. 10 is a diagram showing a specific example of the user registration information I12. The user registration information I12 includes, for each piece of identification information (user ID) of each user U, the number of users of the refrigerator 100 owned by the user, the installation location, the gender, the age, the employment style, the presence or absence of marital, the living area, and the manner of residence (residence manner) in which the user lives. The estimated attribute of the user U may be something other than the above-mentioned items as long as it can be estimated with respect to the user U based on the accumulated information I11. The learning unit 203 performs machine learning in which data obtained by associating each attribute of the user U with various types of input information for estimation having correlation with the attribute is used as training data, thereby learning the relationship between each attribute of the user U and various types of input information for estimation.
The association of the attributes of the user U with the input information for various types of estimation may be performed manually or mechanically. For example, the learning unit 203 may calculate the strength of the correlation between each attribute and each type of input information for estimation, and generate training data by associating each type of input information for estimation with the attribute having the strongest correlation.
The estimation unit 204 estimates the user attribute of the user U of the refrigerator 100 to be judged based on the data D received from the refrigerator 100 to be judged of the user attribute (hereinafter referred to as "refrigerator 100 to be judged") using the estimation model M obtained by the learning unit 203. The term "estimation" herein includes not only the case where the most likely one of the attribute candidates is determined, but also the case where the probability of each of the plurality of attribute candidates is output (for example, the probability of 1 person being used: 10%, the probability of 2 persons being used: 20%, the probability of 3 persons being used: 50%, and the probability of 4 or more persons being used: 20%).
The estimation unit 204 inputs various kinds of input information for estimation based on the data D obtained from the refrigerator 100 to be judged to the estimation model M, and obtains the estimation result of the user attribute of the user U of the refrigerator 100 to be judged as the output information of the estimation model M. In the present embodiment, the estimating unit 204 inputs the above-described input information for estimating the number of people used, input information for estimating gender, input information for estimating age, input information for estimating the housing style, input information for estimating the installation location, input information for estimating the employment style, input information for estimating marital, and input information for estimating the region of residence into the corresponding estimation models MA to MH, respectively, as input information based on the data D obtained from the determination target refrigerator 100, so that (a) the number of people used in the refrigerator 100, (b) the gender, (c) the age, (D) the housing style, (e) the installation location, (f) the employment style, (g) the presence or absence of marital, and (h) the estimation result of the region of residence are output as output information of the estimation models MA to MH.
The information recording unit 205 stores the user attribute estimated by the estimating unit 204 in the storage unit 207 as user attribute information I13.
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 or service provision.
< 4. flow of processing
Next, the flow of the processing will be described.
Fig. 11 is a diagram showing a flow of processing in the refrigerator 100. First, the control portion 80 determines whether or not the power supply of the refrigerator 100 is set to on (S101). When the power supply of refrigerator 100 is off, control unit 80 waits until the power supply of refrigerator 100 is turned on.
On the other hand, when the power supply of refrigerator 100 is turned on (yes in S101), control unit 80 transmits the detection result detected by sensor group SU to server 200 at a predetermined cycle or in real time (S102).
Next, control unit 80 determines whether or not the power supply of refrigerator 100 is turned off (S103). When the power of refrigerator 100 is turned on (no in S103), control unit 80 repeats the process in S102. On the other hand, when the power supply of refrigerator 100 is turned off (S103: yes), control unit 80 ends the series of processing. Refrigerator 100 repeats the above-described processing for a predetermined period of time (S101 to S103), for example.
Fig. 12 is a diagram showing a flow of processing in server 200. As a premise, data D transmitted from refrigerator 100 to server 200 is acquired by information acquisition unit 201 and stored as stored information I11.
First, the information conversion unit 202 generates the various types of input information for estimation described above based on the accumulated information I11 (S201). Next, the estimation unit 204 inputs the generated various types of input information for estimation to the estimation models MA to MH, respectively, and obtains an estimation result regarding the attribute of the user U as output information (S202). Next, the information output unit 206 outputs information indicating the estimation result regarding the attribute of the user U estimated by the estimation unit 204 to the terminal device 300.
< 5. Effect >
As a comparative example, it is conceivable to collect attribute information of the user U by inputting information such as sex, age, number of users, or living area on a questionnaire or web page. However, in these cases, the user may not input information because of the input effort, and the information input by the user may not match the actual situation. In addition, it is also difficult to confirm the detailed usage status to the user in the form of a questionnaire.
On the other hand, in the present embodiment, information processing system 1 includes information acquisition unit 201 that acquires data D transmitted from refrigerator 100; and an estimation unit 204 for estimating the attribute of user U of refrigerator 100 based on various input information for estimation obtained from data D acquired by information acquisition unit 201, using estimation model M after the machine learning. According to such a configuration, even if there is no input by the user U, the attribute of the user U can be estimated based on the result of use of the refrigerator 100 by the user U. This reduces the burden of collecting attribute information of the user U.
Further, the server 200 may be installed using a plurality of information processing apparatuses communicably connected via a network. In this case, each functional unit included in the server 200 may be distributed among a plurality of information processing apparatuses and installed. For example, the learning unit 203 and the estimating unit 204 may be mounted on different information processing apparatuses.
According to at least one embodiment described above, the refrigerator includes an acquisition unit that acquires data relating to the state of the refrigerator; and an estimation unit that estimates an attribute of a user of the refrigerator based on the data acquired by the acquisition unit using a learned model generated by machine learning, thereby estimating the attribute of the user using the refrigerator without depending on a setting behavior of the user.
The present invention has been described with reference to several embodiments, but these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other ways, and various omissions, substitutions, and changes can be made without departing from the scope of the invention. These embodiments and modifications thereof 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 (9)
1. An information processing system, comprising:
an acquisition unit that acquires data relating to the state of the refrigerator; and
an estimation unit configured to estimate an attribute of a user of the refrigerator based on the data acquired by the acquisition unit, using a learned model generated by machine learning.
2. The information processing system of claim 1,
the data includes information related to a model of the refrigerator, a type of the door, a number of times the door is opened and closed, a time when the door is opened and closed, an opening and closing time of the door, an in-box temperature, an operation of the compressor, an operation of the cooling fan, an operation of the ice maker, or a quick freezing operation,
the estimation unit estimates an attribute related to the number of persons using the refrigerator as the attribute of the user.
3. The information processing system of claim 1,
the data includes information representing food materials stored in the refrigerator or appearance characteristics of the user,
the estimating unit estimates an attribute relating to the gender of the user as the attribute of the user.
4. The information processing system of claim 1,
the data includes information related to the opening and closing timing of the door of the refrigerator or the temperature inside the refrigerator,
the estimation unit estimates an attribute related to the age of the user as the attribute of the user.
5. The information processing system of claim 1,
the data contains information related to the temperature or humidity inside the building in which the refrigerator is disposed,
the estimation unit estimates an attribute relating to a residence form of the user as the attribute of the user.
6. The information processing system of claim 1,
the data contains information related to the temperature or humidity inside the building in which the refrigerator is disposed,
the estimation portion estimates an attribute related to a setting position of the refrigerator as the attribute of the user.
7. The information processing system of claim 1,
the data includes information related to the number of times the door of the refrigerator is opened and closed, the opening and closing time of the door, the temperature inside the refrigerator, the operation of the compressor, the operation of the fan, the operation of the ice maker, and the quick freezing operation,
the estimation unit estimates an attribute relating to a employment mode of the user as the attribute of the user.
8. The information processing system of claim 1,
the data includes information representing food materials stored in the refrigerator or appearance characteristics of the user,
the estimation unit estimates an attribute relating to the presence or absence of a marital of the user as the attribute of the user.
9. The information processing system of claim 1,
the data contains information related to the temperature or humidity inside the building in which the refrigerator is disposed,
the estimation unit estimates an attribute related to the living area of the user as the attribute of the user.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2020084528A JP7456844B2 (en) | 2020-05-13 | 2020-05-13 | information processing system |
| JP2020-084528 | 2020-05-13 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113669983A true CN113669983A (en) | 2021-11-19 |
| CN113669983B CN113669983B (en) | 2024-09-10 |
Family
ID=78511380
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110154628.7A Active CN113669983B (en) | 2020-05-13 | 2021-02-04 | Information processing system |
Country Status (2)
| Country | Link |
|---|---|
| JP (1) | JP7456844B2 (en) |
| CN (1) | CN113669983B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20060102022A (en) * | 2005-03-22 | 2006-09-27 | 엘지전자 주식회사 | Health care system of refrigerator |
| JP2011201213A (en) * | 2010-03-26 | 2011-10-13 | Seiko Epson Corp | Printer, control method for the same, and program |
| DE202011103185U1 (en) * | 2011-07-06 | 2011-10-24 | Jochen Hein | fridge use |
| CN103838884A (en) * | 2014-03-31 | 2014-06-04 | 联想(北京)有限公司 | Information processing equipment and information processing method |
| CN105933425A (en) * | 2016-05-18 | 2016-09-07 | 北京奇虎科技有限公司 | Application recommendation method and device |
| CN107659622A (en) * | 2017-09-06 | 2018-02-02 | 珠海格力电器股份有限公司 | Equipment model selection method and device, storage medium and server |
| CN107767932A (en) * | 2017-10-19 | 2018-03-06 | 上海斐讯数据通信技术有限公司 | The method and system that a kind of Weight-detecting device and refrigerator binding uses |
| KR20190100112A (en) * | 2019-08-09 | 2019-08-28 | 엘지전자 주식회사 | Refrigerator for providing information of item using artificial intelligence and operating method thereof |
| CN209823796U (en) * | 2019-08-14 | 2019-12-20 | 合肥美菱物联科技有限公司 | Intelligent refrigerator |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6586758B2 (en) * | 2015-03-31 | 2019-10-09 | ソニー株式会社 | Information processing system, information processing method, and program |
| JP2017211168A (en) * | 2016-05-27 | 2017-11-30 | シャープ株式会社 | Refrigerator and advertisement display program |
| JP6452254B2 (en) * | 2016-07-11 | 2019-01-16 | シャープ株式会社 | Broadcast receiver, notification method, program, and storage medium |
| KR101984515B1 (en) * | 2016-09-28 | 2019-05-31 | 엘지전자 주식회사 | Refrigerator and home automation system having the same |
| CN109074601A (en) * | 2017-02-03 | 2018-12-21 | 松下知识产权经营株式会社 | Model generating method, the model generating means that learn of learning and the model that learns utilize device |
| CN110622203B (en) * | 2017-03-17 | 2023-05-09 | 本田技研工业株式会社 | Mobile plan providing system and mobile plan providing method |
| JP6939412B2 (en) * | 2017-10-26 | 2021-09-22 | 三菱電機株式会社 | Refrigerator system |
-
2020
- 2020-05-13 JP JP2020084528A patent/JP7456844B2/en active Active
-
2021
- 2021-02-04 CN CN202110154628.7A patent/CN113669983B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20060102022A (en) * | 2005-03-22 | 2006-09-27 | 엘지전자 주식회사 | Health care system of refrigerator |
| JP2011201213A (en) * | 2010-03-26 | 2011-10-13 | Seiko Epson Corp | Printer, control method for the same, and program |
| DE202011103185U1 (en) * | 2011-07-06 | 2011-10-24 | Jochen Hein | fridge use |
| CN103838884A (en) * | 2014-03-31 | 2014-06-04 | 联想(北京)有限公司 | Information processing equipment and information processing method |
| CN105933425A (en) * | 2016-05-18 | 2016-09-07 | 北京奇虎科技有限公司 | Application recommendation method and device |
| CN107659622A (en) * | 2017-09-06 | 2018-02-02 | 珠海格力电器股份有限公司 | Equipment model selection method and device, storage medium and server |
| CN107767932A (en) * | 2017-10-19 | 2018-03-06 | 上海斐讯数据通信技术有限公司 | The method and system that a kind of Weight-detecting device and refrigerator binding uses |
| KR20190100112A (en) * | 2019-08-09 | 2019-08-28 | 엘지전자 주식회사 | Refrigerator for providing information of item using artificial intelligence and operating method thereof |
| CN209823796U (en) * | 2019-08-14 | 2019-12-20 | 合肥美菱物联科技有限公司 | Intelligent refrigerator |
Also Published As
| Publication number | Publication date |
|---|---|
| JP2021179276A (en) | 2021-11-18 |
| CN113669983B (en) | 2024-09-10 |
| JP7456844B2 (en) | 2024-03-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6745872B2 (en) | Refrigerator and network system including the same | |
| CN110410964B (en) | Control method and control system of air conditioner | |
| KR20170087705A (en) | Storage apparatus and control method thereof | |
| JP7012263B2 (en) | refrigerator | |
| US20220316741A1 (en) | Information processing method, information processing apparatus, and program | |
| CN110793167B (en) | Air conditioner control method and device | |
| JP6486111B2 (en) | refrigerator | |
| JP6447334B2 (en) | Refrigerator and network system | |
| US20180106523A1 (en) | Refrigerator food inventory preservation | |
| CN105222504B (en) | Refrigerator and its control method | |
| CN114237069A (en) | Indoor environment control method, device, system and storage medium | |
| WO2018020541A1 (en) | Refrigerator, network system provided with same, living circumstances reporting method and living circumstance reporting program | |
| JP2015222138A (en) | Refrigerator and network system | |
| JP2023181404A (en) | refrigerator | |
| JP2019160109A (en) | Server, equipment, terminal, and equipment system including the same | |
| JP7113281B2 (en) | refrigerator | |
| CN113669983B (en) | Information processing system | |
| JP2022094595A (en) | Household appliance system | |
| CN111381507B (en) | Recommendation method, medium, server and intelligent electrical appliance management system for electrical appliance operating parameters | |
| WO2022255344A1 (en) | Refrigerator, refrigerator control method, and program | |
| JP7090796B2 (en) | Watching system, watching method, refrigerator, and communication terminal | |
| JP7336948B2 (en) | Refrigerator management system, refrigerator management server, refrigerator management method and program | |
| JP2021096686A (en) | Refrigerator management system, refrigerator, and server system | |
| US11768031B1 (en) | Refrigerator appliance and methods for responding to ambient humidity levels | |
| KR20200083016A (en) | Electronic apparatus and control method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |