WO2022202410A1 - 判定装置、学習装置、判定システム、判定方法、学習方法、及び、プログラム - Google Patents
判定装置、学習装置、判定システム、判定方法、学習方法、及び、プログラム Download PDFInfo
- Publication number
- WO2022202410A1 WO2022202410A1 PCT/JP2022/010963 JP2022010963W WO2022202410A1 WO 2022202410 A1 WO2022202410 A1 WO 2022202410A1 JP 2022010963 W JP2022010963 W JP 2022010963W WO 2022202410 A1 WO2022202410 A1 WO 2022202410A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- oil
- cooking
- edible oil
- information
- determination device
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 84
- 238000010411 cooking Methods 0.000 claims abstract description 143
- 239000008157 edible vegetable oil Substances 0.000 claims abstract description 122
- 235000013305 food Nutrition 0.000 claims abstract description 85
- 238000003384 imaging method Methods 0.000 claims abstract description 20
- 239000003921 oil Substances 0.000 claims description 126
- 239000008162 cooking oil Substances 0.000 claims description 61
- 239000002699 waste material Substances 0.000 claims description 16
- 230000006866 deterioration Effects 0.000 claims description 13
- 150000001875 compounds Chemical class 0.000 claims description 6
- 239000002253 acid Substances 0.000 claims description 5
- 239000000779 smoke Substances 0.000 claims description 4
- 125000002915 carbonyl group Chemical group [*:2]C([*:1])=O 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 claims description 3
- BHAAPTBBJKJZER-UHFFFAOYSA-N p-anisidine Chemical compound COC1=CC=C(N)C=C1 BHAAPTBBJKJZER-UHFFFAOYSA-N 0.000 claims description 3
- 230000007423 decrease Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 description 40
- 230000008569 process Effects 0.000 description 38
- 238000005259 measurement Methods 0.000 description 31
- 238000007781 pre-processing Methods 0.000 description 29
- 238000010586 diagram Methods 0.000 description 26
- 238000013473 artificial intelligence Methods 0.000 description 22
- 238000001931 thermography Methods 0.000 description 20
- 238000004458 analytical method Methods 0.000 description 13
- 230000010365 information processing Effects 0.000 description 10
- 238000010438 heat treatment Methods 0.000 description 9
- 238000010998 test method Methods 0.000 description 8
- 238000009529 body temperature measurement Methods 0.000 description 7
- 238000011156 evaluation Methods 0.000 description 7
- 238000002360 preparation method Methods 0.000 description 7
- GVJHHUAWPYXKBD-UHFFFAOYSA-N d-alpha-tocopherol Natural products OC1=C(C)C(C)=C2OC(CCCC(C)CCCC(C)CCCC(C)C)(C)CCC2=C1C GVJHHUAWPYXKBD-UHFFFAOYSA-N 0.000 description 6
- 239000000796 flavoring agent Substances 0.000 description 6
- 235000019634 flavors Nutrition 0.000 description 6
- 238000003860 storage Methods 0.000 description 6
- 238000012937 correction Methods 0.000 description 5
- 238000009826 distribution Methods 0.000 description 5
- 239000000203 mixture Substances 0.000 description 5
- ZCYVEMRRCGMTRW-UHFFFAOYSA-N 7553-56-2 Chemical compound [I] ZCYVEMRRCGMTRW-UHFFFAOYSA-N 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 230000000875 corresponding effect Effects 0.000 description 4
- 229910052740 iodine Inorganic materials 0.000 description 4
- 239000011630 iodine Substances 0.000 description 4
- 229930003799 tocopherol Natural products 0.000 description 4
- 229960001295 tocopherol Drugs 0.000 description 4
- 239000011732 tocopherol Substances 0.000 description 4
- 235000010384 tocopherol Nutrition 0.000 description 4
- GVJHHUAWPYXKBD-IEOSBIPESA-N α-tocopherol Chemical compound OC1=C(C)C(C)=C2O[C@@](CCC[C@H](C)CCC[C@H](C)CCCC(C)C)(C)CCC2=C1C GVJHHUAWPYXKBD-IEOSBIPESA-N 0.000 description 4
- 238000012935 Averaging Methods 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000011084 recovery Methods 0.000 description 3
- 235000013194 Lyophyllum decastes Nutrition 0.000 description 2
- 240000005856 Lyophyllum decastes Species 0.000 description 2
- 239000003795 chemical substances by application Substances 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000008034 disappearance Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 235000015277 pork Nutrition 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000001953 sensory effect Effects 0.000 description 2
- 229930003427 Vitamin E Natural products 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 150000001299 aldehydes Chemical class 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 235000012020 french fries Nutrition 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- WIGCFUFOHFEKBI-UHFFFAOYSA-N gamma-tocopherol Natural products CC(C)CCCC(C)CCCC(C)CCCC1CCC2C(C)C(O)C(C)C(C)C2O1 WIGCFUFOHFEKBI-UHFFFAOYSA-N 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000004128 high performance liquid chromatography Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000001771 impaired effect Effects 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 150000002576 ketones Chemical class 0.000 description 1
- 150000002632 lipids Chemical class 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000015654 memory Effects 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 235000019629 palatability Nutrition 0.000 description 1
- 229920000642 polymer Chemical class 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- -1 that is Substances 0.000 description 1
- 238000013526 transfer learning Methods 0.000 description 1
- 238000011282 treatment Methods 0.000 description 1
- 239000011709 vitamin E Substances 0.000 description 1
- 229940046009 vitamin E Drugs 0.000 description 1
- 235000019165 vitamin E Nutrition 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A23—FOODS OR FOODSTUFFS; TREATMENT THEREOF, NOT COVERED BY OTHER CLASSES
- A23D—EDIBLE OILS OR FATS, e.g. MARGARINES, SHORTENINGS, COOKING OILS
- A23D9/00—Other edible oils or fats, e.g. shortenings, cooking oils
- A23D9/06—Preservation of finished products
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47J—KITCHEN EQUIPMENT; COFFEE MILLS; SPICE MILLS; APPARATUS FOR MAKING BEVERAGES
- A47J37/00—Baking; Roasting; Grilling; Frying
- A47J37/12—Deep fat fryers, e.g. for frying fish or chips
- A47J37/1266—Control devices, e.g. to control temperature, level or quality of the frying liquid
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N11/00—Investigating flow properties of materials, e.g. viscosity, plasticity; Analysing materials by determining flow properties
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/27—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands using photo-electric detection ; circuits for computing concentration
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/02—Food
- G01N33/03—Edible oils or edible fats
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/12—Hotels or restaurants
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/68—Food, e.g. fruit or vegetables
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
Definitions
- the present invention relates to a determination device, a learning device, a determination system, a determination method, a learning method, and a program.
- Cooking oil may be used for a long period of time when frying foods and the like. Cooking uses edible oil at a temperature of about 130°C to 180°C. The edible oil deteriorates when it is oxidized by oxygen or the like in the atmosphere. Thus, when deterioration occurs, for example, aldehydes, ketones, polymer compounds, and the like are generated. Such ingredients adversely affect taste and the like.
- a sensor measures the electrical properties of the edible oil.
- a technique of measuring such characteristics with a sensor and protecting the sensor with a coating is known (see Patent Document 1, for example).
- the cooking environment hereinafter referred to as the "cooking environment”
- the cooking environment for the fried food is not prepared.
- the conventional technology has problems in efficiently determining the cooking environment and obtaining information for adjusting the cooking environment.
- the purpose of the present invention is to determine the cooking environment in advance based on the state of edible oil, and to efficiently acquire information for adjusting the cooking environment to provide delicious fried food.
- a judgment device for judging the cooking environment of edible oil comprises: an imaging unit that acquires an image of the edible oil; a first input unit for inputting first information, which is information of fried food to be put into the edible oil and cooked; a first identifying unit that analyzes the image to identify the state of the edible oil; A second identification unit that identifies a cooking environment in which the fried food is cooked based on the first information and the state.
- the present invention it is possible to determine the cooking environment in advance based on the state of the cooking oil, and efficiently acquire information for adjusting the cooking environment to provide delicious fried food.
- FIG. It is a figure which shows the structural example of the kitchen 1.
- FIG. It is a figure which shows the hardware structural example of an information processing apparatus.
- 4 is a diagram showing an example of a scale 24;
- FIG. It is a figure which shows the example of an entire process.
- 1 is a diagram showing an example of an information system 200;
- FIG. It is a figure which shows an example of a network structure.
- FIG. 10 is a diagram showing an example in which a fly basket 3 is provided;
- FIG. 10 is a diagram showing a second example without the fly basket 3;
- FIG. 11 shows a second example with a fly basket 3;
- FIG. 10 is a diagram showing the example of the process which presumes the height of the surface of edible oil.
- FIG. 10 is a diagram showing an example of a boundary;
- FIG. 10 is a diagram showing an example of detection of a boundary;
- fried foods include fried chicken, croquettes, French fries, fried chicken, tempura, pork cutlets, and the like.
- FIG. 1 is a diagram showing a configuration example of the kitchen 1.
- An example of the edible oil is hereinafter referred to as "frying oil Y”.
- the kitchen 1 is, for example, inside a store such as a convenience store or a supermarket.
- the kitchen 1 is provided with facilities for cooking the fried food X.
- the facility is an electric fryer (Fryer, hereinafter simply referred to as "fryer 2").
- the fryer 2 is, for example, equipment having an oil tank 21, a housing 22, and the like.
- the oil tank 21 stores the frying oil Y. Also, the oil tank 21 is composed of, for example, a handle 30, a frying basket 3, and the like.
- the housing 22 accommodates the oil tank 21 .
- the housing 22 also has a switch 22A or the like on its side, which serves as a setting operation unit for setting the temperature of the frying oil Y or the contents of cooking for each type of fried food X.
- the cook When cooking, the cook first puts the fried food X into the fry basket 3. Next, the cook dips the fried food X into the frying oil Y and hooks the handle 30 to the upper end of the housing 22 . At the same time, or before or after, the cook presses the switch 22A according to the type of fried food X.
- the fryer 2 notifies the cook of the completion of frying when a predetermined frying time has elapsed according to the switch 22A. At the same time, the fryer 2 raises the frying basket 3 from the oil tank 21 . In this way, the fried food X is lifted from the state of being immersed in the frying oil.
- the notification method is, for example, a method of outputting a buzzer sound from a speaker, or a method of displaying on the monitor 41 installed on the wall 10A.
- the elapse of frying time is notified by light, sound, or a combination thereof.
- the cook pulls up the fry basket 3 and takes out the fried food X.
- the fly basket 3 may be pulled up by a driving mechanism or the like.
- the kitchen 1 is not limited to the configuration using the utensils shown in the figure.
- the fryer 2 is a cooking utensil capable of cooking, the type, arrangement, etc. may be other than those shown in the drawings.
- An imaging device for imaging the frying oil Y is installed in the kitchen 1.
- the imaging device is a video camera 42 .
- the video camera 42 is attached to the ceiling 10B or the like.
- the video camera 42 continuously takes images of the surface of the frying oil Y and generates images. In addition, it is desirable that the image be a moving image. Further, the conditions of the video camera 42, such as the angle of view and focus, are adjusted.
- the video camera 42 may be located at a position other than the ceiling 10B. That is, the video camera 42 may be attached to the wall 10A or the like as long as the frying oil Y can be photographed.
- the image capturing device does not necessarily have to capture images in the form of moving images. That is, for example, the imaging device may be a still camera, a tablet, or the like that captures still images. When a still camera or the like is used, an imaging device that can intermittently capture images in time series may be used.
- the imaging device may be a camera or the like included in a mobile device such as a tablet or a smartphone.
- the determination device 5 is configured to be connected to the monitor 41, the video camera 42, the flyer 2, and the like. Note that the determination device 5 does not always have to be connected to the video camera 42 or the like, and may be configured to separately acquire images captured by the video camera 42 from those once stored in a storage medium, and execute identification and the like. may
- the video camera 42 may be installed at a position other than the one shown.
- the installation position of the video camera 42 is, for example, a position where the scale 24 can be imaged.
- FIG. 2 is a diagram illustrating a hardware configuration example of an information processing apparatus.
- the determination device 5 is an information processing device having the following hardware resources.
- the determination device 5 has a Central Processing Unit (hereinafter referred to as "CPU 500A”), a Random Access Memory (hereinafter referred to as “RAM 500B”), and the like. Furthermore, the determination device 5 includes a Read Only Memory (hereinafter referred to as "ROM 500C”), a hard disk drive (hereinafter referred to as “HDD 500D”), an interface (hereinafter referred to as "I/F 500E”), etc. have a Central Processing Unit (hereinafter referred to as "CPU 500A”), a Random Access Memory (hereinafter referred to as "RAM 500B”), and the like. Furthermore, the determination device 5 includes a Read Only Memory (hereinafter referred to as "ROM 500C”), a hard disk drive (hereinafter referred to as "HDD 500D”), an interface (hereinafter referred to as "I/F 500E”), etc. have a Central Processing Unit (hereinafter referred to as "CPU 500A”), a Random Access Memory (hereinafter
- the CPU 500A is an example of an arithmetic device and a control device.
- the RAM 500B is an example of a main storage device.
- the ROM 500C and HDD 500D are examples of auxiliary storage devices.
- the I/F 500E connects an input device or an output device. Specifically, the I/F 500E connects an external device such as the monitor 41 or the video camera 42 by wire or wirelessly, and inputs/outputs data.
- the determination device 5 is not limited to the hardware configuration shown above.
- the determination device 5 may further include an arithmetic device, a control device, a storage device, an input device, an output device, or an auxiliary device.
- the information processing device may have an auxiliary device such as a Graphics Processing Unit (GPU) externally or internally.
- GPU Graphics Processing Unit
- the determination device 5 may be a plurality of devices.
- the determination device 5 specifies the state of cooking oil (hereinafter sometimes simply referred to as “state”) on the scale 24 . Specifically, first, the video camera 42 captures an image so that the scale 24 is reflected. Then, the determination device 5 acquires an image including the scale 24 from the video camera 42 .
- the scale 24 is written on the wall surface of the oil tank 21.
- the scale 24 indicates where the surface of the frying oil Y is positioned in the height direction. Therefore, when the scale 24 is imaged together with the frying oil Y, the surface height of the frying oil Y becomes clear.
- the determination device 5 can convert it into the amount of oil based on the height. Therefore, the scale 24 may be located at any position as long as the height or the like can be determined.
- the scale 24 may be configured as follows.
- FIG. 3 is a diagram showing an example of the scale 24.
- the scale 24 may be a line indicating the correct amount, as shown. When such a scale 24 is used, it is analyzed how far the mesh, which is the lower surface of the flyer 2, is with respect to the scale 24 in the image.
- the scale 24 may be, for example, the "appropriate oil amount line” described in "https://www.tanico.co.jp/category/maint/vol003/".
- the status may be other than the amount of oil. That is, states other than the amount of oil may be analyzed based on the image.
- the state may be the amount of oil, the difference from the optimum amount of edible oil (for example, the amount of oil that can provide the most delicious fried food determined by experiments, etc.), the temperature of edible oil, or a combination thereof.
- the state may be specified using something other than an image.
- sensors other than video camera 42 may be used to identify conditions.
- the sensors may include flow meters, weight scales, stereo cameras, light field cameras, and the like.
- the sensor is a device or the like capable of measuring distance, measuring weight, or measuring the amount of fluid.
- the senor may be a microphone, a thermometer, or an odor sensor.
- the determination device 5 may acquire measurement results from these sensors. In this way, by combining the analysis result of the image and the measurement result other than the image, the determination device 5 can accurately identify the state such as the amount of oil.
- FIG. 4 is a diagram illustrating an example of overall processing.
- the determination device 5 executes each process in the order of "pre-processing” and "execution process".
- Pre-processing is processing that is executed in advance in order to prepare for execution processing rather than execution processing.
- the pre-processing is a process of making preparations such as learning a learning model.
- the execution process is a process using the trained model prepared in the pre-processing.
- the execution process may be a process using a table or the like.
- the pre-processing is a process of preparing to input a table (also referred to as a lookup table (LUT), etc.) or the like.
- the execution process is a process using the table input in the pre-processing.
- the determination device 5 does not have to execute the preliminary processing and the execution processing in a continuous order as illustrated in the figure. Therefore, it is not essential to continue the period of preparation by preliminary processing and the subsequent period of execution processing.
- the learned model may be diverted, and the determination device 5 may start from the execution process, omitting the preprocessing.
- the learning model and the trained model may be configured to perform transfer learning, fine tuning, or the like. That is, the determination device 5 often has a different execution environment for each device. Therefore, the basic configuration of AI is learned by another information processing device. Thereafter, each determination device 5 may be further trained, set, or the like in order to be further optimized for each execution environment.
- step S0401 the determination device 5 prepares. Further, the content of the pre-processing differs depending on whether the configuration uses AI or the configuration uses a table.
- the determination device 5 makes preparations such as learning a learning model.
- the determination device 5 makes preparations such as inputting the table. The details of the preparation will be described later.
- execution processing example After the preprocessing is executed, that is, after the AI or the table is prepared, the determination device 5 performs execution processing, for example, in the following procedure.
- step S0402 the determination device 5 acquires an image of the cooking oil.
- the images may be images captured by a plurality of frames or by a plurality of devices.
- images a plurality of images or moving images will be simply referred to as "images”.
- the image be in color. That is, the image is preferably in a data format such as RGB or YCrCb. If color is used, analysis or recognition can be performed with high accuracy using color or the like.
- step S0403 the determination device 5 inputs the first information.
- the first information is information about fried food that is put into cooking oil and cooked. Specifically, the first information is information indicating a type of fried food, an input amount of fried food, or a combination thereof. Therefore, the first information is input in the form of a name for distinguishing the types of fried foods, or a format specifying the number of fried foods to be put in the oil tank 21 for cooking, or the like.
- step S0404 the determination device 5 analyzes the image and identifies the state. That is, the determination device 5 analyzes the image acquired in step S0402.
- step S0405 the determination device 5 determines the cooking environment.
- step S0406 the determination device 5 outputs based on the cooking environment and the like.
- step S0405 in the overall processing described above differ depending on whether the configuration uses AI or uses a table. Each configuration will be described separately below.
- FIG. 5 is a diagram showing an example of overall processing of a configuration using AI.
- the preprocessing is processing for learning the learning model A1.
- the execution process is a process of judging the cooking environment or the like using the learned model A2, which is a learning model that has completed learning to some extent by preprocessing or the like.
- Pre-processing is, for example, a process of learning a learning model using learning data D11. That is, the pre-processing is a process of making the learning model A1 learn by "supervised” learning using the learning data D11 to generate the trained model A2.
- the learning data D11 is, for example, data obtained by combining data such as the oil amount D111, the first information D112, and the cooking temperature D113.
- the amount of oil D111 is the amount of edible oil. Also, the oil amount D111 is an analysis result or the like obtained by analyzing the image acquired in step S0402.
- the oil amount D111 is preferably obtained by analyzing the image. That is, it is desirable to input the oil amount D111 in a format obtained by analyzing an image based on the scale 24 or the like.
- the determination device 5 can acquire information other than the oil amount D111 by analyzing the image. Therefore, when an image is input, the determination device 5 may be able to identify and learn the state that affects the cooking environment.
- the first information D112 is information indicating the type of fried food to be cooked under the conditions indicated by the amount of oil D111, the amount of input, or a combination thereof.
- the first information D112 is input as text data or the like, or is input by analyzing an image and specifying the type of fried food by image recognition.
- the cooking temperature D113 is an example of the cooking environment. That is, it is information indicating the result of the cooking temperature D113 when cooking is performed under the conditions indicated by the amount of oil D111 and the first information D112. Therefore, the cooking temperature D113 is information indicating in what kind of cooking environment the fried food is to be cooked, and is information that becomes "correct data" in the configuration of "supervised” learning.
- the cooking environment is not limited to the cooking temperature D113.
- the cooking environment may be the temperature at which fried food can be cooked, the amount of temperature drop when fried food is introduced, the degree of deterioration of cooking oil, or a combination thereof.
- the cooking environment is information indicating in what kind of environment the fried food is cooked using the current cooking oil.
- the cooking environment may be determined, for example, in the form of how much it deviates from the optimum cooking temperature.
- the cooking environment is determined in the form of, for example, the optimum cooking temperature cannot be maintained, that is, the extent to which the frying oil is not the optimum cooking environment under the current usage of cooking oil. good too.
- the determination device 5 can learn the relationship between the state and the combination of the first information and the cooking environment. By using the trained model A2 generated by such learning, the determination device 5 can execute the following processing.
- the execution process inputs the input data D12 and outputs the estimated result of the cooking temperature (hereinafter simply referred to as "estimated result D13").
- the determination device 5 inputs the input data D12 including the state such as the oil amount and the first information in the same format as the pre-processing.
- the execution processing differs in that the resulting cooking environment is unknown with respect to the state such as the amount of oil and the first information.
- the oil amount input in the execution process will be referred to as "unknown oil amount D121”.
- the first information input in the execution process is called “unknown first information D122”.
- the input data D12 is a combination of the unknown oil amount D121 and the unknown first information D122.
- the determination device 5 inputs the input data D12 to the learned model A2 (steps S0403 and S0404 in FIG. 4).
- the determination device 5 outputs an estimation result D13. That is, if cooking is performed under the conditions indicated by the input data D12, the cooking environment is estimated (step S0405 in FIG. 4).
- the determination device 5 can estimate the cooking environment and the like based on the learning.
- FIG. 6 is a diagram showing an example of overall processing of a configuration using a table.
- the pre-processing is the processing of generating the table D22.
- the execution process is a process of judging the cooking environment and the like using the table D22 generated in the pre-processing.
- the preprocessing is, for example, a process of putting together the experimental data D21 into a table format.
- the table D22 may not be a two-dimensional table as illustrated. That is, the data format of the table D22 does not matter as long as the cooking temperature D113 corresponding to the oil amount D111 and the first information D112 can be uniquely identified.
- the format of the table D22 shown in the figure will be described below as an example.
- the experimental data D21 is, for example, data obtained by combining data such as the oil amount D111, the first information D112, and the cooking temperature D113. Note that the oil amount D111, the first information D112, and the cooking temperature D113 are the same as those in FIG. 5, for example.
- the table D22 is data that associates the oil amount D111, the first information D112, and the cooking temperature D113. Note that the table D22 may include information other than those shown.
- the determination device 5 can associate the combination of the state and the first information with the cooking environment. By using such a table D22, the determination device 5 can execute the following processing.
- the determination device 5 inputs the input data D12 including the state such as the oil amount and the first information (steps S0403 and S0404 in FIG. 4), similar to the configuration using AI. .
- the input data D12 is a combination of the unknown oil amount D121 and the unknown first information D122 will be described as in the configuration using AI.
- the determination device 5 when the determination device 5 inputs a combination of the state and the first information from the input data D12, it extracts the corresponding cooking temperature from the table D22. Thus, the determination device 5 outputs the extraction result D23 in response to the input. That is, similar to the configuration using AI, when cooking is performed under the conditions indicated by the input data D12, the determination device 5 extracts from the table D22 the cooking environment in which the cooking is performed (step S0405).
- the determination device 5 can perform high-speed processing because it searches for the cooking temperature corresponding to the conditions that are input on the table D22.
- the determination device 5 may estimate the cooking environment or the like by linear interpolation or the like. That is, in the case of conditions not entered in the table D22, the determination device 5 may calculate the cooking environment by, for example, averaging similar conditions in the table D22.
- “oil amount is 200 g” and “oil amount is 250 g” are input to table D22, and "oil amount is 225 g" (that is, unknown) is executed.
- the determination device 5 may calculate an intermediate value between "oil amount is 200 g" and "oil amount is 250 g".
- the determination device 5 can handle conditions that are not entered in the table D22.
- the determination device 5 preferably specifies the amount of expansion and performs correction based on the amount of expansion.
- the amount of edible oil before correction that is, the amount of cooking oil obtained as a result of image analysis is referred to as a "first oil amount”.
- the amount of edible oil after correcting the first amount of oil by the expansion rate is referred to as the "second amount of oil”.
- the expansion rate can be specified, for example, based on the type of edible oil and temperature. That is, the determination device 5 can specify the expansion rate of the cooking oil to be determined by specifying the type of the cooking oil, the temperature, and the like.
- the volume of cooking oil changes depending on the temperature. Moreover, the expansion rate differs for each type of edible oil. Therefore, if the expansion rate is considered and the amount of oil is corrected, the determination device 5 can accurately specify the amount of oil.
- the determination device 5 identifies the type of edible oil by analyzing the image or inputting the name of the edible oil. Next, the determination device 5 identifies the temperature of the cooking oil by measurement or the like.
- the determination device 5 inputs in advance data that associates the type of cooking oil, the temperature set, and the coefficient of expansion.
- the determination device 5 inputs in advance a calculation formula or the like for calculating the expansion coefficient.
- the determination device 5 identifies the first oil amount and the expansion rate by analyzing the image or the like. Next, the determination device 5 corrects the first oil amount to identify the second oil amount. Specifically, the second oil amount is calculated by the following formula (1).
- 2nd oil amount 1st oil amount x temperature difference x expansion coefficient (1)
- the "temperature difference” is a value that indicates how many degrees of difference there is from the reference temperature of the current edible oil.
- the "expansion coefficient” is a value determined in advance by setting the type of cooking oil and the temperature. In this way, the determination device 5 multiplies the first oil amount by the temperature difference and the expansion coefficient, and performs correction based on the expansion coefficient.
- the correction is not limited to the calculation based on the formula (1) above, and any calculation method or the like can be used as long as the amount of oil before expansion can be specified by eliminating the influence of expansion due to temperature.
- the expansion rate may be calculated using specific gravity or the like.
- the determination device 5 can accurately identify the cooking environment and the like.
- step S0406 in FIG. 4 the determination device may further output the deliciousness identification result. That is, the judging device specifies the deliciousness when cooking in the cooking environment judged in step S0405.
- the deliciousness is the result of a comprehensive evaluation of the oiliness, smell, texture, and flavor of the fried food. For example, deliciousness is evaluated by sensory evaluation or the like.
- the cooking environment has a strong correlation with deliciousness. Therefore, if the cooking environment can be assumed, the determination device can specify how delicious the fried food will be in the assumed cooking environment. That is, deep-fried food can often be made more palatable when cooked at the optimum cooking temperature.
- An example in which the cooking temperature is set as the cooking environment will be described below.
- FIG. 7 is a diagram showing an example of specifying deliciousness. For example, a case where the overall processing shown in FIG. 4 is performed will be described.
- the determination device can prepare the learned model A2 or the table D22. After such preparations are completed, the determination device performs execution processing.
- step S0402 the determination device acquires the image IMG.
- step S0403 the determination device inputs the unknown first information D122.
- step S0404 the determination device inputs the unknown oil amount D121 based on the analysis result of the image IMG.
- the determination device determines the cooking environment in step S0405.
- the cooking environment is the cooking temperature, the temperature at which fried food X can be cooked, the amount of temperature drop when fried food X is added, the degree of deterioration of cooking oil, or a combination of these.
- the determination device can grasp at what temperature the fried food X is cooked.
- the cooking temperature has a strong correlation with the taste of the type of fried food X and the like. Specifically, deep-fried foods often cannot be delicious unless they are cooked at the optimum temperature.
- the cooking environment such as cooking temperature can often limit the temperature at which cooking can be done, depending on the amount of oil and the object to be cooked. Therefore, there is a strong correlation between the amount of oil, the type of fried food, and the like, and the cooking environment. Therefore, the determination device can estimate the deliciousness based on the cooking temperature or the like.
- the determination device may take into consideration preferences, as illustrated. That is, the determination device may estimate whether the taste matches the input preference.
- the taste may differ depending on each person's taste. For example, when deliciousness includes oiliness, some people like high oiliness and others dislike high oiliness. Preference indicates the optimal values of attributes that make up such palatability.
- preferences when preferences are entered, it is desirable that attributes that are objects of preferences be entered in the correct answer data or the table in order to correspond to preferences in pre-processing. Specifically, when the desired oiliness is input in the execution process, it is desirable to input the correct answer data or the result of the oiliness into the table.
- the determination device can determine the cooking environment, it may be possible to determine whether or not the cooking will be to your liking. In such a case, if the determination device grasps the relationship between the cooking environment and the target attribute of preference, it is not necessary to input the target attribute of preference to the correct answer data.
- the judgment device can estimate the deliciousness according to each person. Further, in step S0406, the determination device may output the taste of the fried food under the input conditions using numerical values, qualitative expressions, or the like.
- 2nd Embodiment differs from 1st Embodiment in the point which considers an oil supply, a waste oil, etc.
- FIG. 1st Embodiment differs from 1st Embodiment in the point which considers an oil supply, a waste oil, etc.
- FIG. 8 is a diagram showing an example of the second embodiment. Compared with FIG. 7, the second embodiment differs in that the oil amount is adjusted in step S0801.
- the unknown oil amount D121 changes as the oil amount increases or decreases.
- the determination device determines the cooking environment, taste, and the like.
- the input/output relationship is as follows.
- FIG. 9 is a diagram showing an example of the input/output relationship in the second embodiment.
- the unknown oil amount D121 may be generated by adjusting multiple patterns.
- the pattern in which the oil amount is not increased or decreased in other words, the pattern in which the current state is maintained without any adjustment is referred to as the "current state.”
- “Pattern 1" and “Pattern 2" are examples of making adjustments by adding oil, that is, cooking oil.
- “Pattern 1” is a pattern for adjusting the "current state” by adding "+200g” of cooking oil.
- “Pattern 2” is a pattern for adjusting the "current state” by adding "+250 g” of cooking oil.
- the pattern may be other than the above three. That is, there may be patterns in which parameters other than the amount of oil are different. Specifically, the patterns may be set such that the first information is different. An example in which only the amount of oil is changed for each pattern will be described below.
- the determination device determines the cooking environment for each pattern. Therefore, the determination device can output deliciousness for each cooking environment, that is, for each pattern.
- the evaluation of deliciousness is indicated by “ ⁇ ”, “ ⁇ ”, and “ ⁇ ” in descending order of evaluation.
- the deliciousness may be expressed numerically or in words.
- the deliciousness may have attributes, and may be in a format that indicates the evaluation result for each attribute and the evaluation result that integrates a plurality of attributes.
- the determination device outputs a message 50 or the like indicating the optimum pattern (in this example, "Pattern 2", which is the deliciousness of "o").
- the message 50 is output to a monitor or the like.
- the format of the message 50 may be any format.
- the determination device may control the adjuster 51 and the like so as to realize the optimum pattern.
- regulator 51 is a pump or the like. Therefore, when the determination device outputs a signal instructing the operation of the pump or the like to the regulator 51 or the like to control it, the oil amount can be adjusted by the operation of the pump or the like.
- the determination device may be configured to control related equipment such as the connected adjuster 51 so as to realize the optimum pattern.
- the determination device can adjust the cooking environment based on the result of determining the cooking environment in advance.
- the determination device may generate an optimal pattern. That is, the determination device may extract an adjustment amount or the like that makes the current taste higher than the current state.
- the determination device outputs the additional amount of additional oil that optimizes the cooking environment or deliciousness, the amount of waste oil, etc., based on the results of specifying the cooking environment or deliciousness.
- second information information indicating the amount of added cooking oil, the amount of waste oil, or a combination of these.
- the determination device may consider adjustments other than the second information, that is, other than the oil amount. For example, the determination device may adjust the timing of adding additional oil (hereinafter referred to as “first timing”) or the timing of discarding waste oil (hereinafter referred to as “second timing").
- first timing additional oil
- second timing the timing of discarding waste oil
- the timing of adding or discarding cooking oil may affect the preparation of the cooking environment. Therefore, the determination device may estimate which of the first timing and the second timing is the cooking environment in which more delicious fried food can be provided.
- the determination device may control the adjuster 51 or the like to adjust the cooking oil at the optimum first timing and second timing.
- the determination device may provide information regarding adjustments, etc. in the information system.
- FIG. 10 is a diagram showing an example of the information system 200.
- the information system 200 is constructed by connecting the determination devices 5 installed in each of the stores S1 to S3 via a communication line or the like.
- the store S2 (in this example, the store S2 is an izakaya) notifies the general headquarters H of the notification information.
- the general headquarters H analyzes the number of times or frequency of receiving the notification information.
- the general headquarters H analyzes the store S1 (store S1 is a tempura restaurant) and the store S3 (store S3 is a pork cutlet restaurant).
- the General Headquarters H will propose or provide guidance on whether the cooking oil is being used appropriately, whether it is being replaced as appropriate, and whether there is any waste.
- the general headquarters H may also manage the factory where the fryer 2 is installed. Also, the general headquarters H may exist in a store or a factory and manage the fryer 2 and the like in the facility.
- the notification information is notified to, for example, the edible oil manufacturer P and the distributor Q. Then, the manufacturer P draws up a manufacturing plan or a sales plan based on the reported information. In addition, distributor Q orders edible oil and purchases edible oil from manufacturer P based on the notification information. Then, the distributor Q delivers the edible oil or the like to the stores S1 to S3.
- the notification information is notified to collection company Z (collection company Z and manufacturer P may be the same company, etc.). Then, upon receiving the notification information, the collecting company Z collects the waste oil W. Specifically, when the recovery agent Z receives the notification information a predetermined number of times, the recovery agent Z visits the store S2 and recovers the waste oil W from the oil tank 21 of the fryer 2 .
- the notification information may also be notified to cleaning contractors.
- the cleaning operator visits the store S2 and cleans the inside of the oil tank 21 of the fryer 2 or the vicinity thereof.
- the notification information is used as described above, it is possible to quickly perform operations from supply to waste oil and cleaning at stores S1 to S3. Further, automating the exchange of cooking oil and the like can further reduce the burden on the user (for example, a store clerk). Specifically, when notification information such as that the degree of deterioration exceeds a threshold value is output, the cooking oil in use is replaced with new cooking oil or the like.
- the determination device 5 when additional oil or waste oil is generated in the adjustment, the determination device 5 sends the amount of edible oil to the general headquarters H, the recovery company Z, the manufacturer P, etc. The time when additional oil or waste oil is generated may be notified. In this way, if the information system 200 can automate ordering, collection, delivery, and procedures for additional oil or waste oil, the user's workload can be reduced.
- AI is realized by, for example, the following network.
- FIG. 11 is a diagram showing an example network structure.
- a learning model and a trained model are structures of network 300 as follows.
- the network 300 has, for example, an input layer L1, an intermediate layer L2 (also referred to as a "hidden layer”), an output layer L3, and the like.
- the input layer L1 is a layer for inputting data.
- the intermediate layer L2 converts the data input in the input layer L1 based on weights, biases, and the like.
- the results processed in the intermediate layer L2 are transmitted to the output layer L3.
- the output layer L3 is a layer that outputs inference results and the like.
- the network 300 is not limited to the illustrated network structure.
- AI may be realized by other machine learning.
- the degree of deterioration is, for example, the acid value of the edible oil, the viscosity of the edible oil, the viscosity increase rate of the edible oil, the color tone of the edible oil, the anisidine value of the edible oil, the amount of polar compounds in the edible oil, the carbonyl value of the edible oil, and the edible oil.
- the acid value (acid value, sometimes referred to as "AV") of edible oil is, for example, a value measured by a method according to the Standard Fat Analysis Test Method 2.3.1-2013.
- the viscosity increase rate of the edible oil is based on, for example, the viscosity before the edible oil is replaced and the new oil is used to fry the food for the first time (that is, the viscosity at the start of use), etc., and the ratio of the amount of viscosity increase to the standard. It is a value calculated by The viscosity is measured with a viscometer or the like.
- the viscometer is an E-type viscometer (TVE-25H, manufactured by Toki Sangyo Co., Ltd.).
- the color tone of edible oil (sometimes referred to as “color” or “hue”) is, for example, a value measured by a method according to the Standard Fat Analysis Test Method 2.2.1.1-2013 (e.g., yellow component value and the red component value, the value is calculated by yellow component value+10 ⁇ red component value).
- the anisidine value of edible oil is a value measured by a method according to the Standard Fat Analysis Test Method 2.5.3-2013.
- the amount of polar compounds in edible oil is a value measured by a method according to the Standard Fat Analysis Test Method 2.5.5-2013.
- the amount of polar compounds in edible oil is a value measured by a polar compound measuring device (devices such as those manufactured by Testo Co., Ltd.).
- the carbonyl value of an edible oil is, for example, a value measured by a method according to Standard Fat Analysis Test Method 2.5.4.2-2013.
- the smoke point of edible oil is a value measured by a method that conforms to the Standard Fat Analysis Test Method 2.2.11.1-2013. Smoke is generated by combustion of lipids contained in edible oil or decomposition products thereof.
- the tocopherol (sometimes referred to as "vitamin E") content of edible oil is the amount of tocopherol contained in the edible oil.
- tocopherol is a value measured by a method according to a high performance liquid chromatography (HPLC) method or the like.
- the iodine value of edible oil indicates, for example, the number of grams of iodine that can be added to 100 grams of oil.
- the iodine value of the edible oil is, for example, a value measured by a method according to Standard Fat Analysis Test Method 2.3.41-2013.
- the refractive index of edible oil is, for example, a value measured by a method according to the Standard Fat Analysis Test Method 2.2.3-2013.
- Volatile components such as the amount of volatile components of edible oil, the volatile component composition of edible oil, the amount of volatile components of fried food fried in edible oil, and the volatile component composition of fried food are obtained from fried food or edible oil It is determined by volatile components (mainly odorous components) and the like. In addition, the amount or composition of volatile components changes as the edible oil deteriorates. For example, volatile components are measured with a gas chromatograph-mass spectrometer (GC-MS), an odor sensor, or the like.
- GC-MS gas chromatograph-mass spectrometer
- Flavors such as the flavor of edible oil and the flavor of fried foods are values measured by sensory evaluation (for example, a method of actually eating and evaluating by people) or by a taste sensor or the like.
- FIG. 12 is a diagram illustrating a functional configuration example.
- the determination device 5 has a functional configuration including an imaging unit 5F1, a first input unit 5F2, a first specifying unit 5F3, a second specifying unit 5F4, and the like.
- the determination device 5 preferably has a functional configuration further including a second input section 5F5, an output section 5F6, an adjustment section 5F7, and the like.
- the illustrated functional configuration will be described below as an example.
- the imaging unit 5F1 performs an imaging procedure for acquiring an image of the cooking oil.
- the imaging unit 5F1 is implemented by the video camera 42, the I/F 500E, and the like.
- the first input unit 5F2 performs the first input procedure of inputting the first information.
- the first input section 5F2 is realized by an I/F 500E or the like.
- the first identification unit 5F3 analyzes the image and performs the first identification procedure of identifying the state.
- the first specifying unit 5F3 is realized by the CPU 500A or the like.
- the second specifying unit 5F4 performs a second specifying procedure for specifying the cooking environment in which the fried food is cooked based on the first information and the state.
- the second specifying unit 5F4 is realized by the CPU 500A or the like.
- the second input unit 5F5 performs a second input procedure of inputting second information indicating the additional amount of additional oil, the amount of waste oil, or a combination thereof.
- the second input section 5F5 is realized by an I/F 500E or the like.
- the output unit 5F6 outputs the additional amount of additional oil that optimizes the cooking environment and deliciousness, the amount of waste oil, the first timing, the second timing, or any of these based on the cooking environment or the result of specifying the deliciousness. Perform the output procedure to output the combination.
- the output unit 5F6 is realized by an I/F 500E or the like.
- the adjustment unit 5F7 performs an adjustment procedure for adding, discarding, or both of the cooking oil based on the output result from the output unit 5F6.
- the adjuster 5F7 is realized by the adjuster 51 or the like.
- the determination system 7 having the determination device 5 and the learning device 6 has, for example, the following functional configuration.
- a case where the learning device 6 has the same hardware configuration as the determination device 5 will be taken as an example below.
- the determination device 5 and the learning device 6 may have different hardware configurations.
- the learning device 6 for example, similarly to the determination device 5, has a functional configuration including an imaging unit 5F1, a first input unit 5F2, a first specifying unit 5F3, and the like. However, as long as the learning device 6 can input the state and the first information, the configuration of the input and the format of the data do not matter.
- functional configurations similar to those of the determination device 5 are denoted by the same reference numerals, and descriptions thereof are omitted.
- the cooking environment input unit 5F8 performs a cooking environment input procedure for inputting the cooking environment in which fried foods are cooked.
- the cooking environment input unit 5F8 is realized by an I/F 500E or the like.
- the generation unit 5F9 performs a generation procedure for learning the learning model A1 and generating a trained model A2. Alternatively, the generation unit 5F9 performs a generation procedure for generating the table D22.
- the generation unit 5F9 is realized by the CPU 500A or the like.
- the learned model A2 generated by the learning device 6 or the table D22 is distributed from the learning device 6 to the determination device 5 or the like via a network or the like.
- the learning device 6 By preprocessing, the learning device 6 generates a learned model A2 or a table D22. With such a learned model A2 or table D22, the determination device 5 can determine the cooking environment in advance based on the state of the cooking oil by executing processing. If such determination, that is, information such as what kind of cooking environment it will be or the deviation from the optimal cooking environment is known before cooking, it will be easier to prepare the cooking environment to provide delicious fried food. becomes easier.
- the user can efficiently acquire information such as how to prepare the cooking environment, compared to the case of adjusting the amount of oil, etc. by trial and error.
- the determination device 5 may generate and utilize thermography data.
- FIG. 13 is a diagram showing an example of thermography data.
- the thermography data shown in the figure is an example of data generated by measuring the temperature of edible oil in a setting where the edible oil is heated to 180°C using "FLIR (registered trademark) Systems FLIR E4" as a measuring device. be.
- Thermography data is data that shows the temperature distribution of cooking oil in color.
- thermography data is generated by measuring the infrared rays emitted by cooking oil and plotting the temperature at each measurement point with color pixels.
- the illustrated example is an example of thermography data in which temperatures are color-coded in the range of 20°C to 190°C.
- the coefficient of expansion is a value that varies with temperature.
- temperature is not always uniformly distributed in edible oils. That is, edible oil may have different temperatures depending on the location. Even if the temperature is biased in this way, if there is thermography data, the determination device 5 can grasp the temperature for each position, and even if there is temperature bias, etc., the expansion rate can be specified with high accuracy. .
- the temperature may be measured, for example, for each area set in advance as follows (hereinafter referred to as "area").
- FIG. 14 is a diagram showing an example of areas.
- the figure shows an example in which the entire area for temperature measurement is set so as to be divided into six areas in FIG. 13 .
- the division method is not limited to the illustrated example. That is, the areas do not have to be even, and may be divided into areas other than six.
- the area does not have to be the entire area.
- the area is desirably set by extracting an area where there is no heating wire and there is cooking oil out of the entire area. In other words, it is desirable to set the area so as to avoid areas where there are heating wires. If there is a heating wire, it may be measured higher depending on the temperature of the heating wire. Therefore, if the area is set by excluding the high-temperature part such as the heating wire, the temperature can be measured with high accuracy.
- the scale 24 can be determined from the image, it is desirable to set the area by extracting the area including the scale 24 . That is, the area is preferably set with respect to the area where the scale 24 can be seen.
- the temperature measurement range it is desirable to perform the measurement excluding the measurement result of the object other than edible oil.
- the determination device 5 also specifies the expansion rate and the like for each area. For example, the determination device 5 statistically processes a plurality of measurement results indicated by the thermography data for each area (for example, averaging the measurement results belonging to the area) to identify the temperature of each area.
- the temperature may be measured by installing a thermometer for each area.
- the determination device 5 further include a temperature measurement unit. Then, the determination device 5 specifies the expansion coefficient for each measurement result indicating the temperature distribution of the cooking oil.
- the determination device 5 can consider the temperature distribution, it can accurately identify the expansion coefficient.
- the determination device 5 preferably considers the fly basket 3 and the like as follows. For example, when there is no fly basket 3, the thermography data are as shown in FIG. On the other hand, when the fly basket 3 is present, the thermographic data are as follows.
- FIG. 15 is a diagram showing an example in which the fly basket 3 is present. Compared with FIG. 13, it differs in that there is a fly basket 3. FIG. On the other hand, both Figs. 13 and 15 are settings for heating the edible oil to 177°C.
- the temperature measurement result tends to be low even under the same heating conditions as in the case without the fry basket 3 as shown in FIG. Specifically, when the fry basket 3 is present, the temperature distribution has many low temperature portions due to the temperature of the fry basket 3 . As a result, similar to the example shown in FIG. 13, even if the thermography data is used to identify the temperature of the cooking oil based on the position, the temperature is identified as a low value. Such a tendency is the same even if conditions such as a fryer are changed.
- FIG. 16 is a diagram showing a second example without the fly basket 3.
- FIG. 17 is a diagram showing a second example with a fly basket 3.
- FIG. 17 is a diagram showing a second example with a fly basket 3.
- FIG. 13 and 15 have a fryer capacity of 3 liters
- Figs. 16 and 17 have a fryer capacity of 7 liters.
- 13 and 15 are for the heating condition of 177° C.
- FIGS. 16 and 17 are for the heating condition of 180° C.
- FIG. 13 and 15 are for the heating condition of 177° C.
- FIGS. 16 and 17 differ in the presence or absence of the fly basket 3.
- the fly basket 3 recognizes the shape or the like based on the image or thermography data, and the determination device 5 grasps the presence or absence.
- the presence or absence of the fry basket 3 may be grasped by the weight or by the user's operation.
- the determination device 5 may correct the temperature measurement result. That is, the determination device 5 may grasp the temperature that is lowered by the fry basket 3 in advance, and when determining that there is the fry basket 3, correct the temperature for the amount that is lowered, and specify the expansion rate and the like. .
- the temperature may be measured with high accuracy, for example, when the surface of the cooking oil is visible.
- the determination device 5 corrects the temperature measurement result based on the thermography data. may be performed.
- the determination device 5 may use the temperature difference due to the fry basket 3 to estimate the height of the surface of the cooking oil.
- the determination device 5 is equipped with a measurement device for measuring temperature on the fryer side, in addition to the measurement device for generating thermography data.
- the measuring device that measures the temperature on the fryer side will be referred to as the "first measuring device”
- the measuring device that measures the temperature for thermography data will be referred to as the "second measuring device”.
- first measurement result the measurement result of the first measuring device
- second measurement result the measurement result of the second measuring device
- the scale 24 shown in FIG. 3 may be difficult to see from the video camera 42 shown in FIG.
- the determination device 5 estimates the height of the surface of the cooking oil based on the temperature difference between the first measurement result and the second measurement result.
- Thermography data often measures low temperatures when the amount of cooking oil is small. Therefore, when the amount of edible oil is small, the temperature difference between the first measurement result and the second measurement result tends to increase. Therefore, the height of the surface of the cooking oil can be estimated from the temperature difference between the first measurement result and the second measurement result.
- the determination device 5 further includes a first temperature measuring unit that measures the temperature of the cooking oil in the oil tank that stores the cooking oil, and a second temperature measuring unit that measures the temperature of the cooking oil from the surface of the cooking oil. Prepare. Then, the determination device 5 specifies the temperature difference between the first measurement result, which is the result of measurement by the first temperature measurement unit, and the second measurement result, which is the result of measurement by the second measurement result.
- the determination device 5 further includes a determination unit that determines whether cooking utensils such as the fry basket 3 are present.
- the determination device 5 estimates the height of the surface of the cooking oil based on the temperature difference between the first measurement result and the second measurement result. By estimating the height of the surface of the edible oil in this manner, the determination device 5 can accurately estimate the height of the surface of the edible oil.
- Thermographic data may be used to estimate the surface height of edible oils.
- FIG. 18 is a diagram showing an example of processing for estimating the height of the surface of edible oil. For example, the process as shown is performed before the process of identifying the surface height of the edible oil, ie, the amount of oil.
- step S1801 the determination device 5 determines whether or not the scale can be seen.
- Whether or not the scale can be seen is determined, for example, by the presence or absence of the fry basket 3. Specifically, for example, as shown in FIG. 17, when it can be determined that there is a fly basket 3, it is determined that the scale cannot be seen (NO in step S1801).
- the determination device 5 may determine whether or not the scale is visible based on factors other than the presence or absence of the fly basket 3. For example, the scale 24 may be difficult to see due to malfunction of the camera 42, polymerized material, fried scum, or the like. Therefore, the determination device 5 may determine that the scale cannot be seen when the scale 24 cannot be recognized as a result of image recognition of the scale 24 in the image (NO in step S1801).
- the determination of whether or not the scale can be seen may be made based on the estimation results. Specifically, the determination device 5 may estimate whether or not there is a line where the temperature changes abruptly, and determine whether or not the scale can be seen, as follows.
- the determination device 5 may determine that the scale is visible (YES in step S1801). That is, when it can be determined that there is a line where the temperature changes rapidly, the determination device 5 may directly identify the position of the oil level.
- FIG. 19 is a diagram showing an example of boundaries.
- boundary 55 is a line where the temperature changes abruptly.
- FIG. 20 is a diagram showing an example of boundary detection.
- the figure shows an example of the result of measuring the temperature near the boundary 55 for each pixel.
- the determination device 5 determines a pixel for which a relatively high temperature is measured (hereinafter referred to as a "high temperature pixel 551”) and a pixel for which a low temperature is measured compared to the high temperature pixel 551 (hereinafter referred to as a "low temperature pixel 552"). ) is determined to exist.
- the temperature of the high-temperature pixel 551 is "160° C.” or higher.
- the cold pixel 552 is below "160 degrees Celsius”.
- the determination device 5 determines that the temperature has changed abruptly beyond the threshold.
- the determination device 5 recognizes such a portion as the boundary 55 .
- the threshold for judging the boundary 55 is a preset value.
- the determination device 5 determines that the scale can be seen (YES in step S1801).
- step S1801 when determining that the scale can be seen (YES in step S1801), the determination device 5 proceeds to step S1802. On the other hand, when determining that the scale cannot be seen (NO in step S1801), the determination device 5 proceeds to step S1803.
- step S1802 the determination device 5 uses the scale to specify the height of the surface of the cooking oil.
- step S1803 the determination device 5 identifies the height of the surface of the edible oil using the thermography data. That is, the determination device 5 estimates the height of the surface of the cooking oil based on the temperature difference between the first measurement result and the second measurement result.
- the determination device 5 can accurately identify the surface height of the edible oil.
- the determination device 5 uses the scale when the scale can be recognized from the image, or when it can be determined that the scale can be seen, such as when there is a line where the temperature changes rapidly.
- the height is specified (step S1802). Note that the determination device 5 may use thermography data to specify the height of the surface of the edible oil using the scale.
- the determination device 5 determines that the scale is difficult to see, it identifies the height of the surface of the cooking oil using thermography data (step S1803).
- the amount of edible oil may be specified by multiple treatments.
- the determination device 5 may specify the height of the surface of the edible oil using thermography data even when the scale is visible. Then, when performing a plurality of processes, the determination device 5 may perform statistical processing such as averaging the results of a plurality of processes to finally specify the amount of cooking oil.
- Modification Some or all of the parameters may be obtained from data other than the image, input by the user, or the like.
- the expiration date for example, for fried foods, the expiration date, weight, temperature, humidity, size, arrangement of fried foods in cooking, thickness, ratio of batter, or a combination of these may be considered.
- the determination device may estimate the degree of deterioration of the cooking oil.
- the estimation result may be in the form of the tendency of deterioration, whether it is time to replace the cooking oil, or the result of estimating the time to replace the cooking oil.
- the estimation result is displayed on the monitor in a format such as "The current degree of deterioration is XX%.”
- the monitor indicates the current timing in percentage form with respect to the future timing when the degree of deterioration is "100%”.
- the monitor may display a determination result such as, for example, "Please replace the frying oil.”
- the monitor displays, for example, "The remaining number of fried foods is 0", "Next time, the number of fried foods that can be cooked is 0 ⁇ is ⁇ , or ⁇ is ⁇ .” That is, the monitor may display the type of fried food and the number of fried foods that can be cooked before the replacement time is reached, based on the determination result of the determination device.
- the determination device performs both pre-processing for the learning model and execution processing using the trained model.
- the preprocessing and the execution processing may not be performed by the same information processing device.
- the pre-processing and the execution processing may not be consistently executed by one information processing apparatus. That is, each process, data storage, and the like may be performed by an information system or the like composed of a plurality of information processing apparatuses.
- determination device or the like may perform additional learning after the execution process or before the execution process.
- the embodiment may be a combination of the above embodiments.
- a process for reducing overfitting such as dropout (also referred to as “overfitting” or “overfitting”) may be performed.
- preprocessing such as dimensionality reduction and normalization may be performed.
- a learning model and a trained model may have a CNN network structure or the like.
- the network structure may have a configuration such as RNN (Recurrent Neural Network) or LSTM (Long Short-Term Memory). That is, AI may be a network structure or the like other than deep learning.
- the learning model and the trained model may be configured with hyperparameters. That is, the learning model and the learned model may be partially configured by the user. Furthermore, the AI may specify the feature amount to be learned, or the user may set some or all of the feature amounts to be learned.
- the learning model and the trained model may use other machine learning.
- the learning model and the trained model may be subjected to preprocessing such as normalization by an unsupervised model.
- the learning may be reinforcement learning or the like.
- preprocessing may be performed by expanding one piece of experimental data or the like into a plurality of pieces of learning data. By increasing the amount of learning data in this way, the learning of the learning model can be further advanced.
- program including firmware and programs equivalent thereto, hereinafter simply referred to as "program" that executes the determination method, the learning method, or the processing equivalent to the above-exemplified processing.
- the present invention may be implemented by a program or the like written in a programming language or the like so as to issue a command to a computer and obtain a predetermined result.
- the program may have a configuration in which part of the processing is executed by hardware such as an integrated circuit (IC) or an arithmetic unit such as a GPU.
- the program causes the computer to execute the above-described processes by cooperating with the arithmetic device, control device, storage device, etc. of the computer. That is, the program is loaded into the main storage device or the like, issues instructions to the arithmetic unit to perform arithmetic operation, and operates the computer.
- the program may be provided via a computer-readable recording medium or an electric communication line such as a network.
- the present invention may be implemented in a system composed of multiple devices. That is, a multi-computer information processing system may perform the processes described above redundantly, in parallel, distributed, or in a combination thereof. Therefore, the present invention may be realized by devices with hardware configurations other than those shown above, and systems other than those shown above.
- the present invention has been described above.
- the present invention is not limited to the above-described embodiments, and includes various modifications.
- the above-described embodiments have been described in detail in order to explain the present invention in an easy-to-understand manner, and are not necessarily limited to those having all the configurations described.
- part of the configuration of this embodiment can be replaced with the configuration of another embodiment, and it is also possible to add the configuration of another embodiment to the configuration of this embodiment.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Chemical & Material Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Tourism & Hospitality (AREA)
- Food Science & Technology (AREA)
- Biochemistry (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Analytical Chemistry (AREA)
- Multimedia (AREA)
- Marketing (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Medicinal Chemistry (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Oil, Petroleum & Natural Gas (AREA)
- Polymers & Plastics (AREA)
- Frying-Pans Or Fryers (AREA)
- Image Analysis (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
Description
食用油を撮像した画像を取得する撮像部と、
前記食用油へ投入して調理する揚げ物の情報である第1情報を入力する第1入力部と、
前記画像を解析して、前記食用油の状態を特定する第1特定部と、
前記第1情報と、前記状態とに基づき、前記揚げ物が調理される調理環境を特定する第2特定部とを備える。
まず、調理が行われる環境として想定される調理場1の一構成例について、図1を参照して説明する。
図2は、情報処理装置のハードウェア構成例を示す図である。例えば、判定装置5は、以下のようなハードウェア資源を有する情報処理装置である。
例えば、判定装置5は、目盛24で食用油の状態(以下単に「状態」という場合がある。)を特定する。具体的には、まず、ビデオカメラ42は、目盛24が映り込むように画像を撮像する。そして、判定装置5は、目盛24が写る画像をビデオカメラ42から取得する。
図4は、全体処理例を示す図である。例えば、判定装置5は、図示するように、「事前処理」、及び、「実行処理」の順に各処理を実行する。
ステップS0401では、判定装置5は、準備を行う。また、事前処理は、AIを用いる構成であるか、又は、テーブルを用いる構成であるかにより処理の内容が異なる。
事前処理が実行された後、すなわち、AI又はテーブルが準備された後、判定装置5は、例えば、以下のような手順で実行処理を行う。
図5は、AIを用いる構成の全体処理例を示す図である。図示するように、AIを用いる構成では、事前処理は、学習モデルA1を学習する処理である。そして、実行処理は、事前処理等によって、ある程度の学習が完了した学習モデルである、学習済みモデルA2を用いて調理環境等を判定する処理である。
図6は、テーブルを用いる構成の全体処理例を示す図である。図示するように、テーブルを用いる構成では、事前処理は、テーブルD22を生成する処理である。そして、実行処理は、事前処理で生成したテーブルD22を用いて調理環境等を判定する処理である。
判定装置5は、膨張量の特定、及び、膨張量に基づく補正を行うのが望ましい。以下、補正を行う前、すなわち、画像の解析結果で得られる食用油の量を「第1油量」という。一方で、第1油量を膨張率で補正した後の食用油の量を「第2油量」という。
上記(1)式において、「温度差」は、現在の食用油が基準とする温度に対して、何℃差があるかを示す値である。また、上記(1)式において、「膨張率」は、食用油の種類、及び、温度のセットで事前に定まる値である。このように、判定装置5は、第1油量に、温度差、及び、膨張率を乗じる計算を行って、膨張率に基づく補正を行う。
図4におけるステップS0406では、判定装置は、美味しさの特定結果を更に出力してもよい。すなわち、判定装置は、ステップS0405で判定する調理環境で調理した場合の美味しさを特定する。
第2実施形態は、差し油、及び、廃油等を考慮する点が第1実施形態と異なる。
AIは、例えば、以下のようなネットワークで実現する。
劣化度は、例えば、食用油の酸価、食用油の粘度、食用油の粘度上昇率、食用油の色調、食用油のアニシジン価、食用油の極性化合物量、食用油のカルボニル価、食用油の発煙点、食用油のトコフェロール含量、食用油のヨウ素価、食用油の屈折率、食用油の揮発性成分量、食用油の揮発性成分組成、食用油の風味、食用油で揚げた揚げ物の揮発性成分量、揚げ物の揮発性成分組成、揚げ物の風味、又は、これらの組み合わせ等でもよい。
図12は、機能構成例を示す図である。例えば、判定装置5は、撮像部5F1、第1入力部5F2、第1特定部5F3、及び、第2特定部5F4等を備える機能構成である。なお、図示するように、判定装置5は、第2入力部5F5、出力部5F6、及び、調整部5F7等を更に備える機能構成であるのが望ましい。以下、図示する機能構成を例に説明する。
判定装置5は、サーモグラフィ(thermography)データを生成して利用してもよい。
判定装置5は、以下のように、フライバスケット3等を考慮するのが望ましい。例えば、フライバスケット3が無い場合には、サーモグラフィデータは、図13のようになる。一方で、フライバスケット3が有る場合には、サーモグラフィデータは、以下のようになる。
サーモグラフィデータは、食用油の表面の高さを推定するのに用いてもよい。
パラメータの一部、又は、全部は、画像以外のデータ、又は、ユーザによる入力等で取得されてもよい。
上記の例では、判定装置は、学習モデルに対する事前処理、及び、学習済みモデルを用いて実行処理の両方を行う。ただし、事前処理、及び、実行処理は、同じの情報処理装置が行わなくともよい。また、事前処理、及び、実行処理も、1つの情報処理装置で一貫して実行しなくともよい。すなわち、各処理、及び、データの記憶等は、複数の情報処理装置で構成する情報システム等で行ってもよい。
5F1 :撮像部
5F2 :第1入力部
5F3 :第1特定部
5F4 :第2特定部
5F5 :第2入力部
5F6 :出力部
5F7 :調整部
5F8 :調理環境入力部
5F9 :生成部
6 :学習装置
7 :判定システム
24 :目盛
41 :モニタ
42 :ビデオカメラ
51 :調整器
200 :情報システム
300 :ネットワーク
A1 :学習モデル
A2 :学習済みモデル
D11 :学習データ
D111 :油量
D112 :第1情報
D113 :調理温度
D12 :入力データ
D121 :未知油量
D122 :未知第1情報
D13 :推定結果
D22 :テーブル
IMG :画像
L1 :入力層
L2 :中間層
L3 :出力層
W :廃油
X :揚げ物
Y :揚げ油
Z :回収業者
Claims (17)
- 食用油の調理環境を判定する判定装置であって、
前記食用油を撮像した画像を取得する撮像部と、
前記食用油へ投入して調理する揚げ物の情報である第1情報を入力する第1入力部と、
前記画像を解析して、前記食用油の状態を特定する第1特定部と、
前記第1情報と、前記状態とに基づき、前記揚げ物が調理される前記調理環境を特定する第2特定部とを備える判定装置。 - 前記食用油に追加する追加油の追加量、前記食用油のうち廃棄する廃油の廃油量、又は、これらの組み合わせを示す第2情報を入力する第2入力部を更に備える請求項1に記載の判定装置。
- 前記調理環境は、
前記揚げ物を調理できる温度、前記揚げ物を投入すると低下する温度の低下量、前記食用油の劣化度、又は、これらの組み合わせである請求項1又は2に記載の判定装置。 - 前記食用油の劣化度は、
前記食用油の酸価、前記食用油の粘度、前記食用油の粘度上昇率、前記食用油の色調、前記食用油のアニシジン価、前記食用油の極性化合物量、前記食用油のカルボニル価、前記食用油の発煙点、又は、前記食用油の揮発性成分量である請求項3に記載の判定装置。 - 前記状態は、
前記食用油の量、前記食用油の最適量に対する差分、前記食用油の温度、又は、これらの組み合わせである請求項1乃至4のいずれか1項に記載の判定装置。 - 前記第2特定部は、
前記第1情報、及び、前記状態の組み合わせを含む入力データと、前記調理環境との関係を示すテーブル、又は、
前記入力データ、及び、前記調理環境の関係を機械学習した学習済みモデルを用いて前記調理環境を特定する請求項1乃至5のいずれか1項に記載の判定装置。 - 前記第1情報は、
前記揚げ物の種類、前記揚げ物の投入量、又は、これらの組み合わせを示す情報である請求項1乃至6のいずれか1項に記載の判定装置。 - 前記第2特定部は、
前記調理環境で調理した場合の前記揚げ物の美味しさを更に特定し、
前記調理環境、又は、前記美味しさの特定結果に基づき、前記調理環境、前記美味しさが最適となる前記食用油に追加する追加油の追加量、前記食用油のうち廃棄する廃油の廃油量、前記追加油を追加する第1タイミング、前記廃油を廃棄する第2タイミング、又は、これらの組み合わせを出力する出力部を更に備える請求項1乃至7のいずれか1項に記載の判定装置。 - 前記出力部による出力結果に基づき、
前記食用油の追加、廃棄、又は、両方を行う調整部を更に備える請求項8に記載の判定装置。 - 前記状態は、
前記食用油の量を示す第1油量であって、
前記第1特定部は、
前記食用油の膨張率を特定し、
前記膨張率に基づいて、前記第1油量を補正して第2油量を特定し、
前記第2特定部は、
前記第1情報と、前記第2油量とに基づき、前記調理環境を特定する請求項1乃至9のいずれか1項に記載の判定装置。 - 前記第2特定部は、
前記第1情報、及び、前記状態、並びに、前記調理環境の相関関係に基づき、前記調理環境を特定する請求項1乃至10のいずれか1項に記載の判定装置。 - 学習モデルを学習させて、食用油の調理環境を判定する学習済みモデルを生成する学習装置であって、
前記食用油を撮像した画像を取得する撮像部と、
前記食用油へ投入して調理する揚げ物の情報である第1情報を入力する第1入力部と、
前記画像を解析して、前記食用油の状態を特定する第1特定部と、
前記揚げ物が調理される前記調理環境を入力する調理環境入力部と、
前記第1情報、前記状態、及び、前記調理環境を入力して、前記学習モデルを学習させて前記学習済みモデルを生成する生成部とを備える学習装置。 - 請求項1乃至11のいずれか1項に記載の判定装置と、
請求項12に記載の学習装置とを有する判定システム。 - 食用油の調理環境を判定する判定方法であって、
前記食用油を撮像した画像を取得する撮像手順と、
前記食用油へ投入して調理する揚げ物の情報である第1情報を入力する第1入力手順と、
前記画像を解析して、前記食用油の状態を特定する第1特定手順と、
前記第1情報と、前記状態とに基づき、前記揚げ物が調理される前記調理環境を特定する第2特定手順とを備える判定方法。 - 請求項14に記載の判定方法をコンピュータに実行させるためのプログラム。
- 学習モデルを学習させて、食用油の調理環境を判定する学習済みモデルを生成する学習方法であって、
前記食用油を撮像した画像を取得する撮像手順と、
前記食用油へ投入して調理する揚げ物の情報である第1情報を入力する第1入力手順と、
前記画像を解析して、前記食用油の状態を特定する第1特定手順と、
前記揚げ物が調理される前記調理環境を入力する調理環境入力手順と、
前記第1情報、前記状態、及び、前記調理環境を入力して、前記学習モデルを学習させて前記学習済みモデルを生成する生成手順とを備える学習方法。 - 請求項16に記載の学習方法をコンピュータに実行させるためのプログラム。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US18/281,738 US20240159659A1 (en) | 2021-03-25 | 2022-03-11 | Determination device, learning device, determination system, determination method, learning method, and program |
CA3213613A CA3213613A1 (en) | 2021-03-25 | 2022-03-11 | Determination device, learning device, determination system, determination method, learning method, and program |
JP2022526817A JP7171970B1 (ja) | 2021-03-25 | 2022-03-11 | 判定装置、学習装置、判定システム、判定方法、学習方法、及び、プログラム |
JP2022175584A JP2023022010A (ja) | 2021-03-25 | 2022-11-01 | 判定装置、学習装置、判定システム、判定方法、学習方法、及び、プログラム |
Applications Claiming Priority (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2021051744 | 2021-03-25 | ||
JP2021-051744 | 2021-03-25 | ||
JP2021084010 | 2021-05-18 | ||
JP2021-084010 | 2021-05-18 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022202410A1 true WO2022202410A1 (ja) | 2022-09-29 |
Family
ID=83395726
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2022/010963 WO2022202410A1 (ja) | 2021-03-25 | 2022-03-11 | 判定装置、学習装置、判定システム、判定方法、学習方法、及び、プログラム |
Country Status (4)
Country | Link |
---|---|
US (1) | US20240159659A1 (ja) |
JP (2) | JP7171970B1 (ja) |
CA (1) | CA3213613A1 (ja) |
WO (1) | WO2022202410A1 (ja) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116804669A (zh) * | 2023-06-16 | 2023-09-26 | 枣庄华宝牧业开发有限公司 | 一种肉制品加工用油炸监视系统 |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2024154473A1 (ja) * | 2023-01-17 | 2024-07-25 | 株式会社J-オイルミルズ | 油脂劣化予測装置、油脂劣化予測システム、および油脂劣化予測方法 |
JP7525757B1 (ja) | 2023-03-07 | 2024-07-30 | 株式会社J-オイルミルズ | 油脂管理装置、油脂管理システム、油脂管理方法、および油脂管理表示装置 |
WO2024185247A1 (ja) * | 2023-03-07 | 2024-09-12 | 株式会社J-オイルミルズ | 油脂管理装置、油脂管理システム、油脂管理方法、および油脂管理表示装置 |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07333039A (ja) * | 1994-06-14 | 1995-12-22 | Hitachi Ltd | 画像処理を用いた液面位置計測方法 |
JP2000005080A (ja) * | 1998-06-17 | 2000-01-11 | Chubu Corporation:Kk | フライヤー及びそれに使用される油槽 |
JP2002081634A (ja) * | 2000-06-29 | 2002-03-22 | Mitsubishi Heavy Ind Ltd | プラズマ式灰溶融炉及びその運転方法 |
JP2002188094A (ja) * | 2000-12-21 | 2002-07-05 | Tama Ogasawara | 食油浄化方法、食油浄化剤、食油浄化器、食油浄化管理方法 |
JP2010519981A (ja) * | 2007-03-01 | 2010-06-10 | レストラン テクノロジー インコーポレイテッド | 少量の油で揚げ調理をする装置および方法 |
WO2021200103A1 (ja) * | 2020-03-31 | 2021-10-07 | 株式会社J-オイルミルズ | 食用油の劣化度判定装置、食用油の劣化度判定システム、食用油の劣化度判定方法、食用油の劣化度判定プログラム、食用油の劣化度学習装置、食用油の劣化度判定に用いられる学習済モデル、及び食用油の交換システム |
-
2022
- 2022-03-11 CA CA3213613A patent/CA3213613A1/en active Pending
- 2022-03-11 US US18/281,738 patent/US20240159659A1/en active Pending
- 2022-03-11 WO PCT/JP2022/010963 patent/WO2022202410A1/ja active Application Filing
- 2022-03-11 JP JP2022526817A patent/JP7171970B1/ja active Active
- 2022-11-01 JP JP2022175584A patent/JP2023022010A/ja active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07333039A (ja) * | 1994-06-14 | 1995-12-22 | Hitachi Ltd | 画像処理を用いた液面位置計測方法 |
JP2000005080A (ja) * | 1998-06-17 | 2000-01-11 | Chubu Corporation:Kk | フライヤー及びそれに使用される油槽 |
JP2002081634A (ja) * | 2000-06-29 | 2002-03-22 | Mitsubishi Heavy Ind Ltd | プラズマ式灰溶融炉及びその運転方法 |
JP2002188094A (ja) * | 2000-12-21 | 2002-07-05 | Tama Ogasawara | 食油浄化方法、食油浄化剤、食油浄化器、食油浄化管理方法 |
JP2010519981A (ja) * | 2007-03-01 | 2010-06-10 | レストラン テクノロジー インコーポレイテッド | 少量の油で揚げ調理をする装置および方法 |
WO2021200103A1 (ja) * | 2020-03-31 | 2021-10-07 | 株式会社J-オイルミルズ | 食用油の劣化度判定装置、食用油の劣化度判定システム、食用油の劣化度判定方法、食用油の劣化度判定プログラム、食用油の劣化度学習装置、食用油の劣化度判定に用いられる学習済モデル、及び食用油の交換システム |
Non-Patent Citations (2)
Title |
---|
OHTA SHIZUYUKI: "About "decrease" of frying oil", SCIENCE OF COOKERY, THE JAPAN SOCIETY OF COOKERY SCIENCE, JP, vol. 2, no. 3, 1 January 1969 (1969-01-01), JP , pages 147 - 155, XP055971030, ISSN: 0910-5360, DOI: 10.11402/cookeryscience1968.2.3_147 * |
TAMURA SAKIE: "Science of Sodium Chloride Used in Cooking", NIPPON KAISUI GAKKAI-SHI - BULLETIN OF THE SOCIETY OF SEA WATERSCIENCE, JAPAN, NIPPON KAISUI GAKKAI, TOKYO, JP, vol. 48, no. 3, 1 January 1994 (1994-01-01), JP , pages 224 - 231, XP055971032, ISSN: 0369-4550, DOI: 10.11457/swsj1965.48.224 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116804669A (zh) * | 2023-06-16 | 2023-09-26 | 枣庄华宝牧业开发有限公司 | 一种肉制品加工用油炸监视系统 |
CN116804669B (zh) * | 2023-06-16 | 2024-04-02 | 枣庄华宝牧业开发有限公司 | 一种肉制品加工用油炸监视系统 |
Also Published As
Publication number | Publication date |
---|---|
JPWO2022202410A1 (ja) | 2022-09-29 |
CA3213613A1 (en) | 2022-09-29 |
JP7171970B1 (ja) | 2022-11-15 |
US20240159659A1 (en) | 2024-05-16 |
JP2023022010A (ja) | 2023-02-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2022202410A1 (ja) | 判定装置、学習装置、判定システム、判定方法、学習方法、及び、プログラム | |
US11506395B2 (en) | Tailored food preparation with an oven | |
CN113194792B (zh) | 训练烹饪器具、定位食物以及确定烹饪进度的系统和方法 | |
JP6997362B1 (ja) | 食用油の劣化度判定装置、食用油の劣化度判定システム、食用油の劣化度判定方法、食用油の劣化度判定プログラム、食用油の劣化度学習装置、食用油の劣化度判定に用いられる学習済モデル、及び食用油の交換システム | |
CN108665134A (zh) | 用于监控食品制备的装置和方法 | |
TWI841796B (zh) | 油脂的劣化預測系統、劣化預測方法、油脂更換系統及油炸器系統 | |
JP2023021124A (ja) | 揚げ物廃棄時期管理装置、揚げ物廃棄時期管理システム、および揚げ物廃棄時期管理方法 | |
WO2022113755A1 (ja) | 食用油劣化度判定装置、食用油劣化度判定処理装置、食用油劣化度判定方法、およびフライヤー | |
WO2022202409A1 (ja) | 判定装置、学習装置、判定システム、判定方法、学習方法、及び、プログラム | |
KR20190021047A (ko) | 튀김방 서비스 시스템 | |
JP6829347B1 (ja) | フライ油劣化判定装置及びフライ油劣化判定方法 | |
JP2023054824A (ja) | 食品廃棄時期管理装置、食品廃棄時期管理システム、および食品廃棄時期管理方法 | |
KR102445650B1 (ko) | 튀김 식품 제조 장치 및 시스템 | |
WO2023054100A1 (ja) | 食用油の劣化度判定装置、食用油の劣化度判定システム、食用油の劣化度判定方法、食用油の劣化度学習装置、および食用油の劣化度判定に用いられる学習済モデル | |
WO2022163435A1 (ja) | 学習装置、予測装置、学習方法、プログラム、及び、学習システム | |
TW202124956A (zh) | 油炸油劣化判定裝置及油炸油劣化判定方法 | |
KR102611452B1 (ko) | 인공지능(ai) 기반 비대면 qsc 점검 솔루션 시스템 | |
WO2024111554A1 (ja) | 油脂劣化度検出装置、油脂劣化度検出システム、油脂劣化度検出方法、および油脂劣化度検出プログラム | |
CN111603050A (zh) | 一种炒菜机控制方法、装置、存储介质及炒菜机 | |
JP7266157B1 (ja) | 食品廃棄時点管理制御装置、食品廃棄時点管理システム、および食品廃棄時点管理方法 | |
WO2023106034A1 (ja) | 食品販売促進制御装置、食品販売促進システム、および食品販売促進方法 | |
WO2023106035A1 (ja) | 食品廃棄時点管理制御装置、食品廃棄時点管理システム、および食品廃棄時点管理方法 | |
WO2022065074A1 (ja) | 情報処理装置、情報処理方法、およびプログラム | |
CN114831514A (zh) | 智能预约烹饪方法及烹饪器材 | |
KR20240014911A (ko) | 능동적으로 조리 조건을 조절하는 프라잉 로봇 제어 시스템 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
ENP | Entry into the national phase |
Ref document number: 2022526817 Country of ref document: JP Kind code of ref document: A |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22775202 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 18281738 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 3213613 Country of ref document: CA |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 22775202 Country of ref document: EP Kind code of ref document: A1 |