CN116448706A - Refrigerator and food ingredient identification method and device - Google Patents
Refrigerator and food ingredient identification method and device Download PDFInfo
- Publication number
- CN116448706A CN116448706A CN202210005193.4A CN202210005193A CN116448706A CN 116448706 A CN116448706 A CN 116448706A CN 202210005193 A CN202210005193 A CN 202210005193A CN 116448706 A CN116448706 A CN 116448706A
- Authority
- CN
- China
- Prior art keywords
- food
- food material
- detected
- main
- refrigerator
- 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.)
- Pending
Links
- 235000012041 food component Nutrition 0.000 title claims abstract description 104
- 238000000034 method Methods 0.000 title claims abstract description 51
- 239000005417 food ingredient Substances 0.000 title claims abstract description 16
- 235000013305 food Nutrition 0.000 claims abstract description 299
- 239000000463 material Substances 0.000 claims abstract description 240
- 239000000306 component Substances 0.000 claims abstract description 80
- 238000002329 infrared spectrum Methods 0.000 claims abstract description 59
- 239000005428 food component Substances 0.000 claims abstract description 31
- 235000015097 nutrients Nutrition 0.000 claims abstract description 22
- 239000004615 ingredient Substances 0.000 claims abstract description 16
- 230000004044 response Effects 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims description 50
- 238000010521 absorption reaction Methods 0.000 claims description 37
- 238000001228 spectrum Methods 0.000 claims description 15
- 235000016709 nutrition Nutrition 0.000 claims description 12
- 230000035764 nutrition Effects 0.000 claims description 11
- 238000007405 data analysis Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 7
- 238000013145 classification model Methods 0.000 claims description 6
- 125000000524 functional group Chemical group 0.000 claims description 6
- 235000015219 food category Nutrition 0.000 claims description 3
- 230000003595 spectral effect Effects 0.000 claims description 2
- 235000005911 diet Nutrition 0.000 abstract description 6
- 230000037213 diet Effects 0.000 abstract description 6
- 230000036541 health Effects 0.000 abstract description 5
- 238000004458 analytical method Methods 0.000 description 8
- 230000006872 improvement Effects 0.000 description 8
- 241000220225 Malus Species 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 235000013399 edible fruits Nutrition 0.000 description 6
- 235000021016 apples Nutrition 0.000 description 5
- 235000015278 beef Nutrition 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000013135 deep learning Methods 0.000 description 5
- 239000000126 substance Substances 0.000 description 5
- BJEPYKJPYRNKOW-REOHCLBHSA-N (S)-malic acid Chemical compound OC(=O)[C@@H](O)CC(O)=O BJEPYKJPYRNKOW-REOHCLBHSA-N 0.000 description 4
- 229920002472 Starch Polymers 0.000 description 4
- BJEPYKJPYRNKOW-UHFFFAOYSA-N alpha-hydroxysuccinic acid Natural products OC(=O)C(O)CC(O)=O BJEPYKJPYRNKOW-UHFFFAOYSA-N 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 235000019625 fat content Nutrition 0.000 description 4
- 235000011090 malic acid Nutrition 0.000 description 4
- 239000001630 malic acid Substances 0.000 description 4
- 235000019698 starch Nutrition 0.000 description 4
- 239000008107 starch Substances 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 241000238557 Decapoda Species 0.000 description 3
- -1 dry matter Substances 0.000 description 3
- 235000013372 meat Nutrition 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004445 quantitative analysis Methods 0.000 description 3
- 235000013311 vegetables Nutrition 0.000 description 3
- 241000251468 Actinopterygii Species 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 229920002678 cellulose Polymers 0.000 description 2
- 239000001913 cellulose Substances 0.000 description 2
- 150000001875 compounds Chemical class 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000013499 data model Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 102000004169 proteins and genes Human genes 0.000 description 2
- 108090000623 proteins and genes Proteins 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 241000287828 Gallus gallus Species 0.000 description 1
- 240000008790 Musa x paradisiaca Species 0.000 description 1
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 241000220324 Pyrus Species 0.000 description 1
- 238000000862 absorption spectrum Methods 0.000 description 1
- 235000021015 bananas Nutrition 0.000 description 1
- 125000002915 carbonyl group Chemical group [*:2]C([*:1])=O 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000009614 chemical analysis method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000008157 edible vegetable oil Substances 0.000 description 1
- 235000013312 flour Nutrition 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 235000004280 healthy diet Nutrition 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 235000021017 pears Nutrition 0.000 description 1
- 235000015277 pork Nutrition 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
Classifications
-
- 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
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
-
- 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
-
- 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
- F25D29/003—Arrangement or mounting of control or safety devices for movable devices
-
- 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
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- 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
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3577—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing liquids, e.g. polluted water
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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
-
- 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
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
- G01N2021/0106—General arrangement of respective parts
- G01N2021/0112—Apparatus in one mechanical, optical or electronic block
Abstract
The invention discloses a refrigerator and a method and a device for identifying food ingredients. The refrigerator comprises an infrared spectrometer for detecting infrared spectrum data of food materials and a main control device for: determining the type of food materials to be detected in response to a preset food material component identification instruction; receiving infrared spectrum data of the food material to be detected, which is detected by the infrared spectrometer; inputting the infrared spectrum data into a preset food component identification model corresponding to the food type to obtain main nutritional components of the food to be detected and the proportion of each main nutritional component; the proportion is the ratio of the main nutrient components in the total ingredients of the food materials. By adopting the embodiment of the invention, the identification of the main nutritional components and the proportion of the main nutritional components of different food material types can be effectively realized, basic data support is provided for the diet health of a user, and better use experience is provided for the user.
Description
Technical Field
The invention relates to the technical field of food detection, in particular to a refrigerator and food ingredient identification method and device.
Background
With the improvement of the living standard and the consumption level of people, food materials in the refrigerator are more and more abundant, and the quality requirements of users on the nutrition, taste and the like of the food materials are also more and more high, so that intelligent refrigerator products become more and more focus of attention of people.
The intelligent refrigerator is generally provided with functions of video and audio entertainment, news broadcasting, food management and the like. The function of food material management relates to the ratio of food ingredients, such as moisture, protein, fat, sugar, starch, cellulose, etc. The conventional intelligent refrigerator identification strategy is generally to set preset values for components and proportions of certain types of foods according to literature records, determine the types of food materials through image identification, electronic tags or bar codes and the like, and then call the components and proportions corresponding to the types of the foods to obtain component identification results.
However, the inventors found that the prior art has at least the following problems: since the existing method for identifying the ingredients of the food materials has a single and fixed preset value for the ingredients and the proportion of the ingredients of a certain type of food materials, in actual situations, the proportions of the ingredients of the same type of food materials are not completely the same. For example, beef, may have different fat contents, and if a user pays high attention to the nutrition, the prior art method cannot distinguish one part of beef with higher fat content from one part of beef with lower fat content, so that the defects of the prior art method for identifying the fat content are obvious.
Disclosure of Invention
The embodiment of the invention aims to provide a refrigerator and food material component identification method and device, which can effectively identify main nutritional components and proportions of different food material types, provide basic data support for the diet health of a user and provide better use experience for the user.
To achieve the above object, an embodiment of the present invention provides a refrigerator including:
the refrigerator comprises a refrigerator body, a refrigerator cover and a refrigerator cover, wherein a storage chamber is arranged in the refrigerator body and used for storing food materials;
the infrared spectrometer is arranged on the refrigerator body and is used for detecting infrared spectrum data of food materials;
the main control device is connected with the infrared spectrometer and is used for:
determining the type of food materials to be detected in response to a preset food material component identification instruction;
receiving infrared spectrum data of the food material to be detected, which is detected by the infrared spectrometer;
inputting the infrared spectrum data into a preset food component identification model corresponding to the food type to obtain main nutritional components of the food to be detected and the proportion of each main nutritional component; the proportion is the ratio of the main nutrient components in the total ingredients of the food materials.
As an improvement of the above-described scheme, a food component identification model corresponding to each food category is constructed by:
acquiring a plurality of food training samples corresponding to each food type; wherein the main nutritional components of each food material category are preset, and the proportion of the main nutritional components of each food material training sample is known;
detecting infrared spectrum data of each food material training sample by adopting an infrared spectrometer;
and training to obtain a food component identification model corresponding to each food material type according to the proportion of the nutritional components of all the food material training samples corresponding to each food material type and the infrared spectrum data.
As an improvement of the above solution, training to obtain a food component identification model corresponding to each food material category according to the proportion of the nutritional components and the infrared spectrum data of all the food material training samples corresponding to each food material category specifically includes:
determining each characteristic absorption peak of the infrared spectrum data of each food material training sample, and calculating characteristic parameters of each characteristic absorption peak; wherein the characteristic parameters include position and wavelength;
according to the characteristic parameters of the characteristic absorption peaks, a preset spectrum data analysis method is adopted to determine the functional groups corresponding to the characteristic absorption peaks so as to determine the main nutritional components corresponding to the characteristic absorption peaks;
and under each food material type, importing the corresponding relation of the characteristic parameters of each characteristic absorption peak of each food material training sample and the proportion of the main nutrition components corresponding to the characteristic absorption peak into a preset fitting model for fitting so as to train and obtain a food material component identification model corresponding to each food material type.
As an improvement of the above scheme, the predetermined spectrum data analysis method is a space partial least square method, a backward space partial least square method or a dynamic backward space partial least square method.
As an improvement of the above solution, the determining the food material type of the food material to be detected specifically includes:
acquiring image information of the food material to be detected;
inputting the image information of the food material to be detected into a preset food material type classification model to obtain the food material type of the food material to be detected.
As an improvement of the above solution, after the inputting the infrared spectrum data into a preset food component identification model corresponding to the type of the food to obtain the main nutritional components of the food to be detected and the proportion of each main nutritional component, the main control device is further configured to:
acquiring the weight of the food material to be detected;
and calculating the heat value of the food material to be detected according to the weight of the food material to be detected and the proportion of each main nutrient component.
As an improvement of the scheme, the refrigerator further comprises a display device, wherein the display device is connected with the main control device;
the master control device is also used for:
and sending each main nutrient component, each proportion and each caloric value of the food material to be detected to the display device for display.
As an improvement of the above scheme, each food component identification model corresponding to each food type is stored in a cloud server, and then the master control device is further connected with the cloud server to obtain the food component identification model issued by the cloud server.
The embodiment of the invention also provides a food material component identification method, which comprises the following steps:
determining the type of food materials to be detected in response to a preset food material component identification instruction;
detecting infrared spectrum data of the food material to be detected;
inputting the infrared spectrum data into a preset food component identification model corresponding to the food type to obtain main nutritional components of the food to be detected and the proportion of each main nutritional component; the proportion is the ratio of the main nutrient components in the total ingredients of the food materials.
The embodiment of the invention also provides a food material component identification device, which comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, wherein the processor realizes the food material component identification method when executing the computer program.
Compared with the prior art, the refrigerator and the food component identification method and device disclosed by the embodiment of the invention are used for responding to the preset food component identification instruction to determine the type of food to be detected; receiving infrared spectrum data of the food material to be detected, which is detected by an infrared spectrometer; inputting the infrared spectrum data into a preset food component identification model corresponding to the food type to obtain main nutritional components of the food to be detected and the proportion of each main nutritional component; the proportion is the ratio of the main nutrient components in the total ingredients of the food materials. By adopting the technical means of the embodiment of the invention, the main nutritional components and the proportion of the food to be detected can be accurately calculated by inputting the infrared spectrum data of the food to be detected into the pre-established food component identification model for comparison and analysis, so that basic data support is provided for the diet health of a user, a more intelligent, edited and scientific refrigerator is provided, and better use experience is provided for the user.
Drawings
Fig. 1 is a schematic view of a refrigerator according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a workflow executed by a master device according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of training steps of a food ingredient identification model according to an embodiment of the present invention;
fig. 4 is a schematic flow chart of a method for identifying food ingredients according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a food ingredient identification device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a schematic structure of a refrigerator according to an embodiment of the present invention is shown. An embodiment of the present invention provides a refrigerator 10, including: the refrigerator body 11 is provided with a storage chamber inside for storing food materials.
The refrigerator 10 is further provided with an infrared spectrometer 12, which is arranged on the refrigerator body 11 and is used for detecting infrared spectrum data of food materials.
Specifically, in the actual use process, the user may hold the food to be detected by hand, place the food to be detected at the data detection end of the infrared spectrometer 12, and detect the food to be detected after the infrared spectrometer 12 is powered on and started, and output infrared spectrum data.
Preferably, a storage chamber for storing food to be detected may be provided in the refrigerator, and the data detecting end of the infrared spectrometer 12 is aligned with the storage chamber for storing food to be detected. In actual use, after the user puts the food material to be detected into the storage chamber, the infrared spectrometer 12 is started to detect the food material to be detected, and infrared spectrum data is output.
As a preferred embodiment, a parameter correction operation is also required prior to use of the infrared spectrometer 12. The parameter correcting operation specifically comprises the following steps: by scanning the blank background and the white background, the obtained blank data is used as a baseline for measuring absorbance spectrum, and correction is performed according to the baseline before each use.
By adopting the technical means of the embodiment of the invention, the light path system of the infrared spectrometer can be prevented from being shifted when receiving vibration in the transportation process, and the peak position of the spectrum absorption peak scanned each time is ensured not to be changed.
The refrigerator 10 further comprises a main control device 13 connected with the infrared spectrometer 12.
Referring to fig. 2, a schematic diagram of a workflow executed by a master device in an embodiment of the present invention is shown. The master control device is specifically configured to perform steps S11 to S13:
s11, responding to a preset food component identification instruction, and determining the type of food materials to be detected;
s12, receiving infrared spectrum data of the food material to be detected, which is detected by the infrared spectrometer;
s13, inputting the infrared spectrum data into a preset food component identification model corresponding to the food type to obtain main nutritional components of the food to be detected and the proportion of each main nutritional component; the proportion is the ratio of the main nutrient components in the total ingredients of the food materials.
In the embodiment of the present invention, when a user needs to detect a food component of a certain food to be detected, the infrared spectrometer 12 is started to detect the food to be detected, and the infrared spectrometer 12 sends the output infrared spectrum data to the main control device 13.
And, the main control device 13 determines the kind of food material to be detected in response to a preset food material component identification instruction.
In one embodiment, step S11, that is, the determining the food material type of the food material to be detected, specifically includes S111 and S112:
s111, acquiring image information of the food material to be detected;
s112, inputting the image information of the food material to be detected into a preset food material type classification model to obtain the food material type of the food material to be detected.
In the embodiment of the invention, a food material type classification model is trained in advance, and when the main control device 13 receives a food material component identification instruction, image information of food materials to be detected is obtained and input into the food material type classification model, and the food material type of the food materials to be detected is obtained through analysis based on a neural network deep learning algorithm.
Optionally, a camera is arranged on the refrigerator, when a user needs to identify food ingredients, the camera shoots image information of food to be detected, and the image information is sent to the main control device, so that the main control device analyzes the food types.
The food material type analysis model is obtained by training an initial neural network model by acquiring a plurality of pieces of image information marked with corresponding food material types in advance. In addition, the image recognition technology adopted by the food material type analysis model can adopt the image recognition technology in the prior art, and details are not repeated here.
In another embodiment, step S11, that is, determining the type of food material to be detected, specifically includes S111',:
s111', determining the food material type of the food material to be detected according to the food material type information input by the user.
In the embodiment of the present invention, when the user needs to identify the ingredients of the food materials, the information of the types of the food materials is input to the main control device 13 through the preset man-machine interaction interface, so that the main control device can determine the types of the food materials to be detected.
Further, after the main control device 13 obtains the food material type and the infrared spectrum data of the food material to be detected, determining a corresponding food material component identification model according to the food material type of the food material to be detected, and further inputting the infrared spectrum data into the food material component identification model corresponding to the food material type to obtain main nutritional components of the food material to be detected and the proportion of each main nutritional component; the proportion is the ratio of the main nutrient components in the total ingredients of the food materials.
Specifically, the food ingredient identification model is specifically used for: and comparing the input infrared spectrum data with a local or cloud standard database, and judging and detecting all main nutritional components and the proportion of the main nutritional components of the food to be detected by using the similarity of the two spectrum curves. When the proportion of the main nutrient components is matched with the data of the standard database, a food component identification result can be obtained and output; the food material component identification result comprises the main nutritional components of the food material to be detected and the proportion of each main nutritional component.
As a preferred embodiment, each food material component identification model corresponding to each food material type is stored in a cloud server, and the main control device is further connected with the cloud server, and uploads the obtained food material type of the food material to be detected to a cloud processor after receiving the food material component identification instruction, so as to trigger the food material component identification model corresponding to the food material type issued by the cloud processor.
By adopting the technical means of the embodiment of the invention, the models are stored in the cloud server, so that the identification speed is not influenced by the data quantity of the database model, and each model is convenient to update.
The embodiment of the invention provides a refrigerator, which comprises an infrared spectrometer, a control unit and a control unit, wherein the infrared spectrometer is used for detecting infrared spectrum data of food materials; the main control device is used for: determining the type of food materials to be detected in response to a preset food material component identification instruction; receiving infrared spectrum data of the food material to be detected, which is detected by the infrared spectrometer; inputting the infrared spectrum data into a preset food component identification model corresponding to the food type to obtain main nutritional components of the food to be detected and the proportion of each main nutritional component; the proportion is the ratio of the main nutrient components in the total ingredients of the food materials. By adopting the technical means of the embodiment of the invention, the main nutritional components and the proportion of the food to be detected can be accurately calculated by inputting the infrared spectrum data of the food to be detected into the pre-established food component identification model for comparison and analysis, so that basic data support is provided for the diet health of a user, a more intelligent, edited and scientific refrigerator is provided, and better use experience is provided for the user.
The preferred embodiment is a schematic diagram of training steps of the food material component identification model provided by the embodiment of the invention. In the embodiment of the invention, a food component identification model corresponding to each food type is constructed through the following steps S21 to S23:
s21, acquiring a plurality of food training samples corresponding to each food type; wherein the main nutritional components of each food material category are preset, and the proportion of the main nutritional components of each food material training sample is known.
In the embodiment of the invention, the common food materials in daily life are divided into a plurality of food material types in advance according to the composition components and main nutrient substances. By way of example, the food material classes include, but are not limited to, meats, fish, shrimps, crabs, leafy vegetables, rhizome vegetables, fruit vegetables, fruits of different general classes, edible oils, starch-based food materials. Different food materials are assigned to different food material categories, for example beef, mutton and pork are assigned to meat, apples, bananas and pears etc. are assigned to fruits.
It should be noted that the above classification of the types of food materials is only taken as an example, and in practical application, the classification of the types of food materials into more and more detailed types of food materials according to the composition of the food materials can be performed according to the diet requirement of the user, the accuracy requirement of the recognition result of the food material components by the user, and the like, without affecting the beneficial effects obtained by the present invention.
The main nutritional components of each food material are predetermined for each food material type. As an example, apples are a kind of food material, and the main nutritional ingredients include water, dry matter, malic acid and sugar degree.
Further, a plurality of food training samples corresponding to each food category are obtained, for example, for fruits, a plurality of fruit samples are required to be obtained, and the number of the same fruit samples is required to be as large as possible, and factors such as different maturity, different production areas, different production seasons and the like are covered, so that the obtained food training samples can cover various possibilities as much as possible. And the proportion of the main nutrition components of each food material training sample is obtained.
Optionally, the method for obtaining the proportion of the main nutritional components of each food material training sample comprises the following steps: in a laboratory setting, the analysis is performed using different testing methods and testing instruments to obtain the proportions of each major nutrient component, such as moisture, protein, fat, sugar, starch, cellulose, etc., of each food training sample.
S22, detecting infrared spectrum data of each food material training sample by adopting an infrared spectrometer.
And detecting each food material training sample by adopting a preset infrared spectrometer so as to acquire infrared spectrum data of each food material training sample.
S23, training to obtain a food material component identification model corresponding to each food material type according to the proportion of the nutritional components and the infrared spectrum data of all the food material training samples corresponding to each food material type.
And constructing a corresponding initial neural network model for each food material type in advance. After the proportion of the main nutrition components and the infrared spectrum data of all the food training samples corresponding to the food types are obtained, the initial neural network model can be trained to obtain a food component identification model corresponding to the food types. And training the food material training samples corresponding to each food material type to obtain a food material component identification model corresponding to each food material type.
As a preferred embodiment, step S23 is specifically performed by steps S231 to S233:
s231, determining each characteristic absorption peak of the infrared spectrum data of each food material training sample, and calculating characteristic parameters of each characteristic absorption peak; wherein the characteristic parameters include position and wavelength;
s232, determining a functional group corresponding to the characteristic absorption peak by adopting a preset spectral data analysis method according to the characteristic parameter of the characteristic absorption peak so as to determine a main nutritional component corresponding to the characteristic absorption peak;
and S233, under each food material type, importing the corresponding relation of the characteristic parameters of each characteristic absorption peak of each food material training sample and the proportion of the main nutrition components corresponding to the characteristic absorption peak into a preset fitting model for fitting so as to train and obtain a food material component identification model corresponding to each food material type.
Specifically, normalization processing is performed on the infrared spectrum data collected each time, and each maximum absorption peak in the infrared spectrum data, namely the characteristic absorption peak, is obtained.
It will be appreciated that the commonly used identification band of the near infrared spectrum is 740 nm-2450 nm. Of which the main observed is the vibrational transition of the groups. The intensity of the infrared band is a measure of the probability of a vibration transition, the greater the change in dipole moment as the molecule vibrates, the greater the band intensity. The absorption peaks in the characteristic frequency region are generated by the telescopic vibration of the group, the number is not very large, but the characteristic is very strong, so that the method can be mainly used for identifying the functional group. The corresponding band wavenumbers of certain groups or chemical bonds in the molecule in different compounds are essentially only fixed or vary only over a small band. For example, the characteristic wave number of carbonyl is basically 1600-1750 nm. Many chemical bonds have characteristic wavenumbers and thus can be used to identify the type of compound.
And determining characteristic parameters of each characteristic absorption peak of the infrared spectrum data, and repeatedly selecting characteristic wavelengths, namely accurate positions of peak tips and peak valleys of the spectrum absorption peaks by repeated genetic algorithm and the like to determine specific characteristic parameters.
And further, determining the functional group corresponding to the characteristic absorption peak by adopting a preset spectrum data analysis method so as to determine the main nutritional component corresponding to the characteristic absorption peak.
Preferably, the preset spectrum data analysis method is a space partial least square method, a backward space partial least square method or a dynamic backward space partial least square method.
Further, under each food material category, the corresponding relation of the proportion of the main nutrition component corresponding to the characteristic absorption peak of each food material training sample is imported into a preset fitting model for fitting so as to train and obtain a food material component identification model corresponding to each food material category.
The preset fitting model is a univariate fitting model, a multivariate fitting model or a random forest fitting model.
When the food material model is built, the known food material model can be repeatedly checked so as to train a deep learning algorithm of the model. In order to reduce the operand of the model and facilitate the online rapid detection reference in the subsequent research, a component content detection model can also be established by using a multiple linear regression method. In the actual modeling process, the characteristic wavelength can be further optimized through the significance index, so that the model is further simplified. And training the data model through different samples of the food materials to obtain a trained food material component identification model. And, the proportion of the components in the data model can be corrected according to the chemical analysis method.
As examples, apples are mainly composed of water, dry matter, malic acid, sugar degree, etc. In the specific implementation, the combination of the characteristic wave numbers (characteristic peaks) of the four main components can be found out respectively so as to realize the purpose of qualitative property. Then, modeling is carried out on the near infrared spectrum model of the apple, and a characteristic spectrum of the characteristic wave number combination containing the four main components is carried out. The model is simplified, namely, only the characteristic spectrums of four main components are adopted, namely, the preliminary model is built. Thus, the obtained apples (with different contents) in different types, maturity and different areas are repeatedly modeled to correct the model, and the model is trained by a deep learning method to enhance the applicability of the model.
Meanwhile, for a specific apple, quantitative analysis is carried out on the four main components by adopting a chemical quantitative analysis method, and the quantitative analysis result is related to the judgment result of the model, so that the quantitative relation between a certain component and a single characteristic spectrum can be established.
For example, when the model is first built, only characteristic peaks of four components of water, dry matter, malic acid, sugar degree and the like are obtained, and the accurate content of the characteristic peaks is not known. And the chemical analysis can accurately obtain that the dry matter is 11.5%, the malic acid is 0.13%, the sugar degree is 10.3% and the water content is 88%. The contents of the four components are respectively corresponding to the characteristic spectrums, and the corresponding relation can be established through the peak area and the contents of the characteristic spectrums. And training the model by repeating a deep learning algorithm to realize the model adaptability of the content difference among four components of different apples.
Similarly, for starch foods (rice, flour), meats (beef, mutton, chicken), aquatic products (fish, shrimp) and other foods with basically the same main nutrition components, the above method can be used for modeling and simplifying the model. In order to build a relatively complete infrared spectrum database.
By adopting the technical means of the embodiment of the invention, the wavelength characteristics of the near infrared spectrum are learned and extracted based on the deep learning algorithm of the neural network, the near infrared spectrum formed by the food material to be detected is directly processed and identified, and the identification of the food material components and proportions is realized.
As a preferred embodiment, after step S13, the master device is further configured to perform steps S31 to S32:
s31, acquiring the weight of the food material to be detected;
s32, calculating the heat value of the food material to be detected according to the weight of the food material to be detected and the proportion of each main nutrient component.
In the embodiment of the present invention, the main control device 13 may further obtain the weight of the food material to be detected. And after analyzing and calculating the proportion of each main nutrient component of the food material to be detected, converting each main nutrient component into a calorific value, and multiplying the calorific value by the weight of the food material to be detected to obtain the total calorific value of the food material to be detected.
Preferably, the refrigerator further comprises a display device, and the display device is connected with the main control device. The master device is further configured to perform step S33:
and S33, transmitting each main nutrient component, each proportion and each caloric value of the food materials to be detected to the display device for display.
In the embodiment of the invention, the calculated main nutritional components, proportion and heat value of the food material to be detected are displayed through a display end of the refrigerator. Of course, the data can also be sent to the mobile phone APP of the user for display, so that real-time and original data support is provided for healthy diet of the user.
Referring to fig. 4, a flow chart of a method for identifying food ingredients according to an embodiment of the present invention is shown. The embodiment of the invention provides a food material component identification method, which comprises the following steps of S41 to S43:
s41, responding to a preset food component identification instruction, and determining the type of food materials to be detected;
s42, detecting infrared spectrum data of the food material to be detected;
s43, inputting the infrared spectrum data into a preset food component identification model corresponding to the food type to obtain main nutritional components of the food to be detected and the proportion of each main nutritional component; the proportion is the ratio of the main nutrient components in the total ingredients of the food materials.
By adopting the technical means of the embodiment of the invention, the main nutritional components and the proportion of the food to be detected can be accurately calculated by inputting the infrared spectrum data of the food to be detected into the pre-established food component identification model for comparison and analysis, so that basic data support is provided for the diet health of a user, a more intelligent, edited and scientific refrigerator is provided, and better use experience is provided for the user.
As a preferred embodiment, the food material component identification model corresponding to each food material category is constructed by:
acquiring a plurality of food training samples corresponding to each food type; wherein the main nutritional components of each food material category are preset, and the proportion of the main nutritional components of each food material training sample is known;
detecting infrared spectrum data of each food material training sample by adopting an infrared spectrometer;
and training to obtain a food component identification model corresponding to each food material type according to the proportion of the nutritional components of all the food material training samples corresponding to each food material type and the infrared spectrum data.
Preferably, the training is performed according to the ratio of the nutritional components and the infrared spectrum data of all the food material training samples corresponding to each food material category to obtain a food material component identification model corresponding to each food material category, and the method specifically includes:
determining each characteristic absorption peak of the infrared spectrum data of each food material training sample, and calculating characteristic parameters of each characteristic absorption peak; wherein the characteristic parameters include position and wavelength;
according to the characteristic parameters of the characteristic absorption peaks, a preset spectrum data analysis method is adopted to determine the functional groups corresponding to the characteristic absorption peaks so as to determine the main nutritional components corresponding to the characteristic absorption peaks;
and under each food material type, importing the corresponding relation of the characteristic parameters of each characteristic absorption peak of each food material training sample and the proportion of the main nutrition components corresponding to the characteristic absorption peak into a preset fitting model for fitting so as to train and obtain a food material component identification model corresponding to each food material type.
Preferably, the preset spectrum data analysis method is a space partial least square method, a backward space partial least square method or a dynamic backward space partial least square method.
Preferably, step S41, that is, the determining the food material type of the food material to be detected specifically includes:
s411, acquiring image information of the food material to be detected;
s412, inputting the image information of the food material to be detected into a preset food material type classification model to obtain the food material type of the food material to be detected.
As a preferred embodiment, after step S43, the method further comprises steps S44 to S46:
s44, acquiring the weight of the food material to be detected;
s45, calculating the heat value of the food material to be detected according to the weight of the food material to be detected and the proportion of each main nutrient component.
And S46, displaying the main nutrition components, the proportion and the caloric value of each food material to be detected.
Referring to fig. 5, a schematic structural diagram of a device for identifying food ingredients according to an embodiment of the present invention is shown. An embodiment of the present invention provides a food material component identification apparatus 50, including a processor 51, a memory 52, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the food material component identification method as described in the above embodiment when executing the computer program.
It should be noted that, the food component identification device provided by the embodiment of the present invention is configured to execute all the steps of the flow of the food component identification method in the foregoing embodiment, and the working principles and beneficial effects of the two correspond to each other one by one, so that the description is omitted.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-only memory (ROM), a random access memory (RandomAccessMemory, RAM), or the like.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that changes and modifications may be made without departing from the principles of the invention, such changes and modifications are also intended to be within the scope of the invention.
Claims (10)
1. A refrigerator, comprising:
the refrigerator comprises a refrigerator body, a refrigerator cover and a refrigerator cover, wherein a storage chamber is arranged in the refrigerator body and used for storing food materials;
the infrared spectrometer is arranged on the refrigerator body and is used for detecting infrared spectrum data of food materials;
the main control device is connected with the infrared spectrometer and is used for:
determining the type of food materials to be detected in response to a preset food material component identification instruction;
receiving infrared spectrum data of the food material to be detected, which is detected by the infrared spectrometer;
inputting the infrared spectrum data into a preset food component identification model corresponding to the food type to obtain main nutritional components of the food to be detected and the proportion of each main nutritional component; the proportion is the ratio of the main nutrient components in the total ingredients of the food materials.
2. The refrigerator of claim 1, wherein the food material composition identification model corresponding to each food material category is constructed by:
acquiring a plurality of food training samples corresponding to each food type; wherein the main nutritional components of each food material category are preset, and the proportion of the main nutritional components of each food material training sample is known;
detecting infrared spectrum data of each food material training sample by adopting an infrared spectrometer;
and training to obtain a food component identification model corresponding to each food material type according to the proportion of the nutritional components of all the food material training samples corresponding to each food material type and the infrared spectrum data.
3. The refrigerator of claim 2, wherein the training to obtain the food material component identification model corresponding to each food material category according to the ratio of the nutritional components and the infrared spectrum data of all the food material training samples corresponding to each food material category specifically comprises:
determining each characteristic absorption peak of the infrared spectrum data of each food material training sample, and calculating characteristic parameters of each characteristic absorption peak; wherein the characteristic parameters include position and wavelength;
according to the characteristic parameters of the characteristic absorption peaks, a preset spectrum data analysis method is adopted to determine the functional groups corresponding to the characteristic absorption peaks so as to determine the main nutritional components corresponding to the characteristic absorption peaks;
and under each food material type, importing the corresponding relation of the characteristic parameters of each characteristic absorption peak of each food material training sample and the proportion of the main nutrition components corresponding to the characteristic absorption peak into a preset fitting model for fitting so as to train and obtain a food material component identification model corresponding to each food material type.
4. The refrigerator of claim 3, wherein the predetermined spectral data analysis method is a space-partial least square method, a backward space-partial least square method, or a dynamic backward space-partial least square method.
5. The refrigerator of claim 1, wherein the determining of the food material type of the food material to be detected specifically includes:
acquiring image information of the food material to be detected;
inputting the image information of the food material to be detected into a preset food material type classification model to obtain the food material type of the food material to be detected.
6. The refrigerator according to claim 1, wherein after the input of the infrared spectrum data into a preset food material component identification model corresponding to the kind of the food material to obtain the main nutritional components of the food material to be detected and the proportion of each of the main nutritional components, the main control device is further configured to:
acquiring the weight of the food material to be detected;
and calculating the heat value of the food material to be detected according to the weight of the food material to be detected and the proportion of each main nutrient component.
7. The refrigerator of claim 6, further comprising a display device connected to the master control device;
the master control device is also used for:
and sending each main nutrient component, each proportion and each caloric value of the food material to be detected to the display device for display.
8. The refrigerator according to any one of claims 1 to 6, wherein a food ingredient identification model corresponding to each of the food categories is stored in a cloud server, and the main control device is further connected to the cloud server to obtain the food ingredient identification model issued by the cloud server.
9. A method for identifying a food component, comprising:
determining the type of food materials to be detected in response to a preset food material component identification instruction;
detecting infrared spectrum data of the food material to be detected;
inputting the infrared spectrum data into a preset food component identification model corresponding to the food type to obtain main nutritional components of the food to be detected and the proportion of each main nutritional component; the proportion is the ratio of the main nutrient components in the total ingredients of the food materials.
10. A food ingredient identification apparatus comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the food ingredient identification method of claim 9 when executing the computer program.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210005193.4A CN116448706A (en) | 2022-01-04 | 2022-01-04 | Refrigerator and food ingredient identification method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210005193.4A CN116448706A (en) | 2022-01-04 | 2022-01-04 | Refrigerator and food ingredient identification method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116448706A true CN116448706A (en) | 2023-07-18 |
Family
ID=87126077
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210005193.4A Pending CN116448706A (en) | 2022-01-04 | 2022-01-04 | Refrigerator and food ingredient identification method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116448706A (en) |
-
2022
- 2022-01-04 CN CN202210005193.4A patent/CN116448706A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Qu et al. | Applications of near-infrared spectroscopy in food safety evaluation and control: A review of recent research advances | |
Hassoun et al. | Food quality 4.0: From traditional approaches to digitalized automated analysis | |
Kademi et al. | Applications of miniaturized and portable near infrared spectroscopy (NIRS) for inspection and control of meat and meat products | |
Khulal et al. | Intelligent evaluation of total volatile basic nitrogen (TVB-N) content in chicken meat by an improved multiple level data fusion model | |
CN107873101B (en) | Imaging system for object recognition and evaluation | |
Khaled et al. | Emerging nondestructive approaches for meat quality and safety evaluation—A review | |
ElMasry et al. | Meat quality evaluation by hyperspectral imaging technique: an overview | |
CN107992583B (en) | Information pushing method, information pushing device, equipment and storage medium | |
CN108960315B (en) | Intelligent evaluation system and method for quality of cooked meat product | |
Sliwinska et al. | Food analysis using artificial senses | |
Konda Naganathan et al. | Partial least squares analysis of near-infrared hyperspectral images for beef tenderness prediction | |
Zamora-Rojas et al. | In-situ Iberian pig carcass classification using a micro-electro-mechanical system (MEMS)-based near infrared (NIR) spectrometer | |
Xu et al. | Methods for performing dimensionality reduction in hyperspectral image classification | |
Huang et al. | Rapid and nondestructive detection of freshness quality of postharvest spinaches based on machine vision and electronic nose | |
Khodabakhshian et al. | Application of Vis/SNIR hyperspectral imaging in ripeness classification of pear | |
Weng et al. | Nondestructive detection of storage time of strawberries using visible/near-infrared hyperspectral imaging | |
Yang et al. | Detection of the freshness state of cooked beef during storage using hyperspectral imaging | |
Ji et al. | Recent advances and application of machine learning in food flavor prediction and regulation | |
Zhang et al. | Rapid identification of lamb freshness grades using visible and near-infrared spectroscopy (Vis-NIR) | |
Huang et al. | Near-Infrared spectral image analysis of pork marbling based on Gabor filter and wide line detector techniques | |
Ali et al. | Innovative non-destructive technologies for quality monitoring of pineapples: Recent advances and applications | |
Zeng et al. | Food flavor analysis 4.0: A cross-domain application of machine learning | |
Jiang et al. | Detecting total acid content quickly and accurately by combining hyperspectral imaging and an optimized algorithm method | |
Han et al. | Predicting the ripening time of ‘Hass’ and ‘Shepard’avocado fruit by hyperspectral imaging | |
Chen et al. | Advanced nondestructive detection technologies in food |
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 |