CN113915841B - Refrigerator and food material positioning method thereof - Google Patents
Refrigerator and food material positioning method thereof Download PDFInfo
- Publication number
- CN113915841B CN113915841B CN202111212660.2A CN202111212660A CN113915841B CN 113915841 B CN113915841 B CN 113915841B CN 202111212660 A CN202111212660 A CN 202111212660A CN 113915841 B CN113915841 B CN 113915841B
- Authority
- CN
- China
- Prior art keywords
- positioning
- food material
- training data
- reader
- writer
- 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.)
- Active
Links
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
- F25D11/00—Self-contained movable devices, e.g. domestic refrigerators
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
- F25D29/00—Arrangement or mounting of control or safety devices
- F25D29/005—Mounting of control devices
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
- F25D2400/00—General features of, or devices for refrigerators, cold rooms, ice-boxes, or for cooling or freezing apparatus not covered by any other subclass
- F25D2400/36—Visual displays
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
- F25D2500/00—Problems to be solved
- F25D2500/06—Stock management
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Physics & Mathematics (AREA)
- Mechanical Engineering (AREA)
- Thermal Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Cold Air Circulating Systems And Constructional Details In Refrigerators (AREA)
Abstract
The invention discloses a refrigerator, comprising: a box body; the reader-writer comprises a reader-writer host and a plurality of antennas, and the reader-writer transmits or receives radio frequency signals to the RFID label through the antennas so that the RFID label calculates the signal intensity and returns the signal intensity to the reader-writer host through the antennas; the controller is configured to: when the preset positioning condition is met, acquiring the signal intensity and the food material information of the RFID label acquired by the reader-writer host; inputting the signal intensity of the RFID labels corresponding to the same food material information and received by different antennas into a pre-trained positioning model; the positioning model comprises a convolution layer, a pooling layer, an inclusion structure and a full-connection layer; acquiring positioning information output by the positioning model as the positioning information of the current food material; and displaying the positioning information of the current food material in the display. The invention discloses a food material positioning method of a refrigerator. By adopting the embodiment of the invention, the accuracy of positioning the food material can be improved, so that a user can quickly know the storage position of the food material.
Description
Technical Field
The invention relates to the technical field of refrigerators, in particular to a refrigerator and a food material positioning method thereof.
Background
The rapid development of the internet of things technology, the control technology and the communication technology promotes the intelligent high-speed development, and the household appliance industry has an intelligent trend and widely enters families and lives of people. The network is integrated into the design of the refrigerator product, so that more intelligent and humanized life experience is provided for users, and the network gradually becomes an important development direction of the refrigerator product. The method comprises the steps that the food material positioning of the refrigerator is one of hot spot directions, an antenna is arranged at a specific position of the refrigerator, an RFID (Radio Frequency Identification) tag is placed on the food material in the refrigerator, data received by each tag are collected through a reader-writer, and then the data are processed through a corresponding classification algorithm to predict the position partition of each food material in the refrigerator, so that the intelligent management of the food material is realized. However, the existing technology for identifying the storage location of food based on RFID tag can only identify the storage room in which the food is stored, and cannot further identify the distribution location of the food in the storage room.
Disclosure of Invention
The embodiment of the invention aims to provide a refrigerator and a food material positioning method thereof, which can improve the accuracy of food material positioning and enable a user to quickly know the storage position of food materials.
To achieve the above object, an embodiment of the present invention provides a refrigerator, including:
a cabinet serving as a support structure of the refrigerator and having a plurality of storage compartments therein;
the reader-writer is arranged in the box body and comprises a reader-writer host and a plurality of antennas, and the reader-writer transmits or receives radio frequency signals to the RFID label through the antennas so that the RFID label calculates the signal intensity and returns the signal intensity to the reader-writer host through the antennas;
the controller is configured to:
when a preset positioning condition is met, acquiring the signal intensity of the RFID tag and food material information acquired by the reader-writer host;
inputting the signal intensity of the RFID labels corresponding to the same food material information and received by different antennas into a pre-trained positioning model; the positioning model is obtained by pre-training a server and comprises a convolution layer, a pooling layer, an inclusion structure and a full-connection layer;
and acquiring the positioning information output by the positioning model as the positioning information of the current food material, and displaying the positioning information of the current food material in a display.
As an improvement of the above solution, the method for training the positioning model includes:
acquiring training data and preprocessing the training data; the training data comprises the signal intensity of the RFID labels to be trained, and the RFID labels to be trained are distributed in the storeroom according to a preset distribution rule;
building a positioning model;
inputting the training data into the positioning model for training.
As an improvement of the above scheme, the preprocessing the training data includes:
carrying out normalization processing on the training data;
and performing dimension increasing processing on the training data after the normalization processing so as to convert the training data into two-dimensional data.
As an improvement of the above scheme, the building positioning model includes:
padding with zero values at the edges of the input matrix;
after inputting the matrix, connecting a pan-convolution;
connecting two Incepotion structures after pan-convolution; wherein the inclusion structure is composed of a plurality of convolutions;
the inclusion structure is connected with the pooling layer;
and the full connecting layer is connected behind the pooling layer.
In order to achieve the above object, an embodiment of the present invention further provides a method for positioning food materials of a refrigerator, including:
when the preset positioning condition is met, acquiring the signal intensity of the RFID tag and food material information acquired by a reader-writer in the refrigerator; the reader-writer comprises a reader-writer host and a plurality of antennas, and the reader-writer transmits or receives radio frequency signals to the RFID label through the antennas so that the RFID label calculates the signal intensity and returns the signal intensity to the reader-writer host through the antennas;
inputting the signal intensity of the RFID labels corresponding to the same food material information and received by different antennas into a pre-trained positioning model; the positioning model is obtained by pre-training a server and comprises a convolution layer, a pooling layer, an inclusion structure and a full-connection layer;
and acquiring the positioning information output by the positioning model as the positioning information of the current food material, and displaying the positioning information of the current food material in a display.
As an improvement of the above solution, the training method of the positioning model includes:
acquiring training data and preprocessing the training data; the training data comprises the signal intensity of the RFID labels to be trained, and the RFID labels to be trained are distributed in the storeroom according to a preset distribution rule;
building a positioning model;
inputting the training data into the positioning model for training.
As an improvement of the above scheme, the preprocessing the training data includes:
carrying out normalization processing on the training data;
and performing dimension increasing processing on the training data after the normalization processing so as to convert the training data into two-dimensional data.
As an improvement of the above scheme, the building positioning model includes:
padding with zero values at the edges of the input matrix;
after inputting the matrix, connecting a pan-convolution;
connecting two Incepotion structures after pan-convolution; wherein the inclusion structure is composed of a plurality of convolutions;
the inclusion structure is connected with the pooling layer;
and the full connecting layer is connected behind the pooling layer.
Compared with the prior art, the refrigerator and the food material positioning method thereof disclosed by the embodiment of the invention have the advantages that the signal intensity of the RFID tag corresponding to the same food material information is identified through the storage positioning model in the refrigerator, so that the distribution position of the current food material in the storage chamber is identified, the positioning information is displayed in the display, and a user can conveniently and quickly know the storage position of the food material. The refrigerator provided by the embodiment of the invention can improve the accuracy of food material positioning, so that a user can quickly know the storage position of the food material.
Drawings
Fig. 1 is a schematic structural diagram of a refrigerator according to an embodiment of the present invention;
fig. 2 is a schematic distribution diagram of an antenna provided by an embodiment of the present invention in a refrigerator;
FIG. 3 is a block diagram of a positioning model provided by an embodiment of the present invention;
fig. 4 is a flowchart of a food material positioning method for a refrigerator according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.
Referring to fig. 1, a schematic structural diagram of a refrigerator provided in embodiment 1 of the present invention is shown, where the refrigerator includes:
a cabinet 10 serving as a support structure of the refrigerator and having a plurality of storage compartments therein;
the reader-writer 20 is arranged in the box body and comprises a reader-writer host and a plurality of antennas, and the reader-writer transmits or receives radio frequency signals to the RFID label through the antennas so that the RFID label calculates the signal intensity and returns the signal intensity to the reader-writer host through the antennas;
the controller 30 is configured to:
when a preset positioning condition is met, acquiring the signal intensity of the RFID tag and food material information acquired by the reader-writer host;
inputting the signal intensity of the RFID labels corresponding to the same food material information and received by different antennas into a pre-trained positioning model; the positioning model is obtained by pre-training a server and comprises a convolution layer, a pooling layer, an inclusion structure and a full-connection layer;
and acquiring the positioning information output by the positioning model as the positioning information of the current food material, and displaying the positioning information of the current food material in a display.
Specifically, referring to fig. 2, in the embodiment of the present invention, the refrigerator is divided into three partitions, each partition is distributed with antennas, and it should be noted that the dividing manner of the partitions of the refrigerator may be divided according to the distribution manner of the storage chambers, which is not limited herein. The positioning condition includes at least one of: acquiring a positioning instruction of a certain food material sent by a user; the method is triggered automatically after a preset positioning period, for example, the positioning period is 2 days.
Illustratively, in the embodiment of the invention, eight antennas are arranged inside the refrigerator, and the radio frequency identification technology is used for collecting the signal strength measured by each RFID tag. After the food and the RFID tags are bound and placed in the storage room by the user, the eight antennas simultaneously send signals, so that eight data are measured by each RFID tag, namely the signal intensity and the food information of the No. 1 to No. 8 antennas corresponding to the tag position, and the food information is used for distinguishing the signal intensity subsequently. The method comprises the steps that the RFID tags send out measured signal strength after receiving signals sent by antennas, a reader-writer host at the top of a refrigerator receives reading data in sequence, then the signal strength of the RFID tags corresponding to the same food material information and received by different antennas is input into a pre-trained positioning model, and therefore positioning information output by the positioning model is obtained and used as positioning information of current food materials, and the positioning information of the current food materials is displayed on a display.
Further, in the embodiment of the present invention, the display may display a three-dimensional model of a storage room of the refrigerator, and mark the positioning information of the current food material in the three-dimensional model, so that the user can know the position of the current food material according to the mark.
Optionally, the training method of the positioning model includes:
acquiring training data and preprocessing the training data; the training data comprises the signal intensity of the RFID labels to be trained, and the RFID labels to be trained are distributed in the storeroom according to a preset distribution rule;
building a positioning model;
inputting the training data into the positioning model for training.
Specifically, the distribution rule is: and distributing the RFID labels to be trained at equal intervals according to preset intervals. In the training process, the distribution space of the storage room needs to be divided into a plurality of areas at equal intervals, and an RFID label to be trained is placed in each area. It will be appreciated that the more zones divided, the smaller the spacing between the RFID tags to be trained, and the more accurate the positioning.
Before the training data are input into a positioning model, preprocessing needs to be carried out on the training data, firstly, normalization processing is carried out on the training data, the training data are mapped into an interval from 0 to 1, the convergence speed of a neural network model is improved, and the time needed by training is shortened; and then, performing dimension increasing processing on the training data after normalization processing to convert the training data into two-dimensional data, expanding two dimensions of the data, storing the extracted two-dimensional data in a csv file, regarding the data of each line in the csv file as a picture, regarding the line number of the file as the number of the pictures, representing the signal intensity in the form of the pictures, and facilitating the identification of a positioning model.
Specifically, the building and positioning model comprises the following steps: padding with zero values at the edges of the input matrix; after inputting the matrix, connecting a pan-convolution; connecting two Incepotion structures after pan-convolution; wherein the inclusion structure is composed of a plurality of convolutions; the inclusion structure is connected with the pooling layer; and the full connecting layer is connected behind the pooling layer.
Illustratively, referring to fig. 3, after data preprocessing, the training data is input to a feature matrix of 8 × 1 size, and zero values are filled in the edges of the input matrix to increase the height and width of the input feature matrix for facilitating subsequent convolution operations. The generalized convolution is followed by a 1-by-1 convolution in order to change the dimensionality of the data and increase the number of channels input to the feature matrix. After the operation of pan-convolution and 1 × 1 convolution, two rows of zero values are respectively filled in the upper part, the lower part, the left part and the right part of the original feature matrix, and in the step of 1 × 1 convolution, six convolution kernels participate in convolution operation, so that the size of the input feature matrix is changed into 12 × 5 × 6. The method comprises the steps that two addition blocks with the same structure are connected, each addition structure is composed of four branches, the first branch only conducts 1 × 1 convolution operation on an input feature matrix, the second branch conducts 1 × 1 convolution on the input feature matrix, then convolution operation is conducted through convolution kernels with the sizes of 3 × 3, after 1 × 1 convolution operation is conducted on the third branch, convolution processing is conducted through convolution kernels with the sizes of 5 × 5, and finally the last branch conducts maximum pooling down-sampling on the input feature matrix and then conducts 1 × 1 convolution operation. The width and the height of the feature matrix output by each branch are kept consistent in the whole process, and then all the output feature matrices are spliced together in the depth direction on a DepthCocato layer to obtain a complete output feature matrix. After the processing of the two layers of inclusion structures, the size of an output feature matrix is 12 x 5 x 48, the overall average pooling down-sampling is carried out behind the inclusion structure, the size of the output feature matrix is 6 x 2 x 48 after the sampling is finished, and finally the output feature matrix is in full connection with three output nodes to output a training result.
Compared with the prior art, the refrigerator disclosed by the embodiment of the invention has the advantages that the signal intensity of the RFID tag corresponding to the same food material information is identified through the storage positioning model in the refrigerator, so that the distribution position of the current food material in the storage chamber is identified, the positioning information is displayed in the display, and a user can conveniently and quickly know the storage position of the food material. The refrigerator provided by the embodiment of the invention can improve the accuracy of positioning the food materials, so that a user can quickly know the storage positions of the food materials.
Referring to fig. 4, fig. 4 is a flowchart of a food material positioning method for a refrigerator according to an embodiment of the present invention, where the food material positioning method for the refrigerator includes:
s1, when a preset positioning condition is met, acquiring the signal intensity of an RFID label and food material information acquired by a reader-writer in a refrigerator; the reader-writer comprises a reader-writer host and a plurality of antennas, and the reader-writer transmits or receives radio frequency signals to the RFID label through the antennas so that the RFID label calculates the signal intensity and returns the signal intensity to the reader-writer host through the antennas;
s2, inputting the signal intensity of the RFID labels corresponding to the same food material information and received by different antennas into a pre-trained positioning model; the positioning model is obtained by pre-training a server and comprises a convolution layer, a pooling layer, an inclusion structure and a full-connection layer;
and S3, acquiring the positioning information output by the positioning model as the positioning information of the current food material, and displaying the positioning information of the current food material in a display.
Specifically, in the embodiment of the present invention, the refrigerator is divided into three partitions, and each partition is distributed with antennas, and it should be noted that the dividing manner of the partitions of the refrigerator may be divided according to the distribution manner of the storage chambers, which is not specifically limited herein. The positioning condition includes at least one of: acquiring a positioning instruction of a certain food material sent by a user; the method is triggered automatically after a preset positioning period, for example, the positioning period is 2 days.
Illustratively, in the embodiment of the invention, eight antennas are arranged inside the refrigerator, and the radio frequency identification technology is used for collecting the signal strength measured by each RFID tag. After the food and the RFID tags are bound and placed in the storage room by the user, the eight antennas simultaneously send signals, so that eight data are measured by each RFID tag, namely the signal intensity and the food information of the No. 1 to No. 8 antennas corresponding to the tag position, and the food information is used for distinguishing the signal intensity subsequently. The RFID tag sends out the measured signal intensity after receiving signals sent by the antenna, a reader-writer host at the top of the refrigerator receives reading data in sequence, then the signal intensities of the RFID tags corresponding to the information of the same food material and received by different antennas are input into a pre-trained positioning model, and therefore the positioning information output by the positioning model is obtained and used as the positioning information of the current food material, and the positioning information of the current food material is displayed on a display.
Further, in the embodiment of the present invention, the display may display a three-dimensional model of a storage room of the refrigerator, and mark the positioning information of the current food material in the three-dimensional model, so that the user can know the position of the current food material according to the mark.
Optionally, the training method of the positioning model includes steps S21 to S23:
s21, acquiring training data and preprocessing the training data; the training data comprises the signal intensity of the RFID labels to be trained, and the RFID labels to be trained are distributed in the storeroom according to a preset distribution rule;
s22, building a positioning model;
and S23, inputting the training data into the positioning model for training.
Specifically, the distribution rule is: and distributing the RFID labels to be trained at equal intervals according to preset intervals. In the training process, the distribution space of the storage room needs to be divided into a plurality of areas at equal intervals, and an RFID label to be trained is placed in each area. It will be appreciated that the more zones that are divided, the smaller the spacing between the RFID tags to be trained, and the more accurate the positioning.
Before the training data are input into a positioning model, preprocessing the training data is needed, firstly, normalization processing is carried out on the training data, the training data are mapped into an interval from 0 to 1, the convergence speed of a neural network model is improved, and the time needed by training is shortened; and then, performing dimension increasing processing on the training data after normalization processing to convert the training data into two-dimensional data, expanding two dimensions of the data, storing the extracted two-dimensional data in a csv file, regarding the data of each line in the csv file as a picture, regarding the line number of the file as the number of the pictures, representing the signal intensity in the form of the pictures, and facilitating the identification of a positioning model.
Specifically, the building and positioning model comprises the following steps: padding with zero values at the edges of the input matrix; after inputting the matrix, connecting a pan-convolution; connecting two Incepotion structures after pan-convolution; wherein the inclusion structure is composed of a plurality of convolutions; the rear part of the Incepration structure is connected with a pooling layer; and the full connecting layer is connected behind the pooling layer.
Illustratively, after data preprocessing, the training data is input into a feature matrix with a size of 8 × 1, and zero values are filled in the edges of the input matrix to increase the height and width of the input feature matrix in order to facilitate subsequent convolution operations. The generalized convolution is followed by a 1-by-1 convolution in order to change the dimensionality of the data and increase the number of channels input to the feature matrix. After the operation of pan-convolution and 1 × 1 convolution, two rows of zero values are respectively filled in the upper part, the lower part, the left part and the right part of the original feature matrix, and in the step of 1 × 1 convolution, six convolution kernels participate in convolution operation, so that the size of the input feature matrix is changed into 12 × 5 × 6. The method comprises the steps that two addition blocks with the same structure are connected, each addition structure is composed of four branches, the first branch only conducts 1 × 1 convolution operation on an input feature matrix, the second branch conducts 1 × 1 convolution on the input feature matrix, then convolution operation is conducted through convolution kernels with the sizes of 3 × 3, after 1 × 1 convolution operation is conducted on the third branch, convolution processing is conducted through convolution kernels with the sizes of 5 × 5, and finally the last branch conducts maximum pooling down-sampling on the input feature matrix and then conducts 1 × 1 convolution operation. The width and the height of the feature matrix output by each branch are kept consistent in the whole process, and then all the output feature matrices are spliced together in the depth direction on a DepthCocato layer to obtain a complete output feature matrix. After the processing of the two layers of inclusion structures, the size of an output feature matrix is 12 x 5 x 48, the overall average pooling down-sampling is carried out behind the inclusion structure, the size of the output feature matrix is 6 x 2 x 48 after the sampling is finished, and finally the output feature matrix is in full connection with three output nodes to output a training result.
Compared with the prior art, the food material positioning method of the refrigerator disclosed by the embodiment of the invention has the advantages that the signal intensity of the RFID tag corresponding to the same food material information is identified through the storage positioning model in the refrigerator, so that the distribution position of the current food material in the storage chamber is identified, the positioning information is displayed in the display, and a user can conveniently and quickly know the storage position of the food material. The refrigerator provided by the embodiment of the invention can improve the accuracy of food material positioning, so that a user can quickly know the storage position of the food material.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (6)
1. A refrigerator, characterized by comprising:
a cabinet serving as a support structure of the refrigerator and having a plurality of storage compartments therein;
the reader-writer is arranged in the box body and comprises a reader-writer host and a plurality of antennas, and the reader-writer transmits or receives radio frequency signals to the RFID label through the antennas so that the RFID label calculates the signal intensity and returns the signal intensity to the reader-writer host through the antennas;
the controller is configured to:
when a preset positioning condition is met, acquiring the signal intensity and the food material information of the RFID label acquired by the reader-writer host;
inputting the signal intensity of the RFID labels corresponding to the same food material information and received by different antennas into a pre-trained positioning model; the positioning model is obtained by pre-training a server and comprises a convolution layer, a pooling layer, an inclusion structure and a full-connection layer;
acquiring positioning information output by the positioning model as positioning information of the current food material, and displaying the positioning information of the current food material in a display;
the training method of the positioning model comprises the following steps:
acquiring training data and preprocessing the training data; the training data comprises the signal intensity of the RFID labels to be trained, and the RFID labels to be trained are distributed in the storeroom according to a preset distribution rule;
building a positioning model;
inputting the training data into the positioning model for training.
2. The refrigerator of claim 1, wherein the preprocessing the training data comprises:
carrying out normalization processing on the training data;
and performing dimension increasing processing on the training data after the normalization processing so as to convert the training data into two-dimensional data.
3. The refrigerator according to claim 1, wherein the building positioning model comprises:
padding with zero values at the edges of the input matrix;
after inputting the matrix, connecting a pan-convolution;
connecting two Incepotion structures after pan-convolution; wherein the inclusion structure is composed of a plurality of convolutions;
the rear part of the Incepration structure is connected with a pooling layer;
and the full connecting layer is connected behind the pooling layer.
4. A method for positioning food materials of a refrigerator is characterized by comprising the following steps:
when the preset positioning condition is met, acquiring the signal intensity and food material information of the RFID tag acquired by a reader-writer in the refrigerator; the reader-writer comprises a reader-writer host and a plurality of antennas, and the reader-writer transmits or receives radio frequency signals to the RFID label through the antennas so that the RFID label calculates the signal intensity and returns the signal intensity to the reader-writer host through the antennas;
inputting the signal intensity of the RFID labels corresponding to the same food material information and received by different antennas into a pre-trained positioning model; the positioning model is obtained by pre-training a server and comprises a convolution layer, a pooling layer, an inclusion structure and a full-connection layer;
acquiring positioning information output by the positioning model as positioning information of the current food material, and displaying the positioning information of the current food material in a display;
the training method of the positioning model comprises the following steps:
acquiring training data and preprocessing the training data; the training data comprise the signal intensity of the RFID labels to be trained, and the RFID labels to be trained are distributed in the storage room according to a preset distribution rule;
building a positioning model;
inputting the training data into the positioning model for training.
5. The food material positioning method for the refrigerator as claimed in claim 4, wherein the pre-processing of the training data comprises:
carrying out normalization processing on the training data;
and performing dimension increasing processing on the training data after the normalization processing so as to convert the training data into two-dimensional data.
6. The food material positioning method for the refrigerator as claimed in claim 4, wherein the building of the positioning model comprises:
padding with zero values at the edges of the input matrix;
after inputting the matrix, connecting a pan-convolution;
connecting two Incepotion structures after pan-convolution; wherein the inclusion structure is composed of a plurality of convolutions;
the rear part of the Incepration structure is connected with a pooling layer;
and the full connecting layer is connected behind the pooling layer.
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111212660.2A CN113915841B (en) | 2021-10-18 | 2021-10-18 | Refrigerator and food material positioning method thereof |
PCT/CN2022/120029 WO2023065933A1 (en) | 2021-10-18 | 2022-09-20 | Refrigerator, refrigerator management system, and control method for refrigerator management system |
CN202280052817.6A CN117730235A (en) | 2021-10-18 | 2022-09-20 | Refrigerator, refrigerator management system and control method of refrigerator management system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111212660.2A CN113915841B (en) | 2021-10-18 | 2021-10-18 | Refrigerator and food material positioning method thereof |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113915841A CN113915841A (en) | 2022-01-11 |
CN113915841B true CN113915841B (en) | 2023-04-07 |
Family
ID=79241335
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111212660.2A Active CN113915841B (en) | 2021-10-18 | 2021-10-18 | Refrigerator and food material positioning method thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113915841B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117730235A (en) * | 2021-10-18 | 2024-03-19 | 海信冰箱有限公司 | Refrigerator, refrigerator management system and control method of refrigerator management system |
CN114485037B (en) * | 2022-02-11 | 2024-04-05 | 海信冰箱有限公司 | Refrigerator and food material positioning method thereof |
Family Cites Families (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005173675A (en) * | 2003-12-08 | 2005-06-30 | Hitachi Ltd | Article management and health management system |
JP2005221177A (en) * | 2004-02-06 | 2005-08-18 | Toshiba Corp | Household electrical appliance |
KR100673707B1 (en) * | 2005-05-27 | 2007-01-24 | 엘지전자 주식회사 | Food managing refrigerator using rfid |
CN101071015A (en) * | 2006-05-12 | 2007-11-14 | 泰州乐金电子冷机有限公司 | Food management type electric refrigerator utilizing RFID |
KR20070116335A (en) * | 2006-06-05 | 2007-12-10 | 주식회사 대우일렉트로닉스 | Refrigerator with rfid system and method for displaying an information of the contents in refrigerator |
DE102014213912A1 (en) * | 2014-07-17 | 2016-01-21 | BSH Hausgeräte GmbH | Household appliance, in particular household refrigeration appliance |
CN105159103A (en) * | 2015-07-31 | 2015-12-16 | 小米科技有限责任公司 | Mode adjusting method and mode adjusting device |
CN105444515A (en) * | 2015-12-11 | 2016-03-30 | 四川长虹电器股份有限公司 | Refrigerator |
CN107798277A (en) * | 2016-09-05 | 2018-03-13 | 合肥美的智能科技有限公司 | Food materials identifying system and method, food materials model training method, refrigerator and server |
CN106568293B (en) * | 2016-10-14 | 2019-03-12 | 青岛海尔特种电冰箱有限公司 | The detection method and refrigerator of refrigerator food operation |
CN107975996A (en) * | 2016-10-21 | 2018-05-01 | 九阳股份有限公司 | A kind of controlling method for refrigerator |
CN108932512A (en) * | 2017-05-22 | 2018-12-04 | 九阳股份有限公司 | A kind of refrigerator food materials input method |
CN107623724A (en) * | 2017-08-28 | 2018-01-23 | 合肥美的智能科技有限公司 | The shared method and system in food materials and space, refrigerator in refrigerator |
CN109425192A (en) * | 2017-08-28 | 2019-03-05 | 合肥美的智能科技有限公司 | Indicate the method and system of food materials position in refrigerator |
CN110906640B (en) * | 2018-09-14 | 2022-08-12 | 博西华电器(江苏)有限公司 | Article positioning method of storage equipment and storage equipment |
EP3816552A1 (en) * | 2019-10-31 | 2021-05-05 | Arçelik Anonim Sirketi | Refrigerator with rfid function |
JP7467897B2 (en) * | 2019-12-04 | 2024-04-16 | 三菱電機株式会社 | Food Management System |
CN111258858A (en) * | 2020-01-07 | 2020-06-09 | 青岛海尔电冰箱有限公司 | Refrigerator and control method thereof |
CN113494803B (en) * | 2020-05-29 | 2022-09-20 | 海信集团有限公司 | Intelligent refrigerator and storage and taking operation detection method for storage in refrigerator door |
CN114485037B (en) * | 2022-02-11 | 2024-04-05 | 海信冰箱有限公司 | Refrigerator and food material positioning method thereof |
-
2021
- 2021-10-18 CN CN202111212660.2A patent/CN113915841B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN113915841A (en) | 2022-01-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113915841B (en) | Refrigerator and food material positioning method thereof | |
CN111507253B (en) | Display article auditing method and device based on artificial intelligence | |
CN106557906A (en) | A kind of warehouse management method and system based on three-dimensional modeling | |
WO2019133337A1 (en) | System and method for determining and implementing sales clusters for stores | |
CN105718975A (en) | Library robot intelligent three-dimensional (3D) navigation and putaway system based on radio frequency identification devices (RFID) technology | |
CA2494784A1 (en) | Methods, devices and associated computer program products for use in the maintenance of complex articles | |
US11276033B2 (en) | System and method for fine-tuning sales clusters for stores | |
CN113915840B (en) | Refrigerator and food material positioning method thereof | |
CN112348737B (en) | Method for generating simulation image, electronic device and storage medium | |
CN107239993A (en) | A kind of matrix decomposition recommendation method and system based on expansion label | |
CN109034694B (en) | Production raw material intelligent storage method and system based on intelligent manufacturing | |
CN110705424A (en) | Method and device for positioning commodity display position and storage medium | |
CN108229413A (en) | Pest and disease damage kind identification method and device | |
JP2022532039A (en) | Convolutional neural network-based landmark tracker | |
CN106915585A (en) | Warehouse article intelligent positioning system | |
CN110610149A (en) | Information processing method and device and computer storage medium | |
CN116649191A (en) | Remote fertilization and irrigation control system and method based on PLC | |
US20220147565A1 (en) | Method of video search in an electronic device | |
Balaska et al. | Smart counting of unboxed stocks in the Warehouse 4.0 ecosystem | |
CN112232334B (en) | Intelligent commodity selling identification and detection method | |
CN110163149A (en) | Acquisition methods, device and the storage medium of LBP feature | |
CN115841718A (en) | Device and method for analyzing goods inventory and logistics through intelligent shelf system | |
CN113743382B (en) | Shelf display detection method, device and system | |
CN209640977U (en) | Intelligent commodity shelf system | |
CN103366032A (en) | System and method for Internet of Things perception layer to conduct unified representation |
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 | ||
CB02 | Change of applicant information |
Address after: 266000 Haixin Avenue, Nancun Town, Pingdu City, Qingdao City, Shandong Province Applicant after: Hisense refrigerator Co.,Ltd. Address before: 266100 Songling Road, Laoshan District, Qingdao, Shandong Province, No. 399 Applicant before: HISENSE (SHANDONG) REFRIGERATOR Co.,Ltd. |
|
CB02 | Change of applicant information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |