CN112231506A - Information recommendation method and device based on food material identification - Google Patents
Information recommendation method and device based on food material identification Download PDFInfo
- Publication number
- CN112231506A CN112231506A CN202011174057.5A CN202011174057A CN112231506A CN 112231506 A CN112231506 A CN 112231506A CN 202011174057 A CN202011174057 A CN 202011174057A CN 112231506 A CN112231506 A CN 112231506A
- Authority
- CN
- China
- Prior art keywords
- food material
- target
- user
- information
- dish
- 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
- 235000013305 food Nutrition 0.000 title claims abstract description 345
- 239000000463 material Substances 0.000 title claims abstract description 336
- 238000000034 method Methods 0.000 title claims abstract description 90
- 238000010411 cooking Methods 0.000 claims abstract description 62
- 235000019640 taste Nutrition 0.000 claims abstract description 43
- 239000002994 raw material Substances 0.000 claims description 43
- 238000013527 convolutional neural network Methods 0.000 claims description 27
- 238000005516 engineering process Methods 0.000 claims description 23
- 238000010586 diagram Methods 0.000 claims description 13
- 238000004891 communication Methods 0.000 claims description 12
- 235000016709 nutrition Nutrition 0.000 claims description 7
- 238000012790 confirmation Methods 0.000 claims description 3
- 235000015278 beef Nutrition 0.000 description 7
- 238000004590 computer program Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 235000004280 healthy diet Nutrition 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 235000009508 confectionery Nutrition 0.000 description 2
- 230000008451 emotion Effects 0.000 description 2
- 235000001497 healthy food Nutrition 0.000 description 2
- 235000007688 Lycopersicon esculentum Nutrition 0.000 description 1
- 240000003768 Solanum lycopersicum Species 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/53—Querying
- G06F16/535—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Library & Information Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses an information recommendation method and device based on food material identification. Firstly, identifying food material elements in a shot food material picture through image processing; then dishes which accord with the favorite taste of the user are searched for aiming at the food material elements; and finally, displaying the information of the dishes for the user to refer to through the display. Therefore, the user can obtain the recommended relevant dishes according to the favorite tastes of the user only by shooting the food materials, so that the user can conveniently know the purposes and relevant cooking methods of the food materials in time, and the method is greatly convenient for the young people who are not good at cooking due to busy work to cook delicious food.
Description
Technical Field
The application relates to the technical field of robots, in particular to an information recommendation method and device based on food material identification.
Background
The cooking at home is economical, practical, clean and sanitary, and is beneficial to healthy diet and enhancement of family emotion. However, people's lives become increasingly busy, and young people often do not cook at home, so that cooking is careless, and various food materials and corresponding dishes are often searched by means of a network to be known.
The functions of the existing household cooking equipment are often single and are only limited to a single function of cooking food. The cooking guide device has the advantage that the cooking guide device can not play an effective guiding and assisting role in cooking for young people.
Disclosure of Invention
The embodiment of the application provides an information recommendation method and device based on food material identification, which can recommend related dishes for shot food materials according to the favorite taste types of users, so that the users can conveniently know the purposes and related cooking methods of the food materials in time, and the method greatly facilitates cooking of young people who are not good at cooking due to busy work at present to cook delicious food.
In a first aspect, an embodiment of the present application provides an information recommendation method based on food material identification, where the method includes:
shooting food materials by using a camera or downloading pictures containing food material contents from a cloud end to obtain food material pictures;
extracting the image characteristics of the food material picture by utilizing a convolutional neural network image processing technology to obtain an image characteristic diagram of the food material picture, wherein the image characteristic diagram comprises food material elements;
performing content identification on the food material elements in the image feature map to obtain a target food material;
acquiring the favorite taste types of the user from personal information of the user;
searching dish information containing the target food material in a dish information database corresponding to the favorite taste type;
and displaying the searched dish information through a display, wherein the dish information comprises dish names, various raw materials, nutritional value analysis and cooking methods.
The information recommendation method and device based on food material identification are disclosed. Firstly, identifying food material elements in a shot food material picture through image processing; then dishes which accord with the favorite taste of the user are searched for aiming at the food material elements; and finally, displaying the information of the dishes for the user to refer to through the display. Therefore, the user can obtain the recommended relevant dishes according to the favorite tastes of the user only by shooting the food materials, so that the user can conveniently know the purposes and relevant cooking methods of the food materials in time, and the method is greatly convenient for the young people who are not good at cooking due to busy work to cook delicious food.
As an optional implementation manner, the extracting, by using a convolutional neural network image processing technique, image features of the food material picture to obtain an image feature map of the food material picture, where the image feature map includes food material elements, includes: extracting image features of the food material picture by using a convolutional neural network image processing technology to obtain an image feature map of the food material picture, wherein the image feature map comprises a first food material element and a second food material element; the content identification of the food material elements in the image feature map to obtain the target food material comprises the following steps: performing content classification prediction on the first food material element to obtain a first food material classification result, and performing content classification prediction on the second food material element to obtain a second food material classification result; displaying an icon of the first food material classification result and an icon of the second food material classification result through a display; and acquiring target food material selection operation of the icon of the target food material classification result selected by the user, and confirming the target food material according to the target food material selection operation.
It can be understood that the food material picture taken by the user may simultaneously include a plurality of food material elements. After the food material elements in the picture are identified through image processing, all the food material elements can be displayed, and a user selects which food material element to recommend related dishes.
As an optional implementation manner, the extracting, by using a convolutional neural network image processing technique, image features of the food material picture to obtain an image feature map of the food material picture, where the image feature map includes food material elements, includes: extracting image features of the food material picture by using a convolutional neural network image processing technology to obtain an image feature map of the food material picture, wherein the image feature map comprises a first food material element and a second food material element; the content identification of the food material elements in the image feature map to obtain the target food material comprises the following steps: performing content classification prediction on the first food material element to obtain a first food material classification result, predicting the outline size of the first food material element to obtain a first prediction size, performing content classification prediction on the second food material element to obtain a second food material classification result, and predicting the outline size of the second food material element to obtain a second prediction size; selecting the first food material classification result as the target food material if the first predicted size is larger than the second predicted size.
It can be understood that the shot food material picture may include a plurality of food material elements, and the selection of the food material elements closer to the camera for recommending related dishes is more intelligent. Due to the principle of big-end-up and small-end-up during shooting, the food material elements with large sizes are close to the camera, and the food material elements with small sizes are far from the camera. It is thus possible to select a relevant dish recommendation for food material elements of larger size.
As an optional implementation manner, the extracting, by using a convolutional neural network image processing technique, image features of the food material picture to obtain an image feature map of the food material picture, where the image feature map includes food material elements, includes: extracting image features of the food material picture by using a convolutional neural network image processing technology to obtain an image feature map of the food material picture, wherein the image feature map comprises a first food material element and a second food material element; after obtaining the image feature map of the food material picture and before performing content recognition on the food material elements in the image feature map, the information recommendation method based on food material recognition further includes: respectively detecting the distances from the first food material element and the second food material element to the robot through a radar detector; taking a distance of the first food material element to the robot as a first distance; taking the distance of the second food material element to the robot as a second distance; the content identification of the food material elements in the image feature map to obtain the target food material comprises the following steps: under the condition that the first distance is smaller than the second distance, selecting to perform content classification prediction on the first food material element to obtain a first food material classification result; and taking the first food material classification result as the target food material.
It can be understood that the shot food material picture may include a plurality of food material elements, and the selection of the food material elements closer to the camera for recommending related dishes is more intelligent. Therefore, the equipped radar detectors are used for respectively detecting the distances of the food material elements, and the food material element closest to the camera is judged.
As an optional implementation manner, after displaying the found dish information through the display, the method further includes: acquiring a dish selection operation of selecting target dish information from the displayed dish information by a user, and confirming the target dish information of the user according to the dish selection operation; and ordering and purchasing the raw materials in the target dish information in a target supermarket through an online purchasing platform.
It can be understood that after the relevant recommended dishes are displayed to the user, the user can select the favorite target dishes from the relevant recommended dishes. After the target dish selected by the user is obtained, the raw materials of the target dish can be ordered and purchased in time through a third-party shopping platform.
As an optional implementation manner, after the target dish information of the user is confirmed according to the dish selection operation, before the item of raw materials in the target dish information is ordered and purchased by the online purchasing platform in a target supermarket, the information recommendation method based on food material identification further includes: uploading the user ID of the user and the target dish name in the target dish information to a cloud; searching personal basic information of other users which are located within a threshold range from the user and select the target dish at the same time in the cloud, wherein the personal basic information comprises a user ID, an address and a telephone; and displaying the searched personal basic information of the other users through the display.
It can be understood that, in order to enhance communication among users, information of other users who select the same target dishes and are close to each other can be displayed for the users, so that the communication and communication between the users and the other users for the food cooking method are facilitated.
As an optional implementation manner, after the displaying the searched personal basic information of the other user through the display, before ordering and purchasing the various raw materials in the target dish information in a target supermarket through an online purchasing platform, the method further includes: acquiring a list spelling object selected by the user from the other users; and sending a list-sharing request to the list-sharing object through the communication equipment.
It can be understood that the user can select a suitable order object from the displayed other users, and the order object and the appropriate order object are used for ordering and purchasing raw materials in the target dish.
As an optional implementation manner, after the sending of the order combining request to the order combining object by the communication device, before the ordering purchase of each item of raw materials in the target dish information is performed in a target supermarket by an online purchase platform, the method further includes: displaying the raw material names of the raw materials in the target dish information and the unit prices of the raw materials sold by the target supermarket; after receiving the confirmation feedback information of the order object, acquiring target raw materials selected by the user and the order object and corresponding purchase quantity; the ordering purchase of the raw materials in the target dish information in a target supermarket through the online purchase platform comprises the following steps: and ordering and purchasing the target raw materials according to the purchase quantity in a target supermarket through the online purchasing platform.
Immediately, when the user and the order sharing object purchase the raw materials of the target dish together, the order can be placed for purchase only after the two parties confirm the list of order sharing purchase together.
As an optional implementation manner, after displaying the found dish information through the display, the method further includes: acquiring cooking selection operation of the user for selecting a cooking method from the displayed dish information, and confirming a target cooking method according to the cooking selection operation; downloading a cooking teaching video corresponding to the target cooking method from a cloud; and playing a cooking teaching video corresponding to the target cooking method through the display.
It is understood that people now become increasingly busy, young people often become less well cooked, and have little knowledge of a healthy diet. Even after the recommended dishes are displayed to the user, the user may not be able to cook the dishes well. Therefore, the robot can play the corresponding cooking teaching video for the user according to the selection of the user so as to assist the user in cooking and making healthy food.
In a second aspect, an embodiment of the present application provides an information recommendation apparatus based on food material identification, which includes means for performing the method of the first aspect. The information recommendation device based on food material identification comprises a camera, a processor and a display, wherein the processor is respectively and electrically connected with the camera and the display;
the camera is used for shooting food materials to obtain food material pictures and transmitting the food material pictures to the processor;
the processor includes: the device comprises an identification module, a taste acquisition module and an inquiry module;
the identification module is used for extracting the image characteristics of the food material picture by utilizing a convolutional neural network image processing technology to obtain an image characteristic diagram of the food material picture, wherein the image characteristic diagram comprises food material elements; performing content identification on the food material elements in the image feature map to obtain a target food material;
the taste acquisition module is used for acquiring the favorite taste types of the user from the personal information of the user;
the searching module is used for searching the dish information database corresponding to the favorite taste type for the dish information containing the target food material;
the display is used for acquiring the dish information which is transmitted by the processor and contains the target food material and displaying the dish information, and the dish information comprises dish names, various raw materials, nutritional value analysis and cooking methods.
Has the advantages that:
the application discloses an information recommendation method and device based on food material identification. Firstly, identifying food material elements in a shot food material picture through image processing; then dishes which accord with the favorite taste of the user are searched for aiming at the food material elements; and finally, displaying the information of the dishes for the user to refer to through the display. Therefore, the user can obtain the recommended relevant dishes according to the favorite tastes of the user only by shooting the food materials, so that the user can conveniently know the purposes and relevant cooking methods of the food materials in time, and the method is greatly convenient for the young people who are not good at cooking due to busy work to cook delicious food.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flowchart of an information recommendation method based on food material identification according to an embodiment of the present application;
fig. 2 is a schematic flowchart of another information recommendation method based on food material identification according to an embodiment of the present application;
fig. 3 is a schematic diagram of module connections of an information recommendation device based on food material identification according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The cooking at home is economical, practical, clean and sanitary, and is beneficial to healthy diet and enhancement of family emotion. However, people's lives become increasingly busy, and young people often do not cook at home, so that cooking is careless, and various food materials and corresponding dishes are often searched by means of a network to be known. The functions of the existing household cooking equipment are often single and are only limited to a single function of cooking food. The cooking guide device has the advantage that the cooking guide device can not play an effective guiding and assisting role in cooking for young people.
As shown in fig. 1, an embodiment of the present application provides an information recommendation method based on food material identification, where the method includes:
101. and shooting the food materials by using a camera or downloading pictures containing the food material contents from the cloud end to obtain food material pictures.
In the embodiment of the application, the information recommendation device based on food material identification can be a terminal device such as a mobile phone or a household robot, and is provided with a camera, so that a user can shoot a food material interested by the user by using the camera to obtain a food material picture.
For example, when a user shops in a supermarket, the user can shoot beef which is a food material interested by the user to obtain a beef picture.
102. Extracting the image characteristics of the food material picture by utilizing a convolutional neural network image processing technology to obtain an image characteristic diagram of the food material picture, wherein the image characteristic diagram comprises food material elements; and performing content identification on the food material elements in the image feature map to obtain the target food material.
In the embodiment of the present application, the "extracting the image features of the food material picture" means that the processor extracts the image features of the food material picture to be processed by using an image processing technology such as a Convolutional Neural Network (CNN) to obtain an image Feature Map of the food material picture. And performing content identification on food material elements in the food material picture to obtain the target food material. For example, a food material element, beef, in a beef picture shot by a user shopping a supermarket is identified.
103. Acquiring the favorite taste type of the user from the personal information of the user; and searching the dish information database corresponding to the favorite taste type for the dish information containing the target food material.
In the embodiment of the present application, the above-mentioned personal information is created by the user himself, and the personal information includes the user ID and the favorite taste type. Displaying a plurality of taste type icons through a display during creation, wherein each taste type corresponds to a separate dish information database; acquiring a taste selection operation of selecting a favorite taste type icon by a user, and confirming the favorite taste type of the user according to the taste selection operation; and recording the favorite taste types in the personal information of the user. The above taste types include: the taste types are sour and sweet, spicy and light, each taste type corresponds to a dish information database, and dishes in the dish information database are dishes with the taste.
For example, after the target food material is beef obtained through image recognition, if the favorite taste type of the user is sour and sweet, dishes such as tomato, beef and the like can be inquired from the corresponding dish information database; if the acquired favorite taste type of the user is partial spicy, dishes such as boiled beef and the like can be inquired from the corresponding dish information database.
104. And displaying the searched dish information through a display, wherein the dish information comprises the name of the dish, various raw materials, nutritional value analysis and a cooking method.
The information recommendation method and device based on food material identification are disclosed. Firstly, identifying food material elements in a shot food material picture through image processing; then dishes which accord with the favorite taste of the user are searched for aiming at the food material elements; and finally, displaying the information of the dishes for the user to refer to through the display. Therefore, the user can obtain the recommended relevant dishes according to the favorite tastes of the user only by shooting the food materials, so that the user can conveniently know the purposes and relevant cooking methods of the food materials in time, and the method is greatly convenient for the young people who are not good at cooking due to busy work to cook delicious food.
As an optional implementation manner, extracting image features of a food material picture by using a convolutional neural network image processing technology to obtain an image feature map of the food material picture, where the image feature map includes food material elements, and the method includes: extracting image features of the food material picture by using a convolutional neural network image processing technology to obtain an image feature map of the food material picture, wherein the image feature map comprises a first food material element and a second food material element; performing content identification on food material elements in the image feature map to obtain a target food material, wherein the content identification comprises the following steps: performing content classification prediction on the first food material element to obtain a first food material classification result, and performing content classification prediction on the second food material element to obtain a second food material classification result; displaying an icon of the first food material classification result and an icon of the second food material classification result through a display; and acquiring target food material selection operation of the icon of the target food material classification result selected by the user, and confirming the target food material according to the target food material selection operation.
It can be understood that the food material picture taken by the user may simultaneously include a plurality of food material elements. After the food material elements in the picture are identified through image processing, all the food material elements can be displayed, and a user selects which food material element to recommend related dishes.
In the embodiment of the application, a user can select a target food material through an input device such as a touch display or a keyboard.
As an optional implementation manner, extracting image features of a food material picture by using a convolutional neural network image processing technology to obtain an image feature map of the food material picture, where the image feature map includes food material elements, and the method includes: extracting image features of the food material picture by using a convolutional neural network image processing technology to obtain an image feature map of the food material picture, wherein the image feature map comprises a first food material element and a second food material element; performing content identification on food material elements in the image feature map to obtain a target food material, wherein the content identification comprises the following steps: performing content classification prediction on a first food material element to obtain a first food material classification result, predicting the outline size of the first food material element to obtain a first prediction size, performing content classification prediction on a second food material element to obtain a second food material classification result, and predicting the outline size of the second food material element to obtain a second prediction size; and selecting the first food material classification result as the target food material under the condition that the first prediction size is larger than the second prediction size.
It can be understood that the shot food material picture may include a plurality of food material elements, and the selection of the food material elements closer to the camera for recommending related dishes is more intelligent. Due to the principle of big-end-up and small-end-up during shooting, the food material elements with large sizes are close to the camera, and the food material elements with small sizes are far from the camera. It is thus possible to select a relevant dish recommendation for food material elements of larger size.
As an optional implementation manner, extracting image features of a food material picture by using a convolutional neural network image processing technology to obtain an image feature map of the food material picture, where the image feature map includes food material elements, and the method includes: extracting image features of the food material picture by using a convolutional neural network image processing technology to obtain an image feature map of the food material picture, wherein the image feature map comprises a first food material element and a second food material element; after the image feature map of the food material picture is obtained and before the content identification is performed on the food material elements in the image feature map, the information recommendation method based on the food material identification further comprises the following steps: respectively detecting the distances from the first food material element and the second food material element to the robot through a radar detector; taking the distance from the first food material element to the robot as a first distance; taking the distance from the second food material element to the robot as a second distance; performing content identification on food material elements in the image feature map to obtain a target food material, wherein the content identification comprises the following steps: under the condition that the first distance is smaller than the second distance, content classification prediction is conducted on the first food material elements to obtain a first food material classification result; and taking the first food material classification result as the target food material.
It can be understood that the shot food material picture may include a plurality of food material elements, and the selection of the food material elements closer to the camera for recommending related dishes is more intelligent. Therefore, the equipped radar detectors are used for respectively detecting the distances of the food material elements, and the food material element closest to the camera is judged.
In this embodiment, the radar detector is disposed near the camera so as to accurately detect the distance from the food material element to the camera.
As an optional implementation manner, after displaying the found dish information through the display, the method further includes: acquiring cooking selection operation of a user for selecting a cooking method from the displayed dish information, and confirming a target cooking method according to the cooking selection operation; downloading a cooking teaching video corresponding to the target cooking method from the cloud; and playing a cooking teaching video corresponding to the target cooking method through the display.
It is understood that people now become increasingly busy, young people often become less well cooked, and have little knowledge of a healthy diet. Even after the recommended dishes are displayed to the user, the user may not be able to cook the dishes well. Therefore, the robot can play the corresponding cooking teaching video for the user according to the selection of the user so as to assist the user in cooking and making healthy food.
As shown in fig. 2, an embodiment of the present application further provides another information recommendation method based on food material identification, and compared with the method shown in fig. 1, the method shown in fig. 2 further includes:
205. and acquiring a dish selection operation for selecting target dish information from the displayed dish information by the user, and confirming the target dish information of the user according to the dish selection operation.
In the embodiment of the application, after the searched dish information is displayed through the display, the user can select the favorite target dish for further understanding and purchase through input equipment such as a touch display or a keyboard.
206. And ordering and purchasing each raw material in the target dish information in the target supermarket through the online purchasing platform.
It can be understood that after the relevant recommended dishes are displayed to the user, the user can select the favorite target dishes from the relevant recommended dishes. After the target dish selected by the user is obtained, the raw materials of the target dish can be ordered and purchased in time through a third-party shopping platform.
As an optional implementation manner, after confirming target dish information of a user according to a dish selection operation, before ordering and purchasing each raw material in the target dish information in a target supermarket through an online purchasing platform, the information recommendation method based on food material identification further includes: uploading the user ID of the user and the target dish name in the target dish information to the cloud; searching personal basic information of other users, which are positioned within a threshold range from the user and select the target dish at the same time, in the cloud, wherein the personal basic information comprises a user ID, an address and a telephone; and displaying the searched personal basic information of other users through the display.
It can be understood that, in order to enhance communication among users, information of other users who select the same target dishes and are close to each other can be displayed for the users, so that the communication and communication between the users and the other users for the food cooking method are facilitated.
As an optional implementation manner, after the found personal basic information of the other users is displayed through the display, before the purchase of orders of the raw materials in the target dish information is performed in the target supermarket through the online purchase platform, the method further includes: acquiring a list spelling object selected by a user from other users; and sending a list-sharing request to the list-sharing object through the communication equipment.
It can be understood that the user can select a suitable order object from the displayed other users, and the order object and the appropriate order object are used for ordering and purchasing raw materials in the target dish.
As an optional implementation manner, after the order matching request is sent to the order matching object through the communication device, before the order is placed and purchased for each raw material in the target dish information in the target supermarket through the online purchasing platform, the method further includes: displaying the raw material names of all raw materials in the target dish information and the unit prices of the raw materials sold by a target supermarket; after receiving the confirmation feedback information of the order object, acquiring target raw materials selected by the user and the order object and corresponding purchase quantity; ordering and purchasing each raw material in the target dish information in a target supermarket through an online purchasing platform, comprising the following steps: and ordering and purchasing the target raw materials according to the purchase quantity in the target supermarket through the online purchasing platform.
Immediately, when the user and the order sharing object purchase the raw materials of the target dish together, the order can be placed for purchase only after the two parties confirm the list of order sharing purchase together.
As shown in fig. 3, an embodiment of the present application provides an information recommendation device based on food material identification, which includes a unit for executing the method shown in fig. 1 or fig. 2.
The information recommendation device based on food material identification comprises a camera 31, a processor 33 and a display 32, wherein the processor 33 is electrically connected with the camera 31 and the display 32 respectively.
The camera 31 is used for shooting food materials to obtain food material pictures, and transmitting the food material pictures to the processor 33;
the processor 33 includes: an identification module 331, a taste acquisition module 332 and a query module 333;
the identification module 331 is configured to extract image features of the food material picture by using a convolutional neural network image processing technology to obtain an image feature map of the food material picture, where the image feature map includes food material elements; performing content identification on food material elements in the image feature map to obtain a target food material;
a taste acquisition module 332, configured to acquire a favorite taste type of the user from the personal information of the user;
the searching module is used for searching the dish information containing the target food material in the dish information database corresponding to the favorite taste type;
and a display 32 for acquiring the dish information including the target food material transmitted from the processor 33 and displaying the dish information, wherein the dish information includes a name of the dish, each raw material, a nutritional value analysis and a cooking method.
In another embodiment of the present application, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program, the computer program comprising program instructions that, when executed by a processor, implement:
shooting food materials by using a camera or downloading pictures containing food material contents from a cloud end to obtain food material pictures;
extracting the image characteristics of the food material picture by utilizing a convolutional neural network image processing technology to obtain an image characteristic diagram of the food material picture, wherein the image characteristic diagram comprises food material elements; performing content identification on food material elements in the image feature map to obtain a target food material;
acquiring the favorite taste type of the user from the personal information of the user; searching dish information containing target food materials in a dish information database corresponding to the favorite taste types;
and displaying the searched dish information through a display, wherein the dish information comprises the name of the dish, various raw materials, nutritional value analysis and a cooking method.
The computer readable storage medium may be an internal storage unit of the terminal device of any of the foregoing embodiments, for example, a hard disk or a memory of the terminal device. The computer readable storage medium may also be an external storage device of the terminal device, such as a plug-in hard disk provided on the terminal device, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like. Further, the computer-readable storage medium may also include both an internal storage unit of the terminal device and an external storage device. The computer-readable storage medium is used for storing computer programs and other programs and data required by the terminal device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, and the program can be stored in a computer readable storage medium, and when executed, can include the processes 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 (RAM), or the like.
While the invention has been described with reference to a number of embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
While the invention has been described with reference to a number of embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. An information recommendation method based on food material identification is characterized by comprising the following steps:
shooting food materials by using a camera or downloading pictures containing food material contents from a cloud end to obtain food material pictures;
extracting the image characteristics of the food material picture by utilizing a convolutional neural network image processing technology to obtain an image characteristic diagram of the food material picture, wherein the image characteristic diagram comprises food material elements;
performing content identification on the food material elements in the image feature map to obtain a target food material;
acquiring the favorite taste types of the user from personal information of the user;
searching dish information containing the target food material in a dish information database corresponding to the favorite taste type;
and displaying the searched dish information through a display, wherein the dish information comprises dish names, various raw materials, nutritional value analysis and cooking methods.
2. The food material identification-based information recommendation method according to claim 1,
the method for extracting the image features of the food material picture by using the convolutional neural network image processing technology to obtain the image feature map of the food material picture, wherein the image feature map contains food material elements, and comprises the following steps:
extracting image features of the food material picture by using a convolutional neural network image processing technology to obtain an image feature map of the food material picture, wherein the image feature map comprises a first food material element and a second food material element;
the content identification of the food material elements in the image feature map to obtain the target food material comprises the following steps:
performing content classification prediction on the first food material element to obtain a first food material classification result, and performing content classification prediction on the second food material element to obtain a second food material classification result;
displaying an icon of the first food material classification result and an icon of the second food material classification result through a display;
and acquiring target food material selection operation of the icon of the target food material classification result selected by the user, and confirming the target food material according to the target food material selection operation.
3. The food material identification-based information recommendation method according to claim 1,
the method for extracting the image features of the food material picture by using the convolutional neural network image processing technology to obtain the image feature map of the food material picture, wherein the image feature map contains food material elements, and comprises the following steps:
extracting image features of the food material picture by using a convolutional neural network image processing technology to obtain an image feature map of the food material picture, wherein the image feature map comprises a first food material element and a second food material element;
the content identification of the food material elements in the image feature map to obtain the target food material comprises the following steps:
performing content classification prediction on the first food material element to obtain a first food material classification result, predicting the outline size of the first food material element to obtain a first prediction size, performing content classification prediction on the second food material element to obtain a second food material classification result, and predicting the outline size of the second food material element to obtain a second prediction size;
selecting the first food material classification result as the target food material if the first predicted size is larger than the second predicted size.
4. The food material identification-based information recommendation method according to claim 1,
the method for extracting the image features of the food material picture by using the convolutional neural network image processing technology to obtain the image feature map of the food material picture, wherein the image feature map contains food material elements, and comprises the following steps:
extracting image features of the food material picture by using a convolutional neural network image processing technology to obtain an image feature map of the food material picture, wherein the image feature map comprises a first food material element and a second food material element;
after obtaining the image feature map of the food material picture and before performing content recognition on the food material elements in the image feature map, the information recommendation method based on food material recognition further includes:
respectively detecting the distances from the first food material element and the second food material element to the robot through a radar detector;
taking a distance of the first food material element to the robot as a first distance;
taking the distance of the second food material element to the robot as a second distance;
the content identification of the food material elements in the image feature map to obtain the target food material comprises the following steps:
under the condition that the first distance is smaller than the second distance, selecting to perform content classification prediction on the first food material element to obtain a first food material classification result;
and taking the first food material classification result as the target food material.
5. The food material identification-based information recommendation method according to claim 1,
after the found dish information is displayed through the display, the method further comprises:
acquiring a dish selection operation of selecting target dish information from the displayed dish information by a user, and confirming the target dish information of the user according to the dish selection operation;
and ordering and purchasing the raw materials in the target dish information in a target supermarket through an online purchasing platform.
6. The food material identification-based information recommendation method according to claim 5,
after the target dish information of the user is confirmed according to the dish selection operation, before the various raw materials in the target dish information are placed for purchase in a target supermarket by the online purchase platform, the information recommendation method based on food material identification further comprises the following steps:
uploading the user ID of the user and the target dish name in the target dish information to a cloud;
searching personal basic information of other users which are located within a threshold range from the user and select the target dish at the same time in the cloud, wherein the personal basic information comprises a user ID, an address and a telephone;
and displaying the searched personal basic information of the other users through the display.
7. The food material identification-based information recommendation method according to claim 6,
after the personal basic information of the other users found out by the display is displayed, before the items of raw materials in the target dish information are ordered and purchased in a target supermarket by an online purchasing platform, the method further comprises the following steps:
acquiring a list spelling object selected by the user from the other users;
and sending a list-sharing request to the list-sharing object through the communication equipment.
8. The food material identification-based information recommendation method according to claim 7,
after the order combining request is sent to the order combining object through the communication equipment, before the order is placed and purchased for each raw material in the target dish information in a target supermarket through an online purchasing platform, the method further comprises the following steps:
displaying the raw material names of the raw materials in the target dish information and the unit prices of the raw materials sold by the target supermarket;
after receiving the confirmation feedback information of the order object, acquiring target raw materials selected by the user and the order object and corresponding purchase quantity;
the ordering purchase of the raw materials in the target dish information in a target supermarket through the online purchase platform comprises the following steps:
and ordering and purchasing the target raw materials according to the purchase quantity in a target supermarket through the online purchasing platform.
9. The food material identification-based information recommendation method according to claim 1,
after the found dish information is displayed through the display, the method further comprises:
acquiring cooking selection operation of the user for selecting a cooking method from the displayed dish information, and confirming a target cooking method according to the cooking selection operation;
downloading a cooking teaching video corresponding to the target cooking method from a cloud;
and playing a cooking teaching video corresponding to the target cooking method through the display.
10. An information recommendation device based on food material identification, which is used for executing the information recommendation method based on food material identification according to any one of claims 1 to 9, and is characterized by comprising:
the processor is electrically connected with the camera and the display respectively;
the camera is used for shooting food materials to obtain food material pictures and transmitting the food material pictures to the processor;
the processor includes: the device comprises an identification module, a taste acquisition module and an inquiry module;
the identification module is used for extracting the image characteristics of the food material picture by utilizing a convolutional neural network image processing technology to obtain an image characteristic diagram of the food material picture, wherein the image characteristic diagram comprises food material elements; performing content identification on the food material elements in the image feature map to obtain a target food material;
the taste acquisition module is used for acquiring the favorite taste types of the user from the personal information of the user;
the searching module is used for searching the dish information database corresponding to the favorite taste type for the dish information containing the target food material;
the display is used for acquiring the dish information which is transmitted by the processor and contains the target food material and displaying the dish information, and the dish information comprises dish names, various raw materials, nutritional value analysis and cooking methods.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011174057.5A CN112231506A (en) | 2020-10-28 | 2020-10-28 | Information recommendation method and device based on food material identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011174057.5A CN112231506A (en) | 2020-10-28 | 2020-10-28 | Information recommendation method and device based on food material identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112231506A true CN112231506A (en) | 2021-01-15 |
Family
ID=74110760
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011174057.5A Pending CN112231506A (en) | 2020-10-28 | 2020-10-28 | Information recommendation method and device based on food material identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112231506A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105635251A (en) * | 2015-12-21 | 2016-06-01 | 美的集团股份有限公司 | Recipe pushing method and system and cloud server |
| CN106886910A (en) * | 2015-12-16 | 2017-06-23 | 阿里巴巴集团控股有限公司 | The recommendation method and apparatus of consumption information, the method and apparatus for spelling list |
| CN109165991A (en) * | 2018-07-10 | 2019-01-08 | 无锡天脉聚源传媒科技有限公司 | Folk prescription method, system, device and storage medium are spelled in a kind of take-away |
| CN109509038A (en) * | 2018-12-27 | 2019-03-22 | 盯盯拍（深圳）云技术有限公司 | Information-pushing method and information push-delivery apparatus |
| CN109829774A (en) * | 2018-11-30 | 2019-05-31 | 广州富港万嘉智能科技有限公司 | One key booking method of food materials, system, electronic equipment and storage medium |
| CN110223757A (en) * | 2019-04-23 | 2019-09-10 | 平安科技（深圳）有限公司 | The recommended method of recipe scheme, device, medium, electronic equipment |
| CN111125516A (en) * | 2019-12-03 | 2020-05-08 | 深圳厨小易网络科技有限公司 | Intelligent menu recommendation method and system based on image recognition |
| CN111522848A (en) * | 2020-04-21 | 2020-08-11 | 珠海格力电器股份有限公司 | Method, device, computer equipment and storage medium for processing dish data |
| CN111568153A (en) * | 2020-03-31 | 2020-08-25 | 海信集团有限公司 | Kitchen electrical system for realizing dish cooking procedure recommendation |
| CN111667348A (en) * | 2020-06-30 | 2020-09-15 | 拉扎斯网络科技（上海）有限公司 | Order splicing method and device |
-
2020
- 2020-10-28 CN CN202011174057.5A patent/CN112231506A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106886910A (en) * | 2015-12-16 | 2017-06-23 | 阿里巴巴集团控股有限公司 | The recommendation method and apparatus of consumption information, the method and apparatus for spelling list |
| CN105635251A (en) * | 2015-12-21 | 2016-06-01 | 美的集团股份有限公司 | Recipe pushing method and system and cloud server |
| CN109165991A (en) * | 2018-07-10 | 2019-01-08 | 无锡天脉聚源传媒科技有限公司 | Folk prescription method, system, device and storage medium are spelled in a kind of take-away |
| CN109829774A (en) * | 2018-11-30 | 2019-05-31 | 广州富港万嘉智能科技有限公司 | One key booking method of food materials, system, electronic equipment and storage medium |
| CN109509038A (en) * | 2018-12-27 | 2019-03-22 | 盯盯拍（深圳）云技术有限公司 | Information-pushing method and information push-delivery apparatus |
| CN110223757A (en) * | 2019-04-23 | 2019-09-10 | 平安科技（深圳）有限公司 | The recommended method of recipe scheme, device, medium, electronic equipment |
| CN111125516A (en) * | 2019-12-03 | 2020-05-08 | 深圳厨小易网络科技有限公司 | Intelligent menu recommendation method and system based on image recognition |
| CN111568153A (en) * | 2020-03-31 | 2020-08-25 | 海信集团有限公司 | Kitchen electrical system for realizing dish cooking procedure recommendation |
| CN111522848A (en) * | 2020-04-21 | 2020-08-11 | 珠海格力电器股份有限公司 | Method, device, computer equipment and storage medium for processing dish data |
| CN111667348A (en) * | 2020-06-30 | 2020-09-15 | 拉扎斯网络科技（上海）有限公司 | Order splicing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10467267B2 (en) | Iterative image search algorithm informed by continuous human-machine input feedback | |
| CN106598998B (en) | Information acquisition method and information acquisition device | |
| CN111984837B (en) | Commodity data processing method, device and equipment | |
| US20140172821A1 (en) | Generating filters for refining search results | |
| US11823042B2 (en) | System for measuring food weight | |
| KR20200136445A (en) | Ordering method and device, electronic equipment | |
| JP6310599B1 (en) | SEARCH DEVICE, SEARCH METHOD, AND SEARCH PROGRAM | |
| CN109146630A (en) | Information-pushing method | |
| CN112528076A (en) | Video recommendation method, device, equipment and storage medium | |
| US20190325501A1 (en) | Meal-Kit Recommendation Engine | |
| CN109741125A (en) | Recommend method and device, the storage medium, electronic device of vegetable | |
| CN112464013A (en) | Information pushing method and device, electronic equipment and storage medium | |
| CN112069403A (en) | Menu recommendation method and device, computer equipment and storage medium | |
| CN110675389A (en) | Food recommendation method, storage medium and intelligent household equipment | |
| CN109344323A (en) | Information-pushing method | |
| JP6353118B1 (en) | Display program, information providing apparatus, display apparatus, display method, information providing method, and information providing program | |
| KR20220128883A (en) | Apparatus, method and computer readable recording medium for pairing and recommending wine and food | |
| CN116703503A (en) | Intelligent recommendation method and system for campus canteen dishes | |
| CN112419432A (en) | Method and device for controlling food in refrigerator, electronic equipment and storage medium | |
| CN112231506A (en) | Information recommendation method and device based on food material identification | |
| JP6396568B1 (en) | PROVIDING PROGRAM, PROVIDING DEVICE, PROVIDING METHOD, TERMINAL DEVICE, AND INFORMATION PROVIDING DEVICE | |
| JP2004086684A (en) | Cooking recipe inquiry system, cooking recipe inquiry method, and cooking recipe inquiry program | |
| CN116206296A (en) | Food material input method and equipment | |
| CN114218415A (en) | Cooking recipe display method and device | |
| CN114677190A (en) | Method, device and system for processing visual material and computer terminal |
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 |