CN111046289A - Food processing recommendation method, training method of food processing model and related device - Google Patents
Food processing recommendation method, training method of food processing model and related device Download PDFInfo
- Publication number
- CN111046289A CN111046289A CN201911284771.7A CN201911284771A CN111046289A CN 111046289 A CN111046289 A CN 111046289A CN 201911284771 A CN201911284771 A CN 201911284771A CN 111046289 A CN111046289 A CN 111046289A
- Authority
- CN
- China
- Prior art keywords
- food material
- information
- material processing
- processing model
- user
- 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
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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The application relates to a food material processing recommendation method, a training method of a food material processing model and a related device. The method comprises the following steps: acquiring preset dish information and user information; analyzing preset dish information to obtain food material information of dishes; and inputting the food material information and the user information into the food material processing model to obtain food material guide information. The method can improve the accuracy of the amount of the seasoning, the user experience and convenience. Therefore, the food material information and the user information can be combined to realize automatic and intelligent generation of food material guide information, and the processing mode of the food material corresponding to the dish is determined autonomously.
Description
Technical Field
The present application relates to the technical field of artificial intelligence, and in particular, to a method for recommending food processing, a method for training a food processing model, and a related apparatus.
Background
With the pace of life increasing, more and more people choose to eat outside, particularly some young people and office workers. This is not the case, not least because they are not as simple as cooking.
At present, the living idea of people is changed, and even a common well-off family, only one dish is unlikely to be available on a dining table. Then, an increase in the number of dishes leads to a doubling of the cooking time, wherein the most time consuming is reflected in the step of food material preparation. In order to save the time consumption of the step, a plurality of intelligent vegetable cutting devices are provided for realizing automatic vegetable cutting food processing. However, whether the food material is processed manually or by the intelligent vegetable-cutting device, the processing mode of the food material is determined by the user, and the mode of processing the food material by autonomous intelligentization cannot be realized.
Disclosure of Invention
In view of the above, it is necessary to provide a food material processing recommendation method, a food material processing model training method, and a related apparatus capable of improving intellectualization of cutting food.
According to a first aspect of the application, a food material processing recommendation method is provided, and the method comprises the following steps: acquiring preset dish information and user information; analyzing the preset dish information to obtain food material information of the dish; and inputting the food material information and the user information into a food material processing model to obtain food material guide information, wherein the food material guide information is used for guiding food material processing of food materials corresponding to the dishes in a corresponding mode.
Optionally, the user information includes one or more of the following: weather information of the position where the user is located, medical information of the user, taste information of the user and historical processing information of the user on food materials corresponding to the dishes.
Optionally, after the food material information and the user information are both input to a food material processing model to obtain food material guidance information, the method further includes: and sending the food material guide information to a vegetable cutting device so that the vegetable cutting device can perform corresponding food material processing on the food materials corresponding to the dish according to the food material guide information.
Optionally, the food material processing model is trained through the following steps: acquiring user evaluation information about preset dishes; preprocessing the evaluation information to obtain sample updating data, wherein the sample updating data comprises: food material information and user information of the dishes; and updating the current sample base based on the sample updating data, training a current food material processing model according to the updated sample base, and taking the trained food material processing model as a food material processing model for outputting food material guide information.
Optionally, the food material processing comprises one or more of the following: the method comprises the steps of cutting the food materials in a preset mode, storing the cut food materials, configuring the type of seasonings required during cooking and adding time of various seasonings.
Optionally, the food material processing model comprises a BP neural network model.
According to a second aspect of the present application, there is provided a method for training a food material processing model, the method comprising: acquiring user evaluation information about preset dishes; preprocessing the evaluation information to obtain sample updating data, wherein the sample updating data comprises: food material information and user information of the dishes; and updating the current sample base based on the sample updating data, training a current food material processing model according to the updated sample base, and taking the trained food material processing model as a food material processing model for outputting food material guide information.
Optionally, updating the current sample library based on the sample update data includes: and replacing the earliest acquired sample data in the current sample library by the sample updating data.
Optionally, after the current sample base is updated based on the sample update data and before the current food material processing model is trained according to the updated sample base, the method further includes: judging whether the number of the sample updating data is larger than a preset number threshold value or not; and under the condition that the number of the sample updating data is judged to be larger than the preset number threshold, determining to train the current food material processing model according to the updated sample library.
Optionally, after updating the current sample library based on the sample update data and before training the current food material processing model according to the updated sample library, the method further includes: and setting the initial weight and the threshold of the current food material processing model as the initial weight and the threshold of the trained food material processing model.
Optionally, after the current food material processing model is trained according to the updated sample library, the method further includes: judging whether the learning precision in the training process is converged to a set minimum value; and determining that the training of the food material processing model is finished when the learning precision is judged to be converged to the set minimum value.
Optionally, in a case where it is determined that the learning accuracy does not converge to the set minimum value, the method further includes: judging whether the iteration times in the training process reach the set iteration times or not; if so, determining that the training of the food material processing model is finished; otherwise, continuing to train the current food material processing model according to the updated sample library.
Optionally, the user information includes one or more of the following: weather information of the position where the user is located, medical information of the user, taste information of the user and historical food material processing information of the user on food materials corresponding to the preset dishes.
According to a third aspect of the present application, there is provided a food material processing recommendation system, the system comprising: the dish information acquisition module is used for acquiring preset dish information; the analysis module is used for analyzing the preset dish information to obtain food material information and user information of the dish; and the guidance information generation module is used for inputting the food material information and the user information into a food material processing model to obtain food material guidance information, wherein the food material guidance information is used for guiding food material processing of food materials corresponding to the dishes in a corresponding mode.
According to a fourth aspect of the present application, there is provided a training system of food material processing models, the system comprising: the evaluation information acquisition module is used for acquiring user evaluation information about preset dishes; a preprocessing module, configured to preprocess the evaluation information to obtain sample update data, where the sample update data includes: food material information and user information of the dishes; the updating module is used for updating the current sample library based on the sample updating data; and the training module is used for training the current food material processing model according to the updated sample library, and the trained food material processing model is used as a food material processing model for outputting food material guide information.
According to a fifth aspect of the present application, there is provided a computer device comprising a processor and a memory; the memory is used for storing computer instructions, and the processor is used for operating the computer instructions stored by the memory so as to realize the food material processing recommendation method.
According to a sixth aspect of the present application, there is provided a computer-readable storage medium storing one or more programs, which are executable by one or more processors, to implement the food material processing recommendation method described above.
According to a seventh aspect of the present application, there is provided a computer device comprising a processor and a memory; the memory is used for storing computer instructions, and the processor is used for operating the computer instructions stored in the memory so as to realize the training method of the food material processing model.
According to an eighth aspect of the present application, there is provided a computer readable storage medium storing one or more programs, the one or more programs being executable by one or more processors to implement the method for training a food material processing model as described above.
The beneficial effect of this application is as follows: the food material guiding information can be obtained by obtaining preset dish information, analyzing the preset dish information to obtain food material information and user information of the dish, and inputting the food material information and the user information into a food material processing model. And the food material guiding information is used for guiding a user or vegetable cutting equipment to process food materials corresponding to the dishes in a corresponding mode. Therefore, by the method, the food material information and the user information can be combined to realize automatic and intelligent generation of the food material guide information, so that the processing mode of the food material corresponding to the dish can be autonomously determined.
Drawings
Fig. 1 is an application environment diagram of a food material processing recommendation method in a first embodiment;
fig. 2 is a flowchart illustrating a food material processing recommendation method according to a first embodiment;
FIG. 3 is a flowchart illustrating a method for training a food material processing model according to a second embodiment;
fig. 4 is a flowchart illustrating a food material processing recommendation method in a third embodiment;
FIG. 5 is a schematic structural diagram of a food material processing model in a third embodiment;
fig. 6 is a schematic structural diagram of a food material processing recommendation system in the first embodiment;
FIG. 7 is a schematic structural diagram of a training system of a food material processing model in the first embodiment;
fig. 8 is an internal structural view of a computer device in the sixth and eighth embodiments.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
A first embodiment of the present application provides a food material processing recommendation method, which can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The method comprises the steps that a terminal 102 obtains preset dish information and user information, the preset dish information and the user information are transmitted to a server 104, and the server 104 analyzes the preset dish information to obtain food material information of a dish; and inputting the food material information and the user information into a food material processing model to obtain food material guide information. And the food material guide information is used for guiding food material processing of food materials corresponding to the dishes in a corresponding mode. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.
In an embodiment, as shown in fig. 2, a food material processing recommendation method is provided, which is exemplified by the application of the method to the server 104 in fig. 1, and includes the following steps:
step S201: acquiring preset dish information and user information;
step S202: analyzing the preset dish information to obtain food material information of the dish;
step S203: and inputting the food material information and the user information into a food material processing model to obtain food material guide information.
The food material processing model includes but is not limited to a BP neural network model. And the food material guiding information is used for guiding food material processing in a corresponding mode on the food material corresponding to the dish.
Furthermore, the above food material processing includes, but is not limited to, one or more of the following: the method comprises the steps of cutting the food materials in a preset mode, storing the cut food materials, configuring the type of seasonings required during cooking and adding time of various seasonings.
According to the food material processing and recommending method, the food material information and the user information of the dish are obtained by acquiring the preset dish information and analyzing the preset dish information, and the food material guiding information can be obtained by inputting the food material information and the user information into the food material processing model. And the food material guiding information is used for guiding a user or vegetable cutting equipment to process food materials corresponding to the dishes in a corresponding mode. Therefore, by the method, the food material information and the user information can be combined to realize automatic and intelligent generation of the food material guide information, so that the processing mode of the food material corresponding to the dish can be autonomously determined.
In another embodiment, the user information includes, but is not limited to, one or more of the following: weather information of the position where the user is located, medical information of the user, taste information of the user and historical processing information of the user on food materials corresponding to the dishes.
Of course, the preset dish information includes, but is not limited to: name of dish and/or menu directory.
Of course, in this embodiment, the user information and the food material information may be both input by the user, or may be directly retrieved from the data, or of course, there may be some user input information and another part of information retrieved from the database, or another part of information obtained from the online network.
Such as: the preset dish information can be input by a user, and the user information can be directly called from a database or acquired from an online network in real time.
Therefore, one implementation of step S203 includes:
step S2031: and inputting the food material information and one or more types of user information into the food material processing model to obtain the food material guiding information.
Such as: and inputting the food material information and all the user information into a food material processing model to obtain food material guide information. Specifically, the obtained preset dish information is ' cooked pork ribs ' of cucumber ', so that the food materials corresponding to the dish can be known to be the cucumber and the pork ribs through analysis. In the exemplary case, aiming at the cucumber, the fact that the user needs to supplement the crude fiber is known according to the medical information of the user, the user likes to eat spicy food, the area where the user is located is rainy, the weather is humid, and the user likes to eat blocky cucumber before, so that after all the information is input into the food material processing model, the recommended user can be generated to not peel the cucumber, the cucumber is directly cut into pieces, and a small amount of spicy food material guiding information can be placed during cooking.
In another embodiment, after the step S203, the method further comprises the following steps:
step S2041: and sending the food material guide information to a vegetable cutting device so that the vegetable cutting device can perform corresponding food material processing on the food materials corresponding to the dish according to the food material guide information.
And (3) returning the generated optimal food material guide information (the cutting shape, the cutting thickness and the like) under the current input condition to the user app or the intelligent cutting equipment, and cutting the vegetable by the user or the cutting equipment according to the strategy.
Of course, in another embodiment, after the step S203, the method further includes the following steps:
step S2042: and sending the food material guiding information to a user terminal so that a user can determine food material processing in a corresponding mode on food materials corresponding to the dishes according to the food material guiding information.
The steps S2041 and S2041 may be executed simultaneously, or alternatively.
The method can provide the current optimal food material guiding information for the user before cooking, or can provide the current optimal food material guiding information for the vegetable-cutting equipment when the user has food material processing requirements each time by combining some intelligent vegetable-cutting equipment in the current market, such as: and guiding the vegetable cutting equipment to automatically adjust parameters such as blade distance and the like.
In another embodiment, the method further comprises: and acquiring user evaluation information, and performing optimization training on the food material processing model based on the user evaluation information. Specifically, in this embodiment, the execution time of this step is not limited, and the food material processing model can be optimally trained according to the user evaluation information only after the user evaluation information is acquired.
It should be understood that, although the steps in the flowchart of fig. 2 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in fig. 2 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
In addition, in order to make the food material processing model more suitable for the user's needs, the food material processing model needs to be updated in real time. Specifically, a second embodiment of the present application provides a method for training a food material processing model, which can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The method comprises the steps that a terminal 102 obtains user evaluation information about a preset dish and transmits the user evaluation information about the preset dish to a server 104, the server 104 preprocesses the evaluation information to obtain sample updating data, and the sample updating data comprise: food material information and user information of the dishes; and then, updating the current sample base based on the sample updating data, and training a current food material processing model according to the updated sample base, wherein the trained food material processing model is used as a food material processing model for outputting food material guide information. And the food material guide information is used for guiding food material processing of food materials corresponding to the dishes in a corresponding mode. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.
In a second embodiment of the present application, as shown in fig. 3, a method for training a food material processing model is provided, which is described by taking the method as an example applied to the server 104 in fig. 1, and includes the following steps:
step S301: acquiring user evaluation information about preset dishes;
the user feeds back the user evaluation information of the food material guiding information after processing the food material according to the food material guiding information each time. These user rating information provide up-to-date information of user preferred behavior for newly generated sample update data.
Step S302: preprocessing the evaluation information to obtain sample updating data;
wherein the sample update data comprises: food material information and user information of the dishes;
step S303: updating a current sample library based on the sample update data;
step S304: and training the current food material processing model according to the updated sample library.
Wherein the trained food material processing model is used as a food material processing model for outputting food material guide information.
Specifically, in the present embodiment, by acquiring user evaluation information about a preset dish; obtaining sample updating data by preprocessing the evaluation information, wherein the sample updating data comprises: food material information and user information of the dishes; therefore, when sample updating data is added into the current sample base, the current sample base is updated through the sample updating data, and the current food material processing model is trained according to the updated sample base. Wherein the trained food material processing model is used as a food material processing model for outputting food material guide information. Therefore, in this embodiment, the food material processing model can be updated and trained according to the user evaluation information, so that the trained food material processing model is more and more adapted to the use requirements of the user.
In another embodiment, one implementation of step S303 includes:
step S3031: and replacing the earliest acquired sample data in the current sample library by the sample updating data.
Specifically, when new sample update data is added to the current sample library, in order to update the current sample library, in this embodiment, the update mode of the current sample library is not limited, and only the update mode needs to meet the requirements of this embodiment. Therefore, one of the update methods is: and replacing the earliest acquired sample data in the current sample library by sample updating data.
In another embodiment, the sample data generated earliest in the training sample set of the current sample library is replaced with the sample update data newly added to the current sample library, so as to obtain an updated sample library, that is: a new training sample set may be obtained. In this way, the accuracy of the food material processing model training can be improved.
In addition, between the above steps S303 to S304, the method for training a food material processing model further includes:
step S3032: judging whether the number of the sample updating data is larger than a preset number threshold, if so, executing a step S3033, otherwise, executing a step S3034;
and S3033, determining to train the current food material processing model according to the updated sample library.
Step 3034, no processing is performed.
Specifically, in this embodiment, in order to select the timing for training the food material processing model, one implementation manner is to set the following conditions: when a preset amount of sample updating data is added into the current sample library, the training program is started, and the amount of the sample updating data can be determined by experiments according to actual conditions, and can be set by a user or a training system.
Such as: assuming that the current food material processing model is Net (i), when n sample update data are added into the current sample library, whether the number of the added sample update data meets a preset number threshold value needs to be judged, and under the condition that the number of the sample update data meets the preset number threshold value, the training condition of the food material processing model is met, so that the training action of the food material processing model is started, and the trained food material processing model Net (i +1) is obtained. Of course, if it is determined that the number of the sample update data does not satisfy the preset number threshold, the starting of the training of the food material processing model is stopped.
In another embodiment, between the steps S303 to S304, the method for training the food material processing model further includes:
s3035: and setting the initial weight and the threshold of the current food material processing model as the initial weight and the threshold of the trained food material processing model.
Namely: and setting the initial weight and the threshold of the trained food material processing model Net (i +1) as the weight and the threshold of the current food material processing model Net (i). In this way, for the training of the trained food material processing model Net (i +1), the weight and the value are fine-tuned on the basis that the current food material processing model is Net (i), and the training speed of the trained food material processing model Net (i +1) can be improved.
In another embodiment, after the step S304, the method for training the food material processing model further includes:
step S305: judging whether the learning precision in the training process is converged to a set minimum value; if yes, executing the following step S306, otherwise, executing step S307;
step S306: and determining that the training of the food material processing model is completed.
Step S307: judging whether the iteration times in the training process reach the set iteration times or not; if yes, executing the following step S306; otherwise, the following step S308 is executed;
step S308: and continuing to train the current food material processing model according to the updated sample library.
In order to better explain the implementation process of the method described in this embodiment, the method described in this embodiment is described below with reference to a specific application example, a third embodiment.
In the third embodiment, the food material processing model adopts the BP neural network model and the food material processing mode, which only take vegetable cutting as an example for description, because the BP neural network has the advantages of simple network structure, easy training and the like, and can perform reverse optimization according to the prediction result.
As shown in fig. 4, the model is trained by using weather information of the user position, medical information of the user, taste information of the user, historical processing information of the user on food corresponding to the dish, and a menu of the current food as data. The data training models can enable the models to not only consider the health condition of the user when generating the food material guiding information, but also meet the taste of the user, so that the system is more intelligent and humanized.
The operating system executing the food processing recommendation method and the training method of the food processing model can interact with the user through the mobile phone app, and provides the current optimal food material guidance information for the user before the user makes a dish. Or by combining some intelligent vegetable cutting equipment in the current market, when a user needs to cut vegetables each time, the system generates food material guiding information to guide the vegetable cutting equipment to automatically adjust parameters such as blade distance and the like. The working flow of the system is shown in fig. 4, after a user inputs a vegetable cutting demand (food material name, vegetable name), the system collects real-time data such as current weather conditions of the location of the user in combination with a GPS positioning network of a user mobile phone or vegetable cutting equipment, and inputs the data into a food material processing model in combination with data such as user health and historical vegetable cutting habits. The model generates optimal food material guiding information (cutting shapes, cutting thicknesses and the like) under the current input condition and then returns to the user app or the intelligent cutting equipment, and the user or the cutting equipment cuts the vegetables according to the strategy. For example: the user inputs a food material name of 'potato' and a menu name of 'potato spareribs', the system recognizes that the taste of the user is heavy, but the health condition is poor, and at the moment, the system may prompt the user to cut the potatoes into small pieces, need to soak the potatoes in cold water for ten minutes and the like. If the user inputs 'cucumber', the system finds that the 'coarse fiber' needs to be supplemented according to the health data of the user, and then the user is recommended not to peel the cucumber. The system can also learn local weather conditions according to user positioning, recommend strategies for making food taste more refreshing in summer, and the like.
Meanwhile, the user can also feed back the evaluation of the food material guide information to the system every time, and the system updates the food material processing model according to the feedback information of the user, so that the food material processing model is more and more fit with the use requirements of the user.
Moreover, as shown in fig. 5, when the food material processing model recommends food material guidance information through the output layer, user evaluation information of the user on new food material guidance information can be obtained through the input layer, so that new sample data can be obtained from the current sample database. These newly generated samples (sample update data) provide up-to-date information of user preferred behavior and should be well utilized. Therefore, the food material processing model of the user needs to be updated in real time, that is, when new sample updating data is added into the current sample library, the hidden layer needs to perform neural network training of the food material processing model again according to the new sample library, so that the existing model is improved. The condition for retraining the neural network of the food material processing model can be set as starting the training program when a certain number (n) of new samples are added, and the specific value of n can be determined by experiment according to the actual situation. Assuming that the current neural network model is Net (i), when n new samples are added into the sample library, the condition that the recommendation system retrains the neural network of the food material processing model is met, starting the neural network training action of the food material processing model, and obtaining a new neural network model Net (i + 1). In fact, the neural network model can obtain much information from the last neural network net (i). Therefore, when training the new neural network model Net (i + l), we can do the following processing: in terms of samples, in order to achieve training accuracy, a training sample set needs to be adjusted, and n samples generated earliest in the training sample set are replaced by n samples newly added into a sample library, so that a new training sample set is obtained. And setting the initial weight and threshold of the Net (i +1) as the weight and threshold of the neural network Net (i). In this way, for the training of the neural network Net (i +1), the weight and the value are finely adjusted on the basis of the previous network Net (i), and the training speed of Net (i +1) can be improved. Thus, an online BP neural network Net (i +1) training step is obtained.
And a neural network on-line training step of the food material processing model:
(1) and setting a sample database of the neural network. And (5) replacing n samples generated earliest in the sample database of Net (i) with n samples newly added into the sample database to obtain a training sample set of Net (i + 1).
(2) And setting an input layer, an output layer and a hidden layer, and initializing.
(3) And setting an initial weight value and a threshold value of the network Net (i + 1). Make Net (i +1) initial weight and threshold equal to Net (i) weight and threshold.
(4) And training the network according to the algorithm corresponding to the food material processing model.
(5) Determining whether learning accuracy converges to a minimum value: if yes, turning to (7), if not, turning to (6);
(6) determining whether the number of iteration steps exceeds a specified number of steps: turning to (7); if not, turning to (4);
(7) the algorithm terminates.
Of course, in another embodiment, the verification of the food material processing model can be accomplished by adopting a cross-validation method.
According to fig. 6, a fourth embodiment of the present application provides a food material processing recommendation system, including:
a dish information obtaining module 110, configured to obtain preset dish information;
the analyzing module 120 is configured to analyze the preset dish information to obtain food material information of the dish and user information;
the guidance information generating module 130 is configured to input the food material information and the user information to a food material processing model to obtain food material guidance information, where the food material guidance information is used to guide food material processing of food materials corresponding to the dishes in a corresponding manner.
Optionally, the user information includes one or more of the following: weather information of the position where the user is located, medical information of the user, taste information of the user and historical processing information of the user on food materials corresponding to the dishes.
Optionally, the food material information and one or more types of user information are input into the food material processing model, so as to obtain the food material guidance information.
Optionally, the system further includes: and the vegetable cutting equipment module is used for inputting the food material information and the user information into a food material processing model, and after food material guide information is obtained, sending the food material guide information to vegetable cutting equipment so that the vegetable cutting equipment can perform corresponding food material processing on the food material corresponding to the dish according to the food material guide information.
Optionally, the system further includes: and the evaluation information acquisition module is used for acquiring user evaluation information and carrying out optimization training on the food material processing model based on the user evaluation information.
Optionally, the food material processing comprises one or more of the following: the method comprises the steps of cutting the food materials in a preset mode, storing the cut food materials, configuring the type of seasonings required during cooking and adding time of various seasonings.
Optionally, the system further includes: the food material processing model comprises a BP neural network model.
According to fig. 7, a fifth embodiment of the present application provides a system for training a food material processing model, which includes:
an evaluation information obtaining module 210 for obtaining user evaluation information about a preset dish;
a preprocessing module 220, configured to preprocess the evaluation information to obtain sample update data, where the sample update data includes: food material information and user information of the dishes;
an update module 230, configured to update the current sample library based on the sample update data;
and a training module 240, configured to train the current food material processing model according to the updated sample library, where the trained food material processing model is used as a food material processing model for outputting food material guidance information.
Optionally, the update module is specifically configured to: and replacing the earliest acquired sample data in the current sample library by the sample updating data.
Optionally, the system further comprises: the judging module is used for judging whether the number of the sample updating data is larger than a preset number threshold value or not after the current sample library is updated based on the sample updating data and before the current food material processing model is trained according to the updated sample library; and determining to train the current food material processing model according to the updated sample library under the condition that the number of the sample updating data is larger than the preset number threshold.
Optionally, the system further comprises: and the weight setting module is used for setting the initial weight and the threshold of the current food material processing model as the initial weight and the threshold of the trained food material processing model after the current sample library is updated based on the sample updating data and before the current food material processing model is trained according to the updated sample library.
Optionally, the system further comprises: the learning precision module is used for judging whether the learning precision in the training process is converged to a set minimum value or not after the current food material processing model is trained according to the updated sample library; and determining that the training of the food material processing model is completed if the learning accuracy is determined to converge to the set minimum value.
Optionally, the system further comprises: the iteration module is used for judging whether the iteration times in the training process reach the set iteration times or not under the condition that the learning precision is determined not to be converged to the set minimum value; if so, determining that the training of the food material processing model is finished; otherwise, continuing to train the current food material processing model according to the updated sample library.
Optionally, the user information includes one or more of the following: weather information of the position where the user is located, medical information of the user, taste information of the user and historical food material processing information of the user on food materials corresponding to the preset dishes.
For the specific limitations of the two systems, reference may be made to the limitations of the two methods above, which are not described herein again. The respective modules in the above two apparatuses may be wholly or partially implemented by software, hardware, and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
A sixth embodiment of the present application provides a computer device comprising a processor and a memory; the internal structure diagram of the food processing recommendation method can be as shown in fig. 8, where the memory is used to store computer instructions, and the processor is used to execute the computer instructions stored in the memory, so as to implement the food processing recommendation method.
The terms and implementation principles related to the computer device in the sixth embodiment of the present application may specifically refer to the food material processing recommendation method in the first embodiment of the present application, and are not described herein again.
A seventh embodiment of the present application provides a computer-readable storage medium, where one or more programs are stored, and the one or more programs are executable by one or more processors to implement the food processing recommendation method.
The terms and implementation principles related to a computer-readable storage medium in the seventh embodiment of the present application may specifically refer to the food material processing and recommending method in the first embodiment of the present application, and are not described herein again.
An eighth embodiment of the present application provides a computer device comprising a processor and a memory; the internal structure diagram of the food processing model can be as shown in fig. 8, the memory is used for storing computer instructions, and the processor is used for executing the computer instructions stored in the memory, so as to implement the above-mentioned training method for the food processing model.
The nouns and implementation principles related to the computer device in the eighth embodiment of the present application may specifically refer to the method for training the food material processing model in the second embodiment of the present application, and are not described herein again.
A ninth embodiment of the present application provides a computer-readable storage medium, which stores one or more programs, where the one or more programs are executable by one or more processors to implement the method for training a food material processing model described above.
The terms and implementation principles related to a computer-readable storage medium in the ninth embodiment of the present application may specifically refer to the method for training a food material processing model in the first embodiment of the present application, and are not described herein again.
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 instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (15)
1. A food material processing recommendation method is characterized by comprising the following steps:
acquiring preset dish information and user information;
analyzing the preset dish information to obtain food material information of the dish;
and inputting the food material information and the user information into a food material processing model to obtain food material guide information, wherein the food material guide information is used for guiding food material processing of food materials corresponding to the dishes in a corresponding mode.
2. The method of claim 1, wherein the user information comprises one or more of: weather information of the position where the user is located, medical information of the user, taste information of the user and historical processing information of the user on food materials corresponding to the dishes.
3. The method of claim 1, wherein the food material information and the user information are both input into a food material processing model, and after obtaining the food material guiding information, the method further comprises:
and sending the food material guide information to a vegetable cutting device so that the vegetable cutting device can perform corresponding food material processing on the food materials corresponding to the dish according to the food material guide information.
4. The method of claim 1, wherein the food material processing model is trained by:
acquiring user evaluation information about preset dishes;
preprocessing the evaluation information to obtain sample updating data, wherein the sample updating data comprises: food material information and user information of the dishes;
and updating the current sample base based on the sample updating data, training a current food material processing model according to the updated sample base, and taking the trained food material processing model as a food material processing model for outputting food material guide information.
5. The method of claim 1, wherein the food material processing comprises one or more of: the method comprises the steps of cutting the food materials in a preset mode, storing the cut food materials, configuring the type of seasonings required during cooking and adding time of various seasonings.
6. The method of claim 1, wherein the food material processing model comprises a BP neural network model.
7. A method for training a food processing model, the method comprising:
acquiring user evaluation information about preset dishes;
preprocessing the evaluation information to obtain sample updating data, wherein the sample updating data comprises: food material information and user information of the dishes;
and updating the current sample base based on the sample updating data, training a current food material processing model according to the updated sample base, and taking the trained food material processing model as a food material processing model for outputting food material guide information.
8. The method of claim 7, wherein updating the current sample library based on the sample update data comprises:
and replacing the earliest acquired sample data in the current sample library by the sample updating data.
9. The method of claim 7, wherein after updating the current sample base based on the sample update data and before training the current food material processing model according to the updated sample base, the method further comprises:
judging whether the number of the sample updating data is larger than a preset number threshold value or not;
and under the condition that the number of the sample updating data is judged to be larger than the preset number threshold, determining to train the current food material processing model according to the updated sample library.
10. The method of claim 7, wherein after updating the current sample library based on the sample update data and before training the current food material processing model according to the updated sample library, the method further comprises:
and setting the initial weight and the threshold of the current food material processing model as the initial weight and the threshold of the trained food material processing model.
11. The method of claim 7, wherein after training the current food material processing model according to the updated sample library, the method further comprises:
judging whether the learning precision in the training process is converged to a set minimum value;
and determining that the training of the food material processing model is finished when the learning precision is judged to be converged to the set minimum value.
12. The method according to claim 11, wherein in a case where it is determined that the learning accuracy does not converge to the set minimum value, the method further comprises:
judging whether the iteration times in the training process reach the set iteration times or not;
if so, determining that the training of the food material processing model is finished; otherwise, continuing to train the current food material processing model according to the updated sample library.
13. The method according to any of claims 7-12, wherein the user information comprises one or more of: weather information of the position where the user is located, medical information of the user, taste information of the user and historical food material processing information of the food material corresponding to the dish of the user.
14. A computer device comprising a processor and a memory;
the memory is configured to store computer instructions, and the processor is configured to execute the computer instructions stored by the memory to implement the food material processing recommendation method of any one of claims 1 to 6 and/or the training method of the food material processing model of any one of claims 7 to 13.
15. A computer readable storage medium, characterized in that the computer readable storage medium stores one or more programs which are executable by one or more processors to implement the food material processing recommendation method of any of claims 1 to 6 and/or the training method of the food material processing model of any of claims 7 to 13.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911284771.7A CN111046289A (en) | 2019-12-13 | 2019-12-13 | Food processing recommendation method, training method of food processing model and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911284771.7A CN111046289A (en) | 2019-12-13 | 2019-12-13 | Food processing recommendation method, training method of food processing model and related device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111046289A true CN111046289A (en) | 2020-04-21 |
Family
ID=70236273
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911284771.7A Pending CN111046289A (en) | 2019-12-13 | 2019-12-13 | Food processing recommendation method, training method of food processing model and related device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111046289A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111651982A (en) * | 2020-04-30 | 2020-09-11 | 广州富港万嘉智能科技有限公司 | Method for obtaining dish temperature information, neural network training method thereof, storage medium and dish flavor reproduction method |
| CN111665715A (en) * | 2020-05-15 | 2020-09-15 | 广州富港万嘉智能科技有限公司 | Training method for artificial neural network, automatic cooking method, computer-readable storage medium, and cooking apparatus |
| CN112294143A (en) * | 2020-10-12 | 2021-02-02 | 华帝股份有限公司 | Food material processing system and control method applying same |
| CN112738109A (en) * | 2020-12-30 | 2021-04-30 | 杭州迪普科技股份有限公司 | Web attack detection method and device |
| US11270789B1 (en) * | 2020-11-30 | 2022-03-08 | Kpn Innovations, Llc. | Methods and systems for timing impact of nourishment consumpiion |
| CN118039072A (en) * | 2024-02-22 | 2024-05-14 | 天津市中西医结合医院（天津市南开医院） | Personalized nutrition scheme generation method and system for diabetics |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101006833A (en) * | 2006-01-06 | 2007-08-01 | 李卫红 | Full automatic cooking robot system |
| CN101461655A (en) * | 2009-01-09 | 2009-06-24 | 聂怀军 | Full-automatic cooking system |
| CN103646172A (en) * | 2013-12-04 | 2014-03-19 | 浙江绍兴苏泊尔生活电器有限公司 | Cooking guiding method and device based on historical cooking information |
| CN109191242A (en) * | 2018-08-17 | 2019-01-11 | 口口相传(北京)网络技术有限公司 | Food product method for pushing and device |
| CN109875381A (en) * | 2019-02-28 | 2019-06-14 | 秒针信息技术有限公司 | Cooking methods and its equipment |
-
2019
- 2019-12-13 CN CN201911284771.7A patent/CN111046289A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101006833A (en) * | 2006-01-06 | 2007-08-01 | 李卫红 | Full automatic cooking robot system |
| CN101461655A (en) * | 2009-01-09 | 2009-06-24 | 聂怀军 | Full-automatic cooking system |
| CN103646172A (en) * | 2013-12-04 | 2014-03-19 | 浙江绍兴苏泊尔生活电器有限公司 | Cooking guiding method and device based on historical cooking information |
| CN109191242A (en) * | 2018-08-17 | 2019-01-11 | 口口相传(北京)网络技术有限公司 | Food product method for pushing and device |
| CN109875381A (en) * | 2019-02-28 | 2019-06-14 | 秒针信息技术有限公司 | Cooking methods and its equipment |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111651982A (en) * | 2020-04-30 | 2020-09-11 | 广州富港万嘉智能科技有限公司 | Method for obtaining dish temperature information, neural network training method thereof, storage medium and dish flavor reproduction method |
| CN111665715A (en) * | 2020-05-15 | 2020-09-15 | 广州富港万嘉智能科技有限公司 | Training method for artificial neural network, automatic cooking method, computer-readable storage medium, and cooking apparatus |
| CN112294143A (en) * | 2020-10-12 | 2021-02-02 | 华帝股份有限公司 | Food material processing system and control method applying same |
| US11270789B1 (en) * | 2020-11-30 | 2022-03-08 | Kpn Innovations, Llc. | Methods and systems for timing impact of nourishment consumpiion |
| US20220172820A1 (en) * | 2020-11-30 | 2022-06-02 | Kpn Innovations, Llc. | Methods and systems for timing impact of nourishment consumption |
| US11894124B2 (en) * | 2020-11-30 | 2024-02-06 | Kpn Innovations, Llc. | Methods and systems for timing impact of nourishment consumption |
| CN112738109A (en) * | 2020-12-30 | 2021-04-30 | 杭州迪普科技股份有限公司 | Web attack detection method and device |
| CN118039072A (en) * | 2024-02-22 | 2024-05-14 | 天津市中西医结合医院（天津市南开医院） | Personalized nutrition scheme generation method and system for diabetics |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111046289A (en) | Food processing recommendation method, training method of food processing model and related device | |
| Eggers et al. | Balancing different forest values: Evaluation of forest management scenarios in a multi-criteria decision analysis framework | |
| US20190034556A1 (en) | Method, apparatus and refrigerator for recipe recommendation | |
| CN108108821B (en) | Model training method and device | |
| CN105335391B (en) | The treating method and apparatus of searching request based on search engine | |
| Stevenson et al. | Green Revolution research saved an estimated 18 to 27 million hectares from being brought into agricultural production | |
| CN109711887B (en) | Generation method and device of mall recommendation list, electronic equipment and computer medium | |
| CN105260171B (en) | A kind of generation method and device of virtual item | |
| JP2015505629A (en) | Information search method and server | |
| Irwin et al. | Defining economic injury levels for sea lamprey control in the Great Lakes basin | |
| WO2015028607A1 (en) | Agent system, agent control method, agent control program, and recording medium, with ability of natural conversation with users | |
| Hewitt et al. | The fishery on Antarctic krill: defining an ecosystem approach to management | |
| Kusmierczyk et al. | Temporal patterns in online food innovation | |
| CN109063105A (en) | File memory method, device, computer equipment and storage medium | |
| TW201545091A (en) | Method, apparatus and system for processing promotion information | |
| CN105938484B (en) | Robot interaction method and system based on user feedback knowledge base | |
| CN109918574A (en) | Item recommendation method, device, equipment and storage medium | |
| CN110991640A (en) | Method and device for determining seasoning usage amount and method and device for optimizing model | |
| CN109491424A (en) | A kind of intelligent control method and relevant device of drinking water | |
| CN115689649A (en) | Video advertisement putting method and device, computer equipment and storage medium | |
| Doole et al. | Economic value of grazing vegetative wheat (Triticum aestivum L.) crops in mixed-farming systems of Western Australia | |
| Yaragina et al. | Extrapolating predation mortalities back in time: an example from North-east Arctic cod cannibalism | |
| Ghysels | Mixed frequency models | |
| Carstens et al. | The growth response of ostrich (Struthio camelus var. domesticus) chicks fed on diets with three different dietary protein and amino acid concentrations | |
| CN106874455A (en) | Task scheduling recommends method, device and server |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200421 |
|
| RJ01 | Rejection of invention patent application after publication |