CN114372412A - Balanced tempering intelligent thawing method and system for low-temperature frozen food - Google Patents
Balanced tempering intelligent thawing method and system for low-temperature frozen food Download PDFInfo
- Publication number
- CN114372412A CN114372412A CN202210009429.1A CN202210009429A CN114372412A CN 114372412 A CN114372412 A CN 114372412A CN 202210009429 A CN202210009429 A CN 202210009429A CN 114372412 A CN114372412 A CN 114372412A
- Authority
- CN
- China
- Prior art keywords
- information
- data
- food
- temperature
- temperature gradient
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
Abstract
The application discloses a low-temperature frozen food balanced-temperature-return intelligent thawing method and system, wherein a matching data set is obtained by screening from a historical database according to screening conditions; performing data annotation based on data information in the matched data set, and determining an annotated data set; performing model training by using the matching data set and the labeling data set to obtain a temperature gradient selection model; obtaining food information to be unfrozen, and inputting the food information to be unfrozen into the temperature gradient selection model; and setting a temperature control strategy by using a temperature gradient output result, and performing gradient thawing on the food to be thawed according to the temperature control strategy. The technical problem that in the prior art, unfreezing of frozen products mainly depends on manual experience, and the unfreezing effect is not good due to inaccurate temperature and time control, so that the food quality is affected is solved. The technical effects of balancing the temperature return effect and keeping the food quality are achieved according to the characteristics of the unfrozen food and the strategy of gradient temperature control.
Description
Technical Field
The application relates to the technical field of data analysis, in particular to a low-temperature frozen food balanced-temperature-return intelligent thawing method and system.
Background
Along with the development of economy, the living standard of people is provided, the pace of life and work is accelerated, the living materials are rich, the requirements of the pace of life are added, and the frozen products are developed and created along with the pace of life, and the frozen products are widely applied to the production, transportation and storage of perishable foods such as meat, poultry, aquatic products, milk, eggs, vegetables, fruits and the like because the frozen foods are easy to store; the product is nutritious, convenient, sanitary and economical, and has large market demand. The frozen product has certain influence on the quality and the taste of the product, needs to be thawed before use, and how to guarantee the quality of the frozen product to the maximum extent needs to effectively control the freezing time and temperature, the thawing time and the temperature of the frozen product. Usually, a proper thawing mode such as water, air, a microwave oven and the like is selected according to manual experience, how to control the thawing mode and the temperature lack reliable guidance, and the problem that the food quality is influenced due to poor thawing effect exists.
The above-mentioned techniques have been found to have at least the following technical problems:
in the prior art, the unfreezing of frozen products mainly depends on manual experience, and the technical problem that the unfreezing effect is not good and the food quality is influenced due to inaccurate temperature and time control exists.
Disclosure of Invention
The application aims to provide a low-temperature frozen food balanced-temperature-return intelligent unfreezing method and system, which are used for solving the technical problems that unfreezing of frozen products mainly depends on artificial experience, and the unfreezing effect is not good and the food quality is influenced due to inaccurate temperature and time control in the prior art. The technical effects of making a strategy according to the characteristics of unfreezing food and gradient temperature control, unfreezing frozen food according to a preset temperature gradient through the temperature control device, balancing the temperature return effect and maintaining the quality of the food are achieved.
In view of the above problems, the embodiment of the present application provides a method and a system for intelligent thawing of low-temperature frozen food by balanced temperature return.
In a first aspect, the present application provides a method for intelligent thawing of low-temperature frozen food by balanced temperature return, the method comprising: collecting unfreezing data of frozen food to construct a historical database; screening from the historical database according to screening conditions to obtain a matching data set; performing data annotation based on the data information in the matched data set, and determining an annotated data set; performing model training by using the matching data set and the labeling data set to obtain a temperature gradient selection model; obtaining food information to be unfrozen, and inputting the food information to be unfrozen into the temperature gradient selection model; and obtaining a temperature gradient output result, setting a temperature control strategy by using the temperature gradient output result, and performing gradient thawing on the food to be thawed according to the temperature control strategy.
In another aspect, the present application further provides a system for intelligent thawing of low-temperature frozen food at equalized temperature return, which is used for executing the method for intelligent thawing of low-temperature frozen food at equalized temperature return, and the system includes:
the first building unit is used for collecting unfreezing data of frozen food to build a historical database;
the first obtaining unit is used for screening from the historical database according to screening conditions to obtain a matching data set;
a first determining unit, configured to perform data annotation based on data information in the matching data set, and determine an annotated data set;
the second obtaining unit is used for carrying out model training by utilizing the matching data set and the labeling data set to obtain a temperature gradient selection model;
the third obtaining unit is used for obtaining food information to be unfrozen and inputting the food information to be unfrozen into the temperature gradient selection model;
the first control unit is used for obtaining a temperature gradient output result, setting a temperature control strategy by using the temperature gradient output result, and performing gradient thawing on food to be thawed according to the temperature control strategy.
In a third aspect, the present application further provides a system for intelligent thawing of low-temperature frozen food by equalized temperature return, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to the first aspect when executing the program.
In a fourth aspect, the present application provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method according to the first aspect.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
1. constructing a historical database by collecting unfreezing data of frozen food; screening from the historical database according to screening conditions to obtain a matching data set; performing data annotation based on the data information in the matched data set, and determining an annotated data set; performing model training by using the matching data set and the labeling data set to obtain a temperature gradient selection model; obtaining food information to be unfrozen, and inputting the food information to be unfrozen into the temperature gradient selection model; and obtaining a temperature gradient output result, setting a temperature control strategy by using the temperature gradient output result, and performing gradient thawing on the food to be thawed according to the temperature control strategy. The technical effects of making a strategy according to the characteristics of unfreezing food and gradient temperature control, unfreezing frozen food according to a preset temperature gradient through the temperature control device, balancing the temperature return effect and maintaining the quality of the food are achieved.
2. Obtaining an associated data set according to the marking parameter information and associated case-matching data; acquiring a state value set according to the associated data set; calculating a conditional probability based on the state value set, and constructing a conditional probability matrix; analyzing and processing the conditional probability matrix to obtain a transfer function relation; and predicting the label missing information, the corresponding label parameter information and the associated case data by using the transfer function relationship to obtain prediction label information, and continuing to label by using the prediction label information. The method and the device achieve the technical effects of predicting missing data and finishing the labeled data, thereby providing a guarantee for effective model training.
3. Obtaining the unfreezing effect information; determining a first temperature gradient selection result through the temperature gradient selection model according to the unfreezing effect information; performing data loss analysis on the first temperature gradient selection result to obtain loss data; and continuously carrying out incremental learning on the temperature gradient selection model through the loss data, and updating the temperature gradient selection model. The incremental learning of the model by adding new requirements is achieved, effective expansion is carried out on the basis of ensuring the functions of the original model, different requirements of users are met, and convenient technical effects are provided for the users.
4. Obtaining trend information of the labeling information; judging whether the trend information of the labeling information meets the trend smoothness requirement or not; and when the trend smoothness requirement is not met, the prediction annotation information and the associated annotation information obtained by the case example data are adjusted according to the trend smoothness requirement. The training data and the prediction labeling result are further verified, and therefore the technical effect of ensuring the accuracy of the model training result is achieved.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only exemplary, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for intelligent thawing of low-temperature frozen food by balanced temperature return according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a balanced tempering intelligent thawing system for low-temperature frozen food according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.
Description of reference numerals: a first construction unit 11, a first obtaining unit 12, a first determination unit 13, a second obtaining unit 14, a third obtaining unit 15, a first control unit 16, a bus 300, a receiver 301, a processor 302, a transmitter 303, a memory 304, a bus interface 305.
Detailed Description
The embodiment of the application provides a method and a system for intelligent thawing of low-temperature frozen food by balanced temperature return, and solves the technical problems that thawing of frozen products mainly depends on artificial experience, and the thawing effect is not good due to inaccurate temperature and time control, so that the food quality is influenced in the prior art.
In the following, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings, and it is to be understood that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application. It should be further noted that, for the convenience of description, only some but not all of the elements relevant to the present application are shown in the drawings.
The technical scheme provided by the application has the following general idea:
the thawing data of frozen food is acquired based on big data, the historical database of the assembly is used, the historical database is used for training and constructing a tempering temperature gradient selection model, the tempering temperature gradient selection model is optimized according to the quality change rule of the frozen food made of different raw materials in the thawing process, thereby passing through the temperature control device, the cod section is thawed according to the preset temperature gradient, the strategy formulation according to the characteristics of the thawed food and the gradient temperature control is achieved, the thawing of the frozen food is carried out according to the preset temperature gradient through the temperature control device, the effect of balancing tempering is achieved, and the technical effect of food quality is maintained.
Having thus described the general principles of the present application, various non-limiting embodiments thereof will now be described in detail with reference to the accompanying drawings.
Example one
Referring to fig. 1, an embodiment of the present application provides a method for intelligent thawing of a low-temperature frozen food at a balanced temperature, where the method includes:
specifically, the low-temperature frozen food balanced-temperature-return intelligent thawing method provided by the application can be applied to intelligent electric appliances such as a microwave oven, an oven and a refrigerator, and certainly not limited by specific limitations, and automatic identification and control processing are performed according to control signals through temperature and time control elements of the intelligent electric appliances.
Step S100: collecting unfreezing data of frozen food to construct a historical database;
further, the collecting of the thawing data of the frozen food constructs a historical database, which comprises: determining the category of frozen food, and acquiring big data unfreezing data through big data based on the type of the frozen food; sequentially acquiring big data unfreezing data of all frozen foods, and extracting data parameter information by using the big data unfreezing data, wherein the data parameter information comprises time information, temperature information, frozen food attributes and unfrozen food quality; and constructing a mapping database according to the data parameters, and taking the mapping database as the historical database.
Specifically, unfreezing data of frozen food is collected through big data, the unfreezing data are collected in sequence according to the types of unfrozen food, including seafood, meat, instant food and the like, the unfreezing data can be further refined according to the difference of food characteristics contained in the types in various categories and are refined into each food, the unfreezing data mainly comprise food attribute information, unfreezing time, unfreezing temperature, unfrozen food quality and the like, and the relationship among data is recorded as one piece of data in one unfreezing process, each piece of data comprises the data parameters, the database is constructed by using the relevance among the data parameters in each piece of record, so that the mapping relationship is constructed for all the parameters in each piece of record, and other data can be extracted and analyzed through one data requirement. The method comprises the steps of obtaining unfreezing data from big data, collecting and obtaining local experimental data, selecting experimental objects of different types of products according to requirements of the unfreezing objects, carrying out experiments of different products without understanding the types through different temperature gradient control, and carrying out multi-data combination by changing parameters in the experiments, so that the construction of a historical database is completed.
Step S200: screening from the historical database according to screening conditions to obtain a matching data set;
specifically, the screening conditions are corresponding screening according to the set requirements of the products, if the method is applied to the thawing of seafood, the screening conditions are food category attributes of the seafood, the food category attributes of the seafood can be further refined into specific seafood names, the screening conditions are set according to the environment and the requirements of the method application, if the method is applied to a microwave oven and the object categories facing the method are more, multi-category data can be screened, and the matching data set is a data set which meets the screening requirements and is obtained from a historical database according to the set screening conditions.
Step S300: performing data annotation based on the data information in the matched data set, and determining an annotated data set;
further, the data labeling based on the data information in the matching data set to determine a labeled data set includes: determining labeling parameter information; scanning the labeled parameter information from the matched data set, and associating the labeled parameter information with case data; judging whether the labeling parameter information and the associated case-instance data meet the labeling requirements or not; and when the condition is met, marking the marking parameter information.
Further, after determining whether the labeling parameter information and the associated case-by-case data satisfy the labeling requirement, the method includes: when the marking parameter information and the associated case-of-the-same-case data do not meet the marking requirements, obtaining marking missing information; acquiring a related data set according to the marking parameter information and related case-matching data; acquiring a state value set according to the associated data set; calculating a conditional probability based on the state value set, and constructing a conditional probability matrix; analyzing and processing the conditional probability matrix to obtain a transfer function relation; and predicting the label missing information, the corresponding label parameter information and the associated case data by using the transfer function relationship to obtain prediction label information, and continuing to label by using the prediction label information.
Specifically, the matching data set is used for training a corresponding model, and data in the selected matching data set is labeled during model training, so that a supervision test in the training and learning process is realized. When marking data, determining parameters of marked data according to analysis requirements, such as marking thawing temperature in the data, marking food quality after thawing, learning according to the data and marking information, and when marking a matched data set, the parameters are incomplete in type, lack of marking information, and need to be supplemented for the parameter types which cannot be marked or lack of data. The marked parameter information is the parameter information needing to be marked, the related case-by-case data is the data in the same record as the marked parameter information, the data in one record is used as complete data to carry out model training, whether the marked parameter information and other data in the record have coherence or not is judged, if the temperature has correlation or not, if the marked parameter information and other data in the record meet the requirement of coherence, the data is confirmed to be correct, if the marked parameter information and other data do not meet the requirement of coherence, the data is indicated to be abnormal, and at the moment, the Markov chain is also used for predicting and correcting the data.
The main processing procedure of the Markov chain is as follows: selecting associated data set with correlation with characteristics of missing labeled data, thawing curve of same food, and temperature controlThe ranges are close to each other, a state space is constructed by utilizing a plurality of groups of associated data sets to represent the state of the food in a certain time, a set formed by data of all state values is taken as the state space, the probability of a certain state from the current time state to the next time, namely the conditional probability, is calculated through a formula Pij＝P(xn＝j︱Xn-1I) is obtained by calculation, wherein PijIs the transition probability of state i to state j, Xn-1Is the state at time n-1, xnAnd for the state at the time n, forming a matrix by the transition probabilities among all the states as a conditional probability matrix, obtaining the relation between the number of transition steps and the transition probability by utilizing the transition of the conditional probability in the conditional probability matrix, obtaining a transition equation as a transition function relation to complete the construction of a Markov chain, inputting the data before and after the missing labeled data into the transition function relation, predicting the data of the trend by calculating to obtain the state of the data after the transition, and supplementing and labeling the data according to the prediction result.
Step S400: performing model training by using the matching data set and the labeling data set to obtain a temperature gradient selection model;
specifically, the relation between the temperature control condition in the matching data set and the food quality after thawing is learned through machine learning, the temperature gradient change condition meeting the thawing quality condition is learned, so as to obtain what change of the thawing food quality can be caused by the gradient change of the temperature along with the time, the thawing food quality can be fixed in a range in the learning training, the corresponding temperature gradient selection processing is carried out through the attribute of the thawing food, the set thawing food quality range requirement can be reached along with the change of the temperature and the passage of the time, in order to realize the determination of the temperature gradient selection, the neural network model training is carried out by utilizing the set label parameters and the matching data set, the supervised training method is used, the matching data set and the labeled data are used as the training data and the test data to carry out the training learning of the neural network model, each group of training data comprises food information to be thawed, thawing time information, thawed food quality and labeling information for marking temperature gradient change information, a training model is obtained through training of multiple groups of training data, testing and convergence are carried out through the testing data, the trained model is used for calculating and outputting the testing data, the obtained output result is compared with the labeling information, calculation is carried out through a loss function, the deviation is reduced to the minimum, when the deviation approaches to 0, the training is finished, a temperature gradient selection model is obtained, therefore, the food information to be thawed and the thawing time requirement are input into the temperature gradient selection model, and the temperature gradient change information matched with the temperature gradient selection model is output.
The process of training and testing the temperature gradient selection model is the process of supervision and learning, labeled data are utilized, information of food to be thawed, thawing time and food quality after thawing are input into the model, the model can output temperature gradient changes, the output temperature gradient changes are checked with the temperature gradient changes of the identification, if the temperature gradient changes are not satisfied, correction is carried out until the output result is consistent with the labeled information, the model is correct, and therefore the training of the model is completed. The food thawing system comprises a system, a freezing grade state detection module, a food attribute detection module, a parameter setting module, a food thawing time detection module, a food quality setting module, a numerical requirement setting module, a food thawing time detection module and a food thawing time detection module, wherein the thawing time carries out intelligent analysis according to the freezing grade state and the food attribute of food to be thawed, the parameter setting module can carry out default setting on the quality of the thawed food according to needs, the food quality is set in a numerical requirement, only food information to be thawed needs to be input when the food is used, the system inputs the default food quality information after thawing together, and outputs corresponding temperature gradient changes.
Step S500: obtaining food information to be unfrozen, and inputting the food information to be unfrozen into the temperature gradient selection model;
further, the obtaining of the information of the food to be thawed includes: obtaining image information, wherein the image information comprises food to be unfrozen; extracting the characteristics of the image information to determine food attribute information; acquiring hardness information and temperature information of food to be thawed through a sensor, and combining the hardness information and the temperature information with the food attribute information to obtain a freezing grade; and obtaining the information of the food to be unfrozen based on the food attribute information and the freezing grade.
Specifically, food information to be unfrozen is acquired, automatic identification and acquisition are carried out through detection equipment, image acquisition is carried out on food to be unfrozen through image acquisition equipment, the type variety of the food is acquired through image acquisition, if the food to be unfrozen is a cod section, the cod section to be unfrozen is placed in a tray of a microwave oven, the type of the food is acquired through image acquisition of the food inside through the image acquisition equipment, hardness and temperature information of the cod is obtained through an integrated hardness and temperature sensor, different food attributes have different hardness and temperature effects on the freezing degree, and therefore the freezing grade of the current food is predicted through combination of the food attribute information, and the food attribute information and the freezing grade form the food information to be unfrozen. And performing corresponding thawing time matching according to the freezing grade, and inputting the obtained food attribute information and the obtained thawing time information into the temperature gradient selection model for operation processing.
Step S600: and obtaining a temperature gradient output result, setting a temperature control strategy by using the temperature gradient output result, and performing gradient thawing on the food to be thawed according to the temperature control strategy.
Specifically, the temperature gradient selection model analyzes and processes input data according to a learning training result to obtain a temperature gradient selection result matched with the input data, the temperature gradient selection result is a temperature with gradient change set according to characteristics of unfrozen food, and the temperature is balanced to ensure good quality of the unfrozen food, so that the technical problem that the unfreezing effect is not good due to inaccurate temperature and time control and the food quality is affected due to the fact that unfreezing of frozen products mainly depends on manual experience in the prior art is solved. The technical effects of formulating according to the characteristics of unfreezing food and the strategy of controlling the gradient temperature, automatically unfreezing frozen food according to the preset temperature gradient through the temperature control device, having the effect of balancing the temperature return, keeping the food quality and meeting the daily life needs of people are achieved.
Further, the method further comprises: obtaining unfreezing effect information; determining a first temperature gradient selection result through the temperature gradient selection model according to the unfreezing effect information; performing data loss analysis on the first temperature gradient selection result to obtain loss data; and continuously carrying out incremental learning on the temperature gradient selection model through the loss data, and updating the temperature gradient selection model.
Further, the method further comprises: obtaining user unfreezing effect requirement information; inputting the user thawing effect requirement information and the food information to be thawed into an updated temperature gradient selection model; and obtaining a second temperature gradient selection result output by the model, wherein the second temperature gradient selection result is temperature gradient selection information which accords with the user unfreezing effect requirement information.
Particularly, except the food quality scope requirement after defaulting, can also require to carry out different unfreezes according to the different unfreezes effect that the user proposed, some users require that degree of unfreezing is little, some users require degree of unfreezing to be big, different unfreezing effect require to have an influence to the settlement of temperature, therefore utilize the relation between unfreezing requirement and the temperature, select the model to carry out the increment study to the temperature gradient, the increment study is on the basis of keeping original model function, carry out the retraining of model through increasing the parameter variable, the function of expansion model reduces the training process simultaneously. The method comprises the steps of inputting a new defrosting effect of a user into an original temperature gradient selection model to obtain a corresponding temperature gradient change result, calculating a loss function by using the obtained temperature gradient change result to obtain a deviation between an output result and the temperature meeting the requirement, wherein the loss data is obtained by introducing the loss function into a first temperature gradient selection result to complete data loss calculation, namely the loss data of the first temperature gradient selection result to the current model is input into the temperature gradient selection model to be subjected to incremental learning, and the obtained new model updates the temperature gradient selection model, so that the updated temperature gradient selection model has the corresponding analysis output by using the input defrosting effect requirement, the reliability of the output result is ensured, and the requirements of different users are met. When the system is used, a user inputs thawing effect requirement information of the user, the system carries out analysis processing according to the thawing effect requirement information of the user and food information to be thawed to obtain a second temperature gradient selection result, and corresponding temperature setting is carried out by utilizing the second temperature gradient selection result to carry out thawing operation.
Further, the method further comprises: acquiring trend information of the labeling information based on the prediction labeling information and the associated case-matching data; judging whether the trend information of the labeling information meets the trend smoothness requirement or not; and when the trend smoothness requirement is not met, the prediction annotation information and the associated annotation information obtained by the case example data are adjusted according to the trend smoothness requirement.
Specifically, in verification of training data, the change of temperature and food quality in the thawing process is considered to have a certain rule, the change of the temperature and the food quality is required to meet the amplitude requirement of trend change, the accuracy and the reasonability of the supplemented prediction marking information are verified, the data development trend of the training data is determined, a trend curve graph can be used for distinguishing, the trend change condition is calculated according to the slope of the trend curve graph, if the trend change is overlarge, the trend change condition does not meet the trend smoothness requirement, on the contrary, the trend change condition is met, the data which do not meet the trend smoothness requirement are correspondingly adjusted according to the trend, the reliability of the data is ensured, and the accuracy of the training result of the model is ensured.
Example two
Based on the same inventive concept as the method for intelligent thawing of low-temperature frozen food with balanced temperature return in the previous embodiment, the present invention further provides an intelligent thawing system for low-temperature frozen food with balanced temperature return, please refer to fig. 2, wherein the system comprises:
the first building unit 11 is used for collecting frozen food unfreezing data to build a historical database;
a first obtaining unit 12, where the first obtaining unit 12 is configured to perform screening from the historical database according to a screening condition to obtain a matching data set;
a first determining unit 13, where the first determining unit 13 is configured to perform data annotation based on the data information in the matching data set, and determine an annotated data set;
a second obtaining unit 14, where the second obtaining unit 14 is configured to perform model training by using the matching data set and the labeled data set to obtain a temperature gradient selection model;
a third obtaining unit 15, where the third obtaining unit 15 is configured to obtain information of food to be thawed, and input the information of food to be thawed into the temperature gradient selection model;
the first control unit 16 is configured to obtain a temperature gradient output result, set a temperature control strategy by using the temperature gradient output result, and perform gradient thawing on food to be thawed according to the temperature control strategy.
Further, the system further comprises:
a fourth obtaining unit configured to determine a frozen food category and obtain big data thawing data through big data based on the frozen food type;
the first extraction unit is used for sequentially acquiring big data unfreezing data of all frozen foods and extracting data parameter information by using the big data unfreezing data, wherein the data parameter information comprises time information, temperature information, frozen food attributes and unfrozen food quality;
the first execution unit is used for constructing a mapping database according to the data parameters, and the mapping database is used as the historical database.
Further, the system further comprises:
a second determining unit, configured to determine labeling parameter information;
the second execution unit is used for scanning the marking parameter information from the matching data set and associating the marking parameter information with case data;
the first judging unit is used for judging whether the labeling parameter information and the associated case example data meet the labeling requirements or not;
and the first labeling unit is used for labeling the labeling parameter information when the condition is met.
Further, the system further comprises:
a fifth obtaining unit, configured to obtain annotation missing information when the annotation parameter information and the associated case data do not meet the annotation requirement;
a sixth obtaining unit, configured to obtain an associated data set according to the labeled parameter information and the associated case data;
a seventh obtaining unit, configured to obtain a state value set according to the associated data set;
the second construction unit is used for calculating the conditional probability based on the state value set and constructing a conditional probability matrix;
the third execution unit is used for analyzing and processing the conditional probability matrix to obtain a transfer function relation;
and the eighth obtaining unit is used for predicting the annotation missing information, the corresponding annotation parameter information and the associated case-matching data by using the transfer function relationship to obtain the prediction annotation information, and continuing to label by using the prediction annotation information.
Further, the system further comprises:
a ninth obtaining unit configured to obtain thawing effect information;
a third determining unit, configured to determine a first temperature gradient selection result according to the thawing effect information through the temperature gradient selection model;
the fourth execution unit is used for carrying out data loss analysis on the first temperature gradient selection result to obtain loss data;
and the first updating unit is used for continuously learning the increment of the temperature gradient selection model through the loss data and updating the temperature gradient selection model.
Further, the system further comprises:
a tenth obtaining unit, configured to obtain user unfreezing effect requirement information;
the first input unit is used for inputting the user unfreezing effect requirement information and the food information to be unfrozen into the updated temperature gradient selection model;
an eleventh obtaining unit, configured to obtain a second temperature gradient selection result output by the model, where the second temperature gradient selection result is temperature gradient selection information that meets the user thawing effect requirement information.
Further, the system further comprises:
a twelfth obtaining unit configured to obtain image information including food to be thawed;
a fourth determining unit, configured to perform feature extraction on the image information, and determine food attribute information;
the thirteenth obtaining unit is used for collecting hardness information and temperature information of the food to be unfrozen through a sensor, and obtaining a freezing grade by combining the hardness information and the temperature information with the food attribute information;
a fourteenth obtaining unit, configured to obtain the information on the food to be thawed based on the food attribute information and the freezing level.
Further, the system further comprises:
a fifteenth obtaining unit, configured to obtain trend information of annotation information based on the prediction annotation information and associated case data;
the second judging unit is used for judging whether the trend information of the labeling information meets the trend smoothness requirement or not;
and the first adjusting unit is used for adjusting the prediction annotation information and the associated annotation information obtained by the case example data according to the trend smoothness requirement when the trend smoothness requirement is not met.
In the present specification, each embodiment is described in a progressive manner, and the emphasis of each embodiment is to expect the difference of the other embodiments, the aforementioned method for intelligent thawing of the low-temperature frozen food in the first embodiment of fig. 1 and the specific example are also applicable to the system for intelligent thawing of the low-temperature frozen food in the present embodiment, and through the foregoing detailed description of the method for intelligent thawing of the low-temperature frozen food in the first embodiment, those skilled in the art can clearly know that the system for intelligent thawing of the low-temperature frozen food in the present embodiment is an intelligent thawing system for equilibrium temperature return of the low-temperature frozen food, so for the brevity of the description, detailed description is omitted here. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Exemplary electronic device
The electronic device of the embodiment of the present application is described below with reference to fig. 3.
Fig. 3 illustrates a schematic structural diagram of an electronic device according to an embodiment of the present application.
Based on the inventive concept of the balanced-tempering intelligent thawing method for the low-temperature frozen food in the previous embodiment, the invention also provides a balanced-tempering intelligent thawing system for the low-temperature frozen food, which is stored with a computer program, and the computer program realizes the steps of any one of the above-mentioned balanced-tempering intelligent thawing methods for the low-temperature frozen food when being executed by a processor.
Where in fig. 3 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 305 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be the same element, i.e., a transceiver, providing a means for communicating with various other apparatus over a transmission medium.
The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.
In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
the application provides a low-temperature frozen food balanced-temperature-return intelligent thawing method and system, wherein a historical database is constructed by collecting frozen food thawing data; screening from the historical database according to screening conditions to obtain a matching data set; performing data annotation based on the data information in the matched data set, and determining an annotated data set; performing model training by using the matching data set and the labeling data set to obtain a temperature gradient selection model; obtaining food information to be unfrozen, and inputting the food information to be unfrozen into the temperature gradient selection model; and obtaining a temperature gradient output result, setting a temperature control strategy by using the temperature gradient output result, and performing gradient thawing on the food to be thawed according to the temperature control strategy. Realized formulating according to the characteristic of food and the tactics of gradient temperature control unfreeze, carried out the unfreezing of freezing food according to predetermineeing temperature gradient through temperature control device, balanced effect of returning the temperature keeps the technical effect of food quality to having solved among the prior art mainly depending on the artificial experience to the unfreezing of freezing product, having temperature time control inaccurate and making the effect of unfreezing not good and influence the technical problem of food quality.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, apparatus, or computer program product. Accordingly, the present application may take the form of an entirely software embodiment, an entirely hardware embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application is in the form of a computer program product that may be embodied on one or more computer-usable storage media having computer-usable program code embodied therewith. And such computer-usable storage media include, but are not limited to: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk Memory, a Compact Disc Read-Only Memory (CD-ROM), and an optical Memory.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a system for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction system which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the same technology as the present invention, it is intended that the present invention encompass such modifications and variations as well.
Claims (10)
1. A low-temperature frozen food balanced-temperature-return intelligent thawing method is characterized by comprising the following steps:
collecting unfreezing data of frozen food to construct a historical database;
screening from the historical database according to screening conditions to obtain a matching data set;
performing data annotation based on the data information in the matched data set, and determining an annotated data set;
performing model training by using the matching data set and the labeling data set to obtain a temperature gradient selection model;
obtaining food information to be unfrozen, and inputting the food information to be unfrozen into the temperature gradient selection model;
and obtaining a temperature gradient output result, setting a temperature control strategy by using the temperature gradient output result, and performing gradient thawing on the food to be thawed according to the temperature control strategy.
2. The method of claim 1, wherein said collecting frozen food thaw data builds a historical database comprising:
determining the category of frozen food, and acquiring big data unfreezing data through big data based on the type of the frozen food;
sequentially acquiring big data unfreezing data of all frozen foods, and extracting data parameter information by using the big data unfreezing data, wherein the data parameter information comprises time information, temperature information, frozen food attributes and unfrozen food quality;
and constructing a mapping database according to the data parameters, and taking the mapping database as the historical database.
3. The method of claim 2, wherein the performing data annotation based on the data information in the matching data set to determine an annotated data set comprises:
determining labeling parameter information;
scanning the labeled parameter information from the matched data set, and associating the labeled parameter information with case data;
judging whether the labeling parameter information and the associated case-instance data meet the labeling requirements or not;
and when the condition is met, marking the marking parameter information.
4. The method of claim 3, wherein the determining whether the annotation parameter information and the associated case data satisfy the annotation requirement comprises:
when the marking parameter information and the associated case-of-the-same-case data do not meet the marking requirements, obtaining marking missing information;
acquiring a related data set according to the marking parameter information and related case-matching data;
acquiring a state value set according to the associated data set;
calculating a conditional probability based on the state value set, and constructing a conditional probability matrix;
analyzing and processing the conditional probability matrix to obtain a transfer function relation;
and predicting the label missing information, the corresponding label parameter information and the associated case data by using the transfer function relationship to obtain prediction label information, and continuing to label by using the prediction label information.
5. The method of claim 1, wherein the method further comprises:
obtaining unfreezing effect information;
determining a first temperature gradient selection result through the temperature gradient selection model according to the unfreezing effect information;
performing data loss analysis on the first temperature gradient selection result to obtain loss data;
and continuously carrying out incremental learning on the temperature gradient selection model through the loss data, and updating the temperature gradient selection model.
6. The method of claim 5, wherein the method further comprises:
obtaining user unfreezing effect requirement information;
inputting the user thawing effect requirement information and the food information to be thawed into an updated temperature gradient selection model;
and obtaining a second temperature gradient selection result output by the model, wherein the second temperature gradient selection result is temperature gradient selection information which accords with the user unfreezing effect requirement information.
7. The method of claim 1, wherein the obtaining information of the food to be thawed comprises:
obtaining image information, wherein the image information comprises food to be unfrozen;
extracting the characteristics of the image information to determine food attribute information;
acquiring hardness information and temperature information of food to be thawed through a sensor, and combining the hardness information and the temperature information with the food attribute information to obtain a freezing grade;
and obtaining the information of the food to be unfrozen based on the food attribute information and the freezing grade.
8. The method of claim 4, wherein the method further comprises:
acquiring trend information of the labeling information based on the prediction labeling information and the associated case-matching data;
judging whether the trend information of the labeling information meets the trend smoothness requirement or not;
and when the trend smoothness requirement is not met, the prediction annotation information and the associated annotation information obtained by the case example data are adjusted according to the trend smoothness requirement.
9. The utility model provides a balanced intelligent thawing system that returns temperature of low temperature frozen food which characterized in that, the system includes:
the first building unit is used for collecting unfreezing data of frozen food to build a historical database;
the first obtaining unit is used for screening from the historical database according to screening conditions to obtain a matching data set;
a first determining unit, configured to perform data annotation based on data information in the matching data set, and determine an annotated data set;
the second obtaining unit is used for carrying out model training by utilizing the matching data set and the labeling data set to obtain a temperature gradient selection model;
the third obtaining unit is used for obtaining food information to be unfrozen and inputting the food information to be unfrozen into the temperature gradient selection model;
the first control unit is used for obtaining a temperature gradient output result, setting a temperature control strategy by using the temperature gradient output result, and performing gradient thawing on food to be thawed according to the temperature control strategy.
10. An intelligent thawing system for equalized temperature return of low-temperature frozen food, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 8 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210009429.1A CN114372412B (en) | 2022-01-05 | 2022-01-05 | Balanced tempering intelligent thawing method and system for low-temperature frozen food |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210009429.1A CN114372412B (en) | 2022-01-05 | 2022-01-05 | Balanced tempering intelligent thawing method and system for low-temperature frozen food |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114372412A true CN114372412A (en) | 2022-04-19 |
| CN114372412B CN114372412B (en) | 2023-04-07 |
Family
ID=81142713
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210009429.1A Active CN114372412B (en) | 2022-01-05 | 2022-01-05 | Balanced tempering intelligent thawing method and system for low-temperature frozen food |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114372412B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115561443A (en) * | 2022-11-17 | 2023-01-03 | 云贺生物科技(南京)有限公司 | Activity detection data processing system and method |
| CN117064031A (en) * | 2023-08-30 | 2023-11-17 | 嘉兴美旺机械制造有限公司 | Food processing baking method and system based on flowing layer |
| CN117168080A (en) * | 2023-10-30 | 2023-12-05 | 南通百源制冷设备有限公司 | Energy-saving spiral instant freezer state control method |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004271060A (en) * | 2003-03-10 | 2004-09-30 | Fujitsu Ltd | Cooking ingredient storage management method |
| JP2006174730A (en) * | 2004-12-21 | 2006-07-06 | Mayekawa Mfg Co Ltd | Method and device for thawing frozen food |
| CN104824116A (en) * | 2015-06-05 | 2015-08-12 | 中国农业科学院农产品加工研究所 | Intelligent unfreezing warehouse for frozen meat |
| US20160286847A1 (en) * | 2013-11-08 | 2016-10-06 | Novasyst Inc. | Frozen food thawing |
| JP2017142035A (en) * | 2016-02-12 | 2017-08-17 | 令 大川 | Freezing and thawing device |
| US20190110638A1 (en) * | 2017-10-16 | 2019-04-18 | Midea Group Co., Ltd | Machine learning control of cooking appliances |
| CN109924391A (en) * | 2017-12-18 | 2019-06-25 | 宁波方太厨具有限公司 | The adaptive defreezing method of micro-wave oven based on food situation and system of adaptively thawing |
| CN110398130A (en) * | 2019-08-08 | 2019-11-01 | 珠海格力电器股份有限公司 | Refrigerator defrosting control method, device and refrigerator |
| CN111684223A (en) * | 2018-02-06 | 2020-09-18 | Bsh家用电器有限公司 | Domestic refrigeration device with a defrosting compartment and method for operating a domestic refrigeration device |
| US20200387122A1 (en) * | 2019-06-05 | 2020-12-10 | International Business Machines Corporation | Automated transfer of items between compartments of a smart appliance |
| CN112413992A (en) * | 2020-12-04 | 2021-02-26 | 武汉碗上好科技有限公司 | Food unfreezing control method and refrigerator using same |
| US20210186066A1 (en) * | 2019-12-20 | 2021-06-24 | Illinois Tool Works Inc. | Food thawing cabinet and related methods |
| US20210239338A1 (en) * | 2020-01-30 | 2021-08-05 | Lg Electronics Inc. | Artificial intelligence device for freezing product and method therefor |
-
2022
- 2022-01-05 CN CN202210009429.1A patent/CN114372412B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004271060A (en) * | 2003-03-10 | 2004-09-30 | Fujitsu Ltd | Cooking ingredient storage management method |
| JP2006174730A (en) * | 2004-12-21 | 2006-07-06 | Mayekawa Mfg Co Ltd | Method and device for thawing frozen food |
| US20160286847A1 (en) * | 2013-11-08 | 2016-10-06 | Novasyst Inc. | Frozen food thawing |
| CN104824116A (en) * | 2015-06-05 | 2015-08-12 | 中国农业科学院农产品加工研究所 | Intelligent unfreezing warehouse for frozen meat |
| JP2017142035A (en) * | 2016-02-12 | 2017-08-17 | 令 大川 | Freezing and thawing device |
| US20190110638A1 (en) * | 2017-10-16 | 2019-04-18 | Midea Group Co., Ltd | Machine learning control of cooking appliances |
| CN109924391A (en) * | 2017-12-18 | 2019-06-25 | 宁波方太厨具有限公司 | The adaptive defreezing method of micro-wave oven based on food situation and system of adaptively thawing |
| CN111684223A (en) * | 2018-02-06 | 2020-09-18 | Bsh家用电器有限公司 | Domestic refrigeration device with a defrosting compartment and method for operating a domestic refrigeration device |
| US20200387122A1 (en) * | 2019-06-05 | 2020-12-10 | International Business Machines Corporation | Automated transfer of items between compartments of a smart appliance |
| CN110398130A (en) * | 2019-08-08 | 2019-11-01 | 珠海格力电器股份有限公司 | Refrigerator defrosting control method, device and refrigerator |
| US20210186066A1 (en) * | 2019-12-20 | 2021-06-24 | Illinois Tool Works Inc. | Food thawing cabinet and related methods |
| US20210239338A1 (en) * | 2020-01-30 | 2021-08-05 | Lg Electronics Inc. | Artificial intelligence device for freezing product and method therefor |
| CN112413992A (en) * | 2020-12-04 | 2021-02-26 | 武汉碗上好科技有限公司 | Food unfreezing control method and refrigerator using same |
Non-Patent Citations (2)
| Title |
|---|
| 岳占凯等: "数值模拟在食品冻融过程中的应用进展", 《食品与发酵工业》 * |
| 王安敏等: "基于神经网络PID的解冻装置温湿度控制系统设计", 《计算机与数字工程》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115561443A (en) * | 2022-11-17 | 2023-01-03 | 云贺生物科技(南京)有限公司 | Activity detection data processing system and method |
| CN115561443B (en) * | 2022-11-17 | 2023-03-07 | 云贺生物科技(南京)有限公司 | Activity detection data processing system and method |
| CN117064031A (en) * | 2023-08-30 | 2023-11-17 | 嘉兴美旺机械制造有限公司 | Food processing baking method and system based on flowing layer |
| CN117064031B (en) * | 2023-08-30 | 2024-04-19 | 嘉兴美旺机械制造有限公司 | Food processing baking method and system based on flowing layer |
| CN117168080A (en) * | 2023-10-30 | 2023-12-05 | 南通百源制冷设备有限公司 | Energy-saving spiral instant freezer state control method |
| CN117168080B (en) * | 2023-10-30 | 2024-02-02 | 南通百源制冷设备有限公司 | Energy-saving spiral instant freezer state control method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114372412B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114372412B (en) | Balanced tempering intelligent thawing method and system for low-temperature frozen food | |
| CN107765347B (en) | Short-term wind speed prediction method based on Gaussian process regression and particle filtering | |
| CN108564326A (en) | Prediction technique and device, computer-readable medium, the logistics system of order | |
| CN103443809A (en) | Discriminant model learning device, method and program | |
| CN116562514B (en) | Method and system for immediately analyzing production conditions of enterprises based on neural network | |
| EP3502978A1 (en) | Meta-learning system | |
| CN115545300B (en) | Method and device for predicting user behavior based on graph neural network | |
| CN109615080B (en) | Unsupervised model evaluation method and device, server and readable storage medium | |
| CN110738362A (en) | method for constructing prediction model based on improved multivariate cosmic algorithm | |
| CN111754370B (en) | Artificial intelligence-based online education course management method and system | |
| CN117574201A (en) | Model training method, device, equipment and storage medium based on multi-industry model | |
| CN117094782A (en) | Agricultural product market price early warning management system based on big data analysis | |
| CN115659124A (en) | Stability prediction method, apparatus, device and medium based on random sample weighting | |
| CN115238964A (en) | Rice harvest prediction evaluation method and system | |
| CN115600102A (en) | Abnormal point detection method and device based on ship data, electronic device and medium | |
| CN115169458A (en) | Adaptive fault diagnosis method and device based on active learning and related medium | |
| CN114139937A (en) | Indoor thermal comfort data generation method, system, equipment and medium | |
| CN113887816A (en) | Intelligent prediction method, device and equipment for social reserve of household appliances | |
| Editya et al. | Effect of Kernel in Support Vector Regression Method to Predict Surabaya Consumer Price Index Trend | |
| CN117594195B (en) | Kidney disease patient diet analysis system and method based on big data | |
| CN113674869B (en) | Medical big data sharing method and system based on artificial intelligence | |
| CN114417138B (en) | Health information recommendation method and equipment | |
| WO2024004071A1 (en) | State estimation device, problem recommendation device, state estimation method, problem recommendation method, and program | |
| CN117057224A (en) | Method and device for predicting energy consumption of refrigerator, refrigerator and storage medium | |
| CN118036887A (en) | Intelligent management and control and early warning model device for fresh agricultural product shelf life quality |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |