An intelligent design method for food factories based on big data

Abstract

The present invention relates to an intelligent design method for a food factory based on big data, comprising: obtaining a standard database; establishing a food factory database according to the standard database; using a knowledge graph to perform information association on the food factory database to establish a food factory knowledge system; obtaining keywords and inputting them into the food factory knowledge system to determine the associated indicators corresponding to the keywords; performing various data mining according to the associated indicators to generate a target database, and realizing the automatic design of food processing. Based on knowledge mining, the present invention quickly establishes the connection between information, can quickly and effectively realize the factory design in the food production and processing process according to different food information, and informatizes the food factory design process.

Description

Technical Field

[0001] The present invention relates to the technical field of food information relationships, and particularly to an intelligent design method for food factories based on big data. Background Art

[0002] In recent years, with the rapid development of Internet technology, big data technology has been successfully applied to the field of food safety. A large amount of food safety data can bring a vast amount of information to people, but the difficulty of discovering useful knowledge for regulatory authorities, enterprises, and testing institutions from the massive food safety data has also increased. Currently, the food design efficiency is low, and the processing process lacks real-time supervision. Therefore, it is necessary to reasonably utilize big data technology, establish a food factory knowledge system, conduct food factory information mining, intelligent factory design, intelligent quality and safety management of food factories, and intelligent evaluation of design quality. Provide a reference basis for enterprises to conduct factory design, and enable enterprises to clarify the food safety hazards that need to be controlled and the risks that need to be prevented, and then establish targeted control measures to prevent the occurrence of food safety incidents and the production of unsafe foods. Therefore, how to provide accurate, efficient, and practical food processing design management is an urgent problem to be solved. Summary of the Invention

[0003] In view of this, it is necessary to provide an intelligent design method for food factories based on big data to overcome the problem of the lack of efficient and intelligent food processing design management in the prior art.

[0004] To solve the above technical problems, the present invention provides an intelligent design method for food factories based on big data, including:

[0005] Obtain a standard database;

[0006] According to the standard database, establish a food factory database;

[0007] Use a knowledge graph to perform information association on the food factory database to establish a food factory knowledge system;

[0008] Obtain keywords and input them into the food factory knowledge system to determine the associated indicators corresponding to the keywords;

[0009] According to the associated indicators, perform various data mining to generate a target database and realize the automatic design of food processing.

[0010] Further, the use of a knowledge graph to perform information association on the food factory database to establish a food factory knowledge system includes:

[0011] Use a knowledge graph to integrate each standard database in the food factory database into a knowledge database through common fields;

[0012] Associate the data in the knowledge database through hypernyms, hyponyms, synonyms, and related words to establish the food factory knowledge system;

[0013] Among them, the food factory knowledge system associates at least one of the information such as process flow, formula, processing equipment and corresponding equipment parameters, requirement parameters of raw and auxiliary materials, and nutritional components in the food processing process.

[0014] Furthermore, obtaining the keyword and inputting it into the food factory knowledge system to determine the associated indicators corresponding to the keyword includes:

[0015] Obtain the keyword;

[0016] Query according to the keyword in the food factory knowledge system to determine the key data corresponding to the keyword;

[0017] Extract the data that meets the conditions from the key data to form multiple associated indicators.

[0018] Furthermore, performing multiple data mining according to the associated indicators to generate a target database and realizing the automatic design of food processing includes:

[0019] Form the target data table according to the associated indicators;

[0020] Perform data analysis on the target data table using multiple analysis models to determine the preferred indicators affecting the food factory design;

[0021] Automatically determine the automatic design result of food processing according to the preferred indicators.

[0022] Furthermore, forming the target data table according to the associated indicators includes:

[0023] According to the associated indicators, excavate the key factors in food processing design, where the key factors include at least one of finished product price, selling price, designed output, actual output, production load rate, and profit rate;

[0024] Perform data mining and data fusion on the key factors to form the target data table.

[0025] Furthermore, performing data analysis on the target data table using multiple analysis models to determine the preferred indicators affecting the food factory design includes:

[0026] Perform data analysis on the variable elements in the target data table using correlation analysis to determine the first analysis result;

[0027] Perform data analysis on the variable elements in the target data table using principal component analysis to determine the second analysis result;

[0028] Perform data analysis on the variable elements in the target data table using linear regression analysis to determine the third analysis result;

[0029] Combine the first analysis result, the second analysis result, and the third analysis result to determine the preferred indicators affecting the food factory design.

[0030] Further, automatically determining the automatic design result of food processing according to the preferred indicators includes: according to the preferred indicators, establishing a mining model for target information, determining the raw material requirements, process recipes, equipment matching, and standard parameters corresponding to product quality, and automatically determining the automatic design result of food processing according to the standard parameters.

[0031] Further, establishing a food factory database according to the standard database includes:

[0032] Obtain relevant data of at least one of food production standards, production process standards, product quality standards, process recipe data, equipment data, and engineering design, and perform data sorting and data integration on the relevant data to generate multiple standard libraries, where the data sorting includes at least one of extraction, cleaning, complementing, conversion, and summarization, and the data integration includes data fusion of the multiple industrial chain data to generate new information data;

[0033] Construct the food factory database based on the multiple standard libraries.

[0034] Further, the method further includes:

[0035] Search for keywords to be queried according to the knowledge system, and automatically evaluate the design result, including the rationality of process, production method, equipment selection and matching, factory building, and economic analysis.

[0036] Further, the method for establishing the mining model of the target information includes:

[0037] Obtain the target to be queried, relevant fields, and keywords;

[0038] According to the query results in the food factory knowledge system for the target to be queried, the relevant fields, and the keywords, determine the target database, and extract the data that meets the conditions corresponding to the indicators according to the target database, form a data table, perform analysis, optimize the indicators affecting processing, and establish a mining model for target information.

[0039] Compared with the prior art, the beneficial effects of the present invention include: First, effectively obtain the standard databases; then, establish a complete food factory database based on multiple standard databases to ensure the richness and integrity of the data; furthermore, use a knowledge graph to associate the information in the food factory database and establish a relevant food factory knowledge system; then, use the keywords input by the user to query and search in the food factory knowledge system to determine the associated indicators related to the keywords; finally, perform data mining and various data analyses on the associated indicators to generate a corresponding target database, and based on this target database, realize the automatic design of food processing. In summary, the technical method of the present invention is based on knowledge mining, quickly establishes the connection between information, can quickly and effectively realize the factory design in the food production and processing process according to different food information, and informatizes the food factory design process. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a schematic flowchart of an embodiment of the intelligent design method of a food factory based on big data provided by the present invention;

[0041] Figure 2 Provided by the present invention Figure 1 It is a schematic flowchart of an embodiment of step S103 in

[0042] Figure 3 It is a schematic structural diagram of an embodiment of the knowledge graph provided by the present invention;

[0043] Figure 4 Provided by the present invention Figure 1 It is a schematic flowchart of an embodiment of step S104 in

[0044] Figure 5 Provided by the present invention Figure 1 It is a schematic flowchart of an embodiment of step S105 in

[0045] Figure 6 Provided by the present invention Figure 5 It is a schematic flowchart of an embodiment of step S501 in

[0046] Figure 7 It is a schematic structural diagram of an embodiment of the intelligent design device of a food factory based on big data provided by the present invention;

[0047] Figure 8 It is a schematic structural diagram of an embodiment of the electronic device provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0048] The following will specifically describe the preferred embodiments of the present invention in conjunction with the drawings, where the drawings form a part of this application and are used together with the embodiments of the present invention to explain the principles of the present invention, and are not used to limit the scope of the present invention.

[0049] In the description of the present invention, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In addition, the meaning of "a plurality" is at least two, such as two, three, etc., unless otherwise specifically defined.

[0050] In the description of the present invention, referring to "embodiment" means that the specific features, structures or characteristics described in connection with the embodiment may be included in at least one embodiment of the present invention. The appearance of this phrase at various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art explicitly and implicitly understand that the described embodiments may be combined with other embodiments.

[0051] The present invention provides an intelligent design method for food factories based on big data, which utilizes knowledge graphs and data mining to intelligently manage food factories, providing new ideas for further improving the intelligence of food processing management.

[0052] Before the description of the embodiments, the relevant terms involved are defined as follows:

[0053] Knowledge graph: It is a modern theory that combines the theories and methods of disciplines such as applied mathematics, graphics, information visualization technology, and information science with methods such as bibliometric citation analysis and co-occurrence analysis, and uses visual graphs to vividly display the core structure, development history, frontier fields, and overall knowledge architecture of a discipline to achieve the purpose of multi-disciplinary integration. It displays complex knowledge fields through data mining, information processing, knowledge metrology, and graphic drawing, reveals the dynamic development laws of knowledge fields, and provides practical and valuable references for disciplinary research.

[0054] Based on the description of the above technical terms, aiming at the problems of the existing food processing design being not standard enough, not efficient enough, and not making full use of information, the present invention aims to propose an intelligent design method for food factories based on big data.

[0055] The following will separately elaborate on the specific embodiments in detail:

[0056] The embodiment of the present invention provides an intelligent design method for food factories based on big data, combined with Figure 1 seen Figure 1 is a schematic flow chart of an embodiment of the intelligent design method for food factories based on big data provided by the present invention, including steps S101 to S105, where:

[0057] In step S101, obtain a standard database;

[0058] In step S102, establish a food factory database according to the standard database;

[0059] In step S103, use a knowledge graph to associate the information in the food factory database and establish a food factory knowledge system;

[0060] In step S104, obtain keywords and input them into the food factory knowledge system to determine the associated indicators corresponding to the keywords;

[0061] In step S105, perform various data mining based on the associated indicators to generate a target database and realize the automatic design of food processing.

[0062] In the embodiment of the present invention, first, effectively obtain a standard database; then, establish a complete food factory database according to multiple standard databases to ensure the richness and integrity of the data; furthermore, use a knowledge graph to associate the information in the food factory database and establish a relevant food factory knowledge system; then, use the keywords input by the user to query and search in the food factory knowledge system to determine the associated indicators related to the keywords; finally, perform data mining and various data analyses on the associated indicators to generate a corresponding target database, and based on this target database, realize the automatic design of food processing.

[0063] As a preferred embodiment, in combination with Figure 2 viewed as Figure 2 provided by the present invention Figure 1 is a schematic flowchart of an embodiment of step S103, including steps S201 to S202, where:

[0064] In step S201, use a knowledge graph to integrate each standard database in the food factory database into a knowledge database through common fields;

[0065] In step S202, associate the data in the knowledge database through hypernyms, hyponyms, synonyms, and related words to establish the food factory knowledge system;

[0066] Among them, the food factory knowledge system associates at least one of the information such as technological processes, formulas, processing equipment and corresponding equipment parameters, requirement parameters of raw and auxiliary materials, and nutritional components in the food processing process.

[0067] In the embodiment of the present invention, through the knowledge graph, effectively mine the connections between information and efficiently construct a food factory knowledge system.

[0068] In a specific embodiment of the present invention, in combination with Figure 3 viewed as Figure 3 FIG. is a schematic structural diagram of an embodiment of the knowledge graph provided by the present invention. The intelligent association of data and databases, that is, the intelligent association of indicators (fields) and databases, refers to the method of using a knowledge graph to integrate the data of different databases through common indicators or fields into a new database, that is, using the system or software used to perform intelligent query, comprehensive analysis and storage of the target to be queried, indicators, and keywords to form a new target database. By establishing upper-level words, lower-level words, synonyms, and related words related to a ham sausage processing factory, relevant data or databases are linked, and all relevant knowledge is intelligently recognized during target query, and the required data is extracted to form a food factory knowledge system.

[0069] Among them, the knowledge points related to the design of food factories include: processing technological processes, formulas, processing equipment and their parameters, requirements for raw and auxiliary materials, nutritional components, etc. The association is realized by searching for data related to ham sausages in the process library, formula library, equipment library, and product quality standard library in the standard library. See Figure 3 .

[0070] In a specific embodiment of the present invention, taking rice as an example, the quality and safety risk assessment results of multi-source information rice products are associated and integrated with existing databases to complete the integration and merger of knowledge. In the risk assessment of rice foods, mainly the risk assessment of each node's detection indicators is carried out, including the material attributes of rice raw materials, pesticide residues, chemical fertilizer residues, microorganisms, and mycotoxins during the production process, and temperature, humidity, etc. in the circulation link. When inputting detection indicators, they should be associated with corresponding databases, such as the food attribute library, inspection and testing standard library, and circulation database, and relevant characteristic data is extracted. After fusing the data through the above logic, it is structurally processed to form a risk database.

[0071] As a preferred embodiment, in combination with Figure 4 viewed as Figure 4 is a schematic flow diagram of an embodiment of step S104 provided by the present invention, including steps S401 to S403, where: Figure 1 In step S401, the keyword is obtained;

[0072] In step S402, a query is made in the food factory knowledge system according to the keyword to determine the key data corresponding to the keyword;

[0073] In step S403, data that meets the conditions is extracted from the key data to form a plurality of the associated indicators.

[0074]

[0075] ​In the embodiment of the present invention, according to the keyword, query in the food factory knowledge system to determine the corresponding associated indicators, so as to effectively query the associated information.

[0076] As a preferred embodiment, combined with Figure 5 to see, Figure 5 provided by the present invention Figure 1 is a schematic flow chart of an embodiment of step S105 in

[0077] In step S501, according to the associated indicators, form the target data table;

[0078] In step S502, perform data analysis on the target data table using multiple analysis models to determine the preferred indicators affecting the food factory design;

[0079] In step S503, according to the preferred indicators, automatically determine the automatic design result of food processing.

[0080] In the embodiment of the present invention, using the preferred indicators obtained by data mining, automatically determine the relevant parameters required for the design of food processing to ensure the accuracy and efficiency of automatic design.

[0081] As a preferred embodiment, combined with Figure 6 to see, Figure 6 provided by the present invention Figure 5 is a schematic flow chart of an embodiment of step S501 in

[0082] In step S601, according to the associated indicators, excavate the key factors for food processing design, where the key factors include at least one of finished product price, selling price, designed output, actual output, production load rate, and profit rate;

[0083] In step S602, perform data mining and data fusion on the key factors to form the target data table.

[0084] In the embodiment of the present invention, using the associated indicators, determine the key factors corresponding to the keyword in food processing design, and perform corresponding data processing to obtain the target data table.

[0085] As a preferred embodiment, step S502 includes:

[0086] Perform data analysis on the variable elements in the target data table using correlation analysis to determine the first analysis result;

[0087] Perform data analysis on the variable elements in the target data table using principal component analysis to determine the second analysis result;

[0088] Performing data analysis on the variable elements in the target data table using linear regression analysis to determine a third analysis result;

[0089] The preferred index affecting the food factory design is determined by combining the first analysis result, the second analysis result and the third analysis result.

[0090] In the embodiment of the present invention, various data analyses are used to analyze and process the variable elements in the target data table, thereby ensuring the accuracy of the preferred indicators.

[0091] As a preferred embodiment, step S303 specifically includes: according to the preferred indicators, establishing a mining model of target information, determining the standard parameters corresponding to raw material requirements, process formula, equipment matching, and product quality, and automatically determining the automatic design results of food processing based on the standard parameters.

[0092] In an embodiment of the present invention, standard parameters in the food production process are determined based on the preferred indicators, thereby automatically planning and designing the relevant processes of food processing and production.

[0093] In a specific embodiment of the present invention, keyword searches are performed based on the knowledge system to uncover the elements and influencing factors of factory design. Based on the process standards of factory design, design results are automatically determined, including raw material requirements, process formulas, equipment matching, product quality, and benefit analysis.

[0094] As a preferred embodiment, step S102 specifically includes:

[0095] Obtaining relevant data of at least one of food production standards, production process standards, product quality standards, process formula data, equipment data, and engineering design, and organizing and integrating the relevant data to generate multiple standard libraries, wherein the data organization includes at least one of extraction, cleaning, completion, conversion, and aggregation, and the data integration includes fusing the multiple industry chain data to generate new information data;

[0096] The food factory database is constructed based on the multiple standard libraries.

[0097] In the embodiment of the present invention, a variety of standard libraries are used to construct a food factory database to ensure the integrity and richness of its information.

[0098] Among them, engineering design includes relevant data such as document basis, site selection, factory buildings, drawings, tables, economic analysis, etc.

[0099] In a specific embodiment of the present invention, the standard library includes: a process library, a recipe library, an equipment library, a production process database, a product quality standard library, a production specification standard library, a factory design library, a workshop design library, a product plan library, an auxiliary department database, a labor quota standard library, a factory water use standard library, and a design basis standard library, where:

[0100] The process library is a database established according to the different processing process flows of different foods. The main information is sourced from website searches. Classification 1 is by main processing method, Classification 2 is by food category, and Classification 3 is by the attributes of the main raw materials. The main contents of the process library include product name, pre-treatment steps, key processes, process parameters, and typical applications, etc.;

[0101] The recipe library is a data set established according to the ingredients and ratios required for producing a certain food. Its main information is sourced from website searches. The main contents of the recipe library include a database composed of the raw materials, auxiliary materials required for food processing, and the ratios required for each raw and auxiliary material;

[0102] The equipment library is an equipment database composed of the equipment information used in food processing and transportation. The information in the equipment library mainly includes equipment name, classification, model, equipment code, specifications, dimensions, production capacity, power, technical parameters, access ports, typical applications, production unit name, service life, maintenance period, vulnerable parts, replacement cycle, usage cycle, and pictures. Classification 1 is by category, for example: special equipment, general equipment, complete sets of equipment, or other equipment; Classification 2 is by type, for example: power equipment, conduction equipment, production equipment, transportation equipment, management equipment, or other equipment; Classification 3 is by the type of processing node, for example: mixing equipment, cleaning equipment, sterilization equipment, packaging equipment, etc.;

[0103] The production process database is mainly used by the factory during the actual production process to record the enterprise's production and processing process using video monitoring, intelligent sensors, etc., to update product information in real time, collect information on objects according to a certain collection method, and complete the update of the production process database to facilitate the enterprise's self-management. At the same time, after a food safety hazard occurs, it provides a basis for the enterprise's self-inspection and traceability. The production process database includes monitoring links, monitoring time, monitoring objects, monitoring indicators, monitoring results, operators, shifts, batches, and monitoring methods;

[0104] The product quality standard library is mainly the basis for factories to test the required raw materials and finished products during the processing. The main content is mainly established based on various food laws, regulations and national standards. Its main contents include product name, food classification, standard name, standard number, standard classification, test indicators, test methods, detection limits and units. Food classification is divided into 16 categories, including milk and dairy products; fats, oils and emulsified fat products; frozen foods; fruits, vegetables (including roots), beans, edible fungi, algae, nuts and seeds; cocoa products, chocolate and chocolate products (including chocolate-like and chocolate substitutes) and candies; grains and grain products; baked goods; meat and meat products; aquatic products and their products; eggs and egg products; sweeteners; condiments; special nutritional foods; beverages; others;

[0105] The production specification standard library is a database collection of production, processing, and management specifications for factories in the production process. It provides technical references for the actual production and processing of enterprises and helps to standardize the production and processing technology of enterprises. The production specification standard library includes the standard name, standard type, specification category, standard number, specification link, specification object, and specification details. Standard types include local standards, industry standards, group standards, and national standards. Specification categories include inspection specifications, legal specifications, planting specifications, processing specifications, management specifications, hygiene specifications, and technical specifications.

[0106] The Factory Design Library is a database built based on the specific considerations that different factories need to consider when designing their factories. The main content is sourced from website searches and literature. It provides a reference for the intelligent design of food factories. The Factory Design Library includes site selection, production workshop area, scale, plant layout, production workshop layout, daily output, daily consumption of raw materials, daily consumption of auxiliary materials, daily consumption of packaging materials, daily consumption of water and electricity, total cost, total profit, labor quota, and drawings.

[0107] The Workshop Design Library is a database of building structure requirements for factories when designing production workshops. Primarily derived from the "Food Factory Design" publication, the library includes requirements for building exteriors, workshop doors, ventilation and lighting, flooring, interior walls, floor coverings, staircases, and design standards for workshop offices, control rooms, quality inspection rooms, and welfare facilities.

[0108] The product solution library is a database consisting of production plans for different products, mainly derived from website searches. The product solution library includes annual output, daily shifts, output per shift, working days, and packaging specifications.

[0109] The auxiliary department database is a database composed of the basic design contents of workshops other than the production workshop. Its main contents are sourced from "Food Factory Design". The auxiliary department database includes the design principles, functions, configurations, design requirements, and facility contents of raw material reception, laboratory, central laboratory, raw material and finished product warehouses, machine repair workshop, transportation, etc.;

[0110] The labor quota standard database is a database composed of the basis for labor quota and the calculation method of labor force. Its main source is "Food Factory Design";

[0111] The factory water standard database is a database composed of the water usage items and water consumption required by the factory. Its main contents are sourced from "Food Factory Design", and its contents include the water consumption of production water, domestic water, shower water, washing water, fire water, and plant area water;

[0112] The design basis standard database consists of architectural design specifications such as "General Code for Overall Plant Design of Industrial Enterprises", "General Hygiene Code for Food Enterprises", "Code for Design of Clean Factories", and "Code for Design of Cold Storage". Its main contents come from the specific contents of the above specifications, and its main contents include the standard name, standard number, scope of application, regulated object, and details of the regulations.

[0113] As a preferred embodiment, the above method further includes:

[0114] According to the knowledge system, search for the keywords to be queried, and automatically evaluate the design results, including the rationality of process, production method, equipment selection and matching, workshop, and economic analysis.

[0115] In the embodiment of the present invention, further evaluate the design results, analyze their rationality, and ensure the accuracy and reliability of automatic design.

[0116] As a preferred embodiment, the method for establishing the above-mentioned mining model of standard information includes:

[0117] Obtain the target to be queried, relevant fields, and keywords;

[0118] According to the target to be queried, the relevant fields, and the keywords, determine the target database based on the query results in the food factory knowledge system, and extract the data that meet the conditions corresponding to the indicators according to the target database, form a data table, conduct analysis, optimize the indicators affecting processing, and establish a mining model for target information.

[0119] In the embodiment of the present invention, according to the target to be queried, relevant fields, and keywords determined by the user, determine the relevant target database, and conduct corresponding data analysis and mining to ensure the accuracy of the finally determined preferred indicators.

[0120] In a specific embodiment of the present invention, the intelligent design method of a food factory based on big data specifically includes steps such as the establishment of a food factory database, the establishment of a food factory knowledge system, the mining of food factory information, and the intelligent design of the factory. Among them:

[0121] The food factory database includes a standard database (including a design basis standard library, a general layout design technical and economic index library, a workshop design standard library, an auxiliary department design standard library, a factory water use standard library, a product quality standard library, a production regulation standard library), a process library, an equipment library, a formula library, a production process database, and an economic analysis library (including a labor quota database, a profit analysis database, an investment analysis database);

[0122] The establishment of the food factory knowledge system refers to forming a food factory knowledge system through food factory knowledge modeling and food factory knowledge reasoning based on the food factory database, performing data aggregation. By inputting target information (or keywords), this knowledge system mines corresponding factory design knowledge from the food factory database, establishes an application database (including factory design, design quality assessment,...), and outputs the design result;

[0123] The mining of food factory information refers to obtaining relevant indicators from the big data of the food factory according to the keywords input into the knowledge system, then extracting the data that meets the conditions corresponding to the indicators to form corresponding application data tables, and then using analysis models (correlation analysis, regression analysis, clustering analysis, principal component analysis, discriminant analysis, etc.) to optimize the key indicators affecting processing and establish a mining model for the target information;

[0124] The intelligent design of the food factory refers to using the food factory knowledge system to mine the elements and influencing factors of factory design, and automatically determining the design result according to the process standards of factory design, including raw material requirements, process formula, equipment matching, product quality, and benefit analysis.

[0125] Based on the above design method, the specific process is as follows:

[0126] Obtain a standard database (including food production standards, production process standards, product quality standards), a process formula database, an equipment database, and an engineering design standard library (document basis, site selection, factory building, drawings, tables, economic analysis, etc.) to establish a food factory database;

[0127] Establish a knowledge model, input the keywords to be searched into the food factory database, this knowledge system mines the corresponding factory design knowledge, establishes a food factory knowledge system, and outputs the design result;

[0128] Input keywords into the knowledge system, obtain relevant indicators from the food factory database, extract the qualified data corresponding to the data, form a corresponding data table, conduct analysis, optimize the key indicators affecting processing, and establish a mining model for target information;

[0129] Utilize the food factory knowledge system to excavate the elements and influencing factors of factory design. According to the process standards of factory design, automatically determine the design results, including raw material requirements, process formulas, equipment matching, product quality, and economic benefit analysis, to achieve intelligent design of food factories.

[0130] In a specific embodiment of the present invention, according to the keywords input into the knowledge system, associate indicators from the food factory knowledge system, then extract the qualified data corresponding to the indicators to form an application data table, and adopt analysis models (statistics (average value, sorting, maximum value...), correlation analysis, regression analysis, cluster analysis, principal component analysis, discriminant analysis, etc.) to calculate and determine the indicators affecting food processing;

[0131] First, influencing factors of food factory design (data mining):

[0132] According to the keywords input into the knowledge system, associate indicators from the food factory database, then extract the qualified data corresponding to the indicators to form an application data table, and adopt analysis models (correlation analysis, regression analysis, cluster analysis, principal component analysis, etc.) to calculate and determine the indicators affecting food factory design.

[0133] Among them, the synthesis of the target data table includes: using the database and knowledge graph to excavate the key factors of factory design, including influencing factors such as finished product price, selling price, designed output, actual output, production load rate, and profit rate. Conduct data mining on the above influencing factors and fuse the relevant data to form a target data table. As shown in the figure.

[0134] Among them, the mathematical statistics analysis of the target data table includes:

[0135] Correlation analysis: It refers to the analysis of two or more variable elements with correlation to measure the degree of correlation between two variable factors. There must be a certain connection or probability between the relevant elements for correlation analysis. Conduct Pearson correlation statistical analysis on 6 factors affecting food factory design, including the analysis results of finished product price (yuan / root), selling price (yuan / root), designed output (tons / year), actual output (tons / year), production load rate (%), and profit rate (%). When P < 0.05 between two groups of variables, it shows a positive correlation and the correlation is significant. And the larger the Pearson correlation coefficient, the stronger the correlation between the two groups of variables;

[0136] Principal component analysis: SPSS software was used to perform principal component analysis on six influencing factors involved in food factory design. In the common factor variance diagram, an extraction amount > 0.5 is statistically significant. According to the total variance interpretation diagram analysis, a cumulative contribution rate > 0.6 is statistically significant. The six influencing factors were classified into two main components. According to the rotated component matrix diagram analysis, the finished product price, profit rate, and selling price were used as the first main component, and the actual output, designed output, and production load rate were used as the second main component, with a cumulative contribution rate of 81.55%;

[0137] Linear regression analysis: It is a statistical analysis method that uses regression analysis in mathematical statistics to determine the quantitative relationship of interdependence between two or more variables and is widely used. Six influencing factors were analyzed, including: finished product price (yuan / root), selling price (yuan / root), designed output (tons / year), actual output (tons / year), production load rate (%), and profit rate (%). As Figure 1 shown, according to the coefficient diagram and R-squared analysis, the finished product price has a significant correlation, the B value < 0, showing a significant negative impact. The lower the finished product price, the higher the profit rate, and the VIF < 10, indicating no multicollinearity. Considering both the R-squared and VIF values, it can be explained that the finished product price is 83.9% correlated with the profit rate.

[0138] In a specific embodiment of the present invention, taking ham sausage processing as an example:

[0139] Pork is used as the raw material for ham sausage processing, and corresponding inspection and testing are essential. Through the product quality standard library in Example 1, the items that need to be inspected and tested for pork can be found, including veterinary drug residues, pollutants, and volatile basic nitrogen, detection methods, and the upper and lower limits of each index. According to the association between pork and the content in the knowledge base, a new data table is formed, including inspection objects, inspection items, detection standards, detection methods, upper and lower limits, and units;

[0140] According to the content of the above production specification standard library and factory design library, searching for the keyword "processing factory" will show the requirements for site selection and environment, requirements for workshops and factories, requirements for facilities and equipment, inspection and quarantine requirements, hygiene control, packaging, storage, and transportation, product traceability, personnel requirements, record requirements, etc.;

[0141] Furthermore, the intelligent design process of food engineering is as follows:

[0142] First, using the knowledge system, the elements and influencing factors of food engineering design are excavated, and according to the process standards of food engineering design, the design results are automatically determined, including raw material requirements, process formulas, equipment matching, and product quality;

[0143] Second, mining relevant information for food engineering design. By using the established food factory database and food factory knowledge system, input keywords into the knowledge system, obtain relevant indicators from the food factory database, and then extract the data that meet the conditions corresponding to the indicators, such as building area, equipment selection, process flow, product quality, etc., to form a secondary data table. Then, perform data analysis on the corresponding secondary data table, and use mathematical statistical analysis models (correlation analysis, regression analysis, clustering analysis, principal component analysis, discriminant analysis, etc.) to perform statistical analysis on the secondary data table to obtain the key indicators that preferably affect food engineering design, and establish a mining model for target information;

[0144] Third, intelligent food engineering design refers to using the food factory knowledge system to mine the elements and influencing factors involved in the food factory design process, and automatically determine the design results according to the standards involved in the food factory design, including raw material requirements, process formulas, equipment matching, and product quality.

[0145] Among them, taking the standard requirements of raw and auxiliary materials as an example, search for the requirements of raw and auxiliary materials for ham sausage in the knowledge system, and the content is as follows:

[0146] Fresh pork: It should meet the requirements of the national food safety standard GB 2707-201 for fresh (frozen) livestock and poultry products;

[0147] Water: It should meet the requirements of the hygienic standard for drinking water GB 5749-2006;

[0148] Soy protein: It should meet the requirements of GB / T 22493-2008 for soy protein powder;

[0149] Starch: It should meet the requirements of the national food safety standard GB 31637-2016 for edible starch;

[0150] White granulated sugar: It should meet the requirements of the national food safety standard GB 13104-2014 for sugar;

[0151] Edible salt: It should meet the requirements of the national food safety standard GB 2721-2015 for edible salt;

[0152] Sodium hexametaphosphate: It should meet the requirements of the national food safety standard GB 1886.4-2020 for food additive sodium hexametaphosphate;

[0153] Sodium pyrophosphate: It should meet the requirements of the national food safety standard GB 1886.339-2021 for food additive sodium pyrophosphate;

[0154] D-sodium erythorbate: It should meet the requirements of the national food safety standard GB 1886.28-2016 for food additive D-sodium erythorbate;

[0155] Sodium nitrite: It shall comply with the requirements of the National Food Safety Standard Food Additive Sodium Nitrite (GB 1886.11-2016);

[0156] Monosodium glutamate: It shall comply with the requirements of the National Food Safety Standard Monosodium Glutamate (GB 2720-2015);

[0157] The quality of food additives shall comply with the corresponding standards and relevant regulations;

[0158] The variety, usage amount and residue amount of food additives shall comply with the provisions of GB 2760;

[0159] Other excipients shall comply with the provisions of relevant national standards;

[0160] Among them, taking the sensory standard requirements as an example, by searching for the keyword "sensory requirements" in the knowledge system, the sensory requirements of ham sausage can be seen, as shown in Table 1 below:

[0161] Table 1

[0162]

[0163] Taking the physical and chemical index requirements as an example, by searching for the keyword "physical and chemical indexes" in the knowledge system, the physical and chemical indexes of ham sausage can be seen, including the requirement ranges and detection methods of moisture, protein, fat, starch and salt, as shown in Table 2 below:

[0164] Table 2

[0165]

[0166]

[0167] Taking the pollutant requirements as an example, by searching for the keyword "pollutants" in the knowledge system, the detection items and detection limits of pollutants in cooked meat products can be seen, including the limit ranges of lead, cadmium, total mercury, total arsenic, chromium, sodium nitrite and benzo[a]pyrene, as shown in Table 3 below:

[0168] Table 3

[0169] Project Index Lead (Pb) (mg / kg) ≤0.5 Cadmium (Cd) (mg / kg) ≤0.1 Total mercury (mg / kg) ≤0.05 Total arsenic (mg / kg) ≤0.5 Chromium (Cr) (mg / kg) ≤1.0 Sodium nitrite (NaNO2) (mg / kg) ≤30 Benzo[a]pyrene (μg / kg) ≤5.0

[0170] Taking the microbial requirements as an example, by searching for the keyword "microorganisms" in the knowledge system, the detection items and detection limits of microorganisms in cooked meat products can be seen, including the limit ranges of total number of colonies, coliform group, Salmonella, Listeria monocytogenes and Staphylococcus aureus, as shown in Table 4 below:

[0171] Table 4 Microbiological Indexes of Ham Sausage

[0172]

[0173]

[0174] It should be noted that the device assembly generates a target database according to the devices required for processing products; according to the data in the product quality standard library, it mines the limit values and detection methods of physical and chemical indicators, pollutants, microorganisms, etc. that need to be detected for ham sausages, and generates a target database.

[0175] An embodiment of the present invention also provides an intelligent design device for a food factory based on big data. Combining Figure 7 viewed Figure 7 FIG. 11 is a schematic structural diagram of an embodiment of the intelligent design device for a food factory based on big data provided by the present invention. The intelligent design device 700 for a food factory based on big data includes:

[0176] An acquisition unit 701, configured to acquire a standard database;

[0177] A processing unit 702, configured to establish a food factory database according to the standard database; configured to perform information association on the food factory database by using a knowledge graph to establish a food factory knowledge system; configured to acquire a keyword and input it into the food factory knowledge system to determine the associated indicators corresponding to the keyword.

[0178] A design unit 703, configured to perform various data mining according to the associated indicators to generate a target database, and realize the automatic design of food processing.

[0179] For a more specific implementation manner of each unit of the intelligent design device for a food factory based on big data, reference may be made to the description of the above-mentioned intelligent design method for a food factory based on big data, and it has similar beneficial effects, which will not be elaborated here.

[0180] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the above-mentioned intelligent design method for a food factory based on big data is implemented.

[0181] Generally speaking, computer instructions for implementing the method of the present invention can be carried by any combination of one or more computer-readable storage media. A non-transitory computer-readable storage medium can include any computer-readable medium except for a signal propagating temporarily itself.

[0182] A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (a non-exhaustive list) of the computer-readable storage medium include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0183] Computer program code for performing the operations of the present invention may be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. In particular, the Python language suitable for neural network computing and platform frameworks based on TensorFlow, PyTorch, etc. can be used. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (for example, by connecting through an Internet service provider via the Internet).

[0184] Embodiments of the present invention also provide an electronic device. In combination Figure 8 viewed Figure 8 FIG. 10 is a schematic structural diagram of an embodiment of the electronic device provided by the present invention. The electronic device 800 includes a processor 801, a memory 802, and a computer program stored on the memory 802 and executable on the processor 801. When the processor 801 executes the program, the intelligent design system of the food factory based on big data as described above is implemented.

[0185] As a preferred embodiment, the above-mentioned electronic device 800 further includes a display 803 for displaying the data processing result after the processor 801 executes the intelligent design system of the food factory based on big data.

[0186] Exemplarily, a computer program can be divided into one or more modules / units. One or more modules / units are stored in the memory 802 and executed by the processor 801 to implement the present invention. One or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program in the electronic device 800. For example, the computer program can be divided into the acquisition unit 701, the processing unit 702, and the design unit 703 in the above embodiments. The specific functions of each unit are as described above and will not be elaborated here one by one.

[0187] The electronic device 800 can be a device such as a desktop computer, a notebook, a palm computer, or a smart phone with an adjustable camera module.

[0188] Among them, the processor 801 may be an integrated circuit chip with signal processing capabilities. The above-mentioned processor 801 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0189] Among them, the memory 802 can be, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc. Among them, the memory 802 is used to store the program. After receiving the execution instruction, the processor 801 executes the program. The method defined by the process disclosed in any one of the foregoing embodiments of the present invention can be applied to the processor 801 or implemented by the processor 801.

[0190] Among them, the display 803 can be an LCD display screen or an LED display screen. For example, the display screen on a mobile phone.

[0191] It can be understood that Figure 8 The structure shown is only a schematic diagram of one structure of the electronic device 800, and the electronic device 800 may further include more or fewer components than Figure 8 those shown. Figure 8 Each component shown in can be implemented by hardware, software, or a combination thereof.

[0192] According to the computer-readable storage medium and the electronic device provided in the above embodiments of the present invention, it can be implemented with reference to the content specifically described in the intelligent design system of the food factory based on big data implemented according to the present invention, and has beneficial effects similar to those of the intelligent design system of the food factory based on big data described above, which will not be elaborated here.

[0193] The present invention discloses an intelligent design method for a food factory based on big data. First, effectively obtain the standard database; then, establish a complete food factory database according to multiple standard databases to ensure the richness and integrity of the data; furthermore, use a knowledge graph to associate the information in the food factory database and establish a related food factory knowledge system; then, use the keywords input by the user to query and search in the food factory knowledge system to determine the associated indicators related to the keywords; finally, perform data mining and various data analyses on the associated indicators to generate a corresponding target database, and based on this target database, realize the automatic design of food processing.

[0194] The technical solution of the present invention, based on knowledge mining, quickly establishes the connection between information, can quickly and effectively realize the factory design in the food production and processing process according to different food information, and informatizes the food factory design process.

[0195] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present invention should be covered by the protection scope of the present invention.

Claims

1. An intelligent design method for food factories based on big data, characterized in that, Including: Obtain a standard database; Establish a food factory database according to the standard database; Use a knowledge graph to associate information in the food factory database and establish a food factory knowledge system; Obtain keywords and input them into the food factory knowledge system to determine the associated indicators corresponding to the keywords; Perform various data mining based on the associated indicators to generate a target database and achieve automatic design of food processing; Among them, the performing various data mining based on the associated indicators to generate a target database and achieve automatic design of food processing includes: Form the target database according to the associated indicators; Perform data analysis on the target database using various analysis models to determine the preferred indicators affecting the design of the food factory; Automatically determine the automatic design result of food processing according to the preferred indicators; The forming the target database according to the associated indicators includes: Based on the associated indicators, excavate the key factors in food processing design, where the key factors include at least one of finished product price, selling price, designed output, actual output, production load rate, and profit rate; Perform data mining and data fusion on the key factors to form the target database; The performing data analysis on the target database using various analysis models to determine the preferred indicators affecting the design of the food factory includes: Perform data analysis on the variable elements in the target database using correlation analysis to determine the first analysis result; Perform data analysis on the variable elements in the target database using principal component analysis to determine the second analysis result; Perform data analysis on the variable elements in the target database using linear regression analysis to determine the third analysis result; Combine the first analysis result, the second analysis result, and the third analysis result to determine the preferred indicators affecting the design of the food factory; The automatically determining the automatic design result of food processing according to the preferred indicators includes: according to the preferred indicators, establish a mining model for target information, determine the standard parameters corresponding to raw material requirements, process formulas, equipment matching, and product quality, and automatically determine the automatic design result of food processing according to the standard parameters.

2. The intelligent design method of a food factory based on big data according to claim 1, characterized in that The using a knowledge graph to associate information in the food factory database and establish a food factory knowledge system includes: Use a knowledge graph to integrate each standard database in the food factory database into a knowledge database through common fields; Associate the data in the knowledge database through hypernyms, hyponyms, synonyms, and related words to establish the food factory knowledge system; Among them, the food factory knowledge system associates at least one of information such as process flow, formula, processing equipment and corresponding equipment parameters, requirement parameters of raw and auxiliary materials, and nutritional components in the food processing process.

3. The intelligent design method of a food factory based on big data according to claim 1, characterized in that, The obtaining keywords and inputting them into the food factory knowledge system to determine the associated indicators corresponding to the keywords includes: Obtain the keywords; Query according to the keywords in the food factory knowledge system to determine the key data corresponding to the keywords; Extract the qualified data from the key data to form multiple association indicators.

4. The intelligent design method for a food factory based on big data according to claim 1, wherein Based on the standard database, establish a food factory database, including: Obtain the relevant data of at least one of food production standards, production process standards, product quality standards, process formula data, equipment data, and engineering design. Sort and integrate the relevant data to generate multiple standard libraries. Among them, the data sorting includes at least one of extraction, cleaning, complementing, conversion, and summarization, and the data integration includes data fusion of various industrial chain data to generate new information data; Construct the food factory database based on the multiple standard libraries.

5. The intelligent design method for a food factory based on big data according to claim 1, wherein The method further includes: According to the knowledge system, search for the keywords to be queried and automatically evaluate the design results, including the rationality of process, production method, equipment selection and matching, workshop, and economic analysis.

6. The intelligent design method of a food factory based on big data according to claim 1, wherein The method for establishing the mining model of the target information includes: Obtain the target to be queried, relevant fields, and keywords; According to the query results in the food factory knowledge system for the target to be queried, relevant fields, and keywords, determine the target database. According to the target database, extract the qualified data corresponding to the indicators to form a data table, conduct analysis, optimize the indicators affecting processing, and establish a mining model of the target information.

Images