CN116681357B - Food quality analysis system and method based on artificial intelligence - Google Patents
Food quality analysis system and method based on artificial intelligence Download PDFInfo
- Publication number
- CN116681357B CN116681357B CN202310941661.3A CN202310941661A CN116681357B CN 116681357 B CN116681357 B CN 116681357B CN 202310941661 A CN202310941661 A CN 202310941661A CN 116681357 B CN116681357 B CN 116681357B
- Authority
- CN
- China
- Prior art keywords
- data
- food
- module
- unit
- analysis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 235000013305 food Nutrition 0.000 title claims abstract description 330
- 238000004458 analytical method Methods 0.000 title claims abstract description 79
- 238000000034 method Methods 0.000 title claims abstract description 17
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 12
- 238000005457 optimization Methods 0.000 claims abstract description 44
- 230000006872 improvement Effects 0.000 claims abstract description 38
- 238000012545 processing Methods 0.000 claims abstract description 30
- 238000007405 data analysis Methods 0.000 claims abstract description 20
- 238000000605 extraction Methods 0.000 claims description 53
- 238000007781 pre-processing Methods 0.000 claims description 29
- 238000004519 manufacturing process Methods 0.000 claims description 12
- 238000013480 data collection Methods 0.000 claims description 7
- 239000000126 substance Substances 0.000 claims description 6
- 235000016709 nutrition Nutrition 0.000 claims description 5
- 244000005700 microbiome Species 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 4
- 239000004615 ingredient Substances 0.000 claims description 3
- 238000007477 logistic regression Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 239000000796 flavoring agent Substances 0.000 claims description 2
- 235000019634 flavors Nutrition 0.000 claims description 2
- 238000004806 packaging method and process Methods 0.000 claims description 2
- 230000001953 sensory effect Effects 0.000 claims description 2
- 230000036541 health Effects 0.000 abstract description 7
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 239000000306 component Substances 0.000 description 7
- 235000012041 food component Nutrition 0.000 description 6
- 238000001514 detection method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000009826 distribution Methods 0.000 description 4
- 239000005428 food component Substances 0.000 description 4
- 235000015097 nutrients Nutrition 0.000 description 4
- 239000000447 pesticide residue Substances 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000013500 data storage Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 229910001385 heavy metal Inorganic materials 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 102000004169 proteins and genes Human genes 0.000 description 2
- 108090000623 proteins and genes Proteins 0.000 description 2
- 239000000273 veterinary drug Substances 0.000 description 2
- 235000013343 vitamin Nutrition 0.000 description 2
- 229940088594 vitamin Drugs 0.000 description 2
- 229930003231 vitamin Natural products 0.000 description 2
- 239000011782 vitamin Substances 0.000 description 2
- 241000894006 Bacteria Species 0.000 description 1
- 241000607142 Salmonella Species 0.000 description 1
- 239000008186 active pharmaceutical agent Substances 0.000 description 1
- 239000000654 additive Substances 0.000 description 1
- 239000013566 allergen Substances 0.000 description 1
- 230000000844 anti-bacterial effect Effects 0.000 description 1
- 239000003963 antioxidant agent Substances 0.000 description 1
- 230000003078 antioxidant effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000005802 health problem Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 244000045947 parasite Species 0.000 description 1
- 239000000049 pigment Substances 0.000 description 1
- 239000004014 plasticizer Substances 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 239000003755 preservative agent Substances 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 235000021404 traditional food Nutrition 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
- 235000015099 wheat brans Nutrition 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- 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
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention relates to the technical field of food quality analysis, in particular to a food quality analysis system and method based on artificial intelligence. The system comprises a collection processing unit, a characteristic engineering unit, an analysis dividing unit and a modeling optimizing unit, wherein the modeling optimizing unit is used for receiving collected data, extracted and combined data and analyzed and divided data and carrying out improvement optimization on the collected data, the extracted and combined data and the analyzed and divided data. The invention generates a food scheme with more scientific basis, improves and optimizes the food quality and safety to meet the standards and regulations, effectively ensures the food quality safety and the health of consumers, improves the food quality, and then transmits the improved and optimized food data into the data analysis module, and the data analysis module re-analyzes the improved and optimized food data, thereby being beneficial to reducing the health risks in the potential food quality.
Description
Technical Field
The invention relates to the technical field of food quality analysis, in particular to a food quality analysis system and method based on artificial intelligence.
Background
In the real market, food quality is closely related to human life and health, so that market regulatory authorities need to spend a lot of manpower resources to check food quality safety problems.
With the development of technology, a food quality analysis system is provided, although unqualified food can be reduced to flow into the market, the problem of improving the food quality is solved, and the market is also potential for some food safety risks, and the potential harmful substances, microorganisms and other pollutants in the food can not greatly improve the food quality in the existing food quality analysis system, and a food scheme with more scientificalness and safer food quality can not be intelligently produced after intelligent analysis according to a large amount of food data.
Disclosure of Invention
The invention aims to provide a food quality analysis system and a food quality analysis method based on artificial intelligence, so as to solve the problems in the background technology.
In order to achieve the above object, one of the objects of the present invention is to provide an artificial intelligence based food quality analysis system, which comprises a collection processing unit, a feature engineering unit, an analysis dividing unit and a modeling optimizing unit;
the collecting and processing unit is used for collecting data, preprocessing the collected data, transmitting the preprocessed data into the characteristic engineering unit, and transmitting the data collected in the collecting and processing unit to the modeling and optimizing unit;
the feature engineering unit is used for receiving the data after the pretreatment operation, extracting and combining the data after the pretreatment operation, and respectively transmitting the extracted and combined data into the analysis dividing unit and the modeling optimizing unit;
the analysis dividing unit is used for receiving the extracted and combined data, analyzing and dividing the extracted and combined data, and transmitting the analyzed and divided data into the modeling optimizing unit;
the modeling optimization unit is used for receiving the collected data in the collection processing unit, receiving the extracted and combined data in the characteristic engineering unit, receiving the analyzed and divided data in the analysis and division unit, and carrying out improvement optimization on the collected data, the extracted and combined data and the analyzed and divided data;
when the modeling optimizing unit receives the collected data, the extracted and combined data and the analyzed and divided data, the modeling optimizing unit improves and optimizes the collected data, the extracted and combined data and the analyzed and divided data, the improved and optimized data is transmitted to the analyzing and dividing unit, and the analyzing and dividing unit analyzes the improved and optimized data again.
As a further improvement of the technical scheme, the collecting and processing unit comprises a data collecting module and a preprocessing module, wherein the data collecting module is used for collecting food data, the collected food data are respectively transmitted into the preprocessing module and the modeling optimizing unit, the preprocessing module is used for receiving the collected food data, preprocessing operation is carried out on the collected food data, and the data after preprocessing operation are transmitted into the characteristic engineering unit.
As a further improvement of the technical scheme, the feature engineering unit comprises a feature extraction module and a feature combination module, wherein the feature extraction module is used for receiving food data after pretreatment operation in the pretreatment module, carrying out feature extraction on the food data after pretreatment operation, respectively transmitting the food data after feature extraction into the feature combination module and the analysis and division unit, and the feature combination module is used for receiving the food data after feature extraction, carrying out feature combination on the food data after feature extraction and transmitting the food data after feature combination into the modeling and optimizing unit.
As a further improvement of the technical scheme, the analysis dividing unit comprises a data analysis module, wherein the data analysis module is used for receiving the food data after feature extraction in the feature extraction module, analyzing the food data after feature extraction, and transmitting the food data after analysis into the modeling optimizing unit.
As a further improvement of the technical scheme, the analysis and division unit further comprises a food classification module, the modeling and optimization unit comprises a modeling display module and an improvement and optimization module, the improvement and optimization module is used for receiving the food data collected in the data collection module, receiving the food data after feature combination in the feature combination module, receiving the food data analyzed in the data analysis module, improving and optimizing the collected food data, the food data after feature combination and the food data after analysis, transmitting the food data after improvement and optimization into the data analysis module, the food classification module is used for receiving the food data after improvement and optimization in the data analysis module, classifying the food data after improvement and optimization, the modeling display module is used for receiving the food data after improvement and optimization classified in the food classification module, establishing template data for the food data after improvement and optimization after classification, displaying the template data, and simultaneously receiving the food data after analysis in the data analysis module.
As a further improvement of the technical scheme, the improvement optimizing module is connected with the collected food data, the food data with combined characteristics and the analyzed food data, improves and optimizes the collected food data, the food data with combined characteristics and the analyzed food data, transmits the improved and optimized food data into the data analyzing module, and the data analyzing module re-analyzes the improved and optimized food data.
It is a second object of the present invention to provide a method for operating an artificial intelligence based food quality analysis system comprising any of the above, comprising the method steps of:
s1, collecting food data by a collecting and processing unit, preprocessing the collected food data, and transmitting the food data after preprocessing into a characteristic engineering unit.
S2, the feature engineering unit receives the food data after the pretreatment operation, performs feature extraction on the food data after the pretreatment operation, performs feature combination on the food data after the feature extraction, and simultaneously transmits the food data after the feature extraction into the analysis dividing unit, and transmits the food data after the feature combination into the modeling optimizing unit.
S3, the analysis dividing unit receives the food data after feature extraction, analyzes the food data after feature extraction, transmits the analyzed food data into the modeling optimizing unit, improves and optimizes the analyzed food data, transmits the improved and optimized food data into the analysis dividing unit, re-analyzes the improved and optimized food data, classifies the re-analyzed food data, transmits the classified food data into the modeling optimizing unit, and models and displays the classified food data.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the artificial intelligence-based food quality analysis system and method, the improved optimization module is used for receiving the collected food data, the food data with combined characteristics and the analyzed food data, carrying out improved optimization according to the collected food data, the food data with combined characteristics and the analyzed food data, generating a food scheme with more scientific basis, improving and optimizing the food quality and safety to meet standards and regulations, effectively guaranteeing the food quality safety and the health of consumers, improving the food quality, transmitting the improved and optimized food data into the data analysis module, and carrying out re-analysis on the improved and optimized food data by the data analysis module, so that the health risk in the potential food quality is reduced.
Drawings
FIG. 1 is an overall block diagram of the present invention;
FIG. 2 is a block diagram of a collection processing unit of the present invention;
FIG. 3 is a block diagram of a feature engineering unit of the present invention;
FIG. 4 is a block diagram of an analysis partitioning unit of the present invention;
FIG. 5 is a block diagram of a modeling optimization unit of the present invention.
The meaning of each reference sign in the figure is:
1. a collection processing unit; 11. a data collection module; 12. a preprocessing module;
2. a feature engineering unit; 21. a feature extraction module; 22. a feature combination module;
3. an analysis dividing unit; 31. a data analysis module; 32. a food classification module;
4. a modeling optimization unit; 41. modeling and displaying the module; 42. the optimization module is improved.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
1-5, it is an object of the present embodiment to provide an artificial intelligence-based food quality analysis system, which includes a collection processing unit 1, a feature engineering unit 2, an analysis dividing unit 3, and a modeling optimization unit 4;
considering that food quality is closely related to life and health of people, market supervision departments need to spend a large amount of manpower resources to check food quality safety problems, but market can also have potential food safety risks, so we provide an artificial intelligence based food quality analysis system, a collection processing unit 1 of the system is used for collecting data and preprocessing the collected data, the preprocessed data is transmitted into a characteristic engineering unit 2, meanwhile, the collected data in the collection processing unit 1 is transmitted into a modeling optimization unit 4, the characteristic engineering unit 2 is used for receiving the preprocessed data and extracting and combining the preprocessed data, the extracted and combined data is respectively transmitted into an analysis division unit 3 and a modeling optimization unit 4, the analysis division unit 3 is used for receiving the extracted and combined data and analyzing and dividing the extracted and combined data, the analyzed and divided data is transmitted into the modeling optimization unit 4, the modeling optimization unit 4 is used for receiving the collected data in the collection processing unit 1, and receiving the extracted and combined data in the characteristic engineering unit 2, the extracted and divided data and the received data after the analysis division unit 3 and the collected and analyzed and combined data after the analysis division are respectively transmitted into the modeling optimization unit 4;
when the modeling optimizing unit 4 receives the collected data, the extracted and combined data and the analyzed and divided data, the collected data, the extracted and combined data and the analyzed and divided data are improved and optimized, the improved and optimized data are transmitted to the analyzing and dividing unit 3, and the analyzing and dividing unit 3 analyzes the improved and optimized data again.
The above units are detailed below, please refer to fig. 2-5;
the collection processing unit 1 comprises a data collection module 11 and a preprocessing module 12;
the data collection module 11 is configured to collect a large amount of related food data by using various different channels, including data provider, public data set, website crawler, API interface, etc., and obtain a large amount of food data, or may establish a cooperative relationship with a food producer, a detection mechanism, a related research mechanism, etc., to obtain a large amount of food data, where the large amount of food data includes food components, food production information, and food detection indexes, the food components include nutritional components (such as proteins and vitamins), additives (such as preservatives and pigments), residues (such as pesticide residues and veterinary drug residues), and allergens (such as wheat bran and nuts), the food production information includes production place (country/region of origin of food), production process (such as processing method, raw material source, preservation mode, packaging specification of food), production date and shelf life (such as production date and effective period of food), manufacturer/supplier information (such as name, address, contact mode of food manufacturer/supplier), food detection index including microorganism index (such as coliform group, salmonella), residue index (such as pesticide residue, veterinary drug residue), food contact material index (such as plasticizer, heavy metal), nutrient component and tag index (to detect whether food component is consistent with tag statement), functional component index (such as antioxidant, antibacterial component), and food consumer opinion, preference, satisfaction, sales quantity, return rate, food product, the distribution timeliness facilitates the improvement optimization module 42 to improve and optimize the food regimen based on these consumer feedback, and the collected food data is passed to the pre-processing module 12 and the modeling optimization unit 4, respectively.
The preprocessing module 12 is configured to receive the collected food data and perform preprocessing operations on the collected food data, where the preprocessing operations include data deduplication (removing duplicate records in the collected data by using a deduplication function in the SQL language to ensure uniqueness of the data), missing value processing (checking whether there is a missing value in the collected data, where the missing value may be processed by a suitable method selected according to actual conditions, such as deleting the missing value, interpolating and filling or replacing with a specific value), outlier processing (the outlier may be caused by data acquisition or recording errors, identifying and processing outliers by visual inspection or using a statistical method (such as 3σ principle), data normalization (ensuring format consistency of the data, unifying standard units (converting all weight data into grams, all energy data converted to kcal) and naming specifications (different spellings of the same food are unified into a unified standard name)), calculating the nutritional composition of the food, data integration (integrating the data of multiple data sources into one unified data set), 3 sigma principle refers to one rule in statistics, also called "68-95-99.7" rule, which is based on the nature of normal distribution, indicating that in one data set conforming to normal distribution, about 68% of the data falls within the range of average value (μ) plus or minus one standard deviation (σ), about 95% of the data falls within the range of average value plus or minus two standard deviations, about 99.7% of the data falls within the range of average value plus or minus three standard deviations, the food data in the system after preprocessing operation, the method reduces a large amount of errors in food data, ensures high quality and reliability of the food data, and facilitates the improvement and optimization of the later improvement and optimization module 42 according to the high quality food data after the pretreatment operations, thereby providing a food scheme with more scientific basis, effectively guaranteeing food quality safety and health of consumers, and transmitting the data after the pretreatment operations into the characteristic engineering unit 2.
The feature engineering unit 2 comprises a feature extraction module 21 and a feature combination module 22;
the feature extraction module 21 is configured to receive the food data after the preprocessing operation in the preprocessing module 12, perform feature extraction on the food data after the preprocessing operation, select suitable features for extraction, such as statistical feature extraction, frequency domain feature extraction (based on understanding of knowledge and research background of the food field, select features that may be related to a prediction target, understand the influence of specific food attributes, processing methods, components, etc. on a target variable may instruct feature selection), image feature extraction (different image features are combined, such as color features, texture features and shape features may be combined together to obtain more accurate food classification and recognition results), text feature extraction (different text features are combined, such as food names, food lists, nutritional components and recipe descriptions may be combined together to obtain more comprehensive food description), extract relevant features, such as food components, food production information, food detection indexes, etc. according to the knowledge and research background, the extracted food data are convenient for subsequent analysis, the extracted food data after feature extraction are respectively transferred into the feature combining module 22 and the analysis unit 3, the feature combining module is used for receiving the feature extraction data, and performing new feature data after feature extraction is combined to generate the new feature data according to the improved data, and the feature is optimized according to the improved, and the feature is better in the quality of the data is generated after the feature combining module is combined with the new feature data after the feature extraction module is combined to generate the new feature data, and the feature is better according to the improved quality data is optimized, and is better in the quality based on the quality feature 4.
The analysis dividing unit 3 includes a data analysis module 31 for receiving the food data after feature extraction in the feature extraction module 21 and analyzing the food data after feature extraction, including food safety analysis (detection of potentially harmful substances (such as heavy metals, pesticide residues) or microorganisms (such as bacteria, parasites) in the food), nutrient component analysis (determination of various nutrient components in the food, such as proteins, vitamins), biochemical index analysis (analysis of biochemical index in the food, such as pH value, moisture content), functional quality analysis (evaluation of appearance, taste, flavor of the food by human sensory reaction), tag and declaration analysis (verification of whether tag and nutritional declaration on the food package are accurate, legal and in compliance with related regulations and regulations), food processing process monitoring (analysis of the production process of the food, and monitoring the control of relevant parameters (such as temperature, humidity, time), detecting food fraud (by detecting components, indexes and special marks in food, preventing and identifying food fraud such as adulteration, falsification, false propaganda), analyzing whether food data contains adulteration, falsification, false propaganda, unlawful, potential harmful substances and indexes, if so, marking the food data as unqualified, notifying that the food is unqualified by using a modeling display module 41, and performing off-shelf retrospective processing on all the food in the market, the manufacturer producing the food is penalized, so that the rights and interests of consumers and the food quality safety are guaranteed, the food is provided for the consumers as a safe, qualified and nutrient-rich product, and the analyzed food data are transmitted to the modeling optimization unit 4;
logistic regression mathematical algorithm formula:
in this formula, p represents the criterion for analyzing the food, z represents the result of inputting the feature combination, e represents the base of the natural logarithm, which is about 2.71828, and the formula can predict whether the food meets a certain criterion, can reduce the potential danger in the food, and can improve the quality of the food and the health problem of consumers.
The analysis dividing unit 3 further includes a food classification module 32, and the modeling optimizing unit 4 includes a modeling display module 41 and an improvement optimizing module 42;
the improvement optimizing module 42 is configured to receive the food data collected in the data collecting module 11, receive the food data after feature combination in the feature combining module 22, receive the food data after analysis in the data analyzing module 31, and perform improvement optimization on the collected food data, the food data after feature combination, and the analyzed food data, according to the opinion, preference, satisfaction, sales number, return rate, and distribution timeliness of the collected food consumer, perform improvement optimization on the food data after feature combination and the analyzed food data, and perform improvement optimization on a production method of the food, such as adjusting temperature and changing ingredients, when improving and optimizing the food, can appropriately preserve and respect the characteristics of local culture and traditional food, continuously improve and innovate the production food method, thereby generating a food scheme with scientific basis, so that not only can improve the quality and safety of the food, but also increase the trust and satisfaction of consumers, the improved food data after improvement optimization is input into the data analyzing module 31, the food classifying module 32 is configured to receive the improved food data after analysis in the data analyzing module 31, and the improved food data after the improvement optimizing the food data is analyzed by the food classifying module, and the improved food classifying module is configured to display the improved food data after the improved food data is configured to perform classification and the food classifying module is configured to display the improved food data after the improved food data is configured to display the improved and the food classifying and the improved food data. The displayed template data is stored by using a non-relational database, so that the management and the query of food data are facilitated, the non-relational database is a database system which is compared with the traditional relational database, and the non-relational database adopts a more flexible data storage mode and is suitable for processing semi-structured and unstructured data, unlike the relational database which uses a structured form and SQL query language for data storage and query.
The improvement optimizing module 42 receives the collected food data, the food data with combined characteristics and the analyzed food data, improves and optimizes the collected food data, the food data with combined characteristics and the analyzed food data to obtain a new food production scheme, and transmits the improved and optimized food data to the data analyzing module 31, wherein the data analyzing module 31 analyzes the improved and optimized food data again, so that potential hazards in the new food scheme can be found in time, the control of the food quality is increased, more accurate food data is obtained, and therefore a more accurate food scheme is obtained, and the high quality of the food is greatly improved.
The use flow is as follows:
the data collection module 11 collects food data, the collected food data is transmitted to the preprocessing module 12 and the improvement optimizing module 42, the preprocessing module 12 receives the collected food data and performs preprocessing operation, the feature extraction module 21 receives the food data after preprocessing operation, performs feature extraction and feature combination on the food data after preprocessing operation, transmits the food data after feature extraction to the data analysis module 31, transmits the food data after feature combination to the improvement optimizing module 42, and the data analysis module 31 receives the food data after feature extraction, analyzes the food data after feature extraction, and transmits the food data after analysis to the improvement optimizing module 42.
The improvement optimizing module 42 receives the collected food data, receives the feature-combined food data, receives the analyzed food data, and performs improvement optimization on the collected food data, the feature-combined food data, and the analyzed food data, the improvement-optimized food data is transmitted to the data analyzing module 31, the data analyzing module 31 re-analyzes the improvement-optimized food data, the re-analyzed improvement-optimized food data is transmitted to the food classifying module 32, the food classifying module 32 receives the re-analyzed improvement-optimized food data and performs food classification, the classified improvement-optimized food data is transmitted to the modeling display module 41, the modeling display module 41 receives the classified improvement-optimized food data, and establishes template data for the classified improvement-optimized food data, displays the template data, and simultaneously receives the food data analyzed in the data analyzing module 31.
It is a second object of the present invention to provide a method for operating an artificial intelligence based food quality analysis system comprising any of the above, comprising the method steps of:
s1, the collection processing unit 1 collects food data, performs pretreatment operation on the collected food data, and transmits the food data after the pretreatment operation to the characteristic engineering unit 2.
S2, the characteristic engineering unit 2 receives the food data after the pretreatment operation, performs characteristic extraction on the food data after the pretreatment operation, performs characteristic combination on the food data after the characteristic extraction, and simultaneously transmits the food data after the characteristic extraction into the analysis dividing unit 3, and transmits the food data after the characteristic combination into the modeling optimizing unit 4.
S3, the analysis dividing unit 3 receives the food data after feature extraction, analyzes the food data after feature extraction, transmits the analyzed food data into the modeling optimizing unit 4, improves and optimizes the analyzed food data, transmits the improved and optimized food data into the analysis dividing unit 3, re-analyzes the improved and optimized food data, classifies the re-analyzed food data, transmits the classified food data into the modeling optimizing unit 4, and models and displays the classified food data.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the above-described embodiments, and that the above-described embodiments and descriptions are only preferred embodiments of the present invention, and are not intended to limit the invention, and that various changes and modifications may be made therein without departing from the spirit and scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (1)
1. Food quality analysis system based on artificial intelligence, its characterized in that: the system comprises a collection processing unit (1), a characteristic engineering unit (2), an analysis dividing unit (3) and a modeling optimizing unit (4);
the collecting and processing unit (1) is used for collecting data, preprocessing the collected data, transmitting the preprocessed data into the characteristic engineering unit (2), and transmitting the data collected in the collecting and processing unit (1) to the modeling and optimizing unit (4);
the characteristic engineering unit (2) is used for receiving the data after the pretreatment operation, extracting and combining the data after the pretreatment operation, and respectively transmitting the extracted and combined data into the analysis dividing unit (3) and the modeling optimizing unit (4);
the analysis dividing unit (3) is used for receiving the extracted and combined data, analyzing and dividing the extracted and combined data, and transmitting the analyzed and divided data into the modeling optimizing unit (4);
the modeling optimization unit (4) is used for receiving the collected data in the collection processing unit (1), receiving the extracted and combined data in the characteristic engineering unit (2), receiving the analyzed and divided data in the analysis and division unit (3), and carrying out improvement optimization on the collected data, the extracted and combined data and the analyzed and divided data;
when the modeling optimization unit (4) receives the collected data, the extracted and combined data and the analyzed and divided data, the collected data, the extracted and combined data and the analyzed and divided data are improved and optimized, the improved and optimized data are transmitted to the analysis and division unit (3), and the analysis and division unit (3) analyzes the improved and optimized data again;
the collection processing unit (1) comprises a data collection module (11) and a preprocessing module (12);
the data collection module (11) is used for collecting food data, and the collected food data are respectively transmitted into the preprocessing module (12) and the modeling optimization unit (4);
the preprocessing module (12) is used for receiving the collected food data, preprocessing the collected food data and transmitting the preprocessed data into the characteristic engineering unit (2);
the feature engineering unit (2) comprises a feature extraction module (21) and a feature combination module (22);
the feature extraction module (21) is used for receiving the food data after the pretreatment operation in the pretreatment module (12), extracting features of the food data after the pretreatment operation, and respectively transmitting the food data after the feature extraction into the feature combination module (22) and the analysis and division unit (3);
the feature combination module (22) is used for receiving the food data after feature extraction, carrying out feature combination on the food data after feature extraction, and transmitting the food data after feature combination into the modeling optimization unit (4);
the analysis dividing unit (3) comprises a data analysis module (31), the data analysis module (31) is used for receiving food data after feature extraction in the feature extraction module (21), analyzing the food data after feature extraction, and transmitting the food data after analysis into the modeling optimizing unit (4), wherein the analysis comprises:
food safety analysis, detecting potentially harmful substances or microorganisms in food;
analyzing the nutritional ingredients, and measuring various nutritional ingredients in the food;
biochemical index analysis, namely analyzing biochemical indexes in food;
functional quality analysis, namely evaluating the appearance, the taste and the flavor of the food through human sensory response;
label and statement analysis, verifying whether labels and nutritional statements on food packaging are accurate, legal and in compliance with relevant regulations and regulations;
monitoring the food processing process, analyzing the food production processing process, and monitoring the control of related parameters;
detecting food fraud, preventing and identifying food fraud by detecting components, indicators and special marks in the food;
analyzing whether food data contains adulterated, forged, false propaganda, illegal, potential harmful substances and indexes which are not up to standard or not by utilizing a logistic regression mathematical algorithm, marking the problems of adulterated, forged, false propaganda, illegal, potential harmful substances and indexes which are not up to standard in the analyzed food data as unqualified, notifying and displaying that the food is unqualified by utilizing a modeling display module (41), carrying out off-frame retrospective processing on all the food in the market, punishing manufacturers producing the food, and transmitting the analyzed food data into a modeling optimizing unit 4;
logistic regression mathematical algorithm formula:
；
where p represents a criterion for analyzing food, z represents a result of inputting a feature combination, e represents a bottom of natural logarithm, and its value is 2.71828;
the analysis and division unit (3) further comprises a food classification module (32), and the modeling and optimization unit (4) comprises a modeling display module (41) and an improvement and optimization module (42);
the improvement optimizing module (42) is used for receiving the food data collected in the data collecting module (11), receiving the food data after feature combination in the feature combining module (22), receiving the food data after analysis in the data analyzing module (31), carrying out improvement optimization on the collected food data, the food data after feature combination and the food data after analysis, and transmitting the food data after improvement optimization into the data analyzing module (31);
the food classification module (32) is used for receiving the food data after the improvement optimization in the data analysis module (31) and classifying the food after the improvement optimization;
the modeling display module (41) is used for receiving the improved optimized food data classified in the food classification module (32), establishing template data for the classified improved optimized food data, displaying the template data, and receiving the food data analyzed in the data analysis module (31);
the improved optimization module (42) is connected with the collected food data, the food data with combined characteristics and the analyzed food data, improves and optimizes the collected food data, the food data with combined characteristics and the analyzed food data, transmits the improved and optimized food data into the data analysis module (31), and the data analysis module (31) re-analyzes the improved and optimized food data;
a method for food quality analysis by a food quality analysis system, comprising the method steps of:
s1, a collection processing unit (1) collects food data, performs pretreatment operation on the collected food data, and transmits the food data after the pretreatment operation into a characteristic engineering unit (2);
s2, a characteristic engineering unit (2) receives food data after pretreatment operation, performs characteristic extraction on the food data after pretreatment operation, performs characteristic combination on the food data after characteristic extraction, and simultaneously transmits the food data after characteristic extraction into an analysis dividing unit (3), and transmits the food data after characteristic combination into a modeling optimizing unit (4);
s3, the analysis dividing unit (3) receives the food data after feature extraction, analyzes the food data after feature extraction, transmits the analyzed food data into the modeling optimizing unit (4), improves and optimizes the analyzed food data, transmits the improved and optimized food data into the analysis dividing unit (3), re-analyzes the improved and optimized food data, classifies the re-analyzed food data, transmits the classified food data into the modeling optimizing unit (4), and models and displays the classified food data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310941661.3A CN116681357B (en) | 2023-07-28 | 2023-07-28 | Food quality analysis system and method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310941661.3A CN116681357B (en) | 2023-07-28 | 2023-07-28 | Food quality analysis system and method based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116681357A CN116681357A (en) | 2023-09-01 |
| CN116681357B true CN116681357B (en) | 2023-10-27 |
Family
ID=87789405
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310941661.3A Active CN116681357B (en) | 2023-07-28 | 2023-07-28 | Food quality analysis system and method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116681357B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103700019A (en) * | 2013-12-17 | 2014-04-02 | 吉林大学 | Food quality analysis method |
| WO2014092230A1 (en) * | 2012-12-13 | 2014-06-19 | 대한민국 (식품의약품안전청장) | System and method for inspecting imported food-based harm prediction |
| KR20170062564A (en) * | 2015-11-27 | 2017-06-08 | 한국식품연구원 | Method, Apparatus for Food Safety Data Analysis Based on Big Data, And a Computer-readableStorage Medium for executing the Method |
| CN108182555A (en) * | 2018-02-09 | 2018-06-19 | 重庆市农业科学院 | A kind of Safety of Food Quality risk evaluating system |
| JP6497426B1 (en) * | 2017-10-17 | 2019-04-10 | Ｊｆｅスチール株式会社 | Shape optimization analysis method and apparatus for laminated composite member |
| CN109685522A (en) * | 2018-11-15 | 2019-04-26 | 中国农业大学 | Food Cold Chain Quality Monitoring Control System and method |
| CN111079063A (en) * | 2019-11-07 | 2020-04-28 | 国网河北省电力有限公司电力科学研究院 | Detection efficiency analysis-based provincial level detection capability optimization method and system |
| CN111160923A (en) * | 2018-11-06 | 2020-05-15 | 上海仪电（集团）有限公司中央研究院 | Graph database construction system for food traceability and analysis |
| CN111260155A (en) * | 2020-02-17 | 2020-06-09 | 武汉轻工大学 | Grain processing procedure optimization method and device, electronic equipment and storage medium |
| CN111553520A (en) * | 2020-04-22 | 2020-08-18 | 武汉轻工大学 | Grain production optimization method and device based on supply chain traceability evaluation system |
| AU2020103340A4 (en) * | 2020-11-10 | 2021-01-21 | Guizhou Provincial Center For Disease Control And Prevention | A Physical and Chemical Data Analysis System for Food Safety Risk Monitoring |
| CN114202232A (en) * | 2021-12-21 | 2022-03-18 | 国家海洋环境监测中心 | System and method for optimizing ecological resource protection based on data analysis |
| KR20220062935A (en) * | 2020-11-09 | 2022-05-17 | 소재완 | Health functional food online marketing analysis system based on artificial intelligence |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190295440A1 (en) * | 2018-03-23 | 2019-09-26 | Nutrino Health Ltd. | Systems and methods for food analysis, personalized recommendations and health management |
-
2023
- 2023-07-28 CN CN202310941661.3A patent/CN116681357B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014092230A1 (en) * | 2012-12-13 | 2014-06-19 | 대한민국 (식품의약품안전청장) | System and method for inspecting imported food-based harm prediction |
| CN103700019A (en) * | 2013-12-17 | 2014-04-02 | 吉林大学 | Food quality analysis method |
| KR20170062564A (en) * | 2015-11-27 | 2017-06-08 | 한국식품연구원 | Method, Apparatus for Food Safety Data Analysis Based on Big Data, And a Computer-readableStorage Medium for executing the Method |
| JP6497426B1 (en) * | 2017-10-17 | 2019-04-10 | Ｊｆｅスチール株式会社 | Shape optimization analysis method and apparatus for laminated composite member |
| CN108182555A (en) * | 2018-02-09 | 2018-06-19 | 重庆市农业科学院 | A kind of Safety of Food Quality risk evaluating system |
| CN111160923A (en) * | 2018-11-06 | 2020-05-15 | 上海仪电（集团）有限公司中央研究院 | Graph database construction system for food traceability and analysis |
| CN109685522A (en) * | 2018-11-15 | 2019-04-26 | 中国农业大学 | Food Cold Chain Quality Monitoring Control System and method |
| CN111079063A (en) * | 2019-11-07 | 2020-04-28 | 国网河北省电力有限公司电力科学研究院 | Detection efficiency analysis-based provincial level detection capability optimization method and system |
| CN111260155A (en) * | 2020-02-17 | 2020-06-09 | 武汉轻工大学 | Grain processing procedure optimization method and device, electronic equipment and storage medium |
| CN111553520A (en) * | 2020-04-22 | 2020-08-18 | 武汉轻工大学 | Grain production optimization method and device based on supply chain traceability evaluation system |
| KR20220062935A (en) * | 2020-11-09 | 2022-05-17 | 소재완 | Health functional food online marketing analysis system based on artificial intelligence |
| AU2020103340A4 (en) * | 2020-11-10 | 2021-01-21 | Guizhou Provincial Center For Disease Control And Prevention | A Physical and Chemical Data Analysis System for Food Safety Risk Monitoring |
| CN114202232A (en) * | 2021-12-21 | 2022-03-18 | 国家海洋环境监测中心 | System and method for optimizing ecological resource protection based on data analysis |
Non-Patent Citations (3)
| Title |
|---|
| The analysis and re-optimization of food systems by using intelligentoptimization algorithms and machine learning;Jilin University等;《ALL LIFE》;第15卷(第1期);656–677 * |
| 农产品电子商务全渠道供应链的逆向整合与优化;刘娜娜等;《商业经济研究》;第22卷;153-156 * |
| 大数据挖掘在食品安全风险预警领域的应用;卢大安;;食品安全导刊(第36期);342-344 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116681357A (en) | 2023-09-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kong et al. | Deep-stacking network approach by multisource data mining for hazardous risk identification in IoT-based intelligent food management systems | |
| Li et al. | Nondestructive detection of total volatile basic nitrogen (TVB-N) content in pork meat by integrating hyperspectral imaging and colorimetric sensor combined with a nonlinear data fusion | |
| CN111666269B (en) | Automatic coding and full-chain traceability system for big food safety data | |
| Wang et al. | Application of machine learning to the monitoring and prediction of food safety: A review | |
| CN112116277A (en) | Full-chain food safety big data acquisition method | |
| CN109191338B (en) | Student behavior early warning method based on campus one-card consumption data | |
| Yang et al. | Detection of the freshness state of cooked beef during storage using hyperspectral imaging | |
| Saleh et al. | Palm oil classification using deep learning | |
| CN116596305A (en) | Risk grading method for food safety management | |
| Ma et al. | Neural network in food analytics | |
| Xu et al. | Olfactory visualization sensor system based on colorimetric sensor array and chemometric methods for high precision assessing beef freshness | |
| CN113762764B (en) | Automatic grading and early warning system and method for imported food safety risks | |
| Hua et al. | A feature dimensionality reduction strategy coupled with an electronic nose to identify the quality of egg | |
| CN114186933A (en) | Cold chain food intelligent supervision platform | |
| CN116681357B (en) | Food quality analysis system and method based on artificial intelligence | |
| CN113722430A (en) | Multi-mode man-machine interaction method and system, equipment and medium for food safety | |
| Panghal et al. | Blockchain technology for enhancing sustainable food systems: A consumer perspective | |
| CN116109325B (en) | Internet of things-based food safety control and tracing system and method | |
| CN110163722B (en) | Big data analysis system and analysis method for accurate sale of agricultural products | |
| CN116205688A (en) | Fresh product information processing method and device, computer equipment and storage medium | |
| CN113821494A (en) | Method for establishing food safety knowledge base | |
| Sarveswaran et al. | MilkSafe: A Hardware-Enabled Milk Quality Prediction using Machine Learning | |
| CN111125351A (en) | Business condition briefing generation method and device, electronic equipment and storage medium | |
| CN113191926B (en) | Method and system for identifying grain and oil crop supply chain hazard based on deep integrated learning network | |
| Martínez-Simarro et al. | Applications and business impact of artificial intelligence in the industrial production of food and beverages |
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 |