Food processing traceability system based on electronic tag and RFID device

Abstract

The invention belongs to the technical field of food information management, and discloses a food processing traceability system based on an electronic tag and RFID equipment. A food data set and a personnel data set are collected and preprocessed, the food data set comprises raw material quality guarantee data, raw material date data, raw material storage data and raw material batch data, and the personnel data set comprises employee job number data, employee batch data and employee contact data; analyzing the food data set to obtain a food quality reference value, and classifying the food quality reference value to obtain a food classification result; processing the food classification result to obtain a food processing result; the food quality reference value, the food classification result and the food processing result are stored, and generally, the method has the remarkable advantages of being high in auxiliary production capacity, high in risk prevention and good in raw material information tracing effect.

Description

Technical Field

[0001] The present invention relates to the technical field of food information management, and more specifically, to a food processing traceability system and RFID equipment based on electronic tags. Background Art

[0002] The food processing industry refers to the grain grinding, feed processing, vegetable oil and sugar processing, slaughtering and meat processing, aquatic product processing, as well as processing activities such as vegetables, fruits and nuts that directly use agricultural, forestry, animal husbandry and fishery products as raw materials. It is a type of agricultural product processing industry in a broad sense. Since the "Eleventh Five-Year Plan", my country's food processing industry has developed rapidly and has undergone gratifying changes. It has become an industry with strong development potential. With the rapid development of my country's economy in recent years, people's demand for food has also increased, and the food processing industry is also developing rapidly.

[0003] The patent with application publication number CN202584166U discloses a food safety traceability system based on RFID technology. Through the technical characteristics of combining the product with RFID electronic tags and automatically identifying the target and obtaining relevant data through radio frequency signals, all stages of the food chain, including food production, testing, processing, wholesale and retail, are fully monitored and supervised. Once a food safety emergency occurs, not only can the final consumer of the food be found based on the food traceability management system, but also the link where the problem occurs in the circulation or production and processing process can be found, which can effectively protect the health of consumers.

[0004] However, the above-mentioned food safety traceability system based on RFID technology, although it uses RFID electronic tags for products and gives the production, testing, processing, wholesale and retail information of food in the RFID electronic tags, so that the process information of the product can be queried by scanning the RFID electronic tags of the product, in the food processing process, the storage of food raw materials is an important part of the safe production of food products. At present, most of them are sampled and tested manually, which not only requires high labor costs, but also is prone to expired or spoiled food raw materials appearing in the processing steps due to insufficient test samples or slackness of personnel, thus posing a food safety hazard.

[0005] In view of this, the present invention proposes a food processing traceability system and RFID equipment based on electronic tags to solve the above problems. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solutions: comprising:

[0007] The data collection module is used to collect food data sets and personnel data sets and perform preprocessing. The food data sets include raw material shelf life data, raw material date data, raw material storage data and raw material batch data. The personnel data sets include employee work number data, employee batch data and employee contact data.

[0008] Furthermore, the methods of collecting food datasets and personnel datasets include:

[0009] By connecting to the enterprise's raw material management platform, the shelf life of food raw materials, the date of collection of food raw materials and the batch number of food raw materials are collected to obtain raw material shelf life data, raw material date data and raw material batch data;

[0010] By installing temperature and humidity sensors, the temperature and humidity inside the warehouse are collected, and the raw material storage data is obtained by entering the calculation formula: Aa=Ab×A1+Ac×A2, where Ab is the temperature, Ac is the humidity, and A1 and A2 are the corresponding weight factors;

[0011] By connecting to the enterprise personnel management platform, the employee's work number, the batch number of food raw materials that the employee is responsible for, and the employee's mobile phone number are collected to obtain the employee's work number data, employee batch data, and employee contact data;

[0012] The preprocessing methods include data cleaning and data denoising;

[0013] The data processing module is used to analyze the food data set, obtain the food quality reference value, and classify it to obtain the food classification result;

[0014] Further, the methods for analyzing the food dataset include:

[0015] By substituting into the calculation formula: Get the food shelf life reference value, where Bb is the current time data, Bc is the raw material date data, Bd is the raw material shelf life data, and An is the ideal shelf life data;

[0016] Collect historical food quality reference values ​​of group P as the sample set, and divide the sample set into a training set of 70% P, a test set of 15% P, and a validation set of 15% P;

[0017] A quality classification model is established based on the sample set, and the normal cluster center C1, abnormal cluster center C2 and dangerous cluster center C3 are preset. Three values ​​are selected in the training set as the first cluster center. The original cluster centers represent the normal cluster center C1, abnormal cluster center C2 and dangerous cluster center C3 respectively.

[0018] By substituting into the calculation formula: Get the distance between the data item and the first cluster center, calculate the distance between the data item and the original cluster center in the training set, and assign the data item to the first cluster center closest to the example, and get three second cluster centers. Calculate the mean of the first cluster centers respectively as the new first cluster centers, where i is the number of first cluster centers, Ei is the i-th first cluster center, Db is the data item, and Di is the centroid of the i-th first cluster center;

[0019] After reaching the preset number of iterations, the raw material quality classification model is obtained;

[0020] The food quality reference value is input into the raw material quality classification model, and the food quality reference value is output;

[0021] Further, the classification methods include:

[0022] Preset the raw material shelf life threshold interval (D1, D2). When the food quality reference value is less than D1, normal quality information is generated. When the food quality reference value is greater than D1 and less than D2, abnormal quality information is generated. When the food quality reference value is greater than D2, dangerous quality information is generated.

[0023] Normal quality information includes a set of fields representing normal quality of raw materials, abnormal quality information includes a set of fields representing abnormal quality of raw materials, and dangerous quality information includes a set of fields representing dangerous quality of raw materials;

[0024] Pack normal quality information, abnormal quality information and dangerous quality information to obtain food classification results;

[0025] An analysis and early warning module is used to process the food classification results and obtain food processing results;

[0026] Furthermore, the methods for processing the food classification results include:

[0027] When the food processing result is normal quality information, a normal quality SMS is sent to the staff receiving end through the communication unit; when the food processing result is abnormal quality information, an abnormal quality SMS is sent to the staff receiving end through the communication unit; when the food processing result is dangerous quality information, a dangerous quality SMS is sent to the staff receiving end through the communication unit;

[0028] Normal quality SMS includes explanation of the normal quality of food raw materials during storage, reminding staff to regularly check the quality of food raw materials and use food raw materials according to the first-in-first-out principle;

[0029] Abnormal quality text messages include explanations of insufficient shelf life of food ingredients during storage, requiring staff to arrange for the use of such food ingredients as soon as possible, and checking whether the food ingredients are spoiled or damaged;

[0030] Emergency quality text messages include information about expired or spoiled food raw materials during storage, requiring staff to trace the responsible person based on raw material batch data and employee batch data, and to properly handle or destroy such food raw materials in accordance with the plan;

[0031] Pack normal quality SMS, abnormal quality SMS and emergency quality SMS, and get food processing results;

[0032] A data storage module, used for storing food quality reference values, food classification results and food processing results;

[0033] Furthermore, the step of storing includes:

[0034] Q1: Based on the raw material batch data, the food quality reference value, food classification results and food processing results are packaged to obtain the traceability information set;

[0035] Q2: Encrypt the traceability information set based on the AES encryption algorithm to obtain the traceability ciphertext;

[0036] Q3: Based on the hash algorithm, calculate the traceability ciphertext, obtain the hash value of the traceability ciphertext, package the traceability ciphertext and the hash value, upload them to the blockchain network, and store them in the corresponding block;

[0037] Further, S1: collecting food data sets and personnel data sets and preprocessing them, the food data sets include raw material shelf life data, raw material date data, raw material storage data and raw material batch data, and the personnel data sets include employee work number data, employee batch data and employee contact data;

[0038] S2: Analyze the food data set to obtain food quality reference values, classify them, and obtain food classification results;

[0039] S3: Process the food classification results to obtain food processing results;

[0040] S4: Store food quality reference values, food classification results and food processing results.

[0041] The technical effects and advantages of the food processing traceability system and RFID equipment based on electronic tags of the present invention are as follows:

[0042] The food quality reference value obtained by the present invention through the analysis of the food data set can intuitively reflect the state of food raw materials in the storage process, assist the staff in the storage management of food raw materials, and reduce the high labor cost and time cost caused by manual inspection. The food processing results obtained by processing the food classification results can effectively assist the staff in making rapid decision responses when facing the states of different food raw materials, and reduce the risk of improper processing caused by temporary manual processing. The food processing results can trace the responsible persons for the picking, entry and storage of food raw materials based on the raw material batch data and the employee batch data, which greatly enhances the safety of the food raw material processing process. Generally speaking, the present invention has the significant advantages of strong auxiliary production capacity, high risk prevention and good raw material information tracing effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a schematic diagram of the food processing traceability system based on electronic tags of the present invention;

[0044] Figure 2 It is a schematic diagram of the food processing traceability method based on electronic tags of the present invention. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] Example 1

[0047] See also Figure 1 As shown, the food processing traceability system based on electronic tags described in this embodiment includes:

[0048] The data collection module is used to collect food data sets and personnel data sets and perform preprocessing. The food data sets include raw material shelf life data, raw material date data, raw material storage data and raw material batch data. The personnel data sets include employee work number data, employee batch data and employee contact data.

[0049] Furthermore, the methods of collecting food datasets and personnel datasets include:

[0050] By connecting to the enterprise's raw material management platform, the shelf life of food raw materials, the date of collection of food raw materials and the batch number of food raw materials are collected to obtain raw material shelf life data, raw material date data and raw material batch data;

[0051] It should be explained that the shelf life of raw materials is based on the shelf life under the company's existing storage conditions. For example, if the shelf life of flour is 200 days under the company's existing storage conditions, the raw material category data value is 200;

[0052] By installing temperature and humidity sensors, the temperature and humidity inside the warehouse are collected, and the raw material storage data is obtained by entering the calculation formula: Aa=Ab×A1+Ac×A2, where Ab is the temperature, Ac is the humidity, and A1 and A2 are the corresponding weight factors;

[0053] By connecting to the enterprise personnel management platform, the employee's work number, the batch number of food raw materials that the employee is responsible for, and the employee's mobile phone number are collected to obtain the employee's work number data, employee batch data, and employee contact data;

[0054] The preprocessing methods include data cleaning and data denoising;

[0055] The data processing module is used to analyze the food data set, obtain the food quality reference value, and classify it to obtain the food classification result;

[0056] Further, the methods for analyzing the food dataset include:

[0057] By substituting into the calculation formula: Get the food shelf life reference value, where Bb is the current time data, Bc is the raw material date data, Bd is the raw material shelf life data, and An is the ideal shelf life data;

[0058] It should be explained that the current time data is the date and time for calculating the food quality reference value, which is collected through the timestamp, and the ideal shelf life data is the length of time that the food raw materials can be stored under ideal conditions;

[0059] Collect historical food quality reference values ​​of group P as the sample set, and divide the sample set into a training set of 70% P, a test set of 15% P, and a validation set of 15% P;

[0060] A quality classification model is established based on the sample set, and the normal cluster center C1, abnormal cluster center C2 and dangerous cluster center C3 are preset. Three values ​​are selected in the training set as the first cluster center. The original cluster centers represent the normal cluster center C1, abnormal cluster center C2 and dangerous cluster center C3 respectively.

[0061] By substituting into the calculation formula: Get the distance between the data item and the first cluster center, calculate the distance between the data item and the original cluster center in the training set, and assign the data item to the first cluster center closest to the example, and get three second cluster centers. Calculate the mean of the first cluster centers respectively as the new first cluster centers, where i is the number of first cluster centers, Ei is the i-th first cluster center, Db is the data item, and Di is the centroid of the i-th first cluster center;

[0062] It needs to be explained that the centroid refers to the central position of a cluster center, which is the average value of the coordinates of all data items in the cluster;

[0063] After reaching the preset number of iterations, the raw material quality classification model is obtained;

[0064] The food quality reference value is input into the raw material quality classification model, and the food quality reference value is output;

[0065] Further classification methods include:

[0066] Preset the raw material shelf life threshold interval (D1, D2). When the food quality reference value is less than D1, normal quality information is generated. When the food quality reference value is greater than D1 and less than D2, abnormal quality information is generated. When the food quality reference value is greater than D2, dangerous quality information is generated.

[0067] Normal quality information includes a set of fields representing normal quality of raw materials, abnormal quality information includes a set of fields representing abnormal quality of raw materials, and dangerous quality information includes a set of fields representing dangerous quality of raw materials;

[0068] Pack normal quality information, abnormal quality information and dangerous quality information to obtain food classification results;

[0069] An analysis and early warning module is used to process the food classification results and obtain food processing results;

[0070] Furthermore, the methods for processing the food classification results include:

[0071] When the food processing result is normal quality information, a normal quality SMS is sent to the staff receiving end through the communication unit; when the food processing result is abnormal quality information, an abnormal quality SMS is sent to the staff receiving end through the communication unit; when the food processing result is dangerous quality information, a dangerous quality SMS is sent to the staff receiving end through the communication unit;

[0072] Normal quality SMS includes explanation of the normal quality of food raw materials during storage, reminding staff to regularly check the quality of food raw materials and use food raw materials according to the first-in-first-out principle;

[0073] Abnormal quality text messages include explanations of insufficient shelf life of food ingredients during storage, requiring staff to arrange for the use of such food ingredients as soon as possible, and checking whether the food ingredients are spoiled or damaged;

[0074] Emergency quality text messages include information about expired or spoiled food raw materials during storage, requiring staff to trace the responsible person based on raw material batch data and employee batch data, and to properly handle or destroy such food raw materials in accordance with the plan;

[0075] Pack normal quality SMS, abnormal quality SMS and emergency quality SMS, and get food processing results;

[0076] A data storage module, used for storing food quality reference values, food classification results and food processing results;

[0077] Furthermore, the step of storing includes:

[0078] Q1: Based on the raw material batch data, the food quality reference value, food classification results and food processing results are packaged to obtain the traceability information set;

[0079] Q2: Encrypt the traceability information set based on the AES encryption algorithm to obtain the traceability ciphertext;

[0080] Q3: Based on the hash algorithm, calculate the traceability ciphertext, obtain the hash value of the traceability ciphertext, package the traceability ciphertext and the hash value, upload them to the blockchain network, and store them in the corresponding block;

[0081] The beneficial effects of this embodiment are as follows: by analyzing the food data set, the food quality reference value obtained can intuitively reflect the state of the food raw materials during the storage process, assist the staff in the storage management of the food raw materials, and reduce the high labor cost and time cost caused by manual inspections; by processing the food classification results, the food processing results obtained can effectively assist the staff in making rapid decision responses in the face of different states of food raw materials, reduce the risk of improper processing caused by manual temporary processing, and the food processing results can trace the responsible persons for the picking, entry and storage of food raw materials based on the raw material batch data and the employee batch data, which greatly enhances the safety of the food raw material processing process. In general, the present invention has the significant advantages of strong auxiliary production capacity, high risk prevention and good raw material information traceability.

[0082] Example 2

[0083] See also Figure 2As shown, the part not described in detail in this embodiment is described in Example 1, and an RFID device based on an electronic tag is provided, including: S1: collecting a food data set and a personnel data set, and preprocessing them, the food data set includes raw material shelf life data, raw material date data, raw material storage data and raw material batch data, and the personnel data set includes employee work number data, employee batch data and employee contact data;

[0084] S2: Analyze the food data set to obtain food quality reference values, classify them, and obtain food classification results;

[0085] S3: Process the food classification results to obtain food processing results;

[0086] S4: Store food quality reference values, food classification results and food processing results.

[0087] Example 3

[0088] This embodiment discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the operation mode of the food processing traceability method based on electronic tags provided above is implemented.

[0089] Since the electronic device introduced in this embodiment is an electronic device used to implement the food processing traceability method based on electronic tags in the embodiment of this application, based on the food processing traceability method based on electronic tags introduced in the embodiment of this application, the technical personnel of this field can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application is not described in detail here. As long as the technical personnel of this field implement the electronic device used in the food processing traceability method based on electronic tags in the embodiment of this application, it belongs to the scope of protection of this application.

[0090] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0091] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technical users in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. The food processing traceability system based on electronic tags is characterized by: include: The data collection module is used to collect food data sets and personnel data sets and perform preprocessing. The food data sets include raw material shelf life data, raw material date data, raw material storage data and raw material batch data. The personnel data sets include employee work number data, employee batch data and employee contact data. The data processing module is used to analyze the food data set, obtain the food quality reference value, and classify it to obtain the food classification result; An analysis and early warning module is used to process the food classification results and obtain food processing results; The data storage module is used to store food quality reference values, food classification results and food processing results.

2. The food processing traceability system based on electronic tags according to claim 1 is characterized in that: Ways to collect food datasets and personnel datasets include: By connecting to the enterprise's raw material management platform, the shelf life of food raw materials, the date of collection of food raw materials and the batch number of food raw materials are collected to obtain raw material shelf life data, raw material date data and raw material batch data; By installing temperature and humidity sensors, the temperature and humidity inside the warehouse are collected, and the raw material storage data is obtained by entering the calculation formula: Aa=Ab×A1+Ac×A2, where Ab is the temperature, Ac is the humidity, and A1 and A2 are the corresponding weight factors; By connecting to the enterprise personnel management platform, the employee's work number, the batch number of food raw materials that the employee is responsible for, and the employee's mobile phone number are collected to obtain the employee's work number data, employee batch data, and employee contact data; The preprocessing methods include data cleaning and data denoising.

3. The food processing traceability system based on electronic tags according to claim 2 is characterized in that: The methods used to analyze the food dataset include: By substituting into the calculation formula: Get the food shelf life reference value, where Bb is the current time data, Bc is the raw material date data, Bd is the raw material shelf life data, and An is the ideal shelf life data; Collect historical food quality reference values ​​of group P as the sample set, and divide the sample set into a training set of 70% P, a test set of 15% P, and a validation set of 15% P; A quality classification model is established based on the sample set, and the normal cluster center C1, abnormal cluster center C2 and dangerous cluster center C3 are preset. Three values ​​are selected in the training set as the first cluster center. The original cluster centers represent the normal cluster center C1, abnormal cluster center C2 and dangerous cluster center C3 respectively. By substituting into the calculation formula: Get the distance between the data item and the first cluster center, calculate the distance between the data item and the original cluster center in the training set, and assign the data item to the first cluster center closest to the example, and get three second cluster centers. Calculate the mean of the first cluster centers respectively as the new first cluster centers, where i is the number of first cluster centers, Ei is the i-th first cluster center, Db is the data item, and Di is the centroid of the i-th first cluster center; After reaching the preset number of iterations, the raw material quality classification model is obtained; The food quality reference value is input into the raw material shelf life classification model, and the food quality reference value is output.

4. The food processing traceability system based on electronic tags according to claim 3 is characterized in that: The classification methods include: Preset the raw material shelf life threshold interval (D1, D2). When the food quality reference value is less than D1, normal quality information is generated. When the food quality reference value is greater than D1 and less than D2, abnormal quality information is generated. When the food quality reference value is greater than D2, dangerous quality information is generated. Normal quality information includes a set of fields representing normal quality of raw materials, abnormal quality information includes a set of fields representing abnormal quality of raw materials, and dangerous quality information includes a set of fields representing dangerous quality of raw materials; Normal quality information, abnormal quality information and dangerous quality information are packaged to obtain food classification results.

5. The food processing traceability system based on electronic tags according to claim 4 is characterized in that: The methods for processing food classification results include: When the food processing result is normal quality information, a normal quality SMS is sent to the staff receiving end through the communication unit; when the food processing result is abnormal quality information, an abnormal quality SMS is sent to the staff receiving end through the communication unit; when the food processing result is dangerous quality information, a dangerous quality SMS is sent to the staff receiving end through the communication unit; Normal quality SMS includes explanation of the normal quality of food raw materials during storage, reminding staff to regularly check the quality of food raw materials and use food raw materials according to the first-in-first-out principle; Abnormal quality text messages include explanations of insufficient shelf life of food ingredients during storage, requiring staff to arrange for the use of such food ingredients as soon as possible, and checking whether the food ingredients are spoiled or damaged; Emergency quality text messages include information about expired or spoiled food raw materials during storage, requiring staff to trace the responsible person based on raw material batch data and employee batch data, and to properly handle or destroy such food raw materials in accordance with the plan; Pack normal quality SMS, abnormal quality SMS and emergency quality SMS to get food processing results.

6. The food processing traceability system based on electronic tags according to claim 5 is characterized in that: The steps to store include: Q1: Based on the raw material batch data, the food quality reference value, food classification results and food processing results are packaged to obtain the traceability information set; Q2: Encrypt the traceability information set based on the AES encryption algorithm to obtain the traceability ciphertext; Q3: Based on the hash algorithm, calculate the traceability ciphertext, obtain the hash value of the traceability ciphertext, package the traceability ciphertext and the hash value, upload them to the blockchain network, and store them in the corresponding block.

7. A food processing traceability method based on electronic tags, implemented according to any one of the food processing traceability systems based on electronic tags according to claims 1-6, characterized in that: S1: Collect food data sets and personnel data sets and preprocess them. The food data sets include raw material shelf life data, raw material date data, raw material storage data and raw material batch data. The personnel data sets include employee ID data, employee batch data and employee contact data. S2: Analyze the food data set to obtain food quality reference values, classify them, and obtain food classification results; S3: Process the food classification results to obtain food processing results; S4: Store food quality reference values, food classification results and food processing results.

8. An RFID device based on an electronic tag, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the food processing traceability system based on the electronic tag as described in any one of claims 1 to 6 is implemented.

Images