CN116385031A - Data tracing method based on big data and multiple data sources - Google Patents
Data tracing method based on big data and multiple data sources Download PDFInfo
- Publication number
- CN116385031A CN116385031A CN202310664313.6A CN202310664313A CN116385031A CN 116385031 A CN116385031 A CN 116385031A CN 202310664313 A CN202310664313 A CN 202310664313A CN 116385031 A CN116385031 A CN 116385031A
- Authority
- CN
- China
- Prior art keywords
- raw material
- food
- information
- type
- cloud server
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 239000002994 raw material Substances 0.000 claims abstract description 238
- 235000013305 food Nutrition 0.000 claims abstract description 225
- 238000004519 manufacturing process Methods 0.000 claims abstract description 86
- 230000002159 abnormal effect Effects 0.000 claims abstract description 47
- 238000012545 processing Methods 0.000 claims abstract description 27
- 230000008451 emotion Effects 0.000 claims description 20
- 238000005516 engineering process Methods 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 7
- 239000000203 mixture Substances 0.000 claims description 6
- 238000010923 batch production Methods 0.000 claims description 3
- 238000005303 weighing Methods 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 claims description 2
- 239000000463 material Substances 0.000 claims 2
- 235000012041 food component Nutrition 0.000 description 9
- 239000005417 food ingredient Substances 0.000 description 9
- 239000013598 vector Substances 0.000 description 8
- 238000012549 training Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 235000013312 flour Nutrition 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000006386 memory function Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000005180 public health Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 235000021404 traditional food Nutrition 0.000 description 1
Images
Classifications
-
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a data tracing method based on big data and multiple data sources, which relates to the technical field of food safety tracing, and comprises the steps of generating a food safety standard table based on a food raw material proportioning table by collecting the food raw material proportioning table in advance, collecting raw material purchase orders and stock information of a food processing factory, collecting food production process information of the food processing factory, sending a first alarm signal to a food safety supervision party if the food production process information is abnormal, comparing the food production process information with the stock information, generating food comparison information, and sending a second alarm signal to the food safety supervision party if the food comparison information is abnormal; generating a tracing code for each batch of food, receiving feedback information of a user in real time based on the tracing code, and sending a third alarm signal to a food safety supervision party if the feedback information is abnormal; the transparency of food production is ensured, and the food safety of users is ensured.
Description
Technical Field
The invention belongs to the food safety tracing technology, and particularly relates to a data tracing method based on big data and multiple data sources.
Background
Food safety issues have a significant impact on public health and social stability. However, food safety management methods tend to have the following characteristics;
complex supply chain: the food production involves a plurality of links including raw material purchase, production and processing, transportation and distribution and the like. The complexity of the food supply chain makes it difficult to trace food safety issues;
lack of real-time monitoring and early warning: traditional food safety management methods are typically based on off-line sampling detection and periodic inspection; this approach does not allow real-time monitoring of the quality and safety conditions of the food, resulting in potential hazards and problems that may not be found prior to detection;
data dispersion and isolation: food production involves a plurality of links and participants, related data are generally scattered in different organizations and systems, and integration and sharing of the data are difficult to achieve, so that the tracing process is difficult and the efficiency is low;
therefore, the invention provides a data tracing method based on big data and multiple data sources.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems existing in the prior art. Therefore, the invention provides a data tracing method based on big data and multiple data sources, which ensures the transparency of food production and ensures the food safety of users.
In order to achieve the above purpose, the invention provides a data tracing method based on big data and multiple data sources, which comprises the following steps:
step one: the cloud server side collects a food raw material proportioning table and generates a food safety standard table based on the food raw material proportioning table;
step two: the cloud server side collects raw material purchase orders and inventory information of the food processing factory, and updates the inventory information in real time when the inventory is new;
step three: the cloud server collects food production process information of the food processing factory, analyzes whether the food production process information is abnormal, and sends a first alarm signal to a food safety supervision party if the food production process information is abnormal;
step four: the cloud server compares the food production process information with the inventory information, generates food comparison information, analyzes whether the food comparison information is abnormal based on a food safety standard table, and sends a second alarm signal to a food safety supervision party if the food comparison information is abnormal;
step five: the cloud server generates tracing codes for each batch of food, receives feedback information of a user in real time based on the tracing codes, analyzes the feedback information, and sends a third alarm signal to a food safety supervision party if the feedback information is abnormal;
the food ingredient proportioning table is a food ingredient table stored in a cloud database of a cloud server, wherein the food ingredient table takes a food type as a main key and takes a raw material type and a food ingredient proportioning range as attributes;
the food safety standard table is generated by the following steps: the cloud server sets a proportioning upper limit and a proportioning lower limit for the raw material proportioning of each food type in the food composition table based on food safety standards to obtain a food safety standard table; the food safety standard table takes the type of food as a main key and takes the type of raw materials, the upper limit of the proportion and the lower limit of the proportion as attributes;
the raw material purchase orders are orders generated by purchasing various raw materials from various raw material factories, wherein the raw material purchase orders are electronic orders, and the raw material purchase orders are automatically uploaded to a cloud server after being generated; the raw material purchase order comprises a raw material type, an order number and a purchase quantity;
the stock information is the real-time stock quantity of each raw material; the method for obtaining the real-time stock quantity of the raw materials comprises the following steps:
presetting a stacking raw material type for each warehouse shelf for stacking raw materials; the stacking raw material type is the raw material type required to be stacked for each warehouse shelf;
a weight sensor arranged under a warehouse shelf obtains the weight of raw materials in real time, and the real-time stock quantity of the stacked raw material types corresponding to the warehouse shelf is set as the weight of the raw materials; the cloud server stores real-time inventory of each raw material type in real time as inventory information;
when the inventory is new, the mode of updating the inventory information is as follows:
a first image capturing device is arranged on each warehouse goods shelf, and scans raw material codes outside raw material packages before raw materials are stacked on the warehouse goods shelves each time to obtain scanned raw material information, and the first image capturing device sends the raw material information to a cloud server end; the raw material code is any one of a bar code or a two-dimensional code, and raw material information is stored;
the raw material information is an encrypted raw material purchase order, the encryption mode is asymmetric encryption, the private key of the secret key is held by a raw material factory, and the raw material factory for stacking raw material types encrypts the raw material purchase order by using the private key; the cloud server end decrypts the raw material information by using the public key corresponding to the raw material factory, and if the decryption is successful and the decrypted raw material purchase order is contained in the historical raw material purchase order of the food processing factory, the processing is not performed; if the decryption is unsuccessful or the decrypted raw material purchase order is not contained in the historical raw material purchase order of the food processing factory, the cloud server side sends a raw material alarm signal to a food safety supervisor;
the method for collecting the information of the food production process of the food processing factory is as follows:
installing a plurality of second image capturing devices at raw material input positions on the food production line, and sending captured input raw material images to a cloud server end in real time by the second image capturing devices; the raw material input position is a position on a food production line, where various types of raw materials enter the production line for food processing;
a weight sensor is arranged at a food outlet of a food production line, and the weight sensor measures the food yield in real time;
all captured raw material images and food yield as food production process information;
the method for analyzing whether the food production process information is abnormal is as follows:
the cloud server side obtains the food type according to the food production line type; the cloud server side uses a target recognition technology to recognize the type of the raw materials input into the production line in real time, obtains a raw material recognition result, searches a food raw material proportioning table to determine whether the raw material recognition result is contained in the raw material type corresponding to the food type, and judges that the information of the food production process is abnormal if the raw material recognition result is not contained in the corresponding raw material type;
if the information is contained in the corresponding raw material type, judging that the food production process information is not abnormal; the raw material identification result is the raw material type identified by the target identification technology;
the food contrast information is generated by the following modes:
after the completion of the production of the food product in each production batch, calculating the total weight of the food product yield in the batch, and marking the total weight as W;
counting stock quantity difference values of each raw material type before and after the batch production; each raw material type is marked as i, and the stock quantity difference of the ith raw material type is marked as Ci; if the ith raw material type is newly stocked in the batch, updating the stock quantity difference value Ci into a stock quantity difference value Ci minus the weight of the new ith raw material type, wherein the weight of the new ith raw material type is obtained by weighing the weight sensor before the new ith raw material type is stocked in advance;
calculating a production ratio Bi of the stock quantity difference Ci of each raw material type and the total weight W; the food comparison information includes a production ratio value for each raw material type;
the method for analyzing whether the food contrast information is abnormal or not is as follows:
retrieving the upper limit and the lower limit of the proportion of the ith raw material type from the food safety standard table according to the corresponding food type; if the production ratio Bi is larger than the upper ratio limit or smaller than the lower ratio limit, judging that the food contrast information is abnormal; if the production ratio Bi is smaller than the upper ratio limit and larger than the lower ratio limit, judging that the food comparison information is not abnormal;
based on the tracing codes, the mode of receiving feedback information of the user in real time is as follows:
the cloud server receives a tracing request initiated by a user scanning tracing code in real time and displays a tracing result to the user; the tracing code is a two-dimensional code and comprises a batch number and a webpage address of food production, and after a user scans the tracing code, a tracing request for accessing the webpage address is generated; the tracing result is web page content corresponding to the web page address, and the web page content comprises the raw material type of the batch number and a feedback frame; the raw material types of the batch number are all raw material types which are captured by the first image capturing equipment and identified by the cloud server side in the food production process of the batch number;
the feedback information is analyzed in the following manner:
using the content filled in by the user in the feedback frame as feedback information, analyzing the emotion positive and negative of each feedback information by using a text emotion analysis technology, and if the feedback information is all, calculating a negative feedback ratio, wherein the negative feedback ratio is the ratio of the number of feedback information with emotion negative to all feedback information; if the emotion negative ratio is larger than a preset negative feedback threshold, judging that the feedback information is abnormal; if the emotion negative ratio is smaller than a preset negative feedback threshold, judging that the feedback information is not abnormal.
Compared with the prior art, the invention has the beneficial effects that:
the invention generates a food safety standard table based on a food raw material proportioning table by collecting the food raw material proportioning table in advance, then collects raw material purchase order and stock information of a food processing factory, updates the stock information in real time when the stock is new, monitors the types of raw materials added in food in the food production process, alarms abnormal raw materials, monitors the proportion of each raw material type after each batch of food production is completed, alarms the abnormal proportion, finally generates tracing codes, displays the raw material types of food finished products to users, receives feedback information of the users, monitors the food quality based on the feedback information of the users, alarms the abnormal quality, thereby realizing the monitoring and tracing of all the raw material types used in the food production, ensuring the transparency of the food production and guaranteeing the food safety of the users.
Drawings
Fig. 1 is a flowchart of a data tracing method based on big data and multiple data sources in embodiment 1 of the present invention.
Detailed Description
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is obvious that the described embodiments are only some embodiments of the present invention, 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
As shown in fig. 1, a data tracing method based on big data and multiple data sources includes the following steps:
step one: the cloud server side collects a food raw material proportioning table and generates a food safety standard table based on the food raw material proportioning table;
step two: the cloud server side collects raw material purchase orders and inventory information of the food processing factory, and updates the inventory information in real time when the inventory is new;
step three: the cloud server collects food production process information of the food processing factory, analyzes whether the food production process information is abnormal, and sends a first alarm signal to a food safety supervision party if the food production process information is abnormal; if the food production process information is not abnormal, not processing;
step four: the cloud server compares the food production process information with the inventory information, generates food comparison information, analyzes whether the food comparison information is abnormal or not based on a food safety standard table, sends a second alarm signal to a food safety supervision party if the food comparison information is abnormal, and does not process if the food comparison information is not abnormal;
step five: the cloud server generates tracing codes for each batch of food, receives feedback information of a user in real time based on the tracing codes, analyzes the feedback information, sends a third alarm signal to a food safety supervision party if the feedback information is abnormal, and does not process if the feedback information is not abnormal;
in a preferred embodiment, the food ingredient ratio table is a food ingredient table stored in a cloud database of a cloud server, the food ingredient table uses a food type as a main key, and uses a raw material type and a food ingredient ratio range as attributes;
it is understood that the food composition table is based on the type of food actually produced in the food processing plant and the actual proportions of the raw materials; for example: one row of the food ingredient list can be cake, flour, 30% -40%;
the food safety standard table is generated by the following steps: the cloud server sets a proportioning upper limit and a proportioning lower limit for the raw material proportioning of each food type in the food composition table based on food safety standards to obtain a food safety standard table; the food safety standard table takes the type of food as a main key and takes the type of raw materials, the upper limit of the proportion and the lower limit of the proportion as attributes;
the raw material purchase orders are orders generated by purchasing various raw materials from various raw material factories, wherein the raw material purchase orders are electronic orders, and the raw material purchase orders are automatically uploaded to a cloud server after being generated; the raw material purchase order comprises a raw material type, an order number and a purchase quantity;
the stock information is the real-time stock quantity of each raw material; the method for obtaining the real-time stock quantity of the raw materials comprises the following steps:
presetting a stacking raw material type for each warehouse shelf for stacking raw materials; the stacking raw material type is the raw material type required to be stacked for each warehouse shelf;
a weight sensor arranged under a warehouse shelf obtains the weight of raw materials in real time, and the real-time stock quantity of the stacked raw material types corresponding to the warehouse shelf is set as the weight of the raw materials; the cloud server stores real-time inventory of each raw material type in real time as inventory information;
in order to ensure the authenticity of the stock quantity of the raw materials, when the stock is new, the mode of updating the stock information is as follows:
a first image capturing device is arranged on each warehouse goods shelf, and scans raw material codes outside raw material packages before raw materials are stacked on the warehouse goods shelves each time to obtain scanned raw material information, and the first image capturing device sends the raw material information to a cloud server end; the raw material code can be any one of a bar code and a two-dimensional code, and raw material information is stored;
the raw material information is an encrypted raw material purchase order, the encryption mode is asymmetric encryption, the private key of the secret key is held by a raw material factory, and the raw material factory for stacking raw material types encrypts the raw material purchase order by using the private key; the cloud server end decrypts the raw material information by using the public key corresponding to the raw material factory, and if the decryption is successful and the decrypted raw material purchase order is contained in the historical raw material purchase order of the food processing factory, the raw materials stacked to the warehouse shelf are correct and are not processed; if the decryption is unsuccessful or the decrypted raw material purchase order is not contained in the historical raw material purchase order of the food processing factory, the raw materials stacked on the warehouse shelf are not of the stacked raw material type, and the cloud server side sends a raw material alarm signal to the food safety supervision party; preferably, the encryption mode can be any one of RSA, DSA or ECC encryption algorithm;
the method for collecting the information of the food production process of the food processing factory is as follows:
installing a plurality of second image capturing devices at raw material input positions on the food production line, and sending captured input raw material images to a cloud server end in real time by the second image capturing devices; the raw material input position is a position on a food production line, where various types of raw materials enter the production line for food processing;
a weight sensor is arranged at a food outlet of a food production line, and the weight sensor measures the food yield in real time;
all captured raw material images and food yield as food production process information;
the method for analyzing whether the food production process information is abnormal is as follows:
the cloud server side obtains the food type according to the food production line type; the cloud server side uses a target recognition technology to recognize the type of the raw materials input into the production line in real time, obtains a raw material recognition result, searches whether the raw material recognition result is contained in the raw material type corresponding to the food type from a food raw material proportioning table, and if the raw material recognition result is not contained in the corresponding raw material type, judges that the information of the food production process is abnormal, and sends a first alarm signal to a food safety supervisor; the first alarm signal is a raw material abnormality alarm;
if the information is contained in the corresponding raw material type, judging that the food production process information is not abnormal; the raw material identification result is the raw material type identified by the target identification technology;
it should be noted that, the target recognition technology belongs to a technology commonly used in the field, by collecting several pictures of each raw material type and non-food raw materials, labeling each picture with a corresponding raw material type or non-food raw material, taking the labeled picture dataset as training data, taking the training data as training data of a CNN neural network model, and training the CNN neural network model, the CNN neural network model for recognizing the raw material type or the non-raw material type can be obtained;
the food contrast information is generated by the following modes:
after the completion of the production of the food product in each production batch, calculating the total weight of the food product yield in the batch, and marking the total weight as W; each production batch can take other production periods of one day and one week as a unit, and is specifically determined according to the requirements of a food production plant, and a batch number is set for each production batch;
counting stock quantity difference values of each raw material type before and after the batch production; each raw material type is marked as i, and the stock quantity difference of the ith raw material type is marked as Ci; if the ith raw material type is newly stocked in the batch, updating the stock quantity difference value Ci into a stock quantity difference value Ci minus the weight of the new ith raw material type, wherein the weight of the new ith raw material type is obtained by weighing the weight sensor before the new ith raw material type is stocked in advance;
calculating a production ratio Bi of the stock quantity difference Ci of each raw material type and the total weight W; the food comparison information includes a production ratio value for each raw material type;
the method for analyzing whether the food contrast information is abnormal or not is as follows:
retrieving the upper limit and the lower limit of the proportion of the ith raw material type from the food safety standard table according to the corresponding food type; if the production proportioning ratio Bi is larger than the proportioning upper limit or smaller than the proportioning lower limit, judging that the food contrast information is abnormal, and sending a second alarm signal to a food safety supervision party; the second alarm signal is a food raw material proportioning alarm; if the production ratio Bi is smaller than the upper ratio limit and larger than the lower ratio limit, judging that the food comparison information is not abnormal;
based on the tracing codes, the mode of receiving feedback information of the user in real time is as follows:
the cloud server receives a tracing request initiated by a user scanning tracing code in real time and displays a tracing result to the user; the tracing code is a two-dimensional code and comprises a batch number and a webpage address of food production, and after a user scans the tracing code, a tracing request for accessing the webpage address is generated; the tracing result is web page content corresponding to the web page address, and the web page content comprises the raw material type of the batch number and a feedback frame; the raw material types of the batch number are all raw material types which are captured by the first image capturing equipment and identified by the cloud server side in the food production process of the batch number;
the feedback information is analyzed in the following manner:
using the content filled in by the user in the feedback frame as feedback information, analyzing the emotion positive and negative of each feedback information by using a text emotion analysis technology, and if the feedback information is all, calculating a negative feedback ratio, wherein the negative feedback ratio is the ratio of the number of feedback information with emotion negative to all feedback information; if the emotion negative ratio is greater than a preset negative feedback threshold, judging that the feedback information is abnormal, and sending a third alarm signal to a food safety supervision party, wherein the third alarm signal is food quality alarm; if the emotion negative ratio is smaller than a preset negative feedback threshold, judging that the feedback information is not abnormal;
it should be noted that, the text emotion analysis technology is a relatively mature prior art, for example, an authorized Chinese word vector and aspect word vector joint embedding emotion analysis method (patent bulletin number: CN 110083833B) discloses a Chinese word vector and aspect word vector joint embedding CNN-LSTM emotion analysis model. Comprising the following steps: the word vector joint embedded representation, the word vector and the aspect word joint embedded representation, the convolution neural network integrates sentence features and aspect word features, the sentence features and the aspect word features are jointly input into the LSTM neural network, the text features are ordered by utilizing the time sequence memory function of the LSTM, an attention mechanism based on the aspect word is added, and finally the emotion category is judged by using the full connection layer and the Softmax function. Because the Chinese characters in the words have a certain characterization effect on the meaning of the words, the Chinese word vectors are combined and embedded, so that the words sharing the Chinese characters can be connected. The word vector combination in the aspect words and comments is input into the neural network for training, so that the accuracy of emotion judgment of the comment content theme can be improved.
The above embodiments are only for illustrating the technical method of the present invention and not for limiting the same, and it should be understood by those skilled in the art that the technical method of the present invention may be modified or substituted without departing from the spirit and scope of the technical method of the present invention.
Claims (10)
1. The data tracing method based on big data and multiple data sources is characterized by comprising the following steps of:
step one: the cloud server side collects a food raw material proportioning table and generates a food safety standard table based on the food raw material proportioning table;
step two: the cloud server side collects raw material purchase orders and inventory information of the food processing factory, and updates the inventory information in real time when the inventory is new;
step three: the cloud server collects food production process information of the food processing factory, analyzes whether the food production process information is abnormal, and sends a first alarm signal to a food safety supervision party if the food production process information is abnormal;
step four: the cloud server compares the food production process information with the inventory information, generates food comparison information, analyzes whether the food comparison information is abnormal based on a food safety standard table, and sends a second alarm signal to a food safety supervision party if the food comparison information is abnormal;
step five: the cloud server generates tracing codes for each batch of food, receives feedback information of a user in real time based on the tracing codes, analyzes the feedback information, and sends a third alarm signal to a food safety supervision party if the feedback information is abnormal.
2. The data tracing method based on big data and multiple data sources according to claim 1, wherein the food raw material proportioning table is a food composition table stored in a cloud database of a cloud server side, the food composition table takes a food type as a main key and takes a raw material type and a food raw material proportioning range as attributes;
the food safety standard table is generated by the following modes: the cloud server sets a proportioning upper limit and a proportioning lower limit for the raw material proportioning of each food type in the food composition table based on food safety standards to obtain a food safety standard table; the food safety standard table takes the type of food as a main key and takes the type of raw materials, the upper limit of the proportion and the lower limit of the proportion as attributes.
3. The data tracing method based on big data and multiple data sources according to claim 2, wherein the raw material purchase order is an order generated by purchasing various raw materials from each raw material factory by a food processing factory, the raw material purchase order is an electronic order, and the raw material purchase order is automatically uploaded to a cloud server after being generated; the raw material purchase order comprises a raw material type, an order number and a purchase quantity;
the stock information is the real-time stock quantity of each raw material; the method for obtaining the real-time stock quantity of the raw materials comprises the following steps:
presetting a stacking raw material type for each warehouse shelf for stacking raw materials; the stacking raw material type is the raw material type required to be stacked for each warehouse shelf;
a weight sensor arranged under a warehouse shelf obtains the weight of raw materials in real time, and the real-time stock quantity of the stacked raw material types corresponding to the warehouse shelf is set as the weight of the raw materials; the cloud service end stores real-time stock quantity of each raw material type in real time as stock information.
4. The data tracing method based on big data and multiple data sources according to claim 3, wherein when the stock is new, the way to update the stock information is:
a first image capturing device is arranged on each warehouse goods shelf, and scans raw material codes outside raw material packages before raw materials are stacked on the warehouse goods shelves each time to obtain scanned raw material information, and the first image capturing device sends the raw material information to a cloud server end; the raw material code is any one of a bar code or a two-dimensional code, and raw material information is stored;
the raw material information is an encrypted raw material purchase order, the encryption mode is asymmetric encryption, the private key of the secret key is held by a raw material factory, and the raw material factory for stacking raw material types encrypts the raw material purchase order by using the private key; the cloud server end decrypts the raw material information by using the public key corresponding to the raw material factory, and if the decryption is successful and the decrypted raw material purchase order is contained in the historical raw material purchase order of the food processing factory, the processing is not performed; if the decryption is unsuccessful or the decrypted raw material purchase order is not included in the historical raw material purchase order of the food processing plant, the cloud server side sends a raw material alarm signal to the food safety supervisor.
5. The method of claim 4, wherein the collecting information about the food production process of the food processing plant is as follows:
installing a plurality of second image capturing devices at raw material input positions on the food production line, and sending captured input raw material images to a cloud server end in real time by the second image capturing devices; the raw material input position is a position on a food production line, where various types of raw materials enter the production line for food processing;
a weight sensor is arranged at a food outlet of a food production line, and the weight sensor measures the food yield in real time;
all captured raw material images and food product yields are used as food production process information.
6. The data tracing method based on big data and multiple data sources according to claim 5, wherein the way of analyzing whether the information of the food production process has abnormality is:
the cloud server side obtains the food type according to the food production line type; the cloud server side uses a target recognition technology to recognize the type of the raw materials input into the production line in real time, obtains a raw material recognition result, searches a food raw material proportioning table to determine whether the raw material recognition result is contained in the raw material type corresponding to the food type, and judges that the information of the food production process is abnormal if the raw material recognition result is not contained in the corresponding raw material type;
if the information is contained in the corresponding raw material type, judging that the food production process information is not abnormal; the material identification result is a material type identified by a target identification technique.
7. The data tracing method based on big data and multiple data sources according to claim 6, wherein the manner of generating the food contrast information is:
after the completion of the production of the food product in each production batch, calculating the total weight of the food product yield in the batch, and marking the total weight as W;
counting stock quantity difference values of each raw material type before and after the batch production; each raw material type is marked as i, and the stock quantity difference of the ith raw material type is marked as Ci; if the ith raw material type is newly stocked in the batch, updating the stock quantity difference value Ci into a stock quantity difference value Ci minus the weight of the new ith raw material type, wherein the weight of the new ith raw material type is obtained by weighing the weight sensor before the new ith raw material type is stocked in advance;
calculating a production ratio Bi of the stock quantity difference Ci of each raw material type and the total weight W; the food comparison information includes the ratio of the production of each raw material type.
8. The data tracing method based on big data and multiple data sources according to claim 7, wherein the way of analyzing whether the food contrast information is abnormal is:
retrieving the upper limit and the lower limit of the proportion of the ith raw material type from the food safety standard table according to the corresponding food type; if the production ratio Bi is larger than the upper ratio limit or smaller than the lower ratio limit, judging that the food contrast information is abnormal; if the production ratio Bi is smaller than the upper ratio limit and larger than the lower ratio limit, judging that the food comparison information is not abnormal.
9. The data tracing method based on big data and multiple data sources according to claim 8, wherein the manner of receiving feedback information of the user in real time based on tracing codes is as follows:
the cloud server receives a tracing request initiated by a user scanning tracing code in real time and displays a tracing result to the user; the tracing code is a two-dimensional code and comprises a batch number and a webpage address of food production, and after a user scans the tracing code, a tracing request for accessing the webpage address is generated; the tracing result is web page content corresponding to the web page address, and the web page content comprises the raw material type of the batch number and a feedback frame; the raw material types of the batch number are all raw material types which are captured by the first image capturing device and identified by the cloud server side in the food production process of the batch number.
10. The data tracing method based on big data and multiple data sources according to claim 9, wherein the analysis mode of the feedback information is as follows:
using the content filled in by the user in the feedback frame as feedback information, analyzing the emotion positive and negative of each feedback information by using a text emotion analysis technology, and if the feedback information is all, calculating a negative feedback ratio, wherein the negative feedback ratio is the ratio of the number of feedback information with emotion negative to all feedback information; if the emotion negative ratio is larger than a preset negative feedback threshold, judging that the feedback information is abnormal; if the emotion negative ratio is smaller than a preset negative feedback threshold, judging that the feedback information is not abnormal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310664313.6A CN116385031A (en) | 2023-06-07 | 2023-06-07 | Data tracing method based on big data and multiple data sources |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310664313.6A CN116385031A (en) | 2023-06-07 | 2023-06-07 | Data tracing method based on big data and multiple data sources |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116385031A true CN116385031A (en) | 2023-07-04 |
Family
ID=86975491
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310664313.6A Pending CN116385031A (en) | 2023-06-07 | 2023-06-07 | Data tracing method based on big data and multiple data sources |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116385031A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117372051A (en) * | 2023-12-08 | 2024-01-09 | 龙岩市新罗区鞠翰食品有限公司 | Eight delicacies cake food processing information management system that traces to source |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106570542A (en) * | 2016-11-16 | 2017-04-19 | 深圳市裕同包装科技股份有限公司 | Food anti-counterfeiting tracing system and method based on RFID |
| CN108399506A (en) * | 2018-03-15 | 2018-08-14 | 华中农业大学 | Food security source tracing method based on industry chain (supply chain) and system |
| CN111882326A (en) * | 2020-06-20 | 2020-11-03 | 茅台学院 | Food safety monitoring traceability platform |
| CN113988881A (en) * | 2021-09-24 | 2022-01-28 | 仲恺农业工程学院 | Food quality safety tracing system and method |
| CN114066485A (en) * | 2021-11-17 | 2022-02-18 | 成都微佰特科技有限公司 | Food safety deep reinforcement traceability system and method and computer readable medium |
| CN114780943A (en) * | 2022-04-20 | 2022-07-22 | 珠海复旦创新研究院 | Food supply chain management system based on block chain and decentralization attribute password |
| CN115205042A (en) * | 2022-07-25 | 2022-10-18 | 江苏大学 | Cosmetic product tracing system based on block chain and access control and generation method |
| CN116109325A (en) * | 2023-01-05 | 2023-05-12 | 重庆云厨明视物联网科技有限公司 | Internet of things-based food safety control and tracing system and method |
-
2023
- 2023-06-07 CN CN202310664313.6A patent/CN116385031A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106570542A (en) * | 2016-11-16 | 2017-04-19 | 深圳市裕同包装科技股份有限公司 | Food anti-counterfeiting tracing system and method based on RFID |
| CN108399506A (en) * | 2018-03-15 | 2018-08-14 | 华中农业大学 | Food security source tracing method based on industry chain (supply chain) and system |
| CN111882326A (en) * | 2020-06-20 | 2020-11-03 | 茅台学院 | Food safety monitoring traceability platform |
| CN113988881A (en) * | 2021-09-24 | 2022-01-28 | 仲恺农业工程学院 | Food quality safety tracing system and method |
| CN114066485A (en) * | 2021-11-17 | 2022-02-18 | 成都微佰特科技有限公司 | Food safety deep reinforcement traceability system and method and computer readable medium |
| CN114780943A (en) * | 2022-04-20 | 2022-07-22 | 珠海复旦创新研究院 | Food supply chain management system based on block chain and decentralization attribute password |
| CN115205042A (en) * | 2022-07-25 | 2022-10-18 | 江苏大学 | Cosmetic product tracing system based on block chain and access control and generation method |
| CN116109325A (en) * | 2023-01-05 | 2023-05-12 | 重庆云厨明视物联网科技有限公司 | Internet of things-based food safety control and tracing system and method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117372051A (en) * | 2023-12-08 | 2024-01-09 | 龙岩市新罗区鞠翰食品有限公司 | Eight delicacies cake food processing information management system that traces to source |
| CN117372051B (en) * | 2023-12-08 | 2024-03-08 | 龙岩市新罗区鞠翰食品有限公司 | Eight delicacies cake food processing information management system that traces to source |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20190139441A1 (en) | Contextual training systems and methods | |
| CN109978573B (en) | Information traceability system based on block chain | |
| CN110210812B (en) | Article cold chain tracing method and system | |
| Maity et al. | Stochastic batch dispersion model to optimize traceability and enhance transparency using Blockchain | |
| CN114819862B (en) | Cold-chain logistics tracing service method, system and storage medium | |
| CN116385031A (en) | Data tracing method based on big data and multiple data sources | |
| CN103106590A (en) | Method of credible production and credible sale | |
| CN107451636A (en) | Retrospect inquiry system based on screw rod production technology | |
| US11357234B2 (en) | Food safety quality and performance monitoring system and method thereof | |
| CN115115382A (en) | Tobacco product tracing system and method based on block chain | |
| CN103530693A (en) | Risk control system and control method for movable-property pledge financing service | |
| CN112396433A (en) | Method and system for identifying false commodity comments based on behavior of person to be evaluated | |
| CN112184254A (en) | Medical instrument product traceability management system based on two-dimensional code | |
| CN114186933A (en) | Cold chain food intelligent supervision platform | |
| CN205375178U (en) | Utilize real -time quality management system of RFID to steel pipe circulation process | |
| CN114511265A (en) | Tea production circulation tracing method and system based on logistics Internet of things and block chain | |
| CN112418888A (en) | Milk powder quality safety tracing system and method based on HACCP | |
| CN116664152A (en) | Supply chain full-flow node tracing system and method | |
| CN115018433B (en) | Wine supply chain monitoring method, device, equipment and medium | |
| CN116739332A (en) | Industrial chain intelligent management method, system and medium based on big data | |
| CN113887977A (en) | Food and drug quality safety tracing method and system based on block chain technology | |
| CN115471201B (en) | Industrial chain digital collaborative supervision platform based on big data and blockchain | |
| CN111626677A (en) | Information display system, method and device | |
| CN116029594A (en) | Food quality safety monitoring system based on block chain | |
| CN115511396B (en) | Food management equipment operation monitoring method and system based on data analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230704 |
|
| RJ01 | Rejection of invention patent application after publication |