Food supply chain tracing method based on multi-source data
Through the food supply chain traceability method of multi-source data, the problem of food supply information missing or forgery caused by a single data source in the existing technology is solved, and the full monitoring and risk identification of the food supply chain are realized, and management transparency and efficiency are improved.
Patent Information
- Application Number
- CN202411130982.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-16
- Publication Date
- 2024-11-29
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing food traceability technologies mainly rely on a single data source and cannot provide a complete supply chain view, resulting in the lack or forgery of food supply information. It is difficult to monitor all links of the supply chain in real time and find potential problems.
Using a food supply chain traceability method based on multi-source data, by obtaining data from multiple data sources such as production, logistics, inventory distribution and sales, data participant determination, batch synchronization division, sub-data correlation mining analysis and abnormal problem traceability Analysis and generate distributed supply chains and abnormal warning control strategies.
It has realized the full monitoring of the food supply chain, improved food safety and quality management capabilities, identified potential risk points, clarified responsible parties, improved supply chain transparency and traceability, optimized resource allocation and operational efficiency, and ensured data consistency and accuracy. Respond to abnormal problems in a timely manner.
Smart Images

Figure CN119048113A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of food traceability management, and in particular to a food supply chain traceability method based on multi-source data. Background Art
[0002] In the modern food supply chain, food safety issues are increasingly concerned, and the complexity of the food supply chain makes it particularly important to track the entire process of food from production to consumption. Most of the existing food traceability technologies focus on data records in specific links, such as production logs on farms, production records in processing plants, or temperature control information in transportation links. In addition, in recent years, with the advancement of information technology, especially the development of big data and Internet of Things technology, the application of multi-source data has become a new direction to solve this problem. By integrating data sources from different links, such as production source data, logistics tracking source data, and sales feedback source data, a comprehensive food supply chain data network can be constructed. This integration of multi-source data can not only improve the accuracy of food traceability, but also monitor each link of the supply chain in real time, so as to discover potential problems in a timely manner. However, traditional food traceability methods mainly rely on a single data source, such as production records or logistics information. These methods often fail to provide a complete view of the supply chain, which can easily lead to the loss or falsification of food supply information. Summary of the invention
[0003] Based on this, it is necessary for the present invention to provide a food supply chain traceability method and system based on multi-source data to solve at least one of the above technical problems.
[0004] To achieve the above purpose, a food supply chain traceability method based on multi-source data includes the following steps:
[0005] Step S1: Acquire food production source data, food logistics and transportation source data, food inventory distribution source data and food sales source data, and determine food source participants and divide production batches synchronously for the food production source data, food logistics and transportation source data, food inventory distribution source data and food sales source data, to obtain different food data source participants and food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch;
[0006] Step S2: performing sub-data association mining analysis on food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch, so as to obtain the production association connection relationship between different sub-data of food sources under the same production batch; performing food supply link processing on food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch based on the production association connection relationship between different sub-data of food sources under the same production batch, so as to generate a distributed supply chain of food of the same production batch;
[0007] Step S3: Based on different food data source participants, a food supply abnormality problem tracing analysis is performed on the distributed supply chain of the same production batch of food to obtain the source of abnormality problems in the same production batch of food supply chain;
[0008] Step S4: Perform abnormal warning response control processing on the source of abnormal problems in the food supply chain of the same production batch, generate an abnormal warning control strategy for the food supply chain of the same production batch, and execute corresponding food supply chain traceability abnormal control operations.
[0009] Further, step S1 includes the following steps:
[0010] Step S11: Acquire food production source data, food logistics and transportation source data, food inventory distribution source data, and food sales source data;
[0011] Step S12: determining different food source participants for food production source data, food logistics and transportation source data, food inventory and distribution source data, and food sales source data, to obtain different food data source participants;
[0012] Step S13: Perform production batch identification analysis on the food production source data, food logistics and transportation source data, food inventory and distribution source data, and food sales source data to obtain the food production source production batch identification, food logistics and transportation source production batch identification, food inventory and distribution source production batch identification, and food sales source production batch identification;
[0013] Step S14: performing interactive mining analysis of the same production batches of different food sources on the production batch identifiers of food production sources, the production batch identifiers of food logistics and transportation sources, the production batch identifiers of food inventory and distribution sources, and the production batch identifiers of food sales sources, so as to obtain interactive connection relationships of the same production batches between different food sources;
[0014] Step S15: Based on the interactive connection relationship of the same production batch between different food sources, the food production source data, food logistics and transportation source data, food inventory distribution source data and food sales source data are synchronously divided into production batches to obtain food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch.
[0015] Further, step S14 includes the following steps:
[0016] Step S141: performing association matching analysis on the production batch identifiers of food production sources, the production batch identifiers of food logistics and transportation sources, the production batch identifiers of food inventory and distribution sources, and the production batch identifiers of food sales sources, so as to obtain the production batch association matching connection relationship between different food sources;
[0017] Step S142: establishing a correlation matrix connection for the production batch identifiers of the food production source, the production batch identifiers of the food logistics transportation source, the production batch identifiers of the food inventory distribution source, and the production batch identifiers of the food sales source based on the production batch association matching connection relationship between different food sources, so as to obtain a production batch association matrix between different food sources;
[0018] Step S143: performing a same production batch interaction pattern analysis on the production batch association matrix between different food sources to obtain the same production batch association interaction pattern between different food sources;
[0019] Step S144: Based on the same production batch association interaction pattern between different food sources, the same production batch interaction of different food sources is mined and analyzed on the food production source production batch identification, food logistics transportation source production batch identification, food inventory distribution source production batch identification and food sales source production batch identification to obtain the same production batch interaction connection relationship between different food sources.
[0020] Further, step S142 includes the following steps:
[0021] Based on the production batch association matching connection relationship between different food sources, the production batch identification of the food production source, the production batch identification of the food logistics transportation source, the production batch identification of the food inventory distribution source and the production batch identification of the food sales source are integrated and verified to obtain the production batch matching rule base between the production batch identifications of different food sources;
[0022] Performing a refined matching pattern analysis on the production batch matching rule base between production batch identifiers of different food sources, and obtaining the production batch matching pattern between production batch identifiers of different food sources;
[0023] According to the production batch matching mode between the production batch identifications of different food sources, the production batch matching connection analysis is performed between the different food sources corresponding to the production batch identifications of the food production source, the production batch identifications of the food logistics and transportation source, the production batch identifications of the food inventory and distribution source, and the production batch identifications of the food sales source, so as to construct a production batch matching connection map between different food sources;
[0024] Perform timestamp extraction processing on production batch nodes of different food sources in the production batch matching connection map between different food sources to obtain the timestamps at the production batch nodes of different food sources in the production batch matching connection map; perform pairwise comparison on the timestamps at the production batch nodes of different food sources in the production batch matching connection map. If the timestamps between a production batch node of a food source and a production batch node of another food source are in the same time period, then the matching connection relationship between the production batch nodes of the food sources is explicitly processed to generate the explicit matching connection relationship of the same production batch between different food sources; if the timestamps between a production batch node of a food source and a production batch node of another food source are not in the same time period, then the matching connection relationship between the production batch nodes of the food sources is implicitly processed to generate the implicit matching connection relationship of different production batches between different food sources;
[0025] According to the explicit connection relationship of the same production batch matching between different food sources and the implicit connection relationship of different production batch matching, the production batch matching connection map between different food sources is optimized to obtain the production batch association matrix between different food sources.
[0026] Further, step S143 includes the following steps:
[0027] Perform spatial distribution analysis on the production batch nodes of each food source in the production batch association matrix between different food sources, and obtain spatial distribution characteristic data of the production batch nodes of each food source in the production batch association matrix;
[0028] The spatial distribution characteristic data of each food source production batch node in the production batch association matrix are aggregated and analyzed in the same production batch to obtain the spatial distribution characteristic data of each food source production batch node under the same production batch;
[0029] Based on the spatial distribution characteristic data of each food source production batch node under the same production batch, the interaction path identification analysis is performed between the corresponding food source production batch nodes in the production batch association matrix between different food sources to obtain the same production batch interaction connection path between different food sources;
[0030] Perform production batch interaction change analysis between production batch nodes of each food source on the same production batch interaction connection path between different food sources to obtain production batch interaction change data between each food source node on the same production batch interaction path; perform interaction strength evaluation analysis on the same production batch interaction connection path between different food sources based on the production batch interaction change data between each food source node on the same production batch interaction path to obtain production batch interaction strength between each food source node on the same production batch interaction path;
[0031] According to the production batch interaction intensity between each food source node on the same production batch interaction path, the same production batch interaction pattern analysis is performed on the same production batch interaction connection path between different food sources to obtain the same production batch association interaction pattern between different food sources.
[0032] Further, step S2 includes the following steps:
[0033] Step S21: Perform food source node docking and interaction analysis on the food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch, and obtain production process interaction nodes of different food data sources under the same production batch, including food production source process interaction nodes, food logistics and transportation source process interaction nodes, food inventory distribution source process interaction nodes and food sales source process interaction nodes;
[0034] Step S22: performing production association mining analysis on the production process interaction nodes of different food data sources under the same production batch, so as to obtain the production association connection relationship between different sub-data of food sources under the same production batch;
[0035] Step S23: Based on the production association connection relationship between different sub-data of food sources under the same production batch, food supply link processing is performed on the food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch to generate a distributed supply chain of food under the same production batch.
[0036] Further, step S21 includes the following steps:
[0037] Determine different food source process point sets for food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch, and obtain the food production source process point set, food logistics and transportation source process point set, food inventory distribution source process point set and food sales source process point set under the same production batch;
[0038] Performing interactive screening and processing of process link docking for the food production source process point set and the food logistics transportation source process point set under the same production batch, and obtaining the food production source process interactive nodes and the food logistics transportation source process interactive nodes;
[0039] Based on the food production source process interaction nodes and the food logistics transportation source process interaction nodes, the food inventory distribution source process point set under the same production batch is subjected to cross-layer process synchronous docking interactive screening and processing to obtain the food inventory distribution source process interaction nodes;
[0040] Based on the food inventory distribution source process interaction node, the food sales source process point set under the same production batch is subjected to sales flow docking interactive screening and processing to obtain the food sales source process interaction node.
[0041] Further, step S22 includes the following steps:
[0042] Conduct production-logistics association mining analysis on the food production source process interaction nodes and the food logistics transportation source process interaction nodes to obtain the production-logistics association connection relationship between the food production source and the logistics transportation source;
[0043] Based on the food inventory distribution source process interaction node, the food production source process interaction node and the food logistics transportation source process interaction node are dynamically mined and analyzed to obtain the dynamic inventory-production logistics association connection relationship between food inventory distribution and production and logistics;
[0044] Performing inventory-sales association mining analysis on the food inventory distribution source process interaction nodes and the food sales source process interaction nodes to obtain the inventory-sales association connection relationship between the food inventory distribution source and the sales source;
[0045] The production-logistics association connection relationship between food production sources and logistics transportation sources, the dynamic inventory-production logistics association connection relationship between food inventory distribution and production and logistics, and the inventory-sales association connection relationship between food inventory distribution sources and sales sources are integrated into the same production batch to obtain the production association connection relationship between different sub-data of food sources under the same production batch.
[0046] Further, step S3 includes the following steps:
[0047] Step S31: Verify the production record changes of the corresponding food supply links on the distributed supply chain of the same production batch of food based on different food data source participants, and obtain the verification results of the production link changes of the same production batch of food supply chain;
[0048] Step S32: performing food supply change abnormality problem location processing on the verification results of the production link changes of the food supply chain of the same production batch, and obtaining the distribution locations of the production change abnormality problems of the same production batch supply chain;
[0049] Step S33: Based on the distributed supply chain of food of the same production batch, a food supply abnormality problem traceability analysis is performed on the distribution location of abnormal production change problems in the supply chain of the same production batch to obtain the traceability source of abnormal problems in the food supply chain of the same production batch.
[0050] Further, step S4 includes the following steps:
[0051] Step S41: tracing the source of abnormal problems in the food supply chain of the same production batch to determine the abnormal problem points, and obtaining the abnormal problem points in the food supply chain of the same production batch;
[0052] Step S42: performing abnormal pattern recognition analysis on abnormal problem points in the food supply chain of the same production batch to obtain abnormal patterns of food supply at each abnormal problem point;
[0053] Step S43: Based on the food supply abnormality patterns at each abnormal problem point, risk level assessment and classification are performed on the corresponding abnormal problem points in the same production batch of food supply chain to obtain the food supply abnormality risk level of each abnormal problem point;
[0054] Step S44: designing abnormal early warning responses for the abnormal risk levels of food supply at each abnormal problem point, so as to generate early warning response mechanism solutions for each abnormal risk level of food supply;
[0055] Step S45: According to the early warning response mechanism scheme of each food supply abnormality risk level, the corresponding food supply chain abnormality problem traceability of the same production batch is subjected to abnormal early warning response control processing, and the abnormal early warning control strategy of the food supply chain of the same production batch is generated to execute the corresponding food supply chain traceability abnormality control operation.
[0056] Beneficial effects of the present invention:
[0057] The food supply chain traceability method based on multi-source data proposed by the present invention, compared with the prior art, has the beneficial effect that by collecting data sources of various links such as food production, logistics transportation, inventory distribution and sales, the entire process of food from production to consumption can be fully grasped. The acquisition of such data can help to realize the whole process monitoring of the food supply chain and improve the management ability of food safety and quality. By integrating these multi-source data, potential risk points in the supply chain can be identified, and more scientific management and prevention measures can be formulated, so as to provide basic data guarantee for the subsequent processing process. In addition, by determining different food source participants for food production source data, food logistics transportation source data, food inventory distribution source data and food sales source data, the participants of various types of food source data can be determined, and the different responsible entities involved in each link can be clearly divided. This process helps to clarify the roles and responsibilities of all parties in the food supply chain, thereby improving the transparency and traceability of the supply chain. After accurately identifying each participant, the responsible party can be quickly located when abnormal food supply problems occur, effectively solving food quality problems. Further, understanding the role of each participant and its operation process can help optimize supply chain management, reduce resource waste, and improve overall operational efficiency. At the same time, by synchronously dividing the food production source data, food logistics and transportation source data, food inventory distribution source data, and food sales source data into production batches, it is helpful to systematically and structuredly manage the sub-data of each data source link. This step can achieve effective data integration and comparison by synchronously dividing the data from different production sources according to production batches. This process ensures data consistency at different stages and links, which is conducive to the implementation of refined management and analysis. The synchronized data of production batches can support more accurate supply chain optimization decisions and enhance real-time monitoring of food circulation status, thereby improving the response speed and reliability of the overall supply chain. Secondly, by conducting production association mining and analysis on food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data, and food sales sub-data under the same production batch, the main purpose of this step is to reveal the intrinsic connections and dependencies between different food data sources in the production process. Through in-depth analysis of interaction nodes, the production associations between different data sources can be identified, so as to understand how each link affects each other. This process can reveal the connection patterns of each link in the production process and help discover potential production efficiency problems and quality risks. For example, problems in a certain production link will have a chain reaction on subsequent logistics, inventory management, and sales. Mastering these production associations can help trace the corresponding production processes and improve supply chain management, thereby reducing production delays and missing or falsified food supply information caused by information asymmetry or operational errors.By processing the food supply link of food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch based on the production association connection relationship between different sub-data of food sources under the same production batch, the food production, logistics and transportation, inventory distribution and sales data under the same production batch can be integrated into a comprehensive supply chain network. This distributed supply chain not only improves the traceability and visualization of the supply chain, but also optimizes resource allocation and supply chain management, thereby providing a complete supply chain view. Specifically, this integration helps to achieve comprehensive monitoring of the entire production process, ensuring that each link can be efficiently coordinated. By generating a distributed supply chain of the same production batch, resources can be allocated more accurately, inventory backlogs and production delays can be reduced, and production scheduling can be optimized, thereby providing data support for the subsequent supply chain traceability processing process, enabling more flexible response to changes in market demand and potential food supply chain risks. Then, by conducting traceability analysis on abnormal food supply problems in the corresponding food supply links on the distributed supply chain of the same production batch of food based on different food data source participants, the root cause of the abnormal problems in the food supply chain can be traced back, thereby achieving effective solutions and prevention. The traceability analysis not only helps to determine the specific source of the abnormal problem, but also reveals potential loopholes or weaknesses in the entire supply chain. Through traceability analysis, the key links and risk points in the food production process can be identified, and targeted improvement measures can be taken. This in-depth analysis not only improves the accuracy of problem handling, but also reduces the recurrence of similar problems, thereby improving the stability and reliability of the overall supply chain. Finally, by conducting control and management of abnormal early warning responses to the source traceability of abnormal problems in the food supply chain of the same production batch, an early warning response mechanism can be designed based on the corresponding traceability response of abnormal problems in the food supply chain, and applied to actual abnormal control and management, thereby achieving effective management of abnormal problems in the food supply chain. By implementing early warning response mechanisms and control strategies, abnormal problems in the food supply chain can be responded to in a timely manner to avoid greater negative impacts on production and supply chains. This control and management helps to systematically solve abnormal problems in the food supply chain, thereby ensuring the normal operation of the supply chain and the safety of products. In addition, by establishing clear abnormal early warning control strategies, standardized operating procedures can be provided to enhance the traceability management process's response capabilities and collaborative efficiency when facing abnormal situations, thereby improving the overall food supply chain traceability management level. BRIEF DESCRIPTION OF THE DRAWINGS
[0058] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:
[0059] Figure 1 A schematic diagram of the steps of the food supply chain traceability method based on multi-source data of the present invention;
[0060] Figure 2 for Figure 1 Detailed step flow diagram of step S1;
[0061] Figure 3 for Figure 2 Detailed step flow chart of step S14 in FIG. DETAILED DESCRIPTION
[0062] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are 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 technicians in this field without creative work are within the scope of protection of the present invention.
[0063] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.
[0064] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.
[0065] To achieve this, please refer to Figures 1 to 3 The present invention provides a food supply chain traceability method based on multi-source data, the method comprising the following steps:
[0066] Step S1: Acquire food production source data, food logistics and transportation source data, food inventory distribution source data and food sales source data, and determine food source participants and divide production batches synchronously for the food production source data, food logistics and transportation source data, food inventory distribution source data and food sales source data, to obtain different food data source participants and food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch;
[0067] Step S2: performing sub-data association mining analysis on food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch, so as to obtain the production association connection relationship between different sub-data of food sources under the same production batch; performing food supply link processing on food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch based on the production association connection relationship between different sub-data of food sources under the same production batch, so as to generate a distributed supply chain of food of the same production batch;
[0068] Step S3: Based on different food data source participants, a food supply abnormality problem tracing analysis is performed on the distributed supply chain of the same production batch of food to obtain the source of abnormality problems in the same production batch of food supply chain;
[0069] Step S4: Perform abnormal warning response control processing on the source of abnormal problems in the food supply chain of the same production batch, generate an abnormal warning control strategy for the food supply chain of the same production batch, and execute corresponding food supply chain traceability abnormal control operations.
[0070] In the embodiment of the present invention, please refer to Figure 1 FIG. 1 is a schematic diagram of the steps of the food supply chain traceability method based on multi-source data of the present invention. In this example, the food supply chain traceability method based on multi-source data includes the following steps:
[0071] Step S1: Acquire food production source data, food logistics and transportation source data, food inventory distribution source data and food sales source data, and determine food source participants and divide production batches synchronously for the food production source data, food logistics and transportation source data, food inventory distribution source data and food sales source data, to obtain different food data source participants and food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch;
[0072] In an embodiment of the present invention, the original data of food production source, logistics transportation source, inventory distribution source and sales source are obtained by using a data acquisition system, and these data include production batch number, production time, transportation time, inventory information and sales record, and a database management system (such as SQL Server) is used to import these data into a data warehouse to ensure that the format and structure of the data meet the consistency requirements, and at the same time, abnormal data and missing values are processed by a data cleaning tool (such as OpenRefine) to ensure the accuracy of subsequent analysis, thereby obtaining food production source data, food logistics transportation source data, food inventory distribution source data and food sales source data. At the same time, by using a data labeling tool, the previously obtained food production source data, food logistics transportation source data, food inventory distribution source data and food sales source data are marked and determined as food data source participants, so that each data record is assigned a corresponding participant category (including producers, logistics companies, wholesalers, retailers, etc.), thereby obtaining different food data source participants. Then, by identifying and analyzing the production batches of the food production source data, food logistics and transportation source data, food inventory and distribution source data and food sales source data previously obtained from the food production source, logistics and transportation source, inventory and distribution source and sales source, the production batch situation of the corresponding data is extracted from each data source, and the production batches are synchronously divided and processed, so as to use data partitioning tools (such as Apache Hadoop) to divide each food data source into corresponding sub-data sets according to the production batches, and each sub-data set includes food production source sub-data, logistics and transportation source sub-data, inventory and distribution source sub-data and sales source sub-data under the same production batch, so as to ensure that the data under the same production batch are uniformly managed, and use data integration tools (such as ETL tools) to organize these sub-data sets into a unified data platform to ensure that all relevant data under the same batch are effectively managed and tracked, and finally the food production sub-data, food logistics and transportation sub-data, food inventory and distribution sub-data and food sales sub-data under the same production batch are obtained.
[0073] Step S2: performing sub-data association mining analysis on food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch, so as to obtain the production association connection relationship between different sub-data of food sources under the same production batch; performing food supply link processing on food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch based on the production association connection relationship between different sub-data of food sources under the same production batch, so as to generate a distributed supply chain of food of the same production batch;
[0074] In an embodiment of the present invention, by writing a query script or using a data analysis tool (such as SQL query language or data analysis platform), the food production sub-data, food logistics transportation sub-data, food inventory distribution sub-data and food sales sub-data previously screened and divided under the same production batch are identified and determined to perform process points of different food data sources, so as to identify and extract different process point sets such as production time points, logistics delivery points, inventory recording points and sales points, and by screening the process point sets of the previously identified production sources and the process point sets of the logistics transportation sources for process link docking, so as to interactively match the various links of food production with the links of logistics transportation, and confirm the corresponding interaction nodes by matching the production completion time with the logistics delivery time, so as to screen and obtain the production source process interaction nodes and the logistics transportation source process interaction nodes. At the same time, by combining the previously screened production source process interaction nodes and logistics transportation source process interaction nodes, the process point set of the inventory distribution source is screened for process synchronization, so as to use time series analysis to compare the synchronization of production completion time, logistics delivery time and inventory update records, and screen out the inventory distribution process interaction nodes that meet the synchronization standards. The sales flow situation of the process point set of the sales source is screened by combining the screened inventory distribution source process interaction nodes to evaluate and analyze the relationship between inventory distribution and sales links, so as to determine how inventory flow affects sales flow, and screen out the sales process interaction nodes related to the inventory distribution source process interaction nodes. In addition, by applying association rule mining algorithms such as Apriori algorithm or FP-Growth algorithm to the process interaction nodes of different food data sources under the same production batch, production association mining and analysis are performed. These algorithms scan the marked interaction nodes to generate frequent item sets and association rules to reveal the association connection relationship in the production process. By analyzing these association relationships, it can be determined which production links or data nodes are closely related in the entire production process, thereby obtaining the production association connection relationship between different sub-data of the food source under the same production batch.Then, by combining the production association connection relationship between different sub-data of food sources under the same production batch obtained by previous mining analysis, the supply chain management software or ERP system is used to link the corresponding food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch for food supply, so as to apply the association rule relationship to these data, thereby linking and building a supply chain network path from production to sales, and through data modeling and simulation technology, ensure that all nodes and connections accurately reflect the actual supply chain process under the same production batch. For example, if a certain food passes through a specific logistics node to reach a designated inventory location after production, and is then distributed from the inventory to the final sales point, then these nodes and their connection relationships will be recorded and optimized by the system, and the final generated distributed supply chain of food from the same production batch will show a complete distributed supply chain structure, thereby ensuring the coordination and optimization of all links in the supply chain.
[0075] Step S3: Based on different food data source participants, a food supply abnormality problem tracing analysis is performed on the distributed supply chain of the same production batch of food to obtain the source of abnormality problems in the same production batch of food supply chain;
[0076] In an embodiment of the present invention, by combining the previously determined different food data source participants (including producers, logistics companies, wholesalers and retailers, etc.), and collecting corresponding food production data, food logistics transportation status, food inventory records and food sales records from each food data source participant in real time, at the same time, by using data comparison tools (such as data comparison software or database query tools) to verify whether the records of the same production batch of food in each link of the supply chain are consistent, by comparing the timestamps, production batch numbers and product status of each food data source record, the change of the production record can be determined. If the record is inconsistent or changed, a production link change verification result is generated, and by combining the production link change verification result obtained by the previous analysis, a data analysis tool (such as data mining software or statistical analysis tool) is used to locate the abnormal problem, and by analyzing the change verification result, the change anomaly existing in the production link can be identified. For example, a threshold is set to detect the abnormality in the record. The abnormal time span or data fluctuation is not normal. When locating abnormal problems, the distribution analysis of the production links can be carried out in combination with the corresponding food supply chain to determine the specific supply chain production link location where the abnormal problem occurs, thereby identifying the specific supply chain link or geographical location where the problem exists. Then, by combining the previously constructed distributed supply chain of the same production batch of food, the traceability analysis tools (such as traceability tracking system or link analysis software) are used to trace the distribution location of the abnormal problem of the corresponding supply chain production change to trace the abnormal food supply problem, so as to establish the timeline and causal relationship model of the abnormal problem, and trace back to the source of food production that causes the abnormal risk problem. For example, the root cause of the abnormal problem can be determined by tracking the operating status of the production equipment, the supply of raw materials, the logistics and transportation operation records, the inventory distribution records and the food sales situation. The traceability results obtained can clarify the specific source of the abnormal problem in the food supply chain, and finally obtain the traceability of the abnormal problem in the same production batch of food supply chain.
[0077] Step S4: Perform abnormal warning response control processing on the source of abnormal problems in the food supply chain of the same production batch, generate an abnormal warning control strategy for the food supply chain of the same production batch, and execute corresponding food supply chain traceability abnormal control operations.
[0078] In an embodiment of the present invention, the abnormal problem points are identified and determined by tracing back the abnormal problems that occurred in the food supply chain under the same production batch previously obtained, so as to clearly point out the specific link or stage where the abnormal problem occurred in the food supply chain, that is, the time point at which the abnormal problem occurred in the food production source, logistics transportation source, inventory distribution source or sales source, and by collecting food supply information data related to the abnormal problem points of the food supply chain of the same production batch previously identified, including production environment data, food link status and supply chain records, and by using pattern recognition algorithms (such as cluster analysis, principal component analysis (PCA) or decision trees) to conduct in-depth analysis of the collected information data, so as to identify abnormal patterns at the abnormal problem points of the food supply chain. For example, if multiple abnormal problem points occur in the same food supply chain link, it indicates that there are systemic abnormalities in the food supply chain link. Failures, by establishing and training machine learning models to identify abnormal patterns, each abnormal problem point can be classified to obtain the food supply abnormal pattern of each abnormal problem point. This pattern may include the time period, frequency of occurrence and abnormal type of abnormal problems, etc., and the risk level of the corresponding abnormal problem points in the same production batch of food supply chain is evaluated by combining the food supply abnormal patterns at each abnormal problem point obtained by previous analysis with specific risk assessment standards and rules, so as to compare the abnormal pattern with the predefined risk model, and evaluate the risk level of the corresponding abnormal problem point by using quantitative indicators (such as risk frequency, scope of impact and risk severity). For example, the corresponding abnormal problem point can be graded (such as high, medium and low risk) by evaluating the risk frequency corresponding to each abnormal pattern, where the corresponding risk frequency can be calculated by the following risk frequency calculation formula, In the formula, R i (t) is the risk frequency of the ith abnormal problem point at time t, t1 is the initial time when the abnormal problem point appears, t2 is the end time when the abnormal problem point appears, α i is the basic risk value of the i-th abnormal problem point, β i is the risk index attenuation factor of the ith abnormal problem point, κ i is the occurrence frequency of the i-th abnormal problem point, δ iis the periodic fluctuation factor of the occurrence frequency of the ith abnormal problem point, and according to the calculated risk frequency, 0-20% is evaluated as a low risk level, 21%-60% is determined as a medium risk level, and 61%-100% is determined as a high risk level. Then, by designing the response of abnormal warning for the abnormal risk level of each abnormal problem point, detailed early warning response measures are formulated for each risk level based on the previous risk assessment results. For example, for high-risk abnormalities, the early warning mechanism includes an automatic alarm system, the convening of a rapid response team, and the immediate suspension and inspection of the food supply production process. For medium-risk abnormalities, the early warning mechanism includes setting alarms and strengthening monitoring, and there will be regular reports and reviews to detect potential problems earlier. For low-risk abnormalities, basic monitoring and abnormal warning adjustments are generally triggered, thereby automatically generating corresponding early warning response plans. When designing the response, it is necessary to consider the hardware configuration (such as alarms, indicator lights) and software of the early warning system. The system configures the components (such as early warning notification and recording systems) to ensure that the early warning information can be quickly conveyed to the relevant personnel and trigger the corresponding emergency measures. The early warning response plan mentioned above is used to control the abnormal early warning of the corresponding abnormal problem traceability of the same production batch of food supply chain, so as to start the relevant control operations according to the specific measures in the early warning response plan. The specific operations include immediately interrupting the relevant production line for in-depth inspection when high-risk abnormalities are found, correcting potential supply chain problems, and achieving systematic management and improvement of abnormal points in the food supply chain of the same production batch to reduce the risk of similar problems in the future and ensure the safety of the food supply chain. Finally, the control generates the corresponding abnormal early warning control strategy for the same production batch of food supply chain, which includes starting the automated control system (such as shutting down the production machine or adjusting the logistics transportation information, inventory distribution, etc.), dispatching the emergency team for on-site inspection and repair, and implementing temporary quality control measures to perform the corresponding food supply chain traceability abnormal control operations.
[0079] Further, step S1 includes the following steps:
[0080] Step S11: Acquire food production source data, food logistics and transportation source data, food inventory distribution source data, and food sales source data;
[0081] Step S12: determining different food source participants for food production source data, food logistics and transportation source data, food inventory and distribution source data, and food sales source data, to obtain different food data source participants;
[0082] Step S13: Perform production batch identification analysis on the food production source data, food logistics and transportation source data, food inventory and distribution source data, and food sales source data to obtain the food production source production batch identification, food logistics and transportation source production batch identification, food inventory and distribution source production batch identification, and food sales source production batch identification;
[0083] Step S14: performing interactive mining analysis of the same production batches of different food sources on the production batch identifiers of food production sources, the production batch identifiers of food logistics and transportation sources, the production batch identifiers of food inventory and distribution sources, and the production batch identifiers of food sales sources, so as to obtain interactive connection relationships of the same production batches between different food sources;
[0084] Step S15: Based on the interactive connection relationship of the same production batch between different food sources, the food production source data, food logistics and transportation source data, food inventory distribution source data and food sales source data are synchronously divided into production batches to obtain food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch.
[0085] As an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 Detailed step flow diagram of step S1 in FIG. 1 , in this embodiment, step S1 includes the following steps:
[0086] Step S11: Acquire food production source data, food logistics and transportation source data, food inventory distribution source data, and food sales source data;
[0087] In an embodiment of the present invention, the original data of food production source, logistics transportation source, inventory distribution source and sales source are obtained by using a data acquisition system, and these data include production batch number, production time, transportation time, inventory information and sales record, and a database management system (such as SQL Server) is used to import these data into a data warehouse to ensure that the format and structure of the data meet the consistency requirements. At the same time, data cleaning tools (such as OpenRefine) are used to process abnormal data and missing values to ensure the accuracy of subsequent analysis, and finally food production source data, food logistics transportation source data, food inventory distribution source data and food sales source data are obtained.
[0088] Step S12: determining different food source participants for food production source data, food logistics and transportation source data, food inventory and distribution source data, and food sales source data, to obtain different food data source participants;
[0089] In an embodiment of the present invention, the previously acquired food production source data, food logistics and transportation source data, food inventory distribution source data, and food sales source data are labeled and determined by using a data labeling tool to assign each data record to a corresponding participant category (including producers, logistics companies, wholesalers, retailers, etc.), and ensure that the participants of each food data source are correctly identified, ultimately obtaining different food data source participants.
[0090] Step S13: Perform production batch identification analysis on the food production source data, food logistics and transportation source data, food inventory and distribution source data, and food sales source data to obtain the food production source production batch identification, food logistics and transportation source production batch identification, food inventory and distribution source production batch identification, and food sales source production batch identification;
[0091] In an embodiment of the present invention, production batch identification and analysis are performed on food production source data, food logistics and transportation source data, food inventory distribution source data and food sales source data previously acquired from food production sources, logistics and transportation sources, inventory distribution sources and sales sources, so as to extract the production batch situation of the corresponding data from each data source, and perform production batch identification processing thereon, and finally obtain the production batch identification of the food production source, the production batch identification of the food logistics and transportation source, the production batch identification of the food inventory distribution source and the production batch identification of the food sales source.
[0092] Step S14: performing interactive mining analysis of the same production batches of different food sources on the production batch identifiers of food production sources, the production batch identifiers of food logistics and transportation sources, the production batch identifiers of food inventory and distribution sources, and the production batch identifiers of food sales sources, so as to obtain interactive connection relationships of the same production batches between different food sources;
[0093] In an embodiment of the present invention, by using a corresponding production batch association analysis tool (such as a data mining algorithm), an interactive mining analysis of the same production batch is performed between different food sources corresponding to the previously identified food production source production batch identification, food logistics transportation source production batch identification, food inventory distribution source production batch identification, and food sales source production batch identification. First, different food data sources under the same production batch are screened out, and then, by using association rule mining (such as an Apriori algorithm), the interactive connection relationship of the same batch identification in different food sources is identified, and these interactive relationships are displayed in a graphical manner to generate a production batch interactive relationship map. This map shows the interactive mode of the same production batch in different food sources, thereby ensuring that all the connection relationships between the same batches in different food data sources are clearly defined (that is, if there is an interactive connection relationship under the same production batch, it is connected with a solid line, and if there is an interactive connection relationship under different production batches, it is connected with a dotted line), and the corresponding solid line connection relationship is screened out, and finally the same production batch interactive connection relationship between different food sources is obtained.
[0094] Step S15: Based on the interactive connection relationship of the same production batch between different food sources, the food production source data, food logistics and transportation source data, food inventory distribution source data and food sales source data are synchronously divided into production batches to obtain food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch.
[0095] In an embodiment of the present invention, by combining the interactive connection relationship of the same production batch between different food sources obtained by previous mining and analysis, the corresponding food production source data, food logistics and transportation source data, food inventory distribution source data and food sales source data are synchronously divided into production batches, so as to use a data partitioning tool (such as Apache Hadoop) to divide each food data source into corresponding sub-data sets according to the production batch, and each sub-data set includes food production source sub-data, logistics and transportation source sub-data, inventory distribution source sub-data and sales source sub-data under the same production batch, so as to ensure that the data under the same production batch are uniformly managed, and use data integration tools (such as ETL tools) to organize these sub-data sets into a unified data platform, so as to ensure that all relevant data under the same batch are effectively managed and tracked, and finally the food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch are obtained.
[0096] Further, step S14 includes the following steps:
[0097] Step S141: performing association matching analysis on the production batch identifiers of food production sources, the production batch identifiers of food logistics and transportation sources, the production batch identifiers of food inventory and distribution sources, and the production batch identifiers of food sales sources, so as to obtain the production batch association matching connection relationship between different food sources;
[0098] Step S142: establishing a correlation matrix connection for the production batch identifiers of the food production source, the production batch identifiers of the food logistics transportation source, the production batch identifiers of the food inventory distribution source, and the production batch identifiers of the food sales source based on the production batch association matching connection relationship between different food sources, so as to obtain a production batch association matrix between different food sources;
[0099] Step S143: performing a same production batch interaction pattern analysis on the production batch association matrix between different food sources to obtain the same production batch association interaction pattern between different food sources;
[0100] Step S144: Based on the same production batch association interaction pattern between different food sources, the same production batch interaction of different food sources is mined and analyzed on the food production source production batch identification, food logistics transportation source production batch identification, food inventory distribution source production batch identification and food sales source production batch identification to obtain the same production batch interaction connection relationship between different food sources.
[0101] As an embodiment of the present invention, refer to Figure 3 As shown, Figure 2 Detailed step flow diagram of step S14 in the embodiment, step S14 includes the following steps:
[0102] Step S141: performing association matching analysis on the production batch identifiers of food production sources, the production batch identifiers of food logistics and transportation sources, the production batch identifiers of food inventory and distribution sources, and the production batch identifiers of food sales sources, so as to obtain the production batch association matching connection relationship between different food sources;
[0103] In an embodiment of the present invention, a data matching algorithm (such as a rule-based matching algorithm or a fuzzy matching algorithm) is used to perform association matching analysis between different food sources on the production batch identification of food production sources, the production batch identification of food logistics transportation sources, the production batch identification of food inventory distribution sources, and the production batch identification of food sales sources that have been previously identified, so as to associate and compare the production batch identifications of different food sources. The specific operation includes setting matching rules for each production batch identification, such as the same batch number, production date, and batch serial number, to determine their association relationship between different food sources, thereby storing these matching results in an association matching connection relationship database to clarify the batch association situation between different food sources, and finally obtaining the production batch association matching connection relationship between different food sources.
[0104] Step S142: establishing a correlation matrix connection for the production batch identifiers of the food production source, the production batch identifiers of the food logistics transportation source, the production batch identifiers of the food inventory distribution source, and the production batch identifiers of the food sales source based on the production batch association matching connection relationship between different food sources, so as to obtain a production batch association matrix between different food sources;
[0105] In an embodiment of the present invention, by combining the production batch association matching connection relationship between different food sources obtained by previous analysis, the connection matrix between the production batch identification of the food production source, the production batch identification of the food logistics transportation source, the production batch identification of the food inventory distribution source and the production batch identification of the food sales source is established to construct a production batch association matrix, and the production batch identification of all food sources are sorted into rows and columns of the matrix, the rows represent the production batch identification in the food production source, the logistics transportation source, the inventory distribution source and the sales source, and the columns also represent these batch identifications. Using a matrix filling tool, the matching connection relationship obtained in step S141 is filled into the corresponding position of the matrix. Specifically, each cell in the matrix will represent the association relationship between two production batch identifications. If there is a matching relationship between the two batches in different sources, the association mark is filled in the matrix (that is, connected by a solid line), otherwise, the no association mark is filled in (that is, connected by a dotted line). This matrix will show the comprehensive association of the production batches between different food sources, so that it is possible to better screen out which food sources are in the same production batch, and finally obtain the production batch association matrix between different food sources.
[0106] Step S143: performing a same production batch interaction pattern analysis on the production batch association matrix between different food sources to obtain the same production batch association interaction pattern between different food sources;
[0107] In an embodiment of the present invention, a pattern recognition algorithm (such as a frequent item set mining algorithm) is used to perform interaction pattern recognition analysis on the production batch association matrix between different food sources previously connected and constructed under the same production batch, so as to identify and analyze the interaction pattern between different food sources under the same production batch. The specific operation includes calculating the interaction frequency of each batch identifier between different food sources and identifying common interaction patterns. For example, the frequency of the flow path of a production batch from the production source to the sales source is analyzed to determine the common interaction pattern of these batches. This analysis will reveal the interaction rules of the same production batch between different food sources, and finally obtain the same production batch association interaction pattern between different food sources.
[0108] Step S144: Based on the same production batch association interaction pattern between different food sources, the same production batch interaction of different food sources is mined and analyzed on the food production source production batch identification, food logistics transportation source production batch identification, food inventory distribution source production batch identification and food sales source production batch identification to obtain the same production batch interaction connection relationship between different food sources.
[0109] In an embodiment of the present invention, by combining the same production batch association interaction pattern between different food sources obtained by previous analysis, the interaction connection mining analysis under the same production batch is performed between different food sources corresponding to the food production source production batch identification, food logistics transportation source production batch identification, food inventory distribution source production batch identification and food sales source production batch identification, so as to extract the interaction relationship between different food sources under the same production batch with each production batch identification from the interaction pattern, and use data mining tools, such as association rule learning or graph analysis tools, to deeply analyze the interaction behavior between different food sources of the same production batch, and the specific operations include establishing an interaction connection map, identifying and connecting those interaction connection relationships of the same batch in different food sources, and finally analyzing and obtaining the interaction connection relationship of the same production batch between different food sources.
[0110] Further, step S142 includes the following steps:
[0111] Based on the production batch association matching connection relationship between different food sources, the production batch identification of the food production source, the production batch identification of the food logistics transportation source, the production batch identification of the food inventory distribution source and the production batch identification of the food sales source are integrated and verified to obtain the production batch matching rule base between the production batch identifications of different food sources;
[0112] In an embodiment of the present invention, by combining the production batch association matching connection relationship between different food sources obtained by previous analysis, a data matching algorithm (such as a rule-based matching method) is used to integrate and verify the matching rules of the previously identified food production source production batch identification, food logistics transportation source production batch identification, food inventory distribution source production batch identification, and food sales source production batch identification (including production date, batch number and other related data) to integrate the matching rules of the production batch identification of each food source. The specific operation includes establishing a matching rule library, which contains batch identification matching rules between each food source, such as batch number prefix, production date comparison rules, etc. These rules are used to verify the matching relationship of production batches to ensure the consistency and accuracy of batch identification in the entire supply chain, and finally obtain a production batch matching rule library between production batch identifications of different food sources.
[0113] Preferably, a production batch matching rule base between production batch identifiers of different food sources is subjected to a refined matching pattern analysis to obtain a production batch matching pattern between production batch identifiers of different food sources;
[0114] In an embodiment of the present invention, the corresponding production batch matching rules in the production batch matching rule library between production batch identifiers of different food sources obtained through previous integration and verification are classified and screened, and a clustering algorithm, such as K-means or DBSCAN, is used to group the production batch matching rules. The grouped production batch matching rules are then subjected to matching pattern recognition and analysis by applying pattern recognition tools, such as data mining software, to identify different production batch matching patterns. These matching patterns include frequency patterns or time series patterns of the same production batch in different food sources, thereby revealing the matching rules of production batches between different food sources and providing basic data for further graph construction, and ultimately obtaining production batch matching patterns between production batch identifiers of different food sources.
[0115] Preferably, according to the production batch matching mode between the production batch identifications of different food sources, production batch matching connection analysis is performed between different food sources corresponding to the production batch identifications of food production sources, the production batch identifications of food logistics and transportation sources, the production batch identifications of food inventory and distribution sources, and the production batch identifications of food sales sources, so as to construct a production batch matching connection map between different food sources;
[0116] In an embodiment of the present invention, production batch matching connections are performed between different food sources corresponding to the production batch identifications of food production sources, food logistics and transportation sources, food inventory distribution sources, and food sales sources by combining the production batch matching patterns between the production batch identifications of different food sources obtained by previous analysis, and a graph analysis tool such as Gephi or Cytoscape is applied to visualize the production batch identification relationships between food production sources, logistics and transportation sources, inventory distribution sources, and sales sources, thereby constructing a corresponding production batch matching connection map. The specific operation includes marking the production batch identification for each food source node in the map, and connecting these nodes through edges to show the matching connection relationship between them. This map shows the batch connection status between different food sources, for example, showing the flow path of a certain production batch in the production, logistics, inventory, and sales links, and finally constructing a production batch matching connection map between different food sources.
[0117] Preferably, the timestamp extraction process is performed on the production batch nodes of different food sources in the production batch matching connection map between different food sources to obtain the timestamps at the production batch nodes of different food sources in the production batch matching connection map; the timestamps at the production batch nodes of different food sources in the production batch matching connection map are compared pairwise, and if the timestamps between a production batch node of a food source and a production batch node of another food source are in the same time period, the matching connection relationship between the production batch nodes of the food sources is explicitly processed to generate the same production batch matching explicit connection relationship between different food sources; if the timestamps between a production batch node of a food source and a production batch node of another food source are not in the same time period, the matching connection relationship between the production batch nodes of the food sources is implicitly processed to generate different production batch matching implicit connection relationships between different food sources;
[0118] In an embodiment of the present invention, timestamp information is extracted from different food source production batch nodes in the production batch matching connection map between different food sources constructed previously to record the processing time of each production batch on different food source nodes, thereby obtaining the timestamps at different food source production batch nodes in the production batch matching connection map. At the same time, the timestamps at different food source production batch nodes in the production batch matching connection map are paired and compared by using a timestamp comparison tool. The specific operation includes writing a time series analysis script to compare the timestamps of each pair of food source production batches. If the timestamps are in the same time period, the matching relationship between the pair of food source production batch nodes is explicitly processed (that is, connected with a solid line), thereby generating the same production batch matching explicit connection relationship between different food sources; and if the timestamps are in different time periods, the matching relationship is implicitly processed (that is, connected with a dotted line), and finally generating different production batch matching implicit connection relationships between different food sources. This process ensures that in practical applications, it is possible to clearly distinguish which food source production batch nodes are under the same production batch.
[0119] Preferably, the production batch matching connection graph between different food sources is optimized according to the explicit connection relationship of the same production batch matching between different food sources and the implicit connection relationship of different production batch matching, so as to obtain the production batch association matrix between different food sources.
[0120] In an embodiment of the present invention, the production batch matching mapping optimization is performed on the corresponding connection relationships in the production batch matching connection graph between different food sources by combining the explicit connection relationships of the same production batch matching between different food sources obtained in the previous processing and the implicit connection relationships of different production batch matching, so that the food source production batch nodes with corresponding explicit connection relationships in the graph are connected with solid lines, while the food source production batch nodes with implicit connection relationships are connected with dotted lines. Finally, the connection optimization obtains the production batch association matrix between different food sources, so that it can better reflect the production batch association situation between different food sources.
[0121] Further, step S143 includes the following steps:
[0122] Perform spatial distribution analysis on the production batch nodes of each food source in the production batch association matrix between different food sources, and obtain spatial distribution characteristic data of the production batch nodes of each food source in the production batch association matrix;
[0123] In an embodiment of the present invention, a spatial distribution statistical analysis method (such as spatial autocorrelation analysis (Moran's I) and hot spot analysis (Getis-Ord Gi*)) is used to perform spatial distribution identification analysis on the production batch nodes of each food source in the production batch association matrix between different food sources previously mapped and constructed, so as to identify the distribution characteristics of each food source production batch node in the geographic space. These analyses can reveal the concentrated areas or dispersion trends of the production batch nodes, for example, by displaying the distribution density of different food sources in the geographic space through a heat map, and finally obtaining the spatial distribution characteristic data of the production batch nodes of each food source in the production batch association matrix.
[0124] Preferably, the spatial distribution characteristic data of each food source production batch node in the production batch association matrix are subjected to the same production batch aggregation analysis to obtain the spatial distribution characteristic data of each food source production batch node under the same production batch;
[0125] In an embodiment of the present invention, by using a spatial clustering analysis method, such as K-means clustering or DBSCAN, the spatial distribution characteristic data of each food source production batch node in the production batch association matrix obtained by the previous analysis are clustered for the same production batch, so as to classify and summarize the spatial distribution characteristic data of each production batch, and cluster all the nodes of the same production batch together to form a comprehensive data set. For example, the corresponding clustering method is used to determine which production batch nodes' spatial distribution characteristic data are the distribution patterns or clusters under the same production batch, thereby forming a comprehensive spatial characteristic description of the same batch, and finally obtaining the spatial distribution characteristic data of each food source production batch node under the same production batch.
[0126] Preferably, based on the spatial distribution characteristic data of the production batch nodes of each food source under the same production batch, the interactive path identification analysis is performed between the corresponding food source production batch nodes in the production batch association matrix between different food sources to obtain the same production batch interactive connection path between different food sources;
[0127] In an embodiment of the present invention, the spatial interaction paths are identified, planned and analyzed between the corresponding food source production batch nodes in the production batch association matrix between different food sources previously mapped and constructed by combining the spatial distribution feature data of the production batch nodes of each food source under the same production batch obtained by previous clustering, so as to analyze the connection status of the production batch nodes of each food source under the same production batch, and by constructing a network model and applying a graph algorithm, such as a shortest path algorithm or a network flow analysis, the interaction paths between different food sources are identified and planned. The specific operation includes converting the spatial distribution feature data into network space position nodes, and the edges between the nodes represent the interaction relationship between different food sources under the same production batch. For example, the shortest path is calculated by the Dijkstra algorithm to obtain the optimal interaction path between each food source node, and the key connection path from production to sales is identified, so as to finally obtain the same production batch interaction connection path between different food sources.
[0128] Preferably, the production batch interaction change analysis is performed between the production batch nodes of each food source on the same production batch interaction connection path between different food sources to obtain the production batch interaction change data between the various food source nodes on the same production batch interaction path; based on the production batch interaction change data between the various food source nodes on the same production batch interaction path, the interaction strength evaluation analysis is performed on the same production batch interaction connection path between different food sources to obtain the production batch interaction strength between the various food source nodes on the same production batch interaction path;
[0129] In an embodiment of the present invention, by collecting food source dynamic change data from each food source production batch node on the same production batch interactive connection path between different food sources previously planned, including production quantity, transportation time, inventory changes and sales, and using statistical analysis tools, such as data analysis libraries in R or Python, time series analysis is performed on these data to evaluate the interactive changes between production batch nodes at different time points, thereby obtaining production batch interactive change data between each food source node on the same production batch interactive path, and these change data will be used to analyze the stability and change trend of production batches on the interactive path. Further, by combining the production batch interactive change data between each food source node on the same production batch interactive path obtained by previous analysis, the interaction strength between the corresponding food source production batch nodes on the same production batch interactive connection path between different food sources is evaluated and calculated, so as to evaluate and calculate the interaction strength between each production batch node. For example, the corresponding interaction strength can be evaluated and calculated by the above calculation formula: In the formula, I jkis the production batch interaction intensity between food source production batch nodes j and k, T is the total time length of production batch interaction, τ is the integral time variable parameter, θ jk is the initial amount of production batch interaction change between food source production batch nodes j and k, η jk is the time decay factor of the interaction strength between food source production batch nodes j and k, ε jk is the interaction lag between food source production batch nodes j and k, γ jk is the sinusoidal influence parameter of the interaction intensity between food source production batch nodes j and k, ξ jk is the sinusoidal change influence rate of the interaction intensity between food source production batch nodes j and k, so the interaction intensity value between any two production batch nodes is evaluated and calculated through the above formula, and finally the production batch interaction intensity between each food source node on the same production batch interaction path is obtained.
[0130] Preferably, the same production batch interaction pattern analysis is performed on the same production batch interaction connection path between different food sources according to the production batch interaction intensity between each food source node on the same production batch interaction path to obtain the same production batch association interaction pattern between different food sources.
[0131] In an embodiment of the present invention, by combining the production batch interaction strength between each food source node on the same production batch interaction path obtained by previous quantitative calculation, a preset interaction strength threshold is used to compare and judge between each food source production batch node on the same production batch interaction connection path between different food sources. If the production batch interaction strength is greater than or equal to the preset interaction strength threshold, it means that there is a production interaction association relationship between any two corresponding food source production batch nodes, and if it is less than, it is considered that there is no production interaction association relationship. The interaction pattern of the production interaction association relationship between the food source production batch nodes previously screened out is identified and analyzed by using a pattern recognition method, so as to analyze and reveal the interaction patterns of different food sources under the same production batch, and identify the association patterns and laws between different food sources. These analysis results will help understand the collaboration mode and interaction relationship of different food sources in the same batch production process, and finally obtain the same production batch association interaction pattern between different food sources.
[0132] Further, step S2 includes the following steps:
[0133] Step S21: Perform food source node docking and interaction analysis on the food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch, and obtain production process interaction nodes of different food data sources under the same production batch, including food production source process interaction nodes, food logistics and transportation source process interaction nodes, food inventory distribution source process interaction nodes and food sales source process interaction nodes;
[0134] In an embodiment of the present invention, by writing a query script or using a data analysis tool (such as SQL query language or data analysis platform), the food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data previously screened and divided under the same production batch are identified and determined to identify and extract different process point sets such as production time points, logistics delivery points, inventory recording points and sales points, and by using a process mapping tool, the process point set of the previously identified production source and the process point set of the logistics and transportation source are screened for docking and interactive matching of the process links, so as to dock and interactively match each link of food production with the link of logistics and transportation, and confirm the corresponding interaction nodes by matching the production completion time with the logistics delivery time, thereby screening out the food production source process interaction nodes and the food logistics and transportation source process interaction nodes. At the same time, by combining the previously screened food production source process interaction nodes and food logistics transportation source process interaction nodes, the process point set of the inventory distribution source is interactively screened for process synchronization, so as to use time series analysis to compare the synchronization of production completion time, logistics delivery time and inventory update records, and screen out the inventory distribution process interaction nodes that meet the synchronization standards, so as to screen out the food inventory distribution source process interaction nodes that match the corresponding production source and logistics transportation source processes. In addition, by combining the screened food inventory distribution source process interaction nodes, the process point set of the sales source is interactively screened for sales flow, so as to evaluate and analyze the relationship between inventory distribution and sales links, determine how inventory flow affects sales flow, and screen out the sales flow docking points related to the inventory distribution source process interaction nodes, so as to screen out the food sales source process interaction nodes, and finally obtain the production process interaction nodes of different food data sources under the same production batch by integrating the process interaction nodes screened above.
[0135] Step S22: performing production association mining analysis on the production process interaction nodes of different food data sources under the same production batch, so as to obtain the production association connection relationship between different sub-data of food sources under the same production batch;
[0136] In an embodiment of the present invention, production association mining analysis is performed by applying association rule mining algorithms such as the Apriori algorithm or the FP-Growth algorithm to the production process interaction nodes of different food data sources under the same production batch. These algorithms generate frequent item sets and association rules by scanning the marked interaction nodes to reveal the associated connection relationships in the production process. For example, if a certain production batch of food has corresponding delay records in the production and logistics stages, the connection relationship between these nodes will be identified. By analyzing these association relationships, it can be determined which production links or data nodes are closely related in the entire production process, and finally the production associated connection relationship between different sub-data of food sources under the same production batch is obtained.
[0137] Step S23: Based on the production association connection relationship between different sub-data of food sources under the same production batch, food supply link processing is performed on the food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch to generate a distributed supply chain of food under the same production batch.
[0138] In an embodiment of the present invention, by combining the production association connection relationship between different sub-data of food sources under the same production batch obtained by previous mining analysis, the corresponding food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch are processed by linking the food supply using supply chain management software or ERP system, so as to apply the association rule relationship to these data, thereby linking and building a supply chain network path from production to sales, and through data modeling and simulation technology, ensuring that all nodes and connections accurately reflect the actual supply chain process under the same production batch. For example, if a certain food passes through a specific logistics node to reach a designated inventory location after production, and is then distributed from the inventory to the final sales point, then these nodes and their connection relationships will be recorded and optimized by the system, and the distributed supply chain of food from the same production batch finally generated will show a complete distributed supply chain structure, thereby ensuring the coordination and optimization of each link of the supply chain.
[0139] Further, step S21 includes the following steps:
[0140] Determine different food source process point sets for food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch, and obtain the food production source process point set, food logistics and transportation source process point set, food inventory distribution source process point set and food sales source process point set under the same production batch;
[0141] In an embodiment of the present invention, by writing a query script or using a data analysis tool (such as SQL query language or data analysis platform), the process points of different food data sources are identified and determined for the food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch that were previously screened and divided, so as to identify and extract different production time points, logistics delivery points, inventory recording points and sales points, and finally obtain the food production source process point set, food logistics and transportation source process point set, food inventory distribution source process point set and food sales source process point set under the same production batch.
[0142] Preferably, the food production source process point set and the food logistics transportation source process point set under the same production batch are subjected to process link docking interactive screening processing to obtain food production source process interactive nodes and food logistics transportation source process interactive nodes;
[0143] In an embodiment of the present invention, a process mapping tool is used to perform docking, interactive matching and screening processing on the food production source process point set and the food logistics transportation source process point set under the same production batch that have been previously identified, so as to interactively match the various links of food production with the links of logistics transportation. The specific operation includes identifying the time and data consistency between the production link and the logistics link. For example, the corresponding interaction node is confirmed by matching the production completion time with the logistics delivery time, thereby screening out the successfully matched link interaction matching nodes, and finally obtaining the food production source process interaction node and the food logistics transportation source process interaction node.
[0144] Preferably, based on the food production source process interaction node and the food logistics transportation source process interaction node, the food inventory distribution source process point set under the same production batch is subjected to cross-layer process synchronous docking interactive screening processing to obtain the food inventory distribution source process interaction node;
[0145] In an embodiment of the present invention, by combining the food production source process interaction nodes and food logistics transportation source process interaction nodes corresponding to the previously determined food production source and logistics transportation source as input, the food inventory distribution source process point set under the same production batch is subjected to process synchronization docking and interactive screening, and the impact of the corresponding production and logistics links on inventory distribution is analyzed. By establishing a cross-layer data model, it is detected whether the interaction between the production and logistics links is synchronized in the inventory distribution. For example, time series analysis is used to compare the synchronization of production completion time, logistics delivery time and inventory update records, and the inventory distribution process interaction nodes that meet the synchronization standards are screened out, and finally the food inventory distribution source process interaction nodes with a higher match with the corresponding production source and logistics transportation source processes are screened out.
[0146] Preferably, based on the food inventory distribution source process interaction node, the food sales source process point set under the same production batch is subjected to sales flow docking interactive screening processing to obtain the food sales source process interaction node.
[0147] In an embodiment of the present invention, the sales flow situation of the corresponding food sales source process point set under the same production batch is docked and interactively screened by combining the previously determined food inventory distribution source process interaction node to evaluate and analyze the relationship between inventory distribution and sales links. The specific operation includes comparing the inventory distribution records with the sales data to determine how inventory flow affects sales flow. For example, by setting a threshold to screen the time and quantity match between the inventory distribution records and the sales records, the sales flow docking points related to the inventory distribution source process interaction node are screened out, and finally the food sales source process interaction node is screened out.
[0148] Further, step S22 includes the following steps:
[0149] Conduct production-logistics association mining analysis on the food production source process interaction nodes and the food logistics transportation source process interaction nodes to obtain the production-logistics association connection relationship between the food production source and the logistics transportation source;
[0150] In an embodiment of the present invention, relevant data are extracted from the data systems of food production sources and logistics transportation sources corresponding to previously determined food production source process interaction nodes and food logistics transportation source process interaction nodes, including production records, production process nodes, logistics scheduling records and transportation routes, and these data are analyzed by applying an association analysis algorithm, such as an association rule mining algorithm (Apriori or FP-Growth). The specific steps include matching the data of the production process nodes with the data of the logistics transportation nodes, identifying the connection points between the production links and the logistics links, and finally obtaining the production-logistics association connection relationship between the food production source and the logistics transportation source. This connection relationship can show the specific connection between the production source and the logistics transportation source, such as the correspondence between the production start time and the logistics delivery time.
[0151] Preferably, based on the food inventory distribution source process interaction node, the food production source process interaction node and the food logistics transportation source process interaction node are subjected to dynamic inventory association mining analysis to obtain the dynamic inventory-production logistics association connection relationship between food inventory distribution and production and logistics;
[0152] In an embodiment of the present invention, corresponding food inventory data is extracted from a food inventory management system in combination with a food inventory distribution source process interaction node, and analyzed in combination with data from a production source process interaction node and a logistics transportation source process interaction node, so that inventory changes are compared with production and logistics data by utilizing a dynamic inventory management tool or dynamic data association analysis software, and association analysis is performed with production data and logistics data through real-time updated inventory data, thereby revealing how inventory changes affect production and logistics links, and ultimately analyzing the dynamic inventory-production logistics association connection relationship between food inventory distribution and production and logistics, which can display the real-time connection between inventory changes and production activities and logistics scheduling.
[0153] Preferably, the food inventory distribution source process interaction node and the food sales source process interaction node are subjected to inventory-sales association mining analysis to obtain the inventory-sales association connection relationship between the food inventory distribution source and the sales source;
[0154] In an embodiment of the present invention, inventory and sales data are extracted from the data systems of food inventory distribution sources and sales sources corresponding to previously determined food inventory distribution source process interaction nodes and food sales source process interaction nodes, and inventory data and sales data are compared by applying inventory-sales association analysis tools. At the same time, by utilizing data mining techniques, such as time series analysis or regression analysis, the association relationship between inventory and sales volume is determined. For example, how changes in inventory levels affect sales trends is analyzed, and the connection between sales peaks and inventory changes is identified, and finally the inventory-sales association connection relationship between the food inventory distribution source and the sales source is obtained. This connection relationship can reflect the specific interaction pattern between the inventory distribution source and the sales source.
[0155] Preferably, the production-logistics association connection relationship between the food production source and the logistics transportation source, the dynamic inventory-production logistics association connection relationship between food inventory distribution and production and logistics, and the inventory-sales association connection relationship between the food inventory distribution source and the sales source are integrated into the same production batch to obtain the production association connection relationship between different sub-data of food sources under the same production batch.
[0156] In an embodiment of the present invention, the production-logistics association connection relationship between the food production source and the logistics transportation source, the dynamic inventory-production logistics association connection relationship between food inventory distribution and production and logistics, and the inventory-sales association connection relationship between the food inventory distribution source and the sales source obtained by the previous mining and analysis are comprehensively integrated and processed, so that by using a data integration tool, the production-logistics association connection relationship, the dynamic inventory-production logistics association connection relationship and the inventory-sales association connection relationship are integrated into a unified production association connection relationship, so that the association relationship between different sub-data under the same production batch can be integrated, and finally the production association connection relationship between different sub-data of the food source under the same production batch is obtained. This production association connection relationship integrates the data association relationship between food production, logistics, inventory and sales, so that the complete production chain under the same production batch can be displayed.
[0157] Further, step S3 includes the following steps:
[0158] Step S31: Verify the production record changes of the corresponding food supply links on the distributed supply chain of the same production batch of food based on different food data source participants, and obtain the verification results of the production link changes of the same production batch of food supply chain;
[0159] In an embodiment of the present invention, by combining the different food data source participants (including producers, logistics companies, wholesalers and retailers, etc.) previously determined, and collecting corresponding food production data, food logistics transportation status, food inventory records and food sales records and other data from each food data source participant in real time, at the same time, by using data comparison tools (such as data comparison software or database query tools) to verify whether the records of the same production batch of food in each link of the supply chain are consistent, by comparing the timestamps, production batch numbers and product status of each food data source record, the changes in the production records can be determined. If the records are inconsistent or changed, the production link change verification result is generated, so as to point out the specific link where the food supply data is abnormal, and finally obtain the production link change verification result of the same production batch of food supply chain.
[0160] Step S32: performing food supply change abnormality problem location processing on the verification results of the production link changes of the food supply chain of the same production batch, and obtaining the distribution locations of the production change abnormality problems of the same production batch supply chain;
[0161] In an embodiment of the present invention, abnormal problems are located by using data analysis tools (such as data mining software or statistical analysis tools) in combination with the verification results of changes in the production links of the food supply chain of the same production batch obtained by previous analysis. The change verification results are analyzed to identify the abnormal changes in the production links. For example, a threshold is set to detect the abnormal time span or data fluctuation in the record. When locating abnormal problems, the distribution analysis of the production links can be performed in combination with the corresponding food supply chain to determine the specific supply chain production link location where the abnormal problem occurs, thereby identifying the specific supply chain link or geographical location where the problem occurs, and finally obtaining the distribution location of the abnormal problem of production changes in the same production batch supply chain.
[0162] Step S33: Based on the distributed supply chain of food of the same production batch, a food supply abnormality problem traceability analysis is performed on the distribution location of abnormal production change problems in the supply chain of the same production batch to obtain the traceability source of abnormal problems in the food supply chain of the same production batch.
[0163] In an embodiment of the present invention, by combining the previously constructed distributed supply chain of food of the same production batch, a traceability analysis tool (such as a traceability tracking system or link analysis software) is used to trace the distribution location of abnormal problems in production changes in the corresponding supply chain of the same production batch to trace the abnormal food supply problem, so as to establish a timeline and causal relationship model of the abnormal problem to trace back to the source of food production that causes abnormal risk problems. For example, the root cause of the abnormal problem can be determined by tracking the operating status of the production equipment, the supply of raw materials, the logistics and transportation operation records, the inventory distribution records, and the food sales situation. The traceability results obtained can clarify the specific source of the abnormal problem in the food supply chain, and finally obtain the traceability of the abnormal problem in the same production batch of food supply chain.
[0164] Further, step S4 includes the following steps:
[0165] Step S41: tracing the source of abnormal problems in the food supply chain of the same production batch to determine the abnormal problem points, and obtaining the abnormal problem points in the food supply chain of the same production batch;
[0166] In an embodiment of the present invention, the abnormal problem points are identified and determined by tracing the source of abnormal problems that occurred in the food supply chain under the same production batch previously obtained, so as to clearly point out the specific link or stage where the abnormal problem occurred in the food supply chain, that is, the time point when the abnormal problem occurred in the food production source, logistics transportation source, inventory distribution source or sales source, and finally the abnormal problem points of the food supply chain of the same production batch are obtained.
[0167] Step S42: performing abnormal pattern recognition analysis on abnormal problem points in the food supply chain of the same production batch to obtain abnormal patterns of food supply at each abnormal problem point;
[0168] In an embodiment of the present invention, food supply information data related to abnormal problem points in the food supply chain of the same production batch previously identified, including production environment data, food link status and supply chain records, is collected, and the collected information data is deeply analyzed by using a pattern recognition algorithm (such as cluster analysis, principal component analysis (PCA) or decision tree) to identify abnormal patterns at abnormal problem points in the food supply chain. For example, if multiple abnormal problem points occur in the same food supply chain link, it indicates that there is a systemic abnormal failure in the food supply chain link. By establishing and training a machine learning model to identify abnormal patterns, each abnormal problem point can be classified to obtain a food supply abnormality pattern for each abnormal problem point. This pattern may include the time period, frequency and type of abnormality, etc., and finally the food supply abnormality pattern at each abnormal problem point is obtained.
[0169] Step S43: Based on the food supply abnormality patterns at each abnormal problem point, risk level assessment and classification are performed on the corresponding abnormal problem points in the same production batch of food supply chain to obtain the food supply abnormality risk level of each abnormal problem point;
[0170] In an embodiment of the present invention, the risk level of the corresponding abnormal problem points in the same production batch of food supply chain is evaluated by combining the food supply abnormality patterns at each abnormal problem point obtained by previous analysis with specific risk assessment standards and rules, so as to compare the abnormal pattern with the predefined risk model, and evaluate the risk level of the corresponding abnormal problem point by using quantitative indicators (such as risk frequency, impact range and risk severity). For example, the corresponding abnormal problem point can be graded (such as high, medium and low risk) by evaluating the risk frequency corresponding to each abnormal pattern, wherein the corresponding risk frequency can be calculated by the following risk frequency calculation formula: In the formula, R i (t) is the risk frequency of the ith abnormal problem point at time t, t1 is the initial time when the abnormal problem point appears, t2 is the end time when the abnormal problem point appears, α i is the basic risk value of the i-th abnormal problem point, β i is the risk index attenuation factor of the ith abnormal problem point, κ i is the occurrence frequency of the i-th abnormal problem point, δ iis the periodic fluctuation factor of the occurrence frequency of the ith abnormal problem point, and according to the calculated risk frequency, 0% to 20% is evaluated as a low risk level, 21% to 60% is determined as a medium risk level, and 61% to 100% is determined as a high risk level, thereby ensuring the accuracy and consistency of the risk level, and finally obtaining the abnormal risk level of food supply for each abnormal problem point.
[0171] Step S44: designing abnormal early warning responses for the abnormal risk levels of food supply at each abnormal problem point, so as to generate early warning response mechanism solutions for each abnormal risk level of food supply;
[0172] In an embodiment of the present invention, the response design of abnormal warning is performed by combining the food supply abnormal risk level of each abnormal problem point previously determined, so as to formulate detailed early warning response measures for each risk level according to the previous risk assessment results. For example, for high-risk level abnormalities, the early warning mechanism includes an automatic alarm system, the convening of a rapid response team, and the immediate suspension and inspection of the food supply production process. For medium-risk level abnormalities, the early warning mechanism includes setting alarms and strengthening monitoring, and there will be regular reports and reviews to detect potential problems earlier. For low-risk level abnormalities, basic monitoring and abnormal early warning adjustments are generally triggered. This step automatically generates corresponding early warning response plans based on real-time data and risk levels by using early warning models and rule engines. When designing the response, it is necessary to consider the hardware configuration (such as alarms, indicator lights) and software configuration (such as early warning notifications and recording systems) of the early warning system, so as to ensure that the early warning information can be quickly conveyed to relevant personnel and trigger corresponding emergency measures. Finally, early warning response mechanism plans for each food supply abnormal risk level are designed and generated.
[0173] Step S45: According to the early warning response mechanism scheme of each food supply abnormality risk level, the corresponding food supply chain abnormality problem traceability of the same production batch is subjected to abnormal early warning response control processing, and the abnormal early warning control strategy of the food supply chain of the same production batch is generated to execute the corresponding food supply chain traceability abnormality control operation.
[0174] In an embodiment of the present invention, by combining the early warning response mechanism scheme of each food supply abnormality risk level generated by the previous response, the corresponding food supply chain abnormal problem traceability of the same production batch is controlled and processed for abnormal early warning, so as to start the relevant control operations according to the specific measures in the early warning response scheme. The specific operations include immediately interrupting the relevant production line for in-depth inspection when a high-risk abnormality is found, correcting potential supply chain problems, and achieving systematic management and improvement of abnormal points in the food supply chain of the same production batch to reduce the risk of similar problems in the future and ensure the safety of the food supply chain. Finally, the corresponding food supply chain abnormality early warning control strategy for the same production batch is generated, which includes starting the automated control system (such as shutting down the production machine or adjusting the logistics transportation information, inventory distribution, etc.), dispatching the emergency team for on-site inspection and repair, and implementing temporary quality control measures to perform the corresponding food supply chain traceability abnormality control operations.
[0175] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.
[0176] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.
Claims
1. A food supply chain traceability method based on multi-source data, characterized in that: The following steps are involved: Step S1: Acquire food production source data, food logistics and transportation source data, food inventory distribution source data and food sales source data, and determine food source participants and divide production batches synchronously for the food production source data, food logistics and transportation source data, food inventory distribution source data and food sales source data, to obtain different food data source participants and food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch; Step S2: performing sub-data association mining analysis on food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch, so as to obtain the production association connection relationship between different sub-data of food sources under the same production batch; performing food supply link processing on food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch based on the production association connection relationship between different sub-data of food sources under the same production batch, so as to generate a distributed supply chain of food of the same production batch; Step S3: Based on different food data source participants, a food supply abnormality problem tracing analysis is performed on the distributed supply chain of the same production batch of food to obtain the source of abnormality problems in the same production batch of food supply chain; Step S4: Perform abnormal warning response control processing on the source of abnormal problems in the food supply chain of the same production batch, generate an abnormal warning control strategy for the food supply chain of the same production batch, and execute corresponding food supply chain traceability abnormal control operations.
2. The food supply chain traceability method based on multi-source data according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: Acquire food production source data, food logistics and transportation source data, food inventory distribution source data, and food sales source data; Step S12: determining different food source participants for food production source data, food logistics and transportation source data, food inventory and distribution source data, and food sales source data, to obtain different food data source participants; Step S13: Perform production batch identification analysis on the food production source data, food logistics and transportation source data, food inventory and distribution source data, and food sales source data to obtain the food production source production batch identification, food logistics and transportation source production batch identification, food inventory and distribution source production batch identification, and food sales source production batch identification; Step S14: performing interactive mining analysis of the same production batches of different food sources on the production batch identifiers of food production sources, the production batch identifiers of food logistics and transportation sources, the production batch identifiers of food inventory and distribution sources, and the production batch identifiers of food sales sources, so as to obtain interactive connection relationships of the same production batches between different food sources; Step S15: Based on the interactive connection relationship of the same production batch between different food sources, the food production source data, food logistics and transportation source data, food inventory distribution source data and food sales source data are synchronously divided into production batches to obtain food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch.
3. The food supply chain traceability method based on multi-source data according to claim 2 is characterized in that: Step S14 includes the following steps: Step S141: performing association matching analysis on the production batch identifiers of food production sources, the production batch identifiers of food logistics and transportation sources, the production batch identifiers of food inventory and distribution sources, and the production batch identifiers of food sales sources, so as to obtain the production batch association matching connection relationship between different food sources; Step S142: establishing a correlation matrix connection for the production batch identifiers of the food production source, the production batch identifiers of the food logistics transportation source, the production batch identifiers of the food inventory distribution source, and the production batch identifiers of the food sales source based on the production batch association matching connection relationship between different food sources, so as to obtain a production batch association matrix between different food sources; Step S143: performing a same production batch interaction pattern analysis on the production batch association matrix between different food sources to obtain the same production batch association interaction pattern between different food sources; Step S144: Based on the same production batch association interaction pattern between different food sources, the same production batch interaction of different food sources is mined and analyzed on the food production source production batch identification, food logistics transportation source production batch identification, food inventory distribution source production batch identification and food sales source production batch identification to obtain the same production batch interaction connection relationship between different food sources.
4. The food supply chain traceability method based on multi-source data according to claim 3 is characterized in that: Step S142 includes the following steps: Based on the production batch association matching connection relationship between different food sources, the production batch identification of the food production source, the production batch identification of the food logistics transportation source, the production batch identification of the food inventory distribution source and the production batch identification of the food sales source are integrated and verified to obtain the production batch matching rule base between the production batch identifications of different food sources; Performing a refined matching pattern analysis on the production batch matching rule base between production batch identifiers of different food sources, and obtaining the production batch matching pattern between production batch identifiers of different food sources; According to the production batch matching mode between the production batch identifications of different food sources, the production batch matching connection analysis is performed between the different food sources corresponding to the production batch identifications of the food production source, the production batch identifications of the food logistics and transportation source, the production batch identifications of the food inventory and distribution source, and the production batch identifications of the food sales source, so as to construct a production batch matching connection map between different food sources; Perform timestamp extraction processing on production batch nodes of different food sources in the production batch matching connection map between different food sources to obtain the timestamps at the production batch nodes of different food sources in the production batch matching connection map; perform pairwise comparison on the timestamps at the production batch nodes of different food sources in the production batch matching connection map. If the timestamps between a production batch node of a food source and a production batch node of another food source are in the same time period, then the matching connection relationship between the production batch nodes of the food sources is explicitly processed to generate the explicit matching connection relationship of the same production batch between different food sources; if the timestamps between a production batch node of a food source and a production batch node of another food source are not in the same time period, then the matching connection relationship between the production batch nodes of the food sources is implicitly processed to generate the implicit matching connection relationship of different production batches between different food sources; According to the explicit connection relationship of the same production batch matching between different food sources and the implicit connection relationship of different production batch matching, the production batch matching connection map between different food sources is optimized to obtain the production batch association matrix between different food sources.
5. The food supply chain traceability method based on multi-source data according to claim 3 is characterized in that: Step S143 includes the following steps: Perform spatial distribution analysis on the production batch nodes of each food source in the production batch association matrix between different food sources, and obtain spatial distribution characteristic data of the production batch nodes of each food source in the production batch association matrix; The spatial distribution characteristic data of each food source production batch node in the production batch association matrix are aggregated and analyzed in the same production batch to obtain the spatial distribution characteristic data of each food source production batch node under the same production batch; Based on the spatial distribution characteristic data of each food source production batch node under the same production batch, the interaction path identification analysis is performed between the corresponding food source production batch nodes in the production batch association matrix between different food sources to obtain the same production batch interaction connection path between different food sources; Perform production batch interaction change analysis between production batch nodes of each food source on the same production batch interaction connection path between different food sources to obtain production batch interaction change data between each food source node on the same production batch interaction path; perform interaction strength evaluation analysis on the same production batch interaction connection path between different food sources based on the production batch interaction change data between each food source node on the same production batch interaction path to obtain production batch interaction strength between each food source node on the same production batch interaction path; According to the production batch interaction intensity between each food source node on the same production batch interaction path, the same production batch interaction pattern analysis is performed on the same production batch interaction connection path between different food sources to obtain the same production batch association interaction pattern between different food sources.
6. The food supply chain traceability method based on multi-source data according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: Perform food source node docking and interaction analysis on the food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch, and obtain production process interaction nodes of different food data sources under the same production batch, including food production source process interaction nodes, food logistics and transportation source process interaction nodes, food inventory distribution source process interaction nodes and food sales source process interaction nodes; Step S22: performing production association mining analysis on the production process interaction nodes of different food data sources under the same production batch, so as to obtain the production association connection relationship between different sub-data of food sources under the same production batch; Step S23: Based on the production association connection relationship between different sub-data of food sources under the same production batch, food supply link processing is performed on the food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch to generate a distributed supply chain of food under the same production batch.
7. The food supply chain traceability method based on multi-source data according to claim 6 is characterized in that: Step S21 includes the following steps: Determine different food source process point sets for food production sub-data, food logistics and transportation sub-data, food inventory distribution sub-data and food sales sub-data under the same production batch, and obtain the food production source process point set, food logistics and transportation source process point set, food inventory distribution source process point set and food sales source process point set under the same production batch; Performing interactive screening and processing of process link docking for the food production source process point set and the food logistics transportation source process point set under the same production batch, and obtaining the food production source process interactive nodes and the food logistics transportation source process interactive nodes; Based on the food production source process interaction nodes and the food logistics transportation source process interaction nodes, the food inventory distribution source process point set under the same production batch is subjected to cross-layer process synchronous docking interactive screening and processing to obtain the food inventory distribution source process interaction nodes; Based on the food inventory distribution source process interaction node, the food sales source process point set under the same production batch is subjected to sales flow docking interactive screening and processing to obtain the food sales source process interaction node.
8. The food supply chain traceability method based on multi-source data according to claim 6 is characterized in that: Step S22 includes the following steps: Conduct production-logistics association mining analysis on the food production source process interaction nodes and the food logistics transportation source process interaction nodes to obtain the production-logistics association connection relationship between the food production source and the logistics transportation source; Based on the food inventory distribution source process interaction node, the food production source process interaction node and the food logistics transportation source process interaction node are dynamically mined and analyzed to obtain the dynamic inventory-production logistics association connection relationship between food inventory distribution and production and logistics; Performing inventory-sales association mining analysis on the food inventory distribution source process interaction nodes and the food sales source process interaction nodes to obtain the inventory-sales association connection relationship between the food inventory distribution source and the sales source; The production-logistics association connection relationship between food production sources and logistics transportation sources, the dynamic inventory-production logistics association connection relationship between food inventory distribution and production and logistics, and the inventory-sales association connection relationship between food inventory distribution sources and sales sources are integrated into the same production batch to obtain the production association connection relationship between different sub-data of food sources under the same production batch.
9. The food supply chain traceability method based on multi-source data according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: Verify the production record changes of the corresponding food supply links on the distributed supply chain of the same production batch of food based on different food data source participants, and obtain the verification results of the production link changes of the same production batch of food supply chain; Step S32: performing food supply change abnormality problem location processing on the verification results of the production link changes of the food supply chain of the same production batch, and obtaining the distribution locations of the production change abnormality problems of the same production batch supply chain; Step S33: Based on the distributed supply chain of food of the same production batch, a food supply abnormality problem traceability analysis is performed on the distribution location of abnormal production change problems in the supply chain of the same production batch to obtain the traceability source of abnormal problems in the food supply chain of the same production batch.
10. The food supply chain traceability method based on multi-source data according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: tracing the source of abnormal problems in the food supply chain of the same production batch to determine the abnormal problem points, and obtaining the abnormal problem points in the food supply chain of the same production batch; Step S42: performing abnormal pattern recognition analysis on abnormal problem points in the food supply chain of the same production batch to obtain abnormal food supply patterns at each abnormal problem point; Step S43: Based on the food supply abnormality patterns at each abnormal problem point, risk level assessment and classification are performed on the corresponding abnormal problem points in the same production batch of food supply chain to obtain the food supply abnormality risk level of each abnormal problem point; Step S44: designing abnormal early warning responses for the abnormal risk levels of food supply at each abnormal problem point, so as to generate early warning response mechanism solutions for each abnormal risk level of food supply; Step S45: According to the early warning response mechanism scheme of each food supply abnormality risk level, the corresponding food supply chain abnormality problem traceability of the same production batch is subjected to abnormal early warning response control processing, and the abnormal early warning control strategy of the food supply chain of the same production batch is generated to execute the corresponding food supply chain traceability abnormality control operation.
Citation Information
Patent Citations
Network tracing system and network tracing method for non-staple food industrial chain
CN102708410A
Food traceability verification method and system
CN117788019A
Agricultural product tracing method and system
CN117993923A
Traceability management method for supply chains of agricultural, fishery and animal husbandry products
US20220391822A1
Cited By
One-object-one-code-based commodity traceability full-life-cycle traceability method and system
CN120163596A
Food safety tracing method and system based on multi-source monitoring
CN120278727A
Campus food digital supervision method based on rationed meal and traceability
CN122694478A
