Logistics Integration Management Platform System and Method for Food Material Supply Chain

Abstract

The present invention discloses a logistics integrated management platform system and method for a food ingredient supply chain, including a food ingredient supply chain knowledge graph construction module for obtaining information related to the food ingredient supply chain to construct a food ingredient supply chain knowledge graph, a freshness analysis module for generating food ingredient freshness result information after performing food ingredient freshness evaluation and analysis based on the food ingredient supply chain knowledge graph, a food ingredient supply chain logistics analysis module and a food ingredient supply chain logistics scheduling module for generating corresponding food ingredient supply chain logistics analysis result strategies and scheduling route information by combining logistics scheduling information and real-time operation information. Through these functions, the logistics integrated management platform system of the food ingredient supply chain of the present invention can intelligently schedule according to the analysis results without manual judgment of food ingredient supply and distribution strategies, thereby improving the transparency, response speed and overall efficiency of the food ingredient supply chain, while reducing costs and risks and ensuring the quality and safety of food ingredients.

Description

Technical Field

[0001] The present invention relates to the technical field of food logistics data processing, in particular to a logistics integrated management platform system and method for a food ingredient supply chain. Background Art

[0002] The food ingredient storage centers of food ingredient supply chain manufacturers supply food ingredients to various local required places through a logistics system. At present, there are relevant food ingredient supply management systems for managing the logistics distribution process; Frozen food ingredients, chilled fresh food ingredients, and packaged dry food ingredients are three common types in the food ingredient supply chain, and they have their own characteristics in storage, transportation, and processing. When sorting, the logistics system sorts and distributes according to frozen food ingredients, chilled fresh food ingredients, packaged dry food ingredients, etc., then packs the same kind of food ingredients, and finally transports them to the corresponding destinations through the corresponding logistics vehicles by selecting reasonable routes.

[0003] However, at present, the relevant systems of the food ingredient supply chain often judge the freshness of food ingredients based on manual work or simple temperature and time, without a reasonable standardized analysis process, resulting in problems of low accuracy and efficiency. In addition, there is also a lack of an intelligent analysis function for intelligent scheduling of logistics distribution according to the freshness of food ingredients. When making a simple route plan according to orders and delivery addresses, the freshness judgment of food ingredients is ignored, which is likely to cause the deterioration of food ingredients during the scheduling and distribution process. This leads to the inability to effectively control the freshness of food ingredients during the distribution process, affecting their quality and taste, and increasing the risks and costs of the food ingredient supply chain. Summary of the Invention

[0004] In view of the above problems existing in the freshness and distribution routes of different categories of food logistics at present, the present invention is proposed.

[0005] Therefore, one of the purposes of the present invention is to provide a logistics integrated management platform system and method for a food ingredient supply chain, which uses the Internet of Things and big data analysis to realize intelligent analysis of the freshness of food ingredients and the distribution chain, and generates corresponding scheduling and distribution strategies in real time, not only maintaining the relationship between the best supply time and location of the freshness of food ingredients, but also improving the efficiency and transparency of the food ingredient supply chain distribution.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] On the one hand, the present invention provides a logistics integrated management platform system for a food ingredient supply chain, including a food ingredient freshness analysis system for generating corresponding scheduling and distribution strategies after analyzing the freshness of food ingredients and the distribution chain. The food ingredient freshness analysis system includes:

[0008] A food ingredient supply chain knowledge graph construction module, which is used to obtain relevant information of the food ingredient supply chain and construct a food ingredient supply chain knowledge graph based on natural language NLP processing;

[0009] A freshness analysis module for evaluating the freshness of food ingredients based on the food ingredient supply chain knowledge graph, including real-time freshness impact analysis and potential freshness impact analysis of the food ingredient portrait, and generating food ingredient freshness result information according to the real-time freshness impact analysis and potential freshness impact analysis; the real-time freshness impact analysis uses TTI tags to monitor the time and temperature conditions of food ingredients in the entire supply chain, evaluates and generates real-time freshness impact values, and the potential freshness impact analysis is carried out by one of image processing, microbial detection, monitoring volatile organic compounds or spectral analysis, evaluates and generates potential freshness impact values through potential freshness impact analysis, analyzes and generates food ingredient freshness evaluation values according to the real-time freshness impact values and potential freshness impact values, and uses them as the food ingredient freshness result information;

[0010] A food ingredient supply chain logistics analysis module for responding to the food ingredient freshness result information, combining logistics scheduling information and real-time operation information, and generating corresponding food ingredient supply chain logistics analysis result strategies and scheduling route information;

[0011] A food ingredient supply chain logistics scheduling module for responding to and generating corresponding scheduling and distribution plans according to the food ingredient supply chain logistics analysis result strategies and scheduling route information, and then performing corresponding food ingredient supply chain logistics scheduling.

[0012] As a preferred embodiment of the present invention, wherein: the food ingredient supply chain knowledge graph construction module includes a preprocessing unit, a natural language processing unit, an attribute extraction unit, a knowledge fusion unit and a knowledge graph construction unit;

[0013] The preprocessing unit preprocesses the information related to the food ingredient supply chain obtained and generates a text data set in a unified format;

[0014] The natural language processing unit, based on named entity recognition in natural language NLP, identifies entities in the food ingredient supply chain from the text data set, and the entities include suppliers, products, geographical locations, organizations, logistics and inventory;

[0015] The attribute extraction unit extracts relationship information according to the identified entities in the food ingredient supply chain, that is, identifies the relationship information between entities and constructs the connection relationship between entities, and then extracts according to the attribute information of the entities; such as the shelf life of food ingredients, the credit rating of suppliers, etc.

[0016] The knowledge fusion unit integrates and processes the extracted knowledge information;

[0017] The knowledge graph construction unit stores the processed data in a graph database and constructs a knowledge graph of the food ingredient supply chain.

[0018] As a preferred embodiment of the present invention, wherein: the food ingredient supply chain knowledge graph construction module further includes a fusion representation unit for feature mining of the food ingredient supply chain knowledge graph. The fusion representation unit is used to perform feature mining after integrating different data sources in the food ingredient supply chain and using a clustering algorithm to represent the nodes in the knowledge graph, specifically as follows:

[0019] The fusion representation unit calculates the weight of each node attribute dataset in the data object of the mixed attribute dataset corresponding to the knowledge graph node according to the information entropy formula, and the attribute dataset is a vector attribute dataset;

[0020] The fusion representation unit then selects a corresponding number of data objects from the mixed attribute dataset as clustering centroid points according to the preset number of clustering clusters of the knowledge graph nodes;

[0021] Calculate the distance value between the data object to be clustered and the attribute datasets of the same attribute type in the clustering centroid points, and determine the dissimilarity between the data object of the knowledge graph node to be clustered and the clustering centroid points according to the distance and the weight of each node attribute dataset;

[0022] Cluster the data object of the knowledge graph node to be clustered into the clustering cluster corresponding to the clustering centroid point with the minimum dissimilarity, and then represent the clustering cluster, so as to enhance the feature mining of the food ingredient supply chain knowledge graph construction module.

[0023] As a preferred embodiment of the present invention, wherein: it further includes an information collection and release system, an identity authentication system, and a food ingredient supply chain management system;

[0024] The information collection and release system includes collection management, release management, website release, and short message service. The data stream formats of the collection management and release management adopt network formats such as html, asp, aspx, and jsp, and are used for the collection of food ingredient supply chain related information, logistics regulations, weather, and the acquisition and release management of logistics industry information;

[0025] The identity authentication system includes user registration, login, password setting, identity verification API, access control, and encrypted communication;

[0026] The food ingredient supply chain management system includes a management unit, an enterprise self - building website unit, and a GIS and GPS positioning management unit; the management unit includes a food ingredient management subunit, a supply chain management subunit, an order management subunit, an inventory management subunit, and a logistics management subunit.

[0027] As a preferred embodiment of the present invention, wherein: the freshness analysis module includes a real-time freshness impact analysis unit, and the real-time freshness impact analysis unit analyzes the freshness state of the food ingredients based on the time and temperature information of the food ingredients, evaluates and generates a real-time freshness impact value, as follows:

[0028]

[0029]

[0030] In the formula, n is the i-th temperature sensor of the v-th type of food ingredient, T is the t-th acquisition time period sequence, is the food ingredient freshness evaluation value calculated and analyzed for the v-th type of food ingredient in the t-th time period sequence, Av is the freshness impact analysis and evaluation adjustment coefficient of the v-th type of food ingredient, is the temperature value collected by the i-th temperature sensor of the v-th type of food ingredient in the t-th time period sequence, that is, the temperature data monitoring list where the v-th type of food ingredient exists; P i v,t is the real-time freshness impact value evaluation base number, that is, the fuzzy evaluation list for the freshness evaluation of the v-th type of food ingredient; is the weight of the temperature value collected by the i-th temperature sensor of the v-th type of food ingredient in the t-th time period sequence; is the real-time freshness impact value analyzed for the v-th type of food ingredient in the t-th time period sequence, is the real-time freshness judgment prediction threshold for the v-th type of food ingredient in the t-th time period sequence.

[0031] As a preferred embodiment of the present invention, wherein: the potential freshness impact analysis monitors the change of volatile organic compounds and evaluates the freshness, that is, by evaluating the index data of total volatile basic nitrogen TVB-N, and using the partial least squares method PLS to establish a model for analyzing the potential freshness impact value, and verifying the model;

[0032]

[0033] Among them, is the potential freshness impact value, K is the index evaluation coefficient of total volatile basic nitrogen TVB-N, is the total volatile basic nitrogen TVB-N monitoring value monitored for the v-th type of food ingredient in the t-th time period sequence.

[0034] As a preferred embodiment of the present invention, wherein: the food ingredient freshness evaluation value is generated based on the analysis of the real-time freshness impact value and the potential freshness impact value, and used as the food ingredient freshness result information. The correlation coefficient between the real-time freshness impact value and the potential freshness impact value is analyzed, and the root mean square error of calibration RMSEC is used as the calibration evaluation index for the real-time freshness impact analysis. The food ingredient freshness evaluation value is generated according to the evaluation index, and the calculation formula of the root mean square error of calibration RMSEC is as follows:

[0035]

[0036] Among them, m is the k-th real-time freshness impact analysis sample data, is the corrected mean square error of real-time freshness impact analysis, y ck is the freshness analysis value of the index data of total volatile basic nitrogen TVB-N, is the freshness prediction value of the model established by the least squares method PLS to analyze the potential freshness impact value.

[0037] As a preferred embodiment of the present invention, wherein: the least squares method PLS is to establish a regression prediction model according to the correlation decomposition of the eigenvector of the index data of total volatile basic nitrogen TVB-N. At the same time, the determination of the abstract number of components in the PLS algorithm adopts the cross-validation method, that is, the sample data not selected in the potential freshness impact analysis data set is excluded from the one-dimensional PLS modeling calculation. The model parameter vector is calculated from the selected sample data, and then the predicted value and the true value are obtained from the real-time freshness impact value. After selection and then deletion for the second time, the calculation is repeated.

[0038] As a preferred embodiment of the present invention, wherein: a regression prediction model is established according to the correlation decomposition of the eigenvector of the index data of total volatile basic nitrogen TVB-N. The eigenvector similarity calculation formula is as follows:

[0039]

[0040] Among them, is the similarity between the real-time freshness impact value and the potential freshness impact value analysis, is the eigenvector of the real-time freshness impact value analysis of the v-th type of food ingredient in the t-th time period sequence analysis, is the eigenvector of the potential freshness impact value analysis of the v-th type of food ingredient in the t-th time period sequence analysis.

[0041] On the one hand, the present invention provides a method for the logistics integrated management platform system of a food ingredient supply chain, including the following steps:

[0042] Obtain relevant information of the food ingredient supply chain and construct a food ingredient supply chain knowledge graph based on natural language NLP processing;

[0043] Conduct food ingredient freshness evaluation according to the food ingredient supply chain knowledge graph, including real-time freshness impact analysis and potential freshness impact analysis of the food ingredient portrait, and generate food ingredient freshness result information according to the real-time freshness impact analysis and potential freshness impact analysis;

[0044] Respond to the fresh - degree result information of the food ingredients, and combine the logistics scheduling information and real - time operation information to generate corresponding food - ingredient supply - chain logistics analysis result strategies and scheduling route information;

[0045] Respond to and generate a corresponding scheduling and distribution plan according to the food - ingredient supply - chain logistics analysis result strategies and scheduling route information, and then perform the corresponding food - ingredient supply - chain logistics scheduling.

[0046] Advantages of the present invention: This application integrates functions such as Internet of Things (IoT) monitoring in the food - ingredient supply process, in - depth analysis of food - ingredient freshness and distribution chain, intelligent real - time freshness - impact analysis and potential freshness - impact analysis, and intelligent scheduling of logistics distribution into the system platform. It can achieve intelligent and accurate analysis of food - ingredient freshness and distribution chain, and generate corresponding scheduling and distribution strategies in real - time. It not only maintains the relationship between the best supply time and location of food - ingredient freshness, but also improves the efficiency and transparency of food - ingredient supply - chain distribution. In summary, through these functions, the logistics integrated management platform system of the food - ingredient supply chain can, without manual judgment of food - ingredient supply and distribution strategies, perform intelligent scheduling according to the analysis results, thereby improving the transparency, response speed and overall efficiency of the food - ingredient supply chain, while reducing costs and risks, and ensuring the quality and safety of food ingredients. Brief Description of the Drawings

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for description in the embodiments. Obviously, the following - described drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings. Among them:

[0048] Figure 1 is a schematic modular structure diagram of the present invention;

[0049] Figure 2 is a schematic application diagram of freshness analysis of the present invention;

[0050] Figure 3 is a schematic modular structure diagram of the food - ingredient supply - chain knowledge - graph construction module of the present invention;

[0051] Figure 4 is a scatter plot of freshness analysis values and freshness prediction values of the total volatile basic nitrogen (TVB - N) index data of potential freshness - impact values of the freshness analysis module of the present invention;

[0052] Figure 5 is a flowchart of the method of the present invention;

[0053] Reference numerals in the figures: 10, food - ingredient supply - chain knowledge - graph construction module; 20, freshness analysis module; 30, food - ingredient supply - chain logistics analysis module; 40, food - ingredient supply - chain logistics scheduling module. Detailed implementation manners

[0054] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the described embodiments of the present invention fall within the scope of protection of the present invention.

[0055] At present, relevant systems of the food ingredient supply chain often judge the freshness of food ingredients based on manual work or simple temperature and time, without a reasonable standardized analysis process, resulting in problems of low accuracy and efficiency. In addition, there is also a lack of intelligent analysis function for intelligent scheduling of logistics distribution according to the freshness of food ingredients. When making a simple path planning based on orders and delivery addresses, the freshness judgment of food ingredients is ignored.

[0056] Refer to Figures 1-5 , which is an embodiment of the present invention. This embodiment provides a logistics integrated management platform system for the food ingredient supply chain, including a food ingredient freshness analysis system for generating corresponding scheduling and distribution strategies after analyzing the freshness of food ingredients and the distribution chain. As Figure 1 and Figure 2 shown, the application scenarios include enterprises related to the food ingredient supply chain, logistics operation enterprises, the logistics integrated management platform of the food ingredient supply chain, and mobile clients. The food ingredient freshness analysis system includes:

[0057] A food ingredient supply chain knowledge graph construction module 10, configured to obtain information related to the food ingredient supply chain and construct a food ingredient supply chain knowledge graph based on natural language NLP processing;

[0058] A freshness analysis module 20, configured to evaluate the freshness of food ingredients according to the food ingredient supply chain knowledge graph, including real-time freshness impact analysis and potential freshness impact analysis of the food ingredient portrait, and generate food ingredient freshness result information according to the real-time freshness impact analysis and potential freshness impact analysis; the real-time freshness impact analysis uses TTI tags to monitor the time and temperature conditions of food ingredients in the entire supply chain, evaluate and generate a real-time freshness impact value, and the potential freshness impact analysis is performed by one of image processing, microbial detection, monitoring of volatile organic compounds or spectral analysis. Through the potential freshness impact analysis, a potential freshness impact value is evaluated and generated. According to the real-time freshness impact value and the potential freshness impact value, a food ingredient freshness evaluation value is analyzed and generated as the food ingredient freshness result information;

[0059] A food ingredient supply chain logistics analysis module 30, configured to respond to the food ingredient freshness result information, and generate corresponding food ingredient supply chain logistics analysis result strategies and scheduling route information in combination with logistics scheduling information and real-time operation information;

[0060] The food ingredient supply chain logistics scheduling module 40 is used to respond to and generate a corresponding scheduling and distribution plan according to the food ingredient supply chain logistics analysis result strategy and scheduling route information, and then perform the corresponding food ingredient supply chain logistics scheduling.

[0061] As Figure 3 shown, specifically in one implementation, the food ingredient supply chain knowledge graph construction module 10 includes a preprocessing unit, a natural language processing unit, an attribute extraction unit, a knowledge fusion unit, and a knowledge graph construction unit;

[0062] The preprocessing unit preprocesses the information related to the food ingredient supply chain and generates a text data set in a unified format;

[0063] Based on named entity recognition in natural language NLP, the natural language processing unit identifies the entities in the food ingredient supply chain from the text data set. The entities include suppliers, products, geographical locations, organizations, logistics, and inventory;

[0064] The attribute extraction unit extracts relationships according to the identified entities in the food ingredient supply chain, that is, identifies the relationship information between entities and constructs the connection relationship between entities, and then extracts according to the attribute information of the entities; such as the shelf life of food ingredients, the credit rating of suppliers, etc.

[0065] The knowledge fusion unit integrates and processes the extracted knowledge information;

[0066] The knowledge graph construction unit stores the processed data in a graph database and constructs a knowledge graph of the food ingredient supply chain.

[0067] As Figure 3 shown, specifically in one implementation, the food ingredient supply chain knowledge graph construction module 10 further includes a fusion representation unit for feature mining of the food ingredient supply chain knowledge graph. The fusion representation unit is used to perform feature mining after representing the nodes in the knowledge graph by integrating different data sources in the food ingredient supply chain and using a clustering algorithm, specifically as follows:

[0068] The fusion representation unit calculates the weight of each node attribute data set in the data object of the mixed attribute data set corresponding to the knowledge graph node according to the information entropy formula. The attribute data set is a vector attribute data set;

[0069] The fusion representation unit then selects a corresponding number of data objects from the mixed attribute data set as clustering centroid points according to the preset number of clustering clusters of the knowledge graph nodes;

[0070] Calculate the distance value between the data object to be clustered and the attribute data set of the same attribute type in the clustering centroid point, and determine the dissimilarity between the data object of the knowledge graph node to be clustered and the clustering centroid point according to the distance and the weight of each node attribute data set;

[0071] After clustering the knowledge graph node data objects to be clustered into the cluster corresponding to the clustering centroid point with the minimum dissimilarity, the cluster is characterized to enhance the feature mining of the food ingredient supply chain knowledge graph construction module 10.

[0072] Specifically, in one implementation, it further includes an information collection and release system, an identity authentication system, and a food ingredient supply chain management system;

[0073] The information collection and release system includes collection management, release management, website release, and short message service. The data stream formats of collection management and release management adopt network formats such as html, asp, aspx, and jsp, and are used for the collection of food ingredient supply chain-related information, logistics regulations, weather, and the acquisition and release management of logistics industry information;

[0074] The identity authentication system includes user registration, login, password setting, identity authentication API, access control, and encrypted communication;

[0075] The food ingredient supply chain management system includes a management unit, an enterprise self-built website unit, and a GIS and GPS positioning management unit; the management unit includes a food ingredient management subunit, a supply chain management subunit, an order management subunit, an inventory management subunit, and a logistics management subunit.

[0076] Food ingredient management subunit: The knowledge graph can model and analyze food ingredients and related attributes. By establishing the knowledge graph of food ingredients, functions such as comprehensive traceability of food ingredients, attribute correlation analysis, and recommendation of similar food ingredients can be realized, so as to improve the efficiency and accuracy of food ingredient management.

[0077] Supply chain management subunit: By establishing the knowledge graph of the supply chain, the credit, qualifications, business relationships, etc. of suppliers in the supply chain can be modeled and analyzed. Through the reasoning function of the knowledge graph, intelligent matching, evaluation, and selection of suppliers can be realized, thereby improving the efficiency and quality of supplier management.

[0078] Order management subunit: The knowledge graph can model and analyze each link of the food ingredient supply chain order, including order generation, allocation, tracking, and delivery, etc. Through the reasoning and prediction functions of the knowledge graph, intelligent scheduling and prediction of orders can be realized, thereby improving the efficiency and accuracy of order management.

[0079] Inventory management subunit: By establishing the knowledge graph of inventory, the location, quantity, quality, freshness preservation period, etc. of food ingredient inventory can be modeled and analyzed. Through the reasoning function of the knowledge graph, intelligent allocation, replenishment, and prediction of inventory can be realized, thereby improving the efficiency of inventory management and cost control.

[0080] Logistics Management Sub-unit: The knowledge graph can model and analyze logistics networks, nodes, paths, and spatio-temporal relationships. By establishing a knowledge graph of logistics, functions such as logistics path optimization, capacity planning, delivery tracking, and exception handling can be achieved, thereby improving the efficiency and reliability of logistics management.

[0081] It can be seen that the application of the food ingredient supply chain knowledge graph in this implementation can help achieve the intelligence, high efficiency, and sustainable development of the food ingredient supply chain, and improve the overall operation effect of the food ingredient supply chain.

[0082] In one implementation, it should be emphasized that the freshness analysis module 20 includes a real-time freshness impact analysis unit. The real-time freshness impact analysis unit analyzes the freshness status of the food ingredients based on the time and temperature information of the food ingredients, and evaluates and generates a real-time freshness impact value as follows:

[0083]

[0084] In the formula, n is the i-th temperature sensor for the v-th type of food ingredient, T is the t-th acquisition time period sequence, is the food ingredient freshness evaluation value calculated and analyzed for the v-th type of food ingredient in the t-th time period sequence, Av is the freshness impact analysis and evaluation adjustment coefficient for the v-th type of food ingredient, is the temperature value collected by the i-th temperature sensor for the v-th type of food ingredient in the t-th time period sequence, that is, the temperature data monitoring list where the v-th type of food ingredient exists; P i v,t is the real-time freshness impact value evaluation base number, that is, the fuzzy evaluation list for the freshness evaluation of the v-th type of food ingredient; is the weight of the temperature value collected by the i-th temperature sensor for the v-th type of food ingredient in the t-th time period sequence; is the real-time freshness impact value analyzed for the v-th type of food ingredient in the t-th time period sequence, is the real-time freshness judgment and prediction threshold for the v-th type of food ingredient in the t-th time period sequence.

[0085] Specifically, in one implementation, the potential freshness impact analysis monitors the change of volatile organic compounds and evaluates the freshness, that is, by evaluating the index data of total volatile basic nitrogen TVB-N, and using the partial least squares method PLS to establish a model for analyzing the potential freshness impact value, and verifying the model;

[0086]

[0087] Among them, is the potential freshness impact value, K is the index evaluation coefficient of total volatile basic nitrogen TVB-N, It is the monitored value of total volatile basic nitrogen (TVB-N) for the v-th type of food ingredient in the t-th time period sequence. Among them, sensory evaluation, physical and chemical indicators, and the indicator analysis of total volatile basic nitrogen (TVB-N) were carried out on food ingredients at different storage temperatures. The results show that with the increase of storage time, the sensory score, TVB-N value, and total bacterial count (TBC) value increase continuously, and the higher the storage temperature, the faster the increase.

[0088] As Figure 4 shown, specifically in one embodiment, a freshness evaluation value of the food ingredient is generated based on the analysis of the real-time freshness impact value and the potential freshness impact value, and is used as the freshness result information of the food ingredient. The correlation coefficient between the real-time freshness impact value and the potential freshness impact value is analyzed, and the root mean square error of cross-validation (RMSEC) is used as the corrected evaluation index for the real-time freshness impact analysis. The food ingredient freshness evaluation value is generated according to the evaluation index. The calculation formula of the root mean square error of cross-validation (RMSEC) is as follows:

[0089]

[0090] where m is the k-th sample data of the real-time freshness impact analysis, is the corrected root mean square error of the real-time freshness impact analysis, y ck is the freshness analysis value of the indicator data of total volatile basic nitrogen (TVB-N), is the freshness prediction value of the model established by the partial least squares (PLS) method for analyzing the potential freshness impact value.

[0091] Specifically in one embodiment, the partial least squares (PLS) method is to establish a regression prediction model based on the correlation decomposition of the characteristic vectors of the indicator data of total volatile basic nitrogen (TVB-N). At the same time, the determination of the abstract number of components in the PLS algorithm adopts the cross-validation method, that is, the sample data not selected in the potential freshness impact analysis dataset is excluded from the one-dimensional PLS modeling calculation. The model parameter vectors are calculated from the selected sample data, and then the predicted value and the true value are obtained from the real-time freshness impact value. After selection and then a second deletion, the calculation is repeated.

[0092] Specifically in one embodiment, a regression prediction model is established based on the correlation decomposition of the characteristic vectors of the indicator data of total volatile basic nitrogen (TVB-N). The calculation formula of the characteristic vector similarity is as follows:

[0093]

[0094] where, is the similarity between the real-time freshness impact value and the potential freshness impact value analysis, is the characteristic vector for analyzing the real-time freshness impact value of the v-th type of food ingredient in the t-th time period sequence, is the characteristic vector for analyzing the potential freshness impact value of the v-th type of food ingredient in the t-th time period sequence.

[0095] Based on the above, in this embodiment, through the real-time freshness impact analysis and potential freshness impact analysis of the food ingredient image, and generating food ingredient freshness result information according to the real-time freshness impact analysis and potential freshness impact analysis, various factors in the food ingredient itself, logistics, supply chain, and scheduling process are combined. It can, based on the changes in the indicators of time, temperature, and total volatile basic nitrogen (TVB-N), perform combined correlation analysis to generate freshness information for different categories of food ingredients, and correspondingly carry out subsequent logistics processing, scheduling, etc. Then, it can accurately analyze the current freshness information of the food ingredients, and at the same time is beneficial to the operation of subsequent logistics and scheduling strategies, maximizing the protection of the freshness and storage time of the food ingredients.

[0096] As Figure 5 shown, at the same time, this embodiment provides a method for a logistics integrated management platform system of a food ingredient supply chain, including the following steps:

[0097] Step S1, obtain food ingredient supply chain related information and construct a food ingredient supply chain knowledge graph after processing based on natural language processing (NLP);

[0098] Step S2, conduct food ingredient freshness assessment according to the food ingredient supply chain knowledge graph, including real-time freshness impact analysis and potential freshness impact analysis of the food ingredient image, and generate food ingredient freshness result information according to the real-time freshness impact analysis and potential freshness impact analysis;

[0099] Step S3, respond to the food ingredient freshness result information, and combine logistics scheduling information and real-time operation information to generate corresponding food ingredient supply chain logistics analysis result strategies and scheduling route information;

[0100] Step S4, respond to and generate a corresponding scheduling and distribution plan according to the food ingredient supply chain logistics analysis result strategies and scheduling route information, and then conduct corresponding food ingredient supply chain logistics scheduling.

[0101] Advantages of the present invention: This application integrates functions such as Internet of Things (IoT) monitoring in the food ingredient supply process, in-depth analysis of food ingredient freshness and distribution chain, intelligent real-time freshness impact analysis and potential freshness impact analysis, and intelligent scheduling of logistics distribution into the system platform. It can achieve intelligent and accurate analysis of food ingredient freshness and distribution chain, and generate corresponding scheduling and distribution strategies in real time. It not only maintains the relationship between the best supply time and location of food ingredient freshness, but also improves the efficiency and transparency of food ingredient supply chain distribution. In summary, through these functions, the logistics integrated management platform system of the food ingredient supply chain can, without manual judgment of food ingredient supply and distribution strategies, perform intelligent scheduling according to the analysis results, thereby improving the transparency, response speed, and overall efficiency of the food ingredient supply chain, while reducing costs and risks, and ensuring the quality and safety of food ingredients.

[0102] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions according to the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0103] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0104] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" can explicitly or implicitly include at least one of the features. In the description of the present application, "a plurality of" means two or more unless otherwise specifically defined.

[0105] Any process or method description represented in a flowchart or described in other ways herein can be understood as representing a module, segment, or part of code including one or more executable instructions for implementing a specific logical function or process. And the scope of the preferred embodiments of the present application includes additional implementations, where the functions can be executed in a substantially simultaneous manner or in a reverse order according to the involved functions, rather than in the order shown or discussed.

[0106] The logic and / or steps represented in a flowchart or described in other ways herein, for example, can be considered as a sequenced list of executable instructions for implementing a logical function, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device, or in combination with these instruction execution systems, apparatus, or devices.

[0107] It should be understood that each part of the present application can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the method in the above embodiments can be completed by a program instructing relevant hardware. The program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0108] In addition, in each embodiment of the present application, each functional unit can be integrated into a processing module, or each unit can exist physically alone, or two or more units can be integrated into one module. The above integrated module can be implemented in the form of hardware or in the form of a software functional module. If the above integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium can be a read-only memory, a magnetic disk, an optical disk, or the like.

[0109] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of various changes or substitutions, and these should all be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. The food supply chain logistics integrated management platform system is characterized by: The invention comprises a food freshness analysis system for generating corresponding dispatching and distribution strategies after analyzing the food freshness and distribution chain, and the food freshness analysis system comprises: Food supply chain knowledge graph construction module, used to obtain food supply chain related information and construct food supply chain knowledge graph based on natural language NLP processing; A freshness analysis module is used to evaluate the freshness of food according to the food supply chain knowledge graph, including real-time freshness impact analysis and potential freshness impact analysis of food portraits, and generate food freshness result information according to the real-time freshness impact analysis and potential freshness impact analysis; the real-time freshness impact analysis uses TTI tags to monitor the time and temperature conditions of food in the entire supply chain, evaluates and generates a real-time freshness impact value, the potential freshness impact analysis uses one of image processing, microbial detection, monitoring of volatile organic compounds or spectral analysis, and evaluates and generates a potential freshness impact value through potential freshness impact analysis, and generates a food freshness evaluation value according to the real-time freshness impact value and potential freshness impact value analysis, and serves as the food freshness result information; The freshness analysis module includes a real-time freshness impact analysis unit, which analyzes the freshness state of the food and evaluates and generates a real-time freshness impact value according to the time and temperature information of the food, as follows: Where n is the ith temperature sensor of the vth type of food, T is the tth collection time period sequence, real(Q) t v is the food freshness evaluation value calculated and analyzed for the vth food in the tth time period, Av is the freshness impact analysis and evaluation adjustment coefficient for the vth food, is the temperature value collected by the ith temperature sensor in the tth time period sequence of the vth type of food, that is, the temperature data monitoring list of the vth type of food; i v,t is the real-time freshness impact value evaluation base, that is, the fuzzy evaluation list of the freshness evaluation of the vth category of food; is the weight of the temperature value collected by the ith temperature sensor in the tth time period sequence in the vth type of food; is the real-time freshness impact value of the sequence analysis of the vth type of food in the tth time period, is the real-time freshness prediction threshold of the vth type of food in the tth time period sequence; A food supply chain logistics analysis module, which is used to respond to the food freshness result information and generate corresponding food supply chain logistics analysis result strategy and scheduling route information in combination with logistics scheduling information and real-time operation information; The food supply chain logistics scheduling module is used to respond to and generate a corresponding scheduling and delivery plan based on the food supply chain logistics analysis result strategy and scheduling route information, and then perform corresponding food supply chain logistics scheduling.

2. The food supply chain logistics integrated management platform system according to claim 1, characterized in that: The food supply chain knowledge graph construction module includes a preprocessing unit, a natural language processing unit, an attribute extraction unit, a knowledge fusion unit and a knowledge graph construction unit; The preprocessing unit obtains the food supply chain related information and generates a text data set in a unified format after data preprocessing; The natural language processing unit identifies entities in the food supply chain from the text data set based on named entity recognition in natural language NLP, the entities including suppliers, products, geographic locations, organizations, logistics and inventory; The attribute extraction unit extracts relationships based on the entities in the identified food supply chain, that is, identifies the relationship information between entities and builds the connection relationship between entities, and then extracts based on the attribute information of the entities, where the attribute information of the entities includes the shelf life of the food and the reputation level of the supplier; The knowledge fusion unit integrates the extracted knowledge information; The knowledge graph construction unit stores the processed data in a graph database to construct a knowledge graph of the food supply chain.

3. The food supply chain logistics integrated management platform system according to claim 1 or 2, characterized in that: The food supply chain knowledge graph construction module also includes a fusion representation unit for performing feature mining on the food supply chain knowledge graph. The fusion representation unit is used to perform feature mining by integrating different data sources in the food supply chain and using a clustering algorithm to represent the nodes in the knowledge graph, as follows: The fusion representation unit calculates the weight of each node attribute data set in the data object of the mixed attribute data set corresponding to the knowledge graph node according to the information entropy formula, and the attribute data set is a vector attribute data set; The fusion representation unit then selects a corresponding number of data objects as cluster centroids from the mixed attribute data set according to the number of clusters preset by the knowledge graph node; Calculate the distance value between the data object to be clustered and the attribute data set of the same attribute type in the cluster centroid point, and determine the dissimilarity between the node data object of the knowledge graph to be clustered and the cluster centroid point according to the distance and the weight of each node attribute data set; The node data objects of the knowledge graph to be clustered are clustered into clusters corresponding to the cluster centroid points with the minimum dissimilarity, and then the clusters are characterized, so as to enhance the feature mining of the food supply chain knowledge graph construction module.

4. The food supply chain logistics integrated management platform system according to claim 1, characterized in that: It also includes information collection and release system, identity authentication system, and food supply chain management system; The information collection and publishing system includes collection management, publishing management, website publishing, and short message service. The data stream format of the collection management and publishing management adopts the network format html, asp, aspx and jsp, and is used for the collection of information related to the food supply chain, logistics regulations, weather, and logistics industry information acquisition and publishing management; The identity authentication system includes user registration, login, password setting, identity authentication API, access control and encrypted communication; The food supply chain management system includes a management unit, an enterprise self-service website building unit, and a GIS and GPS positioning management unit; the management unit includes a food management subunit, a supply chain management subunit, an order management subunit, an inventory management subunit and a logistics management subunit.

5. The food supply chain logistics integrated management platform system according to claim 1, characterized in that: The potential freshness impact analysis adopts monitoring the changes of volatile organic compounds and evaluating the freshness, that is, by evaluating the index data of volatile basic nitrogen TVB-N, and using the partial least squares method PLS method to establish a model for potential freshness impact value analysis, and verify the model; in, is the potential freshness impact value, K is the index evaluation coefficient of volatile basic nitrogen TVB-N, It is the volatile basic nitrogen TVB-N monitoring value of the vth type of food monitored in the tth time period sequence.

6. The food supply chain logistics integrated management platform system according to claim 5, characterized in that: The food freshness evaluation value is generated according to the real-time freshness impact value and the potential freshness impact value analysis, and is used as the food freshness result information. The correlation coefficient between the real-time freshness impact value and the potential freshness impact value is analyzed, and the corrected mean square error RMSEC is used as the corrected evaluation index of the real-time freshness impact analysis. The food freshness evaluation value is generated according to the evaluation index. The corrected mean square error RMSEC calculation formula is as follows: Among them, m is the kth real-time freshness impact analysis sample data, is the corrected mean square error of real-time freshness impact analysis, y ck This is the freshness analysis value of the indicator data of volatile basic nitrogen TVB-N. The freshness prediction value of the model for potential freshness impact value analysis established by the least squares PLS method.

7. The food supply chain logistics integrated management platform system according to claim 5, characterized in that: The least squares PLS method is to establish a regression prediction model after correlation decomposition of the characteristic vector of the indicator data of volatile basic nitrogen TVB-N. At the same time, the cross-validation method is adopted to determine the number of abstract components in the PLS algorithm, that is, the unselected sample data in the potential freshness impact analysis data set are excluded from the one-dimensional PLS modeling calculation, and the model parameter vector is calculated by the selected sample data. Then, the output of the predicted value and the true value obtained by the real-time freshness impact value is selected, and then the second deletion is performed and the calculation is repeated.

8. The food supply chain logistics integrated management platform system according to claim 1, characterized in that: The regression prediction model is established after the correlation decomposition of the characteristic vector of the index data of volatile basic nitrogen TVB-N, wherein The formula for calculating feature vector similarity is as follows: in, is the similarity of the analysis of the real-time freshness impact value and the potential freshness impact value, is the feature vector of the real-time freshness impact value of the sequence analysis of the v-th type of food in the t-th time period, The feature vector of the potential freshness impact value of the v-th type of food in the t-th time period sequence analysis.

9. A method applied to the food supply chain logistics integrated management platform system as claimed in claim 1, characterized in that: The following steps are involved: Obtain information related to the food supply chain and construct a food supply chain knowledge graph based on natural language NLP processing; Performing food freshness evaluation based on the food supply chain knowledge graph, including real-time freshness impact analysis and potential freshness impact analysis of food portraits, and generating food freshness result information based on the real-time freshness impact analysis and potential freshness impact analysis; In response to the food freshness result information, and in combination with the logistics scheduling information and the real-time operation information, generate a corresponding food supply chain logistics analysis result strategy and scheduling route information; In response to and based on the food supply chain logistics analysis result strategy and scheduling route information, a corresponding scheduling and delivery plan is generated and then corresponding food supply chain logistics scheduling is performed.

Images