Knowledge graph-based food supply chain risk perception, identification and rating system

Abstract

The invention discloses a food supply chain risk perception, identification and rating system based on a knowledge graph. The system comprises a food supply chain risk perception module, a risk identification module, a risk rating module and a response processing module. The system is characterized in that the food supply chain risk identification module includes all classification names of the same food in different food supply chain links; the method comprises the following steps: firstly, searching a food supply chain level where a current spot-checked food name is located, and then carrying out fuzzy matching on a classification name and a limit value of the current spot-checked food name for the food supply chain level; the food supply chain risk rating module rating for risk occurrence possibilities and severity is based on spatio-temporal varying risk occurrence possibilities and severity rating. According to the method, the problem that chain breakage exists in food safety risk identification due to the fact that currently constructed food safety knowledge maps are mostly established on food classification standards of the industry and inconsistent classification of the same food in a food supply chain link is not considered is solved.

Description

Technical Field

[0001] The present invention relates to the field of food safety, and in particular to a food supply chain risk perception, identification and rating system based on a knowledge graph. Background Art

[0002] Generally speaking, food safety risk management involves four steps: risk perception, risk identification, risk rating, and risk control.

[0003] In the risk identification step, the description of food classification is different in different links of the food supply chain. For example, the classification of vegetables, in the planting and breeding link, is classified according to the edibility of vegetables, and vegetables are divided into 11 categories, including melons, bulb onions (onions and garlic), green leafy vegetables, beans, eggplants, and aquatic vegetables, and each category is further subdivided into types and varieties; in the production and processing link, it is classified according to the processing technology characteristics of vegetables, and vegetables are divided into 8 categories, including surface-treated fresh vegetables, frozen vegetables, canned vegetables, dried vegetables, and pickled vegetables, and each category is further subdivided into types and varieties; in the commodity circulation and catering consumption link, it is classified according to the edible functional characteristics of vegetables, and the classification of the planting and breeding link and the classification of the production and processing link are taken as the union, that is, vegetables and vegetable products. Due to the inconsistent description of food classification in different links of the food supply chain, it is difficult to accurately identify risks.

[0004] In the risk rating step, the food safety risk level needs to be calculated based on the data including food consumption. At this time, due to the inconsistent description of food classification in different links of the food supply chain, it is impossible to obtain fine-grained food variety consumption data, which leads to the problem of difficult risk rating.

[0005] In the risk control step, risk control needs to be carried out according to the risk rating of the food. Since the descriptions of food classification in different links of the food supply chain are inconsistent, the food supply chain risks will eventually present information islands during management and control, leading to difficulties in risk control.

[0006] As an important part of artificial intelligence semantic web technology, knowledge graph is a technical method to describe the relationship between all things in the world. It aims to identify, discover and infer the complex relationship between things and concepts from data. It is a computable model of the relationship between things. At present, there are food safety incident risk assessment methods and devices based on knowledge graph reasoning.

[0007] However, there are technical deficiencies in practical applications: (1) In terms of food safety risk identification, the food safety knowledge graphs currently constructed are mostly based on the industry's food classification standards, without considering the inconsistent classification of the same food in the food supply chain, resulting in a broken chain in food safety risk identification; (2) In terms of food safety risk identification, there is a lack of food safety risk association identification from the perspective of supply chain migration and diffusion, and a lack of full use of massive food safety supervision sampling and risk monitoring data to reason about upstream and downstream risks in the food supply chain; (3) In terms of food safety risk rating, the risk rating model lacks quantitative analysis of the spatiotemporal dimensions of the possibility and severity of food hazard factors, resulting in insufficient personalization and unsatisfactory timeliness of response and disposal plans. Summary of the invention

[0008] In view of the problems existing in the prior art, the present invention proposes a food supply chain risk perception, identification and rating system based on knowledge graph. The first purpose is to solve the problem of food safety risk identification: the currently constructed food safety knowledge graphs are mostly based on the industry's food classification standards, and do not consider the inconsistent classification of the same food in the food supply chain, resulting in a broken chain in food safety risk identification; the second purpose is to solve the problem of lack of food safety risk association identification from the perspective of supply chain migration and diffusion, and failure to make full use of massive food safety supervision sampling and risk monitoring data to reason about upstream and downstream risks of the food supply chain; the third purpose is to solve the problem of food safety risk rating: the risk rating model lacks quantitative analysis of the spatiotemporal dimensions of the possibility and severity of food hazard factors, resulting in insufficient personalization and unsatisfactory timeliness of response and disposal plans.

[0009] The present invention proposes the following technical solutions to solve the technical problems:

[0010] A food supply chain risk perception, identification and rating system based on knowledge graph, including a food supply chain risk perception module, a food supply chain risk identification module, a food supply chain risk rating module and a food supply chain response and disposal module;

[0011] The food supply chain risk perception module provides basic data for the food supply chain risk identification module;

[0012] The food supply chain risk identification module includes a food supply chain knowledge graph management submodule and a food safety knowledge graph reasoning submodule, wherein the food safety knowledge graph reasoning submodule obtains basic data from the risk perception module and sends the food safety knowledge reasoning data to the risk rating module;

[0013] The food supply chain risk rating module is a risk rating module based on the knowledge graph, which performs risk rating according to the food classification, spatiotemporal risk hierarchy, food hazard factor limit value, and food hazard factor detection value provided by the food safety knowledge graph reasoning submodule, and sends the risk rating result to the food supply chain risk response and disposal module;

[0014] The food supply chain response and disposal module is a response and disposal module based on the knowledge graph, which matches the response and disposal template according to the risk rating result of the food supply chain risk rating module and automatically generates a response and disposal plan;

[0015] Its characteristics are: the multi-level tree structure based on food ontology of the food supply chain knowledge graph management submodule includes all classification names of the same food in different food supply chain links; the food safety knowledge graph reasoning submodule first searches for the food supply chain level where the name of the currently sampled food is located, and then fuzzy matches the classification name and limit value of the currently sampled food name at the food supply chain level; the food supply chain risk rating module rates the possibility and severity of risk based on the possibility and severity of risk changes in time and space.

[0016] Furthermore, the food supply chain risk perception module provides basic data for the food supply chain risk identification module, and the basic data include: the name of the sampled food, the name of the hazard factor of the sampled food, the detection value of the hazard factor of the sampled food, the name of the sampled unit, the name of the sampled nominal production unit, the sampling time, the sampling address, the sampled production time, and the sampled production address; the name of the sampled unit is the name of the unit for food safety sampling and monitoring, including food production units and food business units; the name of the sampled nominal production unit is the name of the food production unit, which is limited to food production units and does not involve food business units.

[0017] Furthermore, the food supply chain knowledge graph management submodule constructs a food safety knowledge ontology library, and provides basic data for the food supply chain risk identification module, the food supply chain risk rating module, and the food supply chain response and disposal module in the form of entity, attribute, and relationship triples, specifically:

[0018] The knowledge graph ontology library is used for management. The highest level of the multiple hierarchical tree structures shared by the food supply chain risk identification module, the food supply chain risk rating module, and the food supply chain response and disposal module is extracted to establish an ontology. Specifically, a food ontology is established. This ontology is used in the food safety knowledge graph reasoning submodule to match the level of the food supply chain where the sampled food name is located with the food subcategories below the food ontology; a food supply chain ontology is established. This ontology is used in the food supply chain risk rating module to match the name of the sampled unit with the food supply chain subcategories below the food supply chain ontology; a food hazard factor ontology based on the food supply chain is established; this ontology is used in the food safety knowledge graph reasoning submodule to match the food classification of the sampled food name with the food hazard factor subcategories corresponding to the food classification below the food hazard factor ontology;

[0019] It is managed in the form of entities and attributes of the knowledge graph, and the upper and lower layers with a master-slave relationship with the food ontology, food supply chain ontology, and food hazard factor ontology are constructed. Specifically, a multi-layer attribute with a subordinate relationship with the food ontology is established, and a multi-level tree structure based on the food ontology is formed. The multi-level tree structure based on the food ontology includes all the classification names of the same food in different food supply chain links; the upper layer below the ontology of the multi-level tree structure is the entity, and the lower layer is the attribute of the upper layer. The multi-level tree structure is used for the risk identification module to match the name of the sampled food with an attribute in the multi-level tree structure; a multi-level attribute with a subordinate relationship with the food supply chain ontology is established, and a multi-level tree structure based on the food ontology is formed. A multi-level tree structure based on the food supply chain ontology is constructed, in which the previous level below the ontology is an entity, and the next level is an attribute of the previous level. The multi-level tree structure is used in the food supply chain risk rating module to match the name of the inspected unit with an attribute in the multi-level tree structure; a multi-level attribute with a subordinate relationship with the food hazard factor ontology is established, and a multi-level tree structure based on the food hazard factor ontology is constructed, in which the previous level below the ontology is an entity, and the next level is an attribute of the previous level; the multi-level tree structure is used in the food safety knowledge graph reasoning submodule to match the food classification of the inspected food name with an attribute corresponding to the food classification in the multi-level tree structure.

[0020] Management is carried out in the form of relations in the knowledge graph, specifically: marking the upstream and downstream in the multi-level tree structure of the food ontology, food supply chain ontology, and food hazard factor ontology; marking the restricting party and the restricted party in the multi-level tree structure of the food ontology, food supply chain ontology, and food hazard factor ontology; marking the supplier and the demander in the multi-level tree structure of the food ontology, food supply chain ontology, and food hazard factor ontology; marking the processor and the processed party in the multi-level tree structure of the food ontology, food supply chain ontology, and food hazard factor ontology.

[0021] Furthermore, the food safety knowledge graph reasoning submodule of the food supply chain risk identification module first performs knowledge reasoning on the food supply chain links for the names of the sampled foods, the names of the sampled units and the names of the sampled nominal production units input by the food supply chain risk perception module. When the name of the sampled unit in the input data is the same as the name of the sampled nominal production unit, it is considered to belong to the food production and processing link, and the production and processing link is used as the food supply chain level where the sampled food is located; when the name of the sampled unit is different from the name of the sampled nominal production unit, it is considered to belong to the food storage, transportation, circulation and catering consumption links, and the representative keywords of the unit name are matched to the subdivided links. And take this subdivision as the food supply chain level where the sampled food is located; in the multi-level tree structure based on the food supply chain ontology, search for the food supply chain level where the sampled food is located, and find the food classification of the sampled food name corresponding to the food supply chain level in the multi-level tree structure based on the food ontology, and send the food classification to the food supply chain risk rating module; for the hazard factor name of the sampled food input by the food supply chain risk perception module, search for the hazard factor limit value corresponding to the food node in the multi-level tree structure based on the food hazard factor ontology, and send the hazard factor limit value and the hazard factor detection value of the sampled food to the food supply chain risk rating module.

[0022] Furthermore, the food safety knowledge graph reasoning sub-module of the food supply chain risk identification module searches, for the name of the inspected unit input by the food supply chain risk perception module, whether the inspected unit is an upstream supply chain node or a downstream supply chain node in the multi-level tree structure based on the food supply chain ontology; if it is an upstream supply chain node, all downstream supply chain nodes corresponding to the name of the inspected nominal production unit associated with the upstream supply chain node are marked as risk nodes, and the spatiotemporal risk hierarchy corresponding to the risk node is sent to the food supply chain risk rating module.

[0023] Furthermore, the food supply chain risk rating module performs risk rating on the name of the sampled food according to the food classification name sent by the food safety knowledge graph reasoning submodule, and the corresponding hazard factor limit and hazard factor detection value; and performs spatiotemporal risk hierarchical labeling on the sampled food unit according to whether the sampled food unit is upstream or downstream in the multi-level tree structure of the food supply chain. If the sampled food unit is upstream in the multi-level tree structure of the food supply chain, all the sampled nominal production units downstream are labeled with spatiotemporal risks; if the sampled food unit is downstream in the multi-level tree structure of the food supply chain, only the current food unit is labeled with spatiotemporal risks.

[0024] Furthermore, the food supply chain risk rating module performs risk rating for the sampled food name according to the hazard factor limit and hazard factor content corresponding to the sampled food name sent by the food safety knowledge graph reasoning submodule, as follows:

[0025] The risk rating is jointly completed by the risk possibility calculation submodule P(X,T), the risk severity calculation submodule S(X,T), and the risk level assessment submodule P(X,T); the risk possibility calculation submodule comprehensively considers the possibility of food safety risk occurrence based on the detection failure rate and consumption volume; the risk severity calculation submodule determines the severity of food risk occurrence based on the degree of food contamination and the degree of harm caused by it; the risk level assessment module determines the level of food safety risk occurrence based on the possibility and severity of the risk.

[0026] Furthermore, the risk occurrence possibility calculation submodule comprehensively considers the possibility of food safety risk occurrence according to the detection failure rate and the consumption volume, specifically: the risk occurrence possibility P(X,T) is set to the product of the failure rate of the hazard factor and the food consumption volume:

[0027] P(X,T)=H(X,T)×F(X,T) (1)

[0028] Among them, H(X,T) is the distribution of the unqualified rate of the hazard factor that changes with time and space, and F(X,T) is the function of the food consumption that changes with time and space. The basic value of food consumption has different settings depending on the season and regional location.

[0029] Furthermore, the risk severity calculation submodule determines the severity of food risk according to the degree of food contamination and the degree of harm caused by the food, specifically, the risk severity S(X,T) is determined by the product of the degree of contamination of the hazard factor and the degree of harm caused by the hazard factor:

[0030] S(X,T)=I(X,T)×D(X,T) (2)

[0031] Among them, I(X,T) is called the pollution index distribution of the hazard factors that change with time and space. The hazard factors are divided into chemical hazard factors and microbial hazard factors. D(X,T) represents the hazard degree of the hazard factors that change with time and space. The hazard degree function has different settings according to the basic values ​​of the specific time and space scenarios in which different hazard factors are located.

[0032] The pollution index I of the chemical hazard factor at the specific time and space x,t The calculation is as follows:

[0033]

[0034] Among them, Mx,t Represents the detection value of the hazard factor at a specific time and space, L x,t Represents the limit value of a hazard factor at a specific time and space.

[0035] The pollution index I of a single indicator of microbial pollutants at a specific time and space x,t The calculation formula is:

[0036]

[0037] Among them, Lmin x,t Represents the minimum limit value of the hazard index at a specific time and space, Lmax x,t Represents the maximum limit value of the hazard index at a specific time and space.

[0038] Furthermore, the risk level assessment module determines the level of food safety risk according to the possibility and severity of the risk. Specifically, the food supply chain risk value R(X, T) is set as the product of the possibility P(X, T) of the hazard factor and the severity S(X, T) of the hazard factor:

[0039] R(X,T)=P(X,T)×S(X,T) (5) According to the size of the risk value R(X,T), the level of risk occurrence is divided into four levels.

[0040] Advantages and effects of the present invention

[0041] 1. The multi-level tree structure based on the food ontology of the present invention includes all classification names of the same food in different food supply chain links. Its advantage is that according to the name of the sampled food, the name of the sampled unit, and the name of the sampled nominal production unit, it can quickly find which food supply chain link it is in in the multi-level tree structure based on the food supply chain ontology, and then according to the food supply chain link it is in, the multi-level tree structure based on the food ontology is fuzzy matched for the food classification name of the current supply chain link, and then according to the food classification name, the hazard factor limit value is accurately found, and then according to the hazard factor limit value and the hazard factor detection value of the sampled food, the food safety spatiotemporal risk rating is performed, thereby making the food risk rating more dynamic and accurate.

[0042] 2. The food safety knowledge graph reasoning submodule of the present invention first searches for the supply chain level of the sampled food unit corresponding to the sampled food name before searching for the food classification of the sampled food name in the knowledge graph, and then searches for the classification of the sampled food name corresponding to it in the multi-level tree structure based on the food ontology according to the supply chain level. This solves the problem in the prior art that the same food is located in different supply chain links, resulting in different classification names, leading to a broken chain in food safety risk identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is a block diagram of the food supply chain risk perception, identification, and rating system used in the present invention;

[0044] Figure 2 This is a flow chart of the food safety knowledge graph reasoning submodule of the present invention;

[0045] Figure 3 This is a schematic diagram of an ontology library based on a food supply chain of the present invention;

[0046] Figure 4 This is a schematic diagram of the knowledge graph based on the food supply chain of the present invention; DETAILED DESCRIPTION

[0047] Design principle of the present invention

[0048] 1. Innovations of the present invention:

[0049] One of the innovations is to organically combine the three information islands of the existing technology (food classification, food supply chain, and food hazard factors) through the knowledge graph. First, organically combine food classification and food supply chain: (1) In the establishment of the knowledge graph (food supply chain knowledge graph management submodule), the food classification commonly used in different industries is integrated with the food supply chain link. In the multi-level tree structure based on the food ontology, the same food entity may correspond to the names of multiple supply chains. The entity is the upper layer, and the names of multiple supply chains are the lower layer of the entity. Then, each supply chain is an entity, and each entity is further subdivided into multiple food classifications, thereby organically combining the multi-level tree structure based on the food ontology and the food supply chain; (2) In the risk reasoning process of the knowledge graph (food safety knowledge graph reasoning submodule), first search for the food supply chain link where the name of the sampled food is located. After determining the food supply chain link where the name of the sampled food is located, search for the food classification corresponding to the food supply chain link in the multi-level tree structure based on the food ontology; conversely, if you don’t know which link the name of the current sampled food is in, it is equivalent to not having a search keyword, and you can’t search without a search keyword. Second, the food hazard factors and the food supply chain are organically combined. In different food supply chain links, the food hazard factor limits of the same food name are different. Before searching for the hazard factor limit corresponding to the sampled food name, the present invention first searches for the food supply chain link where the sampled food name is located, then searches for the food classification according to the food supply chain link, and finally searches for the hazard factor limit corresponding to the food classification.

[0050] The second innovation of the present invention is that it uses the upstream and downstream relationships of the knowledge graph to identify and rate spatiotemporal risks. If the inspected unit is located in an upstream enterprise, then all its downstream related inspected nominal production enterprises will be rated for spatiotemporal risks.

[0051] The third innovation of the present invention is to perform spatiotemporal risk rating according to the possibility and severity of the risk. The possibility P(X, T) and severity S(X, T) here change with the change of time and space, rather than being static. The time refers to the sampling time or the production time of the sampled product, and the space refers to the sampling location or the production location of the sampled product.

[0052] In summary, the present invention accurately finds food classification through the knowledge graph food supply chain, and then accurately finds the corresponding hazard factor limit through food classification, and then quickly finds the correspondence between upstream and downstream in the supply chain through the knowledge graph food supply chain, and then accurately captures the risk radiation area through the upstream and downstream correspondence, and then performs risk rating of the risk radiation area including time and space information, so that the risk rating is more accurate and scientific.

[0053] Based on the above principles, the present invention designs a food supply chain risk perception, identification and rating system based on knowledge graph. Figure 1 As shown, it includes a food supply chain risk perception module, a food supply chain risk identification module, a food supply chain risk rating module, and a food supply chain response and disposal module;

[0054] The food supply chain risk perception module provides basic data for the food supply chain risk identification module;

[0055] The food supply chain risk identification module includes a food supply chain knowledge graph management submodule and a food safety knowledge graph reasoning submodule, wherein the food safety knowledge graph reasoning submodule obtains basic data from the risk perception module and sends the food safety knowledge reasoning data to the risk rating module;

[0056] The food supply chain risk rating module is a risk rating module based on the knowledge graph, which performs risk rating according to the food classification, spatiotemporal risk hierarchy, food hazard factor limit value, and food hazard factor detection value provided by the food safety knowledge graph reasoning submodule, and sends the risk rating result to the food supply chain risk response and disposal module;

[0057] The food supply chain response and disposal module is a response and disposal module based on the knowledge graph, which matches the response and disposal template according to the risk rating result of the food supply chain risk rating module and automatically generates a response and disposal plan;

[0058] Its characteristics are: the multi-level tree structure based on food ontology of the food supply chain knowledge graph management submodule includes all classification names of the same food in different food supply chain links; the food safety knowledge graph reasoning submodule first searches for the food supply chain level where the name of the currently sampled food is located, and then fuzzy matches the classification name and limit value of the currently sampled food name at the food supply chain level; the food supply chain risk rating module rates the possibility and severity of risk based on the possibility and severity of risk changes in time and space.

[0059] like Figure 1 As shown, the food supply chain risk perception module provides basic data for the food supply chain risk identification module, and the basic data include: the name of the sampled food, the name of the hazard factor of the sampled food, the detection value of the hazard factor of the sampled food, the name of the sampled unit, the name of the sampled nominal production unit, the sampling time, the sampling address, the sampled production time, and the sampled production address; the name of the sampled unit is the name of the unit for food safety sampling and monitoring, including food production units and food business units; the name of the sampled nominal production unit is the name of the food production unit, which is limited to food production units and does not involve food business units.

[0060] Furthermore, the food supply chain knowledge graph management submodule constructs a food safety knowledge ontology library, and provides basic data for the food supply chain risk identification module, the food supply chain risk rating module, and the food supply chain response and disposal module in the form of entity, attribute, and relationship triples, specifically:

[0061] like Figure 3 As shown, the knowledge graph ontology library is used for management, and the highest level of the multiple hierarchical tree structures shared by the food supply chain risk identification module, the food supply chain risk rating module, and the food supply chain response and disposal module is extracted to establish an ontology, specifically: establish a food ontology, which is used in the food safety knowledge graph reasoning submodule to match the level of the food supply chain where the sampled food name is located with the food subcategories below the food ontology; establish a food supply chain ontology, which is used in the food supply chain risk rating module to match the name of the sampled unit with the food supply chain subcategories below the food supply chain ontology; establish a food hazard factor ontology based on the food supply chain; this ontology is used in the food safety knowledge graph reasoning submodule to match the food classification of the sampled food name with the food hazard factor subcategories corresponding to the food classification under the food hazard factor ontology;

[0062] It is managed in the form of entities and attributes of the knowledge graph, and the upper and lower layers with a master-slave relationship with the food ontology, food supply chain ontology, and food hazard factor ontology are constructed. Specifically, a multi-layer attribute with a subordinate relationship with the food ontology is established, and a multi-level tree structure based on the food ontology is formed. The multi-level tree structure based on the food ontology includes all the classification names of the same food in different food supply chain links; the upper layer below the ontology of the multi-level tree structure is the entity, and the lower layer is the attribute of the upper layer. The multi-level tree structure is used for the risk identification module to match the name of the sampled food with an attribute in the multi-level tree structure; a multi-level attribute with a subordinate relationship with the food supply chain ontology is established, and a multi-level tree structure based on the food ontology is formed. A multi-level tree structure based on the food supply chain ontology is constructed, in which the previous level below the ontology is an entity, and the next level is an attribute of the previous level. The multi-level tree structure is used in the food supply chain risk rating module to match the name of the inspected unit with an attribute in the multi-level tree structure; a multi-level attribute with a subordinate relationship with the food hazard factor ontology is established, and a multi-level tree structure based on the food hazard factor ontology is constructed, in which the previous level below the ontology is an entity, and the next level is an attribute of the previous level; the multi-level tree structure is used in the food safety knowledge graph reasoning submodule to match the food classification of the inspected food name with an attribute corresponding to the food classification in the multi-level tree structure.

[0063] Management is carried out in the form of relations in the knowledge graph, specifically: marking the upstream and downstream in the multi-level tree structure of the food ontology, food supply chain ontology, and food hazard factor ontology; marking the restricting party and the restricted party in the multi-level tree structure of the food ontology, food supply chain ontology, and food hazard factor ontology; marking the supplier and the demander in the multi-level tree structure of the food ontology, food supply chain ontology, and food hazard factor ontology; marking the processor and the processed party in the multi-level tree structure of the food ontology, food supply chain ontology, and food hazard factor ontology.

[0064] like Figure 1 As shown, the food safety knowledge graph reasoning submodule of the food supply chain risk identification module first performs knowledge reasoning on the food supply chain links for the inspected food name, inspected unit name and inspected nominal production unit name input by the food supply chain risk perception module. When the inspected unit name of the input data is the same as the inspected nominal production unit name, it is considered to belong to the food production and processing link, and the production and processing link is used as the food supply chain level where the inspected food is located; when the inspected unit name is different from the inspected nominal production unit name, it is considered to belong to the food storage, transportation, circulation and catering consumption link, and the representative keywords of the unit name are matched to the subdivided link, and Take this subdivision as the food supply chain level where the sampled food is located; in the multi-level tree structure based on the food supply chain ontology, search for the food supply chain level where the sampled food is located, and find the food classification of the sampled food name corresponding to the food supply chain level in the multi-level tree structure based on the food ontology, and send the food classification to the food supply chain risk rating module; for the hazard factor name of the sampled food input by the food supply chain risk perception module, search for the hazard factor limit value corresponding to the food node in the multi-level tree structure based on the food hazard factor ontology, and send the hazard factor limit value and the hazard factor detection value of the sampled food to the food supply chain risk rating module.

[0065] Furthermore, the food safety knowledge graph reasoning sub-module of the food supply chain risk identification module searches, for the name of the inspected unit input by the food supply chain risk perception module, whether the inspected unit is an upstream supply chain node or a downstream supply chain node in the multi-level tree structure based on the food supply chain ontology; if it is an upstream supply chain node, all downstream supply chain nodes corresponding to the name of the inspected nominal production unit associated with the upstream supply chain node are marked as risk nodes, and the spatiotemporal risk hierarchy corresponding to the risk node is sent to the food supply chain risk rating module.

[0066] Supplementary Note 1:

[0067] The time-space risk hierarchy refers to the sampling time, sampling address, sampling production time, and sampling production address. These information come from the risk perception module, which passes this information to the risk identification module, and the risk identification module passes this information to the risk rating module.

[0068] Furthermore, the food supply chain risk rating module performs risk rating on the name of the sampled food according to the food classification name sent by the food safety knowledge graph reasoning submodule, and the corresponding hazard factor limit and hazard factor detection value; and performs spatiotemporal risk hierarchical labeling on the sampled food unit according to whether the sampled food unit is upstream or downstream in the multi-level tree structure of the food supply chain. If the sampled food unit is upstream in the multi-level tree structure of the food supply chain, all the sampled nominal production units downstream are labeled with spatiotemporal risks; if the sampled food unit is downstream in the multi-level tree structure of the food supply chain, only the current food unit is labeled with spatiotemporal risks.

[0069] Furthermore, the food supply chain risk rating module performs risk rating for the sampled food name according to the hazard factor limit and hazard factor content corresponding to the sampled food name sent by the food safety knowledge graph reasoning submodule, as follows:

[0070] The risk rating is jointly completed by the risk possibility calculation submodule P(X,T), the risk severity calculation submodule S(X,T), and the risk level assessment submodule P(X,T); the risk possibility calculation submodule comprehensively considers the possibility of food safety risk occurrence based on the detection failure rate and consumption volume; the risk severity calculation submodule determines the severity of food risk occurrence based on the degree of food contamination and the degree of harm caused by it; the risk level assessment module determines the level of food safety risk occurrence based on the possibility and severity of the risk.

[0071] Furthermore, the risk occurrence possibility calculation submodule comprehensively considers the possibility of food safety risk occurrence according to the detection failure rate and the consumption volume, specifically: the risk occurrence possibility P(X,T) is set to the product of the failure rate of the hazard factor and the food consumption volume:

[0072] P(X,T)=H(X,T)×F(X,T) (1)

[0073] Among them, H(X,T) is the distribution of the unqualified rate of the hazard factor that changes with time and space, and F(X,T) is the function of the food consumption that changes with time and space. The basic value of food consumption has different settings depending on the season and regional location.

[0074] Supplementary Note 2:

[0075] Time change information is used for dynamic risk rating by the risk rating module. Risk rating should not only be based on the limit value of the hazard factor being sampled and the detection value of the hazard factor being sampled, but also on the time change information. That is, it is necessary to consider whether the intelligent response and disposal module has eliminated the current risk before conducting risk rating. Spatial change information is also used for risk rating. Spatial information refers to the sampling location and the sampled production location. If risks occur repeatedly at the same sampling location or the same sampled production location, the severity level will be relatively high.

[0076] Furthermore, the risk severity calculation submodule determines the severity of food risk according to the degree of food contamination and the degree of harm caused by the food, specifically, the risk severity S(X,T) is determined by the product of the degree of contamination of the hazard factor and the degree of harm caused by the hazard factor:

[0077] S(X,T)=I(X,T)×D(X,T) (2)

[0078] Among them, I(X,T) is called the pollution index distribution of the hazard factors that change with time and space. The hazard factors are divided into chemical hazard factors and microbial hazard factors. D(X,T) represents the hazard degree of the hazard factors that change with time and space. The hazard degree function has different settings according to the basic values ​​of the specific time and space scenarios in which different hazard factors are located.

[0079] The pollution index I of the chemical hazard factor at the specific time and space x,t The calculation is as follows:

[0080]

[0081] Among them, M x,t Represents the detection value of the hazard factor at a specific time and space, L x,t Represents the limit value of a hazard factor at a specific time and space.

[0082] The pollution index I of a single indicator of microbial pollutants at a specific time and space x,t The calculation formula is:

[0083]

[0084] Among them, Lmin x,t Represents the minimum limit value of the hazard index at a specific time and space, Lmax x,t Represents the maximum limit value of the hazard index at a specific time and space.

[0085] Furthermore, the risk level assessment module determines the level of food safety risk according to the possibility and severity of the risk. Specifically, the food supply chain risk value R(X, T) is set as the product of the possibility P(X, T) of the hazard factor and the severity S(X, T) of the hazard factor:

[0086] R(X,T)=P(X,T)×S(X,T) (5) According to the size of the risk value R(X,T), the level of risk occurrence is divided into four levels.

[0087] Supplementary Note 3:

[0088] The food supply chain risk intelligent response and disposal module automatically generates a response and disposal plan according to the food classification, associated risk hierarchy and risk level result matching response and disposal template of the link where the food supply chain risk is located. For details, please refer to the invention patent 202210533370.6 Food safety risk response and disposal method, electronic device and storage medium, which will not be described in detail here.

[0089] The above contents are merely examples and explanations of the concept of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

Claims

1. A food supply chain risk perception, identification and rating system based on knowledge graph, including a food supply chain risk perception module, a food supply chain risk identification module, a food supply chain risk rating module and a food supply chain response and disposal module; The food supply chain risk perception module provides basic data for the food supply chain risk identification module; The food supply chain risk identification module includes a food supply chain knowledge graph management submodule and a food safety knowledge graph reasoning submodule, wherein the food safety knowledge graph reasoning submodule obtains basic data from the risk perception module and sends the food safety knowledge reasoning data to the risk rating module; The food supply chain risk rating module is a risk rating module based on the knowledge graph, which performs risk rating according to the food classification, spatiotemporal risk hierarchy, food hazard factor limit value, and food hazard factor detection value provided by the food safety knowledge graph reasoning submodule, and sends the risk rating result to the food supply chain risk response and disposal module; The food supply chain response and disposal module is a response and disposal module based on the knowledge graph, which matches the response and disposal template according to the risk rating result of the food supply chain risk rating module and automatically generates a response and disposal plan; Features: The multi-level tree structure based on food ontology of the food supply chain knowledge graph management submodule includes all classification names of the same food in different food supply chain links; the food safety knowledge graph reasoning submodule first searches for the food supply chain level where the name of the currently sampled food is located, and then fuzzy matches the classification name and limit value of the currently sampled food name at the food supply chain level; the food supply chain risk rating module rates the possibility and severity of risk based on temporal and spatial changes.

2. A food supply chain risk perception, identification and rating system based on knowledge graph according to claim 1, characterized in that: The food supply chain risk perception module provides basic data for the food supply chain risk identification module, and the basic data include: the name of the sampled food, the name of the hazard factor of the sampled food, the detection value of the hazard factor of the sampled food, the name of the sampled unit, the name of the sampled nominal production unit, the sampling time, the sampling address, the sampled production time, and the sampled production address; the name of the sampled unit is the name of the unit for food safety sampling and monitoring, including food production units and food business units; the name of the sampled nominal production unit is the name of the food production unit, which is limited to food production units and does not involve food business units.

3. According to claim 1, a food supply chain risk perception, identification and rating system based on knowledge graph is characterized by: The food supply chain knowledge graph management submodule constructs a food safety knowledge ontology library and provides basic data for the food supply chain risk identification module, food supply chain risk rating module, and food supply chain response and disposal module in the form of entity, attribute, and relationship triples, specifically: The knowledge graph ontology library is used for management. The highest level of the multiple hierarchical tree structures shared by the food supply chain risk identification module, the food supply chain risk rating module, and the food supply chain response and disposal module is extracted to establish an ontology. Specifically, a food ontology is established. This ontology is used in the food safety knowledge graph reasoning submodule to match the level of the food supply chain where the sampled food name is located with the food subcategories below the food ontology; a food supply chain ontology is established. This ontology is used in the food supply chain risk rating module to match the name of the sampled unit with the food supply chain subcategories below the food supply chain ontology; a food hazard factor ontology based on the food supply chain is established; this ontology is used in the food safety knowledge graph reasoning submodule to match the food classification of the sampled food name with the food hazard factor subcategories corresponding to the food classification below the food hazard factor ontology; It is managed in the form of entities and attributes of the knowledge graph, and the upper and lower layers with a master-slave relationship with the food ontology, food supply chain ontology, and food hazard factor ontology are constructed. Specifically, a multi-layer attribute with a subordinate relationship with the food ontology is established, and a multi-level tree structure based on the food ontology is formed. The multi-level tree structure based on the food ontology includes all the classification names of the same food in different food supply chain links; the upper layer below the ontology of the multi-level tree structure is the entity, and the lower layer is the attribute of the upper layer. The multi-level tree structure is used for the risk identification module to match the name of the sampled food with an attribute in the multi-level tree structure; a multi-level attribute with a subordinate relationship with the food supply chain ontology is established, and a multi-level tree structure based on the food ontology is formed. A multi-level tree structure based on the food supply chain ontology is constructed, in which the previous level below the ontology is an entity, and the next level is an attribute of the previous level. The multi-level tree structure is used in the food supply chain risk rating module to match the name of the inspected unit with an attribute in the multi-level tree structure; a multi-level attribute with a subordinate relationship with the food hazard factor ontology is established, and a multi-level tree structure based on the food hazard factor ontology is constructed, in which the previous level below the ontology is an entity, and the next level is an attribute of the previous level; the multi-level tree structure is used in the food safety knowledge graph reasoning submodule to match the food classification of the inspected food name with an attribute corresponding to the food classification in the multi-level tree structure. Management is carried out in the form of relations in the knowledge graph, specifically: marking the upstream and downstream in the multi-level tree structure of the food ontology, food supply chain ontology, and food hazard factor ontology; marking the restricting party and the restricted party in the multi-level tree structure of the food ontology, food supply chain ontology, and food hazard factor ontology; marking the supplier and the demander in the multi-level tree structure of the food ontology, food supply chain ontology, and food hazard factor ontology; marking the processor and the processed party in the multi-level tree structure of the food ontology, food supply chain ontology, and food hazard factor ontology.

4. A food supply chain risk perception, identification and rating system based on knowledge graph according to claim 3, characterized in that: The food safety knowledge graph reasoning submodule of the food supply chain risk identification module first performs knowledge reasoning on the food supply chain links for the names of the sampled foods, the names of the sampled units and the names of the sampled nominal production units input by the food supply chain risk perception module. When the name of the sampled unit in the input data is the same as the name of the sampled nominal production unit, it is considered to belong to the food production and processing link, and the production and processing link is used as the food supply chain level where the sampled food is located; when the name of the sampled unit is different from the name of the sampled nominal production unit, it is considered to belong to the food storage, transportation, circulation and catering consumption links, and the representative keywords of the unit name are used to match the subdivided links to which it belongs, and the production and processing link is used as the food supply chain level where the sampled food is located. The subdivided links are used as the food supply chain level where the sampled food is located; in the multi-level tree structure based on the food supply chain ontology, the food supply chain level where the sampled food is located is searched, and the food classification of the sampled food name corresponding to the food supply chain level is found in the multi-level tree structure based on the food ontology, and the food classification is sent to the food supply chain risk rating module; for the hazard factor name of the sampled food input by the food supply chain risk perception module, in the multi-level tree structure based on the food hazard factor ontology, the hazard factor limit value corresponding to the food node is searched, and the hazard factor limit value and the hazard factor detection value of the sampled food are sent to the food supply chain risk rating module.

5. According to claim 3, a food supply chain risk perception, identification and rating system based on knowledge graph is characterized by: The food safety knowledge graph reasoning submodule of the food supply chain risk identification module searches for the name of the inspected unit input by the food supply chain risk perception module in the multi-level tree structure based on the food supply chain ontology to determine whether the inspected unit is an upstream supply chain node or a downstream supply chain node. If it is an upstream supply chain node, all downstream supply chain nodes corresponding to the name of the inspected nominal production unit associated with the upstream supply chain node are marked as risk nodes, and the spatiotemporal risk hierarchy corresponding to the risk node is sent to the food supply chain risk rating module.

6. A food supply chain risk perception, identification and rating system based on knowledge graph according to claim 5, characterized in that: The food supply chain risk rating module performs risk rating on the sampled food name according to the food classification name sent by the food safety knowledge graph reasoning submodule, and the corresponding hazard factor limit and hazard factor detection value; And according to whether the sampled food unit is located upstream or downstream in the multi-level tree structure of the food supply chain, the spatiotemporal risk level of the sampled food unit is marked. If the sampled food unit is located upstream in the multi-level tree structure of the food supply chain, all the sampled nominal production units downstream are marked with spatiotemporal risks. If the sampled food unit is located downstream in the multi-level tree structure of the food supply chain, only the current food unit is marked with spatiotemporal risks.

7. A food supply chain risk perception, identification and rating system based on knowledge graph according to claim 6, characterized in that: The food supply chain risk rating module performs risk rating on the sampled food name according to the hazard factor limit and hazard factor content corresponding to the sampled food name sent by the food safety knowledge graph reasoning submodule, as follows: The risk rating is jointly completed by the risk possibility calculation submodule P(X, T), the risk severity calculation submodule S(X, T), and the risk level assessment submodule P(X, T); the risk possibility calculation submodule comprehensively considers the possibility of food safety risk occurrence based on the detection failure rate and consumption volume; the risk severity calculation submodule determines the severity of food risk occurrence based on the degree of food contamination and the degree of harm caused by it; the risk level assessment module determines the level of food safety risk occurrence based on the possibility and severity of the risk occurrence.

8. A food supply chain risk perception, identification and rating system based on knowledge graph according to claim 7, characterized in that: The risk occurrence possibility calculation submodule comprehensively considers the possibility of food safety risk occurrence according to the detection failure rate and the consumption volume, specifically: the risk occurrence possibility P(X, T) is set to the product of the failure rate of the hazard factor and the food consumption volume: P(X,T)=H(X,T)×F(X,T) (1) Among them, H(X, T) is the distribution of the unqualified rate of the hazard factor that changes with time and space, and F(X, T) is the function of the food consumption that changes with time and space. The basic value of food consumption has different settings depending on the season and regional location.

9. A food supply chain risk perception, identification and rating system based on knowledge graph according to claim 7, characterized in that: The risk severity calculation submodule determines the severity of food risk according to the degree of food contamination and the degree of harm caused by it. Specifically, the risk severity S(X, T) is determined by the product of the degree of contamination of the hazard factor and the degree of harm caused by it. S(X,T)=I(X,T)×D(X,T) (2) Among them, I(X, T) is called the pollution index distribution of the hazard factors that change with time and space. The hazard factors are divided into chemical hazard factors and microbial hazard factors. D(X, T) represents the hazard degree of the hazard factors that change with time and space. The hazard degree function has different settings according to the basic values ​​of the specific time and space scenarios in which different hazard factors are located. The pollution index I of the chemical hazard factor at the specific time and space x，t The calculation is as follows: Among them, M x，t Represents the detection value of the hazard factor at a specific time and space, L x，t Represents the limit value of a hazard factor at a specific time and space. The pollution index I of a single indicator of microbial pollutants at a specific time and space x，t The calculation formula is: Among them, Lmin x，t Represents the minimum limit value of the hazard index at a specific time and space, Lmax x，t Represents the maximum limit value of the hazard index at a specific time and space.

10. The food supply chain risk perception, identification and rating system based on knowledge graph according to claim 7 is characterized by: The risk level assessment module determines the level of food safety risk according to the possibility and severity of the risk. Specifically, the food supply chain risk value R(X, T) is set to the product of the possibility of the hazard factor P(X, T) and the severity S(X, T) of the hazard factor: R(X,T)=P(X,T)×S(X,T) (5) According to the size of the risk value R(X, T), the level of risk occurrence is divided into four levels.

Images