[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

CN116777205A - Supply chain risk pre-judging method, electronic equipment and storage medium - Google Patents

Supply chain risk pre-judging method, electronic equipment and storage medium Download PDF

Info

Publication number
CN116777205A
CN116777205A CN202310633258.4A CN202310633258A CN116777205A CN 116777205 A CN116777205 A CN 116777205A CN 202310633258 A CN202310633258 A CN 202310633258A CN 116777205 A CN116777205 A CN 116777205A
Authority
CN
China
Prior art keywords
risk
provider
supply chain
centrality
judging
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202310633258.4A
Other languages
Chinese (zh)
Inventor
李翔宇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Great Wall Motor Co Ltd
Original Assignee
Great Wall Motor Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Great Wall Motor Co Ltd filed Critical Great Wall Motor Co Ltd
Priority to CN202310633258.4A priority Critical patent/CN116777205A/en
Publication of CN116777205A publication Critical patent/CN116777205A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063Operations research, analysis or management
    • G06Q10/0635Risk analysis of enterprise or organisation activities
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/23Clustering techniques
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00Computing arrangements using knowledge-based models
    • G06N5/01Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00Computing arrangements using knowledge-based models
    • G06N5/02Knowledge representation; Symbolic representation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00Commerce
    • G06Q30/06Buying, selling or leasing transactions
    • G06Q30/0601Electronic shopping [e-shopping]
    • G06Q30/0605Supply or demand aggregation

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Computing Systems (AREA)
  • General Business, Economics & Management (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Educational Administration (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application provides a supply chain risk pre-judging method, electronic equipment and a storage medium. The method comprises the following steps: acquiring material supply historical data of a plurality of suppliers; analyzing the association relation of each supplier according to the material supply history data, and constructing an association relation knowledge graph; and performing risk pre-judging operations on one or more suppliers in response to the risk pre-judging instructions, and acquiring one or more risk pre-judging results in a risk supply chain, a risk range, a problem supplier and a risk community. The application can realize the identification and structural visualization of the association condition of each supplier at the upstream and downstream of the supply chain, conveniently, intuitively and accurately determine the risk condition of the suppliers through the association relation knowledge graph, and in addition, the application combines a plurality of risk prejudging modes to realize the risk prejudgment of different dimensionalities, thereby meeting the personalized risk prejudgment requirement of users, and simultaneously realizing comprehensive risk prejudgment so as to improve the influence degree judgment accuracy of the problem suppliers on the whole supply chain.

Description

Supply chain risk pre-judging method, electronic equipment and storage medium
Technical Field
The present application relates to the field of supply chain technologies, and in particular, to a supply chain risk prediction method, an electronic device, and a storage medium.
Background
The supply chain refers to the entire chain of products from the merchant to the consumer during production and distribution, involving the formation of a network chain by the enterprises upstream and downstream of the end user's activities to which the products or services are provided. The dynamic market competition environment and changing customer requirements lead to an increasing uncertainty in the supply chain due to uncertainty factors both internal and external to the supply chain, which creates a number of risks in the operation of the supply chain. These risks result in reduced supply chain efficiency, increased costs, and losses to the enterprise throughout the supply chain.
In the process of implementing the embodiment of the application, the prior art is found to have at least the following problems:
when a problem occurs to one or a plurality of suppliers in the existing supply chain risk management scheme, the degree of influence of the problem supplier on the whole supply chain is judged with low accuracy.
Disclosure of Invention
The embodiment of the application provides a supply chain risk pre-judging method, electronic equipment and a storage medium, which are used for solving the problem that in the existing supply chain risk management scheme, the influence degree judgment accuracy of a problem provider on the whole supply chain is low.
In a first aspect, an embodiment of the present application provides a supply chain risk prediction method, including:
Acquiring material supply historical data of a plurality of suppliers;
analyzing the association relation of each supplier according to the material supply history data, and constructing an association relation knowledge graph;
and performing risk pre-judging operations on one or more suppliers in response to the risk pre-judging instructions, and acquiring one or more risk pre-judging results in a risk supply chain, a risk range, a problem supplier and a risk community.
In one possible implementation, the risk pre-judging operation includes: risk supply chain prejudgment, risk range prejudgment, problem provider prejudgment and risk community prejudgment.
In one possible implementation, the risk supply chain pre-determination includes:
when a problem provider exists, determining a risk node set formed by all upstream nodes and downstream nodes of the problem provider according to the association relationship knowledge graph;
and determining the corresponding supply chain as a risk supply chain according to the risk node set.
In one possible implementation, the risk range pre-determination includes:
inquiring a key node set in the association relation knowledge graph;
if the target provider is in the key node set, inquiring the shortest path set based on the key node corresponding to the target provider; wherein the shortest paths are all shortest paths between two suppliers with the target supplier as a key node;
And the coverage range of each node in the shortest path set is a risk range.
In one possible implementation, the problem provider pre-determination includes:
calculating the centrality value of each provider according to a preset centrality measurement algorithm and the association relation knowledge graph, and determining the provider corresponding to the centrality value larger than the centrality threshold as a problem provider; wherein the preset centrality measurement algorithm is one or more of Degree Centrality algorithm, weighted Degree Centrality algorithm, betweenness Centrality algorithm and Closeness centrality algorithm; or,
calculating the centrality value of each provider according to a preset feature vector centrality algorithm and the association relationship knowledge graph, and determining the provider corresponding to the centrality value larger than the centrality threshold as the problem provider; the preset feature vector centrality algorithm is a PageRank algorithm.
In one possible implementation, the risk community pre-determination includes: clustering all suppliers according to a preset community discovery algorithm and the association relationship knowledge graph to obtain a plurality of supplier communities;
determining a vendor community including the problem vendor as a risk community.
In one possible implementation, the risk pre-determining instruction includes: a risk pre-judging automatic mode instruction and a target provider risk inquiry instruction;
the performing risk prognosis for one or more suppliers in response to the risk prognosis instruction includes:
responding to the risk pre-judging automatic mode instruction, and executing risk pre-judging on each provider according to a set period; the risk pre-judging automatic mode instruction comprises a set period, or the system is preset with the set period and supports self definition;
responding to a target provider risk inquiry instruction, and executing risk pre-judging operation on a target provider corresponding to the target provider risk inquiry instruction; wherein the target provider risk query instruction includes one or more target provider identification information.
In one possible implementation, the method further includes:
updating the association relationship knowledge graph according to the material supply history data of a plurality of suppliers;
the operation of updating the association relationship knowledge graph according to the material supply history data of the multiple suppliers is executed according to a set updating period, or the operation of updating the association relationship knowledge graph according to the material supply history data of the multiple suppliers is executed after the supplier set is adjusted; the adjusting the set of suppliers includes adding suppliers, deleting suppliers, or replacing suppliers.
In one possible implementation manner, the analyzing the association relationship of each supplier according to the material supply history data and constructing an association relationship knowledge graph includes:
storing the material supply history data in a non-relational database;
preprocessing the material supply history data, and determining association relationship information between supplier identification information and suppliers;
constructing a supplier identification information table and an association relation information table, and correspondingly storing the supplier identification information and the association relation information;
and designing a Schema model in the knowledge graph, establishing a provider node according to the provider identification information table, and establishing an association side according to the association information table to obtain an association knowledge graph.
In a second aspect, an embodiment of the present application provides a supply chain risk predicting apparatus, including:
the acquisition module is used for acquiring material supply historical data of a plurality of suppliers;
the construction module is used for analyzing the association relation of each supplier according to the material supply historical data and constructing an association relation knowledge graph;
and the pre-judging module is used for responding to the risk pre-judging instruction to execute risk pre-judging operation on one or more suppliers and obtaining one or more risk pre-judging results in a risk supply chain, a risk range, a problem supplier and a risk community.
In one possible implementation, the risk pre-judging operation includes: risk supply chain prejudgment, risk range prejudgment, problem provider prejudgment and risk community prejudgment.
In one possible implementation manner, the pre-judging module is used for executing risk supply chain pre-judgment, and is specifically used for:
when a problem provider exists, determining a risk node set formed by all upstream nodes and downstream nodes of the problem provider according to the association relationship knowledge graph;
and determining the corresponding supply chain as a risk supply chain according to the risk node set.
In one possible implementation manner, the pre-judging module is configured to perform risk range pre-judging, specifically, to:
inquiring a key node set in the association relation knowledge graph;
if the target provider is in the key node set, inquiring the shortest path set based on the key node corresponding to the target provider; wherein the shortest paths are all shortest paths between two suppliers with the target supplier as a key node;
and the coverage range of each node in the shortest path set is a risk range.
In one possible implementation manner, the pre-judging module is configured to perform pre-judging of the problem provider, specifically:
Calculating the centrality value of each provider according to a preset centrality measurement algorithm and the association relation knowledge graph, and determining the provider corresponding to the centrality value larger than the centrality threshold as a problem provider; wherein the preset centrality measurement algorithm is one or more of Degree Centrality algorithm, weighted Degree Centrality algorithm, betweenness Centrality algorithm and Closeness centrality algorithm; or,
calculating the centrality value of each provider according to a preset feature vector centrality algorithm and the association relationship knowledge graph, and determining the provider corresponding to the centrality value larger than the centrality threshold as the problem provider; the preset feature vector centrality algorithm is a PageRank algorithm.
In one possible implementation manner, the pre-judging module is configured to perform risk community pre-judgment, specifically:
clustering all suppliers according to a preset community discovery algorithm and the association relationship knowledge graph to obtain a plurality of supplier communities;
determining a vendor community including the problem vendor as a risk community.
In one possible implementation, the risk pre-determining instruction includes: a risk pre-judging automatic mode instruction and a target provider risk inquiry instruction;
The prejudgment module is specifically configured to:
responding to the risk pre-judging automatic mode instruction, and executing risk pre-judging on each provider according to a set period; the risk pre-judging automatic mode instruction comprises a set period, or the system is preset with the set period and supports self definition;
responding to a target provider risk inquiry instruction, and executing risk pre-judging operation on a target provider corresponding to the target provider risk inquiry instruction; wherein the target provider risk query instruction includes one or more target provider identification information.
In one possible implementation manner, the construction module is further configured to:
updating the association relationship knowledge graph according to the material supply history data of a plurality of suppliers;
the operation of updating the association relationship knowledge graph according to the material supply history data of the multiple suppliers is executed according to a set updating period, or the operation of updating the association relationship knowledge graph according to the material supply history data of the multiple suppliers is executed after the supplier set is adjusted; the adjusting the set of suppliers includes adding suppliers, deleting suppliers, or replacing suppliers.
In a possible implementation manner, the construction module is specifically configured to:
Storing the material supply history data in a non-relational database;
preprocessing the material supply history data, and determining association relationship information between supplier identification information and suppliers;
constructing a supplier identification information table and an association relation information table, and correspondingly storing the supplier identification information and the association relation information;
and designing a Schema model in the knowledge graph, establishing a provider node according to the provider identification information table, and establishing an association side according to the association information table to obtain an association knowledge graph.
In a third aspect, an embodiment of the present application provides an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method according to the first aspect or any one of the possible implementations of the first aspect, when the computer program is executed by the processor.
In a fourth aspect, embodiments of the present application provide a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the method as described above in the first aspect or any one of the possible implementations of the first aspect.
The embodiment of the application provides a supply chain risk pre-judging method, electronic equipment and a storage medium, which are used for analyzing the association relation of each supplier according to material supply historical data by acquiring the material supply historical data of a plurality of suppliers and constructing an association relation knowledge graph, so that the identification and structure visualization of the association condition of each supplier at the upstream and downstream of a supply chain are realized, and the risk condition of the suppliers is conveniently, intuitively and accurately determined through the association relation knowledge graph. In addition, a risk pre-judging operation is performed on one or more suppliers in response to the risk pre-judging instruction, one or more risk pre-judging results in a risk supply chain, a risk range, a problem supplier and a risk community are obtained, and risk pre-judging in different dimensions is realized by combining multiple risk pre-judging modes, so that personalized risk pre-judging requirements of users are met, and meanwhile comprehensive risk pre-judging can be realized, so that the accuracy of judging the influence degree of the problem supplier on the whole supply chain is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart illustrating a supply chain risk prediction method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a knowledge graph of an association relationship provided in an embodiment of the present application;
FIG. 3 is a schematic diagram of a knowledge graph of an association relationship according to an embodiment of the present application;
FIG. 4 is a schematic diagram of a knowledge graph of an association relationship according to another embodiment of the present application;
FIG. 5 is a schematic diagram of the center of the betweenness provided by an embodiment of the present application;
FIG. 6 is a schematic diagram of a knowledge graph of an association relationship according to another embodiment of the present application;
FIG. 7 is a schematic diagram of compactness centrality provided by an embodiment of the present application;
FIG. 8 is a schematic diagram of a supply chain risk prediction device according to an embodiment of the present application;
fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
The terms first, second and the like in the description and in the claims of embodiments of the application and in the above-described figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe embodiments of the application herein. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion.
The term "plurality" means two or more, unless otherwise indicated. The character "/" indicates that the front and rear objects are an "or" relationship. For example, A/B represents: a or B. The term "and/or" is an associative relationship that describes an object, meaning that there may be three relationships. For example, a and/or B, represent: a or B, or, A and B.
The terminology used in the present application is used for the purpose of describing embodiments only and is not intended to limit the claims. As used in the description of the embodiments and the claims, the singular forms "a," "an," and "the" (the) are intended to include the plural forms as well, unless the context clearly indicates otherwise. Similarly, the term "and/or" as used in this disclosure is meant to encompass any and all possible combinations of one or more of the associated listed. Furthermore, when used in the present disclosure, the terms "comprises," "comprising," and/or variations thereof, mean that the recited features, integers, steps, operations, elements, and/or components are present, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. Without further limitation, an element defined by the phrase "comprising one …" does not exclude the presence of other like elements in a process, method or apparatus comprising such elements.
In the present application, each embodiment is mainly described and may be different from other embodiments, and the same similar parts between the embodiments may be referred to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method sections disclosed in the embodiments, the description of the method sections may be referred to for relevance.
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the following description will be made by way of specific embodiments with reference to the accompanying drawings.
Fig. 1 is a flowchart of an implementation of a supply chain risk prediction method according to an embodiment of the present application, as shown in fig. 1, the method includes the following steps:
s101, acquiring material supply historical data of a plurality of suppliers.
In the embodiment of the application, the execution subject of the supply chain risk prediction method is a supply chain information management platform or a terminal device deploying the supply chain information management platform. The terminal equipment is equipment with communication functions such as server equipment, desktop computers and notebooks.
In addition, the material supply history data of a plurality of suppliers is acquired by a manual acquisition input mode or acquired by using a crawler technology under the condition of adhering to a data protocol. The material supply history data at least comprises enterprise business information and enterprise legal information of a provider (or company). Alternatively, such data sources are primarily enterprise business registration data. In addition, the material supply history data also comprises data showing the association relation of each provider, such as material supply and demand information, material transaction information and the like.
S102, analyzing the association relation of each supplier according to the material supply history data, and constructing an association relation knowledge graph.
In different embodiments, the manner in which the associative knowledge graph is constructed based on the material supply history data is different. Specifically, in this process, the data storage mode, the preprocessing mode, and the like include various embodiments.
In one possible implementation manner, the method analyzes the association relation of each supplier according to the material supply history data and constructs an association relation knowledge graph, and includes the following steps:
s1021, storing the material supply history data into a non-relational database;
s1022, preprocessing the material supply history data, and determining association relationship information between the supplier identification information and the suppliers;
s1023, constructing a supplier identification information table and an association relation information table, and correspondingly storing the supplier identification information and the association relation information;
s1024, designing a Schema model in the knowledge graph, establishing provider nodes according to the provider identification information table, and establishing association relationship edges according to the association relationship information table to obtain an association relationship knowledge graph.
Wherein, in step S1021, the material supply history data acquired based on step S101 is stored in the non-relational database. The application is different from the relational database which adopts a relational model to organize data, and the unstructured data can be stored in the non-relational database, so that the requirements of updating the supplier information at any time and quickly storing mass data according to the acquisition of crawlers are met. Optionally, the non-relational database selected in step S1021 is a mongo db database.
In step S1023, two MYSQL tables are constructed to store the vendor identification information and the association information between vendors, respectively, and optionally, the vendor identification information table and the association information table are named as a company_node table and a relationship table, respectively.
For step S1024, a node of one type is set according to the vendor type, and the attribute of the node can be set according to the application requirement. According to the node of one type, one type of edge is set, and the attribute of the edge can be set according to application requirements.
As shown in fig. 2, a schematic diagram of an association knowledge graph is schematically shown according to an embodiment of the present application. Wherein the entity type (i.e. node type) comprises class 1, i.e. compare, and the properties of the node comprise basic information of the provider. The relationship type (i.e., edge type) includes class 1, INTERACTS, and the edge attribute is weight, i.e., the weight of the association between suppliers.
After the establishment of the association relationship knowledge graph, the association relationship knowledge graph is stored in a graph database, for example: neo4j or Nebula graph database.
And S103, performing risk pre-judging operation on one or more suppliers in response to the risk pre-judging instruction, and acquiring one or more risk pre-judging results in a risk supply chain, a risk range, a problem supplier and a risk community so as to feed back the risk pre-judging results to supply chain management personnel.
In the embodiment of the application, when a problem exists in a provider, in order to improve the accuracy of judging the influence degree of the problem provider on the whole supply chain, at least two or more modes of risk supply chain prejudgment, risk range prejudgment, problem provider prejudgment and risk community prejudgment are adopted for risk prejudgment.
In one possible implementation, the risk pre-determining operation in step S103 includes: risk supply chain prejudgment, risk range prejudgment, problem provider prejudgment and risk community prejudgment, so as to realize comprehensive risk prejudgment through multiple dimensions.
Optionally, the risk pre-judging instruction includes target provider information and a target risk pre-judging mode. The target provider information is one or more pieces of specified provider information to be analyzed, and the target risk pre-judging mode is one or more pieces of risk pre-judging information meeting the requirements of users, for example: one or more of a risk supply chain, a risk range, a problem provider, and a risk community.
On the one hand, in different embodiments, the manner in which risk prediction is initiated is different.
Optionally, the user selects one or more target suppliers according to the requirements, and initiates a risk pre-judging instruction based on the suppliers to instruct the supply chain risk pre-judging system to perform risk pre-judging on the target suppliers.
Optionally, risk prejudging is started regularly, and when the risk is found, a manager is prompted to make a scientific decision rapidly by means of timely generating risk early warning prompt information, sending a risk prejudging result to a management terminal and the like so as to finish supply chain dredging work, so that the normal running state of the supply chain is ensured. The periodic starting risk pre-judging is required to be automatically started according to a starting instruction initiated by a user or in response to the association knowledge graph storage operation after the association knowledge graph is built.
In the specific implementation process, the two risk pre-judging starting modes do not conflict with each other, and the target suppliers can be subjected to key analysis in response to a risk pre-judging instruction according to the requirements of users.
On the other hand, in different embodiments, different risk prejudging modes are selected to execute risk prejudging so as to meet the requirements of users.
Optionally, the user selects one or more risk pre-judging modes according to the requirement, and simultaneously, one or more target suppliers can be selected according to the requirement, and the supply chain risk pre-judging system synthesizes the risk pre-judging modes selected by the user and the target suppliers to generate target supplier risk inquiry instructions.
Optionally, the system periodically starts risk pre-judging, performs risk pre-judging for each provider, and performs four risk pre-judging modes to timely and comprehensively realize risk pre-judging.
In one possible implementation, the risk pre-determination instruction includes: a risk pre-judging automatic mode instruction and a target provider risk inquiry instruction;
performing risk prognosis for one or more suppliers in response to the risk prognosis instruction, comprising:
responding to the risk pre-judging automatic mode instruction, and executing risk pre-judging on each provider according to a set period; the risk pre-judging automatic mode instruction comprises a set period, or the system is preset with the set period and supports self definition;
responding to the risk inquiry instruction of the target provider, and executing risk pre-judging operation on the target provider corresponding to the risk inquiry instruction of the target provider; wherein the target provider risk query instruction includes one or more target provider identification information.
In the embodiment, the material supply historical data of a plurality of suppliers are obtained, the association relation of each supplier is analyzed according to the material supply historical data, and the association relation knowledge graph is constructed, so that the identification and structure visualization of the association condition of each supplier at the upstream and downstream of the supply chain are realized, and the risk condition of the suppliers is conveniently, intuitively and accurately determined through the association relation knowledge graph. In addition, a risk pre-judging operation is performed on one or more suppliers in response to the risk pre-judging instruction, one or more risk pre-judging results in a risk supply chain, a risk range, a problem supplier and a risk community are obtained, and risk pre-judging in different dimensions is realized by combining multiple risk pre-judging modes, so that personalized risk pre-judging requirements of users are met, and meanwhile comprehensive risk pre-judging can be realized, so that the accuracy of judging the influence degree of the problem supplier on the whole supply chain is improved.
The implementation of the supply chain risk prediction method is described above in its entirety. For the specific implementation process of the risk supply chain pre-determination, the risk range pre-determination, the problem provider pre-determination and the risk community pre-determination in the step S103 in different embodiments, there are various ways.
In one possible implementation, the risk supply chain pre-determination includes:
when a problem provider exists, determining a risk node set formed by all upstream nodes and downstream nodes of the problem provider according to the association relation knowledge graph;
and determining the corresponding supply chain as a risk supply chain according to the risk node set.
In the implementation process, in order to solve the problem of how much influence on the whole supply chain is caused when a certain provider or a plurality of providers in the supply chain are determined, risk prediction of the supply chain can be realized by inputting only the provider to be queried through a knowledge graph technology. The specific functional effects are as follows:
when a problem occurs to a certain provider, the provider searches all upstream and downstream associated nodes corresponding to the provider node according to the problem. The analysis of the entire supply link of the provider node is performed, and all providers in this link may be affected.
In one embodiment, as shown in fig. 3, which illustrates Bronn as the problem provider, by querying the upstream and downstream of Bronn providers, it is found that the four Cersei, tyrion, gregor, podrick providers, upstream and downstream providers, i.e., the supply chain including Cersei, tyrion, gregor, podrick, may be affected.
In one possible implementation, the risk range pre-determination includes:
inquiring a key node set in the association relationship knowledge graph;
if the target provider is in the key node set, the shortest path set is queried based on the key node corresponding to the target provider; wherein the shortest path is all shortest paths between two suppliers with the target supplier as a key node;
and the coverage range of each node in the shortest path set is a risk range.
In a specific embodiment, in the association knowledge graph, if one node is located on all the shortest paths of the other two nodes, the node is called a key node.
Table 1 is a key point set information table in an association knowledge graph according to an embodiment of the present application. Taking the first column of data in Table 1 as an example, the first row of Robb suppliers are key nodes for the Pycelle supplier and the Hodor supplier. This means that all shortest paths connecting Robb providers are pyselle providers go through the Robb provider.
TABLE 1 Key Point set information Table
"a.name" "b.name" "PivotalNode"
"Pycelle" "Hodor" "Robb"
"Doran" "Alliser" "Janos"
"Doran" "Alliser" "Tyrion"
"Chataya" Jorah" "Tyrion"
"Ramsay" "Tywin" "Robb"
"Mace" "Dalla" "Tywin"
"Mace" "Dalla" "Val"
"Chataya" "Belwas" "Tyrion"
"Ramsay" "Luwin" "Bran"
"Ramsay" "Luwin" "Robb"
As shown in fig. 4, by querying all shortest paths of the pysele suppliers and the Hodor suppliers through the association knowledge graph, it is found that the four Pycelle, tyrion, tywin, hodor suppliers are the suppliers in all the shortest paths, that is, the four suppliers are risk ranges, which may be affected.
In one possible implementation, the problem provider pre-determination includes:
calculating the centrality value of each supplier according to a preset centrality measurement algorithm and an association relationship knowledge graph, and determining the supplier corresponding to the centrality value larger than the centrality threshold as a problem supplier; wherein the preset centrality measurement algorithm is one or more of Degree Centrality algorithm, weighted Degree Centrality algorithm, betweenness Centrality algorithm and Closeness centrality algorithm; or,
calculating the centrality value of each supplier according to a preset feature vector centrality algorithm and an association relationship knowledge graph, and determining the supplier corresponding to the centrality value larger than the centrality threshold as the problem supplier; the preset feature vector centrality algorithm is a PageRank algorithm.
In a specific implementation process, the centrality value of each supplier is calculated by using Degree Centrality, weighted Degree Centrality, betweenness Centrality and Closeness centrality in a preset centrality measurement algorithm Centrality measures, the suppliers with important attention are screened out by setting a centrality threshold value, and the screened suppliers have a larger influence on the whole supply chain when risks occur.
Wherein Centrality measures algorithm gives a relative measure of the importance of the nodes in the network. There are many different ways to measure centrality, each representing a different type of "importance". Thus, in particular implementations, one or more of the Degree Centrality algorithm, weighted Degree Centrality algorithm, betweenness Centrality algorithm, and Closeness centrality algorithm may be selected to determine the problem provider according to particular needs.
The following describes the Centrality measures algorithms.
Wherein Degree Centrality is a centrality algorithm. In the association relation knowledge graph, the larger the degree of a node is, the higher the degree centrality of the node is, and the more important the node is in the association relation knowledge graph. The calculation formula of the centrality is as follows:
where N represents the number of nodes, N degree Representing the degree of the node.
As shown in table 2, the central value information table of each provider according to an embodiment of the present application is that the provider with important attention is screened out by setting the corresponding threshold value, and this provider has a larger influence when risk occurs.
Table 2 centrality value information table of suppliers
"company" "degree"
"Tyrion" 36
"Sansa" 26
"Jon" 26
"Robb" 25
"Jaime" 24
"Tywin" 22
"Cersei" 20
Wherein Weighted Degree Centrality is a weighted centrality algorithm. The weight attributes of the relationships between suppliers are added to get a weighted centrality.
As shown in table 3, the weighted centrality value information table of each provider according to an embodiment of the present application is used to screen out the provider of great interest by setting the corresponding threshold value, and this provider will have a larger influence when risk occurs.
Table 3 provider weighted centrality value information table
"company" "weightedDegree"
"Tyrion" 551
"Jon" 442
"Sansa" 383
"Jaime" 372
"Bran" 344
"Robb" 342
"Samwell" 282
"Arya" 269
Wherein Betweenness Centrality is the medium centrality algorithm. In the association relationship knowledge graph, the betweenness of one node refers to the betweenness of the other two nodes when all the shortest paths of the other two nodes pass through the node, and the betweenness of the other two nodes is the shortest path number. The betting center is an important metric because it can identify "information intermediaries" in the network or junction points after network clustering.
Fig. 5 is a schematic diagram of the median center, and fig. 5 shows that the black solid nodes have higher median center and are the junction points of the network clusters. The calculation formula of the centrality of the medium number is as follows:
wherein d st Represents the shortest path number, d, from s to t st () Representing the number of nodes traversed in the shortest path from s to t. If normalization is required, dividing the data by (n-1) (n-2) on the basis of the above formula, wherein n is the number of nodes.
Based on the schematic diagram shown in fig. 6, explaining the betweenness centrality calculation process, the betweenness centrality calculation formula for calculating the 4 nodes is:
the first bracket represents the shortest distance from node 1 to the rest of the nodes through node 4/shortest distance from node 1 to the rest of the nodes. Subsequent brackets in turn represent the shortest distances associated with node 2, node 3, node 5, and node 6.
The first bracket is described as an example. 1 to 3, not passing through 4, 0;1 to 2, 1 shortest distance, and 4, 1;1 to 5, 1 shortest distance, and through 4, 1;1 to 6, there are 2 shortest distances, only 1 passing through 4, 0.5.
Node 4 is exemplified above and the remainder are the same.
As shown in table 4, the median value information table of each provider according to an embodiment of the present application is that the provider of great interest is screened out by setting the corresponding threshold value, and this provider will have a larger influence when risk occurs.
Table 4 betting centrality value information table of suppliers
"company" "score"
"Jon" 1279.7533534055322
"Robert" 1165.6025171231624
"Tyrion" 1101.3849724234349
"Daenerys" 874.8372110508583
"Robb" 706.5572832464792
"Sansa" 705.1985623519137
"Stannis" 571.5247305125714
"Jaime" 556.1852522889822
Wherein Closeness centrality is a compactness centrality algorithm. Tightness centrality refers to the reciprocal of the average distance to all other roles in the associative knowledge graph. FIG. 7 is a schematic diagram of closeness centrality in an embodiment of the present application, wherein the black solid nodes are nodes with high centrality, and are highly connected by other nodes, but not necessarily highly connected outside the community, as shown in FIG. 7. The compactness centrality calculation formula is:
Wherein CC i Is tightness centrality; d, d ij Is the distance between node i and node j; d, d i Is the distance between the nodes.
The compactness and centrality of the node are based on the sum of the shortest paths from the node to all other nodes in the association relationship knowledge graph, and if normalization processing is carried out, the average shortest distance from the node to all other nodes is obtained. The smaller the average shortest distance of a node, the greater the tight centrality of this progression. If no path is reachable between node i and node j, then define d ij Is infinite and its reciprocal is 0.
Table 5 shows a compactness centrality value information table for each provider, and the providers with important attention are screened out by setting corresponding threshold values, which have a larger influence when risks occur.
Table 5 vendor affinity centrality value information table
"company" "score"
"Tyrion" 0.004830917874396135
"Sansa" 0.004807692307692308
"Robert" 0.0047169811320754715
"Robb" 0.004608294930875576
"Arya" 0.0045871559633027525
"Jaime" 0.004524886877828055
"Jon" 0.004524886877828055
In addition, the PageRank algorithm is an algorithm that was originally used by Google to rank the importance of web pages, which is a feature vector centrality (eigenvector centrality) algorithm. The PageRank algorithm is used for calculating the value of each provider, and the provider with important attention is screened out by setting a corresponding threshold value, so that the provider has a larger influence when risks occur.
Among them, the PageRank idea:
a) If one web page is linked by many other web pages, it is important that the weight be high.
b) If a page with a high PageRank value links to a certain page, the page weight is also increased. The calculation formula of the web page influence is as follows:
where u is the page to be evaluated, B u A chaining set for page u; for any page v in the incoming chain set, the influence which can be brought to u is the influence PR (v) of the user divided by the outgoing chain quantity L (v) of the pages of the v, namely the page v equally distributes the influence PR (v) of the page v to the outgoing chains of the user, so that all the pages v which can bring links to u are counted, and the obtained sum is the influence of the web page u, namely PR (u).
In the embodiment of the application, PR (u) is the PageRank influence of the node.
In a specific embodiment, we run Pagerank on the iggraph instance and then write the results back to the graph database Neo4j, creating a Pagerank attribute on the role node to store the value just calculated in the iggraph.
Table 6 shows PageRank influence value information tables of each provider, PR values of each provider, and a corresponding threshold is set to screen out the provider of great interest, which has a larger influence when risks occur.
TABLE 6 vendor affinity PageRank influence value information Table
"company" "pagerank"
"Tyrion" 0.04280733585046669
"Jon" 0.03578915958516521
"Robb" 0.03000710274188717
"Sansa" 0.029948520357462004
"Daenerys" 0.028805921534401153
"Jaime" 0.028661872540018285
"Tywin" 0.025597461557687058
"Robert" 0.022257865536054692
In one possible implementation, the risk community pre-judgment includes: clustering all suppliers according to a preset community discovery algorithm and an incidence relation knowledge graph to obtain a plurality of supplier communities;
determining a vendor community including the problem vendor as a risk community.
In a specific implementation process, community discovery is performed by using a Community detection algorithm, and a community in which a provider with problems is located is identified. Suppliers within these communities may be affected. The community discovery algorithm is used to find community clusters in the graph. When looking up community clusters in a graph for a given graph, random walks on the graph are driven by its transition matrix P, which can be derived from the graph's adjacency matrix a. The random walk of length t can be represented by a matrix Pt in whichIs the probability from vertex i to vertex j in step t. The setting of the parameter t should be such that the random walk is long enough to ensure that enough information about the topology of the graph is collected, but not so long that an equilibrium distribution is reached.
We can then make use of the probabilitiesDetermining the similarity between the nodes i and j:
wherein,, |·| is the euclidean norm, Is P t D is the diagonal matrix of degrees of the node.
If two vertices belong to different communities r ij The distance is larger, and the distance is smaller when the distance belongs to the same community. Similarly, we can define the distance between different communities:
wherein,,is a probability vector defined by each element: />The probability from community C to vertex j in step t is defined.
An iggraph implemented random walk algorithm (walktrap) is used to find character communities that frequently touch in communities, with little touch by characters outside communities.
Table 7 is a table of information for communities to which each provider belongs, identifying which community the provider in question is in, according to an embodiment of the present application. Suppliers within these communities may be affected.
TABLE 7 information Table of communities to which suppliers belong
In one possible implementation, the method further includes:
updating the association relationship knowledge graph according to the material supply history data of a plurality of suppliers;
the method comprises the steps of executing operation of updating the association relationship knowledge graph according to material supply historical data of a plurality of suppliers according to a set updating period, or executing operation of updating the association relationship knowledge graph according to the material supply historical data of the plurality of suppliers after adjusting a supplier set; adjusting the set of suppliers includes adding suppliers, deleting suppliers, or replacing suppliers.
In the implementation process, the suppliers can dynamically adjust the cooperative relationship, so that the association relationship knowledge graph is updated in time when the supply relationship is changed, or when the overall cooperative relationship is unchanged but the cooperative compactness among partial suppliers is changed, the operation of updating the association relationship knowledge graph according to the material supply historical data of a plurality of suppliers is performed according to a set updating period, and the judgment accuracy of the influence degree of the problem suppliers on the whole supply chain in the long-term operation process can be improved.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present application.
The following are device embodiments of the application, for details not described in detail therein, reference may be made to the corresponding method embodiments described above.
Fig. 8 is a schematic structural diagram of a supply chain risk predicting device according to an embodiment of the present application, as shown in fig. 8, and for convenience of explanation, only a portion related to the embodiment of the present application is shown, as shown in fig. 8, the device includes: an acquisition module 801, a construction module 802 and a pre-judgment module 803.
An acquisition module 801, configured to acquire material supply history data of a plurality of suppliers;
a construction module 802, configured to analyze association relationships of suppliers according to the material supply history data, and construct an association relationship knowledge graph;
the pre-judging module 803 is configured to perform a risk pre-judging operation on one or more suppliers in response to the risk pre-judging instruction, and obtain one or more risk pre-judging results in a risk supply chain, a risk range, a problem supplier, and a risk community.
In one possible implementation, the risk pre-determination operation includes: risk supply chain prejudgment, risk range prejudgment, problem provider prejudgment and risk community prejudgment.
In one possible implementation, the pre-determining module 803 is configured to perform risk supply chain pre-determination, specifically:
when a problem provider exists, determining a risk node set formed by all upstream nodes and downstream nodes of the problem provider according to the association relation knowledge graph;
and determining the corresponding supply chain as a risk supply chain according to the risk node set.
In one possible implementation, the pre-determining module 803 is configured to perform risk range pre-determination, specifically:
inquiring a key node set in the association relationship knowledge graph;
If the target provider is in the key node set, the shortest path set is queried based on the key node corresponding to the target provider; wherein the shortest path is all shortest paths between two suppliers with the target supplier as a key node;
and the coverage range of each node in the shortest path set is a risk range.
In one possible implementation, the pre-determining module 803 is configured to perform a problem provider pre-determination, specifically:
calculating the centrality value of each supplier according to a preset centrality measurement algorithm and an association relationship knowledge graph, and determining the supplier corresponding to the centrality value larger than the centrality threshold as a problem supplier; wherein the preset centrality measurement algorithm is one or more of Degree Centrality algorithm, weighted Degree Centrality algorithm, betweenness Centrality algorithm and Closeness centrality algorithm; or,
calculating the centrality value of each supplier according to a preset feature vector centrality algorithm and an association relationship knowledge graph, and determining the supplier corresponding to the centrality value larger than the centrality threshold as the problem supplier; the preset feature vector centrality algorithm is a PageRank algorithm.
In one possible implementation, the pre-determining module 803 is configured to perform a risk community pre-determination, specifically:
Clustering all suppliers according to a preset community discovery algorithm and an incidence relation knowledge graph to obtain a plurality of supplier communities;
determining a vendor community including the problem vendor as a risk community.
In one possible implementation, the risk pre-determination instruction includes: a risk pre-judging automatic mode instruction and a target provider risk inquiry instruction;
the pre-judging module 803 is specifically configured to:
responding to the risk pre-judging automatic mode instruction, and executing risk pre-judging on each provider according to a set period; the risk pre-judging automatic mode instruction comprises a set period, or the system is preset with the set period and supports self definition;
responding to the risk inquiry instruction of the target provider, and executing risk pre-judging operation on the target provider corresponding to the risk inquiry instruction of the target provider; wherein the target provider risk query instruction includes one or more target provider identification information.
In one possible implementation, the building block 802 is further configured to:
updating the association relationship knowledge graph according to the material supply history data of a plurality of suppliers;
the method comprises the steps of executing operation of updating the association relationship knowledge graph according to material supply historical data of a plurality of suppliers according to a set updating period, or executing operation of updating the association relationship knowledge graph according to the material supply historical data of the plurality of suppliers after adjusting a supplier set; adjusting the set of suppliers includes adding suppliers, deleting suppliers, or replacing suppliers.
In one possible implementation, the module 802 is specifically configured to:
storing the material supply history data in a non-relational database;
preprocessing the material supply history data, and determining association relationship information between the supplier identification information and suppliers;
constructing a supplier identification information table and an association relation information table, and correspondingly storing the supplier identification information and the association relation information;
and designing a Schema model in the knowledge graph, establishing provider nodes according to the provider identification information table, and establishing association relationship edges according to the association relationship information table to obtain the association relationship knowledge graph.
In the embodiment, the material supply historical data of a plurality of suppliers are obtained, the association relation of each supplier is analyzed according to the material supply historical data, and the association relation knowledge graph is constructed, so that the identification and structure visualization of the association condition of each supplier at the upstream and downstream of the supply chain are realized, and the risk condition of the suppliers is conveniently, intuitively and accurately determined through the association relation knowledge graph. In addition, a risk pre-judging operation is performed on one or more suppliers in response to the risk pre-judging instruction, one or more risk pre-judging results in a risk supply chain, a risk range, a problem supplier and a risk community are obtained, and risk pre-judging in different dimensions is realized by combining multiple risk pre-judging modes, so that personalized risk pre-judging requirements of users are met, and meanwhile comprehensive risk pre-judging can be realized, so that the accuracy of judging the influence degree of the problem supplier on the whole supply chain is improved.
Fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 9, the electronic apparatus 9 of this embodiment includes: a processor 90, a memory 91 and a computer program 92 stored in said memory 91 and executable on said processor 90. The processor 90, when executing the computer program 92, implements the steps of the various supply chain risk prediction method embodiments described above, such as steps S101 through S103 shown in fig. 1. Alternatively, the processor 90, when executing the computer program 92, performs the functions of the modules/units in the above-described device embodiments, for example, the functions of the modules 801 to 803 shown in fig. 8.
Illustratively, the computer program 92 may be partitioned into one or more modules/units that are stored in the memory 91 and executed by the processor 90 to complete the present application. The one or more modules/units may be a series of computer program instruction segments capable of performing the specified functions, which instruction segments are used to describe the execution of the computer program 92 in the electronic device 9. For example, the computer program 92 may be split into modules 301 to 303 shown in fig. 3.
The electronic device 9 may be a computing device such as a desktop computer, a notebook computer, a palm computer, a cloud server, etc. The electronic device 9 may include, but is not limited to, a processor 90, a memory 91. It will be appreciated by those skilled in the art that fig. 9 is merely an example of the electronic device 9 and is not meant to be limiting as the electronic device 9 may include more or fewer components than shown, or may combine certain components, or different components, e.g., the electronic device may further include an input-output device, a network access device, a bus, etc.
The processor 90 may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field-programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 91 may be an internal storage unit of the electronic device 9, such as a hard disk or a memory of the electronic device 9. The memory 91 may also be an external storage device of the electronic device 9, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device 9. Further, the memory 91 may also include both an internal storage unit and an external storage device of the electronic device 9. The memory 91 is used for storing the computer program and other programs and data required by the electronic device. The memory 91 may also be used for temporarily storing data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, the specific names of the functional units and modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus/electronic device and method may be implemented in other manners. For example, the apparatus/electronic device embodiments described above are merely illustrative, e.g., the division of the modules or units is merely a logical function division, and there may be additional divisions in actual implementation, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present application may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and the computer program may implement the steps of the method embodiments of risk prediction of the supply chain when the computer program is executed by a processor. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.

Claims (10)

1. A supply chain risk prediction method, comprising:
acquiring material supply historical data of a plurality of suppliers;
analyzing the association relation of each supplier according to the material supply history data, and constructing an association relation knowledge graph;
and responding to the risk pre-judging instruction, performing risk pre-judging operation on one or more suppliers, and acquiring one or more risk pre-judging results in a risk supply chain, a risk range, a problem supplier and a risk community so as to feed back the risk pre-judging results to a supply chain manager.
2. The supply chain risk prognosis method according to claim 1, wherein the risk prognosis operation includes: risk supply chain prejudgment, risk range prejudgment, problem provider prejudgment and risk community prejudgment.
3. The supply chain risk prognosis method according to claim 2, wherein the risk supply chain prognosis includes:
when a problem provider exists, determining a risk node set formed by all upstream nodes and downstream nodes of the problem provider according to the association relationship knowledge graph;
and determining the corresponding supply chain as a risk supply chain according to the risk node set.
4. The supply chain risk prognosis method according to claim 1, wherein the risk range prognosis includes:
inquiring a key node set in the association relation knowledge graph;
if the target provider is in the key node set, inquiring the shortest path set based on the key node corresponding to the target provider; wherein the shortest paths are all shortest paths between two suppliers with the target supplier as a key node;
and the coverage range of each node in the shortest path set is a risk range.
5. The supply chain risk pre-determination method of claim 1, wherein the problem provider pre-determination comprises:
calculating the centrality value of each provider according to a preset centrality measurement algorithm and the association relation knowledge graph, and determining the provider corresponding to the centrality value larger than the centrality threshold as a problem provider; wherein the preset centrality measurement algorithm is one or more of Degree Centrality algorithm, weighted Degree Centrality algorithm, betweenness Centrality algorithm and Closeness centrality algorithm; or,
Calculating the centrality value of each provider according to a preset feature vector centrality algorithm and the association relationship knowledge graph, and determining the provider corresponding to the centrality value larger than the centrality threshold as the problem provider; the preset feature vector centrality algorithm is a PageRank algorithm.
6. The supply chain risk prognosis method according to claim 1, wherein the risk community prognosis includes:
clustering all suppliers according to a preset community discovery algorithm and the association relationship knowledge graph to obtain a plurality of supplier communities;
determining a vendor community including the problem vendor as a risk community.
7. The supply chain risk prediction method of claim 1, wherein the risk prediction instruction includes: a risk pre-judging automatic mode instruction and a target provider risk inquiry instruction;
the performing risk prognosis for one or more suppliers in response to the risk prognosis instruction includes:
responding to the risk pre-judging automatic mode instruction, and executing risk pre-judging on each provider according to a set period;
responding to a target provider risk inquiry instruction, and executing risk pre-judging operation on a target provider corresponding to the target provider risk inquiry instruction; wherein the target provider risk query instruction includes one or more target provider identification information.
8. The supply chain risk pre-judging method according to claim 1, wherein the analyzing the association relation of each supplier according to the material supply history data and constructing an association relation knowledge graph comprises:
storing the material supply history data in a non-relational database;
preprocessing the material supply history data, and determining association relationship information between supplier identification information and suppliers;
constructing a supplier identification information table and an association relation information table, and correspondingly storing the supplier identification information and the association relation information;
and designing a Schema model in the knowledge graph, establishing a provider node according to the provider identification information table, and establishing an association side according to the association information table to obtain an association knowledge graph.
9. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of the preceding claims 1 to 8 when the computer program is executed.
10. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any of the preceding claims 1 to 8.
CN202310633258.4A 2023-05-31 2023-05-31 Supply chain risk pre-judging method, electronic equipment and storage medium Pending CN116777205A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310633258.4A CN116777205A (en) 2023-05-31 2023-05-31 Supply chain risk pre-judging method, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310633258.4A CN116777205A (en) 2023-05-31 2023-05-31 Supply chain risk pre-judging method, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN116777205A true CN116777205A (en) 2023-09-19

Family

ID=87992172

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310633258.4A Pending CN116777205A (en) 2023-05-31 2023-05-31 Supply chain risk pre-judging method, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN116777205A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118469301A (en) * 2024-07-09 2024-08-09 杭州君方科技有限公司 Supply chain digital risk management method and system

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118469301A (en) * 2024-07-09 2024-08-09 杭州君方科技有限公司 Supply chain digital risk management method and system

Similar Documents

Publication Publication Date Title
US20240185133A1 (en) Root cause discovery engine
Yu et al. Trajectory similarity clustering based on multi-feature distance measurement
CN103513983A (en) Method and system for predictive alert threshold determination tool
CN104995870A (en) Multi-objective server placement determination
CN110679114B (en) Method for estimating deletability of data object
CN104077723B (en) A kind of social networks commending system and method
US20210136120A1 (en) Universal computing asset registry
US10275841B2 (en) Apparatus and method for efficient business name categorization
Meng et al. Intelligent salary benchmarking for talent recruitment: A holistic matrix factorization approach
US20240231909A1 (en) System and method for universal computer asset normalization and configuration management
CN113392150A (en) Data table display method, device, equipment and medium based on service domain
JP2019504393A (en) User data sharing method and apparatus
US10274983B2 (en) Extended business name categorization apparatus and method
US10268965B2 (en) Dictionary enhancement technique for business name categorization
CN116777205A (en) Supply chain risk pre-judging method, electronic equipment and storage medium
US20170115683A1 (en) Interpolative vertical categorization mechanism for energy management
CN114692978A (en) Social media user behavior prediction method and system based on big data
CN110889493A (en) Method and device for adding disturbance aiming at relational network
CN110503117A (en) The method and apparatus of data clusters
US11487964B2 (en) Comprehensive data science solution for segmentation analysis
Almomani et al. Selecting a good stochastic system for the large number of alternatives
AU2022208873B2 (en) Information matching using subgraphs
CN116739605A (en) Transaction data detection method, device, equipment and storage medium
Haghir Chehreghani et al. Discriminative distance-based network indices with application to link prediction
CN113111133A (en) User classification method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination