Intelligent Management System, Intelligent Management Method and Computer Program Product

Abstract

A smart management system is provided. The smart management system includes: a smart supply chain manager configured to generate supply chain constraints based on a supply chain knowledge graph including information on at least one of demand planning and forecasting, inventory planning, sales planning and forecasting, or budget planning; generate industrial chain unexpected events based on the industrial chain event knowledge graph including information on at least one of event urgency, event importance, and event impact propagation degree; generate constraints on the supply chain based on the supply chain constraints and the industrial chain unexpected events; and generate suggestions based on the constraints on the supply chain and provide the suggestions to a business system for supply chain planning, the suggestions including suggestions on at least one of demand replanning and reforecasting, inventory replanning, sales replanning and reforecasting, or budget replanning.

Description

Technical Field

[0001] The present invention relates to intelligent management technology, and more particularly to an intelligent management system, an intelligent management method, and a computer program product. Background Art

[0002] A supply chain is a logistics network that includes suppliers, manufacturers, warehouses, distribution centers, and channel providers. The same business entity can be used as different constituent nodes in the supply chain network. For example, in a given supply chain network, the same enterprise can be a manufacturer and also have a warehouse center and a distribution center. However, more often, different business entities form different nodes in the network. Summary of the Invention

[0003] In one aspect, the present disclosure provides an intelligent management system, including: a supply chain knowledge graph; an industrial chain event knowledge graph; and an intelligent supply chain manager connected to the supply chain knowledge graph and the industrial chain event knowledge graph; wherein, the intelligent supply chain manager includes: a memory; one or more processors; wherein, the memory and the one or more processors are connected to each other; and the memory stores computer-executable instructions for controlling the one or more processors to perform the following operations: generating supply chain constraints based on the supply chain knowledge graph including information of at least one of demand planning and forecasting, inventory planning, sales planning and forecasting, or budget planning; generating industrial chain unexpected events based on the industrial chain event knowledge graph including information of at least one of event urgency, event importance, and event impact propagation degree; generating constraints on the supply chain based on the supply chain constraints and the industrial chain unexpected events; and generating a recommendation based on the constraints on the supply chain and providing the recommendation to a business system for supply chain planning, the recommendation including a recommendation of at least one of re-planning and re-forecasting demand, re-planning inventory, re-planning sales and re-forecasting, or re-planning budget.

[0004] Optionally, the memory further stores computer-executable instructions for controlling the one or more processors to perform the following operations: generating an alert based on a potential conflict between the supply chain constraints and the industrial chain unexpected events and providing the alert to the business system; and receiving a confirmation of the potential conflict from the business system; wherein the recommendation is generated when the confirmation is received.

[0005] Optionally, the recommendation includes a set of alternative recommendations based on alternative priorities respectively.

[0006] Optionally, the intelligent management system further includes a supply chain knowledge graph generator configured to generate the supply chain knowledge graph by extracting entities, relationships, and attributes from a source including at least one of the commercial system or industry standards; wherein, the supply chain knowledge graph generator includes: a memory; one or more processors; wherein, the memory and the one or more processors are connected to each other; and the memory stores computer-executable instructions for controlling the one or more processors to perform the following operations: using an extraction tool to extract entities and relationships from structured data; respectively using an entity extraction template, a relationship extraction template, and an attribute extraction template to extract entities, relationships, and attributes from unstructured data; and when expert verification is performed, storing the extracted entities, the extracted relationships, and the extracted attributes in a knowledge graph database.

[0007] Optionally, in order to extract entities, relationships, and attributes from the unstructured data, the memory further stores computer-executable instructions for controlling the one or more processors to perform the following operations: constructing an entity recognition dictionary and entity recognition rules; based on the entity recognition dictionary and the entity recognition rules, using a heuristic algorithm to expand the entity recognition rules to generate new rules; constructing an entity recognition rule library including the entity recognition rules and the new rules; constructing the entity extraction template based on the entity recognition rule library; and constructing the relationship extraction template and the attribute extraction template based on keyword, lexical, and syntactic analysis.

[0008] Optionally, the intelligent management system further includes an industrial chain event knowledge graph generator configured to generate the industrial chain event knowledge graph by extracting entities, relationships, and attributes from a source including at least one of an internal knowledge base or a public network knowledge base; wherein, the industrial chain event knowledge graph generator includes: a memory; one or more processors; wherein, the memory and the one or more processors are connected to each other; and the memory stores computer-executable instructions for controlling the one or more processors to perform the following operations: crawling the public network knowledge base through a web crawler to obtain trend events in the relevant industry; respectively using an entity extraction template, a relationship extraction template, and an attribute extraction template to extract entities, relationships, and attributes from the trend events; performing knowledge fusion on the internal knowledge base, the extracted entities, the extracted relationships, and the extracted attributes to generate a fused knowledge base; extracting new keywords from the fused knowledge base; and repeatedly executing: crawling the public network knowledge base, extracting entities, relationships, and attributes from the trend events, and performing knowledge fusion.

[0009] Optionally, in order to extract entities, relationships, and attributes from the trend event, the memory further stores computer-executable instructions for controlling the one or more processors to perform the following operations: constructing an entity recognition dictionary and entity recognition rules; based on the entity recognition dictionary and the entity recognition rules, using a heuristic algorithm to expand the entity recognition rules to generate new rules; constructing an entity recognition rule library including the entity recognition rules and the new rules; constructing the entity extraction template based on the entity recognition rule library; and constructing the relationship extraction template and attribute extraction template based on keyword, lexical, and syntactic analysis.

[0010] Optionally, the memory further stores computer-executable instructions for controlling the one or more processors to repeatedly perform: crawling the public network knowledge base, extracting entities, relationships, and attributes from the trend event, and performing knowledge fusion.

[0011] Optionally, the memory further stores computer-executable instructions for controlling the one or more processors to generate a trend event summary based on the TextRank algorithm; wherein, in order to generate the trend event summary, the memory stores computer-executable instructions for controlling the one or more processors to perform the following operations: treating the sentences in the industrial chain event knowledge graph as nodes; connecting the nodes in the industrial chain event knowledge graph with vectorless weighted edges, wherein the corresponding weight of the corresponding edge is the similarity between the corresponding two nodes connected by the corresponding edge; based on the nodes and the vectorless weighted edges, constructing a vectorless weighted graph G(V, E, W), where V represents the nodes, E represents the vectorless weighted edges, and W represents the similarity between the connected nodes; calculating the importance of the nodes respectively; sorting the importance of the nodes by level respectively; and using the selected nodes with relatively higher levels to form the trend event summary.

[0012] Optionally, calculate the importance according to Equation (1):

[0013]

[0014] where S i represents the i-th node; WS(S i ) represents the importance of the i-th node; S j represents the j-th node; w ji represents the similarity between the i-th node and the j-th node; d represents the damping coefficient, which indicates the probability that the i-th node is selected as one of the selected nodes; In(S i ) represents a set of nodes pointing to the i-th node; Out(S j ) represents a set of nodes pointing to the j-th node.

[0015] Optionally, in order for the web crawler to crawl the public network knowledge base, the memory further stores computer-executable instructions for controlling the one or more processors to perform the following operations: initializing a crawler task based on a seed web page; downloading and parsing the seed web page according to the JSoup selector syntax to locate basic information on the seed web page; adding relevant events, tasks, and entity link words on the seed web page to a crawl queue; and storing the parsed data in Json format into a text.

[0016] Optionally, the entity extraction template is configured to extract one or more entities selected from the group consisting of a factory, a logistics company, an order, a raw material supplier, a parts supplier, a subcontractor, a distributor, an inventory, a material, a budget, a country, a region, an enterprise in the upper and lower reaches of the industrial chain, a partner, an outsourcing supplier, a key device, a financial institution, a market, a strategy, a production plan, an industry standard, an output, an order priority, a target, a single-line production index, a product cycle, a constraint, a production stop, abnormal weather, a disease, a natural disaster, a personnel transfer, and a time.

[0017] Optionally, the relationship extraction template is configured to extract one or more relationships selected from the group consisting of an acquisition, a financing, a merger, an upstream, a downstream, a receipt, a payment, a pick-up, a delivery, a demand, a purchase, a maintenance, a derived-from, a containment, a cooperation, a strategic partnership, an impact, a consistency, a distribution, a priority, a receipt, a bottleneck, a limitation, a causal relationship, a chronology, and a regional relationship.

[0018] Optionally, the attribute extraction template is configured to extract one or more attributes selected from the group consisting of a location, a quantity, an order status, a delivery status, an enterprise status, an equipment status, a cooperation status, a transportation status, a production status, a financial status, and a payment status.

[0019] Optionally, the intelligent management system further includes a supply chain knowledge graph generator configured to generate the supply chain knowledge graph and an industrial chain event knowledge graph generator configured to generate the industrial chain event knowledge graph; wherein at least one of the supply chain knowledge graph generator or the industrial chain event knowledge graph generator includes an inferencer configured to infer at least one of a relationship between two entities or a category of an entity.

[0020] Optionally, the inferencer includes: a memory; one or more processors; wherein the memory and the one or more processors are connected to each other; and the memory stores computer-executable instructions for controlling the one or more processors to infer the category of the entity based on constraints in an ontology framework of the knowledge graph, the constraints including a domain and a range of a relationship connected to the entity.

[0021] Optionally, the inferencer includes: a memory; one or more processors; wherein, the memory and the one or more processors are connected to each other; and the memory stores computer-executable instructions for controlling the one or more processors to make inferences using a scoring algorithm; wherein the scoring algorithm includes: the similarity between entity 1 and (relationship entity 2); the similarity between (entity 1 relationship) and entity 2; and the similarity between the relationship and (entity 1 entity 2); wherein, represents a linear or non-linear operation selected from the group consisting of addition, multiplication, and neural network operations.

[0022] Optionally, the memory further stores computer-executable instructions for controlling the one or more processors to train the parameters of the scoring algorithm using a training data set.

[0023] In another aspect, the present disclosure provides an intelligent management method, including: generating supply chain constraints based on a supply chain knowledge graph, the supply chain knowledge graph including information on at least one of demand planning and forecasting, inventory planning, sales planning and forecasting, or budget planning; generating industrial chain unexpected events based on an industrial chain event knowledge graph, the industrial chain event knowledge graph including information on at least one of event urgency, event importance, and event impact propagation degree; generating constraints on the supply chain based on the supply chain constraints and the industrial chain unexpected events; and generating a recommendation based on the constraints on the supply chain and providing the recommendation to a business system for supply chain planning, the recommendation including at least one of a recommendation for re-planning and re-forecasting demand, re-planning inventory, re-planning sales and re-forecasting, or re-planning the budget.

[0024] In another aspect, the present disclosure provides a computer program product, which includes a non-transitory tangible computer-readable medium having computer-readable instructions thereon, the computer-readable instructions being executable by a processor to cause the processor to perform: generating supply chain constraints based on a supply chain knowledge graph, the supply chain knowledge graph including information on at least one of demand planning and forecasting, inventory planning, sales planning and forecasting, or budget planning; generating industrial chain unexpected events based on an industrial chain event knowledge graph, the industrial chain event knowledge graph including information on at least one of event urgency, event importance, and event impact propagation degree; generating constraints on the supply chain based on the supply chain constraints and the industrial chain unexpected events; and generating a recommendation based on the constraints on the supply chain and providing the recommendation to a business system for supply chain planning, the recommendation including at least one of a recommendation for re-planning and re-forecasting demand, re-planning inventory, re-planning sales and re-forecasting, or re-planning the budget. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] According to various disclosed embodiments, the following drawings are merely examples for illustrative purposes and are not intended to limit the scope of the present invention.

[0026] Figure 1 An intelligent management system according to some embodiments of the present disclosure is shown.

[0027] Figure 2A is a schematic diagram of the structure of a device according to some embodiments of the present disclosure.

[0028] Figure 2B is a schematic diagram showing the structure of a device according to some embodiments of the present disclosure.

[0029] Figure 3 The functional modules of a supply chain knowledge graph according to some embodiments of the present disclosure are shown.

[0030] Figure 4 The functional modules of an industrial chain event knowledge graph according to some embodiments of the present disclosure are shown.

[0031] Figure 5 An intelligent management system according to some embodiments of the present disclosure is shown.

[0032] Figure 6 The functional modules of a supply chain knowledge graph according to some embodiments of the present disclosure are shown.

[0033] Figure 7 An intelligent management system according to some embodiments of the present disclosure is shown.

[0034] Figure 8 A method for generating a supply chain knowledge graph according to some embodiments of the present disclosure is shown.

[0035] Figure 9 A method for generating an industrial chain event knowledge graph according to some embodiments of the present disclosure is shown.

[0036] Figure 10 The structure of an industrial chain event knowledge graph according to some embodiments of the present disclosure is shown.

[0037] Figure 11 An intelligent management system according to some embodiments of the present disclosure is shown.

[0038] Figure 12 The structure of an inferencer according to some embodiments of the present invention is shown. DETAILED DESCRIPTION OF THE INVENTION

[0039] The present disclosure will now be described more specifically with reference to the following embodiments. It should be noted that the following description of some embodiments presented herein is for illustrative and descriptive purposes only. It is not exhaustive or limited to the precise forms disclosed.

[0040] The inventors of the present disclosure have found that the public supply chain management system lacks the ability to respond quickly to uncertainties and volatilities because it does not have the ability to predict shortages in a timely manner, analyze events, infer the relationships between events and constraints, or assist in decision-making. Moreover, the database in the public supply chain management system cannot be easily maintained and extended.

[0041] Accordingly, the present disclosure particularly provides an intelligent management system, an intelligent management method, and a computer program product that substantially eliminate one or more problems caused by the limitations and disadvantages of the prior art. In one aspect, the present disclosure provides an intelligent management system. In some embodiments, the intelligent management system includes a supply chain knowledge graph; an industrial chain event knowledge graph; and an intelligent supply chain manager that is connected to the supply chain knowledge graph and the industrial chain event knowledge graph. Optionally, the intelligent supply chain manager includes: a memory; one or more processors. The memory and the one or more processors are connected to each other. The memory stores computer-executable instructions for controlling the one or more processors to perform the following operations: generating supply chain constraints based on the supply chain knowledge graph including information on at least one of demand planning and forecasting, inventory planning, sales planning and forecasting, or budget planning; generating industrial chain unexpected events based on the industrial chain event knowledge graph including information on at least one of event urgency, event importance, and event impact propagation degree; generating constraints on the supply chain based on the supply chain constraints and the industrial chain unexpected events; and generating a recommendation based on the constraints on the supply chain and providing the recommendation to a business system for supply chain planning, the recommendation including a recommendation on at least one of demand replanning and reforecasting, inventory replanning, sales replanning and reforecasting, or budget replanning.

[0042] As used herein, the term "knowledge graph" may represent a networked data structure that includes facts represented by nodes and edges representing connections or links between the nodes. Thus, a knowledge graph can represent a knowledge base for the organization of so-called unstructured data, i.e., facts and their semantic relationships. The core building blocks of a knowledge graph can be nodes that include information and edges that build links between selected different nodes. The edges can have weights or weight factors that define the strength values of the relationships between two nodes. Additionally, the nodes can also have scores or score values to describe some importance of the node content. As used herein, the term "entity" refers to a category of things or objects that are all recognized as being able to exist independently and that can be uniquely identified. Entities are typically represented by nodes in a knowledge graph. As used herein, the term "relationship" refers to the relationship between entities. Relationships are typically represented by edges in a knowledge graph. As used herein, the term "attribute" refers to characteristics available about an entity.

[0043] Figure 1 illustrates an intelligent management system in some embodiments according to the present disclosure. Referring to Figure 1 , in some embodiments, the intelligent management system includes a supply chain knowledge graph SKG; an industrial chain event knowledge graph ICEKG; and an intelligent supply chain manager ISM, which is connected to the supply chain knowledge graph SKG and the industrial chain event knowledge graph ICEKG.

[0044] In some embodiments, the intelligent supply chain manager ISM includes a constraint generator CG configured to generate constraints on the supply chain. Specifically, the constraint generator CG is configured to generate supply chain restrictions based on the supply chain knowledge graph, which includes information on at least one of demand planning and forecasting, inventory planning, or sales planning and forecasting; generate industrial chain contingencies based on the industrial chain event knowledge graph, which includes information on at least one of event urgency, event importance, and event impact propagation; and generate constraints on the supply chain based on the supply chain restrictions and the industrial chain contingencies. In some embodiments, the intelligent supply chain manager ISM further includes an intelligent butler IB configured to receive the constraints generated by the constraint generator CG and generate suggestions based on the constraints on the supply chain and provide the suggestions to the business system BY for supply chain planning, the suggestions including suggestions for at least one of demand replanning and reforecasting, inventory replanning, or sales replanning and reforecasting.

[0045] Figure 2A is a schematic diagram of the structure of the intelligent supply chain manager ISM in some embodiments according to the present disclosure. Referring to Figure 2A, in some embodiments, the device includes a central processing unit (CPU) configured to perform operations in accordance with computer-executable instructions stored in a ROM or a RAM. Optionally, data and programs required by the computer system are stored in the RAM. Optionally, the CPU, ROM, and RAM are electrically connected to each other via a bus. Optionally, an input / output interface is electrically connected to the bus.

[0046] Figure 2B is a schematic diagram showing the structure of an intelligent supply chain manager ISM in some embodiments according to the present disclosure. Refer to Figure 2B , in some embodiments, the device includes a display panel DP; an integrated circuit IC connected to the display panel DP; a memory M; and one or more processors P. The memory M is interconnected with the one or more processors P. In some embodiments, the memory M stores computer-executable instructions for controlling the one or more processors P to perform the method steps described herein.

[0047] In some embodiments, the intelligent supply chain manager includes a memory; one or more processors. The memory and the one or more processors are connected to each other. In some embodiments, the memory stores computer-executable instructions for controlling the one or more processors to generate supply chain constraints based on a supply chain knowledge graph, the supply chain knowledge graph including information on at least one of demand planning and forecasting, inventory planning, or sales planning and forecasting; generate industrial chain unexpected events based on an industrial chain event knowledge graph, the industrial chain event knowledge graph including information on at least one of event urgency, event importance, and event impact propagation; generate constraints on the supply chain based on the supply chain constraints and the industrial chain unexpected events; and generate recommendations based on the constraints on the supply chain and provide the recommendations to a business system BY for supply chain planning, the recommendations including recommendations for at least one of demand replanning and reforecasting, inventory replanning, or sales replanning and reforecasting.

[0048] Refer again to Figure 1 , in some embodiments, the business system BY includes a demand planning and forecasting module DPF (e.g., planning and forecasting market demand on how to meet market demand), an inventory planning module IP (e.g., planning for warehouse inventory), and a sales planning and forecasting module SPF (e.g., planning and forecasting sales). Figure 3 shows the functional modules of a supply chain knowledge graph in some embodiments according to the present disclosure. Refer to Figure 3, in some embodiments, the supply chain knowledge graph SKG includes a short-term planning module STPM, a medium-term planning module MTPM, and a long-term planning module LTPM. In one example, the short-term planning module STPM includes a field work scheduling module FWS and a shipping scheduling module SS; the medium-term planning module MTPM includes a supply planning module SP, a distribution planning module DTP, and a transportation planning module TNP; and the long-term planning module LTPM includes a demand planning and forecasting module DPF, an inventory planning module IP, and a sales planning and forecasting module SPF. The supply chain constraints are generated based on information from at least one of the demand planning and forecasting, inventory planning, or sales planning and forecasting from the demand planning and forecasting module DPF, the inventory planning module IP, and the sales planning and forecasting module SPF, respectively. According to the information included in the long-term planning module LTPM, Figure 1 the constraint generator CG therein is configured to generate supply chain constraints.

[0049] Figure 4 shows the functional modules of the industrial chain event knowledge graph in some embodiments according to the present disclosure. Refer to Figure 4 , in some embodiments, the industrial chain event knowledge graph ICEKG includes a plurality of sub-knowledge graphs. Examples of the sub-knowledge graphs include a procurement sub-knowledge graph PSKG, a logistics sub-knowledge graph LSKG, and a sales sub-knowledge graph SSKG. From these sub-knowledge graphs, information on industry events can be extracted, including event urgency level EUL, event importance level EIL, and event impact propagation degree EISL. Figure 1 the constraint generator CG therein is configured to generate industrial chain contingency events corresponding to the event urgency level EUL, the event importance level EIL, and the event impact propagation degree EISL, respectively.

[0050] The intelligent butler IB is configured to analyze the existing demand planning and forecasting, inventory planning, and sales planning and forecasting, consider the supply chain constraints and the industrial chain contingency events, predict supply delays, demand delays, and logistics delays, and thus recommend at least one of demand replanning and reforecasting, inventory replanning, or sales replanning and reforecasting.

[0051] Referring again to Figure 1 , in some embodiments, the business system BY includes a demand planning and forecasting system DPF', an inventory planning system IP', and a sales planning and forecasting system SPF'. The recommendations for demand replanning and reforecasting, inventory replanning, and sales replanning and reforecasting are provided to the demand planning and forecasting system DPF', the inventory planning system IP', and the sales planning and forecasting system SPF', respectively. Users in the production business entity, the procurement business entity, and the sales business entity can review the recommendations for demand replanning and reforecasting, inventory replanning, and sales replanning and reforecasting, respectively.

[0052] Figure 5 shows an intelligent management system in some embodiments according to the present disclosure. Figure 6 shows the functional modules of a supply chain knowledge graph in some embodiments according to the present disclosure. Refer to Figure 5 and Figure 6 , in some embodiments, the supply chain knowledge graph SKG includes a short-term planning module STPM, a medium-term planning module MTPM, and a long-term planning module LTPM. In one example, the short-term planning module STPM includes a field work scheduling module FWS and a shipment scheduling module SS; the medium-term planning module MTPM includes a supply planning module SP, a distribution planning module DTP, and a transportation planning module TNP; and the long-term planning module LTPM includes a demand planning and forecasting module DPF, an inventory planning module IP, a sales planning and forecasting module SPF, and a budget planning module BP. The supply chain constraints are generated based on information from at least one of demand planning and forecasting, inventory planning, sales planning and forecasting, or budget planning from the demand planning and forecasting module DPF, the inventory planning module IP, the sales planning and forecasting module SPF, and the budget planning module BP, respectively.

[0053] According to the information included in the long-term planning module LTPM, Figure 5 the constraint generator CG therein is configured to generate supply chain constraints. The supply chain constraints are generated based on information from at least one of demand planning and forecasting, inventory planning, sales planning and forecasting, or budget planning from the demand planning and forecasting module DPF, the inventory planning module IP, and the sales planning and forecasting module SPF, respectively.

[0054] The intelligent butler IB is configured to receive the constraints generated by the constraint generator CG, and generate suggestions based on the constraints on the supply chain and provide the suggestions to the business system BY for supply chain planning, the suggestions including suggestions for at least one of demand replanning and reforecasting, inventory replanning, sales replanning and reforecasting, or budget replanning. Specifically, the intelligent butler IB is configured to analyze the existing demand planning and forecasting, inventory planning, sales planning and forecasting, consider the supply chain constraints and industrial chain contingencies, predict supply delays, demand delays, and logistics delays, so as to suggest at least one of demand replanning and reforecasting, inventory replanning, sales replanning and reforecasting, or budget replanning.

[0055] In some embodiments, the intelligent supply chain manager includes a memory; one or more processors. The memory and the one or more processors are connected to each other. In some embodiments, the memory stores computer-executable instructions to control the one or more processors to generate supply chain constraints based on a supply chain knowledge graph, the supply chain knowledge graph including information on at least one of demand planning and forecasting, inventory planning, sales planning and forecasting, or budget planning; generate industrial chain contingencies based on an industrial chain event knowledge graph, the industrial chain event knowledge graph including information on at least one of event urgency, event importance, and event impact propagation; generate constraints on the supply chain based on the supply chain constraints and the industrial chain contingencies; and generate recommendations based on the constraints on the supply chain and provide the recommendations to the business system BY for supply chain planning, the recommendations including recommendations for at least one of demand replanning and reforecasting, inventory replanning, sales replanning and reforecasting, or budget replanning.

[0056] Referring again to Figure 5 , in some embodiments, the business system BY includes a demand planning and forecasting system DPF’, an inventory planning system IP’, a sales planning and forecasting system SPF’, and a budget planning system BP’. Recommendations for demand replanning and reforecasting, inventory replanning, sales replanning and reforecasting, and budget replanning are provided to the demand planning and forecasting system DPF’, the inventory planning system IP’, the sales planning and forecasting system SPF’, and the budget planning system BP’, respectively. Users in production business entities, procurement business entities, sales business entities, and financial business entities (e.g., the production department, procurement department, sales department, and financial department in the same enterprise) can check demand replanning and reforecasting, inventory replanning, sales replanning and reforecasting, and budget replanning, respectively.

[0057] In some embodiments, the intelligent butler IB is configured to generate an alert and provide the alert to the business system BY based on a potential conflict between the supply chain constraints and the industrial chain contingencies. Examples of alerts generated due to potential conflicts between the supply chain constraints and the industrial chain contingencies include alerts for potential material shortages, alerts for potential production capacity shortages, and alerts for potential delays in customized order deliveries. In some embodiments, the alert also includes a comparison between the existing planning and the forecasting reality.

[0058] In some embodiments, a business system BY (e.g., a demand planning and forecasting system DPF’, an inventory planning system IP’, a sales planning and forecasting system SPF’, and a budget planning system BP’) is configured to send a confirmation to confirm a potential conflict. In one example, a user on the business system BY can check and confirm a potential conflict. The intelligent steward IB is configured to receive the confirmation from the business system BY for confirming the potential conflict. Upon receiving the confirmation, the intelligent steward IB is configured to generate a recommendation based on the constraints of the supply chain and provide the recommendation to the business system BY for supply chain planning, the recommendation including a recommendation for at least one of demand replanning and reforecasting, inventory replanning, sales replanning and reforecasting, or budget replanning.

[0059] Optionally, the recommendation includes a set of alternative recommendations based on alternative priorities respectively, e.g., priority placed on delivery, priority placed on procurement, etc. Optionally, the potential conflict between the supply chain constraints and the industrial chain contingencies is resolved in each alternative recommendation.

[0060] Figure 7 An intelligent management system in some embodiments according to the present disclosure is shown. Refer to Figure 7 , in some embodiments, the intelligent management system ISM further includes a supply chain knowledge graph generator GSKG, which is configured to generate a supply chain knowledge graph SKG by extracting entities, relationships, and attributes from a source including at least one of a business system or an industry standard. In some embodiments, the supply chain knowledge graph generator SKG includes a memory and one or more processors. The memory and the one or more processors are connected to each other. The memory stores computer-executable instructions for controlling the one or more processors to perform the following operations: extracting entities and relationships from structured data using an extraction tool; extracting entities, relationships, and attributes from unstructured data using an entity extraction template, a relationship extraction template, and an attribute extraction template respectively; and storing the extracted entities, the extracted relationships, and the extracted attributes in a knowledge graph database during expert verification. Optionally, the extraction tool is an extract-transform-load (ETL) tool. Examples of sources from which entities, relationships, and attributes can be extracted also include process files, documents, cases, device information.

[0061] As used herein, the term “structured data” refers to data in which the semantic meaning of the stored data is clearly defined. For example, structured data sources include relational databases, XML databases, etc. The term “unstructured data” is used to refer to data sources in which the semantic meaning of the data is not clearly defined. For example, unstructured data can refer to plain text documents, scanned documents, portable document format (PDF) files, Word document. The term "unstructured data" is also used herein to refer to semi-structured data, where, for example, metadata tags are used to encode the semantic meaning of the data. Examples of semi-structured documents include Extensible Markup Language (XML) files and Hypertext Markup Language (HTML) files, among others.

[0062] Figure 8 illustrates a method for generating a supply chain knowledge graph in some embodiments of the present disclosure. Referring to Figure 8 , sources from which entities, relationships, and attributes can be extracted include business system BY, industry standards, process documents, documents and cases, and device information. In the knowledge representation and modeling step, the (one or more) extraction tools are configured to incorporate business logic; extract entities, relationships, and attributes; build commercial-grade knowledge graph data fusion and supplementation based on various applications; and extract structured data into entity tables and relationship tables (e.g., via an ETL tool). As Figure 8 shown, in one example, the extracted entities, extracted relationships, and extracted attributes in the knowledge graph database include Neo4j, Titan, Orient DB, gStore, and Jena.

[0063] In some embodiments, to extract entities, relationships, and attributes from unstructured data, the memory also stores computer-executable instructions for controlling one or more processors to perform the following operations: build an entity recognition dictionary and entity recognition rules; based on the entity recognition dictionary and entity recognition rules, use a heuristic algorithm to expand the entity recognition rules to generate new rules; build an entity recognition rule library including the entity recognition rules and the new rules; based on the entity recognition rule library, build an entity extraction template; and based on keyword, lexical, and syntactic analysis, build a relationship extraction template and an attribute extraction template.

[0064] Referring to Figure 7, in some embodiments, the intelligent management system ISM further includes an industrial chain event knowledge graph generator GICEKG, which is configured to generate an industrial chain event knowledge graph ICEKG by extracting entities, relationships, and attributes from a source including at least one of an internal knowledge base or a public network knowledge base. In some embodiments, the industrial chain event knowledge graph generator GICEKG includes a memory and one or more processors. The memory and the one or more processors are connected to each other. To extract entities, relationships, and attributes from the public network knowledge base, the memory stores computer-executable instructions for controlling the one or more processors to perform the following operations: crawling the public network knowledge base through a web crawler to obtain trend events in the relevant industry; using entity extraction templates, relationship extraction templates, and attribute extraction templates to extract entities, relationships, and attributes from the trend events respectively; performing knowledge fusion on the internal knowledge base, the extracted entities, the extracted relationships, and the extracted attributes to generate a fused knowledge base; extracting new keywords from the fused knowledge base; and repeating the execution of: crawling the public network knowledge base, extracting entities, relationships, and attributes from the trend events, and performing knowledge fusion.

[0065] As used herein, the term "crawl" involves using links to browse the network of a computing device in a methodical and / or automated manner (e.g., ). In addition, crawling includes extracting data stored in one of the computing devices of the network. In addition, crawling refers to analyzing and indexing the extracted data in a manner that enables optimizing the process of extracting data stored in the computing devices of the network. Additionally, crawling may include one or more specifications of what to crawl, including how to crawl, when to crawl, and other parameters for controlling the crawling process. Optionally, crawling includes extracting backup data related to static data or resource files associated with the link. In addition, crawling may include extracting dynamic data from the link, such as data downloaded from the Internet or displayed by the link at execution time.

[0066] In some embodiments, to extract entities, relationships, and attributes from the trend events, the memory further stores computer-executable instructions for controlling the one or more processors to perform the following operations: constructing an entity recognition dictionary and entity recognition rules; based on the entity recognition dictionary and entity recognition rules, using a heuristic algorithm to expand the entity recognition rules to generate new rules; constructing an entity recognition rule library including the entity recognition rules and the new rules; constructing an entity extraction template based on the entity recognition rule library; and constructing relationship extraction templates and attribute extraction templates based on keyword, lexical, and syntactic analysis.

[0067] Optionally, the memory further stores computer-executable instructions for controlling the one or more processors to repeat the execution of: crawling the public network knowledge base, extracting entities, relationships, and attributes from the trend events, and performing knowledge fusion.

[0068] Figure 9 illustrates a method for generating an industrial chain event knowledge graph according to some embodiments of the present disclosure. Referring to Figure 9 , trend events can be obtained from various sources including Wikipedia, news reports, official websites, and social media. In order to crawl the public network knowledge base by a web crawler, in some embodiments, the memory further stores computer-executable instructions for controlling one or more processors to perform the following operations: initializing a crawler task based on a seed web page; downloading and parsing the seed web page according to the JSoup selector syntax to locate basic information on the seed web page; adding relevant events, tasks, and links to entity words on the seed web page to a crawl queue; and storing the parsed data in Json format as text. Optionally, during the initialization of the crawler task, the web crawler is configured to set the number of threads, set the access interval, and set the number of retries. Referring to Figure 9 , once the crawler task starts, various information can be extracted from the trend events, including people, companies, time, location, event actions, event descriptions, and influence spread. The extracted trend event information is fused with the internal knowledge base ("knowledge fusion"). The internal knowledge base can include knowledge from supply, collaborators, sales, and logistics. New keywords can be extracted from the fused knowledge base. The new keywords can be provided to the web crawler to repeat the operation of crawling the public network knowledge base. Figure 10 illustrates the structure of an industrial chain event knowledge graph according to some embodiments of the present disclosure.

[0069] In some embodiments, referring to Figure 9 , the industrial chain event knowledge graph generator GICEKG is further configured to generate a trend event summary. In one example, the trend event summary is generated based on the TextRank algorithm. In some embodiments, in order to generate the trend event summary, the memory stores computer-executable instructions for controlling one or more processors to perform the following operations: processing the sentences in the industrial chain event knowledge graph as nodes; connecting the nodes in the industrial chain event knowledge graph with vectorless weighted edges, where the corresponding weight of the corresponding edge is the similarity between the corresponding two nodes connected by the corresponding edge; constructing a vectorless weighted graph G(V, E, W) based on the nodes and the vectorless weighted edges, where V represents the nodes, E represents the vectorless weighted edges, and W represents the similarity between the respective connected nodes; calculating the importance of the nodes respectively; sorting the importance levels of the nodes respectively; and using the selected nodes with relatively higher levels to form the trend event summary.

[0070] In some embodiments, the importance is calculated according to equation (1):

[0071]

[0072] Among them, S i represents the i-th node; WS(S i ) represents the importance of the i-th node; S j represents the j-th node; w ji represents the similarity between the i-th node and the j-th node; d represents the damping coefficient, which indicates the probability that the i-th node is selected as one of the selected nodes; In(S i ) represents a set of nodes pointing to the i-th node; Out(S j ) represents a set of nodes pointing to the j-th node.

[0073] In some embodiments, the entity extraction template is configured to extract one or more entities selected from the group consisting of factory, logistics company, order, raw material supplier, parts supplier, subcontractor, distributor, inventory, material, budget, country, region, upstream and downstream enterprises in the industrial chain, partner, outsourcing supplier, key equipment, financial institution, market, strategy, production plan, industry standard, output, order priority, target, single-line production index, product cycle, constraint, production stop, abnormal weather, disease, natural disaster, personnel transfer, and time.

[0074] In some embodiments, the relationship extraction template is configured to extract one or more relationships selected from the group consisting of acquisition, financing, merger, upstream, downstream, receipt, payment, pickup, delivery, demand, purchase, maintenance, from, containment, cooperation, strategic partnership, influence, consistency, distribution, priority, receipt, bottleneck, restriction, causality, chronology, and regional relationship.

[0075] In some embodiments, the attribute extraction template is configured to extract one or more attributes selected from the group consisting of location, quantity, order status, delivery status, enterprise status, equipment status, cooperation status, transportation status, production status, financial status, and payment status.

[0076] In some embodiments, at least one of the supply chain knowledge graph generator or the industrial chain event knowledge graph generator includes an inferencer configured to infer at least one of the relationship between two entities or the category of an entity. Figure 11 Illustrates an intelligent management system in some embodiments according to the present disclosure. Refer to Figure 11 , both the supply chain knowledge graph generator GSKG and the industrial chain event knowledge graph generator GICEKG include an inferencer IR. Figure 12 Illustrates the structure of an inferencer in some embodiments according to the present invention. Refer to Figure 12, in some embodiments, the inferencer IR includes a data layer configured to receive data from the supply chain knowledge graph SKG and / or the industrial chain event knowledge graph ICEKG. In some embodiments, the inferencer IR further includes a search layer. In some embodiments, the search layer includes a plurality of modules, including an orthographic index module, an inverted index module, an ontology index module, a SPARQL analysis module, an attribute filtering module, and a SPARQL support module. In some embodiments, the inferencer IR further includes an algorithm layer. Optionally, the algorithm layer includes a plurality of modules, including an inference module, a prediction module, and a statistical analysis module.

[0077] In some embodiments, the inferencer IR is configured to infer at least one of the relationship between two entities or the category of an entity. In some embodiments, the inferencer IR includes a memory; one or more processors. The memory and the one or more processors are connected to each other. The memory stores computer-executable instructions for controlling the one or more processors to infer the category of an entity based on constraints in the ontological framework of the knowledge graph, where the constraints include the domain and range of the relationships connected to the entity.

[0078] In some embodiments, the memory stores computer-executable instructions for controlling the one or more processors to perform inferences using a scoring algorithm. Optionally, the scoring algorithm includes the similarity between entity 1 and (relationship entity 2); the similarity between (entity 1 relationship) and entity 2; and the similarity between the relationship and (entity 1 entity 2); where represents a linear or non-linear operation selected from the group consisting of addition, multiplication, and neural network operations.

[0079] Optionally, the memory further stores computer-executable instructions for controlling the one or more processors to train the parameters of the scoring algorithm using a training data set.

[0080] In another aspect, the present disclosure provides an intelligent management method. In some embodiments, the intelligent management method includes generating supply chain constraints based on a supply chain knowledge graph, the supply chain knowledge graph including information on at least one of demand planning and forecasting, inventory planning, sales planning and forecasting, or budget planning; generating industrial chain unexpected events based on an industrial chain event knowledge graph, the industrial chain event knowledge graph including information on at least one of event urgency, event importance, and event impact propagation degree; generating constraints on the supply chain based on the supply chain constraints and the industrial chain unexpected events; and generating suggestions based on the constraints on the supply chain and providing the suggestions to a business system for supply chain planning, the suggestions including suggestions on at least one of re-planning and re-forecasting demand, re-planning inventory, re-planning sales, or re-planning budget.

[0081] In some embodiments, the intelligent management method further includes generating an alert based on a potential conflict between the supply chain constraints and the industrial chain unexpected events and providing the alert to the business system; and receiving, from the business system, confirmation of the potential conflict. Optionally, the suggestions are generated upon receiving the confirmation. Optionally, the suggestions include a set of alternative suggestions based on alternative priorities respectively.

[0082] In some embodiments, the intelligent management method further includes generating the supply chain knowledge graph by a supply chain knowledge graph generator by extracting entities, relationships, and attributes from a source including at least one of the business system or industry standards. Specifically, the intelligent management method includes using an extraction tool to extract entities and relationships from structured data; using entity extraction templates, relationship extraction templates, and attribute extraction templates to extract entities, relationships, and attributes from unstructured data respectively; and storing the extracted entities, the extracted relationships, and the extracted attributes in a knowledge graph database during expert verification.

[0083] In some embodiments, extracting entities, relationships, and attributes from unstructured data includes constructing an entity recognition dictionary and entity recognition rules; based on the entity recognition dictionary and the entity recognition rules, using a heuristic algorithm to expand the entity recognition rules to generate new rules; constructing an entity recognition rule library including the entity recognition rules and the new rules; constructing the entity extraction template based on the entity recognition rule library; and constructing the relationship extraction template and the attribute extraction template based on keyword, lexical, and syntactic analysis.

[0084] In some embodiments, the intelligent management method further includes generating the industrial chain event knowledge graph by an industrial chain event knowledge graph generator extracting entities, relationships, and attributes from a source including at least one of an internal knowledge base or a public network knowledge base. Specifically, the intelligent management method includes crawling the public network knowledge base through a web crawler to obtain trend events in related industries; respectively using an entity extraction template, a relationship extraction template, and an attribute extraction template to extract entities, relationships, and attributes from the trend events; performing knowledge fusion on the internal knowledge base, the extracted entities, the extracted relationships, and the extracted attributes to generate a fused knowledge base; extracting new keywords from the fused knowledge base; and repeatedly executing: crawling the public network knowledge base, extracting entities, relationships, and attributes from the trend events, and performing knowledge fusion.

[0085] In some embodiments, extracting entities, relationships, and attributes from the trend events includes constructing an entity recognition dictionary and entity recognition rules; based on the entity recognition dictionary and the entity recognition rules, using a heuristic algorithm to expand the entity recognition rules to generate new rules; constructing an entity recognition rule library including the entity recognition rules and the new rules; constructing the entity extraction template based on the entity recognition rule library; and constructing the relationship extraction template and the attribute extraction template based on keyword, lexical, and syntactic analysis.

[0086] In some embodiments, the intelligent management method further includes repeatedly executing: crawling the public network knowledge base, extracting entities, relationships, and attributes from the trend events, and performing knowledge fusion.

[0087] In some embodiments, the intelligent management method further includes generating a trend event summary based on the TextRank algorithm. Specifically, generating the trend event summary includes: treating the sentences in the industrial chain event knowledge graph as nodes; using vectorless weighted edges to connect the nodes in the industrial chain event knowledge graph, where the corresponding weight of the corresponding edge is the similarity between the two corresponding nodes connected by the corresponding edge; based on the nodes and the vectorless weighted edges, constructing a vectorless weighted graph G(V, E, W), where V represents the nodes, E represents the vectorless weighted edges, and W represents the similarity between the connected nodes; respectively calculating the importance of the nodes; respectively ranking the importance levels of the nodes; and using the selected nodes with relatively higher levels to form the trend event summary.

[0088] In some embodiments, the importance is calculated according to Equation (1):

[0089]

[0090] where S i represents the i-th node; WS(Si ) represents the importance of the i-th node; S j represents the j-th node; w ji represents the similarity between the i-th node and the j-th node; d represents the damping factor, which indicates the probability that the i-th node is selected as one of the selected nodes; In(S i ) represents a set of nodes pointing to the i-th node; Out(S j ) represents a set of nodes pointing to the j-th node.

[0091] In some embodiments, crawling a public network knowledge base by a web crawler includes initializing a crawler task based on a seed web page; downloading and parsing the seed web page according to the JSoup selector syntax to locate basic information on the seed web page; adding relevant events, tasks, and entity link words on the seed web page to a crawl queue; and storing the parsed data in Json format into a text.

[0092] In some embodiments, an entity extraction template is configured to extract one or more entities selected from the group consisting of a factory, a logistics company, an order, a raw material supplier, a parts supplier, a subcontractor, a distributor, an inventory, a material, a budget, a country, a region, an enterprise in the upper and lower reaches of an industrial chain, a partner, an outsourcing supplier, a key device, a financial institution, a market, a strategy, a production plan, an industry standard, an output, an order priority, a target, a single-line production index, a product cycle, a constraint, a production stop, abnormal weather, a disease, a natural disaster, a personnel transfer, and a time.

[0093] In some embodiments, a relationship extraction template is configured to extract one or more relationships selected from the group consisting of an acquisition, a financing, a merger, an upstream, a downstream, a receipt, a payment, a pick-up, a delivery, a demand, a purchase, a maintenance, a derived-from, a containment, a cooperation, a strategic partnership, an influence, a consistency, a distribution, a priority, a receipt, a bottleneck, a limitation, a causal relationship, a chronology, and a regional relationship.

[0094] In some embodiments, an attribute extraction template is configured to extract one or more attributes selected from the group consisting of a location, a quantity, an order status, a delivery status, an enterprise status, a device status, a cooperation status, a transportation status, a production status, a financial status, and a payment status.

[0095] In some embodiments, the intelligent management method further includes inferring at least one of a relationship between two entities or a category of an entity. Optionally, inferring the category of the entity is based on constraints in an ontology framework of a knowledge graph, and the constraints include a domain and a range of a relationship connected to the entity.

[0096] In some embodiments, the intelligent management method further includes making inferences using a scoring algorithm. Optionally, the scoring algorithm includes: the similarity between entity 1 and (relationship entity 2); the similarity between (entity 1 relationship) and entity 2; and the similarity between the relationship and (entity 1 entity 2); where represents a linear or non-linear operation selected from the group consisting of addition, multiplication, and neural network operations.

[0097] In some embodiments, the intelligent management method further includes using a training data set to train the parameters of the scoring algorithm.

[0098] On the other hand, the present disclosure provides a computer program product. The computer program product includes a non-transitory tangible computer-readable medium having computer-readable instructions thereon. In some embodiments, the computer-readable instructions can be executed by a processor to cause the processor to perform: generating supply chain constraints based on a supply chain knowledge graph, the supply chain knowledge graph including information on at least one of demand planning and forecasting, inventory planning, sales planning and forecasting, or budget planning; generating industrial chain unexpected events based on an industrial chain event knowledge graph, the industrial chain event knowledge graph including information on at least one of event urgency, event importance, and event impact propagation; generating constraints on the supply chain based on the supply chain constraints and the industrial chain unexpected events; and generating recommendations based on the constraints on the supply chain and providing the recommendations to a business system for supply chain planning, the recommendations including recommendations on at least one of demand replanning and reforecasting, inventory replanning, sales replanning and reforecasting, or budget replanning.

[0099] In some embodiments, the computer-readable instructions can be executed by a processor to cause the processor to further perform: generating an alert based on a potential conflict between the supply chain constraints and the industrial chain unexpected events and providing the alert to the business system; and receiving, from the business system, confirmation of the potential conflict. Optionally, the recommendations are generated upon receiving the confirmation. Optionally, the recommendations include a set of alternative recommendations based on alternative priorities respectively.

[0100] In some embodiments, the computer-readable instructions may be executed by a processor to cause the processor to further execute: generating the supply chain knowledge graph by a supply chain knowledge graph generator by extracting entities, relationships, and attributes from a source including at least one of the commercial system or industry standards. Specifically, the computer-readable instructions may be executed by a processor to cause the processor to further execute: using an extraction tool to extract entities and relationships from structured data; using entity extraction templates, relationship extraction templates, and attribute extraction templates to extract entities, relationships, and attributes from unstructured data respectively; and storing the extracted entities, the extracted relationships, and the extracted attributes in a knowledge graph database during expert verification.

[0101] In some embodiments, to extract entities, relationships, and attributes from unstructured data, the computer-readable instructions may be executed by a processor to cause the processor to further execute: constructing an entity recognition dictionary and entity recognition rules; based on the entity recognition dictionary and the entity recognition rules, using a heuristic algorithm to expand the entity recognition rules to generate new rules; constructing an entity recognition rule library including the entity recognition rules and the new rules; constructing the entity extraction template based on the entity recognition rule library; and constructing the relationship extraction template and attribute extraction template based on keyword, lexical, and syntactic analysis.

[0102] In some embodiments, the computer-readable instructions may be executed by a processor to cause the processor to further execute: generating the industrial chain event knowledge graph by an industrial chain event knowledge graph generator by extracting entities, relationships, and attributes from a source including at least one of an internal knowledge base or a public network knowledge base. Specifically, the computer-readable instructions may be executed by a processor to cause the processor to further execute: crawling the public network knowledge base by a web crawler to obtain trend events of related industries; respectively using entity extraction templates, relationship extraction templates, and attribute extraction templates to extract entities, relationships, and attributes from the trend events; performing knowledge fusion on the internal knowledge base, the extracted entities, the extracted relationships, and the extracted attributes to generate a fused knowledge base; extracting new keywords from the fused knowledge base; and repeatedly executing: crawling the public network knowledge base, extracting entities, relationships, and attributes from the trend events, and performing knowledge fusion.

[0103] In some embodiments, to extract entities, relationships, and attributes from the trend events, the computer-readable instructions may be executed by a processor to cause the processor to further execute: constructing an entity recognition dictionary and entity recognition rules; based on the entity recognition dictionary and the entity recognition rules, using a heuristic algorithm to expand the entity recognition rules to generate new rules; constructing an entity recognition rule library including the entity recognition rules and the new rules; constructing the entity extraction template based on the entity recognition rule library; and constructing the relationship extraction template and attribute extraction template based on keyword, lexical, and syntactic analysis.

[0104] In some embodiments, the computer-readable instructions may be executed by a processor to cause the processor to further perform: repeatedly performing: crawling the public network knowledge base, extracting entities, relationships, and attributes from the trending events, and performing knowledge fusion.

[0105] In some embodiments, the computer-readable instructions may be executed by a processor to cause the processor to further perform: generating a summary of the trending events based on the TextRank algorithm. Specifically, generating the summary of the trending events includes: treating sentences in the industrial chain event knowledge graph as nodes; connecting the nodes in the industrial chain event knowledge graph using vectorless weighted edges, where the corresponding weight of a corresponding edge is the similarity between the two corresponding nodes connected by the corresponding edge; constructing a vectorless weighted graph G(V, E, W) based on the nodes and the vectorless weighted edges, where V represents the nodes, E represents the vectorless weighted edges, and W represents the similarity between the connected nodes; calculating the importance of the nodes respectively; sorting the importance levels of the nodes respectively; and using the selected nodes with relatively higher levels to form the summary of the trending events.

[0106] In some embodiments, the importance is calculated according to equation (1):

[0107]

[0108] where S i represents the i-th node; WS(S i ) represents the importance of the i-th node; S j represents the j-th node; w ji represents the similarity between the i-th node and the j-th node; d represents the damping coefficient, which indicates the probability that the i-th node is selected as one of the selected nodes; In(S i ) represents a set of nodes pointing to the i-th node; Out(S j ) represents a set of nodes pointing to the j-th node.

[0109] In some embodiments, in order for a web crawler to crawl the public network knowledge base, the computer-readable instructions may be executed by a processor to cause the processor to further perform: initializing a crawler task based on a seed web page; downloading and parsing the seed web page according to the JSoup selector syntax to locate basic information on the seed web page; adding relevant events, tasks, and entity link words on the seed web page to a crawl queue; and storing the parsed data in Json format into a text.

[0110] In some embodiments, the entity extraction template is configured to extract one or more entities selected from the group consisting of factory, logistics company, order, raw material supplier, parts supplier, subcontractor, distributor, inventory, material, budget, country, region, upstream and downstream enterprises in the industrial chain, partner, outsourcing supplier, key equipment, financial institution, market, strategy, production plan, industry standard, output, order priority, target, single-line production index, product cycle, constraint, production stop, abnormal weather, disease, natural disaster, personnel transfer, and time.

[0111] In some embodiments, the relationship extraction template is configured to extract one or more relationships selected from the group consisting of acquisition, financing, merger, upstream, downstream, receipt, payment, pick-up, delivery, demand, purchase, maintenance, obtained from, containment, cooperation, strategic partnership, influence, consistency, distribution, priority, receipt, bottleneck, limitation, causality, chronology, and regional relationship.

[0112] In some embodiments, the attribute extraction template is configured to extract one or more attributes selected from the group consisting of location, quantity, order status, delivery status, enterprise status, equipment status, cooperation status, transportation status, production status, financial status, and payment status.

[0113] In some embodiments, the computer-readable instructions can be executed by a processor to cause the processor to further perform: inferring at least one of the relationship between two entities or the category of an entity. Optionally, the computer-readable instructions can be executed by a processor to cause the processor to further perform: inferring the category of the entity based on the constraints in the ontology framework of the knowledge graph, where the constraints include the domain and range of the relationships connected to the entity.

[0114] In some embodiments, the computer-readable instructions can be executed by a processor to cause the processor to further perform: making inferences using a scoring algorithm. Optionally, the scoring algorithm includes: the similarity between entity 1 and (relationship entity 2); the similarity between (entity 1 relationship) and entity 2; and the similarity between the relationship and (entity 1 entity 2); where, represents a linear or non-linear operation selected from the group consisting of addition, multiplication, and neural network operations.

[0115] In some embodiments, the computer-readable instructions can be executed by a processor to cause the processor to further perform: using a training data set to train the parameters of the scoring algorithm.

[0116] The foregoing description of the embodiments of the present invention has been presented for purposes of illustration and description. It is not exhaustive and is not intended to limit the present invention to the precise forms or exemplary embodiments disclosed. Accordingly, the foregoing description should be regarded as illustrative rather than restrictive. Obviously, many modifications and variations will be apparent to those skilled in the art. The embodiments were chosen and described in order to explain the principles of the present invention and its best mode of practical application, thereby enabling those skilled in the art to understand the various embodiments of the present invention and the various modifications suitable for the particular use or implementation being considered. The scope of the present invention is intended to be defined by the appended claims and their equivalents, where all terms are meant in their broadest reasonable sense unless otherwise stated. Thus, terms such as "the invention," "the present invention," etc. do not necessarily limit the scope of the claims to a particular embodiment, and reference to exemplary embodiments of the present invention does not imply a limitation of the present invention and should not be inferred as such. The present invention is limited only by the spirit and scope of the appended claims. Additionally, these claims may refer to the use of "first," "second," etc. followed by a noun or element. These terms should be understood as nomenclature and should not be construed as limiting the number of elements modified by such nomenclature unless a specific number has been given. Any advantages and benefits described may not apply to all embodiments of the present invention. It should be understood that those skilled in the art may make changes to the described embodiments without departing from the scope of the present invention as defined by the appended claims. Further, no element or component in this disclosure is intended to be dedicated to the public, whether or not the element or component is expressly recited in the appended claims.

Claims

1. An intelligent management system, comprising: a supply chain knowledge graph; an industrial chain event knowledge graph; and an intelligent supply chain manager connected to the supply chain knowledge graph and the industrial chain event knowledge graph; wherein, the intelligent supply chain manager includes: a memory; one or more processors; wherein, the memory and the one or more processors are connected to each other; and the memory stores computer-executable instructions for controlling the one or more processors to perform the following operations: generating supply chain constraints based on the supply chain knowledge graph including information of at least one of demand planning and forecasting, inventory planning, sales planning and forecasting, or budget planning; generating industrial chain unexpected events based on the industrial chain event knowledge graph including information of at least one of event urgency, event importance, and event impact propagation degree; generating constraints on the supply chain based on the supply chain constraints and the industrial chain unexpected events; and generating a recommendation based on the constraints on the supply chain and providing the recommendation to a business system for supply chain planning, the recommendation including a recommendation of at least one of demand replanning and reforecasting, inventory replanning, sales replanning and reforecasting, or budget replanning.

2. The intelligent management system according to claim 1, wherein the memory further stores computer-executable instructions for controlling the one or more processors to perform the following operations: generating an alert based on a potential conflict between the supply chain constraints and the industrial chain unexpected events and providing the alert to the business system; and receiving a confirmation of the potential conflict from the business system; wherein, generating the recommendation upon receiving the confirmation.

3. The intelligent management system according to claim 1 or 2, wherein the recommendation includes a set of alternative recommendations based on alternative priorities respectively.

4. The intelligent management system according to claim 1 or 2, further comprising a supply chain knowledge graph generator configured to generate the supply chain knowledge graph by extracting entities, relationships, and attributes from a source including at least one of the business system or industry standards; wherein, the supply chain knowledge graph generator includes: a memory; one or more processors; wherein, the memory and the one or more processors are connected to each other; and the memory stores computer-executable instructions for controlling one or more processors to perform the following operations: extracting entities and relationships from structured data using an extraction tool; extracting entities, relationships, and attributes from unstructured data using an entity extraction template, a relationship extraction template, and an attribute extraction template respectively; and storing the extracted entities, the extracted relationships, and the extracted attributes in a knowledge graph database during expert verification.

5. The intelligent management system according to claim 4, wherein, in order to extract entities, relationships, and attributes from the unstructured data, the memory further stores computer-executable instructions for controlling the one or more processors to perform the following operations: constructing an entity recognition dictionary and entity recognition rules; Based on the entity recognition dictionary and the entity recognition rules, use a heuristic algorithm to expand the entity recognition rules to generate new rules; Construct an entity recognition rule library including the entity recognition rules and the new rules; Construct the entity extraction template based on the entity recognition rule library; And Construct the relationship extraction template and the attribute extraction template based on keyword, lexical, and syntactic analysis.

6. The intelligent management system according to claim 1 or 2 further includes an industrial chain event knowledge graph generator configured to generate the industrial chain event knowledge graph by extracting entities, relationships, and attributes from a source including at least one of an internal knowledge base or a public network knowledge base; Wherein, The industrial chain event knowledge graph generator includes: A memory; One or more processors; Wherein, the memory and the one or more processors are connected to each other; and The memory stores computer-executable instructions for controlling the one or more processors to perform the following operations: Crawl the public network knowledge base through a web crawler to obtain trend events in related industries; Respectively use the entity extraction template, the relationship extraction template, and the attribute extraction template to extract entities, relationships, and attributes from the trend events; Perform knowledge fusion on the internal knowledge base, the extracted entities, the extracted relationships, and the extracted attributes to generate a fused knowledge base; Extract new keywords from the fused knowledge base; and Repeat the execution: crawl the public network knowledge base, extract entities, relationships, and attributes from the trend events, and perform knowledge fusion.

7. The intelligent management system according to claim 6, Wherein, In order to extract entities, relationships, and attributes from the trend events, the memory also stores computer-executable instructions for controlling the one or more processors to perform the following operations: Construct an entity recognition dictionary and entity recognition rules; Based on the entity recognition dictionary and the entity recognition rules, use a heuristic algorithm to expand the entity recognition rules to generate new rules; Construct an entity recognition rule library including the entity recognition rules and the new rules; Construct the entity extraction template based on the entity recognition rule library; And Construct the relationship extraction template and the attribute extraction template based on keyword, lexical, and syntactic analysis.

8. The intelligent management system according to claim 6, wherein the memory also stores computer-executable instructions for controlling the one or more processors to repeat the execution: crawl the public network knowledge base, extract entities, relationships, and attributes from the trend events, and perform knowledge fusion.

9. The intelligent management system according to claim 6, wherein the memory also stores computer-executable instructions for controlling the one or more processors to generate a summary of trend events based on the TextRank algorithm; Wherein, In order to generate the summary of trend events, the memory stores computer-executable instructions for controlling the one or more processors to perform the following operations: Treat the sentences in the industrial chain event knowledge graph as nodes; Connect the nodes in the industrial chain event knowledge graph using vectorless weighted edges, where the weight of the corresponding edge is the similarity between the two corresponding nodes connected by the corresponding edge; Based on the nodes and the vectorless weighted edges, construct a vectorless weighted graph G(V, E, W), where V represents the nodes, E represents the vectorless weighted edges, and W represents the similarity between the connected nodes; Calculate the importance of the nodes respectively; Rank the importance of the nodes respectively; and Use the selected nodes with relatively higher levels to form the trend event summary.

10. The intelligent management system according to claim 9, wherein the importance is calculated according to equation (1): Wherein, S i represents the i-th node; WS(S i ) represents the importance of the i-th node; S j represents the j-th node; w ji represents the similarity between the i-th node and the j-th node; d represents the damping factor, which indicates the probability that the i-th node is selected as one of the selected nodes; In(S i ) represents a set of nodes pointing to the i-th node; Out(S j ) represents a set of nodes pointing to the j-th node.

11. The intelligent management system according to claim 6, Wherein, In order for the web crawler to crawl the public network knowledge base, the memory also stores computer-executable instructions for controlling the one or more processors to perform the following operations: Initialize a crawler task based on the seed web page; Download and parse the seed web page according to the JSoup selector syntax to locate the basic information on the seed web page; Add the relevant events, tasks, and entity link words on the seed web page to the crawl queue; And Store the parsed data in Json format into a text.

12. The intelligent management system according to claim 6, wherein the entity extraction template is configured to extract one or more entities selected from the group consisting of factory, logistics company, order, raw material supplier, parts supplier, subcontractor, distributor, inventory, material, budget, country, region, upstream and downstream enterprises in the industrial chain, partner, outsourcing supplier, key equipment, financial institution, market, strategy, production plan, industry standard, output, order priority, target, single-line production index, product cycle, constraint, production stop, abnormal weather, disease, natural disaster, personnel transfer, and time.

13. The intelligent management system according to claim 6, wherein the relationship extraction template is configured to extract one or more relationships selected from the group consisting of acquisition, financing, merger, upstream, downstream, receipt, payment, pick-up, delivery, demand, purchase, maintenance, obtained from, containment, cooperation, strategic partnership, influence, consistency, distribution, priority, receipt, bottleneck, restriction, causality, chronology, and regional relationship.

14. The intelligent management system according to claim 6, wherein the attribute extraction template is configured to extract one or more attributes selected from the group consisting of location, quantity, order status, delivery status, enterprise status, equipment status, cooperation status, transportation status, production status, financial status, and payment status.

15. The intelligent management system according to claim 1 or 2, further comprising a supply chain knowledge graph generator configured to generate the supply chain knowledge graph and an industrial chain event knowledge graph generator configured to generate the industrial chain event knowledge graph; Wherein, At least one of the supply chain knowledge graph generator or the industrial chain event knowledge graph generator includes an inferencer configured to infer at least one of the relationship between two entities or the category of an entity.

16. The intelligent management system according to claim 15, wherein the inferencer comprises: a memory; one or more processors; wherein the memory and the one or more processors are connected to each other; and the memory stores computer-executable instructions for controlling the one or more processors to infer the category of the entity based on constraints in an ontology framework of a knowledge graph, the constraints including the domain and range of relationships connected to the entity.

17. The intelligent management system according to claim 15, wherein the inferencer comprises: a memory; one or more processors; wherein the memory and the one or more processors are connected to each other; and the memory stores computer-executable instructions for controlling the one or more processors to make inferences using a scoring algorithm; wherein the scoring algorithm includes: Similarity between Entity 1 and (Relationship Entity 2); (Similarity between entity 1 relationship) and entity 2; and Similarity between the relationship and (Entity 1 Entity 2); Among them, represents a linear or non-linear operation selected from the group consisting of addition, multiplication, and neural network operations.

18. The intelligent management system according to claim 17, wherein the memory further stores computer-executable instructions for controlling the one or more processors to train parameters of the scoring algorithm using a training data set.

19. An intelligent management method, comprising: generating supply chain constraints based on a supply chain knowledge graph, the supply chain knowledge graph including information on at least one of demand planning and forecasting, inventory planning, sales planning and forecasting, or budget planning; generating industrial chain unexpected events based on an industrial chain event knowledge graph, the industrial chain event knowledge graph including information on at least one of event urgency, event importance, and event impact propagation; generating constraints on the supply chain based on the supply chain constraints and the industrial chain unexpected events; and generating recommendations based on the constraints on the supply chain and providing the recommendations to a business system for supply chain planning, the recommendations including recommendations on at least one of demand replanning and reforecasting, inventory replanning, sales replanning and reforecasting, or budget replanning.

20. A computer program product comprising a non-transitory tangible computer-readable medium having computer-readable instructions thereon, the computer-readable instructions being executable by a processor to cause the processor to perform: generating supply chain constraints based on a supply chain knowledge graph, the supply chain knowledge graph including information on at least one of demand planning and forecasting, inventory planning, sales planning and forecasting, or budget planning; generating industrial chain unexpected events based on an industrial chain event knowledge graph, the industrial chain event knowledge graph including information on at least one of event urgency, event importance, and event impact propagation; generating constraints on the supply chain based on the supply chain constraints and the industrial chain unexpected events; and Based on the constraints on the supply chain, generate recommendations and provide the recommendations to the business system for supply chain planning, where the recommendations include recommendations for at least one of demand replanning and reforecasting, inventory replanning, sales replanning and reforecasting, or budget replanning.

Images