KR-20260064789-A - METHOD AND SYSTEM FOR AI-BASED REAL-TIME SUPPLY CHAIN RISK DETECTION AND RESPONSE

KR20260064789AKR 20260064789 AKR20260064789 AKR 20260064789AKR-20260064789-A

Abstract

An AI-based real-time supply chain risk detection and response method and system are disclosed. The AI-based real-time supply chain risk detection technology extracts supply chain-related information from news articles using natural language processing technology, analyzes global news sources using multilingual processing capabilities, evaluates news sentiment through sentiment analysis, and identifies companies and products related to major news issues through topic modeling and named entity recognition.

Inventors

양진홍

Assignees

인제대학교 산학협력단

Dates

Publication Date: 20260508
Application Date: 20241029

Claims (16)

At least one processor implemented to execute readable instructions on a computer device Includes, The above-mentioned at least one processor is, The process of extracting supply chain-related information from news articles using natural language processing technology; A process of analyzing global news sources through multilingual processing capabilities and evaluating the sentiment of news through sentiment analysis; and The process of identifying companies and products related to major news issues through topic modeling and named entity recognition A computer device that processes.
In paragraph 1, The above-mentioned at least one processor is, Refining and standardizing news data, Through text normalization, it provides data in a consistent format, and Detect the language of the news and translate it into the target language, and Process technical terms using a domain-specific dictionary, and Performing tokenization by considering the linguistic characteristics of news through morphological analysis A computer device characterized by
In paragraph 1, The above-mentioned at least one processor is, Analyze the sentiment of news articles using an LSTM (long short-term memory) network and a supply chain-related sentiment dictionary, and Analyze the topics of news articles using the LAD (latent Dirichlet allocation) model and the BERT (bidirectional encoder representations from transformers) model, and Analyzing named entities in news articles using the CRF (Conditional Random Fields) model A computer device characterized by
In paragraph 1, The above at least one processor is, Calculating a relevance score representing the influence of news articles on the supply chain through multidimensional analysis considering the results of sentiment analysis, topic analysis, and named entity analysis of news articles. A computer device characterized by
In paragraph 1, The above at least one processor is, Predicting supply chain risks using external data sources through time series analysis and machine learning techniques A computer device characterized by
In paragraph 5, The above-mentioned at least one processor is, Collects external data including ERP (enterprise resource planning) data and SCM (supply chain management) data, and Construct a consistent dataset through data consistency verification, and Reflecting the latest information through real-time data streaming and batch processing A computer device characterized by
In paragraph 5, The above-mentioned at least one processor is, Selecting variables related to supply chain risk prediction through characteristic importance analysis A computer device characterized by
In paragraph 5, The above at least one processor is, By combining time series analysis and machine learning techniques to predict short-term and medium-to-long-term risks in the supply chain, and Calculating the final supply chain risk score by synthesizing the causal relationships between the results of short- and medium-to-long-term supply chain risk forecasts and supply chain risk factors. A computer device characterized by
In paragraph 1, The above at least one processor is, Predicting inventory depletion by analyzing supply chain BOM data, inventory data, and production planning data A computer device characterized by
In Paragraph 9, The above-mentioned at least one processor is, Tracking changes over time for supply chain BOM data, inventory data, and production planning data through time-series data synchronization A computer device characterized by
In Paragraph 9, The above at least one processor is, Calculating the probability of inventory shortages and the expected timing of occurrence by simulating the inventory depletion process based on supply and demand forecast results of the supply chain. A computer device characterized by
In Paragraph 9, The above at least one processor is, Generating a risk profile for inventory depletion by analyzing simulation results of the supply chain inventory depletion process. A computer device characterized by
In paragraph 1, The above-mentioned at least one processor is, Recommending alternative suppliers through supplier risk assessment A computer device characterized by
In Paragraph 13, The above-mentioned at least one processor is, Calculate similarity between suppliers through similarity using supplier data, and Evaluate the reliability of suppliers based on past performance data, and Calculating the supplier recommendation score by combining similarity and reliability A computer device characterized by
In Paragraph 13, The above-mentioned at least one processor is, Selecting alternative suppliers through a multi-criteria decision-making model that considers the supplier's profile, past performance, geographical location, and production capacity A computer device characterized by
In an AI-based real-time supply chain risk detection method for a computer device comprising at least one processor, A step of extracting supply chain-related information from news articles through an AI model by the above-mentioned at least one processor; A step of predicting potential risks in the supply chain by integrating external data sources by the above-mentioned at least one processor; A step of predicting inventory depletion by analyzing supply chain BOM data, current inventory levels, production plans, and market demand by at least one processor; and A step of recommending an alternative supplier based on the risk level of the supplier by the above-mentioned at least one processor AI-based real-time supply chain risk detection method including

Description

Method and System for AI-Based Real-Time Supply Chain Risk Detection and Response The following description concerns supply chain management technology. Supply chain management (SCM) refers to a system that identifies the flow of logistics from parts suppliers to producers, distributors, and customers from the perspective of a single value chain and supports the smooth flow of necessary information. It is a management innovation technique that aims to achieve overall process optimization among the components of the supply chain, moving away from departmental or individual firm-level optimization within the company. As an example of supply chain management technology, Korean registered patent No. 10-2535663 (registered on May 18, 2023) discloses a technology that analyzes the risk level in the supply chain by analyzing trade information between companies or countries in the supply chain and transaction information between domestic companies through supply chain analysis of materials including resources, products, and services. FIG. 1 is a block diagram illustrating an example of the internal configuration of a computer device in an embodiment of the present invention. FIG. 2 illustrates the overall architecture of an AI-based real-time supply chain risk detection system in one embodiment of the present invention. FIG. 3 illustrates the detailed configuration of an AI-based news analysis engine in one embodiment of the present invention. Figure 4 illustrates the detailed configuration of a supply chain risk prediction model in one embodiment of the present invention. FIG. 5 illustrates the detailed configuration of an inventory depletion prediction system in one embodiment of the present invention. FIG. 6 illustrates the detailed configuration of an alternative supplier recommendation engine in one embodiment of the present invention. Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings. Embodiments of the present invention relate to supply chain management technology utilizing AI (artificial intelligence) technology. Embodiments including those specifically disclosed in this specification can analyze the impact of global events on the supply chain in real time based on AI, predict risks more accurately by integrating and analyzing various data sources in real time, and support risk management through inventory optimization and supplier diversification, as well as rapid and accurate data-driven decision-making. An AI-based real-time supply chain risk detection system according to embodiments of the present invention may be implemented by at least one computer device, and an AI-based real-time supply chain risk detection method according to embodiments of the present invention may be performed through at least one computer device included in the AI-based real-time supply chain risk detection system. At this time, a computer program according to an embodiment of the present invention may be installed and run on the computer device, and the computer device may perform an AI-based real-time supply chain risk detection method according to embodiments of the present invention under the control of the run computer program. The above-described computer program may be stored on a computer-readable recording medium to be combined with the computer device to execute the AI-based real-time supply chain risk detection method on the computer. FIG. 1 is a block diagram illustrating an example of a computer device according to an embodiment of the present invention. For example, an AI-based real-time supply chain risk detection system according to embodiments of the present invention may be implemented by a computer device (100) illustrated in FIG. 1. As illustrated in FIG. 1, a computer device (100) may include a memory (110), a processor (120), a communication interface (130), and an input/output interface (140) as components for executing an AI-based real-time supply chain risk detection method according to embodiments of the present invention. Memory (110) is a computer-readable recording medium and may include a non-perishable mass storage device such as RAM (random access memory), ROM (read only memory), and a disk drive. Here, a non-perishable mass storage device such as a ROM and a disk drive may be included in the computer device (100) as a separate permanent storage device distinct from memory (110). Additionally, an operating system and at least one program code may be stored in memory (110). These software components may be loaded into memory (110) from a computer-readable recording medium separate from memory (110). This separate computer-readable recording medium may include a computer-readable recording medium such as a floppy drive, disk, tape, DVD/CD-ROM drive, or memory card. In another embodiment, software components may be loaded into memory (110) through a communication interface (130) rather than a computer-readable recording medium. For e