Combined electric appliance supply chain multi-dimensional early warning method and system based on knowledge graph

Abstract

The invention discloses a combined electric appliance supply chain multi-dimensional early warning method and system based on a knowledge graph, and relates to the field of supply chain management, and the method comprises a collection module which is used for collecting the data content of each link of a combined electric appliance supply chain; the construction module is used for receiving the data content acquired by the acquisition module, identifying key entities in the supply chain based on an NER algorithm, determining an association relationship between the key entities through a relationship extraction technology of dependency syntactic analysis and remote supervision, and synchronously extracting attributes of the key entities in combination with an SVM algorithm so as to construct a supply chain knowledge graph model; according to the method, the knowledge graph is constructed, scattered data in the combined electric appliance supply chain are integrated on a unified platform, a comprehensive and transparent supply chain view is provided, and a manager can check the state of each link of the supply chain in real time and find potential problems in time, so that the transparency of the supply chain is effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of supply chain management technology, and specifically to a multi-dimensional early warning method and system for a combination electrical appliance supply chain based on a knowledge graph. Background Art

[0002] In the combined electrical appliance supply chain, data is stored in disparate locations across various links, with varying formats and standards. This prevents effective information connection and integration, creating information silos. Traditional supply chain management decisions rely heavily on manual experience and historical data, lacking a deep understanding of the complex relationships within the supply chain and the ability to dynamically adapt. This leads to slow responses to market changes and external environmental fluctuations, resulting in the accumulation of risks and wasted costs.

[0003] Existing related technologies, such as some power material supply chain risk monitoring and early warning systems, are insufficient in data processing and in-depth correlation analysis; supply chain management platforms based on knowledge graphs lack the ability to monitor and warn of dynamic changes and risk evolution in real time; and supply chain traceability and early warning systems based on blockchain technology have problems such as slow data processing speed, high storage costs, and poor cross-chain interoperability. Summary of the Invention

[0004] In response to the above-mentioned shortcomings of the prior art, the present invention provides a multi-dimensional early warning method and system for the combined electrical supply chain based on knowledge graph, which can effectively solve the problems of the prior art.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0006] The present invention discloses a multi-dimensional early warning system for a combined electrical appliance supply chain based on a knowledge graph, comprising:

[0007] The acquisition module is used to collect data content from each link of the combination electrical supply chain; the construction module is used to receive the data content collected by the acquisition module, identify key entities in the supply chain based on the NER algorithm, determine the association relationship between key entities through dependency syntax analysis and remote supervision relationship extraction technology, and simultaneously combine the SVM algorithm to extract key entity attributes to build a supply chain knowledge graph model; the monitoring module is used to collect dynamic data from each link of the supply chain in real time, integrate the dynamic data with the static information in the knowledge graph, continuously track the actual operation status of each link of the supply chain, and perform real-time comparison according to the preset standard parameters. If the comparison result deviates from the standard, When the parameters are out of the normal range, feedback is given to the early warning module; the early warning module is used to receive data in the monitoring module that deviates from the normal range defined by the standard parameters, quantify the supply chain risk based on the received data, and simultaneously set the early warning trigger threshold. The early warning is triggered based on the comparison between the early warning trigger threshold and the supply chain risk quantification result; the evaluation module is used to obtain the early warning trigger record in the early warning module, forward the early warning trigger record to the message module, and evaluate the security of the combination electrical supply chain based on the early warning trigger record; the message module is used to receive the early warning trigger record in the early warning module transmitted by the evaluation module, generate the early warning trigger record message based on the early warning trigger record, and store the message

[0008] Furthermore, the collection module combines various links of the electronic supply chain including suppliers, production workshops, logistics and transportation, and sales channels. The data collected by the collection module includes production process data, supply time data, equipment status detection data, and inventory data.

[0009] The acquisition module is internally provided with a pre-processing unit, which is used to clean the data content collected by the acquisition module;

[0010] Among them, when the preprocessing unit cleans the data content, it traverses all the data content collected by the acquisition module, deletes duplicate data and missing data in the data content, and after completing the data cleaning, stores the remaining data content in the acquisition module.

[0011] Furthermore, the data content received during the operation phase of the construction module is the data content stored in the acquisition module after cleaning;

[0012] The NER algorithm in the construction module identifies key entities in the supply chain, including suppliers, production workshops, logistics and transportation, and sales channels. The key entity association relationships include: supply relationships, production relationships, and equipment associations. The key entity attributes include: production capacity, delivery cycle, equipment failure rate, and finished product qualification rate.

[0013] Furthermore, the dynamic data of each link in the supply chain in the monitoring module includes: real-time operating parameters of production line equipment, real-time changes in raw material inventory, real-time supply status of suppliers, real-time location and status of goods during logistics transportation, and real-time order volume and return rate of sales channels;

[0014] The real-time operating parameters of the production line equipment include equipment speed, voltage, and vibration amplitude; real-time changes in raw material inventory include the quantity and time of incoming and outgoing goods, and the remaining inventory; the supplier's real-time supply status includes shipping notification information, in-transit location information, and dynamic updates of the estimated arrival time; the real-time location and status of goods during logistics transportation include the driving trajectory of the transport vehicle, whether the goods are damaged, and the damage rate;

[0015] Among them, the operation of continuously tracking the actual operating status of each link in the supply chain in the monitoring module is: continuously monitoring and recording the operating status and activity content of each link in the combination electrical supply chain.

[0016] Furthermore, the quantitative operation logic of the supply chain risk in the early warning module is:

[0017] For different types of data content, customize and edit the risk function of each type of data content relative to the supply chain, so that all functions obey: the greater the data deviates from the normal range defined by the standard parameters, the greater the result of the function;

[0018] Among them, all quantified supply chain risk calculation results are normalized. When the supply chain risk quantification results in the early warning module do not meet the early warning trigger threshold, the early warning module triggers an early warning. The early warning triggering methods include: a text message pop-up on a designated computer device, and a preset early warning audio broadcast by the supply chain management background speaker.

[0019] Furthermore, the acquisition module to the early warning module are repeatedly run in the system. After the early warning module triggers an early warning for at least three times, the evaluation module is subsequently run to evaluate the security of the combination electrical supply chain based on the early warning triggering results.

[0020] The safety evaluation logic of the combination electrical supply chain is as follows:

[0021]

[0022] Where: Q is the safety performance value of the combination electrical supply chain; n is the total number of historical warning triggering times; t i , t t+1 is the timestamp of the i-th and i+1-th warning triggering; m is the total amount of data that deviates from the normal range defined by the standard parameters; q j is the deviation value of the jth data; (q0) j The standard parameters preset for the jth data;

[0023] Among them, the larger the Q is, the safer the combination electrical appliance supply chain is, and vice versa, the less secure the combination electrical appliance supply chain is.

[0024] Furthermore, the system is applied to several combination electrical supply chains, evaluates each combination electrical supply chain based on the evaluation module, and arranges each combination electrical supply chain in descending order based on the evaluation results, so that the ones with larger Q values ​​are arranged in the front and the ones with smaller Q values ​​are arranged in the back. The system-side user independently decides to abandon the combination electrical supply chain at the back of the combination electrical supply chain queue.

[0025] Furthermore, the message content stored in the message module includes: warning trigger time, supply chain function output result;

[0026] Among them, the system end user accesses the system by connecting to the network where the system is located through a mobile computer device, and reads the warning trigger record message in the message module.

[0027] Furthermore, the acquisition module is interactively connected to a preprocessing module via a wireless network, the acquisition module is interactively connected to a construction module, a monitoring module and an early warning module via a wireless network, and the early warning module is interactively connected to an evaluation module and a message module via a wireless network.

[0028] Furthermore, the multi-dimensional early warning method for the combined electrical appliance supply chain based on the knowledge graph includes the following steps:

[0029] Collect data from all links of the combination electrical appliance supply chain; obtain data content, use the NER algorithm to identify key entities, determine the supply, production and other relationships between entities through dependency syntax analysis and remote supervision technology, apply the SVM algorithm to extract key entity attributes such as production capacity and delivery cycle, and build a supply chain knowledge graph model; collect dynamic data from all links of the supply chain in real time, integrate static information of the knowledge graph, track the actual operating status of each link, and compare in real time according to preset standard parameters. Once the data deviates from the normal range, trigger an early warning; quantify supply chain risks, set early warning trigger thresholds, compare the thresholds and risk quantification results, and trigger an early warning when the risk quantification results reach or exceed the threshold; obtain early warning trigger records, and evaluate the security of the combination electrical appliance supply chain based on the record content; generate early warning trigger record messages and store these messages.

[0030] Compared with the prior art, the technical solution provided by the present invention has the following beneficial effects:

[0031] 1. Improve supply chain transparency: By building a knowledge graph, the scattered data in the combination appliance supply chain is integrated on a unified platform, providing a comprehensive and transparent supply chain view. Managers can view the status of each link in the supply chain in real time and identify potential problems in a timely manner, thereby effectively improving supply chain transparency.

[0032] 2. Improve the level of intelligent decision-making: Traditional supply chain decisions rely on manual experience and historical data, making it difficult to deeply understand the complex relationships in the supply chain. This invention uses knowledge graphs and intelligent reasoning based on multi-dimensional data to quickly generate accurate decision-making recommendations. The system can not only make decisions based on the current supply chain status, but also dynamically adjust decisions based on historical trends, external market changes and other factors, greatly improving the intelligence and accuracy of decision support.

[0033] 3. Enhance supply chain adaptability: Utilize the intelligent reasoning function of knowledge graph technology to monitor various risk factors in the supply chain in real time, and predict potential risks based on big data analysis. Through real-time data analysis and intelligent reasoning, the system can flexibly adjust the strategies of each link in the supply chain, making the supply chain more flexible and adaptable, and able to quickly respond to changes in the external environment, effectively enhancing the supply chain's risk resistance. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0035] Figure 1 Schematic diagram of the structure of the multi-dimensional early warning system for the combined electrical supply chain based on knowledge graph;

[0036] Figure 2 Flowchart of the multi-dimensional early warning method for combination electrical appliance supply chain based on knowledge graph. DETAILED DESCRIPTION

[0037] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0038] The present invention will be further described below with reference to the embodiments.

[0039] Example 1:

[0040] The multi-dimensional early warning system for the combined electrical appliance supply chain based on the knowledge graph in this embodiment is as follows: Figure 1 Shown, including:

[0041] The collection module is used to collect data content from various links of the combination electrical supply chain;

[0042] The collection module combines various links of the electronic supply chain, including suppliers, production workshops, logistics and transportation, and sales channels. The data collected by the collection module includes production process data, supply time data, equipment status detection data, and inventory data.

[0043] The acquisition module is internally provided with a pre-processing unit, which is used to clean the data content collected by the acquisition module;

[0044] Among them, when the pre-processing unit cleans the data content, it traverses all the data content collected by the acquisition module, deletes the duplicate data and missing data in the data content, and after completing the data cleaning, stores the remaining data content in the acquisition module;

[0045] The construction module is used to receive the data collected by the collection module, identify key entities in the supply chain based on the NER algorithm, determine the association relationship between key entities through dependency syntax analysis and remote supervision relationship extraction technology, and simultaneously extract key entity attributes in combination with the SVM algorithm to build a supply chain knowledge graph model;

[0046] The data content received during the construction module operation phase is the data content stored in the acquisition module after cleaning;

[0047] The NER algorithm in the construction module identifies key entities in the supply chain, including suppliers, production workshops, logistics and transportation, and sales channels. Key entity relationships include: supply relationships, production relationships, and equipment relationships. Key entity attributes include: production capacity, delivery cycle, equipment failure rate, and finished product qualification rate.

[0048] The monitoring module is used to collect dynamic data from all links of the supply chain in real time, integrate the dynamic data with the static information in the knowledge graph, continuously track the actual operating status of each link in the supply chain, and perform real-time comparison according to preset standard parameters. If the comparison result deviates from the normal range defined by the standard parameters, feedback is provided to the early warning module;

[0049] The dynamic data of each link in the supply chain in the monitoring module includes: real-time operating parameters of production line equipment, real-time changes in raw material inventory, real-time supply status of suppliers, real-time location and status of goods during logistics transportation, and real-time order volume and return rate of sales channels;

[0050] Real-time operating parameters of production line equipment include equipment speed, voltage, and vibration amplitude; real-time changes in raw material inventory include the quantity and time of incoming and outgoing goods, and the remaining inventory; real-time supplier supply status includes shipping notification information, in-transit location information, and dynamic updates of the estimated arrival time; the real-time location and status of goods during logistics transportation include the driving trajectory of the transport vehicle, whether the goods are damaged, and the damage rate;

[0051] Among them, the operation of continuously tracking the actual operating status of each link in the supply chain in the monitoring module is to continuously monitor and record the operating status and activity content of each link in the combination electrical supply chain;

[0052] The early warning module is used to receive data from the monitoring module that deviates from the normal range defined by standard parameters, quantify supply chain risks based on the received data, and simultaneously set early warning trigger thresholds. Based on the comparison between the early warning trigger thresholds and the supply chain risk quantification results, an early warning is triggered;

[0053] The quantitative operation logic of supply chain risk in the early warning module is:

[0054] For different types of data content, customize and edit the risk function of each type of data content relative to the supply chain, so that all functions obey: the greater the data deviates from the normal range defined by the standard parameters, the greater the result of the function;

[0055] Among them, all quantified supply chain risk calculation results are normalized. When the supply chain risk quantification results in the early warning module do not meet the early warning trigger threshold, the early warning module triggers an early warning. The early warning triggering methods include: a text message pop-up on a designated computer device, and a preset early warning audio broadcast by the supply chain management backend speaker;

[0056] The evaluation module is used to obtain the warning trigger record in the warning module, forward the warning trigger record to the message module, and evaluate the security of the combination electrical supply chain based on the warning trigger record;

[0057] The message module is used to receive the warning trigger record in the warning module transmitted by the evaluation module, generate the warning trigger record message based on the warning trigger record, and store the message;

[0058] The message content stored in the message module includes: warning trigger time, supply chain function output results;

[0059] Among them, the system end user accesses the system through a mobile computer device connected to the system's network and reads the warning trigger record message in the message module;

[0060] The collection module to the early warning module are repeatedly run in the system. After the early warning module triggers an alarm for at least three times, the evaluation module will follow and evaluate the security of the combination electrical supply chain based on the early warning trigger results.

[0061] The logic for evaluating the security of the combination electrical supply chain is as follows:

[0062]

[0063] Where: Q is the safety performance value of the combination electrical supply chain; n is the total number of historical warning triggering times; t i , t t+1 is the timestamp of the i-th and i+1-th warning triggering; m is the total amount of data that deviates from the normal range defined by the standard parameters; q j is the deviation value of the jth data; (q0) j The standard parameters preset for the jth data;

[0064] Among them, the larger the Q is, the more secure the supply chain of combination electrical appliances is; conversely, the less secure the supply chain of combination electrical appliances is.

[0065] By calculating the above logical formula, the security of the combined electrical supply chain is obtained, so that system users can adaptively manage the supply chains of each combined electrical appliance;

[0066] The system is applied to several combined electrical supply chains. Based on the evaluation module, each combined electrical supply chain is evaluated and sorted in descending order based on the evaluation results, with the ones with larger Q values ​​arranged at the front and the ones with smaller Q values ​​arranged at the back. The system end user can independently decide to discard the combined electrical supply chain at the back of the supply chain queue.

[0067] The acquisition module is interactively connected to the pre-processing module via a wireless network. The acquisition module is interactively connected to the construction module, the monitoring module and the early warning module via a wireless network. The early warning module is interactively connected to the evaluation module and the message module via a wireless network.

[0068] In this embodiment, the acquisition module collects data content from each link of the combination electrical appliance supply chain; the pre-processing unit cleans the data content collected by the acquisition module synchronously, and the construction module is post-operated to receive the data content collected by the acquisition module, identifies key entities in the supply chain based on the NER algorithm, determines the association relationship between key entities through dependency syntax analysis and remote supervision relationship extraction technology, and synchronously extracts key entity attributes in combination with the SVM algorithm to construct a supply chain knowledge graph model. The monitoring module then collects dynamic data from each link of the supply chain in real time, integrates the dynamic data with the static information in the knowledge graph, continuously tracks the actual operation status of each link of the supply chain, and performs real-time monitoring according to preset standard parameters. When the comparison result deviates from the normal range defined by the standard parameters, it will be fed back to the early warning module. The early warning module further receives the data in the monitoring module that deviates from the normal range defined by the standard parameters, quantifies the supply chain risk based on the received data, and simultaneously sets the early warning trigger threshold. Based on the comparison between the early warning trigger threshold and the supply chain risk quantification result, the early warning is triggered. The early warning trigger record in the early warning module is obtained through the evaluation module at the same time, and the early warning trigger record is forwarded to the message module. The security of the combination electrical supply chain is evaluated based on the early warning trigger record. Finally, the message module receives the early warning trigger record in the early warning module transmitted by the evaluation module, generates an early warning trigger record message based on the early warning trigger record, and stores the message.

[0069] Through the comprehensive data collection and knowledge graph construction of the system in the above embodiment, the integration and visualization of supply chain data are achieved, breaking down data barriers. It can also monitor the dynamics of each link in the supply chain in real time, integrating and comparing real-time data with static information, and promptly identifying and reporting anomalies. Accurately quantifying risks and setting thresholds to trigger warnings facilitates enterprises to prevent and control risks in advance. Supply chain security can be assessed based on warning records, providing strong support for decision-making. Relevant messages are stored to facilitate review and analysis, thereby improving supply chain management and risk response capabilities, and ensuring the stable and efficient operation of the combination appliance supply chain.

[0070] Example 2:

[0071] In terms of specific implementation, based on Example 1, this example refers to Figure 2 The multi-dimensional early warning system for the combined electrical appliance supply chain based on the knowledge graph in Example 1 is further described in detail:

[0072] The multi-dimensional early warning method for the combined electrical appliance supply chain based on knowledge graph includes the following steps:

[0073] Step 1: Collect data from all links of the combination appliance supply chain;

[0074] Step 2: Obtain data content, use the NER algorithm to identify key entities, determine the supply, production and other relationships between entities through dependency syntax analysis and remote supervision technology, apply the SVM algorithm to extract key entity attributes such as production capacity and delivery cycle, and build a supply chain knowledge graph model;

[0075] Step 3: Real-time collection of dynamic data from all links in the supply chain, integration of static information from the knowledge graph, tracking of the actual operating status of each link, and real-time comparison according to preset standard parameters. Once data deviates from the normal range, an early warning is triggered;

[0076] Step 31: Quantify supply chain risks, set warning trigger thresholds, compare the thresholds with risk quantification results, and trigger warnings when the risk quantification results reach or exceed the thresholds;

[0077] Step 4: Obtain the warning trigger records and evaluate the security of the combination appliance supply chain based on the records;

[0078] Step 5: Generate warning trigger record messages and store these messages.

[0079] In summary, the systems and methods in the above embodiments integrate the scattered data in the combination appliance supply chain on a unified platform by constructing a knowledge graph, providing a comprehensive and transparent supply chain view. Managers can view the status of each link in the supply chain in real time and discover potential problems in a timely manner, thereby effectively improving the transparency of the supply chain. In addition, the knowledge graph is used to perform intelligent reasoning based on multi-dimensional data to quickly generate accurate decision-making recommendations. The system can not only make decisions based on the current supply chain status, but also dynamically adjust decisions based on historical trends, external market changes and other factors, greatly improving the intelligence level and accuracy of decision support. At the same time, the intelligent reasoning function of knowledge graph technology is used to monitor various risk factors in the supply chain in real time, and predict potential risks based on big data analysis. Through real-time data analysis and intelligent reasoning, the system can flexibly adjust the strategies of each link in the supply chain, making the supply chain more flexible and adaptable, and able to quickly respond to changes in the external environment, effectively enhancing the risk resistance of the supply chain.

[0080] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A multi-dimensional early warning system for the combined electrical supply chain based on knowledge graph, characterized by: include: The collection module is used to collect data content from various links of the combination electrical supply chain; The construction module is used to receive the data collected by the collection module, identify key entities in the supply chain based on the NER algorithm, determine the association relationship between key entities through dependency syntax analysis and remote supervision relationship extraction technology, and simultaneously extract key entity attributes in combination with the SVM algorithm to build a supply chain knowledge graph model; The monitoring module is used to collect dynamic data from all links of the supply chain in real time, integrate the dynamic data with the static information in the knowledge graph, continuously track the actual operating status of each link in the supply chain, and perform real-time comparison according to preset standard parameters. If the comparison result deviates from the normal range defined by the standard parameters, feedback is provided to the early warning module; The early warning module is used to receive data from the monitoring module that deviates from the normal range defined by standard parameters, quantify supply chain risks based on the received data, and simultaneously set early warning trigger thresholds. Based on the comparison between the early warning trigger thresholds and the supply chain risk quantification results, an early warning is triggered; The evaluation module is used to obtain the warning trigger record in the warning module, forward the warning trigger record to the message module, and evaluate the security of the combination electrical supply chain based on the warning trigger record; The message module is used to receive the warning trigger record in the warning module transmitted by the evaluation module, generate the warning trigger record message based on the warning trigger record, and store the message.

2. The multi-dimensional early warning system for combined electrical appliance supply chain based on knowledge graph according to claim 1 is characterized in that: The collection module combines various links of the electronic supply chain, including suppliers, production workshops, logistics and transportation, and sales channels. The data collected by the collection module includes production process data, supply time data, equipment status detection data, and inventory data. The acquisition module is internally provided with a pre-processing unit, which is used to clean the data content collected by the acquisition module; Among them, when the preprocessing unit cleans the data content, it traverses all the data content collected by the acquisition module, deletes duplicate data and missing data in the data content, and after completing the data cleaning, stores the remaining data content in the acquisition module.

3. The multi-dimensional early warning system for combined electrical appliance supply chain based on knowledge graph according to claim 1 is characterized in that: The data content received during the operation phase of the construction module is the data content stored in the acquisition module after cleaning; The NER algorithm in the construction module identifies key entities in the supply chain, including suppliers, production workshops, logistics and transportation, and sales channels. The key entity association relationships include: supply relationships, production relationships, and equipment associations. The key entity attributes include: production capacity, delivery cycle, equipment failure rate, and finished product qualification rate.

4. The multi-dimensional early warning system for combined electrical appliance supply chain based on knowledge graph according to claim 1 is characterized in that: The dynamic data of each link in the supply chain in the monitoring module includes: real-time operating parameters of production line equipment, real-time changes in raw material inventory, real-time supply status of suppliers, real-time location and status of goods during logistics transportation, and real-time order volume and return rate of sales channels; The real-time operating parameters of the production line equipment include equipment speed, voltage, and vibration amplitude; real-time changes in raw material inventory include the quantity and time of incoming and outgoing goods, and the remaining inventory; the supplier's real-time supply status includes shipping notification information, in-transit location information, and dynamic updates of the estimated arrival time; the real-time location and status of goods during logistics transportation include the driving trajectory of the transport vehicle, whether the goods are damaged, and the damage rate; Among them, the operation of continuously tracking the actual operating status of each link in the supply chain in the monitoring module is: continuously monitoring and recording the operating status and activity content of each link in the combination electrical supply chain.

5. The multi-dimensional early warning system for combined electrical appliance supply chain based on knowledge graph according to claim 1 is characterized in that: The quantitative operation logic of the supply chain risk in the early warning module is: For different types of data content, customize and edit the risk function of each type of data content relative to the supply chain, so that all functions obey: the greater the data deviates from the normal range defined by the standard parameters, the greater the result of the function; Among them, all quantified supply chain risk calculation results are normalized. When the supply chain risk quantification results in the early warning module do not meet the early warning trigger threshold, the early warning module triggers an early warning. The early warning triggering methods include: a text message pop-up on a designated computer device, and a preset early warning audio broadcast by the supply chain management background speaker.

6. The multi-dimensional early warning system for combined electrical appliance supply chain based on knowledge graph according to claim 1 is characterized in that: The acquisition module to the early warning module are repeatedly run in the system. After the early warning module triggers an early warning for at least three times, the evaluation module is run to evaluate the security of the combination electrical supply chain based on the early warning triggering results. The safety evaluation logic of the combination electrical supply chain is as follows: Where: Q is the safety performance value of the combination electrical supply chain; n is the total number of historical warning triggering times; t i , t t+1 The timestamps of the i-th and i+1-th warning triggering; m is the total amount of data that deviates from the normal range defined by the standard parameters; q j is the deviation value of the jth data; (q0) j The standard parameters preset for the jth data; Among them, the larger the Q is, the safer the combination electrical appliance supply chain is, and vice versa, the less secure the combination electrical appliance supply chain is.

7. The multi-dimensional early warning system for combined electrical appliance supply chain based on knowledge graph according to claim 6 is characterized in that: The system is applied to several combination electrical appliance supply chains, evaluates each combination electrical appliance supply chain based on an evaluation module, and arranges each combination electrical appliance supply chain in descending order based on the evaluation results, so that the ones with larger Q values ​​are arranged in the front and the ones with smaller Q values ​​are arranged in the back. The system end user independently decides to abandon the combination electrical appliance supply chain at the back of the combination electrical appliance supply chain queue.

8. The multi-dimensional early warning system for combined electrical appliance supply chain based on knowledge graph according to claim 1 is characterized in that: The message content stored in the message module includes: warning trigger time, supply chain function output result; Among them, the system end user accesses the system by connecting to the network where the system is located through a mobile computer device, and reads the warning trigger record message in the message module.

9. The multi-dimensional early warning system for combined electrical appliance supply chain based on knowledge graph according to claim 1 is characterized in that: The acquisition module is interactively connected to the pre-processing module via a wireless network. The acquisition module is interactively connected to the construction module, the monitoring module and the early warning module via a wireless network. The early warning module is interactively connected to the evaluation module and the message module via a wireless network.

10. A multi-dimensional early warning method for a combined electrical appliance supply chain based on a knowledge graph, the method being an implementation method of a multi-dimensional early warning system for a combined electrical appliance supply chain based on a knowledge graph as claimed in any one of claims 1 to 9, characterized in that: The following steps are involved: Step 1: Collect data from all links of the combination appliance supply chain; Step 2: Obtain data content, use the NER algorithm to identify key entities, determine the supply, production and other relationships between entities through dependency syntax analysis and remote supervision technology, apply the SVM algorithm to extract key entity attributes such as production capacity and delivery cycle, and build a supply chain knowledge graph model; Step 3: Real-time collection of dynamic data from all links in the supply chain, integration of static information from the knowledge graph, tracking of the actual operating status of each link, and real-time comparison according to preset standard parameters. Once data deviates from the normal range, an early warning is triggered; Step 31: Quantify supply chain risks, set warning trigger thresholds, compare the thresholds with risk quantification results, and trigger warnings when the risk quantification results reach or exceed the thresholds; Step 4: Obtain the warning trigger records and evaluate the security of the combination appliance supply chain based on the records; Step 5: Generate warning trigger record messages and store these messages.

Images