Industrial chain risk early warning method, device, equipment, medium and product
By identifying financial risk events and analyzing their impact on the target industrial chain, the shortcomings of existing technologies in identifying and analyzing financial risk events are addressed, thereby improving the stability of the industrial chain.
Patent Information
- Application Number
- CN202510817833.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-18
- Publication Date
- 2025-10-28
AI Technical Summary
Existing technologies are insufficient to effectively identify and analyze the impact of financial risk events on the industrial chain, resulting in insufficient stability of the industrial chain.
By detecting financial risk events, using pre-trained language models to identify target companies, and based on the companies' upstream and downstream order relationships, investment relationships, and service interaction relationships, the target industrial chain is determined, and risk analysis and early warning are conducted.
It improves the stability of the industrial chain and enables timely risk warning and management by identifying and analyzing the impact of financial risk events on the target industrial chain.
Smart Images
Figure CN120851585A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of supply chain technology, and in particular to a method, device, equipment, medium and product for supply chain risk early warning. Background Technology
[0002] The industrial chain is a concept in industrial economics, which refers to the entire industrial chain from production, supply and sales, from raw materials to consumers. It is a chain-like relationship formed objectively between various sectors based on certain technological and economic links and according to specific logical and spatiotemporal layout relationships.
[0003] The essence of a supply chain is the connection between enterprises in different industries, and this connection is essentially the supply and demand relationship between these enterprises. Because supply chains involve numerous upstream and downstream relationships and the exchange of value, upstream links supply products or services to downstream links, and downstream links provide feedback to upstream links. If some enterprises experience operational problems, it may lead to risk propagation and cascading effects on upstream and downstream enterprises in the supply chain. Therefore, it is necessary to conduct risk analysis and identification within the supply chain. Summary of the Invention
[0004] This invention provides a method, device, equipment, medium, and product for early warning of supply chain risks. Based on financial risk events and the upstream and downstream order relationships, investment relationships, and service interaction relationships of target enterprises, it determines that the financial risk event involves the target supply chain and analyzes the impact of the financial risk event on the target supply chain, thereby conducting risk analysis and early warning of the supply chain to improve its stability.
[0005] To achieve the above objectives, embodiments of the present invention provide a supply chain risk early warning method, including:
[0006] When a financial risk event is detected, the target enterprise involved in the financial risk event is determined based on the financial risk event;
[0007] Based on the upstream and downstream order relationships, investment relationships, and service interaction relationships of the target enterprise, the target industry chain to which the target enterprise belongs is determined;
[0008] Based on the aforementioned financial risk events, conduct risk analysis on the target industrial chain;
[0009] Risk warnings are issued for the target industrial chain based on the risk analysis results.
[0010] As an improvement to the above solution, when a financial risk event is detected, determining the target enterprise involved in the financial risk event based on the financial risk event includes:
[0011] When a financial risk event is detected, the event trigger words and key arguments of the financial risk event are obtained;
[0012] The target companies involved in the financial risk event are determined based on the event trigger words and key event arguments.
[0013] As an improvement to the above scheme, the step of determining the target enterprise involved in the financial risk event based on the event trigger words and key event arguments includes:
[0014] Match relevant companies based on the key arguments of the event and a pre-set securities knowledge base;
[0015] If there are multiple related companies, the related companies are verified according to the event trigger words, and the verified related companies are the target companies involved in the financial risk event.
[0016] As an improvement to the above solution, determining the target industry chain to which the target enterprise belongs based on its upstream and downstream order relationships, investment relationships, and service interaction relationships includes:
[0017] Obtain the association information of the target company, and determine the upstream and downstream companies that are associated with the target company based on the association information;
[0018] Based on the upstream and downstream enterprises, determine the upstream and downstream order relationships, investment relationships, and service interaction relationships of the target enterprise;
[0019] Based on the upstream and downstream order relationships, investment relationships, and service interaction relationships, the target industry chain to which the target enterprise belongs is determined.
[0020] As an improvement to the above solution, the step of conducting risk analysis on the target industrial chain based on the financial risk event includes:
[0021] Determine the risk management type for the target industry chain;
[0022] Risk analysis is conducted on the target industrial chain based on the financial risk events and the risk management type.
[0023] As an improvement to the above solution, the step of conducting risk analysis on the target industrial chain based on the financial risk event and the risk management type includes:
[0024] If the target industry chain is capital-driven, risk analysis is performed on the financing data of the target industry chain based on the financial risk event.
[0025] If the target industry chain is technology-innovative, risk analysis is performed on the patent technology data of the target industry chain based on the financial risk event;
[0026] If the target industrial chain is labor-intensive, risk analysis is performed on the worker data of the target industrial chain based on the financial risk event.
[0027] To achieve the above objectives, embodiments of the present invention provide a supply chain risk early warning device, comprising:
[0028] The target enterprise determination module is used to determine the target enterprise involved in the financial risk event based on the financial risk event when a financial risk event is detected.
[0029] The target industry determination module is used to determine the target industry chain to which the target enterprise belongs based on the upstream and downstream order relationships, investment relationships, and service interaction relationships of the target enterprise;
[0030] The industry risk analysis module is used to conduct risk analysis on the target industry chain based on the financial risk event.
[0031] The industry risk early warning module is used to provide risk warnings for the target industry chain based on the risk analysis results.
[0032] To achieve the above objectives, this invention provides a supply chain risk warning device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the supply chain risk warning method described above.
[0033] To achieve the above objectives, embodiments of the present invention also provide a computer-readable storage medium, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to execute the above-mentioned supply chain risk warning method.
[0034] To achieve the above objectives, embodiments of the present invention also provide a computer program product, which is stored in a storage medium and executed by at least one processor to implement the steps of the above-described supply chain risk warning method.
[0035] Compared with existing technologies, the present invention discloses a supply chain risk early warning method, apparatus, equipment, medium, and product. When a financial risk event is detected, the method identifies the target enterprise involved in the financial risk event; determines the target supply chain to which the target enterprise belongs based on the upstream and downstream order relationships, investment relationships, and service interaction relationships of the target enterprise; performs risk analysis on the target supply chain based on the financial risk event; and provides risk early warning for the target supply chain based on the risk analysis results. This method can determine the target supply chain involved in a financial risk event based on the financial risk event and the upstream and downstream order relationships, investment relationships, and service interaction relationships of the target enterprise, and analyze the impact of the financial risk event on the target supply chain, thereby performing risk analysis and early warning for the supply chain to improve its stability. Attached Figure Description
[0036] Figure 1 This is a flowchart illustrating a supply chain risk early warning method provided in an embodiment of the present invention;
[0037] Figure 2 This is a schematic diagram of the structure of a supply chain risk early warning device provided in an embodiment of the present invention;
[0038] Figure 3 This is a structural block diagram of a supply chain risk early warning device provided in an embodiment of the present invention. Detailed Implementation
[0039] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0040] It should be noted that the terms "comprising" and "specific" in this invention, and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such process, method, product, or device.
[0041] Please see Figure 1 , Figure 1 This is a flowchart illustrating a supply chain risk early warning method provided in an embodiment of the present invention. The supply chain risk early warning method includes:
[0042] S1, When a financial risk event is detected, the target enterprise involved in the financial risk event is determined based on the financial risk event;
[0043] S2, determine the target industry chain to which the target enterprise belongs based on the upstream and downstream order relationships, investment relationships, and service interaction relationships of the target enterprise;
[0044] S3, conduct risk analysis on the target industrial chain based on the financial risk event;
[0045] S4, Based on the risk analysis results, issue a risk warning for the target industrial chain.
[0046] For example, the supply chain risk early warning method described in this embodiment of the invention is implemented by a supply chain risk early warning server, which is capable of information interaction with target users. When the supply chain risk early warning server detects a financial risk event through a text recognition model, it determines the target enterprise involved in the financial risk event based on keywords in the financial risk event (such as company name, legal person name, pledged shareholders, and share capital information); it determines the target supply chain to which the target enterprise belongs based on the upstream and downstream order relationships, investment relationships, and service interaction relationships of the target enterprise; it performs risk analysis on the target supply chain based on the financial risk event; and it issues a risk warning for the target supply chain based on the risk analysis results. This method can determine the target supply chain involved in a financial risk event based on the financial risk event and the upstream and downstream order relationships, investment relationships, and service interaction relationships of the target enterprise, and analyze the impact of the financial risk event on the target supply chain, thereby performing risk analysis and early warning for the supply chain to improve its stability.
[0047] Specifically, step S1 includes:
[0048] S11, When a financial risk event is detected, obtain the event trigger words and key arguments of the financial risk event;
[0049] S12, determine the target enterprise involved in the financial risk event based on the event trigger words and event key arguments.
[0050] Understandably, before detecting a financial risk event, it's necessary to define it and categorize its types. For example, events that negatively impact stock prices are called financial risk events. The trigger words for a risk event are the core words that best represent its meaning; these are generally nouns, verbs, or verb-noun phrases. Key arguments are the relevant elements constituting a financial risk event; and the role of risk event arguments refers to their corresponding roles within the sentence describing the financial risk event. Financial risk events can be detected from listing announcements using a pre-trained text recognition model.
[0051] For example, the occurrence of financial risk events can be detected using a pre-built key event sentence recognition model. The specific construction process of the key event sentence recognition model is as follows: event type information is considered in the encoding stage, making full use of the relationship between event type and sentence, and then fully connected layers (FC) are used to classify the sentences.
[0052] (1) Data preprocessing: When the key event sentence recognition model is trained on very long sentences, its adaptability is poor. In actual training, if the longest sentence is padded (in natural language processing, padding is a common data preprocessing technique used to process input sequences of different lengths to make them have a uniform length so that they can be input into the neural network in batches for training or inference), it will waste computing resources and cause the training speed to drop rapidly. Therefore, the maximum sentence length can be set to 256 characters.
[0053] (2) Input layer: The input is organized according to the input format required by BERT (Bidirectional Encoder Representations from Transformers, pre-trained language model), mainly including three parts: character embedding, which uses the dictionary provided by the FinBERT (financial pre-trained language model developed based on BERT architecture) pre-trained model as the embedding. The dictionary has more than 20,000 characters. If a character in the sentence is not in the dictionary, it is marked with "UNK (chromatographic analysis)"; position embedding uses a maximum of 256 characters to label the data. Considering that the event type has a certain indicative meaning for whether the sentence contains trigger words, such as the title and name of the entity in the personnel change event, while the pledge event focuses on the pledged shareholder and pledge quantity information, in order to make full use of the relationship between the event type and the sentence, the event type and the event description are concatenated into a sequence. A represents the event type for embedding, and B represents the event sequence, which serves as the common input of the FinBERT layer.
[0054] (3) BERT encoding layer: This layer contains two bidirectional Transformer layers, which are used to extract features related to the input layer. After the FinBERT pre-trained network, each character in the input sequence is encoded into a 768-dimensional vector output.
[0055] (4) Prediction Layer: The fully connected layer acts as a classifier in the entire neural network, mapping the hidden layer feature information to the sample label space. Whether a sentence is a key sentence is a binary classification problem, and the binary classification cross-entropy loss function is used, which is defined as follows:
[0056]
[0057] Among them, H P (q) represents the loss value, measuring the difference between the predicted distribution P and the true label distribution q; N is the sample size, representing the number of sentences in the batch input; y i p(y) represents the true label of the i-th sample, indicating a binary classification of 0 or 1, such as "1" for a key event sentence and "0" for a non-key event sentence; i The key event sentence recognition model predicts the i-th sample as a positive example (y). i The probability of (=1).
[0058] After identifying key event sentences, it is necessary to extract event arguments from the sentences. Event argument extraction can be viewed as a sequence labeling problem. The FinBERT Chinese language pre-trained model is used to encode the input text, and then a BiLSTM (Bidirectional Long Short-Term Memory) model is used to obtain the contextual information in the sentences. Conditional Random Field (CRF) is used to complete the sequence labeling. The specific construction process of the event argument extraction model is as follows:
[0059] (1) Data preprocessing: Event arguments may be distributed in multiple sentences in an article, and an article may have multiple event sentences; event sentences that are too short are concise but lack contextual information; event sentences that are too long have poor model adaptability. Therefore, a threshold of 256 was set according to the total sentence length, short event sentences were concatenated, and long event sentences were split.
[0060] (2) BERT layer: In order to utilize more mutual information between event types and sentences, the input layer adopts the same method as key event sentence recognition, concatenating the event type and sentence before inputting them into the BERT layer, as defined below:
[0061] xb1,xb2,…,xb n =BERT(x1,x2,…,x m ;e m+1 ,e m+2 ,…,e n ),
[0062] Where x1, x2, ..., x m This represents the input of sentence characters, with a total of m sentence characters; e m+1 ,e m+2 ,…,e n This represents the input of event type characters, with a total of nm event type characters; xb1, xb2, ..., xb n This represents the dense vector representation after BERT pre-training; n is the total length of the input sequence.
[0063] (3) BiLSTM Layer: The input of BiLSTM consists of two parts: the output of the BERT network pre-trained and the relative position vector of the trigger word. Generally, event arguments appear near the trigger word, so the position information of the trigger word has a certain indicative significance for the event arguments, but BERT has difficulty obtaining this information. The construction of the BERT model is divided into two stages: the first stage uses the language model for pre-training, and the second stage performs fine-tuning for a specific task. In the pre-training stage, the input vector is processed by the left and right bidirectional Transformer encoding layers to extract features and obtain the corresponding output vector. Referring to the position information of the Transformer, the relative trigger word position vector is designed as the input, defined as follows:
[0064]
[0065] x1,x2,…,x n =concat(xb1,xb2,…,xb) n ;pe1,pe2,…,pe n ),
[0066] Where abs(pos-pos) trigger The ) represents the relative position of the current character and the trigger word, and pos represents the absolute position of the current character in the sequence. trigger The position of the trigger word; i is the dimension index; d represents the dimension of the vector; {x1,x2,…,x n} represents the {xb1,xb2,…,xb} pre-trained with BERT. n} Concatenate the relative trigger word position vectors {pe1,pe2,…,pe n}, which serves as the input to the BiLSTM.
[0067] (4) CRF Layer: CRF incorporates constraints on the labels (e.g., the first label of a sequence should begin with 'B', and neither of the two labels of a vector should begin with 'B'). These constraints can be learned through the CRF layer. This ensures the effectiveness of the label sequence, thereby achieving a globally optimal sequence labeling. For a target label sequence {y1, y2, ..., y...} n Its score is expressed as The target sequence label is obtained by solving the maximum likelihood estimation in the form of the input X and the labeled sequence y; where Score(X,y) represents the score calculated for the input X and the labeled sequence y, which is used to measure the degree of matching between the labeled sequence y and the input X. The higher the score, the better the match usually is. The output of BiLSTM indicates that the i-th character is labeled as tag y. iThe probability; A is the transition matrix, Indicates label y i Transfer to y i+1 The probability of; Determined by the output of the BiLSTM model. It is determined by the transfer path.
[0068] (5) Output layer: The exchange discloses information according to the listed companies. Based on the semi-structured information disclosed by the listed companies corresponding to the announcement, a pre-set securities knowledge base can be constructed, including information on the company's senior executives, the top ten shareholders, and the company's share capital.
[0069] More specifically, step S12 includes:
[0070] S121, Match relevant companies based on the key arguments of the event and the preset securities knowledge base;
[0071] S122, if there are multiple related companies, the related companies are verified according to the event trigger word, and the verified related companies are taken as the target companies involved in the financial risk event.
[0072] Specifically, step S2 includes:
[0073] S21, Obtain the association information of the target enterprise, and determine the upstream and downstream enterprises that are associated with the target enterprise based on the association information;
[0074] S22, Based on the upstream and downstream enterprises, determine the upstream and downstream order relationships, investment relationships, and service interaction relationships of the target enterprise;
[0075] S23. Based on the upstream and downstream order relationships, investment relationships, and service interaction relationships, determine the target industrial chain to which the target enterprise belongs.
[0076] For example, to identify the supply chain of a ramen restaurant, the ramen restaurant can be considered a business. A business can be a consumer-facing enterprise, such as a ramen restaurant or a crayfish restaurant; or it can be a business-facing enterprise, such as a processing plant or a wholesaler. The related information of a business reflects the relationships between the target business and its related businesses.
[0077] In one example, a semantic network can be pre-built based on objective facts, allowing for the acquisition of relevant information about a company. A semantic network is a structured way of representing knowledge using graphs. In a semantic network, information is expressed as a set of nodes connected by a set of labeled directed lines, representing the relationships between nodes. In this example, the relationships between nodes are semantic; for example, company A is an upstream company of company B, and food C is a product of company D. In the above example, the semantic network is derived from factual information in the objective world. For instance, a semantic network can be obtained through extensive text parsing. Based on a company's publicly available text information online, we can determine if the company has a factory, whether its main products are seasonings, etc. Using this information, a semantic network related to the company can be constructed. For example, assuming the company's business model is a processing plant and its products are seasonings, the parsed semantic network would be: the relationship between the node "company" and the node "processing plant" is "business model"; the relationship between the node "company" and the node "seasonings" is "production". In this example, based on the semantic network and from an objective and realistic perspective, relevant information about the company is acquired, thus more accurately identifying the company's supply chain. Furthermore, since the relationships between nodes in a semantic network possess semantic meaning, the identified industry chain relationships also possess semantic information.
[0078] Taking the catering industry as an example, let's consider a ramen restaurant as the enterprise to be identified. We can collect the ramen restaurant's financial transaction information, such as from a payment platform. Based on this information, we can identify the enterprises that have financial dealings with the ramen restaurant and designate them as affiliated enterprises. For example, if the transaction information indicates that the counterparty to the ramen restaurant's financial transactions is a flour processing plant, then the flour processing plant can be identified as an affiliated enterprise. Alternatively, we can collect the ramen restaurant's contact information, such as the owner's or employees' contact information. From this contact information, we can identify other enterprises connected to the ramen restaurant and designate them as affiliated enterprises. For example, if the ramen restaurant owner has a flour processing plant's phone number stored in their contact list with the note "flour purchase phone number," then the flour processing plant can be identified as an affiliated enterprise. Alternatively, we can identify enterprises with equity relationships with the ramen restaurant and designate them as affiliated enterprises. For example, if the ramen restaurant is an investor in a flour processing plant, then the flour processing plant can be identified as an affiliated company of the ramen restaurant. Alternatively, affiliated companies can be identified based on the legal entity of the ramen restaurant. For instance, another company with the same legal entity as the ramen restaurant can be identified as an affiliated company. The above describes how to identify affiliated companies of a company by using a ramen restaurant in the catering industry as the company to be identified. It should be understood that the above is merely an illustrative explanation. When companies in other industries are used as the company to be identified, there are many other specific ways to identify affiliated companies, and this embodiment does not impose any limitations.
[0079] Specifically, the steps for determining upstream and downstream order relationships are as follows: Classify fund transaction information, mainly into fund inflows and fund outflows. When a company's fund transaction information shows fund inflows, it is a supplier in the upstream and downstream order relationship. When a company's fund transaction information shows fund outflows, it is a buyer in the upstream and downstream order relationship. Determine the investment relationship between related companies and the company. Investment relationships include investors and investees. Query the equity relationships in the company's related information to obtain the investment relationships for that company; the equity relationships are divided into investors and investees. When a company's equity relationship is an investor, its investor relationship is that of an investor. When a company's equity relationship is that of an investee, its investor relationship is that of an investee. Determine the service interaction relationship (service relationship) between related companies and the company. The service interaction relationship (service relationship) involves the provision and enjoyment of consumer services. Service interaction relationships are classified as suppliers and buyers. When a company is a provider of consumer services, its service interaction relationship is that of a supplier. When a company is a consumer of consumer services, its service interaction relationship is that of a buyer. The industrial chain described by the enterprise is determined by upstream and downstream order relationships, investment relationships, and service interaction relationships.
[0080] Specifically, step S3 includes:
[0081] S31, Determine the risk management type of the target industry chain;
[0082] S32, Perform risk analysis on the target industrial chain based on the financial risk event and the risk management type.
[0083] For example, if we consider risk warning as a machine reading comprehension task, the risk warning process for the upstream and downstream of a company's industrial chain after a risk event is predicted is as follows:
[0084] (1) Input layer: Different question and answer templates are designed for different types of risk events and different supply chain relationships; for example, the performance reduction event and the supplier relationship in the supply chain are both used as common inputs into the FinBERT network structure and separated by the "[SEP]" separator.
[0085] (2) BERT Encoding Layer: To utilize more relationships between questions and events, questions and events are concatenated and then input into the BERT layer. For example:
[0086] xb1,xb2,…,xb n =BERT(e1,e2,…,e m ;q m+1 ,q m+2 ,…,q n ),
[0087] Among them, e1, e2, ..., e m This indicates the input of event type characters, with a total of m event type characters; q m+1 ,q m+2 ,…,q n The input represents the answer characters, and there are a total of nm answer characters; xb1, xb2, ..., xb n This represents the dense vector representation after finBERT pre-training; n is the total length of the input sequence.
[0088] (3) Output layer: After passing through a fully connected layer and a softmax function, the output is the probability y of different types of answers. i ,
[0089] y i =Softmax(W*x+b) i ),
[0090] Where W is the weight matrix of the fully connected layer, b i Let x represent the bias matrix corresponding to the i-th type of answer. The loss function is the binary classification cross-entropy loss function, and x is the input of the fully connected layer.
[0091] More specifically, step S32 includes:
[0092] S321, If the target industrial chain is capital-driven, conduct risk analysis on the financing data of the target industrial chain based on the financial risk event;
[0093] S322, If the target industrial chain is technology-innovative, conduct risk analysis on the patent technology data of the target industrial chain based on the financial risk event;
[0094] S323, If the target industrial chain is labor-intensive, conduct risk analysis on the worker data of the target industrial chain based on the financial risk event.
[0095] In a specific implementation, forecasting the impact on the supply chain can include the following: ① Supply disruptions: Risk events may prevent suppliers from providing necessary raw materials or components on time, affecting production and delivery. ② Cost fluctuations: Fluctuations in raw material prices or increases in supply chain costs may affect a company's profit margin. ③ Demand changes: Risk events may alter consumer demand, leading to fluctuations in the sales volume of products or services. ④ Changes in the competitive landscape: Strategic changes by new entrants or existing competitors may affect a company's market position. ⑤ Environmental and social impacts: Risk events in the supply chain may have negative environmental and social impacts, such as pollution and labor issues. ⑥ Human resource impacts: Labor shortages, strikes, or other human resource problems may affect the stability of the supply chain.
[0096] This invention discloses a supply chain risk early warning method. When a financial risk event is detected, the method identifies the target enterprise involved in the financial risk event; determines the target supply chain to which the target enterprise belongs based on its upstream and downstream order relationships, investment relationships, and service interaction relationships; performs risk analysis on the target supply chain based on the financial risk event; and issues a risk warning for the target supply chain based on the risk analysis results. This method can determine the target supply chain involved in a financial risk event based on the financial risk event and the target enterprise's upstream and downstream order relationships, investment relationships, and service interaction relationships, and analyze the impact of the financial risk event on the target supply chain, thereby conducting risk analysis and early warning for the supply chain to improve its stability.
[0097] See Figure 2 , Figure 2 This is a schematic diagram of the structure of a supply chain risk early warning device 10 provided in an embodiment of the present invention. The supply chain risk early warning device 10 includes:
[0098] The target enterprise determination module 11 is used to determine the target enterprise involved in the financial risk event based on the financial risk event when a financial risk event is detected.
[0099] The target industry determination module 12 is used to determine the target industry chain to which the target enterprise belongs based on the upstream and downstream order relationships, investment relationships, and service interaction relationships of the target enterprise;
[0100] Industry risk analysis module 13 is used to perform risk analysis on the target industrial chain based on the financial risk event;
[0101] The industry risk early warning module 14 is used to provide risk warnings for the target industry chain based on the risk analysis results.
[0102] The supply chain risk warning device 10 provided in this embodiment of the invention can realize all the processes of the supply chain risk warning method of the above embodiments. The functions and technical effects of each module in the device are the same as the functions and technical effects of the supply chain risk warning method of the above embodiments, and will not be repeated here.
[0103] See Figure 3 , Figure 3This is a schematic diagram of the structure of a supply chain risk early warning device 20 provided in an embodiment of the present invention. The supply chain risk early warning device 20 of this embodiment includes: a processor 21, a memory 22, and a computer program stored in the memory 22 and executable on the processor 21. When the processor 21 executes the computer program, it implements the steps in the above-described supply chain risk early warning method embodiment. Alternatively, when the processor 21 executes the computer program, it implements the functions of each module in the above-described supply chain risk early warning device embodiment.
[0104] For example, the computer program can be divided into one or more modules, which are stored in the memory 22 and executed by the processor 21 to complete the present invention. The one or more modules can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the supply chain risk warning device 20.
[0105] The supply chain risk warning device 20 can be a computing device such as a desktop computer, laptop, handheld computer, or cloud server. The supply chain risk warning device 20 may include, but is not limited to, a processor 21 and a memory 22. Those skilled in the art will understand that the schematic diagram is merely an example of the supply chain risk warning device 20 and does not constitute a limitation on the supply chain risk warning device 20. It may include more or fewer components than shown in the diagram, or combine certain components, or use different components. For example, the supply chain risk warning device 20 may also include input / output devices, network access devices, buses, etc.
[0106] The processor 21 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor 21 is the control center of the supply chain risk warning device 20, connecting all parts of the supply chain risk warning device 20 via various interfaces and lines.
[0107] The memory 22 can be used to store the computer programs and / or modules. The processor 21 implements various functions of the supply chain risk warning device 20 by running or executing the computer programs and / or modules stored in the memory 22 and calling the data stored in the memory 22. The memory 22 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory 22 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital card (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.
[0108] If the integrated module of the supply chain risk warning device 20 is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by the processor 21, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content contained in the computer-readable medium may be appropriately added to or subtracted from the content as required by the legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium may not include electrical carrier signals and telecommunication signals.
[0109] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.
[0110] This invention also provides a computer-readable storage medium, which includes a stored computer program, wherein the computer program, when running, controls the device where the computer-readable storage medium is located to execute the supply chain risk warning method as described in the above embodiments.
[0111] Furthermore, embodiments of the present invention also provide a computer program product, which is stored in a storage medium and executed by at least one processor to implement the steps of the supply chain risk warning method described in the above embodiments.
[0112] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.
Claims
1. A method for early warning of supply chain risks, characterized in that, include: When a financial risk event is detected, the target enterprise involved in the financial risk event is determined based on the financial risk event; Based on the upstream and downstream order relationships, investment relationships, and service interaction relationships of the target enterprise, the target industry chain to which the target enterprise belongs is determined; Based on the aforementioned financial risk events, conduct risk analysis on the target industrial chain; Risk warnings are issued for the target industrial chain based on the risk analysis results.
2. The supply chain risk early warning method as described in claim 1, characterized in that, When a financial risk event is detected, determining the target enterprise involved in the financial risk event based on the financial risk event includes: When a financial risk event is detected, the event trigger words and key arguments of the financial risk event are obtained; The target companies involved in the financial risk event are determined based on the event trigger words and key event arguments.
3. The supply chain risk early warning method as described in claim 2, characterized in that, The process of determining the target companies involved in the financial risk event based on the event trigger words and key event arguments includes: Match relevant companies based on the key arguments of the event and a pre-set securities knowledge base; If there are multiple related companies, the related companies are verified according to the event trigger words, and the verified related companies are the target companies involved in the financial risk event.
4. The supply chain risk early warning method as described in claim 1, characterized in that, The step of determining the target industry chain to which the target enterprise belongs based on its upstream and downstream order relationships, investment relationships, and service interaction relationships includes: Obtain the association information of the target company, and determine the upstream and downstream companies that are associated with the target company based on the association information; Based on the upstream and downstream enterprises, determine the upstream and downstream order relationships, investment relationships, and service interaction relationships of the target enterprise; Based on the upstream and downstream order relationships, investment relationships, and service interaction relationships, the target industry chain to which the target enterprise belongs is determined.
5. The supply chain risk early warning method as described in claim 1, characterized in that, The risk analysis of the target industrial chain based on the financial risk event includes: Determine the risk management type for the target industry chain; Risk analysis is conducted on the target industrial chain based on the financial risk events and the risk management type.
6. The supply chain risk early warning method as described in claim 5, characterized in that, The risk analysis of the target industrial chain based on the financial risk event and the risk management type includes: If the target industry chain is capital-driven, risk analysis is performed on the financing data of the target industry chain based on the financial risk event. If the target industry chain is technology-innovative, risk analysis is performed on the patent technology data of the target industry chain based on the financial risk event; If the target industrial chain is labor-intensive, risk analysis is performed on the worker data of the target industrial chain based on the financial risk event.
7. A supply chain risk early warning device, characterized in that, include: The target enterprise determination module is used to determine the target enterprise involved in the financial risk event based on the financial risk event when a financial risk event is detected. The target industry determination module is used to determine the target industry chain to which the target enterprise belongs based on the upstream and downstream order relationships, investment relationships, and service interaction relationships of the target enterprise; The industry risk analysis module is used to conduct risk analysis on the target industry chain based on the financial risk event. The industry risk early warning module is used to provide risk warnings for the target industry chain based on the risk analysis results.
8. A supply chain risk early warning device, characterized in that, The system includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the supply chain risk warning method as described in any one of claims 1-6.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the supply chain risk early warning method as described in any one of claims 1-6.
10. A computer program product, characterized in that, The computer program product is stored in a storage medium, and the program product is executed by at least one processor to implement the steps of the supply chain risk warning method as described in any one of claims 1-6.