Transaction risk control analysis method and device based on supply chain financial log and medium

Abstract

The invention relates to the technical field of supply chains, and discloses a supply chain financial log-based transaction risk control analysis method and device and a medium, and the method comprises the steps: collecting a business log corresponding to each transaction link in a supply chain financial transaction business in real time, and extracting a business keyword in the business log corresponding to each transaction link; screening business exception keywords in the business keywords according to risk control exception rules, and calculating the similarity between the business exception keywords in each transaction link; classifying the business exception keywords screened out in each transaction link according to the similarity; determining the business risk control level of each transaction link according to the number of business abnormal keywords in the transaction risk control keyword set, and determining the overall business risk control level of the supply chain financial transaction business through the business risk control level of each transaction link; and determining the business transaction risk of the supply chain financial transaction business according to the overall business risk control level. The accuracy of transaction risk control analysis can be improved.

Description

Technical Field

[0001] The present invention relates to the field of supply chain technology, and in particular to a transaction risk control analysis method, device and medium based on supply chain financial logs. Background Art

[0002] With the rapid development of supply chain finance, many companies' applications in the transaction process will generate a large amount of log data, recording various activities, transactions and events. However, there will be transaction risks in the transaction process. In order to reduce the business risks in the transaction process, it is necessary to conduct real-time risk control analysis of the business transaction process to improve the security of the business transaction process.

[0003] Existing transaction risk control analysis technology evaluates the risk level of each transaction based on historical data and real-time data. In practical applications, the accuracy of risk level assessment depends on the quality of historical data and real-time data. If the data is incomplete, inaccurate or erroneous, the risk control analysis results may be distorted, resulting in low accuracy in transaction risk control analysis. Summary of the invention

[0004] The present invention provides a transaction risk control analysis method, device and medium based on supply chain finance logs, the main purpose of which is to solve the problem of low accuracy when performing transaction risk control analysis.

[0005] To achieve the above purpose, the present invention provides a transaction risk control analysis method based on supply chain finance logs, comprising:

[0006] Collect the business logs corresponding to each transaction link in the supply chain financial transaction business in real time, and extract the business keywords in the business logs corresponding to each transaction link;

[0007] Filtering business abnormality keywords among the business keywords according to the pre-generated risk control abnormality rules, and calculating the similarity between the business abnormality keywords in each transaction link;

[0008] Classify the business abnormality keywords screened out in each transaction link according to the similarity to obtain a transaction risk control keyword set corresponding to each transaction link;

[0009] Determine the business risk control level of each transaction link according to the number of business abnormality keywords in the transaction risk control keyword set, and determine the overall business risk control level of the supply chain financial transaction business through the business risk control level of each transaction link;

[0010] The business transaction risk of the supply chain financial transaction business is determined based on the overall business risk control level.

[0011] Optionally, extracting business keywords from the business log corresponding to each transaction link includes:

[0012] Generate a regular matching expression for the keyword according to the form of each keyword in the keyword list corresponding to each transaction link;

[0013] Perform word segmentation on the log data in the business log corresponding to each transaction link;

[0014] Generate a segmentation sequence from the log data after segmentation processing;

[0015] Using the regular matching expression, the segmented words in the segmented word sequence are matched with the keywords in the keyword list one by one;

[0016] The successfully matched segmented words are used as business keywords in the business log.

[0017] Optionally, screening the business abnormality keywords in the business keywords according to the pre-generated risk control abnormality rules includes:

[0018] Extract the abnormal transaction logic of each transaction link according to the pre-generated risk control abnormal rules, and extract the abnormal transaction keywords corresponding to the abnormal transaction logic;

[0019] Comparing the business keywords with the abnormal transaction keywords one by one;

[0020] When all characters are compared to be the same, the business keyword is used as a business abnormality keyword.

[0021] Optionally, the calculating the similarity between the business abnormality keywords in each transaction link includes:

[0022] Convert the business abnormality keywords in each transaction link into vectors one by one to obtain the business abnormality keyword vector;

[0023] Combine all business abnormality keyword vectors in each transaction link to obtain a business abnormality keyword vector combination sequence;

[0024] The similarity between the business abnormality keywords in each business abnormality keyword vector combination sequence is calculated using a preset similarity algorithm.

[0025] Optionally, the business abnormality keywords screened out in each transaction link are classified according to the similarity to obtain a transaction risk control keyword set corresponding to each transaction link, including:

[0026] Extract the similarity between the business abnormality keywords in all business abnormality keyword vector combination sequences in each transaction link;

[0027] Selecting the business abnormality keyword in the business abnormality keyword vector combination sequence as the abnormal associated word combination according to the similarity and a preset similarity threshold;

[0028] Performing semantic analysis on the business abnormality keywords in the abnormal associated word combination;

[0029] When the semantic contents corresponding to the business abnormality keywords after semantic analysis are similar, the business abnormality keywords are classified as transaction risk control keywords for each transaction link;

[0030] All transaction risk control keywords are collected into a transaction risk control keyword set corresponding to each transaction link.

[0031] Optionally, determining the business risk control level of each transaction link according to the number of business abnormality keywords in the transaction risk control keyword set includes:

[0032] When the number of business abnormality keywords in the transaction risk control keyword set of each transaction link is less than or equal to a preset first number threshold, the business risk control level of the transaction link is determined as a low risk control level;

[0033] When the number of business abnormality keywords in the transaction risk control keyword set of each transaction link is greater than a preset first number threshold and less than or equal to a preset second number threshold, the business risk control level of the transaction link is determined as an intermediate risk control level;

[0034] When the number of business abnormality keywords in the transaction risk control keyword set of each transaction link is greater than a preset second number threshold, the business risk control level of the transaction link is determined as an advanced risk control level.

[0035] Optionally, determining the overall business risk control level of the supply chain financial transaction business through the business risk control level of each transaction link includes:

[0036] Generate a risk control level sequence based on the business risk control levels of all transaction links;

[0037] When the risk control levels in the risk control level sequence are all low risk control levels, the overall business risk control level of the supply chain financial transaction business is set to a low risk control level;

[0038] When any risk control level in the risk control level sequence is at the intermediate risk control level and there is no advanced risk control level, the overall business risk control level of the supply chain financial transaction business is set at the intermediate risk control level;

[0039] When any risk control level in the risk control level sequence is at the advanced risk control level, the overall business risk control level of the supply chain financial transaction business will be set to the advanced risk control level.

[0040] Optionally, determining the business transaction risk of the supply chain financial transaction business according to the overall business risk control level includes:

[0041] Calculate the business transaction score of the supply chain financial transaction business according to the overall business risk control level;

[0042] Extracting a business transaction weight of the supply chain finance transaction business, and calculating a business risk score of the supply chain finance transaction business based on the business transaction weight and the business transaction score;

[0043] The business transaction risk of the supply chain finance transaction business is determined based on the business risk score.

[0044] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0045] at least one processor; and,

[0046] a memory communicatively connected to the at least one processor; wherein,

[0047] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the above-mentioned transaction risk control analysis method based on supply chain finance logs.

[0048] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one computer program is stored. The at least one computer program is executed by a processor in an electronic device to implement the above-mentioned transaction risk control analysis method based on supply chain financial logs.

[0049] The embodiments of the present invention can ensure timely acquisition of the latest business information by real-time collection of business logs, and extract keywords to convert a large amount of log data into analyzable structured information, providing basic data for subsequent risk control analysis; through pre-defined risk control rules, keywords that may be abnormal can be quickly and automatically screened out, reducing the need for manual intervention; calculating the similarity between keywords can help discover the connection between different keywords and improve the accuracy of risk control; classifying abnormal keywords can better understand the risk types in the business; forming a risk control keyword set can comprehensively integrate the risk information of each link; through the determination of the business risk control level, the risks of different links can be quantified and classified, and corresponding risk control strategies can be taken in a targeted manner, and then the overall risk can be evaluated to fully understand the risk level of supply chain financial transaction business. Therefore, the transaction risk control analysis method, device and medium based on supply chain financial logs proposed by the present invention can solve the problem of low accuracy when conducting transaction risk control analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A schematic diagram of a process flow of a transaction risk control analysis method based on supply chain finance logs provided by an embodiment of the present invention;

[0051] Figure 2 A schematic diagram of a process for extracting abnormal transaction keywords provided by an embodiment of the present invention;

[0052] Figure 3 A schematic diagram of a process for determining a business risk control level according to an embodiment of the present invention;

[0053] Figure 4 A schematic diagram of the structure of an electronic device for implementing the transaction risk control analysis method based on supply chain finance logs provided in one embodiment of the present invention.

[0054] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0055] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0056] The embodiment of the present application provides a transaction risk control analysis method based on supply chain finance logs. The execution subject of the transaction risk control analysis method based on the supply chain finance log includes but is not limited to at least one of the electronic devices such as the server, the terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the transaction risk control analysis method based on the supply chain finance log can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms.

[0057] Reference Figure 1 FIG. 1 is a flow chart of a transaction risk control analysis method based on supply chain finance logs provided by an embodiment of the present invention. In this embodiment, the transaction risk control analysis method based on supply chain finance logs includes:

[0058] S1. Collect the business logs corresponding to each transaction link in the supply chain financial transaction business in real time, and extract the business keywords in the business logs corresponding to each transaction link.

[0059] In an embodiment of the present invention, the business log is a file that records important events and information in the financial transaction business process. It is a way to persistently record financial transaction business activities and is used to track system operation, troubleshoot, performance analysis and security auditing. The business log can contain various types of information, such as user operation records, system error information, warning information, performance indicators, etc.

[0060] In detail, in the supply chain finance transaction business, each transaction link refers to a different stage or link involving the flow of goods or funds, covering the entire supply chain finance transaction process, including order generation, payment processing, logistics distribution, and after-sales service. Order generation refers to the process of customers placing orders to purchase goods or services, including order information entry, confirmation and generation; payment processing refers to the process of customers making payments and completing fund settlement, including different payment methods, such as online payment, credit card payment, transfer, etc., as well as settlement procedures with financial institutions; logistics distribution involves the entire process of shipping paid orders from suppliers to the customer's designated location, including logistics transportation, warehousing management, transportation tracking, etc.; after-sales service refers to the service after the customer receives the goods, including returns and refunds, quality issue handling, customer complaint handling, etc.

[0061] Specifically, the business logs corresponding to each transaction link in the supply chain financial transaction business can be collected in real time from a pre-stored storage area through computer statements with data capture functions (such as Java statements, Python statements, etc.), where the storage area includes but is not limited to databases and blockchains.

[0062] Furthermore, in order to promptly identify problems and abnormal situations in each transaction link, it is necessary to extract keywords from the business logs corresponding to each transaction link, so as to quickly locate which transaction link the problem occurs in and understand the operation status of each transaction link.

[0063] In an embodiment of the present invention, the business keywords refer to the corresponding keywords in each transaction link, which are used to describe, identify or distinguish a certain business activity, process or status. For example, business keywords include order status (such as order, shipment, receipt), payment method (Alipay, credit card, bank transfer), etc.

[0064] In the embodiment of the present invention, the extracting of business keywords from the business log corresponding to each transaction link includes:

[0065] Generate a regular matching expression for the keyword according to the form of each keyword in the keyword list corresponding to each transaction link;

[0066] Perform word segmentation on the log data in the business log corresponding to each transaction link;

[0067] Generate a segmentation sequence from the log data after segmentation processing;

[0068] Using the regular matching expression, the segmented words in the segmented word sequence are matched with the keywords in the keyword list one by one;

[0069] The successfully matched segmented words are used as business keywords in the business log.

[0070] In detail, a corresponding keyword list is established for each transaction link, such as the order generation associated word list is ordering, shipping, receipt, order loss, order cancellation, order duplication, order timeout, and order status abnormality; the payment processing keyword list is "Alipay", credit card, bank transfer, transaction failure, duplicate transaction, abnormal transaction amount, transaction timeout, transaction rejection, and transaction abnormality; the logistics distribution keyword list is transportation, warehousing, distribution, logistics delay, logistics loss, logistics damage, and logistics abnormality; the after-sales service keyword list is return, repair, refund, complaint, product quality, and information error, and then a regular expression is generated according to the keywords in each keyword list. For example, in Python, the re library can be used for regular expression matching, such as "keywords = ["order lost", "order cancellation", "order duplication", "order timeout", "order status abnormal"], pattern = r"\b"+r"\b|\b".join(keywords)+r"\b".

[0071] Specifically, the business log data corresponding to each transaction link is segmented. The Chinese segmentation tool jieba can be used for segmentation, and the segmented log data after segmentation is used to generate a segmentation sequence, that is, each log is split into individual segments, and the pre-generated regular expressions are used to match the segmented words in the segmentation sequence with the keywords in the keyword list one by one to find the successfully matched keywords, such as import re, text = "Order timeout detected, please handle it in time;" keywords = ["Order lost", "Order canceled", "Order duplicated", "Order timeout", "Order status abnormal"], pattern = r"\b"+r"\b|\b".join(keywords)+r"\b", matches = re.findall(pattern, text), if matches: print("Matched keywords found:", matches), else: print("No matching keywords found").

[0072] Furthermore, it is possible to identify whether there are abnormal keywords among all the business keywords corresponding to each transaction link, so that business abnormalities can be monitored in real time based on the abnormal keywords. Based on the abnormal situations in each transaction link, the false alarm rate can be reduced and the accuracy of abnormality identification can be improved.

[0073] S2. Filter the business abnormality keywords among the business keywords according to the pre-generated risk control abnormality rules, and calculate the similarity between the business abnormality keywords in each transaction link.

[0074] In an embodiment of the present invention, the pre-generated risk control abnormality rules refer to a series of rules and standards defined in advance based on the needs and experience of business transaction risk management, which are conducive to monitoring and identifying situations where risks or abnormal behaviors may exist, such as abnormal transaction amounts, detecting whether there are abnormally high or abnormally low transaction amounts; abnormal transaction frequencies, detecting whether there are abnormally frequent transaction behaviors; abnormal geographic locations, detecting whether there are transaction behaviors that are inconsistent with the user's normal activity locations; unusual transaction patterns, detecting whether there are transaction patterns or behaviors that are different from the user's usual ones, and the business abnormality keywords refer to specific words or terms that may be associated with abnormal transactions in transaction business operations, such as order loss, order cancellation, transaction failure, repeated transactions, etc.

[0075] In the embodiment of the present invention, refer to Figure 2 As shown, the filtering of business abnormality keywords in the business keywords according to the pre-generated risk control abnormality rules includes:

[0076] S21. Extracting the abnormal transaction logic of each transaction link according to the pre-generated risk control abnormality rules, and extracting the abnormal transaction keywords corresponding to the abnormal transaction logic;

[0077] S22, comparing the business keywords with the abnormal transaction keywords one by one;

[0078] S23. When all characters are compared and found to be identical, the business keyword is used as a business abnormality keyword.

[0079] In detail, based on the risk control abnormality rules in each transaction link, there will be abnormal transaction logic. For example, the abnormal transaction logic in the order generation link is that the same user or account generates a large number of orders in a short period of time, which exceeds the normal order frequency; the amount of a single order is abnormally high or abnormally low, which is inconsistent with the user's historical order amount or average order amount; an order pattern or behavior that is different from the user's usual is detected, such as a sudden change in order type, quantity or frequency; the geographical location where the order is generated is inconsistent with the user's usual location, or the order generation device does not match the user's usual device; the abnormal transaction logic in the payment processing link is the use of abnormal payment methods or channels, or abnormal payment behaviors, such as unconventional bank transfers, virtual currency payments or payment on behalf of others; abnormal payment status, such as an abnormally high payment failure rate, payment timeout or repeated payment; a payment pattern or behavior that is different from the user's usual is detected, such as an unusual The payment process contains abnormal or unusual notes, instructions or additional information, which may indicate fraud or illegal activities. The abnormal transaction logic in the logistics and distribution link is that the order delivery address is inconsistent with the user's usual address, or the delivery address is located in a high-risk area, the delivery time is outside the user's usual receiving time, or the delivery time is frequently changed, the order delivery quantity is abnormally high or abnormally low, which is inconsistent with the user's historical order quantity or average order quantity, and abnormal conditions occur during the delivery process, such as delivery delays, lost goods or unidentified delivery personnel; the abnormal transaction logic in the after-sales service link is that the user frequently makes return and exchange requests, or the return and exchange requests are inconsistent with the user's purchase history, the refund amount is abnormally high or abnormally low, inconsistent with the order amount or product price, the quantity, quality or status of the returned goods are abnormal, and the after-sales service request made by the user does not conform to the normal process.

[0080] Specifically, according to the abnormal transaction logic, the abnormal transaction keywords are extracted, such as the order generation associated word list is order loss, order cancellation, order duplication, repeated order, order timeout, and abnormal order status; the payment processing keyword list is transaction failure, repeated transaction, abnormal transaction amount, payment timeout, payment time exceeded, and transaction rejected; the logistics distribution keyword list is logistics delay, delivery time exceeded, logistics loss, logistics damage, and logistics abnormal status; the after-sales service keyword list is customer refund application, customer complaint, product quality, and customer information error, and the extracted abnormal keywords are compared with the business keywords. For example, the abnormal keyword list is exception_keywords=delay","damage or loss","wrong delivery","rejection of goods","return and exchange","complaint handling","service quality problem","refund processing"}, and the business keyword list is business_keywords={"logistics distribution","delay","damage or loss","wrong delivery","rejection of goods","after-sales service","return and exchange","complaint handling","service quality problem","refund processing"}, then for keywordin business_keywords:if keyword in exception_keywords:print(f"Keyword '{keyword}' is in the abnormal transaction keyword list.")else:print(f"Keyword '{keyword}' is not in the abnormal transaction keyword list.") so that the successfully matched keywords are used as business abnormal keywords.

[0081] Furthermore, similar abnormal problems will exist in each transaction link, and the extracted abnormal keywords will also have similar situations. Therefore, similar abnormal situations occurring in the same transaction link can be identified to ensure that the abnormal situations are effectively handled and the processing efficiency is improved.

[0082] In the embodiment of the present invention, the similarity refers to the similarity between two business abnormality keywords in the same transaction link in a certain metric space.

[0083] In the embodiment of the present invention, the calculating of the similarity between the business abnormality keywords in each transaction link includes:

[0084] Convert the business abnormality keywords in each transaction link into vectors one by one to obtain the business abnormality keyword vector;

[0085] Combine all business abnormality keyword vectors in each transaction link to obtain a business abnormality keyword vector combination sequence;

[0086] The similarity between the business abnormality keywords in each business abnormality keyword vector combination sequence is calculated using a preset similarity algorithm.

[0087] In detail, for the business abnormality keywords in each transaction link, they need to be converted into vectors. Using the word embedding technology, each keyword is mapped to a representation in a high-dimensional vector space. Each keyword can be represented as a real number vector, in which each dimension represents a certain semantic feature. The vectors of all business abnormality keywords in each transaction link are combined to obtain a business abnormality keyword vector combination sequence. For example, if the business keyword vectors in the order generation link are A, B, C, D, then A, B, C, D are arranged and combined to obtain the business abnormality keyword vector combination sequence (A, B), (A, C), (A, D), (B, C), (B, D), ( C, D), and then calculate the similarity between each pair of business abnormality keywords in the business abnormality keyword vector combination sequence, that is, respectively calculate the similarity of each combination of (A, B), (A, C), (A, D), (B, C), (B, D), (C, D), wherein the similarity algorithm includes but is not limited to cosine similarity, Euclidean distance, and Jaccard similarity. According to the result of similarity calculation, the similarity between the business abnormality keywords in each transaction link can be explained, which is conducive to understanding the correlation and similarity between different keywords, thereby providing a basis for anomaly detection and problem location.

[0088] Furthermore, in order to more accurately identify the potential risks of each transaction link, abnormal keywords with similar characteristics are clustered together through similarity analysis to improve the speed of anomaly detection, which can better understand the risk characteristics and potential risk sources of different links.

[0089] S3. Classify the business abnormality keywords screened out in each transaction link according to the similarity to obtain a transaction risk control keyword set corresponding to each transaction link.

[0090] In an embodiment of the present invention, the transaction risk control keyword set refers to a group of keywords determined for the same transaction link, which is used to identify, monitor and control potential risks and abnormal situations. By establishing and continuously optimizing the transaction risk control keyword set, risk identification and control can be more effectively carried out, thereby improving the overall risk management level.

[0091] In the embodiment of the present invention, the business abnormality keywords screened out in each transaction link are classified according to the similarity to obtain a transaction risk control keyword set corresponding to each transaction link, including:

[0092] Extract the similarity between the business abnormality keywords in all business abnormality keyword vector combination sequences in each transaction link;

[0093] Selecting the business abnormality keyword in the business abnormality keyword vector combination sequence as the abnormal associated word combination according to the similarity and a preset similarity threshold;

[0094] Performing semantic analysis on the business abnormality keywords in the abnormal associated word combination;

[0095] When the semantic contents corresponding to the business abnormality keywords after semantic analysis are similar, the business abnormality keywords are classified as transaction risk control keywords for each transaction link;

[0096] All transaction risk control keywords are collected into a transaction risk control keyword set corresponding to each transaction link.

[0097] In detail, based on the calculated similarity between each business abnormality keyword vector combination sequence, the similarity is compared with a preset similarity threshold, and the business abnormality keyword vector combination with a similarity higher than the threshold is selected as the abnormal associated word combination, and those keyword combinations with low similarity and weak correlation are filtered out. The business abnormality keywords in the selected abnormal associated word combination are semantically analyzed. In the semantic analysis process, sometimes a keyword may have multiple different meanings. The exact meaning of the keyword in a specific context is determined by word sense disambiguation, that is, word sense disambiguation is achieved by combining context information, vocabulary resources (such as dictionaries, knowledge graphs, etc.) and grammatical rules to understand the actual meaning and context of the keyword. Then, when the semantic contents corresponding to the business abnormality keywords after semantic analysis are similar, they are classified as transaction risk control keywords for each transaction link, and the classified transaction risk control keywords are collected to form a transaction risk control keyword set corresponding to each transaction link.

[0098] Furthermore, in order to more accurately identify the potential risks of each transaction link, it is necessary to analyze the number of abnormal business keywords. If the number of abnormal business keywords in a certain link is large, it may mean that there are more potential risks in this link and more stringent control measures need to be taken.

[0099] S4. Determine the business risk control level of each transaction link according to the number of business abnormality keywords in the transaction risk control keyword set, and determine the overall business risk control level of the supply chain financial transaction business through the business risk control level of each transaction link.

[0100] In the embodiment of the present invention, the business risk control level refers to the risk control and management level adopted for a specific business link or transaction activity. By evaluating the risk situation of each transaction link, it can be divided into different risk control levels so as to take corresponding monitoring, control and management measures. The higher the business risk control level, the greater the risk faced by the transaction link, and the more stringent monitoring and management measures need to be taken.

[0101] In the embodiment of the present invention, refer to Figure 3 As shown, the business risk control level of each transaction link is determined according to the number of business abnormality keywords in the transaction risk control keyword set, including:

[0102] S31. When the number of business abnormality keywords in the transaction risk control keyword set of each transaction link is less than or equal to a preset first number threshold, the business risk control level of the transaction link is determined as a low risk control level;

[0103] S32. When the number of business abnormality keywords in the transaction risk control keyword set of each transaction link is greater than a preset first number threshold and less than or equal to a preset second number threshold, the business risk control level of the transaction link is determined as an intermediate risk control level;

[0104] S33. When the number of business abnormality keywords in the transaction risk control keyword set of each transaction link is greater than a preset second number threshold, the business risk control level of the transaction link is determined as a high-level risk control level.

[0105] In detail, for each transaction link, there will be a set containing business abnormality keywords, which are used to determine whether the transaction is normal. If among these keywords, the number of business abnormality keywords is very small and does not exceed the first quantity threshold, then this transaction link is considered to be a low-level risk control level; if the number of business abnormality keywords exceeds the first quantity threshold but does not exceed the second quantity threshold, then this transaction link is considered to be a medium-level risk control level; if the number of business abnormality keywords exceeds the second quantity threshold, then this transaction link is considered to be a high-level risk control level.

[0106] For example, if the first quantity threshold is 3 and the second quantity threshold is 5, if the number of business abnormality keywords in the transaction risk control keyword set of a certain transaction link is less than 3, the transaction link can be marked as low risk; if the number of business abnormality keywords in the transaction risk control keyword set of a certain transaction link is between 3 and 5, the transaction link can be marked as medium risk; if the number of business abnormality keywords in the transaction risk control keyword set of a certain transaction link exceeds 5, the transaction link can be marked as high risk. Therefore, according to the different numbers of business abnormality keywords, differentiated risk management strategies can be adopted for different transaction links. For links with a small number of business abnormality keywords, more flexible monitoring measures can be adopted, while for links with a large number of business abnormality keywords, stricter control and review are required.

[0107] Furthermore, the business risk control level corresponding to each transaction link can determine the risk level of the overall business transaction. By considering the risk level of each link, the overall risk can be grasped more accurately to ensure the security and stability of the business.

[0108] In the embodiment of the present invention, the overall business risk control level refers to the risk control level determined after a comprehensive assessment of the entire supply chain financial transaction business, reflecting the risk level of each link involved in the entire business process.

[0109] In the embodiment of the present invention, determining the overall business risk control level of the supply chain financial transaction business through the business risk control level of each transaction link includes:

[0110] Generate a risk control level sequence based on the business risk control levels of all transaction links;

[0111] When the risk control levels in the risk control level sequence are all low risk control levels, the overall business risk control level of the supply chain financial transaction business is set to a low risk control level;

[0112] When any risk control level in the risk control level sequence is at the intermediate risk control level and there is no advanced risk control level, the overall business risk control level of the supply chain financial transaction business is set at the intermediate risk control level;

[0113] When any risk control level in the risk control level sequence is at the advanced risk control level, the overall business risk control level of the supply chain financial transaction business will be set to the advanced risk control level.

[0114] In detail, the business risk control level corresponding to each transaction link is used to generate a risk control level sequence. For example, the business risk control level corresponding to order generation is a low risk control level, the business risk control level corresponding to payment processing is a low risk control level, the business risk control level corresponding to logistics distribution is a low risk control level, and the business risk control level corresponding to after-sales service is a low risk control level. Then the risk control level sequence is {low, low, low, low}.

[0115] Specifically, the overall business risk control level of the supply chain finance transaction business can be determined according to the risk control level sequence. When the risk control levels in the risk control level sequence are all low-level risk control levels, that is, the risk control level sequence is {low, low, low, low}, then the overall business risk control level of the supply chain finance transaction business is a low-level risk control level; when there is an intermediate level but no advanced level in the risk control level sequence, that is, the risk control level sequence is {low, medium, medium, low}, then the overall business risk control level of the supply chain finance transaction business is an intermediate risk control level; when there is only an advanced level in the risk control level in the risk control level sequence, that is, the risk control level sequence is {low, medium, medium, high}, then the overall business risk control level of the supply chain finance transaction business is a advanced risk control level, so that the risk level of each transaction link can be comprehensively considered, making the overall business risk control level more representative and accurate, because even if most links are low-risk, as long as one link is high-risk, the entire transaction business may be affected.

[0116] Furthermore, by determining the overall business risk control level, we can more comprehensively identify and assess the various risks faced by supply chain financial transaction businesses, and we can formulate and implement corresponding risk management strategies and control measures in a targeted manner to reduce the probability and impact of business transaction risks.

[0117] S5. Determine the business transaction risk of the supply chain financial transaction business based on the overall business risk control level.

[0118] In the embodiment of the present invention, the business transaction risk refers to the risk level faced by a financial institution when conducting supply chain financial transaction business transaction activities.

[0119] In the embodiment of the present invention, determining the business transaction risk of the supply chain financial transaction business according to the overall business risk control level includes:

[0120] Calculate the business transaction score of the supply chain financial transaction business according to the overall business risk control level;

[0121] Extracting a business transaction weight of the supply chain finance transaction business, and calculating a business risk score of the supply chain finance transaction business based on the business transaction weight and the business transaction score;

[0122] The business transaction risk of the supply chain finance transaction business is determined based on the business risk score.

[0123] In detail, a business transaction score is assigned to each transaction according to the overall business risk control level. The higher the score, the greater the risk of the transaction. For example, if the overall business risk control level is low, the corresponding transaction score interval is (0,40]; if the overall business risk control level is low, the corresponding transaction score interval is (40,70]; if the overall business risk control level is low, the corresponding transaction score interval is (70,100], and the average of the transaction score intervals is taken as the business transaction score. If the overall business risk control level of the supply chain financial transaction business is medium, the business transaction score is 55, and the business transaction weight of the supply chain financial transaction business is determined. The business transaction weight refers to the importance of the supply chain financial transaction business transaction. The business transaction weight of the supply chain financial transaction business is determined by the hierarchical analysis method, and the business transaction weight of the supply chain financial transaction business is determined from the transaction scale, the credit rating of the participating parties, the transaction cycle, and the transaction variety.

[0124] Specifically, the business transaction weight and the business transaction score are multiplied to obtain the business risk score of the supply chain financial transaction business, and then the business transaction risk of the supply chain financial transaction business is determined according to the business risk score, that is, the business risk score is divided into several levels, such as low risk, medium-low risk, medium risk, medium-high risk and high risk, or a digital identifier (such as 1 to 5) is used. Assuming that the business risk score ranges from 0 to 100, where 0 represents the lowest risk and 100 represents the highest risk, this range is divided into several different levels, for example: 0-20: low risk, 21-40: medium-low risk, 41-60: medium risk, 61-80: medium-high risk, 81-100: high risk, and each transaction is mapped to the corresponding risk level according to the business risk score. For example, if the business risk score of a transaction is 45, then the risk level of this transaction can be classified as medium risk. Based on the risk level of the transaction, a corresponding risk management strategy can be formulated. For low-risk transactions, more relaxed risk management measures may be adopted, while for high-risk transactions, more stringent monitoring and management are required. Regular monitoring and assessment of the risk level of transactions, and adjustments and feedback based on actual conditions will help to timely discover and respond to changes in risks and ensure the stable operation of the company's supply chain financial transaction business.

[0125] The embodiment of the present invention can ensure timely acquisition of the latest business information by real-time collection of business logs, and extract keywords to convert a large amount of log data into analyzable structured information, providing basic data for subsequent risk control analysis; through pre-defined risk control rules, keywords that may be abnormal can be quickly and automatically screened out, reducing the need for manual intervention; calculating the similarity between keywords can help discover the connection between different keywords and improve the accuracy of risk control; classifying abnormal keywords can better understand the risk types in the business; forming a risk control keyword set can comprehensively integrate the risk information of each link; through the determination of the business risk control level, the risks of different links can be quantified and classified, and corresponding risk control strategies can be taken in a targeted manner, and then the overall risk can be evaluated to fully understand the risk level of supply chain financial transaction business. Therefore, the transaction risk control analysis method, device and medium based on supply chain financial logs proposed by the present invention can solve the problem of low accuracy when conducting transaction risk control analysis.

[0126] like Figure 4 , which is a schematic diagram of the structure of an electronic device for implementing a transaction risk control analysis method based on supply chain finance logs provided by an embodiment of the present invention.

[0127] The electronic device may include a processor 10, a memory 11, a communication bus 12, and a communication interface 13, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a transaction risk control analysis program based on a supply chain finance log.

[0128] In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor 10 is the control core (ControlUnit) of the electronic device, and uses various interfaces and lines to connect the various components of the entire electronic device, and executes or executes the programs or modules stored in the memory 11 (for example, executing the transaction risk control analysis program based on the supply chain finance log, etc.), and calls the data stored in the memory 11 to execute various functions of the electronic device and process data.

[0129] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory 11 can also be an external storage device of an electronic device, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory 11 can also include both an internal storage unit of the electronic device and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device, such as the code of the transaction risk control analysis program based on the supply chain finance log, but also can be used to temporarily store data that has been output or is to be output.

[0130] The communication bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0131] The communication interface 13 is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.

[0132] The figure only shows an electronic device with components. Those skilled in the art will understand that the structure shown in the figure does not constitute a limitation on the electronic device, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0133] For example, although not shown, the electronic device may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, etc. The electronic device may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0134] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0135] The transaction risk control analysis program based on the supply chain finance log stored in the memory 11 in the electronic device is a combination of multiple instructions. When running in the processor 10, it can achieve:

[0136] Collect the business logs corresponding to each transaction link in the supply chain financial transaction business in real time, and extract the business keywords in the business logs corresponding to each transaction link;

[0137] Filtering business abnormality keywords among the business keywords according to the pre-generated risk control abnormality rules, and calculating the similarity between the business abnormality keywords in each transaction link;

[0138] Classify the business abnormality keywords screened out in each transaction link according to the similarity to obtain a transaction risk control keyword set corresponding to each transaction link;

[0139] Determine the business risk control level of each transaction link according to the number of business abnormality keywords in the transaction risk control keyword set, and determine the overall business risk control level of the supply chain financial transaction business through the business risk control level of each transaction link;

[0140] The business transaction risk of the supply chain financial transaction business is determined based on the overall business risk control level.

[0141] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, which will not be repeated here.

[0142] Furthermore, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0143] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement:

[0144] Collect the business logs corresponding to each transaction link in the supply chain financial transaction business in real time, and extract the business keywords in the business logs corresponding to each transaction link;

[0145] Filtering business abnormality keywords among the business keywords according to the pre-generated risk control abnormality rules, and calculating the similarity between the business abnormality keywords in each transaction link;

[0146] Classify the business abnormality keywords screened out in each transaction link according to the similarity to obtain a transaction risk control keyword set corresponding to each transaction link;

[0147] Determine the business risk control level of each transaction link according to the number of business abnormality keywords in the transaction risk control keyword set, and determine the overall business risk control level of the supply chain financial transaction business through the business risk control level of each transaction link;

[0148] The business transaction risk of the supply chain financial transaction business is determined based on the overall business risk control level.

[0149] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, media and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0150] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0151] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0152] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0153] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is not limited only according to the above description, and it is intended that all changes within the meaning and scope of equivalent elements within the scope of protection are included in the present invention.

[0154] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0155] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the system can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0156] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A transaction risk control analysis method based on supply chain finance logs, characterized in that: The method comprises: Collect the business logs corresponding to each transaction link in the supply chain financial transaction business in real time, and extract the business keywords in the business logs corresponding to each transaction link; Filtering business abnormality keywords among the business keywords according to the pre-generated risk control abnormality rules, and calculating the similarity between the business abnormality keywords in each transaction link; Classify the business abnormality keywords screened out in each transaction link according to the similarity to obtain a transaction risk control keyword set corresponding to each transaction link; Determine the business risk control level of each transaction link according to the number of business abnormality keywords in the transaction risk control keyword set, and determine the overall business risk control level of the supply chain financial transaction business through the business risk control level of each transaction link; The business transaction risk of the supply chain financial transaction business is determined based on the overall business risk control level.

2. The transaction risk control analysis method based on supply chain finance logs according to claim 1 is characterized in that: The extracting of business keywords from the business log corresponding to each transaction link includes: Generate a regular matching expression for the keyword according to the form of each keyword in the keyword list corresponding to each transaction link; Perform word segmentation on the log data in the business log corresponding to each transaction link; Generate a segmentation sequence from the log data after segmentation processing; Using the regular matching expression, the segmented words in the segmented word sequence are matched with the keywords in the keyword list one by one; The successfully matched segmented words are used as business keywords in the business log.

3. The transaction risk control analysis method based on supply chain finance logs according to claim 1 is characterized in that: The filtering of the business abnormality keywords in the business keywords according to the pre-generated risk control abnormality rules includes: Extract the abnormal transaction logic of each transaction link according to the pre-generated risk control abnormal rules, and extract the abnormal transaction keywords corresponding to the abnormal transaction logic; Comparing the business keywords with the abnormal transaction keywords one by one; When all characters are compared to be the same, the business keyword is used as a business abnormality keyword.

4. The transaction risk control analysis method based on supply chain finance logs according to claim 1 is characterized in that: The calculating of the similarity between the business abnormality keywords in each transaction link includes: Convert the business abnormality keywords in each transaction link into vectors one by one to obtain the business abnormality keyword vector; Combine all business abnormality keyword vectors in each transaction link to obtain a business abnormality keyword vector combination sequence; The similarity between the business abnormality keywords in each business abnormality keyword vector combination sequence is calculated using a preset similarity algorithm.

5. The transaction risk control analysis method based on supply chain finance logs according to claim 1, characterized in that: The abnormal business keywords screened out in each transaction link are classified according to the similarity to obtain a transaction risk control keyword set corresponding to each transaction link, including: Extract the similarity between the business abnormality keywords in all business abnormality keyword vector combination sequences in each transaction link; Selecting the business abnormality keyword in the business abnormality keyword vector combination sequence as the abnormal associated word combination according to the similarity and a preset similarity threshold; Performing semantic analysis on the business abnormality keywords in the abnormal associated word combination; When the semantic contents corresponding to the business abnormality keywords after semantic analysis are similar, the business abnormality keywords are classified as transaction risk control keywords for each transaction link; All transaction risk control keywords are collected into a transaction risk control keyword set corresponding to each transaction link.

6. The transaction risk control analysis method based on supply chain finance logs according to claim 1 is characterized in that: Determining the business risk control level of each transaction link according to the number of business abnormality keywords in the transaction risk control keyword set includes: When the number of business abnormality keywords in the transaction risk control keyword set of each transaction link is less than or equal to a preset first number threshold, the business risk control level of the transaction link is determined as a low risk control level; When the number of business abnormality keywords in the transaction risk control keyword set of each transaction link is greater than a preset first number threshold and less than or equal to a preset second number threshold, the business risk control level of the transaction link is determined as an intermediate risk control level; When the number of business abnormality keywords in the transaction risk control keyword set of each transaction link is greater than a preset second number threshold, the business risk control level of the transaction link is determined as an advanced risk control level.

7. The transaction risk control analysis method based on supply chain finance logs according to claim 1 is characterized in that: The overall business risk control level of the supply chain finance transaction business is determined by the business risk control level of each transaction link, including: Generate a risk control level sequence based on the business risk control levels of all transaction links; When the risk control levels in the risk control level sequence are all low risk control levels, the overall business risk control level of the supply chain financial transaction business is set to a low risk control level; When any risk control level in the risk control level sequence is at the intermediate risk control level and there is no advanced risk control level, the overall business risk control level of the supply chain financial transaction business is set at the intermediate risk control level; When any risk control level in the risk control level sequence is at the advanced risk control level, the overall business risk control level of the supply chain financial transaction business will be set to the advanced risk control level.

8. The transaction risk control analysis method based on supply chain finance logs according to claim 1 is characterized in that: Determining the business transaction risk of the supply chain financial transaction business according to the overall business risk control level includes: Calculate the business transaction score of the supply chain financial transaction business according to the overall business risk control level; Extracting a business transaction weight of the supply chain finance transaction business, and calculating a business risk score of the supply chain finance transaction business based on the business transaction weight and the business transaction score; The business transaction risk of the supply chain finance transaction business is determined based on the business risk score.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the transaction risk control analysis method based on the supply chain finance log as described in any one of claims 1 to 8.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the transaction risk control analysis method based on the supply chain finance log as described in any one of claims 1 to 8 is implemented.

Images