Risky store cluster detection method and its device, equipment, and medium

Abstract

The present application relates to a method for detecting risky shop clusters and its apparatus, equipment, and medium. The method includes: when the number of abnormally traded goods in a shop meets a preset condition, marking the shop as a risky shop, collecting multiple risky shops to form a risky shop set; calculating the ratio of the total number of goods in each of the risky shops in the risky shop set, and when the ratio of the total number of goods is within a preset ratio interval, marking the corresponding two risky shops as suspected risky shop pairs, and the suspected risky shop pairs are used to form a suspected risky shop pair set; filtering out some suspected risky shop pairs from the suspected risky shop pair set; calculating the product similarity coverage rate of the two risky shops corresponding to the suspected risky shop pair, and determining the risky shop cluster based on the corresponding product similarity coverage rate of all suspected risk shop pairs in the suspected risky shop pair set. The present application gradually narrows the detection scope through a multi-stage screening mechanism, and ultimately accurately identifies risky shop clusters.

Description

Technical Field

[0001] The present application relates to the field of e-commerce technology, and in particular to a method for detecting risky store clusters and its apparatus, equipment, and medium. Background Art

[0002] E-commerce platforms typically host a vast number of online stores, each operated by a variety of entities. Different operators and their operating methods result in varying levels of risk. The risk level of an online store is an abstract description of its operational health, typically reflected in its creditworthiness. Low-risk stores are considered to have good credit, while high-risk stores, known as risky stores, have relatively poor credit. Therefore, the risk level of an e-commerce platform's online stores fundamentally determines the platform's survival.

[0003] Existing technologies typically rely on independent analysis of a single store when identifying risky stores. Specifically, existing technologies mainly use preset rules or models to conduct risk assessments and risk level classifications for single stores. However, some operators often set up multiple online stores in order to circumvent e-commerce platform supervision, diversify risks, or engage in other improper behaviors. These stores appear to be independently operated, with different store names and operating entities, but are actually controlled by the same operating entity. In this case, when a store faces risks, if the store cluster to which it belongs cannot be identified and controlled in a timely manner, it will cause huge potential risks and losses to the e-commerce platform.

[0004] Therefore, how to design a detection method that can identify risky store clusters has become a technical problem that e-commerce platforms urgently need to solve. Summary of the Invention

[0005] The primary purpose of this application is to solve at least one of the above problems and provide a method for detecting risky store clusters and its devices, equipment, and media.

[0006] In order to meet the various objectives of this application, this application adopts the following technical solutions:

[0007] A method for detecting risky store clusters provided to meet one of the purposes of this application includes the following steps:

[0008] When the number of abnormally traded goods in a store meets the preset conditions, the store is marked as a risky store, and multiple risky stores are collected to form a risky store set;

[0009] Calculating the ratio of the total number of goods between each of the risky stores in the risky store set; when the ratio of the total number of goods is within a preset ratio interval, marking the corresponding two risky stores as a suspected risky store pair, and the suspected risky store pair is used to form a suspected risky store pair set;

[0010] Based on the quantity of the abnormally traded commodities corresponding to the suspected risky store pairs and a preset similarity determination rule, filtering out some of the suspected risky store pairs from the set of suspected risky store pairs;

[0011] Based on the filtered set of suspected risk store pairs, the product similarity coverage rate of the suspected risk store pairs corresponding to the two risk stores is calculated, and based on the corresponding product similarity coverage rates of all suspected risk store pairs in the set of suspected risk store pairs, the risky site group stores are determined.

[0012] On the other hand, a device for detecting risky store clusters provided to meet one of the purposes of this application includes:

[0013] A risky store marking module is used to mark a store as a risky store when the number of abnormally traded products in the store meets the preset conditions, and collect multiple risky stores to form a risky store set;

[0014] A risky store pair formation module is used to calculate the ratio of the total number of goods between any two risky stores in the risky store set. When the ratio of the total number of goods is within a preset ratio interval, the corresponding two risky stores are marked as a suspected risky store pair. The suspected risky store pair is used to form a suspected risky store pair set.

[0015] a risky store pair filtering module, configured to filter out some of the suspected risky store pairs from the set of suspected risky store pairs based on the quantity of the abnormally traded products corresponding to the suspected risky store pairs and a preset similarity determination rule;

[0016] The risky store cluster determination module is used to calculate the product similarity coverage rate of the suspected risk store pairs corresponding to the two risk stores based on the filtered set of suspected risk store pairs, and determine the risky store cluster based on the corresponding product similarity coverage rate of all suspected risk store pairs in the set of suspected risk store pairs.

[0017] On the other hand, a computer device provided to meet one of the purposes of the present application includes a central processing unit and a memory, and the central processing unit is used to call and run a computer program stored in the memory to execute the steps of the risky store site cluster detection method described in the present application.

[0018] On the other hand, a computer program product provided to meet another purpose of the present application includes a computer program / instruction, which, when executed by a processor, implements the steps of the method described in any embodiment of the present application.

[0019] The technical solution of this application has many advantages, including but not limited to the following:

[0020] On the one hand, this application comprehensively considers the correlation between multiple risky stores and can more effectively identify risky store clusters controlled by the same operating entity. This not only improves the coverage of detection, but also can more accurately capture the behavior of merchants dispersing risks by operating multiple stores.

[0021] On the other hand, the present application gradually narrows the scope of detection through a multi-stage screening mechanism, and finally determines the risky station group stores. Specifically, the present application first screens out risky stores through preset conditions to form a risky store set, and then further screens out suspected risky store pairs based on the ratio of the total number of goods in each of the two risky stores in the risky store set to form a suspected risky store pair set. That is, by quantifying the relationship between the scale of goods between stores, it is possible to preliminarily identify risky store station groups that may be controlled by the same business entity. Then, based on the number of abnormally traded goods and the preset similarity judgment rules, the suspected risky store pairs are filtered, and on the basis of the suspected risky store pair set, more strongly associated suspected risky store pairs are screened out, and suspected risky store pairs that do not meet the preset similarity judgment rules are filtered out, thereby reducing the false alarm rate and improving the accuracy of detection. Finally, by calculating the similarity coverage of goods and determining the risky station group stores, it is possible to fully identify the risky store station groups controlled by the same business entity.

[0022] This application uses a multi-stage screening mechanism to gradually narrow the scope of detection, and ultimately accurately identify risky store clusters controlled by the same business entity, effectively reducing the false alarm rate, improving the accuracy and reliability of detection, and providing e-commerce platforms with more efficient risky store cluster detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0024] Figure 1 This is a flowchart of a typical embodiment of the risky store site group detection method of the present application;

[0025] Figure 2 This is a flowchart of marking risky stores based on the proportion of banned or restricted goods in an embodiment of the present application;

[0026] Figure 3This is a flowchart of marking risky stores according to the fraud risk ratio in an embodiment of the present application;

[0027] Figure 4 This is a flow chart of filtering suspected risky store pairs based on the number of abnormally traded goods in an embodiment of the present application;

[0028] Figure 5 Schematic diagram of the process of determining whether the first similarity judgment condition is met in an embodiment of the present application;

[0029] Figure 6 This is a flowchart of determining risky site group stores based on product similarity coverage in an embodiment of the present application;

[0030] Figure 7 A schematic diagram of a process for determining product similarity coverage in an embodiment of the present application;

[0031] Figure 8 This is a principle block diagram of the risky store cluster detection device of this application;

[0032] Figure 9 This is a schematic diagram of the structure of a computer device used in this application. DETAILED DESCRIPTION

[0033] A risky store cluster detection method of the present application can be programmed as a computer program product, deployed in a server and implemented. For example, in the exemplary application scenario of the present application, it can be deployed in the server of an e-commerce platform, wherein the e-commerce platform can be an e-commerce platform that opens independent station services. An independent station refers to a new type of official website (website) established on a SaaS technology platform, which has an independent domain name, private content, data, and rights and interests, independent business sovereignty and business entity responsibilities, supported by social cloud computing capabilities, and can independently and freely connect to third-party software tools, publicity and promotion media and channels. Usually, product sellers build and operate online stores on independent stations, allowing online stores to display their products on independent stations, and provide product buyers (i.e. users) with e-commerce services such as searching for products on online stores, adding shopping carts, settlement, logistics delivery, placing orders, and after-sales service. Product buyers (users) perform various interactive operations with the e-commerce platform on terminal devices.

[0034] In some embodiments of the present application, commodities with a risk of being banned or restricted for sale or with a risk of fraud are regarded as commodities with abnormal transactions, wherein commodities with a risk of being banned or restricted for sale (hereinafter referred to as banned or restricted commodities) are commodities that are explicitly restricted or prohibited from sale by e-commerce platforms, such as contraband, illegal commodities, dangerous goods, etc. In the field of cross-border e-commerce, banned or restricted commodities may include seafood, agricultural products, alcoholic beverages, etc.; commodities with a risk of fraud (hereinafter referred to as fraud commodities) refer to commodities that are illegally operated by merchants, such as false shipments, selling inferior goods as good ones, and other illegal business practices. It should be noted that when merchants put fraud commodities on the shelves for sale, they will attract the attention of consumers at a low price far below the market standard price, so that consumers ignore the doubts about the authenticity of the commodities. Fraud commodities are usually counterfeit and shoddy products with extremely low costs. Merchants usually sell them at low prices to quickly obtain profits, circumvent platform supervision or induce consumers to place orders.

[0035] In a typical embodiment of the present application, the number of goods with abnormal transactions in a store is obtained, and based on the number of goods, it is determined whether the store is a risk store, and multiple risk stores are collected to form a risk store set. The number of goods with abnormal transactions in risk stores in the risk store set accounts for a high proportion of its total number of goods, which meets the characteristics of risk stores corresponding to the risk store cluster. Moreover, if one of the multiple stores controlled by the same business entity is a risk store, there is a high probability that the other stores controlled by the business entity are also risk stores. The ratio of the total number of goods of each of the risk stores in the risk store set is calculated. When the ratio of the total number of goods is within a preset ratio range, the corresponding two risk stores are marked as suspected risk store pairs. This step takes into account that the number of goods on the shelves of risk stores in the same risk store cluster usually has certain similarities. When the same business entity controls multiple stores, it often adopts a unified operating strategy and product listing model, which causes the total number of goods in these stores to fluctuate within a certain range. By calculating the ratio of the total number of goods and setting a reasonable preset ratio range, these suspected risk store pairs with similar characteristics can be effectively identified.

[0036] Based on the number of goods in the suspected risk store pairs with corresponding abnormal transactions and the preset similarity judgment rules, the similarity and correlation between the suspected risk store pairs are further determined to confirm whether the suspected risk store pairs belong to the same risk store station group. In some embodiments, similarity judgment rules are preset based on the first product category, the risk ratio of banned or restricted goods, the second product category, and the ratio of fraudulent product categories. For specific steps, please refer to the subsequent specific implementation methods, which will not be repeated here. This step filters out some suspected risk store pairs that do not meet the preset similarity judgment rules from the set of suspected risk store pairs. Among them, the similarity judgment rules are preset by those skilled in the art as needed.

[0037] Finally, the risky site cluster stores are determined by calculating the product similarity coverage ratio of the suspected risky store to the corresponding two risky stores. In one embodiment, each store in the suspected risky store pair is marked as a node in the risky site cluster store graph. When the product similarity coverage ratio exceeds a preset coverage ratio threshold, an edge connection is established between the corresponding two stores to form a risky site cluster store graph for determining the risky site cluster to which the store belongs. The coverage ratio threshold is set by those skilled in the art based on business data or experience.

[0038] A risky store site cluster detection method of the present application can be programmed as a computer program product and deployed in a server for execution. For example, in the exemplary application scenario of the present application, it can be deployed and implemented in the server of an e-commerce customer service platform. The method can be executed by accessing the interface opened after the computer program product is run and performing human-computer interaction with the process of the computer program product through a graphical user interface.

[0039] See also Figure 1 The risky store cluster detection method of the present application, in its typical embodiment, includes the following steps:

[0040] Step S5100: When the number of abnormally traded commodities in a store meets a preset condition, the store is marked as a risky store, and multiple risky stores are collected to form a risky store set;

[0041] Obtain the number of goods with abnormal transactions in the store. In one embodiment, goods with prohibited or restricted sales risk are regarded as goods with abnormal transactions. The preset condition is set as the proportion of prohibited or restricted sales goods is greater than the preset ratio threshold, wherein the number of goods with abnormal transactions with prohibited or restricted sales risk in the corresponding store divided by the total number of goods in the store is the proportion of prohibited or restricted sales goods, and the ratio threshold is set as needed by those skilled in the art. Specifically, all valid goods in the store are tested for prohibited or restricted sales risk, and prohibited or restricted sales risk labels are added to the corresponding valid goods. For details of this step, please refer to the subsequent specific implementation methods, which will not be repeated here. After adding prohibited or restricted sales risk labels to valid goods, the number of prohibited or restricted sales risk labels of the store can be directly counted to obtain the number of goods with abnormal transactions. When the number of goods with abnormal transactions in the store meets the preset conditions, that is, when the proportion of prohibited or restricted sales goods is greater than the preset ratio threshold, the corresponding store will be marked as a risky store.

[0042] In another embodiment, commodities with fraud risk are considered as commodities with abnormal transactions, and the preset condition is set as the proportion of fraudulent commodities is greater than a preset second ratio threshold. When the number of commodities with abnormal transactions in a store meets the corresponding preset condition, that is, the proportion of fraudulent commodities is greater than the preset second ratio threshold, the corresponding store is marked as a risky store. In another embodiment, commodities with the risk of being banned or restricted for sale and commodities with fraud risk are both considered as commodities with abnormal transactions. When two corresponding preset conditions are met, that is, the proportion of banned or restricted for sale commodities is greater than the preset ratio threshold and the proportion of fraudulent commodities is greater than the preset second ratio threshold, the corresponding store is marked as a risky store.

[0043] After marking the stores that need to be inspected as risky, we collect data from multiple stores to form a risky store set. This risky store set can be constructed based on the inspection and marking of all stores on the platform, and can be used for comprehensive inspection when subsequently determining risky store clusters. This step uses a screening mechanism based on abnormally traded products to screen out potential risky stores and form a risky store set, providing a data foundation for subsequent risky store cluster detection.

[0044] Step S5200: Calculate the ratio of the total number of products between any two risky stores in the risky store set. When the ratio of the total number of products is within a preset ratio interval, mark the corresponding two risky stores as a suspected risky store pair. The suspected risky store pair is used to form a suspected risky store pair set.

[0045] For each pair of risky stores in the risky store set, the ratio of the total number of goods in each pair of risky stores is calculated. The calculated ratio of the total number of goods is compared with the preset ratio range. The preset ratio range is pre-set based on platform rules and historical data, and is used to determine whether the two risky stores have similarities in terms of product scale. When the ratio of the total number of goods is within the preset ratio range, the corresponding two risky stores are marked as a suspected risky store pair. In this way, suspected risky store pairs with similar product scale can be screened out to form a suspected risky store pair set.

[0046] Risky stores within a risky store cluster are operated by the same or affiliated entities, and their corresponding product quantities are often highly consistent. By screening store pairs whose total product count ratios fall within a preset range, we can effectively identify risky stores that may belong to the same cluster, providing more accurate data support for subsequent risky cluster detection.

[0047] Step S5300: Filter out some of the suspected risky store pairs from the set of suspected risky store pairs based on the quantity of the products with abnormal transactions corresponding to the suspected risky store pairs and a preset similarity determination rule;

[0048] In one embodiment, based on each pair of shops in the set of suspected risk shop pairs (suspected risk shop pairs), and based on the number of goods of the corresponding abnormal transactions of the suspected risk shop pairs (including the number of banned and restricted sales goods and the number of fraudulent goods), the corresponding banned and restricted sales goods risk ratio and fraudulent goods risk ratio are calculated. Then, based on the preset similarity judgment conditions, each pair of shops is screened in two stages. The first stage is based on the similarity judgment of banned and restricted sales goods, and the second stage is based on the similarity judgment of fraudulent goods. Among them, this application does not limit the order of the two stages, that is, the order of the two stages does not affect the embodiment of the creative spirit of this application.

[0049] In the first stage of similarity assessment, the difference in the risk ratios of banned or restricted goods for the two stores is first calculated—that is, the absolute value of the difference between the two stores' risk ratios of banned or restricted goods. This difference is then compared with a preset difference threshold. If the difference is less than the preset difference threshold, the two stores are preliminarily determined to have similar risk ratios of banned or restricted goods. The banned or restricted goods categories of the two stores are further analyzed. Specifically, multiple first product categories with a high number of banned or restricted goods in each store are obtained, and the overlap rate of the first product categories of the two stores is determined. The overlap rate is calculated as the number of identical categories in the first product categories of the two stores divided by the total number of first product categories in either store. If the overlap rate is greater than the preset overlap rate threshold, the two stores are determined to have a high degree of similarity in banned or restricted goods categories, meeting the preset similarity assessment rules. If both the risk ratio difference and the category overlap rate of the two stores meet the preset conditions, the second stage of similarity assessment is performed; otherwise, the suspected risky store pair is filtered out of the set of suspected risky store pairs.

[0050] In the second stage of similarity judgment, further screening is performed based on the similarity of fraudulent goods. Multiple second product categories with a large number of fraudulent goods in the two stores are obtained, and the risk ratio of fraudulent goods is calculated. By analyzing the second product categories of the two stores and their fraudulent product risk ratios, it is determined whether they meet the preset similarity judgment rules. For example, the difference thresholds corresponding to the category overlap rate and the difference in the risk ratio of fraudulent goods can be set. If the two stores meet the preset conditions in terms of fraudulent product categories and risk ratios, they are considered to meet the preset similarity judgment rules; otherwise, the store pair is filtered out from the set of suspected risk store pairs. Please refer to the subsequent specific implementation methods for the specific steps, which will not be repeated here.

[0051] Through the above-mentioned double screening mechanism, suspected risky store pairs that do not meet the preset similarity judgment conditions can be effectively eliminated, and suspected risky store pairs that are highly similar in both banned and restricted goods and fraudulent goods can be retained. This refined screening process not only improves the accuracy of risky store cluster detection, but also provides a more reliable data basis for subsequent risky site cluster determination. At the same time, the preset difference threshold, overlap rate threshold and other parameters can be adjusted according to actual business needs to adapt to the risk detection needs in different scenarios, further improving the flexibility and applicability of this application.

[0052] Step S5400: Based on the filtered set of suspected risk store pairs, calculate the product similarity coverage rate of the suspected risk store pairs corresponding to the two risk stores, and determine the risky site group stores based on the corresponding product similarity coverage rates of all suspected risk store pairs in the set of suspected risk store pairs.

[0053] In one embodiment, for each pair of stores in the filtered set of suspected risk store pairs (suspected risk store pairs), the corresponding product titles are converted into vector representations to obtain product title vectors. The conversion of product title vectors can be achieved through natural language processing technology, such as using a word embedding model (such as Word2Vec, BERT, etc.) to map the words in the product title into vectors, and obtain the vector representation of each product title through weighted averaging or pooling operations to obtain product title vectors. Then, based on the product title vectors, the cosine similarity between the product title vectors of the two stores is calculated to obtain a product similarity matrix. The cosine similarity is calculated as follows: the dot product of the two product title vectors is divided by the corresponding module length product, and the value range is [-1,1]. The closer the value is to 1, the more similar the semantics of the two product titles are.

[0054] Based on the obtained product similarity matrix, the product similarity coverage of the two stores is determined. Specifically, for each store's product title vector, the maximum cosine similarity between the store's product title vector and the other store's product title vector is determined in the product similarity matrix, and the maximum cosine similarity is compared with the preset similarity threshold. The number of products with a maximum cosine similarity greater than the similarity threshold is counted, and the number of products is divided by the total number of products in either of the two stores to obtain the product similarity coverage of the two stores. The product similarity coverage reflects the degree of semantic similarity between the two stores in the product titles. The higher the coverage, the more likely the products of the two stores are to belong to the same category or have the same operating characteristics.

[0055] In another embodiment, a risk station group store graph is constructed based on the commodity similarity coverage of all suspected risk store pairs. Each store is regarded as a node in the graph, and when the commodity similarity coverage of two stores is greater than a preset coverage threshold, an edge connection is established between the corresponding two stores. In this way, pairs of stores with high similarity are connected to form a risk station group store graph. Based on the risk station group store graph, a densely connected subgraph can be identified through a graph analysis algorithm (such as a community detection algorithm) to determine a potential set of risk station group stores. Through this graph construction method based on commodity similarity coverage, risk store clusters operated by the same entity or related entities can be effectively identified, providing strong support for risk management of e-commerce platforms.

[0056] In another embodiment, since a large number of stores need to be detected simultaneously, which includes a huge number of products, directly calculating the product vector representation in real time and performing product similarity coverage analysis between two stores will lead to low computational efficiency. In this embodiment, all product titles are first preprocessed, and the corresponding product title vectors are obtained and stored offline. At the same time, an index is established for the product based on the store ID and product serial number of the product for quick retrieval. When performing risk store cluster detection, the product data is divided into historical product data and newly listed product data. For historical product data, the offline stored product title vector is directly obtained through the product index; for newly listed product data, the corresponding product title vector is obtained, and the product title vector corresponding to the newly listed product data is stored offline, and the corresponding index is updated at the same time. In this way, the time cost of real-time calculation is significantly reduced, providing efficient technical support for large-scale risk store cluster detection.

[0057] It can be seen from the typical embodiments of the present application that the technical solution of the present application has many advantages, including but not limited to the following aspects:

[0058] On the one hand, this application comprehensively considers the correlation between multiple risky stores and can more effectively identify risky store clusters controlled by the same operating entity. This not only improves the coverage of detection, but also can more accurately capture the behavior of merchants dispersing risks by operating multiple stores.

[0059] On the other hand, the present application uses a multi-stage screening mechanism to gradually narrow the scope of detection and ultimately determine the risky station group stores. Specifically, the present application first screens out risky stores through preset conditions to form a risky store set, and then further screens out suspected risky store pairs based on the ratio of the total number of goods in each of the two risky stores in the risky store set to form a suspected risky store pair set. That is, by quantifying the relationship between the scale of goods between stores, it is possible to preliminarily identify risky store station groups that may be controlled by the same business entity. Then, based on the number of abnormal transaction goods and the preset similarity judgment rules, the suspected risky store pairs are filtered, and on the basis of the suspected risky store pair set, more strongly associated suspected risky store pairs are screened out, and suspected risky store pairs that do not meet the preset similarity judgment rules are filtered out, reducing the false alarm rate and improving the accuracy of detection. Finally, by calculating the similarity coverage of goods and determining the risky station group stores, it is possible to fully identify the risky store station group controlled by the same business entity. The present application uses a multi-stage screening mechanism to gradually narrow the scope of detection and ultimately accurately identify the risky store station group controlled by the same business entity, effectively reducing the false alarm rate, improving the accuracy and reliability of detection, and providing e-commerce platforms with more efficient risky store station group detection.

[0060] In addition, by storing product title vectors offline, the need for real-time computing can be greatly reduced, especially when processing large-scale product data, avoiding repeated computing and waste of resources. In addition, the introduction of offline storage and indexing mechanisms also enhances the scalability and flexibility of this application. As the number of products on the platform continues to increase, the accuracy and timeliness of risky store cluster detection can be ensured by regularly updating the offline stored product title vectors and indexes. This enables the technical solution of this application to adapt to the ever-changing data scale and business needs of e-commerce platforms, and provide continuous and reliable risk management support for the platform.

[0061] For further examples, please refer to Figure 2 When the number of abnormally traded goods in a store meets a preset condition, the store is marked as a risky store. Multiple risky stores are collected to form a risky store set, including the following steps:

[0062] Step S5110: Obtain the product titles of all valid products in the store, where the product titles include the product main title and product subtitle;

[0063] You can access the product information of the target store through the data interface or database of the e-commerce platform and extract the product titles of all valid products. Valid products refer to products that are currently on sale, that is, products that have not been removed from the shelves or deleted. The product title consists of the product title and the product subtitle. The product title is the core descriptive information of the product, which is used to summarize the main features of the product, such as brand, model, function, etc. The product subtitle is a supplement to the main title, containing promotional information, specifications, or other detailed descriptions. When extracting product titles, you need to ensure that both the main title and the subtitle are obtained to ensure the completeness and accuracy of the product information. For some products, the subtitle may be empty, in which case only the main title is used as the product title.

[0064] In one embodiment, the title and subtitle of a product are spliced ​​together to form a new text. Taking cross-border e-commerce as an example, when the product title is in English, all texts are lowercase to eliminate the impact of case differences on text analysis. Then, the text can be segmented using BPE (Byte Pai r Encoding), and the segmentation results are mapped into a numerical sequence through a predefined vocabulary. Each integer in the numerical sequence corresponds to a word in the original text, thereby converting the text into a numerical form that can be processed by subsequent models. Finally, the processed text is input into a preset text pre-training model to extract text features and represent them with vectors. The text pre-training model adopts a contrastive learning framework to make similar texts closer in the vector space. The vector obtained by the text pre-training model is L2 normalized so that the sum of the squares of the values ​​at all positions is 1, thereby ensuring the consistency and comparability of the vector in subsequent calculations.

[0065] Step S5120: Input the product title into a pre-trained sales restriction risk detection model to determine whether the valid product corresponding to the product title has a sales restriction risk. Valid products with a sales restriction risk are characterized as products that are restricted or prohibited from sale by the e-commerce platform where the store is located.

[0066] The obtained product title (including the main title and subtitle) is input into a pre-trained sales restriction risk detection model. In one embodiment, the sales restriction risk detection model is constructed based on natural language processing technology and machine learning algorithms, capable of performing semantic analysis and sales restriction risk classification on product titles. The training data for the sales restriction risk detection model includes a large number of labeled product title samples, where positive samples are product titles that are restricted or prohibited from sale by the platform, and negative samples are product titles that comply with regulations. Through training, the sales restriction risk detection model can learn the key features and semantic patterns of sales restriction product titles, such as vocabulary and descriptions related to prohibited items, illegal and non-compliant goods, and dangerous goods. The product title obtained in the previous step is input into the sales restriction risk detection model, which outputs a risk probability value indicating the likelihood that the product title carries a sales restriction risk. Based on a preset risk threshold, the risk probability value is compared with the risk threshold. If the risk probability value is greater than the risk threshold, the valid product corresponding to the product title is determined to carry a sales restriction risk, and a sales restriction risk label is added to the corresponding valid product. The risk threshold can be set as needed by those skilled in the art. Through this step, it is possible to efficiently and accurately identify prohibited or restricted goods that may exist in the store.

[0067] Step S5130: Count the number of products with abnormal transactions that are at risk of being banned or restricted in sale in the store, and obtain the proportion of banned or restricted products in the store based on the number of products with abnormal transactions and the total number of valid products in the store.

[0068] In one embodiment, all valid commodities in the store are traversed to check whether the valid commodities are marked as having the risk of being banned or restricted for sale. By querying the banned or restricted for sale risk label, the number of commodities with abnormal transactions that have the risk of being banned or restricted for sale in the store is counted. Based on the number of banned or restricted commodities obtained by statistics and the total number of valid commodities, the proportion of banned or restricted commodities is calculated. (The number of abnormal transactions that have the risk of being banned or restricted for sale / the total number of valid commodities in the store) × 100% is the proportion of banned or restricted commodities. The proportion of banned or restricted commodities reflects the relative proportion of banned or restricted commodities in the store, and is an important indicator for assessing the risk level of the store.

[0069] Step S5140: When the proportion of the banned or restricted sales commodities is greater than a preset ratio threshold, the store is marked as a risky store, and multiple risky stores are collected to form a risky store set.

[0070] The calculated proportion of banned or restricted sales commodities is compared with the preset proportion threshold. The preset proportion threshold is set by those skilled in the art based on the rules, historical data and / or risk management requirements of the e-commerce platform, and is used to determine whether a store has a higher risk of banned or restricted sales. For example, assuming that the preset proportion threshold is 3%, if the proportion of banned or restricted sales commodities in a store is 5%, it exceeds the preset proportion threshold, indicating that the store has a higher risk of banned or restricted sales, and the store is marked as a risky store. In one embodiment, a risky store label is added to stores whose proportion of banned or restricted sales commodities is greater than the preset proportion threshold. Traverse all stores on the platform, filter out all stores whose proportion of banned or restricted sales commodities is greater than the preset threshold, and constitute a set of risky stores.

[0071] In this embodiment, banned or restricted goods are identified as abnormally traded goods, and the proportion of banned or restricted goods reflects the risk level of the corresponding store. This risk level is then quantified to determine whether the corresponding store is a risky store. Finally, multiple risky stores are collected to form a risky store set. This risk assessment mechanism based on the proportion of banned or restricted goods can accurately identify potentially high-risk stores.

[0072] For further examples, please refer to Figure 3 When the number of abnormally traded goods in a store meets a preset condition, the store is marked as a risky store. Multiple risky stores are collected to form a risky store set, including the following steps:

[0073] Step S5150: Obtain the prices of all valid products in the store and a preset standard price library;

[0074] In one embodiment, the store's product information is accessed through the e-commerce platform's data interface or database, and the product prices of all valid products are extracted. Product prices include one or more price information such as the product's selling price, promotional price, and discount price. A preset standard price library is also obtained. This standard price library contains the standard price ranges of various products on the platform and is set based on historical sales data, market conditions, and platform rules. The construction of the standard price library can be achieved through data mining and statistical analysis techniques to ensure that it reflects the reasonable price range of similar products on the market. Through this step, the identification process of risky stores is ensured to have a reliable price basis.

[0075] Step S5160: Using a fraud risk detection model, determine whether the price of each valid product is artificially low based on a preset standard price database. If the price is artificially low, identify the valid product corresponding to the price as having a fraud risk, and mark the valid product as an abnormally traded product.

[0076] In one embodiment, based on the product title corresponding to the product price, the standard price range of the corresponding product is retrieved from the standard price library. The product price and its corresponding standard price range are then input into a pre-trained fraud risk detection model. The fraud risk detection model can determine the degree of deviation between the product price and the standard price range. By comparing the deviation with the lowest price in the standard price range, the model determines whether the product price of each valid product is falsely low, and thus determines whether the product has a fraud risk. For example, if the product price of a valid product is lower than the risk threshold (e.g., 30%) of the standard price of the corresponding product in the standard price library, the product is marked as having a fraud risk, and the valid product is labeled as an abnormal transaction product. Merchants often list products at extremely low prices to attract consumers, but the actual product received by consumers after purchase often differs from the description on the e-commerce platform. It should be noted that this embodiment is generally applied to standard products, that is, products with clear standards and regulations. The standard price range is related to the corresponding product brand and specifications. For example, a 64-inch TV and a 32-inch TV can have a significant difference in price due to their different sizes.

[0077] Through this embodiment, the fraud risk model will be tested, and a fraud risk label will be added to the corresponding valid product with fraud risk. At the same time, the valid product will be marked as an abnormal transaction product. The fraud risk label is used to count the number of abnormal transaction products with fraud risk in the store.

[0078] Step S5170: Count the number of products with abnormal transactions that pose a risk of fraud in the store, determine whether the corresponding store is a risky store based on the number of products with abnormal transactions and the preset conditions, and collect multiple risky stores to form a risky store set.

[0079] In one embodiment, all valid goods in a store are traversed to check whether all valid goods are marked as having fraud risks. By querying the fraud risk label, the number of goods with abnormal transactions that have fraud risks in the store is counted. Then the total number of valid goods in the store is obtained, and the proportion of fraudulent goods is calculated based on the number of fraud risk goods and the total number of valid goods obtained by statistics. The proportion of fraudulent goods reflects the relative proportion of fraudulent goods in the store. The calculated proportion of fraudulent goods is compared with a preset proportion threshold. The preset proportion threshold is set according to the rules of the e-commerce platform and historical data, and is used to determine whether the store has a high fraud risk. If the proportion of fraudulent goods is greater than the preset proportion threshold, the store is marked as a risky store, and all stores with a proportion of fraudulent goods greater than the preset threshold are screened out to form a set of risky stores.

[0080] In this embodiment, by combining a standard price database with a fraud risk detection model, we can efficiently identify inflated prices as fraud-risk items. These items are then treated as abnormally priced items. The proportion of fraudulent items reflects the risk level of the corresponding store. This risk level is then quantified to determine whether the store is a risky store. Finally, multiple risky stores are collected to form a risky store set. This risk assessment mechanism based on the proportion of fraudulent items can accurately identify potentially high-risk stores.

[0081] For further examples, please refer to Figure 4 , based on the quantity of the abnormally traded commodities corresponding to the suspected risky store pairs and a preset similarity determination rule, filtering out some of the suspected risky store pairs from the set of suspected risky store pairs, including the following steps:

[0082] Step S5310: Based on the suspected risky store and the corresponding two risky stores, obtain whether the prohibited or restricted product categories of the two risky stores include multiple first product categories with a large number of products and the risk ratio of prohibited or restricted products;

[0083] In one embodiment, for each of the two risky stores in a suspected risky store pair, all valid products in the risky stores are traversed to check whether the products are marked as having a risk of prohibited or restricted sales. By querying the prohibited or restricted sales risk label, the category distribution of prohibited or restricted sales products in each store is counted, that is, the number of prohibited or restricted sales products under each category. Specifically, natural language processing technology is used to analyze the product title, description text, or other related information to identify the category to which the product belongs, and the identified category is matched with a preset prohibited or restricted sales category list. The prohibited or restricted sales category list is constructed based on platform rules, laws and regulations, and historical data, and contains product categories that are explicitly prohibited or restricted from sale. In the field of cross-border e-commerce, examples include "aquatic products," "agricultural products," "alcoholic beverages," "electronic products," and "cosmetics." If the product category matches a category in the prohibited or restricted sales category list, a corresponding prohibited or restricted sales category label is added to the product. For example, if a product belongs to the "aquatic products" category, a "prohibited or restricted sales - aquatic products" label is added to the corresponding product. It should be noted that the list of prohibited and restricted sales categories can be dynamically updated based on changes in platform rules, laws and regulations, and actual business needs. When the list is updated, rescan the products in the store to check whether the corresponding product categories match the new list, and update the corresponding prohibited and restricted sales category tags.

[0084] Sort categories by the number of banned or restricted items, and select multiple first-level product categories with a high number of banned or restricted items. The number of first-level product categories can be set based on actual needs, for example, selecting the top three categories with the highest number of banned or restricted items. First-level product categories reflect a store's primary risk distribution for banned or restricted items and serve as the basis for determining store similarity. This also allows for the determination of the banned or restricted item risk ratio. The banned or restricted item risk ratio reflects the concentration of a store's risk for banned or restricted items and is a key indicator for assessing a store's risk level. For example, risky store A has 1,000 valid items, 100 of which are marked as banned or restricted. This means the banned or restricted item risk ratio for this risky store is 10%. By statistically analyzing the distribution of banned or restricted item categories among these 100 banned or restricted items, multiple first-level product categories with a high number of banned or restricted items can be selected. For example, suppose that among the 100 banned or restricted items, there are 40 items in the "Aquatic Products" category, 30 items in the "Agricultural Products" category, 20 items in the "Alcoholic Beverages" category, 5 items in the "Electronic Products" category, and 5 items in the "Cosmetics" category. Sorting by the number of banned or restricted items, the top three product categories are selected as "Aquatic Products," "Agricultural Products," and "Alcoholic Beverages." This step provides data on the banned or restricted product categories and risk ratios of the two risky stores in the suspected risky store pair, providing a comprehensive and accurate basis for subsequent similarity assessments.

[0085] Step S5320: Based on the first product category and the risk ratio of the prohibited or restricted products, determine whether the suspected risky store pair meets a preset first similarity judgment condition; if not, filter the corresponding suspected risky store pair from the set of suspected risky store pairs;

[0086] In one embodiment, assuming that risky store A has a total of 1,000 valid commodities, of which 100 commodities are marked as prohibited or restricted commodities, the corresponding prohibited or restricted commodity risk ratio is 10%; risky store B has a total of 800 valid commodities, of which 80 commodities are marked as prohibited or restricted commodities, the prohibited or restricted commodity risk ratio is 10%. Calculate the difference in the prohibited or restricted commodity risk ratios of the two stores, i.e., |10%-10%|=0%, and compare the difference with a preset first difference threshold (e.g., 5%). If the difference is less than the preset first difference threshold, it is preliminarily determined that the two stores have similarities in the prohibited or restricted commodity risk ratios.

[0087] When the difference is less than the preset first difference threshold, the categories of banned or restricted goods in the two stores are further analyzed. Obtain multiple first commodity categories with a large number of banned or restricted goods in the two stores. For example, the banned or restricted goods of risky store A are mainly distributed in the three categories of "aquatic products" (40), "agricultural products" (30) and "alcoholic beverages" (20); the banned or restricted goods of risky store B are mainly distributed in the three categories of "aquatic products" (35), "agricultural products" (25) and "alcoholic beverages" (15). Calculate the overlap rate of the two first commodity categories. The overlap rate is calculated as the number of the same categories in the first commodity categories of the two stores divided by the total number of the first commodity categories of one of the stores. In this example, the first commodity categories of the two stores are "aquatic products", "agricultural products" and "alcoholic beverages", the number of the same categories is 3, and the total number of the first commodity categories of one of the stores is 3, so the overlap rate is 3 / 3×100%=100%. The overlap rate is compared with a preset first overlap rate threshold (for example, 80%). If the overlap rate is greater than the preset first overlap rate threshold, it is determined that the two stores are highly similar in the categories of banned or restricted goods. That is, when the difference in the risk ratios of banned or restricted goods of the two stores is less than the preset first difference threshold and the overlap rate of the corresponding first product category is greater than the preset first overlap rate threshold, it is determined that the first similarity judgment condition is met.

[0088] If the difference in the risk ratio of banned or restricted goods and the category overlap rate between two stores meet the preset conditions, the suspected risk store pair is retained; otherwise, the suspected risk store pair is filtered out from the suspected risk store pair set. Through the above steps, it is possible to effectively screen out suspected risk store pairs with high similarity in the risk ratio of banned or restricted goods and category distribution.

[0089] Step S5330: When the suspected risky store meets the preset first similarity judgment condition, based on the suspected risky store's comparison with the corresponding two risky stores, obtain the fraudulent product categories of the two risky stores, including multiple second product categories with a large number of products, and the fraudulent product risk ratio, where the fraudulent product risk ratio is the ratio of the number of products with abnormal transactions posing a fraudulent risk in the corresponding store to the total number of valid products in the store;

[0090] For each of the two risky stores in a pair of suspected risky stores that meet the first similarity judgment criteria, fraud risk labels are extracted for all valid products in each risky store. These fraud risk labels are generated using a pre-trained fraud risk detection model. Based on the fraud risk labels, the number of fraudulent products in each store is counted and categorized by product category. For example, fraudulent products in risky store A are primarily distributed in the categories of "Luxury Goods" (30 items), "Electronic Products" (20 items), and "Health Products" (10 items); while fraudulent products in risky store B are primarily distributed in the categories of "Luxury Goods" (25 items), "Electronic Products" (15 items), and "Virtual Goods" (10 items). Multiple secondary product categories with a high number of fraudulent products are selected, for example, the top three categories are selected as the secondary product categories. Simultaneously, the fraud product risk ratio for each store is calculated: that is, the ratio of the number of fraudulent products with abnormal transactions in the corresponding store to the total number of valid products in that store.

[0091] Step S5340: Based on the second product category and the risk ratio of the fraudulent product, determine whether the suspected risk store pair meets the preset second similarity judgment condition; if not, filter the corresponding suspected risk store pair from the suspected risk store pair set.

[0092] In one embodiment, for each of the two risky stores in a suspected risky store pair, the difference in the fraudulent product risk ratios of the two stores is calculated, i.e., the absolute value of the difference between the two stores' fraudulent product risk ratios. This difference is then compared with a preset second difference threshold. For example, if the fraudulent product risk ratio of risky store A is 5%, and that of risky store B is 6%, and the difference is 1%, if the preset difference threshold is 2%, then the difference is less than the preset second difference threshold, preliminarily determining that the two stores have similar fraudulent product risk ratios. The fraudulent product category distributions of the two stores are then further analyzed to obtain multiple second product categories with a high number of fraudulent products, and the overlap rate of these second product categories is calculated. For example, if the second product categories of risky store A are "luxury goods," "electronic products," and "health products," and the second product categories of risky store B are "luxury goods," "electronic products," and "virtual goods," and there are two identical categories, and one store has a total of three second product categories, then the overlap rate is 2 / 3, which is approximately 66.7%. Compare the overlap rate with the preset second overlap rate threshold (for example, 60%). If the overlap rate is greater than the preset second overlap rate threshold, it is determined that the two stores are highly similar in the fraudulent product category and meet the second similarity judgment condition. If the difference in the fraudulent product risk ratio and the category overlap rate of the two stores meet the preset conditions, the suspected risk store pair is retained; otherwise, the suspected risk store pair is filtered out from the suspected risk store pair set. For example, if the fraudulent product risk ratio of risk store A is 5%, and the fraudulent product risk ratio of risk store B is 8%, the difference is 3%, which is greater than the preset difference threshold, or the category overlap rate is 50%, which is less than the preset overlap rate threshold, then the suspected risk store pair is filtered out from the suspected risk store pair set. Through the above steps, suspected risk store pairs with high similarity in fraudulent product risk ratio and category distribution can be effectively screened out.

[0093] In this embodiment, by making multi-dimensional similarity judgments based on banned or restricted goods and fraudulent goods, pairs of stores that are highly similar in risk characteristics are further screened out from the set of suspected risky store pairs, significantly improving the accuracy and reliability of risky store cluster detection. This multi-level similarity judgment mechanism not only improves the accuracy of screening, but also avoids the misjudgment that may be caused by single-dimensional judgment. By filtering out suspected risky store pairs that do not meet the similarity conditions, stores that may belong to the same risky station group can be accurately identified, providing more reliable data support for subsequent risky station group detection. This embodiment significantly improves the comprehensiveness and robustness of risky store cluster detection through multi-dimensional and multi-level similarity judgments.

[0094] For further examples, please refer to Figure 5, based on the first product category and the risk ratio of the prohibited or restricted products, determining whether the suspected risky store pair meets a preset first similarity judgment condition includes the following steps:

[0095] Step S5321: Calculate the difference in risk ratio of the suspected risky store to the corresponding two risky stores for banned or restricted goods.

[0096] For each of the two risky stores in a suspected risky store pair, the difference in their banned or restricted goods risk ratios is calculated. This difference, in other words, the absolute value of the difference between the two stores' banned or restricted goods risk ratios, is used to determine whether the two stores are similar. This difference provides a quantitative basis for subsequent similarity assessments, thereby identifying store pairs with consistent banned or restricted goods risk characteristics.

[0097] Step S5322: When the difference is less than a preset difference threshold, obtain the number of identical first product categories of the two risky stores, divide the number by the total number of first product categories corresponding to any of the two risky stores, and obtain the overlap rate of the first product categories of the two risky stores;

[0098] Determine the first commodity categories corresponding to the two risky stores respectively. The first commodity categories are obtained by counting multiple categories with a large number of banned or restricted goods in each store. When the difference is less than the preset difference threshold (referred to as the first difference threshold above), compare the first commodity categories of the two risky stores to find the number of identical categories. Then, divide the number of identical categories by the total number of first commodity categories of any of the two risky stores. Obtain the overlap rate of the first commodity categories of the two risky stores. The overlap rate reflects the degree of similarity between the two stores in the banned or restricted goods categories. The higher the overlap rate, the more similar the distribution of the two stores in the banned or restricted goods categories, thereby providing a quantitative basis for subsequent similarity judgments.

[0099] Step S5323: When the overlap rate is greater than a preset overlap rate threshold, it is determined that the pair of suspected risky stores meets a preset first similarity judgment condition.

[0100] The preset overlap rate threshold is pre-set based on actual business needs and historical data, and is used to measure whether the similarity between two stores in the categories of banned or restricted goods meets acceptable standards. For example, assuming the preset overlap rate threshold is 60%, if the calculated overlap rate of the first product category of the two risky stores is 66.7%, then the overlap rate is greater than the preset overlap rate threshold, indicating that the two stores are highly similar in the distribution of banned or restricted goods categories. At this point, it is determined that the suspected risk store pair meets the preset first similarity judgment condition, that is, the two stores meet the similarity requirements in the risk ratio and category distribution of banned or restricted goods, and thus the store pair is retained for subsequent risk site group detection and analysis.

[0101] In this embodiment, by calculating the difference in the risk ratio of banned or restricted goods and the overlap rate of the first product category between two stores in a suspected risky store pair, and performing similarity judgment based on preset difference and overlap thresholds, we retain store pairs with similar risk characteristics and filter out store pairs that do not meet the criteria, significantly improving the accuracy and reliability of screening suspected risky store pairs. This similarity judgment mechanism based on quantitative indicators not only improves the accuracy and objectivity of screening, but also avoids the potential bias caused by subjective judgment.

[0102] For further examples, please refer to Figure 6 Based on the filtered set of suspected risk store pairs, calculating the product similarity coverage rate of the suspected risk store pairs of the corresponding two risk stores, and determining the risky station group stores based on the corresponding product similarity coverage rates of all suspected risk store pairs in the suspected risk store pair set, including the following steps:

[0103] Step S5410: Based on the filtered suspected risk store pairs in the set of suspected risk store pairs, convert all product titles in the two risk stores corresponding to the suspected risk store pairs into vector representations to obtain product title vectors;

[0104] All product titles in the two corresponding risk stores of the suspected risk store are extracted. In one embodiment, the extracted product titles are subjected to text preprocessing, including text cleaning, word segmentation, and removal of stop words. After the preprocessing is completed, the processed product titles are converted into vector representations using a pre-trained natural language processing model (such as Word2Vec, BERT, etc.). For each product title, each word in the title is mapped to a high-dimensional vector through word embedding technology. Then, these word vectors are aggregated into a product title vector of a fixed dimension through weighted averaging or pooling operations (such as mean pooling or maximum pooling). Finally, the generated product title vectors are subjected to L2 normalization processing so that the modulus length of all vectors is 1, ensuring consistency in the subsequent calculation of cosine similarity. Through the above steps, all product titles of each store are converted into vector representations, providing a high-quality vector data foundation for subsequent product similarity calculations and risk site group detection.

[0105] Step S5420: Calculate the cosine similarity between the product title vectors of the two risky stores to obtain a product similarity matrix of the risky stores;

[0106] For each pair of product title vectors in the two risky stores corresponding to the suspected risky store pair, the cosine similarity between the two risky stores is calculated. The formula for calculating cosine similarity is the dot product of the two vectors divided by the product of the corresponding module lengths. The value range is [-1, 1]. The closer the value is to 1, the more similar the semantics of the two product titles are. Specifically, for the i-th product title vector of store A and the j-th product title vector of store B, the cosine similarity is calculated and the result is stored in the i-th row and j-th column of the similarity matrix. By traversing all pairs of product title vectors of the two stores, a product similarity matrix is ​​finally generated, in which each element represents the semantic similarity of the corresponding product title in the two stores.

[0107] Step S5430: Determine the product similarity coverage of the suspected risky store to the corresponding two risky stores based on the product similarity matrix;

[0108] In one embodiment, for each row in the product similarity matrix (i.e., each product title vector of store A), the maximum cosine similarity value between all product title vectors of store A and store B is found, and the maximum value is compared with a preset similarity threshold. If the maximum cosine similarity value is greater than the similarity threshold, it is considered that the product of store A is semantically highly similar to a product in store B, and is included in the number of similar products. Then, the number of all similar products that meet the conditions in store A is counted, and the number of similar products is divided by the total number of products in store A to obtain the product similarity coverage rate of store A relative to store B. Similarly, for each column in the product similarity matrix (i.e., each product title vector of store B), the maximum cosine similarity value between all product title vectors of store B and store A is found, and the same comparison and statistics are performed to obtain the product similarity coverage rate of store B relative to store A. Finally, the product similarity coverage rates of the two stores are comprehensively calculated (such as taking the average or weighted average) to obtain the product similarity coverage rate of the suspected risk store to the corresponding two risk stores. The product similarity coverage rate reflects the overall similarity in the semantics of the product titles of the two stores, providing an important quantitative basis for subsequent risk site cluster detection.

[0109] Step S5440: Mark each store in the set of suspected risk store pairs as a node in the risk site group store graph. When the product similarity coverage is greater than a preset coverage threshold, establish an edge connection between the corresponding two stores to form a risk site group store graph for determining the risk site group to which the store belongs.

[0110] All the stores in the set of suspected risk store pairs are taken as nodes to construct an initial undirected graph, where each node represents a risk store. Traverse all suspected risk store pairs, obtain the corresponding product similarity coverage for each pair of stores, and compare the product similarity coverage with the preset coverage threshold. If the product similarity coverage is greater than the preset coverage threshold, an undirected edge is established between the corresponding store nodes, indicating that the two stores have a high degree of similarity in product semantics and may belong to the same risk station group. By traversing all store pairs and completing the edge connection, a risk station group store graph is finally constructed. The nodes in the graph represent risk stores, and the edges represent the semantic similarity of products between stores. Through graph analysis algorithms (such as community detection algorithms), the densely connected subgraphs in the graph can be further identified to determine the potential risk station group store set.

[0111] In this embodiment, by converting the product titles of risky stores into vector representations, and calculating the product similarity coverage between stores based on the product title vectors, and then constructing a risk site group store map, a screening mechanism based on product similarity coverage can effectively identify suspected risk store pairs that are highly similar in product operation characteristics, thereby more accurately locating risk store site groups that may be operated by the same entity or related entities.

[0112] For further examples, please refer to Figure 7 , based on the product similarity matrix, determining the product similarity coverage rate of the suspected risk store to the corresponding two risk stores, including:

[0113] Step S5431: Determine the maximum cosine similarity value of each row in the product similarity matrix, and compare the maximum cosine similarity value with a preset similarity threshold;

[0114] In one embodiment, for each row in the product similarity matrix (i.e., each product title vector of store A), all matrix elements in the row are traversed to determine the maximum cosine similarity value between all product title vectors of store A and store B. The maximum cosine similarity value represents the highest degree of semantic similarity between the current product of store A and a product in store B. The maximum cosine similarity value found is then compared with a preset similarity threshold. The preset similarity threshold is pre-set based on actual business needs and historical data, and is used to measure whether the two product titles have a sufficiently high semantic similarity. If the maximum cosine similarity value is greater than the preset similarity threshold, it is considered that the product of store A and a product in store B are highly similar in semantics, and are included in the subsequent statistics of the number of similar products; otherwise, it is considered that the product and the product in store B do not have a sufficiently high semantic similarity and are not counted.

[0115] Step S5432: Count the number of times the maximum cosine similarity value is greater than the similarity threshold, divide the number by the total number of products in any of the two risky stores, and obtain the product similarity coverage rate of the suspected risky store to the corresponding two risky stores.

[0116] In one embodiment, through the comparison in the previous step, the number of stores A and B whose maximum cosine similarity is greater than the similarity threshold is counted, and the number is divided by the total number of products in store A to obtain the corresponding product similarity coverage. Similarly, for each column in the product similarity matrix, the number of times the corresponding maximum cosine similarity value is greater than the preset similarity threshold is counted, that is, the number of products in store B that are highly similar in semantics to those in store A, and the number is divided by the total number of products in store B to obtain the product similarity coverage of store B relative to store A. Finally, the product similarity coverage of the two stores is comprehensively calculated (such as taking the average or weighted average) to obtain the product similarity coverage of the suspected risk store to the corresponding two risk stores.

[0117] In this embodiment, by calculating the maximum cosine similarity of each row in the product similarity matrix and comparing it with the preset similarity threshold, it is possible to accurately identify product pairs in two stores that are highly similar in product title semantics, and count the number of stores whose maximum cosine similarity is greater than the similarity threshold. Based on the statistical results, the product similarity coverage is calculated, and the overall similarity in product semantics between the two stores can be quantified. Since risky station cluster stores are often operated by the same entity or related entities, the corresponding product selection strategies, operating models, and target customer groups are highly consistent, that is, the products on the shelves show significant convergence in categories, titles, descriptions, and functions. This embodiment quantifies the similarity of product titles between two stores through product similarity coverage, thereby determining the correlation between the two stores and more accurately locating potential risky station clusters.

[0118] See also Figure 8, a risky store cluster detection device provided to meet one of the purposes of the present application is a functional embodiment of the risky store cluster detection method of the present application. On the other hand, the device is a risky store cluster detection device provided to meet one of the purposes of the present application, including a risky store marking module 5100, a risky store pair composition module 5200, a risky store pair filtering module 5300 and a risky store cluster determination module 5400, wherein the risky store marking module 5100 is used to mark the store as a risky store when the number of abnormally traded goods in the store meets the preset conditions, and collect multiple risky stores to form a risky store set; the risky store pair composition module 5200 is used to calculate the ratio of the total number of goods in each of the risky stores in the risky store set, When the ratio of the total number of goods is within a preset ratio interval, the corresponding two risk stores are marked as suspected risk store pairs, and the suspected risk store pairs are used to constitute a suspected risk store pair set; a risk store pair filtering module 5300 is used to filter out some of the suspected risk store pairs from the suspected risk store pair set based on the number of goods of the abnormal transaction goods corresponding to the suspected risk store pairs and a preset similarity judgment rule; a risk store station group determination module 5400 is used to calculate the product similarity coverage rate of the two risk stores corresponding to the suspected risk store pair based on the filtered suspected risk store pair set, and determine the risk station group stores based on the corresponding product similarity coverage rates of all suspected risk store pairs in the suspected risk store pair set.

[0119] In a further embodiment, the risky store marking module 5100 includes: a product title acquisition submodule, which is used to obtain the product titles of all valid products in the store, and the product titles include the product main title and the product subtitle; a prohibited and restricted sale risk determination submodule, which is used to input the product title into a pre-trained prohibited and restricted sale risk detection model to determine whether the valid product corresponding to the product title has the prohibited and restricted sale risk, and the valid product with prohibited and restricted sale risk is characterized as a product that is restricted or prohibited from sale by the e-commerce platform where the store is located; a prohibited and restricted sale product ratio calculation submodule, which is used to count the number of products with abnormal transactions in the store that have the prohibited and restricted sale risk, and obtain the prohibited and restricted sale product ratio of the store based on the number of products with abnormal transactions and the total number of valid products in the store; a risky store marking submodule, which is used to mark the store as a risky store when the proportion of prohibited and restricted sales products is greater than a preset ratio threshold, and collect multiple risky stores to form a risky store set.

[0120] In a further embodiment, the risky store marking module 5100 includes: a product price acquisition submodule, which is used to obtain the product prices of all valid products in the store and a preset standard price library; a fraud risk determination submodule, which is used to use a fraud risk detection model to determine whether the product price of each of the valid products is falsely low based on the preset standard price library. When the product price is falsely low, the valid product corresponding to the product price is confirmed to have a fraud risk, and the valid product is marked as an abnormal transaction product; a risky store determination submodule, which is used to count the number of abnormal transaction products with fraud risks in the store, and determine whether the corresponding store is a risky store based on the number of the abnormal transaction products and the preset conditions, and collect multiple risky stores to form a risky store set.

[0121] In a further embodiment, the risk store pair filtering module 5300 includes: a first commodity category acquisition submodule, for obtaining the prohibited and restricted commodity categories of the two risk stores based on the two risk stores corresponding to the suspected risk store pair, including multiple first commodity categories with a large number of commodities and the prohibited and restricted commodity risk ratios; a first risk store pair filtering submodule, for determining whether the suspected risk store pair meets the preset first similarity judgment condition based on the first commodity category and the prohibited and restricted commodity risk ratios, and if not, filtering the corresponding suspected risk store pair from the suspected risk store pair set; a second commodity category acquisition submodule, for when the suspected risk store pair meets the preset first similarity judgment condition When a store meets the preset first similarity judgment condition, based on the corresponding two risk stores of the suspected risk store pair, the fraudulent product categories of the two risk stores are obtained, including multiple second product categories with a large number of products and the fraudulent product risk ratio. The fraudulent product risk ratio is the ratio of the number of products with abnormal transactions with fraud risks in the corresponding store to the total number of valid products in the store; the second risk store pair filtering submodule is used to determine whether the suspected risk store pair meets the preset second similarity judgment condition based on the second product category and the fraudulent product risk ratio. If not, the corresponding suspected risk store pair will be filtered out of the suspected risk store pair set.

[0122] In a further embodiment, the first risk store pair filtering submodule includes: a proportion difference calculation submodule, which is used to calculate the difference in the risk proportion of banned and restricted goods of the suspected risk store to the corresponding two risk stores; an overlap rate calculation submodule, which is used to obtain the number of the same first product categories of the two risk stores when the difference is less than a preset difference threshold, and divide the number by the total number of first product categories corresponding to any of the two risk stores to obtain the overlap rate of the first product categories of the two risk stores; a condition compliance judgment submodule, which is used to determine that the suspected risk store pair meets the preset first similarity judgment condition when the overlap rate is greater than the preset overlap rate threshold.

[0123] In a further embodiment, the risky store station group determination module 5400 includes: a product title vector conversion submodule, which is used to convert all product titles in the two risk stores corresponding to the suspected risk store pair into vector representations based on the suspected risk store pairs in the filtered suspected risk store pair set, to obtain a product title vector; a product similarity matrix determination submodule, which is used to calculate the cosine similarity between the product title vectors of the two risk stores, to obtain the product similarity matrix of the risk store; a product similarity coverage rate determination submodule, which is used to determine the product similarity coverage rate of the two risk stores corresponding to the suspected risk store pair based on the product similarity matrix; a risk station group store graph determination submodule, which is used to mark each store in the suspected risk store pair set as a node in the risk station group store graph, and when the product similarity coverage rate is greater than the preset coverage rate threshold, establish an edge connection between the corresponding two stores to form a risk station group store graph for determining the risk station group to which the store belongs.

[0124] In a further embodiment, the product similarity coverage determination submodule includes: a cosine similarity comparison submodule, used to determine the maximum cosine similarity of each row in the product similarity matrix, and compare the maximum cosine similarity with a preset similarity threshold; a product similarity coverage calculation submodule, used to count the number of the maximum cosine similarity values ​​greater than the similarity threshold, and divide the number by the total number of products in any of the two risk stores to obtain the product similarity coverage of the suspected risk store to the corresponding two risk stores.

[0125] In order to solve the above technical problems, the embodiment of the present application also provides a computer device. Figure 9As shown, a schematic diagram of the internal structure of a computer device. The computer device includes a processor, a computer-readable storage medium, a memory, and a network interface connected via a system bus. Among them, the computer-readable storage medium of the computer device stores an operating system, a database, and computer-readable instructions. The database may store a control information sequence. When the computer-readable instructions are executed by the processor, the processor may implement a risky store cluster detection method. The processor of the computer device is used to provide computing and control capabilities to support the operation of the entire computer device. The memory of the computer device may store computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor may execute the risky store cluster detection method of the present application. The network interface of the computer device is used to connect and communicate with the terminal. Those skilled in the art will understand that Figure 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0126] In this embodiment, the processor is used to execute Figure 8 The memory stores the program code and various data required to execute the modules and submodules in the device. The network interface is used to transmit data between user terminals or servers. The memory in this embodiment stores the program code and data required to execute all modules / submodules in the risky store cluster detection device of this application. The server can call the server's program code and data to execute the functions of all submodules.

[0127] The present application also provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the risky store cluster detection method of any embodiment of the present application.

[0128] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments of the present application can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The aforementioned storage medium can be a computer-readable storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0129] Those skilled in the art will understand that the various operations, methods, steps, measures, and schemes in the processes discussed in this application may be interchanged, changed, combined, or deleted. Furthermore, other steps, measures, and schemes in the various operations, methods, and processes discussed in this application may also be interchanged, changed, rearranged, decomposed, combined, or deleted. Furthermore, the steps, measures, and schemes in the various operations, methods, and processes in the prior art that are open source and disclosed in this application may also be interchanged, changed, rearranged, decomposed, combined, or deleted.

[0130] The above description is only part of the implementation methods of the present application. 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 application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for detecting risky store clusters, characterized in that: The steps include: When the number of abnormally traded goods in a store meets the preset conditions, the store is marked as a risky store, and multiple risky stores are collected to form a risky store set; Calculating the ratio of the total number of goods between each of the risky stores in the risky store set; when the ratio of the total number of goods is within a preset ratio interval, marking the corresponding two risky stores as a suspected risky store pair, and the suspected risky store pair is used to form a suspected risky store pair set; Based on the quantity of the abnormally traded commodities corresponding to the suspected risky store pairs and a preset similarity determination rule, filtering out some of the suspected risky store pairs from the set of suspected risky store pairs; Based on the filtered set of suspected risk store pairs, the product similarity coverage rate of the suspected risk store pairs corresponding to the two risk stores is calculated, and based on the corresponding product similarity coverage rates of all suspected risk store pairs in the set of suspected risk store pairs, the risky site group stores are determined.

2. The method for detecting risky store clusters according to claim 1, characterized in that: When the number of abnormally traded goods in a store meets the preset conditions, the store is marked as a risky store. Multiple risky stores are collected to form a risky store set, including: Get the product titles of all valid products in the store, including the product title and product subtitle; Input the product title into a pre-trained sales restriction risk detection model to determine whether the valid product corresponding to the product title has a sales restriction risk. Valid products with a sales restriction risk are characterized as products that are restricted or prohibited from sale by the e-commerce platform where the store is located; Counting the number of products with abnormal transactions that are at risk of being banned or restricted in sale in the store, and calculating the percentage of banned or restricted products in the store based on the number of products with abnormal transactions and the total number of valid products in the store; When the proportion of the banned or restricted goods is greater than a preset ratio threshold, the store is marked as a risky store, and multiple risky stores are collected to form a risky store set.

3. The risky store cluster detection method according to claim 1 is characterized in that: When the number of abnormally traded goods in a store meets the preset conditions, the store is marked as a risky store. Multiple risky stores are collected to form a risky store set, including: Get the product prices of all valid products in the store and the preset standard price library; A fraud risk detection model is used to determine whether the price of each valid product is artificially low based on a preset standard price library. If the price is artificially low, the valid product corresponding to the price is confirmed to have a fraud risk and is marked as an abnormal transaction product. The number of products with abnormal transactions and fraud risks in the store is counted, and based on the number of products with abnormal transactions and the preset conditions, whether the corresponding store is a risky store is determined, and multiple risky stores are collected to form a risky store set.

4. The method for detecting risky store clusters according to claim 1, characterized in that: Based on the quantity of the abnormally traded commodities corresponding to the suspected risky store pairs and a preset similarity determination rule, filtering out some of the suspected risky store pairs from the set of suspected risky store pairs includes: Based on the suspected risky store and the corresponding two risky stores, obtaining the banned or restricted product categories of the two risky stores, including multiple first product categories with a large number of products, and the risk ratio of banned or restricted products; Based on the first product category and the risk ratio of the prohibited or restricted products, determining whether the suspected risky store pair meets a preset first similarity judgment condition; if not, filtering the corresponding suspected risky store pair from the set of suspected risky store pairs; When the suspected risky store meets the preset first similarity judgment condition, based on the suspected risky store and the corresponding two risky stores, obtain the fraudulent product categories of the two risky stores, including multiple second product categories with a large number of products, and the fraudulent product risk ratio, where the fraudulent product risk ratio is the ratio of the number of products with abnormal transactions that have fraudulent risks in the corresponding store to the total number of valid products in the store; Based on the second product category and the risk ratio of the fraudulent products, determine whether the suspected risk store pair meets the preset second similarity judgment condition; if not, filter the corresponding suspected risk store pair from the suspected risk store pair set.

5. The method for detecting risky store clusters according to claim 4, characterized in that: Based on the first product category and the risk ratio of the prohibited or restricted products, determining whether the suspected risky store pair meets a preset first similarity judgment condition includes: Calculate the difference in the risk ratio of banned or restricted goods sold by the suspected risky store to the corresponding two risky stores; When the difference is less than a preset difference threshold, the number of identical first product categories of the two risky stores is obtained, and the number is divided by the total number of first product categories corresponding to any of the two risky stores to obtain the overlap rate of the first product categories of the two risky stores; When the overlap rate is greater than a preset overlap rate threshold, it is determined that the pair of suspected risky stores meets a preset first similarity judgment condition.

6. The method for detecting risky store clusters according to claim 1, characterized in that: Based on the filtered set of suspected risk store pairs, calculating the product similarity coverage rate of the suspected risk store pairs of the corresponding two risk stores, and determining the risky site group stores based on the corresponding product similarity coverage rates of all suspected risk store pairs in the set of suspected risk store pairs, including: Based on the suspected risky store pairs in the filtered set of suspected risky store pairs, convert all product titles in the two risky stores corresponding to the suspected risky store pairs into vector representations to obtain product title vectors; Calculating the cosine similarity between the product title vectors of the two risky stores to obtain a product similarity matrix of the risky stores; Determining, based on the product similarity matrix, the product similarity coverage rate of the suspected risky store to the corresponding two risky stores; Each store in the set of suspected risk store pairs is marked as a node in the risk station group store graph. When the product similarity coverage is greater than the preset coverage threshold, an edge connection is established between the corresponding two stores to form a risk station group store graph for determining the risk station group to which the store belongs.

7. The method for detecting risky store clusters according to claim 6, characterized in that: Determining the product similarity coverage of the suspected risk store to the corresponding two risk stores based on the product similarity matrix includes: Determining the maximum cosine similarity of each row in the product similarity matrix, and comparing the maximum cosine similarity with a preset similarity threshold; The number of stores whose maximum cosine similarity is greater than the similarity threshold is counted, and the number is divided by the total number of goods in any of the two risk stores to obtain the similarity coverage of goods of the suspected risk store to the corresponding two risk stores.

8. A risky store cluster detection device, characterized in that: include: A risky store marking module is used to mark a store as a risky store when the number of abnormally traded products in the store meets the preset conditions, and collect multiple risky stores to form a risky store set; A risky store pair formation module is used to calculate the ratio of the total number of goods between any two risky stores in the risky store set. When the ratio of the total number of goods is within a preset ratio interval, the corresponding two risky stores are marked as a suspected risky store pair. The suspected risky store pair is used to form a suspected risky store pair set. a risky store pair filtering module, configured to filter out some of the suspected risky store pairs from the set of suspected risky store pairs based on the quantity of the abnormally traded products corresponding to the suspected risky store pairs and a preset similarity determination rule; The risky store cluster determination module is used to calculate the product similarity coverage rate of the suspected risk store pairs corresponding to the two risk stores based on the filtered set of suspected risk store pairs, and determine the risky store cluster based on the corresponding product similarity coverage rate of all suspected risk store pairs in the set of suspected risk store pairs.

9. A computer device comprising a central processing unit and a memory, characterized in that: The central processing unit is configured to call and run a computer program stored in the memory to execute the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that It stores a computer program implemented according to the method described in any one of claims 1 to 7 in the form of computer-readable instructions, and when the computer program is called and executed by a computer, the steps included in the corresponding method are executed.

Images