Offline merchant identification method, device and equipment and storage medium

Abstract

The invention discloses an offline merchant identification method, device and equipment and a storage medium, and relates to the technical field of artificial intelligence, and the method comprises the steps: determining a first preset number of associated transaction objects corresponding to a target merchant; obtaining first transaction data between the first preset number of associated transaction objects and the first target associated merchant; determining a second preset number of associated merchants based on the first transaction data; taking the target merchant and a second preset number of associated merchants as nodes, based on a public transaction object between the target merchant and each associated merchant, constructing an edge between the target merchant and each associated merchant, and obtaining a first target map; inputting the first target map into a merchant type identification network for merchant type identification processing to obtain target type information; and performing offline merchant identification on the target merchant based on the target type information to obtain an offline merchant identification result. According to the technical scheme provided by the invention, the effectiveness and accuracy of offline merchant identification can be improved.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular, to a method, device, equipment and storage medium for identifying offline merchants. Background Art

[0002] In the task of identifying offline merchants, the existing technology generally determines whether a merchant is an offline merchant by searching for the merchant's name on a map and determining whether the merchant has a specific physical store; or by obtaining all the transaction data of the merchant, and determining that the merchant is an offline merchant if more than 70% of the transaction data occurs in the same province. However, if the merchant is a newly established merchant or a small-scale merchant, the merchant may not be found on the map, resulting in the inability to search for it on the map. And due to the existence of a large number of merchants with the same name, it cannot be guaranteed that the merchant found on the map is the merchant whose offline status needs to be determined; or there are online merchants that belong to the same-city service, and the transaction data they generate is concentrated in the same province, resulting in inaccurate determination of offline merchants. Therefore, a solution that can effectively and accurately identify offline merchants is needed. Summary of the Invention

[0003] This application provides a method, device, equipment, storage medium and computer program product for identifying offline merchants, which can improve the effectiveness and accuracy of offline merchant identification.

[0004] On the one hand, this application provides a method for identifying offline merchants, and the method includes:

[0005] Determine a first preset number of associated transaction objects corresponding to the target merchant;

[0006] Obtain first transaction data between the first preset number of associated transaction objects and first target associated merchants corresponding to the first preset number of associated transaction objects, where the first target associated merchants do not include the target merchant;

[0007] Based on the first transaction data, determine a second preset number of associated merchants from the first target associated merchants;

[0008] Taking the target merchant and the second preset number of associated merchants as nodes, and based on the common transaction objects between the target merchant and each associated merchant, construct edges between the target merchant and each associated merchant to obtain a first target graph corresponding to the target merchant; the edge weights corresponding to the edges between the target merchant and each associated merchant represent the distance between the target merchant and each associated merchant;

[0009] Input the first target graph into a merchant type recognition network for merchant type recognition processing to obtain target type information corresponding to the target merchant;

[0010] Based on the target type information, perform offline merchant identification on the target merchant to obtain the offline merchant identification result corresponding to the target merchant.

[0011] On the other hand, an offline merchant identification device is provided, and the device includes:

[0012] A transaction object determination module, configured to determine a first preset number of associated transaction objects corresponding to the target merchant;

[0013] A first transaction data acquisition module, configured to acquire first transaction data between the first preset number of associated transaction objects and a first target associated merchant corresponding to the first preset number of associated transaction objects, where the first target associated merchant does not include the target merchant;

[0014] An associated merchant determination module, configured to determine a second preset number of associated merchants from the first target associated merchants based on the first transaction data;

[0015] A first target graph construction module, configured to use the target merchant and the second preset number of associated merchants as nodes, and based on the common transaction objects between the target merchant and each associated merchant, construct an edge between the target merchant and each associated merchant to obtain a first target graph corresponding to the target merchant; the edge weight corresponding to the edge between the target merchant and each associated merchant represents the distance between the target merchant and each associated merchant;

[0016] A target type information determination module, configured to input the first target graph into a merchant type recognition network for merchant type recognition processing to obtain the target type information corresponding to the target merchant;

[0017] An offline merchant identification result determination module, configured to perform offline merchant identification on the target merchant based on the target type information to obtain the offline merchant identification result corresponding to the target merchant.

[0018] On the other hand, an electronic device is provided, including: a processor;

[0019] A memory for storing executable instructions of the processor;

[0020] Wherein, the processor is configured to execute the instructions to implement the offline merchant identification method described in any one of the above.

[0021] On the other hand, a computer-readable storage medium is provided, and when the instructions in the storage medium are executed by the processor of the electronic device, the electronic device can execute any of the above offline merchant identification methods.

[0022] On the other hand, a computer program product or a computer program is provided. The computer program product or the computer program includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the offline merchant identification method provided in the above various alternative implementation manners.

[0023] The offline merchant identification method, device, equipment, storage medium and computer program product provided by this application have the following technical effects:

[0024] In the process of offline merchant identification in this application, a first preset number of associated transaction objects corresponding to a target merchant to be identified are determined, and first transaction data between the first preset number of associated transaction objects and a first target associated merchant corresponding to the first preset number of associated transaction objects is obtained. The first target associated merchant does not include the target merchant. Then, based on the first transaction data, a second preset number of associated merchants are determined from the first target associated merchants, and edges between the target merchant and each associated merchant are constructed based on the common transaction objects between the target merchant and each associated merchant to obtain a first target graph corresponding to the target merchant. And edge weights representing the distance between the target merchant and each associated merchant are set for the edges between the target merchant and each associated merchant, which can effectively combine different associated merchants to jointly represent the target merchant. Then, the first target graph integrating the associated merchants is input into a merchant type recognition network to perform merchant type recognition processing on the target merchant, and the target type information corresponding to the target merchant can be accurately recognized. Based on the target type information, offline merchant identification is performed on the target merchant, and the offline merchant identification result corresponding to the target merchant can be accurately obtained, greatly improving the effectiveness and accuracy of offline merchant identification. Description of the Drawings

[0025] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of this application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0026] Figure 1 It is a schematic diagram of the application environment of an offline merchant identification method provided by an embodiment of this application;

[0027] Figure 2 It is a schematic flowchart of an offline merchant identification method provided by an embodiment of this application;

[0028] Figure 3 It is a schematic diagram of a first target atlas provided by an embodiment of the present application;

[0029] Figure 4 It is a schematic structural diagram of an offline merchant identification device provided by an embodiment of the present application;

[0030] Figure 5 It is a block diagram of an electronic device for offline merchant identification provided by an embodiment of the present application;

[0031] Figure 6 It is a block diagram of another electronic device for offline merchant identification provided by an embodiment of the present application. Detailed implementation manners

[0032] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0033] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0034] In the embodiments of the present application, the term "module" or "unit" refers to a computer program with a predetermined function or a part of a computer program, which works together with other related parts to achieve a predetermined goal, and can be fully or partially implemented by using software, hardware (such as a processing circuit or a memory), or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be a part of the overall module or unit that includes the function of the module or unit.

[0035] Artificial intelligence uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, including theories, methods, technologies, and application systems that can perceive the environment, acquire knowledge, and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a way similar to human intelligence. Artificial intelligence also studies the design principles and implementation methods of various intelligent machines to enable machines to have the functions of perception, reasoning, and decision-making.

[0036] Artificial intelligence technology is an interdisciplinary subject with a wide range of fields, including both hardware-level and software-level technologies. The basic technologies of artificial intelligence generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, and mechatronics. The software technologies of artificial intelligence mainly include several major directions such as computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0037] The solution provided in the embodiments of this application relates to technologies such as deep learning in artificial intelligence, and will be specifically described through the following embodiments.

[0038] Please refer to Figure 1 , Figure 1 which is a schematic diagram of the application environment of an offline merchant identification method provided in the embodiments of this application. This application environment can at least include a terminal 100 and a server 200.

[0039] In an optional embodiment, the terminal 100 can be used to provide users with an offline merchant identification service. Specifically, the terminal 100 can include, but is not limited to, types of electronic devices such as smartphones, desktop computers, tablet computers, laptop computers, smart speakers, digital assistants, augmented reality (AR) / virtual reality (VR) devices, smart wearable devices, in-vehicle terminals, and smart TVs; it can also be software running on the above-mentioned electronic devices, such as application programs, applets, etc. The operating systems running on the electronic devices in the embodiments of this application can include, but are not limited to, Android systems, IOS systems, Linux, Windows, etc.

[0040] In an optional embodiment, the server 200 can provide background support for the terminal 100. Specifically, it can be used to pre-train a merchant type recognition network, and then can provide background support for the offline merchant identification service on the terminal 100 side in combination with the merchant type recognition network. The server 200 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0041] In addition, it should be noted that Figure 1 The application environment shown is only for an offline merchant identification method, and the embodiments of this specification are not limited thereto.

[0042] In the embodiments of this specification, the above-mentioned terminal 100 and server 200 can be directly or indirectly connected through wired or wireless communication methods, and this application does not limit this.

[0043] The following introduces an offline merchant identification method of this application. Figure 2 It is a schematic flowchart of an offline merchant identification method provided by an embodiment of this application. This specification provides method operation steps such as in the embodiment or flowchart, but based on routine or non-creative labor, there can be more or fewer operation steps. The step order listed in the embodiment is only one way among the execution orders of numerous steps and does not represent the only execution order. When the actual system or server product executes, it can be executed in the order shown in the embodiment or the drawings or executed in parallel (for example, in an environment of parallel processors or multi-threaded processing). Specifically, as Figure 2 shown, the method may include:

[0044] S201: Determine a first preset number of associated transaction objects corresponding to the target merchant;

[0045] In a specific embodiment, the target merchant may be a merchant for which merchant type identification is required. Specifically, the merchant type may include offline merchant types and online merchant types; optionally, the first preset number of associated transaction objects may be transaction objects whose second transaction data with the target merchant satisfies a first preset condition.

[0046] In an optional embodiment, the above-mentioned determining the first preset number of associated transaction objects corresponding to the target merchant includes:

[0047] Determine multiple transaction objects corresponding to the target merchant within a preset historical time period;

[0048] Obtain the second transaction data between the target merchant and each transaction object;

[0049] Determine the transaction objects whose corresponding second transaction data satisfies the first preset condition among the multiple transaction objects as the associated transaction objects.

[0050] In a specific embodiment, the preset historical time period can be set in combination with actual application requirements, such as within the past year. Specifically, the transaction object may be an object (i.e., user account) that conducts transactions with the target merchant.

[0051] In a specific embodiment, the second transaction data may characterize the transaction situation between the target merchant and each transaction object; optionally, the second transaction data may include the number of transactions, transaction amounts, and transaction contents between the target merchant and each transaction object. Optionally, the second transaction data may be set according to actual application requirements. Correspondingly, the first preset condition may be a condition for determining whether the degree of connection between the target merchant and the transaction object is greater than the first preset degree threshold; optionally, when the second transaction data corresponding to the transaction object satisfies the first preset condition, it indicates that the degree of connection between the target merchant and the transaction object is greater than the first preset degree threshold; when the second transaction data corresponding to the transaction object does not satisfy the first preset condition, it indicates that the degree of connection between the target merchant and the transaction object is less than the first preset degree threshold. Correspondingly, the transaction object whose corresponding second transaction data satisfies the first preset condition may be determined as an associated transaction object. Optionally, the first preset condition may be set according to actual application requirements, and the first preset degree threshold may be set according to actual application requirements.

[0052] Optionally, taking the second transaction data as the number of transactions between the target merchant and each transaction object as an example, the first preset condition may be that the number of transactions between the target merchant and each transaction object is greater than the first preset threshold; correspondingly, among multiple transaction objects, the transaction objects whose corresponding number of transactions with the target merchant is greater than the first preset threshold are determined as associated transaction objects; correspondingly, the above-mentioned first preset number of associated transaction objects may be the transaction objects whose number of transactions with the target merchant is greater than the first preset threshold, that is, the first preset number of associated transaction objects are the top first preset number of transaction objects with the most transactions with the target merchant. Optionally, the first preset number may be set according to actual application requirements, and the first preset threshold may be set according to actual application requirements.

[0053] Optionally, taking the second transaction data as the number of transactions and transaction amounts between the target merchant and each transaction object as an example, the first preset condition may be that the number of transactions between the target merchant and each transaction object is greater than the second preset threshold, and at the same time, the transaction amount between the target merchant and each transaction object is greater than the third preset threshold; correspondingly, among multiple transaction objects, the transaction objects whose number of transactions with the target merchant is greater than the second preset threshold and whose transaction amount with the target merchant is greater than the third preset threshold are determined as associated transaction objects; correspondingly, the above-mentioned first preset number of associated transaction objects may be the transaction objects whose number of transactions with the target merchant is greater than the second preset threshold and whose transaction amount with the target merchant is greater than the third preset threshold. Optionally, the second preset threshold may be set according to actual application requirements, and the third preset threshold may be set according to actual application requirements.

[0054] In a specific embodiment, it is possible to determine multiple trading objects corresponding to the target merchant within the past year; obtain the number of transactions between the target merchant and each trading object; and determine the trading objects with the number of transactions greater than the first preset threshold among the multiple trading objects as associated trading objects.

[0055] In the above embodiment, by combining whether the second transaction data between the target merchant and each trading object corresponding to the target merchant within the preset historical time period meets the first preset condition to determine the associated trading objects for subsequent screening of associated merchants, the effectiveness of the associated trading objects can be improved, and thus the effectiveness of subsequent associated merchants can also be improved.

[0056] S203: Obtain the first transaction data between the first preset number of associated trading objects and the first target associated merchants corresponding to the first preset number of associated trading objects, where the first target associated merchants do not include the target merchant;

[0057] In a specific embodiment, the first target associated merchant corresponding to each associated trading object can be the merchant that conducts transactions with each associated trading object. Optionally, the first transaction data can represent the transaction situation between each associated trading object and the first target associated merchant corresponding to each associated trading object; optionally, the first transaction data can include the number of transactions, transaction amount, and transaction content between each associated trading object and the first target associated merchant corresponding to each associated trading object. Optionally, the first transaction data can be set according to actual application requirements.

[0058] S205: Based on the first transaction data, determine the second preset number of associated merchants from the first target associated merchants;

[0059] In a specific embodiment, the second preset number of associated merchants are the first target associated merchants among the first target associated merchants whose first transaction data with the first preset number of associated trading objects meets the second preset condition.

[0060] In an alternative embodiment, the above determining the second preset number of associated merchants from the first target associated merchants based on the first transaction data includes:

[0061] Determine the first target associated merchants whose corresponding first transaction data meets the second preset condition among the first target associated merchants as associated merchants.

[0062] In a specific embodiment, the second preset condition may be a condition for determining whether the degree of closeness between each associated transaction object and the first target associated merchant corresponding to each associated transaction object is greater than a second preset degree threshold; optionally, when the first transaction data corresponding to the first target associated merchant satisfies the second preset condition, it indicates that the degree of closeness between each associated transaction object and the first target associated merchant corresponding to each associated transaction object is greater than the second preset degree threshold; when the first transaction data corresponding to the first target associated merchant does not satisfy the second preset condition, it indicates that the degree of closeness between each associated transaction object and the first target associated merchant corresponding to each associated transaction object is less than the second preset degree threshold. Accordingly, the first target associated merchant whose corresponding first transaction data satisfies the second preset condition can be determined as the associated merchant. Optionally, the second preset condition can be set in combination with the actual application requirements, and the second preset degree threshold can be set in combination with the actual application requirements.

[0063] Optionally, taking the first transaction data as the number of transactions between each associated transaction object and the first target associated merchant corresponding to each associated transaction object as an example, the second preset condition may be that the number of transactions between each associated transaction object and the first target associated merchant corresponding to each associated transaction object is greater than a fourth preset threshold; accordingly, among the first target associated merchants, the first target associated merchants corresponding to each associated transaction object whose corresponding number of transactions with each associated transaction object is greater than the fourth preset threshold are determined as the associated merchants; accordingly, the above-mentioned second preset number of associated merchants may be the first target associated merchants corresponding to each associated transaction object whose number of transactions with each associated transaction object is greater than the fourth preset threshold, that is, the second preset number of associated merchants are the top second preset number of first target associated merchants with the most number of transactions with the first preset number of associated transaction objects. Optionally, the second preset number can be set in combination with the actual application requirements, and the fourth preset threshold can be set in combination with the actual application requirements. Optionally, there are common transaction objects between the second preset number of associated merchants and the target merchant.

[0064] In a specific embodiment, among the first target associated merchants, the first target associated merchants corresponding to each associated transaction object whose corresponding number of transactions with each associated transaction object is greater than the fourth preset threshold are determined as the associated merchants.

[0065] In the above embodiment, by combining whether the first transaction data between each transaction object corresponding to the target merchant and the first target associated merchant corresponding to each transaction object satisfies the second preset condition to determine the associated merchant for constructing the first target graph corresponding to the target merchant subsequently, the effectiveness of the associated merchant can be improved, and thus the accuracy of the subsequent construction of the first target graph can also be improved.

[0066] S207: Using the target merchant and the second preset number of associated merchants as nodes, and based on the common trading objects between the target merchant and each associated merchant, construct edges between the target merchant and each associated merchant to obtain the first target graph corresponding to the target merchant;

[0067] In a specific embodiment, the edge weight corresponding to the edge between the target merchant and each associated merchant can represent the distance between the target merchant and each associated merchant. Optionally, the closer the distance between the target merchant and each associated merchant, the greater the edge weight corresponding to the edge between the target merchant and each associated merchant, that is, the distance between the target merchant and each associated merchant is negatively correlated with the edge weight corresponding to the edge between the target merchant and each associated merchant.

[0068] Optionally, the first target graph can be a graph representing the target relationship between the target merchant and each associated merchant. The target relationship can include the existence of common trading objects between the target merchant and each associated merchant, and the distance situation between the target merchant and each associated merchant (the shorter the edge between the target merchant and each associated merchant, the closer the distance between the target merchant and each associated merchant; the longer the edge between the target merchant and each associated merchant, the farther the distance between the target merchant and each associated merchant).

[0069] In an alternative embodiment, the above-mentioned method of using the target merchant and the second preset number of associated merchants as nodes, and based on the common trading objects between the target merchant and each associated merchant, constructing edges between the target merchant and each associated merchant to obtain the first target graph corresponding to the target merchant may include:

[0070] Obtain the first location information corresponding to the target merchant and the second location information corresponding to each associated merchant;

[0071] According to the first location information and the second location information corresponding to each associated merchant, determine the distance between the target merchant and each associated merchant;

[0072] Based on the distance between the target merchant and each associated merchant, determine the edge weight between the target merchant and each associated merchant;

[0073] Using the target merchant and the second preset number of associated merchants as nodes, and based on the edge weights between the target merchant and each associated merchant, connect the nodes corresponding to the target merchant and each associated merchant to obtain the first target graph.

[0074] In a specific embodiment, the first location information corresponding to the target merchant can represent the longitude and latitude information of the target merchant's occupancy address; the second location information corresponding to each associated merchant can represent the longitude and latitude information of each associated merchant's occupancy address.

[0075] In an optional embodiment, the above first location information includes the first longitude information and the first latitude information of the target merchant. Correspondingly, the first longitude information can represent the longitude information of the location where the target merchant is located, and the first latitude information can represent the latitude information of the location where the target merchant is located; the second location information corresponding to each associated merchant includes the second longitude information and the second latitude information of each associated merchant. Correspondingly, the second longitude information of each associated merchant can represent the longitude information of the location where each associated merchant is located, and the second latitude information of each associated merchant can represent the latitude information of the location where each associated merchant is located;

[0076] The determining of the distance between the target merchant and each associated merchant according to the first location information and the second location information corresponding to each associated merchant includes:

[0077] Obtain the radius of the earth;

[0078] According to the second latitude information and the first latitude information corresponding to each associated merchant, determine the target latitude difference between the target merchant and each associated merchant;

[0079] According to the second longitude information and the first longitude information corresponding to each associated merchant, determine the target longitude difference between the target merchant and each associated merchant;

[0080] Based on the radius of the earth, the first latitude information, the second latitude information corresponding to each associated merchant, the target latitude difference between the target merchant and each associated merchant, and the target longitude difference between the target merchant and each associated merchant, determine the distance between the target merchant and each associated merchant.

[0081] In a specific embodiment, assume that the first longitude information is lon1, the first latitude information is lat1, the second longitude information is lon2, the second latitude information is lat2, and the radius of the earth is r; subtract the second latitude information lat2 corresponding to each associated merchant from the first latitude information lat1 to obtain the target latitude difference between the target merchant and each associated merchant as lat2 - lat1; subtract the second longitude information lon2 corresponding to each associated merchant from the first longitude information lon1 to obtain the target longitude difference between the target merchant and each associated merchant as lon2 - lon1;

[0082] In a specific embodiment, the above determining of the distance between the target merchant and each associated merchant based on the radius of the earth, the first latitude information, the second latitude information corresponding to each associated merchant, the target latitude difference between the target merchant and each associated merchant, and the target longitude difference between the target merchant and each associated merchant can be combined with the following formula:

[0083]

[0084] Wherein, d is the distance between the target merchant and each associated merchant; r is the radius of the earth; lat1 is the first latitude information; lat2 is the second latitude information corresponding to each associated merchant; lat2 - lat1 is the target latitude difference between the target merchant and each associated merchant; lon2 - lon1 is the target longitude difference between the target merchant and each associated merchant.

[0085] Optionally, the formula for determining the distance between the target merchant and each associated merchant can be set according to the actual application.

[0086] In a specific embodiment, the edge weight between the target merchant and each associated merchant can be determined based on the distance between the target merchant and each associated merchant, and can be combined with the following formula:

[0087]

[0088] Wherein, w i is the edge weight between the target merchant and the i-th associated merchant, d i is the distance between the target merchant and the i-th associated merchant, is denoted as the operation with e as the base and the reciprocal of the distance between the target merchant and the i-th associated merchant as the exponent, ∑exp(d j ) is denoted as the sum of the operations with e as the base and the distances between the target merchant and each associated merchant as exponents respectively. α is a preset coefficient used to prevent the problem that when the distance between the target merchant and a certain associated merchant is 0, the corresponding edge weight between the target merchant and the associated merchant is 0. Correspondingly, combining this preset coefficient can improve the effectiveness of determining the edge weight between the target merchant and each associated merchant. Optionally, α can be set according to the actual application requirements. For example, α can be taken as 0.001. Correspondingly, substituting the distances between the target merchant and each associated merchant into the above formula, the edge weights between the target merchant and each associated merchant can be obtained.

[0089] In a specific embodiment, Figure 3 is a schematic diagram of a first target graph provided by an embodiment of the present application; as Figure 3As shown in the figure, the first target graph includes nodes composed of a target merchant, associated merchant 1, associated merchant 2, associated merchant 3, and associated merchant 4. Based on the existence of common trading objects between the target merchant and associated merchant 1, associated merchant 2, associated merchant 3, and associated merchant 4, edges are respectively constructed between the target merchant and associated merchant 1, associated merchant 2, associated merchant 3, and associated merchant 4. And based on the edge weights between the target merchant and associated merchant 1, associated merchant 2, associated merchant 3, and associated merchant 4, the corresponding nodes of the target merchant and associated merchant 1, associated merchant 2, associated merchant 3, and associated merchant 4 are respectively connected. Optionally, the edge weight corresponding to the edge between the target merchant and each associated merchant can represent the distance between the target merchant and each associated merchant. The greater the edge weight between the target merchant and each associated merchant, the closer the distance between the target merchant and each associated merchant, and then the shorter the edge between the target merchant and each associated merchant; the smaller the edge weight between the target merchant and each associated merchant, the farther the distance between the target merchant and each associated merchant, and then the longer the edge between the target merchant and each associated merchant, that is, the length of the edge in the first target graph is negatively correlated with the edge weight. Specifically, as Figure 3 shown, the distance between associated merchant 3 and the target merchant is the closest, and the distance between associated merchant 1 and the target merchant is the farthest.

[0090] In an optional embodiment, the above method further includes:

[0091] Determine at least one pair of associated merchants corresponding to the existence of common trading objects from the second preset number of associated merchants;

[0092] According to the second position information corresponding to the two associated merchants in each pair of associated merchants, determine the distance between the two associated merchants in each pair of associated merchants;

[0093] Based on the distance between the two associated merchants in each pair of associated merchants, determine the edge weight between the two associated merchants in each pair of associated merchants;

[0094] Correspondingly, the above-mentioned obtaining the first target graph with the target merchant and the second preset number of associated merchants as nodes, and connecting the corresponding nodes of the target merchant and each associated merchant based on the edge weight between the target merchant and each associated merchant may include:

[0095] Taking the target merchant and the second preset number of associated merchants as nodes, connecting the corresponding nodes of the target merchant and each associated merchant based on the edge weight between the target merchant and each associated merchant, and connecting the corresponding nodes of each pair of associated merchants based on the edge weight corresponding to each pair of associated merchants, to obtain the first target graph.

[0096] In a specific embodiment, in the first target graph, nodes corresponding to associated merchant pairs with common trading objects can be connected; optionally, based on the common trading objects between each pair of associated merchants, an edge corresponding to each pair of associated merchants can be constructed, and based on the edge weight corresponding to the edge between the two associated merchants in the associated merchant pair, the nodes corresponding to each pair of associated merchants can be connected.

[0097] In the above embodiment, considering that there are common trading objects between the target merchant and each associated merchant, and the edge weight corresponding to the edge between the target merchant and each associated merchant represents the distance between the target merchant and each associated merchant, and there are common trading objects between each pair of associated merchants, and the edge weight corresponding to the edge between each pair of associated merchants represents the distance between the two associated merchants in each pair of associated merchants, a first target graph corresponding to the target merchant is constructed, so as to effectively represent the target merchant based on the first target graph, and further improve the accuracy and effectiveness of the determination of subsequent target type information.

[0098] S209: Input the first target graph into a merchant type recognition network for merchant type recognition processing to obtain target type information corresponding to the target merchant;

[0099] In a specific embodiment, the merchant type recognition network can be a graph neural network used for merchant type recognition processing in combination with the first target graph corresponding to the target merchant. Optionally, the target type information corresponding to the target merchant can be information representing the merchant type to which the target merchant belongs; optionally, the merchant types include online merchant types and offline merchant types. Optionally, the target type information can represent the probability that the target merchant belongs to the offline merchant type. Optionally, if the target merchant belongs to the offline merchant type, correspondingly, the corresponding probability is 1; if the target merchant does not belong to the offline merchant type (i.e., is an online merchant type), correspondingly, the corresponding probability is 0.

[0100] In an alternative embodiment, the above merchant type recognition network is trained in the following manner:

[0101] Obtain multiple pieces of preset type information corresponding to multiple merchant samples;

[0102] Determine the third preset number of sample associated trading objects corresponding to each merchant sample;

[0103] Obtain the third transaction data between the third preset number of sample associated trading objects and the second target associated merchants corresponding to the third preset number of sample associated trading objects, where the second target associated merchants do not include the corresponding merchant samples;

[0104] Based on the third transaction data, determine the fourth preset number of sample associated merchants corresponding to each merchant sample from the second target associated merchants;

[0105] Using each merchant sample and the fourth preset number of sample-associated merchants corresponding to each merchant sample as nodes, and based on the common trading objects between each merchant sample and each sample-associated merchant corresponding to each merchant sample, construct edges between each merchant sample and each sample-associated merchant corresponding to each merchant sample to obtain a second target graph corresponding to each merchant sample;

[0106] Input the second target graph corresponding to each merchant sample into the graph neural network to be trained for merchant type recognition processing to obtain the predicted type information corresponding to each merchant sample;

[0107] According to the multiple predicted type information corresponding to multiple merchant samples and multiple preset type information, train the graph neural network to be trained to obtain a merchant type recognition network.

[0108] In a specific embodiment, the preset type information may be information representing the merchant type to which the merchant sample belongs. Optionally, the preset type information may represent the probability that the merchant type to which the merchant sample belongs is an offline merchant type. Optionally, if the merchant type to which the merchant sample belongs is an offline merchant type, correspondingly, the corresponding probability is 1; if the merchant type to which the merchant sample belongs is not an offline merchant type (i.e., an online merchant type), correspondingly, the corresponding probability is 0.

[0109] In a specific embodiment, using each merchant sample and the fourth preset number of sample-associated merchants corresponding to each merchant sample as nodes, and based on the common trading objects between each merchant sample and each sample-associated merchant corresponding to each merchant sample, construct edges between each merchant sample and each sample-associated merchant corresponding to each merchant sample to obtain a second target graph corresponding to each merchant sample. For the specific refinement, reference can be made to the relevant refinement of using a target merchant and the second preset number of associated merchants as nodes, and based on the common trading objects between the target merchant and each associated merchant, constructing edges between the target merchant and each associated merchant to obtain a first target graph corresponding to the target merchant, which will not be elaborated here.

[0110] In a specific embodiment, the graph neural network to be trained may be a graph neural network for combining the second target graph of the merchant sample for merchant type recognition processing. Specifically, the network structure of the graph neural network to be trained can be set according to actual application requirements. Optionally, the predicted type information may be information representing the merchant type to which the merchant sample recognized by the graph neural network to be trained belongs. Optionally, the predicted type information may represent the probability that the merchant type to which the merchant sample recognized by the graph neural network to be trained belongs is an offline merchant type.

[0111] In a specific embodiment, training the graph neural network to be trained based on the multiple prediction type information and multiple preset type information corresponding to multiple merchant samples to obtain a merchant type recognition network may include: determining a merchant type loss according to the multiple prediction type information and multiple preset type information corresponding to the multiple merchant samples; and training the graph neural network to be trained based on the merchant type loss to obtain a merchant type recognition network.

[0112] In a specific embodiment, the merchant type loss can be calculated in combination with a preset loss function; optionally, the preset loss function can be set according to actual application requirements, such as an exponential loss function, a cross-entropy loss function, etc. The above merchant type loss can represent the accuracy of the merchant type recognition of the current graph neural network to be trained. Optionally, the above training the graph neural network to be trained based on the merchant type loss to obtain a merchant type recognition network may include: updating the network parameters of the graph neural network to be trained based on the merchant type loss, and based on the updated graph neural network to be trained, repeating the above training iteration steps from inputting the second target graph corresponding to each merchant sample into the graph neural network to be trained for merchant type recognition processing to obtain the prediction type information corresponding to each merchant sample to updating the network parameters of the graph neural network to be trained based on the merchant type loss until a preset training convergence condition is met.

[0113] The above-mentioned meeting the preset training convergence condition may be that the recognition loss information is less than or equal to a preset loss threshold, or the number of training iteration steps reaches a preset number, etc. Specifically, the preset loss threshold and the preset number can be set according to the network accuracy and training speed requirements in actual applications.

[0114] In the above embodiment, inputting the first target graph into the merchant type recognition network and performing merchant type recognition processing on the target network can improve the accuracy of determining the target type information corresponding to the target merchant; and further improve the accuracy of determining the offline merchant recognition result corresponding to the subsequent target merchant.

[0115] S2011: Based on the target type information, perform offline merchant recognition on the target merchant to obtain an offline merchant recognition result corresponding to the target merchant.

[0116] In a specific embodiment, the offline merchant recognition result may be a result representing the merchant type to which the target merchant belongs. Optionally, the target type information may represent the probability that the merchant type to which the target merchant belongs is an offline merchant type. Correspondingly, when the target type information is greater than a preset probability threshold, the target merchant is an offline merchant; optionally, the preset probability threshold can be set according to actual application requirements.

[0117] As can be seen from the technical solutions provided in the embodiments of this specification above, in the process of offline merchant recognition in this specification, a first preset number of associated transaction objects corresponding to the target merchant to be recognized are determined, and first transaction data between the first preset number of associated transaction objects and the first target associated merchants corresponding to the first preset number of associated transaction objects is obtained. The first target associated merchants do not include the target merchant. Then, based on the first transaction data, a second preset number of associated merchants are determined from the first target associated merchants, and taking the target merchant and the second preset number of associated merchants as nodes, edges between the target merchant and each associated merchant are constructed based on the common transaction objects between the target merchant and each associated merchant, obtaining a first target graph corresponding to the target merchant, and an edge weight representing the distance between the target merchant and each associated merchant is set for the edges between the target merchant and each associated merchant, which can effectively combine different associated merchants to jointly represent the target merchant. Then, the first target graph integrating the associated merchants is input into a merchant type recognition network to perform merchant type recognition processing on the target merchant, the target type information corresponding to the target merchant can be accurately recognized, and based on the target type information, offline merchant recognition is performed on the target merchant, and the offline merchant recognition result corresponding to the target merchant can be accurately obtained, greatly improving the effectiveness and accuracy of offline merchant recognition.

[0118] An embodiment of this application also provides an offline merchant recognition device. Correspondingly, Figure 4 is a schematic structural diagram of an offline merchant recognition device provided by an embodiment of this application; as Figure 4 shown, the above device includes:

[0119] An associated transaction object determination module 410, configured to determine a first preset number of associated transaction objects corresponding to the target merchant;

[0120] A first transaction data acquisition module 420, configured to acquire first transaction data between the first preset number of associated transaction objects and the first target associated merchants corresponding to the first preset number of associated transaction objects, where the first target associated merchants do not include the target merchant;

[0121] An associated merchant determination module 430, configured to determine a second preset number of associated merchants from the first target associated merchants based on the first transaction data;

[0122] A first target graph construction module 440, configured to take the target merchant and the second preset number of associated merchants as nodes, and construct edges between the target merchant and each associated merchant based on the common transaction objects between the target merchant and each associated merchant, obtaining a first target graph corresponding to the target merchant; the edge weight corresponding to the edge between the target merchant and each associated merchant represents the distance between the target merchant and each associated merchant;

[0123] A target type information determining module 450, configured to input the first target graph into a merchant type recognition network for merchant type recognition processing to obtain target type information corresponding to the target merchant;

[0124] An offline merchant recognition result determining module 460, configured to perform offline merchant recognition on the target merchant based on the target type information to obtain an offline merchant recognition result corresponding to the target merchant.

[0125] In an optional embodiment, the first target graph construction module 440 includes:

[0126] A location information obtaining unit, configured to obtain first location information corresponding to the target merchant and second location information corresponding to each associated merchant;

[0127] A distance determining unit, configured to determine a distance between the target merchant and each associated merchant according to the first location information and the second location information corresponding to each associated merchant;

[0128] An edge weight determining unit, configured to determine an edge weight between the target merchant and each associated merchant based on the distance between the target merchant and each associated merchant;

[0129] A first target graph construction unit, configured to use the target merchant and the second preset number of associated merchants as nodes, and connect the nodes corresponding to the target merchant and each associated merchant based on the edge weight between the target merchant and each associated merchant to obtain the first target graph.

[0130] In an optional embodiment, the apparatus further includes:

[0131] An associated merchant pair determining unit, configured to determine at least one associated merchant pair corresponding to a common transaction object from the second preset number of associated merchants;

[0132] The distance determining unit is further configured to determine a distance between the two associated merchants in each associated merchant pair according to the second location information corresponding to the two associated merchants in each associated merchant pair;

[0133] The edge weight determining unit is further configured to determine an edge weight between the two associated merchants in each associated merchant pair based on the distance between the two associated merchants in each associated merchant pair;

[0134] The first target graph construction unit is specifically configured to:

[0135] Taking the target merchant and the second preset number of associated merchants as nodes, and based on the edge weights between the target merchant and each associated merchant, connecting the nodes corresponding to the target merchant and each associated merchant, and based on the edge weights corresponding to each pair of associated merchants, connecting the nodes corresponding to each pair of associated merchants, to obtain the first target graph.

[0136] In an alternative embodiment, the first location information includes the first longitude information and the first latitude information of the target merchant; the second location information corresponding to each associated merchant includes the second longitude information and the second latitude information of each associated merchant;

[0137] The distance determination unit is specifically configured to:

[0138] Obtain the radius of the earth;

[0139] According to the second latitude information corresponding to each associated merchant and the first latitude information, determine the target latitude difference between the target merchant and each associated merchant;

[0140] According to the second longitude information corresponding to each associated merchant and the first longitude information, determine the target longitude difference between the target merchant and each associated merchant;

[0141] Based on the radius of the earth, the first latitude information, the second latitude information corresponding to each associated merchant, the target latitude difference between the target merchant and each associated merchant, and the target longitude difference between the target merchant and each associated merchant, determine the distance between the target merchant and each associated merchant.

[0142] In an alternative embodiment, the associated transaction object determination module 410 includes:

[0143] A transaction object determination unit, configured to determine a plurality of transaction objects corresponding to the target merchant within a preset historical time period;

[0144] A second transaction data acquisition unit, configured to acquire second transaction data between the target merchant and each transaction object;

[0145] An associated transaction object determination unit, configured to determine, from the plurality of transaction objects, the transaction objects for which the corresponding second transaction data satisfies a first preset condition as the associated transaction objects.

[0146] In an alternative embodiment, the associated merchant determination module 430 includes:

[0147] An associated merchant determination unit, configured to determine, among the first target associated merchants, the first target associated merchants for which the corresponding first transaction data satisfies a second preset condition as the associated merchants.

[0148] In an optional embodiment, the apparatus further includes a merchant type recognition network training module, specifically including:

[0149] A preset type information acquisition unit, configured to acquire a plurality of preset type information corresponding to a plurality of merchant samples;

[0150] A sample associated transaction object determination unit, configured to determine a third preset number of sample associated transaction objects corresponding to each merchant sample;

[0151] A third transaction data acquisition unit, configured to acquire third transaction data between the third preset number of sample associated transaction objects and second target associated merchants corresponding to the third preset number of sample associated transaction objects, where the second target associated merchants do not include the corresponding merchant samples;

[0152] A sample associated merchant determination unit, configured to determine, based on the third transaction data, a fourth preset number of sample associated merchants corresponding to each merchant sample from the second target associated merchants;

[0153] A second target graph construction unit, configured to use each merchant sample and the fourth preset number of sample associated merchants corresponding to each merchant sample as nodes, and based on the common transaction objects between each merchant sample and each sample associated merchant corresponding to each merchant sample, construct edges between each merchant sample and each sample associated merchant corresponding to each merchant sample, to obtain a second target graph corresponding to each merchant sample;

[0154] A predicted type information determination unit, configured to input the second target graph corresponding to each merchant sample into a graph neural network to be trained for merchant type recognition processing, to obtain predicted type information corresponding to each merchant sample;

[0155] A merchant type recognition network training unit, configured to train the graph neural network to be trained according to the plurality of predicted type information corresponding to the plurality of merchant samples and the plurality of preset type information, to obtain the merchant type recognition network.

[0156] Regarding the apparatus in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated herein.

[0157] Figure 5It is a block diagram of an electronic device provided by an embodiment of the present application for offline merchant identification. The electronic device may be a terminal, and its internal structure diagram may be as shown in Figure 5 shown. The electronic device includes a processor, a memory, a network interface, a display screen, and an input device connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a method for offline merchant identification. The display screen of the electronic device may be a liquid crystal display screen or an electronic ink display screen. The input device of the electronic device may be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the electronic device, or an external keyboard, touchpad, or mouse, etc.

[0158] Figure 6 It is a block diagram of another electronic device provided by an embodiment of the present application for offline merchant identification. The electronic device may be a server, and its internal structure diagram may be as shown in Figure 6 shown. The electronic device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a method for offline merchant identification.

[0159] Those skilled in the art can understand that Figure 5 or Figure 6 the structures shown in do not constitute a limitation on the electronic devices to which the present disclosure solution is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0160] In an exemplary embodiment, an electronic device is further provided, including: a processor; a memory for storing executable instructions of the processor; wherein, the processor is configured to execute the instructions to implement offline merchant identification as in the embodiments of the present disclosure.

[0161] In an exemplary embodiment, a computer-readable storage medium is further provided. When instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform offline merchant identification in the embodiments of the present disclosure.

[0162] In an exemplary embodiment, a computer program product or a computer program is further provided. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the offline merchant identification provided in the above various optional implementation manners.

[0163] It can be understood that in the specific implementation manners of the present application, data related to users is involved. When the above embodiments of the present application are applied to specific products or technologies, user permission or consent needs to be obtained, and the collection, use, and processing of relevant data need to comply with relevant laws, regulations, and standards of relevant countries and regions.

[0164] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above various methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0165] Other embodiments of the present disclosure will be readily apparent to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include known common general knowledge or conventional technical means in the technical field not disclosed in the present disclosure. The specification and examples are only to be considered as exemplary, and the true scope and spirit of the present disclosure are pointed out by the claims.

[0166] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is only limited by the appended claims.

Claims

1. An offline merchant identification method, characterized in that, The method includes: Determine a first preset number of associated transaction objects corresponding to the target merchant; Obtain first transaction data between the first preset number of associated transaction objects and first target associated merchants corresponding to the first preset number of associated transaction objects, where the first target associated merchants do not include the target merchant; Based on the first transaction data, determine a second preset number of associated merchants from the first target associated merchants; Using the target merchant and the second preset number of associated merchants as nodes, based on the common transaction objects between the target merchant and each associated merchant, construct edges between the target merchant and each associated merchant to obtain a first target graph corresponding to the target merchant; the edge weights corresponding to the edges between the target merchant and each associated merchant represent the distance between the target merchant and each associated merchant; Input the first target graph into a merchant type recognition network for merchant type recognition processing to obtain target type information corresponding to the target merchant; Based on the target type information, perform offline merchant recognition on the target merchant to obtain an offline merchant recognition result corresponding to the target merchant.

2. The offline merchant identification method according to claim 1, wherein The step of using the target merchant and the second preset number of associated merchants as nodes, based on the common transaction objects between the target merchant and each associated merchant, constructing edges between the target merchant and each associated merchant to obtain a first target graph corresponding to the target merchant includes: Obtain first location information corresponding to the target merchant and second location information corresponding to each associated merchant; According to the first location information and the second location information corresponding to each associated merchant, determine the distance between the target merchant and each associated merchant; Based on the distance between the target merchant and each associated merchant, determine the edge weight between the target merchant and each associated merchant; Using the target merchant and the second preset number of associated merchants as nodes, and based on the edge weights between the target merchant and each associated merchant, connect the nodes corresponding to the target merchant and each associated merchant to obtain the first target graph.

3. The offline merchant identification method according to claim 2, wherein, The method further includes: Determine at least one pair of associated merchants corresponding to the existence of common transaction objects from the second preset number of associated merchants; According to the second location information corresponding to the two associated merchants in each pair of associated merchants, determine the distance between the two associated merchants in each pair of associated merchants; Based on the distance between the two associated merchants in each pair of associated merchants, determine the edge weight between the two associated merchants in each pair of associated merchants; The step of using the target merchant and the second preset number of associated merchants as nodes, and based on the edge weights between the target merchant and each associated merchant, connecting the nodes corresponding to the target merchant and each associated merchant to obtain the first target graph includes: Taking the target merchant and the second preset number of associated merchants as nodes, and based on the edge weights between the target merchant and each associated merchant, connecting the nodes corresponding to the target merchant and each associated merchant, and based on the edge weights corresponding to each pair of associated merchants, connecting the nodes corresponding to each pair of associated merchants, to obtain the first target graph.

4. The offline merchant identification method according to claim 2, wherein The first location information includes the first longitude information and the first latitude information of the target merchant; the second location information corresponding to each associated merchant includes the second longitude information and the second latitude information of each associated merchant; The determining the distance between the target merchant and each associated merchant according to the first location information and the second location information corresponding to each associated merchant includes: Obtaining the radius of the earth; According to the second latitude information corresponding to each associated merchant and the first latitude information, determining the target latitude difference between the target merchant and each associated merchant; According to the second longitude information corresponding to each associated merchant and the first longitude information, determining the target longitude difference between the target merchant and each associated merchant; Based on the radius of the earth, the first latitude information, the second latitude information corresponding to each associated merchant, the target latitude difference between the target merchant and each associated merchant, and the target longitude difference between the target merchant and each associated merchant, determining the distance between the target merchant and each associated merchant.

5. The offline merchant identification method according to any one of claims 1 to 4, characterized in that, The determining the first preset number of associated transaction objects corresponding to the target merchant includes: Determining a plurality of transaction objects corresponding to the target merchant within a preset historical time period; Obtaining the second transaction data between the target merchant and each transaction object; Determining the transaction objects corresponding to the second transaction data satisfying the first preset condition among the plurality of transaction objects as the associated transaction objects.

6. The offline merchant identification method according to any one of claims 1 to 4, characterized in that, The determining the second preset number of associated merchants from the first target associated merchants based on the first transaction data includes: Determining the first target associated merchants corresponding to the first transaction data satisfying the second preset condition among the first target associated merchants as the associated merchants.

7. The offline merchant identification method according to any one of claims 1 to 4, characterized in that The merchant type recognition network is trained in the following manner: Obtaining a plurality of preset type information corresponding to a plurality of merchant samples; Determining the third preset number of sample associated transaction objects corresponding to each merchant sample; Obtaining the third transaction data between the third preset number of sample associated transaction objects and the second target associated merchants corresponding to the third preset number of sample associated transaction objects, where the second target associated merchants do not include the corresponding merchant samples; Based on the third transaction data, determining the fourth preset number of sample associated merchants corresponding to each merchant sample from the second target associated merchants; Using each merchant sample and the fourth preset number of sample associated merchants corresponding to each merchant sample as nodes, and based on the common trading objects between each merchant sample and each sample associated merchant corresponding to each merchant sample, construct edges between each merchant sample and each sample associated merchant corresponding to each merchant sample to obtain a second target graph corresponding to each merchant sample; Input the second target graph corresponding to each merchant sample into a graph neural network to be trained for merchant type recognition processing to obtain predicted type information corresponding to each merchant sample; Train the graph neural network to be trained according to the multiple predicted type information corresponding to the multiple merchant samples and the multiple preset type information to obtain the merchant type recognition network.

8. An offline merchant identification device, characterized in that, The device includes: A trading object determination module, configured to determine a first preset number of associated trading objects corresponding to a target merchant; A first transaction data acquisition module, configured to acquire first transaction data between the associated trading objects and first target associated merchants corresponding to the associated trading objects, where the first target associated merchants do not include the target merchant; An associated merchant determination module, configured to determine a second preset number of associated merchants from the first target associated merchants based on the first transaction data; A first target graph construction module, configured to use the target merchant and the second preset number of associated merchants as nodes, and construct a first target graph corresponding to the target merchant with the edge weights between the target merchant and each associated merchant, where the edge weights between the target merchant and each associated merchant represent the distance between the target merchant and each associated merchant; A target type information determination module, configured to input the first target graph into a merchant type recognition network for merchant type recognition processing to obtain target type information of the target merchant; An offline merchant recognition result determination module, configured to perform offline merchant recognition on the target merchant based on the target type information to obtain an offline merchant recognition result of the target merchant.

9. An electronic device, characterized in that, Includes: A processor; A memory for storing instructions executable by the processor; Wherein, the processor is configured to execute the instructions to implement the offline merchant recognition method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device can execute the offline merchant recognition method according to any one of claims 1 to 7.

Images