Object recognition method, apparatus, device, medium, and product

Abstract

The present disclosure provides an object identification method, which can be applied to the field of artificial intelligence and big data, and includes: converting transaction data into graph data, wherein the nodes of the graph data are transaction objects contained in the transaction data, and the edges of the nodes are transaction relationships contained in the transaction data; determining an initial community containing a target node based on the graph data; determining a core node set in the initial community and an attribute initial weight of the core node set; determining a quality index of the initial community, the quality index including a community density and a community attribute entropy, the community density being used to represent a dense degree of node pairs in the initial community, and the community attribute entropy being used to represent a confusion degree of nodes in the initial community; expanding the core node set of the initial community based on the attribute initial weight, the community density and the community attribute entropy to obtain a local community; and identifying transaction objects corresponding to core nodes included in the local community as target objects. The present disclosure also provides an object identification device, equipment, storage medium and program product.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of artificial intelligence and big data technology, in particular to the field of data mining and financial technology, and more particularly to an object recognition method, device, equipment, medium and product. BACKGROUND

[0002] The long-tail customer group has the characteristics of large quantity, high potential and difficult to maintain. How to activate or improve the quality of this group has always been the focus of various financial institutions. With the increasing diversification of consumer demand, traditional marketing models often cannot meet the needs of fragmented long-tail customers. Financial institutions promote through general market segmentation methods. For groups with different characteristics hidden in the long tail, it is often difficult to find an effective entry point. Only the marketing strategy of "casting a wide net, catching more fish, and then choosing the best" is adopted. This strategy inevitably leads to high input costs and a mismatch between revenue and costs.

[0003] Currently, for the behavior characteristics of the long-tail customer group, various precise marketing methods have emerged in the field of data mining. Among them, graph data has become a highly regarded data mining and recognition technology. In graph data, the node set with close links within the community and sparse links outside the community is called a community. Community discovery is divided into global graph mining and local community discovery. Unlike general models, local community discovery methods analyze relatively dense connected node sets and node-specific attributes to mine different-sized groups in the market. Through further analysis of the group, financial institutions can better understand the potential needs of long-tail customers. The advantage of this method is that it can capture fragmented and highly personalized consumer behavior and provide more accurate market insights.

[0004] However, traditional local community discovery methods have certain defects. When considering node attributes, they often only measure from the perspective of similarity, ignoring the significance of attribute values in the probability space, resulting in large fluctuations in the quality of local community discovery. That is, it is difficult to use traditional local community discovery techniques to stably and accurately identify long-tail customers. SUMMARY

[0005] In view of the above problems, the present disclosure provides an object recognition method, device, equipment, medium and product for improving the accuracy of target object recognition in big data.

[0006] According to a first aspect of the present disclosure, a subject identification method is provided, the method comprising: converting transaction data into graph data, wherein nodes of the graph data are transaction subjects contained in the transaction data, and edges of the nodes are transaction relationships contained in the transaction data; determining an initial community containing a target node based on the graph data; determining a core node set in the initial community and an initial attribute weight of the core node set; determining a quality indicator of the initial community, the quality indicator comprising a community density and a community attribute entropy, the community density being used to represent a density of node pairs in the initial community, and the community attribute entropy being used to represent a confusion degree of nodes in the initial community; expanding the core node set of the initial community based on the initial attribute weight, the community density and the community attribute entropy to obtain a local community; and identifying transaction subjects corresponding to core nodes in the local community as target subjects.

[0007] According to an embodiment of the present disclosure, the core node set in the initial community is determined, comprising: determining a plurality of maximal cliques containing the target node in the initial community; merging two maximal cliques into a new node set in a case that there are N-1 overlapping nodes between the two maximal cliques with a size of N, and attribute similarity of the two overlapping nodes is greater than average attribute similarity of the two maximal cliques at the same time; and repeating the above operation until all nodes in the initial community do not satisfy the merging condition, and determining a node set with the maximum average attribute similarity as the core node set.

[0008] According to an embodiment of the present disclosure, the initial attribute weight of the core node set in the initial community is determined, comprising: constructing a target function according to the number of nodes in the core node set, the size of the attribute set, and the value of each core node on each attribute, the target function representing a sum of weighted distances between the core nodes in the initial community based on attributes; and determining the initial attribute weight by minimizing the sum of the weighted attribute distances of the core node set.

[0009] According to an embodiment of the present disclosure, the quality indicator of the initial community is determined, comprising: determining the community density according to node pairs in the initial community, neighbor sets of the nodes, and neighbor quantities.

[0010] According to an embodiment of the present disclosure, the quality indicator of the initial community is further determined, comprising: determining the community attribute entropy according to attribute probabilities of the nodes in the initial community on attributes.

[0011] According to an embodiment of the present disclosure, the core node set of the initial community is expanded based on the initial attribute weight, the community density and the community attribute entropy to obtain the local community, comprising: constructing a community quality function according to the initial attribute weight, the community density and the community attribute entropy; and adding neighbor nodes of a core node having a gain in community quality of the initial community to the initial community based on the community quality function to obtain the local community.

[0012] According to an embodiment of the present disclosure, the method further comprises: storing the local community in a graph database, and displaying a real-time local community.

[0013] According to an embodiment of the present disclosure, the method further comprises: in response to the transaction request, obtaining original transaction data generated by executing the transaction request; performing feature screening on the original transaction data to obtain the transaction data; and storing the transaction data in the transaction database.

[0014] A second aspect of the present disclosure provides an object identification device, the device comprising: a conversion module configured to convert transaction data into graph data, wherein a node of the graph data is a transaction object contained in the transaction data, and an edge of the node is a transaction relationship contained in the transaction data; a first determination module configured to determine an initial community containing a target node based on the graph data; a second determination module configured to determine a core node set in the initial community and an attribute initial weight of the core node set; a third determination module configured to determine a quality index of the initial community, the quality index comprising a community density and a community attribute entropy, the community density being used to represent a dense degree of a node pair of the initial community, and the community attribute entropy being used to represent a confusion degree of a node of the initial community; an expansion module configured to expand the core node set of the initial community based on the attribute initial weight, the community density and the community attribute entropy to obtain a local community; and an identification module configured to identify a transaction object corresponding to a core node contained in the local community as a target object.

[0015] A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; a memory configured to store one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the method.

[0016] A fourth aspect of the present disclosure further provides a computer-readable storage medium having a computer program or instructions stored thereon, wherein the computer program or instructions are executed by a processor to implement the steps of the method.

[0017] A fifth aspect of the present disclosure further provides a computer program product comprising a computer program or instructions, wherein the computer program or instructions are executed by a processor to implement the steps of the method. BRIEF DESCRIPTION OF DRAWINGS

[0018] The above and other objects, features and advantages of the present disclosure will become more apparent from the following description when taken in conjunction with the accompanying drawings, in which:

[0019] Figure 1 An application scenario diagram of an object identification method, device, equipment, medium and program product according to an embodiment of the present disclosure is schematically shown;

[0020] Figure 2 A flowchart of long-tail customer group mining using an object identification method according to an embodiment of the present disclosure is schematically shown;

[0021] Figure 3 A flowchart of a method of object recognition according to embodiments of the present disclosure is schematically shown;

[0022] Figure 4 A flowchart of determining a set of core nodes in an initial community according to embodiments of the present disclosure is schematically shown;

[0023] Figure 5 A flowchart of determining an initial weight of an attribute of a set of core nodes in an initial community according to embodiments of the present disclosure is schematically shown;

[0024] Figure 6 A flowchart of determining a local community according to embodiments of the present disclosure is schematically shown;

[0025] Figure 7 A flowchart of details of local community discovery based on attribute entropy weight and topology according to embodiments of the present disclosure is schematically shown;

[0026] Figure 8 A block diagram of a structure of an object recognition apparatus according to embodiments of the present disclosure is schematically shown; and

[0027] Figure 9 A block diagram of an electronic device suitable for implementing the method of object recognition according to embodiments of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0028] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It is to be understood, however, that the description is merely exemplary of the present disclosure, and is not intended to limit the scope of the present disclosure. In the following detailed description of the embodiments of the present disclosure, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure. However, it would be apparent to one skilled in the art that the present disclosure can be practiced without these specific details. In other instances, well-known structures and functions have not been described in detail in order to avoid obscuring aspects of the present disclosure.

[0029] The terms used herein are merely used to describe specific embodiments, and are not intended to limit the present disclosure. The terms "include" and "have" and the like used herein indicate the presence of the described features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0030] All terms used herein, including technical and scientific terms, have the same meanings as those generally understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having meanings consistent with the context of the present description, and should not be interpreted in an idealized or excessively formal manner.

[0031] In the case of using expressions similar to "at least one of A, B, and C, etc.", it is generally interpreted in the meaning that the skilled person in the art usually understands the expression (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B, and C, etc.).

[0032] In the technical solutions of the present disclosure, the user information (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of related data comply with relevant laws, regulations and standards, necessary security measures are taken, do not violate public order and good customs, and provide corresponding operation portal for user to choose authorization or refusal.

[0033] In the scenario of using personal information for automated decision-making, the method, device and system provided by the embodiments of the present disclosure all provide the user with a corresponding operation portal for the user to choose to agree or refuse the automated decision-making result; if the user chooses to refuse, the expert decision-making process is entered. The expression "automated decision-making" here refers to the activity of automatically analyzing, evaluating the behavior habits, interests and hobbies, or economic, health, credit status, etc. of an individual through a computer program and making decisions. The expression "expert decision-making" here refers to the activity of making decisions by personnel who are engaged in a certain field of work, have specialized experience, knowledge and skills, and have reached a certain professional level.

[0034] Embodiments of the present disclosure provide an object identification method, the method comprising: converting transaction data into graph data, wherein the nodes of the graph data are transaction objects contained in the transaction data, and the edges of the nodes are transaction relationships contained in the transaction data; determining an initial community containing a target node based on the graph data; determining a core node set in the initial community and an attribute initial weight of the core node set; determining a quality indicator of the initial community, the quality indicator comprising a community density and a community attribute entropy, the community density being used to represent the intensive degree of node pairs in the initial community, and the community attribute entropy being used to represent the confusion degree of nodes in the initial community; expanding the core node set of the initial community based on the attribute initial weight, the community density and the community attribute entropy to obtain a local community; and identifying the transaction objects corresponding to the core nodes contained in the local community as target objects.

[0035] Figure 1 An application scenario diagram of the object identification method, apparatus, device, medium and program product according to the embodiments of the present disclosure is schematically shown.

[0036] AsFigure 1 As shown, the application scenario 100 according to this embodiment can include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, a server 105, and a database 106. The network 104 is a medium for providing a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, the server 105, and the database 106. The network 104 can include various connection types, such as wired, wireless communication links, or fiber optic cables, and the like.

[0037] A user can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 and the database 106 through the network 104 to receive or send messages, and the like. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, financial consumption applications, and the like (only as examples).

[0038] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smartphones, tablet computers, laptop computers, desktop computers, and the like.

[0039] The server 105 can be a server providing various services, such as a background management server providing support for transaction requests sent by a user using the first terminal device 101, the second terminal device 102, and the third terminal device 103, and processing transaction data to mine target objects (only as examples). The background management server can analyze and process received user requests and the like, and store the processing results in the database 106 and feedback to the terminal device (such as a webpage, information, or data generated or obtained according to a user request, and the like).

[0040] It should be noted that the object recognition method provided by the embodiments of the present disclosure can generally be executed by the server 105. Accordingly, the object recognition apparatus provided by the embodiments of the present disclosure can generally be disposed in the server 105. The object recognition method provided by the embodiments of the present disclosure can also be executed by a server or a server cluster different from the server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or the server 105. Accordingly, the object recognition apparatus provided by the embodiments of the present disclosure can also be disposed in a server or a server cluster different from the server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or the server 105.

[0041] It should be understood that Figure 1 The number of terminal devices, networks, servers, and databases shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, servers, and databases can be included.

[0042] The object recognition method provided in this disclosure can be applied to the fintech field. For example, when financial institutions promote their products using common market segmentation methods, they often find it difficult to find effective entry points for groups with different characteristics hidden in the long tail. They can only adopt a "cast a wide net and catch many fish" marketing strategy and then "select the best" marketing strategy. This strategy inevitably leads to high input costs and a mismatch between returns and costs.

[0043] Figure 2 A flowchart illustrating a long-tail customer segment mining method according to an embodiment of the present disclosure is shown.

[0044] like Figure 2 As shown, a user initiates a transaction request through a first terminal device 101, a second terminal device 102, and a third terminal device 103. The transaction processing center of the server 105 processes the transaction request, marks the generated historical transaction data, stores it in the transaction database, processes the historical transaction data into graph data, trains a local community model based on the graph data, sends the local community to the detection center, and identifies the current transaction data based on the local community model to determine whether the user corresponding to the current transaction data is the target object.

[0045] The object identification method of this disclosure can accurately identify target objects from transaction data based on local communities determined by a large amount of transaction data, so as to carry out precise marketing to the target objects.

[0046] It should be noted that the object identification method and apparatus disclosed herein can be used in the mining of long-tail customers in the fintech field, and can also be used in any field other than fintech, such as e-commerce. The application field of the object identification method and apparatus disclosed herein is not limited.

[0047] The following will be based on Figure 1 The described scene, through Figures 2-6 The object recognition method of the disclosed embodiments will be described in detail.

[0048] Figure 3 A flowchart illustrating an object identification method according to an embodiment of the present disclosure is shown schematically.

[0049] like Figure 3 As shown, the object recognition in this embodiment includes operations S310 to S360, and the object recognition method can be executed by the server 105.

[0050] In operation S310, the transaction data is converted into graph data. The nodes of the graph data are the transaction objects contained in the transaction data, and the edges of the nodes are the transaction relationships contained in the transaction data.

[0051] In operation S320, based on the graph data, an initial community containing a target node is determined.

[0052] In operation S330, a core node set in the initial community and an attribute initial weight of the core node set are determined.

[0053] In operation S340, a quality index of the initial community is determined, the quality index including a community density and a community attribute entropy, the community density being used to represent the intensive degree of the node pairs in the initial community, and the community attribute entropy being used to represent the confusion degree of the nodes in the initial community.

[0054] In operation S350, the core node set of the initial community is expanded based on the attribute initial weight, the community density and the community attribute entropy, to obtain a local community.

[0055] In operation S360, the transaction objects corresponding to the core nodes contained in the local community are identified as target objects.

[0056] For example, the transaction data can include date, location, transaction type, transaction parties (buyer and seller), amount, supplier, transaction device identifier, customer behavior pattern, product ID, product category, etc.

[0057] The transaction relationship can be taken as the edge of the node, and the transaction parties can be taken as the nodes on both sides of the edge, so that the transaction data is processed into a graph G. , wherein is the node set of the graph G, and there are n nodes in total; is the edge set of the graph G, and there are m edges in total; is the attribute set of the graph G, and there are d attributes in total. is the attribute vector of the node , and represents the value of the node on the attribute .

[0058] A subgraph C (i.e., an initial community) containing a target node can be selected on the graph G, and the node set of the initial community is , and there are c nodes in total; is the edge set of the graph.

[0059] After determining the initial weight of the attribute, the core node set can be expanded to obtain the final local community. Since the contribution of different attributes in discovering the community is not the same and is not constant, the weight of the attribute can be determined based on the two-stage attribute weighting strategy. Considering that the core node set of the initial community can represent the final local community to some extent, the initial weight of the attribute can be learned according to the core node set of the community. In the community expansion process, the core node set is expanded by combining the community density and the community attribute entropy to obtain the final local community.

[0060] According to the object recognition method of the embodiment of the present disclosure, abstract transaction data is converted into graph data, and based on graph data technology, firstly, the core node set of the target node is mined in combination with the "node attribute" and the "topological structure". Secondly, the initial attribute weight of the community is learned according to the core node set, and the core node set is expanded in combination with the community weighted attribute entropy to determine the local community. The community weighted attribute entropy can measure the attribute homogeneity of the community, so as to better accurately discover the local community. The two-stage attribute weighting strategy based on the initial attribute weight and the community weighted attribute entropy is used to distinguish the weight of different attributes, so as to meet the dynamic changes in the community expansion process, so as to be able to cope with the variable bank network structure, so as to be able to stably and quickly recognize the target object. In addition, through the improvement of the local community discovery method, the speed and accuracy of object recognition are accelerated, so as to improve the operation efficiency and execution effect of the hardware of the server. Moreover, the improved local community can cope with the variable bank network structure, avoiding the repeated execution of the local community discovery method by the server, so as to further improve the hardware operation efficiency of the server and improve the hardware processing speed.

[0061] Figure 4 A flowchart for determining the core node set in the initial community according to the embodiment of the present disclosure is schematically shown.

[0062] As shown in Figure 4 On the basis of the above embodiment, the operation of determining the core node set in the initial community can include operations S410-S430.

[0063] In operation S410, a plurality of maximal cliques containing the target node in the initial community are determined.

[0064] In operation S420, in the case that there are N-1 overlapping nodes between two maximal cliques with a size of N, and the attribute similarity of the two overlapping nodes is greater than the average attribute similarity of the two maximal cliques at the same time, the two maximal cliques are merged into a new node set.

[0065] In operation S430, the above operations S410 and S420 are repeated until all nodes in the initial community do not meet the merging condition, and the node set with the maximum average attribute similarity is determined as the core node set.

[0066] A maximal clique refers to a clique in an undirected graph, if a clique is not contained in any other clique, that is, it is not a proper subset of any other clique, then the clique is referred to as a maximal clique of the graph G.

[0067] Since the maximal cliques containing the target node can overlap with each other, screening is required. If there are N-1 overlapping nodes between two maximal cliques of size N, and the attribute similarity of the two non-overlapping nodes is greater than the average attribute similarity of the two maximal cliques, then the two maximal cliques are merged into a new node set. When all node sets cannot be merged, the node set with the maximum average attribute similarity is selected as the core node set. The discrete attribute similarity is calculated by using cosine similarity, and the continuous attribute similarity is calculated by using Euclidean similarity.

[0068] According to the object recognition method provided in the embodiments of the present disclosure, the "maximal clique" method is used to mine the core node set around the "seed node" to replace the single seed node, thereby avoiding the problem of "seed dependence", and further accurately discovering the local community, improving the accuracy of object recognition, and improving the execution effect of the hardware of the server.

[0069] Figure 5 A flowchart for determining the attribute initial weight of the core node set in the initial community is schematically shown.

[0070] As shown in Figure 5 , on the basis of the above embodiments, determining the attribute initial weight of the core node set in the initial community can include operation S510 to operation S520.

[0071] In operation S510, a target function is constructed according to the number of nodes of the core node set, the size of the attribute set, and the value of each core node on each attribute, and the target function represents the sum of the weighted distances between the core nodes in the initial community based on the attributes.

[0072] In operation S520, the attribute initial weight is determined by minimizing the sum of the weighted attribute distances of the core node set.

[0073] For example, given the core node set Z, the attribute initial weight vector can be solved by minimizing the sum of the weighted attribute distances of the core node set, and the target function is defined as follows:

[0074]

[0075] where c is the number of nodes of the core node set, d is the size of the attribute set, represents the weight of the attribute , is the parameter of the weight , is a node the value of the attribute on the node , is a node and a node the value of the attribute on the node where . For solving the extreme value of the function with constraints, the Lagrange multiplier method can be used to solve the final solution of the initial weight :

[0076]

[0077] wherein:

[0078] .

[0079] By the object recognition method of the embodiments of the present disclosure, since the core node set of the initial community can represent the final local community to a certain extent, the initial attribute weight can be learned according to the core node set of the initial community, and then the local community can be accurately found, the accuracy of object recognition is improved, and the execution effect of the hardware of the server is improved.

[0080] On the basis of the above embodiments, determining the quality index of the initial community can include: determining the community density according to the node pair of the initial community, the neighbor set of the node, and the neighbor quantity.

[0081] In the embodiments of the present disclosure, the community density of the initial community can measure the structural cohesion of the community. The community density can be defined as the average node pair density in the community. The node pair density may be:

[0082]

[0083] wherein, is a node pair in the community C; is the neighbor set of node a; is the neighbor quantity of node a; is a neighbor of node a; is a neighbor of node b; is an indicator function, which can be as follows:

[0084]

[0085] Further, the local community density calculation method can be:

[0086]

[0087] When using community density As the evaluation standard of community detection, the higher the community density, the closer the node pairs in the community. This trend is very consistent with the community structure required by community discovery. Therefore, community density can be used to judge the goodness of the community discovery result.

[0088] The object recognition method according to the embodiment of the present disclosure, since the community density can be used to judge the goodness of the community discovery result, the community density is added in the process of discovering local communities, further accurately discovering local communities, improving the accuracy of object recognition, and improving the execution effect of the hardware of the server.

[0089] On the basis of the above-mentioned embodiment, the quality index of the initial community can also include: determining the community attribute entropy according to the attribute probability of the nodes in the initial community in the attribute.

[0090] In the embodiment of the present disclosure, based on the idea that information entropy can measure the degree of system confusion, community attribute entropy is proposed.

[0091] Assuming that the attributes in the community are independent of each other, the information entropy value of each attribute in the community can be calculated first, and then the weighted sum of each attribute entropy is the weighted attribute entropy of the community. The calculation method is as follows:

[0092] Let any node in the community be , and the attribute probability of the node in the attribute be . Obviously, the value of the node in the attribute is . Obviously, has natural normalization, and the attribute entropy of the community C in the attribute

[0093] is defined as:

[0094] When each attribute is independent, the weighted attribute entropy calculation formula of the community is:

[0095] .

[0096] Since the value range of the community density in the foregoing is [0, 1], and the value range of the attribute entropy is between [0, ], the two cannot be linearly combined in the case of different value ranges. Therefore, the embodiment of the present disclosure adopts the inverse tangent normalization method to map the community attribute entropy to [0, 1], and finally forms the local community quality index together with the community density. The inverse tangent normalization method calculation formula is:

[0097] .

[0098] Although the community weighted attribute entropy starts from the attribute value probability, it provides a new angle of considering the node attribute, but it also ignores the information of the attribute value itself. Therefore, in the community expansion process, the attribute similarity is used as a basic index to make up for the deficiency of the community attribute entropy, and the attribute weight adjustment in the second stage is completed accordingly.

[0099] According to the object recognition method of the embodiment of the present disclosure, the weighted attribute entropy is determined from the node attribute value probability, the attribute probability value itself is considered, the homogeneity of the community attribute can be better measured, and then the local community can be accurately determined, the accuracy of object recognition is improved, and the execution effect of the hardware of the server can be improved.

[0100] Figure 6 A flowchart for determining a local community according to an embodiment of the present disclosure is schematically shown.

[0101] As shown in Figure 6 , on the basis of the above embodiment, determining a local community can include operation S610 to operation S620.

[0102] In operation S610, a community quality function is constructed according to the attribute initial weight, the community density, and the community attribute entropy.

[0103] In operation S620, based on the community quality function, the neighbor nodes of the core node having gain on the community quality of the initial community are added to the initial community to obtain a local community.

[0104] In an embodiment of the present disclosure, if most nodes in the community take similar values on the attribute , the attribute is conducive to community discovery; otherwise, if the value distribution is very random, the attribute is not a good community attribute. The calculation formula of the community attribute weight is as follows:

[0105]

[0106] wherein, is the similarity of the attribute of the node .

[0107] Figure 7 A detailed flowchart of local community discovery based on attribute entropy weight and topology according to an embodiment of the present disclosure is schematically shown.

[0108] As shown in Figure 7 ​The community quality gain brought by the neighbor node joining the community is calculated. The community local community quality function calculation function measures the community quality from two aspects of community density and community weighted attribute entropy. The function formula can be:

[0109]

[0110] wherein, is a parameter for balancing structure information and attribute information; is the community density; is the normalized community weighted attribute entropy. Since the method proposed in the present application includes two hyperparameters α and β which need to be set according to the data set, it is necessary to calculate the influence of α and β with different values on the Accuracy and local modularity of the algorithm results, so as to determine the optimal hyperparameter value.

[0111] The neighbor nodes of the current community are traversed, and the community quality gain brought by the addition of different neighbor nodes to the community is calculated. If the addition of the neighbor node can bring the community an average quality gain that exceeds the historical joining nodes, the node is added to the community and the community attribute weight is updated; otherwise, the node is skipped. The loop is traversed until there is no neighbor node to join, and the loop is terminated, thereby determining the local community.

[0112] According to the object recognition method of the embodiment of the present disclosure, the community quality gain brought by the neighbor node joining the community is calculated based on the community quality function constructed according to the attribute initial weight, the community density and the community attribute entropy, which can accurately determine the local community and improve the accuracy of object recognition.

[0113] On the basis of the above-mentioned embodiment, the method further comprises: storing the local community in a graph database and displaying the real-time local community.

[0114] According to the object recognition method of the embodiment of the present disclosure, after the local community is determined, the determined local community model can be stored in a graph database, and the local community model can be directly called for object recognition in the subsequent process, avoiding repeated determination of the local community model, which can reduce the repeated determination of the server hardware, reduce the calculation amount and save the computing resources.

[0115] On the basis of the above-mentioned embodiment, the method further comprises: in response to a transaction request, obtaining original transaction data generated by executing the transaction request; performing feature screening on the original transaction data to obtain transaction data; and storing the transaction data in a transaction database.

[0116] After the transaction data is transferred to the bank transaction center for processing after the customer initiates a transaction, all original transaction data can be batched and saved in the transaction database at a T+1 frequency. The actual amount of data contained in the original transaction data is relatively large, and before local community discovery is performed, the original transaction data can be processed. For example, according to a series of data feature selection rules defined in advance, all meaningful features (such as date, location, transaction type, amount, supplier, transaction device identifier, customer behavior pattern, etc.) are retained. Then, the graph data is constructed based on these meaningful features.

[0117] According to the object recognition method of the embodiments of the present disclosure, the transaction data is pre-processed by feature processing, and the invalid features are removed and saved in the transaction database. Subsequently, the local community is directly called when determining, which reduces the operation amount and saves the computing resources.

[0118] Based on the above object recognition method, the present disclosure further provides an object recognition device. The following will be described in detail Figure 8 The device is described in detail.

[0119] Figure 8 The structure block diagram of the object recognition device according to the embodiments of the present disclosure is schematically shown.

[0120] As Figure 8 shown, the object recognition device 800 of the embodiments includes a conversion module 810, a first determination module 820, a second determination module 830, a third determination module 840, an expansion module 850, and a recognition module 860.

[0121] The conversion module 810 is configured to convert the transaction data into graph data, wherein the nodes of the graph data are the transaction objects contained in the transaction data, and the edges of the nodes are the transaction relationships contained in the transaction data. In an embodiment, the conversion module 810 can be configured to perform the operation S310 described above, and details are not repeated here.

[0122] The first determination module 820 is configured to determine an initial community containing a target node based on the graph data. In an embodiment, the first determination module 820 can be configured to perform the operation S320 described above, and details are not repeated here.

[0123] The second determination module 830 is configured to determine a core node set in the initial community and an attribute initial weight of the core node set. In an embodiment, the second determination module 830 can be configured to perform the operation S330 described above, and details are not repeated here.

[0124] The third determining module 840 is configured to determine a quality index of the initial community, the quality index including a community density and a community attribute entropy, the community density being used to represent a density of node pairs in the initial community, and the community attribute entropy being used to represent a confusion degree of nodes in the initial community. In an embodiment, the third determining module 840 can be configured to perform the operation S340 described above, and details are not repeated here.

[0125] The expanding module 850 is configured to expand the core node set of the initial community based on the attribute initial weight, the community density and the community attribute entropy, to obtain a local community. In an embodiment, the expanding module 850 can be configured to perform the operation S350 described above, and details are not repeated here.

[0126] The identifying module 860 is configured to identify a transaction object corresponding to a core node included in the local community as a target object. In an embodiment, the identifying module 860 can be configured to perform the operation S360 described above, and details are not repeated here.

[0127] According to an embodiment of the present disclosure, determining a core node set in an initial community includes: determining a plurality of maximal cliques containing a target node in the initial community; merging two maximal cliques into a new node set in a case that there are N-1 overlapping nodes between the two maximal cliques with a size of N, and attribute similarity of the two overlapping nodes is greater than average attribute similarity of the two maximal cliques at the same time; repeating the above operation until all nodes in the initial community do not satisfy a merging condition, and determining a node set with maximum average attribute similarity as the core node set.

[0128] According to an embodiment of the present disclosure, determining an attribute initial weight of the core node set in the initial community can include: constructing a target function according to a number of nodes in the core node set, a size of an attribute set, and a value of each core node on each attribute, the target function representing a sum of weighted distances between the core nodes in the initial community based on attributes; and determining the attribute initial weight by minimizing the sum of weighted attribute distances of the core node set.

[0129] According to an embodiment of the present disclosure, determining a quality index of the initial community can include: determining the community density according to node pairs in the initial community, a neighbor set of a node, and a number of neighbors.

[0130] According to an embodiment of the present disclosure, determining the quality index of the initial community can further include: determining the community attribute entropy according to an attribute probability of a node in the initial community on an attribute.

[0131] According to an embodiment of the present disclosure, the expanding the core node set of the initial community based on the attribute initial weight, the community density and the community attribute entropy to obtain a local community can include: constructing a community quality function according to the attribute initial weight, the community density and the community attribute entropy; and based on the community quality function, adding neighbor nodes of the core nodes having gain on the community quality of the initial community to the initial community to obtain the local community.

[0132] According to an embodiment of the present disclosure, the device further includes a storage module configured to store the local community in a graph database, and a display module configured to display the real-time local community.

[0133] According to an embodiment of the present disclosure, the device further includes a feature screening module configured to, in response to a transaction request, acquire original transaction data generated by executing the transaction request, perform feature screening on the original transaction data to obtain transaction data, and store the transaction data in a transaction database.

[0134] According to an embodiment of the present disclosure, any of the conversion module 810, the first determination module 820, the second determination module 830, the third determination module 840, the expansion module 850 and the identification module 860 can be combined in one module for implementation, or any of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of the modules can be combined with at least part of the functions of other modules, and implemented in one module. According to an embodiment of the present disclosure, at least one of the conversion module 810, the first determination module 820, the second determination module 830, the third determination module 840, the expansion module 850 and the identification module 860 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on board, a system on package, an application specific integrated circuit (ASIC), or any other reasonable manner of integrating or packaging a circuit, etc. hardware or firmware, or in any one of software, hardware and firmware or in any appropriate combination of any of them. Alternatively, at least one of the conversion module 810, the first determination module 820, the second determination module 830, the third determination module 840, the expansion module 850 and the identification module 860 can be at least partially implemented as a computer program module which can perform corresponding functions when the computer program module is run.

[0135] Figure 9 A block diagram of an electronic device suitable for implementing the object method according to an embodiment of the present disclosure is schematically shown.

[0136] As Figure 9As shown, the electronic device 900 according to an embodiment of the present disclosure includes a processor 901 which can perform various appropriate actions and processes according to a program stored in a read only memory (ROM) 902 or a program loaded from a storage section 908 into a random access memory (RAM) 903. The processor 901 can include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor, and / or a related chipset, and / or a special purpose microprocessor (e.g., an application specific integrated circuit (ASIC)), and so on. The processor 901 can also include an on-board memory for cache use. The processor 901 can include a single processing unit or multiple processing units for executing different actions of the method processes according to embodiments of the present disclosure.

[0137] In the RAM 903, various programs and data required for the operation of the electronic device 900 are stored. The processor 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. The processor 901 performs various operations of the method processes according to embodiments of the present disclosure by executing the programs in the ROM 902 and / or the RAM 903. Note that the programs can also be stored in one or more memories other than the ROM 902 and the RAM 903. The processor 901 can also perform various operations of the method processes according to embodiments of the present disclosure by executing the programs stored in the one or more memories.

[0138] According to an embodiment of the present disclosure, the electronic device 900 can further include an input / output (I / O) interface 905 which is also connected to the bus 904. The electronic device 900 can further include one or more of the following components connected to the input / output (I / O) interface 905: an input section 906 including a keyboard, a mouse, etc.; an output section 907 including a display such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 908 including a hard disk, etc.; and a communication section 909 including a network interface card such as a LAN card, a modem, etc. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the input / output (I / O) interface 905 as necessary. A removable medium 911 such as a magnetic disk, a magneto-optical disk, a semiconductor memory, etc. is attached to the drive 910 as necessary, so that a computer program read out therefrom is installed into the storage section 908 as necessary.

[0139] The present disclosure also provides a computer readable storage medium, which can be included in the device / apparatus / system described in the above embodiments, or exist separately without being assembled into the device / apparatus / system. The above computer readable storage medium carries one or more programs, which, when executed, implement the method according to the embodiments of the present disclosure.

[0140] According to an embodiment of the present disclosure, the computer readable storage medium can be a non-volatile computer readable storage medium, which can include, but is not limited to, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any appropriate combination thereof. In the present disclosure, the computer readable storage medium can be any tangible medium that contains or stores a program, which can be used by or in connection with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present disclosure, the computer readable storage medium can include one or more memories, such as the ROM 902 and / or the RAM 903 described above, and / or one or more memory units other than the ROM 902 and the RAM 903.

[0141] The embodiments of the present disclosure also include a computer program product, which includes a computer program containing program codes for executing the methods shown in the flowcharts. When the computer program product is run in a computer system, the program codes are used to make the computer system implement the object recognition method provided by the embodiments of the present disclosure.

[0142] The above functions defined in the system / apparatus of the embodiments of the present disclosure are performed when the computer program is executed by the processor 901. According to an embodiment of the present disclosure, the system, apparatus, module, unit, etc. described above can be implemented by computer program modules.

[0143] In one embodiment, the computer program can rely on a tangible storage medium, such as an optical storage device, a magnetic storage device, etc. In another embodiment, the computer program can also be transmitted, distributed, and downloaded in the form of a signal via a network medium, and be downloaded and installed via the communication part 909 and / or installed from the detachable medium 911. The program codes contained in the computer program can be transmitted via any appropriate network medium, including but not limited to wireless, wired, etc., or any appropriate combination thereof.

[0144] In such embodiments, the computer program can be downloaded and installed from the network through the communication part 909, and / or installed from the detachable medium 911. When the computer program is executed by the processor 901, the above-described functions defined in the system of the embodiments of the present disclosure are executed. According to the embodiments of the present disclosure, the system, device, apparatus, module, unit, and the like described above can be implemented by the computer program modules.

[0145] According to the embodiments of the present disclosure, the program code for executing the computer program provided by the embodiments of the present disclosure can be written in any combination of one or more programming languages, and specifically, these computer programs can be implemented using high-level procedural and / or object-oriented programming language, and / or assembly / machine language. The programming language includes, but is not limited to, such as Java, C++, python, "C" language or similar programming language. The program code can be executed entirely on the user computing device, partially on the user device, partially on a remote computing device, or entirely on a remote computing device or server. In the case involving a remote computing device, the remote computing device can be connected to the user computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, connected to the Internet through an Internet service provider).

[0146] The flowcharts and block diagrams in the drawings illustrate the possible implementation architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each block in the flowcharts or block diagrams can represent a module, a program segment, or a part of code, which contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur in different order than that shown in the drawings. For example, two blocks that are shown in succession can actually be executed substantially in parallel, and sometimes they can be executed in reverse order, depending on the involved functions. It should also be noted that each block in the block diagrams or flowcharts, and the combination of blocks in the block diagrams or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0147] Those skilled in the art can understand that the features described in various embodiments of the present disclosure can be combined and / or integrated in various combinations, even if such combinations or integrations are not explicitly described in the present disclosure. In particular, the features described in various embodiments of the present disclosure can be combined and / or integrated in various combinations without departing from the spirit and teachings of the present disclosure. All such combinations and / or integrations fall within the scope of the present disclosure.

[0148] The above describes embodiments of the present disclosure. However, these embodiments are merely for illustrative purposes, and are not intended to limit the scope of the present disclosure. Although each embodiment is described above separately, this does not mean that the measures in each embodiment cannot be used advantageously in combination. Those skilled in the art can make various substitutions and modifications without departing from the scope of the present disclosure, and these substitutions and modifications should all fall within the scope of the present disclosure.

Claims

1. A method of object recognition, characterized by, The method comprises: transforming transaction data into graph data, wherein nodes of the graph data are transaction objects contained in the transaction data, and edges of the nodes are transaction relationships contained in the transaction data; determining an initial community containing a target node based on the graph data; determining a core node set in the initial community and an attribute initial weight of the core node set; determining a quality indicator of the initial community, wherein the quality indicator comprises a community density and a community attribute entropy, the community density is used to represent a dense degree of node pairs in the initial community, and the community attribute entropy is used to represent a confusion degree of nodes in the initial community; expanding the core node set of the initial community based on the attribute initial weight, the community density and the community attribute entropy to obtain a local community; identifying transaction objects corresponding to core nodes contained in the local community as target objects; The determination of the core node set in the initial community comprises: determining a plurality of maximum cliques containing the target node in the initial community; In the case that there are N-1 overlapping nodes between two maximum cliques with a size of N, and the attribute similarity of the two overlapping nodes is greater than the average attribute similarity of the two maximum cliques at the same time, the two maximum cliques are merged into a new node set; repeating the above operation until all nodes in the initial community do not meet the merging condition, and determining the node set with the maximum average attribute similarity as the core node set; The determination of the attribute initial weight of the core node set in the initial community comprises: constructing a target function according to the number of nodes in the core node set, the size of the attribute set, and the value of each core node on each attribute, wherein the target function represents the sum of weighted distances between core nodes in the initial community based on attributes; determining the attribute initial weight by minimizing the sum of weighted attribute distances of the core node set; The determination of the quality indicator of the initial community further comprises: determining the community attribute entropy according to the attribute probability of nodes in the initial community on attributes; The expansion of the core node set of the initial community based on the attribute initial weight, the community density and the community attribute entropy to obtain a local community comprises: constructing a community quality function according to the attribute initial weight, the community density and the community attribute entropy; based on the community quality function, adding neighbor nodes of a core node with gain in community quality of the initial community to the initial community to obtain the local community.

2. The method of claim 1, wherein, The determination of the quality indicator of the initial community comprises: determining the community density according to node pairs, neighbor sets of nodes and neighbor numbers in the initial community.

3. The method of claim 1, wherein, The method further comprises: storing the local community in a graph database and displaying a real-time local community.

4. The method of claim 1, wherein, The method further comprises: in response to a transaction request, obtaining original transaction data generated by executing the transaction request; performing feature screening on the original transaction data to obtain the transaction data; storing the transaction data in a transaction database.

5. An object recognition apparatus for performing the method of any one of claims 1 to 4, characterized by The device comprises: a conversion module configured to transform transaction data into graph data, wherein nodes of the graph data are transaction objects contained in the transaction data, and edges of the nodes are transaction relationships contained in the transaction data; A first determining module configured to determine an initial community containing a target node based on the graph data; A second determining module configured to determine a core node set in the initial community and an attribute initial weight of the core node set; A third determining module configured to determine a quality index of the initial community, the quality index including a community density and a community attribute entropy, the community density being used to represent a density of node pairs in the initial community, and the community attribute entropy being used to represent a confusion degree of nodes in the initial community; An expanding module configured to expand the core node set of the initial community based on the attribute initial weight, the community density and the community attribute entropy to obtain a local community; An identifying module configured to identify a transaction object corresponding to a core node in the local community as a target object. 6.An electronic device comprising: one or more processors; memory for storing one or more computer programs, characterized in that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1-4.

7. A computer readable storage medium having stored thereon a computer program or instructions, characterized in that, The computer program or instruction is executed by the processor to implement the steps of the method according to any one of claims 1-4.

8. A computer program product comprising computer programs or instructions, characterized in that, The computer program or instruction is executed by the processor to implement the steps of the method according to any one of claims 1-4.

Images