WO2025213865A1 - 一种数据处理方法、装置、电子设备及存储介质 - Google Patents

一种数据处理方法、装置、电子设备及存储介质

Info

Publication number
WO2025213865A1
WO2025213865A1 PCT/CN2024/142042 CN2024142042W WO2025213865A1 WO 2025213865 A1 WO2025213865 A1 WO 2025213865A1 CN 2024142042 W CN2024142042 W CN 2024142042W WO 2025213865 A1 WO2025213865 A1 WO 2025213865A1
Authority
WO
WIPO (PCT)
Prior art keywords
node
transaction
value
fluctuation
business information
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/CN2024/142042
Other languages
English (en)
French (fr)
Inventor
顾河建
潘婧
刘红宝
李晓刚
陈滢
赵金涛
高鹏飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Unionpay Co Ltd
Original Assignee
China Unionpay Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China Unionpay Co Ltd filed Critical China Unionpay Co Ltd
Publication of WO2025213865A1 publication Critical patent/WO2025213865A1/zh
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange

Definitions

  • the present invention relates to the field of computer technology, and in particular to a data processing method, device, electronic device and storage medium.
  • the embodiments of the present invention provide a data processing method, device, electronic device, and storage medium, which make the method of determining the abnormal transaction subject to be optimized more efficient and accurate.
  • an embodiment of the present invention provides a data processing method, the method comprising:
  • the abnormality value corresponding to each node is determined; wherein each abnormality value is used to indicate the degree of abnormal fluctuation of the transaction of the transaction subject indicated by the node; the abnormal fluctuation degree is determined based on the transaction subject's own business information and the business information of other transaction subjects with which it has an association relationship;
  • the first node is determined to be a change node, and the transaction subject indicated by the first node is determined to be the change transaction subject.
  • determining the transaction value corresponding to each node in the graph association structure based on the business information of the transaction subject indicated by each node, the association relationship between the transaction subjects, and a preset transaction analysis rule includes:
  • the first sub-rule is used to perform magnitude normalization processing on the initial fluctuation values of the nodes obtained based on business information of different magnitudes;
  • the second sub-rule is used to calculate the degree to which the lower-level nodes are affected by the fluctuation of the upper-level nodes, and the lower-level nodes and the upper-level nodes are determined based on the associations between the transaction entities;
  • the abnormal value corresponding to each node is determined.
  • determining the fluctuation value of each node based on the business information of the transaction subject indicated by each node in the graph association structure and the first sub-rule in the preset abnormal movement analysis rule includes:
  • the business information of the transaction subject indicated by each node is respectively input into a preset time series attribution model to obtain an initial fluctuation value corresponding to each node output by the preset time series attribution model;
  • the preset time series attribution model determines the initial fluctuation value of a transaction subject based on the business information of the transaction subject within a preset time period and a preset magnitude fluctuation evaluation rule;
  • the preset magnitude fluctuation evaluation rule includes multiple mapping relationships, and different mapping relationships include numerical ranges corresponding to business information of different magnitudes and initial fluctuation values corresponding to the numerical ranges;
  • the normalization is implemented based on the following method:
  • Si represents the fluctuation value of the node
  • ri represents the initial fluctuation value corresponding to the node
  • K is used to represent the total number of nodes in the graph association structure.
  • the second sub-rule is determined based on the following formula:
  • ep ij represents the influence value of node i relative to node j
  • ⁇ i represents the change value of the business information value of node i between two moments
  • ⁇ j represents the change value of the business information value of node j between two moments
  • e it represents the business information value of node i at time t
  • e it' represents the business information value of node i at time t'
  • e jt represents the business information value of node j at time t
  • e jt' represents the business information value of node j at time t'
  • node i and node j are any nodes in the graph association structure.
  • determining the change value corresponding to each node according to the fluctuation value and the corresponding impact value of each node includes:
  • the third sub-rule of the preset abnormality analysis rule is substituted to determine the abnormality value corresponding to each node respectively; the third sub-rule is used to iteratively optimize the fluctuation value of the node in combination with the influence values corresponding to all nodes that have an associated relationship with the node.
  • the third sub-rule is determined based on the following formula: H n ⁇ H n-1 +d
  • H n represents the set of fluctuation values of all nodes
  • n is used to represent the number of iterations.
  • S′ represents the set of fluctuation values of all nodes.
  • ep ij represents the influence value of node i relative to node j
  • node i and node j are arbitrary nodes in the graph association structure
  • S k represents the fluctuation value of node k
  • d is a non-zero adjustment coefficient
  • i and j are positive integers.
  • the method further includes:
  • the abnormal path is analyzed to obtain an abnormal analysis result; the abnormal analysis result is used to indicate the impact node associated with the abnormal node, and based on the business information corresponding to the abnormal node, the business of the transaction subject corresponding to the impact node is optimized.
  • an embodiment of the present invention provides a data processing device, the device comprising:
  • a construction unit is used to construct a graph association structure with transaction entities in the target business scenario as nodes and association relationships between transaction entities as edges;
  • a determining unit configured to determine an abnormality value corresponding to each node in the graph association structure based on the business information of the transaction subject indicated by each node, the association relationship between the transaction subjects, and a preset abnormality analysis rule; wherein each abnormality value is used to indicate the degree of abnormal fluctuation in the transaction of the transaction subject indicated by the node; the abnormal fluctuation degree is determined based on the transaction subject's own business information and the business information of other transaction subjects with which it has an association relationship;
  • the processing unit is configured to determine that the first node is a changed node when the change value corresponding to the first node is greater than a preset threshold, and to determine the transaction subject indicated by the first node as the changed transaction subject.
  • the determining unit is specifically configured to:
  • the first sub-rule is used to perform magnitude normalization processing on the initial fluctuation values of the nodes obtained based on business information of different magnitudes;
  • the second sub-rule is used to calculate the degree to which the lower-level nodes are affected by the fluctuation of the upper-level nodes, and the lower-level nodes and the upper-level nodes are determined based on the associations between the transaction entities;
  • the abnormal value corresponding to each node is determined.
  • the determining unit is specifically configured to:
  • the business information of the transaction subject indicated by each node is respectively input into a preset time series attribution model to obtain an initial fluctuation value corresponding to each node output by the preset time series attribution model;
  • the preset time series attribution model determines the initial fluctuation value of a transaction subject based on the business information of the transaction subject within a preset time period and a preset magnitude fluctuation evaluation rule;
  • the preset magnitude fluctuation evaluation rule includes multiple mapping relationships, and different mapping relationships include numerical ranges corresponding to business information of different magnitudes and initial fluctuation values corresponding to the numerical ranges;
  • the normalization is implemented based on the following method:
  • Si represents the fluctuation value of the node
  • ri represents the initial fluctuation value corresponding to the node
  • K is used to represent the total number of nodes in the graph association structure.
  • the second sub-rule is determined based on the following formula:
  • ep ij represents the influence value of node i relative to node j
  • ⁇ i represents the change value of the business information value of node i between two moments
  • ⁇ j represents the change value of the business information value of node j between two moments
  • e it represents the business information value of node i at time t
  • e it' represents the business information value of node i at time t'
  • e jt represents the business information value of node j at time t
  • e jt' represents the business information value of node j at time t'
  • node i and node j are any nodes in the graph association structure.
  • the determining unit is specifically configured to:
  • the third sub-rule of the preset abnormality analysis rule is substituted to determine the abnormality value corresponding to each node respectively; the third sub-rule is used to iteratively optimize the fluctuation value of the node in combination with the influence values corresponding to all nodes that have an associated relationship with the node.
  • the third sub-rule is determined based on the following formula: H n ⁇ H n-1 +d
  • H n represents the set of fluctuation values of all nodes
  • n is used to represent the number of iterations.
  • S′ represents the set of fluctuation values of all nodes.
  • ep ij represents the influence value of node i relative to node j
  • node i and node j are arbitrary nodes in the graph association structure
  • S k represents the fluctuation value of node k
  • d is a non-zero adjustment coefficient
  • i and j are positive integers.
  • the apparatus further includes an optimization unit configured to:
  • the abnormal path is analyzed to obtain an abnormal analysis result; the abnormal analysis result is used to indicate the impact node associated with the abnormal node, and based on the business information corresponding to the abnormal node, the business of the transaction subject corresponding to the impact node is optimized.
  • an embodiment of the present invention provides an electronic device comprising at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any method provided in the embodiment of the first aspect of the present invention.
  • an embodiment of the present invention provides a computer storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is used to enable a computer to execute any method provided by the embodiment of the first aspect of the present invention.
  • an embodiment of the present invention provides a computer program product, comprising: a computer program code, which, when executed on a computer, enables the computer to execute any one of the methods provided in the embodiment of the first aspect.
  • a graph association structure can be constructed with transaction entities in a target business scenario as nodes and relationships between transaction entities as edges. Furthermore, based on the business information of the transaction entity indicated by each node in the graph association structure, the relationships between transaction entities, and preset abnormality analysis rules, an abnormality value corresponding to each node is determined. Each abnormality value is used to indicate the degree of abnormal fluctuation in the transaction of the transaction entity indicated by the node. The degree of abnormal fluctuation is determined based on the transaction entity's own business information and the business information of other transaction entities with which it has an associated relationship.
  • the abnormality value corresponding to a node is determined from the perspective of the graph association structure, and the determination of the abnormality value simultaneously considers both the transaction entity's own business information and the business information of other transaction entities with which it has an associated relationship, thereby improving the accuracy of attribution analysis of abnormal performance.
  • the abnormality value corresponding to a first node is greater than a preset threshold, the first node is determined to be an abnormal node, and the transaction entity indicated by the first node is determined to be an abnormal transaction entity, thereby accurately and efficiently determining the abnormal transaction entity that caused the abnormal event.
  • FIG2 is an optional schematic diagram of an application scenario in an embodiment of the present invention.
  • FIG3 is a schematic flow chart of a data processing method according to an embodiment of the present invention.
  • FIG4 is a schematic diagram of a graph association structure according to an embodiment of the present invention.
  • FIG5 is a schematic diagram of fluctuation values of nodes in a graph association structure according to an embodiment of the present invention.
  • FIG6 is a schematic diagram of the influence value of a node in a graph association structure according to an embodiment of the present invention.
  • FIG7 is a schematic diagram of a calculation node corresponding to an abnormal value according to an embodiment of the present invention.
  • FIG8 is a schematic diagram of an abnormal path in an embodiment of the present invention.
  • FIG9 is a schematic diagram of the structure of a data processing device according to an embodiment of the present invention.
  • FIG10 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
  • FIG11 is another structural diagram of an electronic device according to an embodiment of the present invention.
  • an embodiment of the present invention provides a data processing method, through which a graph association structure can be constructed with transaction entities in a target business scenario as nodes and the association relationships between transaction entities as edges. Furthermore, based on the business information of the transaction entity indicated by each node in the graph association structure, the association relationships between transaction entities, and preset anomaly analysis rules, an anomaly value corresponding to each node is determined. Each anomaly value is used to indicate the degree of abnormal fluctuation in the transaction of the transaction entity indicated by a node. The degree of abnormal fluctuation is determined based on the transaction entity's own business information and the business information of other transaction entities with which it has an association relationship.
  • the embodiment of the present invention determines the anomaly value corresponding to a node from the perspective of the graph association structure, and the determination of the anomaly value simultaneously considers both the transaction entity's own business information and the business information of other transaction entities with which it has an association relationship, thereby improving the accuracy of attribution analysis of anomaly performance.
  • the anomaly value corresponding to a first node is greater than a preset threshold, the first node is determined to be an anomaly node, and the transaction entity indicated by the first node is determined to be an anomaly transaction entity, thereby accurately and efficiently determining the anomaly transaction entity that caused the anomaly.
  • the data processing method provided by the embodiment of the present invention can be applied to any business scenario that requires abnormal attribution analysis, such as a business scenario of performing abnormal attribution analysis on each functional module in the software system of business A, a business scenario of performing abnormal attribution analysis on each functional unit in the network platform, etc., and another example is a business scenario of performing abnormal attribution analysis on each subject in the payment system in the financial field, a business scenario of performing abnormal attribution analysis on each subject in the lending system in the financial field, a business scenario of performing abnormal attribution analysis on each subject in the manufacturing system in the manufacturing field, a business scenario of performing abnormal attribution analysis on each subject in the enterprise management system in the management field, etc., and this is not limited in the embodiment of the present invention.
  • FIG. 1 illustrates an application scenario in which the technical solutions of an embodiment of the present invention can be applied.
  • This schematic diagram includes devices 101 corresponding to multiple acquirers, devices 102 corresponding to multiple payment subsidiaries, devices 103 corresponding to the payment head office, and devices 104 corresponding to an analysis system for performing attribution analysis of payment system transactions. It should be noted that acquirers, payment subsidiaries, and the payment head office can all be referred to as transaction entities.
  • the device 104 corresponding to each analysis system may include one or more processors 1041, a memory 1042, and an I/O interface 1043 for interacting with the device. Furthermore, devices 101, 102, 103, and 104, as well as each other, may be directly or indirectly connected to each other via one or more networks 105.
  • objects 1, 2, ..., and n, where n is a positive integer, of devices 101-1, 101-2, ..., and 101-n can simultaneously initiate payment transactions.
  • object 1 can also initiate a transaction first, followed by object 2.
  • the analysis system can receive a large amount of concurrent payment transaction data and perform attribution analysis on the payment transaction data, i.e., determine whether there are any abnormalities in the payment transaction data.
  • the specific scheme for performing attribution analysis on payment transaction data can be found in the data processing method provided in the embodiments of the present invention, which is described in detail later and will not be elaborated on here.
  • FIG. 2 illustrates another application scenario to which the technical solutions of an embodiment of the present invention can be applied.
  • This schematic diagram includes devices 201 corresponding to multiple sales organizations, devices 202 corresponding to multiple manufacturing subsidiaries, devices 203 corresponding to the manufacturing parent company, and devices 104 corresponding to the analysis system for performing attribution analysis on sales system transactions.
  • the sales organizations, manufacturing subsidiaries, and the manufacturing parent company can all be referred to as transaction entities.
  • the device 104 corresponding to each analysis system may include one or more processors 1041, a memory 1042, and an I/O interface 1043 for interacting with the device. Furthermore, devices 201, 202, 203, and 104, as well as each other, may be directly or indirectly connected to each other via one or more networks 105.
  • sales organizations 1, 2, ..., and n can simultaneously initiate sales transactions.
  • sales organization 1 can also initiate a sales transaction first, followed by sales organization 2.
  • the analysis system can receive a large amount of concurrent sales transaction data and perform an abnormal attribution analysis on the sales transaction data, i.e., determine whether there are abnormal performances in the sales transaction data.
  • the specific scheme for performing abnormal attribution analysis on sales transaction data can be found in the data processing method provided in the embodiment of the present invention, which is described in detail later and will not be elaborated here.
  • the various devices in Figures 1 and 2 can be mobile phones, tablet computers (PADs), personal computers (PCs), smart TVs, smart watches, smart speakers, smart car devices, and wearable devices, but are not limited to these. These devices can have the function of logging in to and using learning websites.
  • PDAs tablet computers
  • PCs personal computers
  • smart TVs smart watches
  • smart speakers smart car devices
  • wearable devices but are not limited to these.
  • These devices can have the function of logging in to and using learning websites.
  • the devices in Figures 1 and 2 can also be independent physical servers, or they can be server clusters or distributed systems composed of multiple physical servers. They can also be cloud servers that provide basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms, but are not limited to these.
  • cloud servers that provide basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms, but are not limited to these.
  • the network 105 may be a wired network or a wireless network.
  • the wireless network may be a mobile cellular network or a Wireless-Fidelity (WIFI) network.
  • WIFI Wireless-Fidelity
  • it may also be other possible networks, which are not limited in the embodiment of the present invention.
  • the embodiments of the present invention provide the method operation steps as shown in the following embodiments or drawings, more or fewer operation steps may be included in the method based on routine or no creative labor. In steps where there is no necessary causal relationship logically, the execution order of these steps is not limited to the execution order provided by the embodiments of the present invention. In the actual processing process or when the device is executed, the method may be executed in the order of the methods shown in the embodiments or drawings or in parallel.
  • Figure 3 is a flow chart of a data processing method in an embodiment of the present invention, wherein the data processing method can be executed by the device 104 in Figures 1 and 2 above, and an analysis system for abnormal attribution analysis is deployed on the device 104.
  • Step 301 Construct a graph association structure with transaction entities in the target business scenario as nodes and association relationships between transaction entities as edges.
  • the electronic device may first determine the target business scenario.
  • the target business scenario is hereinafter described as a business scenario of a payment system in the financial field.
  • the business scenario of the payment system in the financial field includes a payment company, multiple payment subsidiaries, and multiple acquiring institutions.
  • the payment company, payment subsidiaries, and acquiring institutions can be understood as the entities that generate transaction data. For the sake of convenience, the entities will be referred to as transaction entities in the following text.
  • the association relationship between the payment company, multiple payment subsidiaries, and multiple acquiring institutions can be determined based on the business information.
  • the business information is the number of merchants
  • the business information is the number of transactions
  • a graph association structure can be constructed with transaction entities in the target business scenario as nodes and association relationships between transaction entities as edges.
  • Figure 4 is a schematic diagram of a graph association structure provided by an embodiment of the present invention.
  • the quadrilateral pattern is used to represent a node where the transaction subject is an acquirer
  • the pentagonal pattern is used to represent a node where the transaction subject is a payment subsidiary
  • the hexagonal pattern is used to represent a node where the transaction subject is a payment head office.
  • V represents the node set included in the graph association structure
  • ⁇ represents the edge set of the graph association structure
  • Step 302 Based on the business information of the transaction subject indicated by each node in the graph association structure, the association relationship between the transaction subjects, and the preset anomaly analysis rules, determine the anomaly value corresponding to each node; wherein each anomaly value is used to indicate the degree of abnormal fluctuation of the transaction of the transaction subject indicated by a node; the degree of abnormal fluctuation is determined based on the transaction subject's own business information and the business information of other transaction subjects with which it has an association relationship.
  • the electronic device may adopt, but is not limited to, the following steps to obtain the corresponding change value of each node:
  • Step A Determine the fluctuation value of each node based on the business information of the transaction subject indicated by each node in the graph association structure and the first sub-rule in the preset abnormality analysis rule; the first sub-rule is used to normalize the initial fluctuation values of the nodes obtained based on business information of different magnitudes.
  • the electronic device may input the business information of the transaction subject indicated by each node into a preset time series attribution model to obtain the initial fluctuation value corresponding to each node output by the preset time series attribution model.
  • the preset time series attribution model determines the initial fluctuation value of the transaction subject based on the business information of the transaction subject within a preset time period and a preset magnitude fluctuation evaluation rule.
  • the preset magnitude fluctuation evaluation rule includes multiple mapping relationships, each of which includes a numerical range corresponding to business information of different magnitudes and an initial fluctuation value corresponding to the numerical range.
  • the input to the preset time series attribution model is the number of transactions counted monthly by acquiring institution A in the two years 2021-2023 as 100. Therefore, based on the fluctuation evaluation rule, it can be determined that the numerical range corresponding to the number of transactions is 100-200, and the initial fluctuation value corresponding to the numerical range of 100-200 is 120%, then the output initial fluctuation value of the node in the order of transactions is determined to be 120%.
  • the initial fluctuation value corresponding to each transaction entity can be normalized to achieve a unified assessment of magnitude.
  • the initial fluctuation value corresponding to each transaction entity can be normalized to obtain the fluctuation value for each node.
  • the fluctuation value indicates fluctuations in the value of the business information of the transaction entity indicated by the node (hereinafter referred to as the business information value for ease of description).
  • normalization is performed based on the following:
  • Si represents the fluctuation value of the node
  • ri represents the initial fluctuation value corresponding to the node
  • K is used to represent the total number of nodes in the graph association structure.
  • Figure 5 is a schematic diagram of the fluctuation value of a node in a graph association structure provided by an embodiment of the present invention.
  • the quadrilateral pattern in Figure 5 is used to represent the node whose transaction subject is the acquiring institution
  • the pentagonal pattern is used to represent the node whose transaction subject is the payment subsidiary
  • the hexagonal pattern is used to represent the node whose transaction subject is the payment head office.
  • Step B Based on the associations between transaction entities and the second sub-rule in the preset abnormality analysis rule, determine the impact value of the fluctuation of business information of each node on the influence of other nodes; the second sub-rule is used to calculate the degree to which the lower-level nodes are affected by the fluctuation of the upper-level nodes.
  • the lower-level nodes and the upper-level nodes are determined based on the associations between transaction entities;
  • the second sub-rule is determined based on the following formula:
  • ep ij represents the influence value of node i relative to node j
  • ⁇ i represents the change value of the business information value of node i between two moments
  • ⁇ j represents the change value of the business information value of node j between two moments
  • e it represents the business information value of node i at time t
  • e it' represents the business information value of node i at time t'
  • e jt represents the business information value of node j at time t
  • e jt' represents the business information value of node j at time t'
  • node i and node j are arbitrary nodes in the graph association structure.
  • the impact value of the fluctuation of the business information of each node affected by other nodes can be determined based on the association relationship between the transaction entities and the aforementioned second sub-rule.
  • Figure 6 is a schematic diagram of the influence value of a node in a graph association structure provided by an embodiment of the present invention.
  • the quadrilateral pattern in Figure 6 is used to represent the node whose transaction subject is the acquiring institution
  • the pentagonal pattern is used to represent the node whose transaction subject is the payment subsidiary
  • the hexagonal pattern is used to represent the node whose transaction subject is the payment head office.
  • Step C Determine the corresponding abnormal value of each node based on the fluctuation value and corresponding impact value of each node.
  • the electronic device may use the influence value of an associated node associated with the node as a basis for constructing an initial change iteration matrix.
  • the initial change iteration matrix may be expressed as:
  • ⁇ represents the initial alternation matrix
  • ⁇ i,j is a matrix factor in ⁇
  • ep ij represents the influence value of node i relative to node j
  • nodes i and j are any nodes in the graph association structure, that is, i, j ⁇ K.
  • no association relationship between node i and node j when there is no association relationship between node i and node j,
  • the electronic device can substitute the initial abnormality iteration matrix and the fluctuation value corresponding to each node into the third sub-rule of the preset abnormality analysis rule to determine the abnormality value corresponding to each node respectively; the third sub-rule is used to iteratively optimize the fluctuation value of the node in combination with the influence values corresponding to all nodes that have an associated relationship with the node.
  • the third sub-rule is determined based on the following formula: H 1 ⁇ S′+d H 2 ⁇ H 1 +d ... H n ⁇ H n-1 +d
  • H represents the intermediate variable in the iterative process
  • Hn represents the result of the nth iteration
  • n is determined by the Euclidean distance between Hn and Hn -1.
  • ⁇ represents the initial dynamic iteration matrix
  • S′ represents the set of fluctuation values for all nodes
  • S′ ⁇ S1 , S2 , ..., SK ⁇
  • d is a nonzero adjustment coefficient
  • i and j are positive integers.
  • the final node's abnormal value distribution is H n is
  • the change value of node 1 is H 1 n, which is the first element of vector H n .
  • the electronic device can also sort the abnormal values corresponding to all nodes from large to small to obtain the abnormal values of all nodes after sorting.
  • Figure 7 is a schematic diagram of a method for calculating the abnormal value corresponding to a node provided by an embodiment of the present invention.
  • the quadrilateral pattern in Figure 7 is used to represent the node whose transaction subject is the acquiring institution
  • the pentagonal pattern is used to represent the node whose transaction subject is the payment subsidiary
  • the hexagonal pattern is used to represent the node whose transaction subject is the payment head office.
  • Step 303 When the change value corresponding to the first node is greater than a preset threshold, the first node is determined to be a change node, and the transaction subject indicated by the first node is determined to be the change transaction subject.
  • a preset threshold value may be determined based on historical experience, such as 0.5.
  • the middle value of the top four ranked values may be used as the preset threshold value.
  • the preset threshold value may also be determined based on other methods, which are not limited in the embodiment of the present invention.
  • the electronic device after the electronic device determines the preset threshold, it can filter out the first node whose corresponding change value is greater than the preset threshold from all nodes, and use the first node as the change node.
  • the first node can be a node or a group of nodes.
  • the changed node after determining the changed node, the changed node can be placed back into the constructed graph association structure for restoration, thereby obtaining a clear association tracing path to enhance the convenience of attribution analysis of transaction entities.
  • the electronic device can screen candidate paths including the first node based on the graph association structure, and use the candidate paths as abnormal paths; analyze the abnormal paths to obtain abnormal analysis results; the abnormal analysis results are used to indicate the influencing nodes associated with the abnormal nodes, and optimize the business of the transaction subject corresponding to the influencing nodes based on the business information corresponding to the abnormal nodes.
  • FIG 8 is a schematic diagram of an abnormal path provided by an embodiment of the present invention.
  • the quadrilateral pattern in Figure 8 is used to represent a node where the transaction subject is an acquirer
  • the pentagonal pattern is used to represent a node where the transaction subject is a payment subsidiary
  • the hexagonal pattern is used to represent a node where the transaction subject is a payment head office.
  • the node represented by the fully filled quadrilateral pattern in Figure 8 is the first node, and this node, the node represented by the fully filled pentagonal pattern, and the node represented by the fully filled hexagonal pattern form an abnormal path.
  • the advantages of the graph association structure are utilized to further restore the association tracing path of attribution analysis, that is, the change path, thereby improving the convenience of transaction entities in performing change attribution analysis, thereby improving the strategy optimization effect on actual business.
  • FIG9 it is a schematic structural diagram of a data processing device 900, which may include:
  • a construction unit 901 is configured to construct a graph association structure with transaction entities in a target business scenario as nodes and association relationships between transaction entities as edges;
  • Determining unit 902 is configured to determine an abnormality value corresponding to each node in the graph association structure based on the business information of the transaction subject indicated by each node, the association relationship between the transaction subjects, and a preset abnormality analysis rule; wherein each abnormality value is used to indicate the degree of abnormal fluctuation in the transaction of the transaction subject indicated by the node; the abnormal fluctuation degree is determined based on the transaction subject's own business information and the business information of other transaction subjects with which it has an association relationship;
  • the processing unit 903 is configured to determine that the first node is a changed node when the change value corresponding to the first node is greater than a preset threshold, and determine the transaction subject indicated by the first node as the changed transaction subject.
  • the determining unit 902 is specifically configured to:
  • the first sub-rule is used to perform magnitude normalization processing on the initial fluctuation values of the nodes obtained based on business information of different magnitudes;
  • the second sub-rule is used to calculate the degree to which the lower-level nodes are affected by the fluctuation of the upper-level nodes, and the lower-level nodes and the upper-level nodes are determined based on the associations between the transaction entities;
  • the abnormal value corresponding to each node is determined.
  • the determining unit 902 is specifically configured to:
  • the preset time series attribution model determines the initial fluctuation value of a transaction subject based on the business information of the transaction subject within a preset time period and a preset magnitude fluctuation evaluation rule;
  • the preset magnitude fluctuation evaluation rule includes multiple mapping relationships, each mapping relationship including a numerical range corresponding to business information of different magnitudes and an initial fluctuation value corresponding to the numerical range;
  • the normalization is implemented based on the following method:
  • Si represents the fluctuation value of the node
  • ri represents the initial fluctuation value corresponding to the node
  • K is used to represent the total number of nodes in the graph association structure.
  • the second sub-rule is determined based on the following formula:
  • ep ij represents the influence value of node i relative to node j
  • ⁇ i represents the change value of the business information value of node i between two moments
  • ⁇ j represents the change value of the business information value of node j between two moments
  • e it represents the business information value of node i at time t
  • e it' represents the business information value of node i at time t'
  • e jt represents the business information value of node j at time t
  • e jt' represents the business information value of node j at time t'
  • node i and node j are any nodes in the graph association structure.
  • the determining unit 902 is specifically configured to:
  • the third sub-rule of the preset abnormality analysis rule is substituted to determine the abnormality value corresponding to each node respectively; the third sub-rule is used to iteratively optimize the fluctuation value of the node in combination with the influence values corresponding to all nodes that have an associated relationship with the node.
  • the third sub-rule is determined based on the following formula: H n ⁇ H n-1 +d
  • Hn represents the set of fluctuation values of all nodes
  • n is used to represent the number of iterations.
  • S′ represents the set of fluctuation values of all nodes
  • S′ ⁇ S1 , S2 , ..., SK ⁇
  • ⁇ represents the initial fluctuation iteration matrix
  • ⁇ i ,j are the matrix factors in ⁇
  • ep ij represents the influence value of node i relative to node j
  • node i and node j are arbitrary nodes in the graph association structure
  • S k represents the fluctuation value of node k
  • d is a non-zero adjustment coefficient
  • i and j are positive integers.
  • the apparatus further includes an optimization unit configured to:
  • the abnormal path is analyzed to obtain an abnormal analysis result; the abnormal analysis result is used to indicate the impact node associated with the abnormal node, and based on the business information corresponding to the abnormal node, the business of the transaction subject corresponding to the impact node is optimized.
  • each module or unit
  • the functions of each module can be implemented in the same or multiple software or hardware.
  • aspects of the present invention may be implemented as systems, methods, or program products. Therefore, various aspects of the present invention may be implemented in the following forms: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which may be collectively referred to herein as "circuits,” “modules,” or “systems.”
  • an electronic device is also provided in the embodiment of the present invention.
  • the principle of solving the problem by the electronic device is similar to the method of the above-mentioned embodiment. Therefore, the implementation of the electronic device can refer to the implementation of the above-mentioned method, and the repeated parts will not be repeated.
  • FIG. 10 is a block diagram of an electronic device 1000 according to an exemplary embodiment.
  • the electronic device in the embodiment of the present invention includes at least one processor 1001 and a memory 1002 connected to the at least one processor 1001.
  • the specific connection medium between the processor 1001 and the memory 1002 is not limited in the embodiment of the present invention.
  • FIG. 10 takes the example of a bus connection between the processor 1001 and the memory 1002.
  • the bus is represented by a bold line in FIG. 10 .
  • the connection methods between other components are merely schematic and are not intended to be limiting. Buses can be divided into address buses, data buses, control buses, etc. For ease of illustration, FIG. 10 uses only one bold line to represent them, but this does not mean that there is only one bus or only one type of bus.
  • the memory 1002 stores instructions that can be executed by at least one processor 1001.
  • the at least one processor 1001 can execute the steps included in the aforementioned data processing method by executing the instructions stored in the memory 1002.
  • the processor 1001 is the control center of the electronic device. It can use various interfaces and lines to connect various parts of the entire fault detection device. By running or executing instructions stored in the memory 1002 and calling data stored in the memory 1002, the various functions of the electronic device and processing data, the electronic device can be monitored as a whole.
  • the processor 1001 may include one or more processing units.
  • the processor 1001 may integrate an application processor and a modem processor. Among them, the processor 1001 mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 1001.
  • the processor 1001 and the memory 1002 can be implemented on the same chip. In some embodiments, they can also be implemented separately on independent chips.
  • the processor 1001 can be a general-purpose processor, such as a central processing unit (CPU), a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, and can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention.
  • a general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present invention can be directly implemented as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor.
  • Memory 1002 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs, and modules.
  • Memory 1002 may include at least one type of storage medium, such as flash memory, a hard disk, a multimedia card, a card-type memory, random access memory (RAM), static random access memory (SRAM), programmable read-only memory (PROM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), magnetic storage, a magnetic disk, an optical disk, and the like.
  • RAM random access memory
  • SRAM static random access memory
  • PROM programmable read-only memory
  • ROM read-only memory
  • EEPROM electrically erasable programmable read-only memory
  • Memory 1002 is any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.
  • Memory 1002 in the embodiments of the present invention
  • the electronic device 104 includes a display unit 1140, a processor 1180, and a memory 1120.
  • the display unit 1140 includes a display panel 1141 for displaying information input by a user or information provided to a user, as well as various object selection interfaces of the electronic device 104.
  • the display panel 1141 is mainly used to display relevant operation interfaces and shortcut windows of the analysis system installed in the electronic device 104.
  • the display panel 1141 can be configured in the form of an LCD (Liquid Crystal Display) or an OLED (Organic Light-Emitting Diode).
  • Processor 1180 is configured to read a computer program and then execute the method defined by the computer program. For example, processor 1180 reads an application program for an analysis system, thereby running the analysis system on electronic device 104 and displaying the relevant operation interface of the analysis system on display unit 1140.
  • Processor 1180 may include one or more general-purpose processors and may also include one or more DSPs (Digital Signal Processors) to perform relevant operations to implement the technical solutions provided by the embodiments of the present invention.
  • DSPs Digital Signal Processors
  • the memory 1120 generally includes internal memory and external memory.
  • the internal memory may be random access memory (RAM), read-only memory (ROM), and cache memory (CACHE).
  • the external memory may be a hard disk, an optical disk, a USB disk, a floppy disk, or a tape drive.
  • the memory 1120 is used to store computer programs and other data.
  • the computer programs include applications corresponding to various software, etc.
  • Other data may include data generated after the operating system or application is run.
  • the data includes system data (such as configuration parameters of the operating system) and user data.
  • program instructions are stored in the memory 1120, and the processor 1180 executes the program instructions in the memory 1120 to implement the functions of the data processing method discussed above.
  • the electronic device 104 may also include a display unit 1140 for receiving input digital information, character information, or contact touch operations/contactless gestures, and generating signal inputs related to user settings and function control of the electronic device 104.
  • the display unit 1140 may include a display panel 1141.
  • the display panel 1141 such as a touch screen, can collect user touch operations on or near it (such as operations performed by a target object using a finger, stylus, or any other suitable object or accessory on or on the display panel 1141) and drive corresponding connected devices according to a pre-set program.
  • the display panel 1141 may include two parts: a touch detection device and a touch controller.
  • the touch detection device detects the user's touch direction and detects signals generated by the touch operation, transmitting the signals to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into touch point coordinates, and then sends it to the processor 1180. It can also receive commands sent by the processor 1180 and execute them.
  • the touch detection device in the display panel 1141 detects the touch operation, and sends a signal corresponding to the detected touch operation to the touch controller.
  • the touch controller converts the signal into touch coordinates and sends them to the processor 1180.
  • the processor 1180 determines the target business scenario selected by the user based on the received touch coordinates, and controls the display panel 1141 to display the transaction subject in the target business scenario.
  • the display panel 1141 can be implemented using various types, such as resistive, capacitive, infrared, and surface acoustic wave.
  • the electronic device 104 can also include an input unit 1130.
  • the input unit 1130 can include, but is not limited to, one or more of a physical keyboard, function keys (such as volume control keys, power keys, etc.), a trackball, a mouse, and a joystick.
  • FIG11 shows an example of the input unit 1130 including an image input device 1131 and other input devices 1132.
  • the electronic device 104 may also include a power supply 1190 for powering other modules, an audio circuit 1160, a near-field communication module 1170, and an RF circuit 1110.
  • the electronic device 104 may also include one or more sensors 1150, such as an accelerometer, a light sensor, a pressure sensor, etc.
  • the audio circuit 1160 specifically includes a speaker 1161 and a microphone 1162.
  • a user can use voice control.
  • the electronic device 104 can collect the user's voice through the microphone 1162, can be controlled by the user's voice, and play a corresponding prompt tone through the speaker 1161 when it is necessary to prompt the user that there is an abnormality in the business information.
  • a storage medium including operations is further provided, for example, a memory 1002 including operations, and the operations may be executed by the processor 1001 of the electronic device 1000 to perform the above method.
  • the storage medium may be a non-transitory computer-readable storage medium, for example, a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.
  • various aspects of the data processing method provided by the present invention can also be implemented in the form of a program product, which includes program code.
  • the program product is run on an electronic device, the program code is used to enable the electronic device to execute the steps of the data processing method according to various exemplary embodiments of the present invention described above in this specification.
  • the electronic device can execute the steps shown in Figure 3.
  • the program product may employ any combination of one or more readable media.
  • the readable medium may be a readable signal medium or a readable storage medium.
  • the readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.
  • the program product of an embodiment of the present invention may be a portable compact disc read-only memory (CD-ROM) and include program code, and may be run on a server.
  • CD-ROM compact disc read-only memory
  • the program product of the present invention is not limited thereto.
  • a readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with a command execution system, apparatus, or device.
  • a readable signal medium may include a data signal transmitted in baseband or as part of a carrier wave, which carries readable program code. Such a transmitted data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof.
  • a readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with a command execution system, apparatus, or device.
  • the program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Engineering & Computer Science (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Technology Law (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Debugging And Monitoring (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

本发明公开了一种数据处理方法、装置、电子设备及存储介质，该方法为：构建以目标业务场景中的交易主体为节点、交易主体间的关联关系为边的图关联结构；基于图关联结构中每个节点所指示的交易主体的业务信息、交易主体间的关联关系和预设异动分析规则，确定每个节点对应的异动值；每个异动值用于指示一个节点所指示交易主体交易的异常波动程度；异常波动程度基于交易主体的自身业务信息以及与其具备关联关系的其他交易主体的业务信息所确定；当第一节点对应的异动值大于预设阈值时，确定第一节点为异动节点，并将第一节点所指示的交易主体确定为异动交易主体。利用图关联结构并融合多种因素确定异动值以确定比较结果，快速、精准地确定异动节点。

Description

一种数据处理方法、装置、电子设备及存储介质
相关申请的交叉引用
本申请要求在2024年04月10日提交中华人民共和国国家知识产权局、申请号为202410432948.8、申请名称为“一种数据处理方法、装置、电子设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明涉及计算机技术领域，尤其涉及一种数据处理方法、装置、电子设备及存储介质。
背景技术
目前，庞大交易网络中，每天都将面临产生海量的交易数据以及由交易主体构成的复杂交易行为关系。因此，当交易数据中出现交易笔数突减等异动表现时，需要确定出可能存在异动表现的交易主体，将该交易主体作为待优化的异动交易主体，从而调整优化对该异动交易主体具体的经营策略，确保交易网络的正常运行。
因此，如何确定待优化的异动交易主体，成为亟待解决的技术问题。
发明内容
本发明实施例中提供了一种数据处理方法、装置、电子设备及存储介质，使得确定待优化的异动交易主体的方法的效率和准确度更高。
第一方面，本发明实施例提供一种数据处理方法，所述方法包括：
构建以目标业务场景中的交易主体为节点、交易主体间的关联关系为边的图关联结构；
基于所述图关联结构中每个所述节点所指示的交易主体的业务信息、交易主体间的关联关系和预设异动分析规则，确定每个所述节点对应的异动值；其中，每个所述异动值用于指示一个节点所指示交易主体交易的异常波动程度；所述异常波动程度基于交易主体的自身业务信息以及与其具备关联关系的其他交易主体的业务信息所确定；
当第一节点对应的异动值大于预设阈值时，确定所述第一节点为异动节点，并将所述第一节点所指示的交易主体确定为异动交易主体。
在一种可能的实施方式中，基于所述图关联结构中每个所述节点所指示的交易主体的业务信息、交易主体间的关联关系和预设异动分析规则，确定每个所述节点对应的异动值，包括：
分别基于所述图关联结构中每个所述节点所指示的交易主体的业务信息和所述预设异动分析规则中的第一子规则，确定每个所述节点的波动值；所述第一子规则用于对基于不同量级的业务信息所获得节点的初始波动值进行量级归一化处理；
分别基于所述交易主体间的关联关系和所述预设异动分析规则中的第二子规则，确定每个所述节点的业务信息的波动受其他节点影响的影响值；所述第二子规则用于计算下层节点被上层节点的波动所影响的程度，所述下层节点和上层节点基于交易主体间的关联关系所确定；
根据每个所述节点的波动值和对应的影响值，确定每个所述节点对应的异动值。
在一种可能的实施方式中，分别基于所述图关联结构中每个所述节点所指示的交易主体的业务信息和所述预设异动分析规则中的第一子规则，确定每个所述节点的波动值，包括：
分别将每个所述节点所指示交易主体的业务信息输入预设时序归因模型，获得所述预设时序归因模型输出的每个所述节点对应的初始波动值；所述预设时序归因模型基于一个交易主体在预设时间段内的业务信息和预设量级波动评价规则，确定所述交易主体的初始波动值；所述预设量级波动评价规则包括多条映射关系，不同映射关系包括不同量级的业务信息对应的数值范围，以及与所述数值范围对应的初始波动值；
对每个所述交易主体对应的初始波动值进行归一化处理，获得每个所述节点的波动值。在一种可能的实施方式中，所述归一化处理基于以下方式实现：
其中，Si表示节点的波动值，ri表示节点对应的初始波动值，K用于表示所述图关联结构中的节点总数量。
在一种可能的实施方式中，所述第二子规则，基于以下公式确定：
其中，epij表示节点i相对于节点j的影响值，Δi表示节点i的两个时刻间的业务信息值的变化值，Δj表示节点j的两个时刻间的业务信息值的变化值，eit表示t时刻节点i的业务信息值，eit’表示t’时刻节点i的业务信息值，ejt表示t时刻节点j的业务信息值，ejt’表示t’时刻节点j的业务信息值，节点i和节点j为所述图关联结构中任意节点。
在一种可能的实施方式中，根据每个所述节点的波动值和对应的影响值，确定每个所述节点对应的异动值，包括：
将与一个所述节点存在关联关系的一个关联节点的影响值，作为一个矩阵因素，构建初始异动迭代矩阵；
根据所述初始异动迭代矩阵和每个所述节点对应的波动值代入所述预设异动分析规则的第三子规则中，分别确定每个所述节点对应的异动值；所述第三子规则用于结合所有与节点存在关联关系的节点对应的影响值对节点的波动值进行迭代优化。
在一种可能的实施方式中，所述第三子规则基于以下公式确定：
Hn←θHn-1+d
其中，Hn表示所有节点的异动值的集合，n用于表征迭代轮数，当n等于1时，H1←θS′+d，S′表示所有节点的波动值的集合，epij表示节点i相对于节点j的影响值，节点i和节点j为所述图关联结构中任意节点，Sk表示节点k的波动值，d为非零调节系数，i，j为正整数。
在一种可能的实施方式中，确定所述第一节点为异动节点之后，所述方法还包括：
基于所述图关联结构，筛选包括第一节点的候选路径，将所述候选路径作为异动路径；
对所述异动路径进行分析，获得异动分析结果；所述异动分析结果用于指示与所述异动节点关联的影响节点，并基于所述异动节点所对应的业务信息对所述影响节点对应的交易主体的业务进行优化。
第二方面，本发明实施例提供一种数据处理装置，所述装置包括：
构建单元，用于构建以目标业务场景中的交易主体为节点、交易主体间的关联关系为边的图关联结构；
确定单元，用于基于所述图关联结构中每个所述节点所指示的交易主体的业务信息、交易主体间的关联关系和预设异动分析规则，确定每个所述节点对应的异动值；其中，每个所述异动值用于指示一个节点所指示交易主体交易的异常波动程度；所述异常波动程度基于交易主体的自身业务信息以及与其具备关联关系的其他交易主体的业务信息所确定；
处理单元，用于当第一节点对应的异动值大于预设阈值时，确定所述第一节点为异动节点，并将所述第一节点所指示的交易主体确定为异动交易主体。
在一种可能的实施方式中，所述确定单元，具体用于：
分别基于所述图关联结构中每个所述节点所指示的交易主体的业务信息和所述预设异动分析规则中的第一子规则，确定每个所述节点的波动值；所述第一子规则用于对基于不同量级的业务信息所获得节点的初始波动值进行量级归一化处理；
分别基于所述交易主体间的关联关系和所述预设异动分析规则中的第二子规则，确定每个所述节点的业务信息的波动受其他节点影响的影响值；所述第二子规则用于计算下层节点被上层节点的波动所影响的程度，所述下层节点和上层节点基于交易主体间的关联关系所确定；
根据每个所述节点的波动值和对应的影响值，确定每个所述节点对应的异动值。
在一种可能的实施方式中，所述确定单元，具体用于：
分别将每个所述节点所指示交易主体的业务信息输入预设时序归因模型，获得所述预设时序归因模型输出的每个所述节点对应的初始波动值；所述预设时序归因模型基于一个交易主体在预设时间段内的业务信息和预设量级波动评价规则，确定所述交易主体的初始波动值；所述预设量级波动评价规则包括多条映射关系，不同映射关系包括不同量级的业务信息对应的数值范围，以及与所述数值范围对应的初始波动值；
对每个所述交易主体对应的初始波动值进行归一化处理，获得每个所述节点的波动值。在一种可能的实施方式中，所述归一化处理基于以下方式实现：
其中，Si表示节点的波动值，ri表示节点对应的初始波动值，K用于表示所述图关联结构中的节点总数量。
在一种可能的实施方式中，所述第二子规则，基于以下公式确定：
其中，epij表示节点i相对于节点j的影响值，Δi表示节点i的两个时刻间的业务信息值的变化值，Δj表示节点j的两个时刻间的业务信息值的变化值，eit表示t时刻节点i的业务信息值，eit’表示t’时刻节点i的业务信息值，ejt表示t时刻节点j的业务信息值，ejt’表示t’时刻节点j的业务信息值，节点i和节点j为所述图关联结构中任意节点。
在一种可能的实施方式中，所述确定单元，具体用于：
将与一个所述节点存在关联关系的一个关联节点的影响值，作为一个矩阵因素，构建初始异动迭代矩阵；
根据所述初始异动迭代矩阵和每个所述节点对应的波动值代入所述预设异动分析规则的第三子规则中，分别确定每个所述节点对应的异动值；所述第三子规则用于结合所有与节点存在关联关系的节点对应的影响值对节点的波动值进行迭代优化。
在一种可能的实施方式中，所述第三子规则基于以下公式确定：
Hn←θHn-1+d
其中，Hn表示所有节点的异动值的集合，n用于表征迭代轮数，当n等于1时，H1←θS′+d，S′表示所有节点的波动值的集合，epij表示节点i相对于节点j的影响值，节点i和节点j为所述图关联结构中任意节点，Sk表示节点k的波动值，d为非零调节系数，i，j为正整数。
在一种可能的实施方式中，确定所述第一节点为异动节点之后，所述装置还包括优化单元，用于：
基于所述图关联结构，筛选包括第一节点的候选路径，将所述候选路径作为异动路径；
对所述异动路径进行分析，获得异动分析结果；所述异动分析结果用于指示与所述异动节点关联的影响节点，并基于所述异动节点所对应的业务信息对所述影响节点对应的交易主体的业务进行优化。
第三方面，本发明实施例提供了一种电子设备，包括至少一个处理器；以及与所述至少一个处理器通信连接的存储器；其中，所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行本发明第一方面实施例提供的任一方法。
第四方面，本发明实施例提供了一种计算机存储介质，其中，所述计算机可读存储介质存储有计算机程序，所述计算机程序用于使计算机执行本发明第一方面实施例提供的任一方法。
第五方面，本发明实施例提供了一种计算机程序产品，所述计算机程序产品包括：计算机程序代码，当所述计算机程序代码在计算机上运行时，使得计算机执行第一方面实施例提供的任一方法。
本发明有益效果如下：
在本发明实施例中，可以构建以目标业务场景中的交易主体为节点、交易主体间的关联关系为边的图关联结构；进一步的，基于图关联结构中每个节点所指示的交易主体的业务信息、交易主体间的关联关系和预设异动分析规则，确定每个节点对应的异动值；其中，每个异动值用于指示一个节点所指示交易主体交易的异常波动程度；异常波动程度基于交易主体的自身业务信息以及与其具备关联关系的其他交易主体的业务信息所确定。可见，本发明实施例中从图关联结构的角度出发，确定节点对应的异动值，且异动值的确定同时考虑了交易主体的自身业务信息以及与其具备关联关系的其他交易主体的业务信息这两个方面，提升了对异动表现的归因分析的准确度。这样，当第一节点对应的异动值大于预设阈值时，确定第一节点为异动节点，并将第一节点所指示的交易主体确定为异动交易主体，从而可以准确且高效的确定导致异动事项的异动交易主体。
本发明的其它特征和优点将在随后的说明书中阐述，并且，部分地从说明书中变得显而易见，或者通过实施本发明而了解。本发明的目的和其他优点可通过在所写的说明书、权利要求书、以及附图中所特别指出的结构来实现和获得。
附图说明
为了更清楚地说明本发明实施例或相关技术中的技术方案，下面将对实施例或相关技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据提供的附图获得其他的附图。
图1为本发明实施例中的一种应用场景的一个可选的示意图；
图2为本发明实施例中的一种应用场景的一个可选的示意图；
图3为本发明实施例中的一种数据处理方法流程示意图；
图4为本发明实施例中一种图关联结构的示意图；
图5为本发明实施例中的一种图关联结构中节点的波动值的示意图；
图6为本发明实施例中的一种图关联结构中节点的影响值的示意图；
图7为本发明实施例中的一种计算节点对应的异动值的示意图；
图8为本发明实施例中的一种异动路径的示意图；
图9为本发明实施例中的一种数据处理装置的组成结构示意图；
图10为本发明实施例中的一种电子设备的一种结构示意图；
图11为本发明实施例中的一种电子设备的又一种结构示意图。
具体实施方式
为使本发明的目的、技术方案和优点更加清楚明白，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。在不冲突的情况下，本发明中的实施例及实施例中的特征可以相互任意组合。并且，虽然在流程图中示出了逻辑顺序，但是在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤。
本发明的说明书和权利要求书及上述附图中的术语，第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本发明的实施例能够在除了这里图示或描述的那些以外的顺序实施。
本发明中所用的词语“示例性”的意思为“用作例子、实施例或说明性”。作为“示例性”所说明的任何实施例不必解释为优于或好于其它实施例。
以下结合附图对本发明的示范性实施例做出说明，其中包括本发明实施例的各种细节以助于理解，应当将它们认为仅仅是示范性的。因此，本领域普通技术人员应当认识到，可以对这里描述的实施例做出各种改变和修改，而不会背离本发明公开的范围。同样，为了清楚和简明，以下的描述中省略了对公知功能和结构的描述。需要说明的是，在本发明实施例中，可能提及某些软件、组件、模型等业界已有方案，应当将它们认为是示范性的，其目的仅仅是为了说明本发明技术方案实施中的可行性，但并不意味着申请人已经或者必然用到了该方案。
本发明技术方案中，对数据的采集、传播、使用等，均符合国家相关法律法规要求。
目前，如前所述，如何确定待优化的异动交易主体，成为亟待解决的技术问题。
鉴于此，本发明实施例提供一种数据处理方法，通过该方法，可以构建以目标业务场景中的交易主体为节点、交易主体间的关联关系为边的图关联结构；进一步的，基于图关联结构中每个节点所指示的交易主体的业务信息、交易主体间的关联关系和预设异动分析规则，确定每个节点对应的异动值；其中，每个异动值用于指示一个节点所指示交易主体交易的异常波动程度；异常波动程度基于交易主体的自身业务信息以及与其具备关联关系的其他交易主体的业务信息所确定。可见，本发明实施例中从图关联结构的角度出发，确定节点对应的异动值，且异动值的确定同时考虑了交易主体的自身业务信息以及与其具备关联关系的其他交易主体的业务信息这两个方面，提升了对异动表现的归因分析的准确度。这样，当第一节点对应的异动值大于预设阈值时，确定第一节点为异动节点，并将第一节点所指示的交易主体确定为异动交易主体，从而可以准确且高效的确定导致异动事项的异动交易主体。
在介绍完本发明实施例的设计思想之后，下面对本发明实施例的技术方案能够适用的应用场景做一些简单介绍，需要说明的是，以下介绍的应用场景仅用于说明本发明实施例而非限定。在具体实施过程中，可以根据实际需要灵活地应用本发明实施例提供的技术方案。
在本发明实施例中，本发明实施例提供的数据处理方法可以应用于任何需要进行异动归因分析的业务场景，例如对A业务的软件系统中各个功能模块进行异动归因分析的业务场景，对网络平台中各个功能单元进行异动归因分析的业务场景等，又例如对金融领域的支付系统中各个主体进行异动归因分析的业务场景、金融领域的借贷系统中各个主体进行异动归因分析的业务场景，制造领域的制造系统中各个主体进行异动归因分析的业务场景、管理领域的企业管理系统中各个主体进行异动归因分析的业务场景等，本发明实施例中对此不做限定。
请参阅图1所示，图1为本发明实施例的技术方案能够适用的一种应用场景。在该场景示意图中，包括多个收单机构对应的设备101、多个支付子公司对应的设备102、支付总公司对应的设备103以及用于对支付系统进行异动归因分析的分析系统对应的设备104。需要说明的是，收单机构、支付子公司以及支付总公司都可以称作交易主体。
其中，每个分析系统对应的设备104均可以包括一个或多个处理器1041、存储器1042以及与设备交互的I/O接口1043等。以及，设备101、设备102设备103以及设备104之间，以及各个设备之间均可以通过一个或者多个网络105进行直接或间接的通信连接。
需要说明的是，在本发明实施例中，使用设备101-1、设备101-2、……、设备101-n的对象1、对象2、……、对象n，n为正整数，可以同时发起支付交易，当然，也可以是对象1先发起交易，对象2再发起交易，本发明实施例中对此不做限制，从而分析系统可以接收大量并发的支付交易数据，对支付交易数据进行异动归因分析，即确定支付交易数据中是否存在异动表现。其中，对支付交易数据进行异动归因分析的具体方案可以参见本发明实施例提供的数据处理方法，后文详细描述，这里不在赘述。
又例如，请参阅图2所示，图2为本发明实施例的技术方案能够适用的另一种应用场景，在该场景示意图中，包括多个售卖机构对应的设备201、多个制造子公司对应的设备202、制造总公司对应的设备203以及用于对售卖系统进行异动归因分析的分析系统对应的设备104。需要说明的是，售卖机构、制造子公司以及制造总公司都可以称作交易主体。
其中，每个分析系统对应的设备104均可以包括一个或多个处理器1041、存储器1042以及与设备交互的I/O接口1043等。以及，设备201、设备202设备203以及设备104之间，以及各个设备之间均可以通过一个或者多个网络105进行直接或间接的通信连接。
需要说明的是，在本发明实施例中，使用设备201-1、设备201-2、……、设备201-n的售卖机构1、售卖机构2、……、售卖机构n，n为正整数，可以同时发起售卖交易，当然，也可以是售卖机构1先发起售卖交易，售卖机构2再发起售卖交易，本发明实施例中对此不做限制，从而分析系统可以接收大量并发的售卖交易数据，对售卖交易数据进行异动归因分析，即确定售卖交易数据中是否存在异动表现。其中，对售卖交易数据进行异动归因分析的具体方案可以参见本发明实施例提供的数据处理方法，后文详细描述，这里不在赘述。
其中，图1、图2中的各个设备可以为手机、平板电脑(PAD)、个人计算机(Personal computer，PC)、智能电视、智能手表、智能音箱、智能车载设备以及可穿戴设备等，但并不局限于此，这些设备可以具有登录并使用学习网站的功能。
以及，图1、图2中设备也可以是独立的物理服务器，也可以是多个物理服务器构成的服务器集群或者分布式系统，还可以是以提供云服务、云数据库、云计算、云函数、云存储、网络服务、云通信、中间件服务、域名服务、安全服务、内容分发网络(Content Delivery Network，CDN)、以及大数据和人工智能平台等基础云计算服务的云服务器，但并不局限于此。
该网络105可以是有线网络，也可以是无线网络，例如无线网络可以是移动蜂窝网络，或者可以是无线保真(Wireless-Fidelity，WIFI)网络，当然还可以是其他可能的网络，本发明实施例对此不做限制。
当然，本发明实施例提供的方法并不限用于图1和图2所示的应用场景中，还可以用于其他可能的应用场景，本发明实施例并不进行限制。
为进一步说明本发明实施例提供的技术方案，下面结合附图以及具体实施方式对此进行详细的说明。虽然本发明实施例提供了如下述实施例或附图所示的方法操作步骤，但基于常规或者无需创造性的劳动在所述方法中可以包括更多或者更少的操作步骤。在逻辑上不存在必要因果关系的步骤中，这些步骤的执行顺序不限于本发明实施例提供的执行顺序。所述方法在实际的处理过程中或者装置执行时，可按照实施例或者附图所示的方法顺序执行或者并行执行。
请参见图3，图3为本发明实施例中的一种数据处理方法流程示意图，其中，数据处理方法可以由前述图1、2中的设备104执行，且设备104上部署有异动归因分析的分析系统。
步骤301：构建以目标业务场景中的交易主体为节点、交易主体间的关联关系为边的图关联结构。
在本发明实施例中，电子设备可以先确定目标业务场景，后文中以目标业务场景为金融领域的支付系统的业务场景为例进行说明。其中，金融领域的支付系统的业务场景包括支付总公司、多个支付子公司以及多个收单机构，支付总公司、支付子公司以及收单机构可以理解为产生交易数据的主体，为了便于描述，后文中将该主体称作交易主体。然后，可以基于业务信息确定支付总公司、多个支付子公司以及多个收单机构之间的关联关系，例如，业务信息为商户数，则可以确定支付总公司和支付子公司存在商户数的关联关系，支付子公司和收单机构间存在商户数的关联关系。又例如，业务信息为交易笔数，则可以确定支付总公司和支付子公司存在交易笔数的关联关系，支付子公司和收单机构间存在交易笔数的关联关系。
进一步的，可以构建以目标业务场景中的交易主体为节点、交易主体间的关联关系为边的图关联结构。
例如，请参见图4，图4为本发明实施例提供的一种图关联结构的示意图。其中，图4中的四边形图案用于表征交易主体为收单机构的节点、五边形图案用于表征交易主体为支付子公司的节点、六边形图案用于表征交易主体为支付总公司的节点。
可选的，图关联结构还可以以数学的形式化表达，具体如下：
G＝{V,ε}
其中，V表示图关联结构包括的节点集合，ε表示图关联结构的边集合。
步骤302：基于图关联结构中每个节点所指示的交易主体的业务信息、交易主体间的关联关系和预设异动分析规则，确定每个节点对应的异动值；其中，每个异动值用于指示一个节点所指示交易主体交易的异常波动程度；异常波动程度基于交易主体的自身业务信息以及与其具备关联关系的其他交易主体的业务信息所确定。
在本发明实施例中，电子设备可以采用但不限于以下步骤每个节点对应的异动值：
步骤A：分别基于图关联结构中每个节点所指示的交易主体的业务信息和预设异动分析规则中的第一子规则，确定每个节点的波动值；第一子规则用于对基于不同量级的业务信息所获得节点的初始波动值进行量级归一化处理。
在本发明实施例中，电子设备可以分别将每个节点所指示交易主体的业务信息输入预设时序归因模型，获得预设时序归因模型输出的每个节点对应的初始波动值；其中，预设时序归因模型基于一个交易主体在预设时间段内的业务信息和预设量级波动评价规则，确定交易主体的初始波动值。其中，预设量级波动评价规则包括多条映射关系，不同映射关系包括不同量级的业务信息对应的数值范围，以及与数值范围对应的初始波动值。
例如，假设节点为收单机构A，且业务信息为收单机构A在2021-2023这2年内的按月统计的交易笔数，则向预设时序归因模型输入的是收单机构A在2021-2023这2年内的按月统计的交易笔数为100，从而可以基于波动评价规则，确定该交易笔数对应的数值范围为100-200，且数值范围为100-200对应的初始波动值为120％，则确定输出该节点在交易笔数量级的初始波动值为120％。
此外，由于不同业务值的尺度不同，例如：交易笔数的数量级别为上亿，商户数的数量级别为千万，即两个业务值的量级存在巨大差异，因此，可以对每个交易主体对应的初始波动值进行归一化处理，从而可以统一评估量级。也就是说，可以对每个交易主体对应的初始波动值进行归一化处理，获得每个节点的波动值。波动值用于指示节点所指示的交易主体的业务信息的值(后文中为了描述方便，称作业务信息值)出现波动的情况。
可选的，归一化处理基于以下方式实现：
其中，Si表示节点的波动值，ri表示节点对应的初始波动值，K用于表示图关联结构中的节点总数量。
例如，请参见图5，图5为本发明实施例提供的一种图关联结构中节点的波动值的示意图。其中，图5中的四边形图案用于表征交易主体为收单机构的节点、五边形图案用于表征交易主体为支付子公司的节点、六边形图案用于表征交易主体为支付总公司的节点。其中，四边形图案所表征的交易主体为收单机构的节点的波动值为0.1，0.1＝120％/1200％，其中，120％是交易主体为收单机构的业务信息的同比增幅值，1200％是除交易主体为总公司的节点外的所有节点指示的交易主体的业务信息的同比增幅值总和。
步骤B：分别基于交易主体间的关联关系和预设异动分析规则中的第二子规则，确定每个节点的业务信息的波动受其他节点影响的影响值；第二子规则用于计算下层节点被上层节点的波动所影响的程度，下层节点和上层节点基于交易主体间的关联关系所确定；
在本发明实施例中，第二子规则，基于以下公式确定：
其中，epij表示节点i相对于节点j的影响值，Δi表示节点i的两个时刻间的业务信息值的变化值，Δj表示节点j的两个时刻间的业务信息值的变化值，eit表示t时刻节点i的业务信息值，eit’表示t’时刻节点i的业务信息值，ejt表示t时刻节点j的业务信息值，ejt’表示t’时刻节点j的业务信息值，节点i和节点j为图关联结构中任意节点。
在本发明实施例中，当确定第二子规则后，可以基于交易主体间的关联关系和前述的第二子规则，确定每个节点的业务信息的波动受其他节点影响的影响值。
例如，请参见图6，图6为本发明实施例提供的一种图关联结构中节点的影响值的示意图。其中，图6中的四边形图案用于表征交易主体为收单机构的节点、五边形图案用于表征交易主体为支付子公司的节点、六边形图案用于表征交易主体为支付总公司的节点。其中，五边形图案所表征的交易主体为子支付公司的节点的影响值为0.2，0.2＝3000万/1.5亿，其中，3000万是交易主体为支付子公司的交易笔数变化值，1.5亿是交易主体为总公司的交易笔数变化值。
步骤C：根据每个节点的波动值和对应的影响值，确定每个节点对应的异动值。
在本发明实施例中，电子设备可以将与一个所述节点存在关联关系的一个关联节点的影响值，作为构建初始异动迭代矩阵。例如，初始异动迭代矩阵可以表示为：
其中，θ表示初始异动迭代矩阵，θi,j为θ中的一个矩阵因素，epij表示节点i相对于节点j的影响值，节点i和节点j为图关联结构中任意节点，即i，j∈K。其中，当节点i和节点j不存在关联关系时，
进一步的，电子设备可以根据初始异动迭代矩阵和每个节点对应的波动值代入预设异动分析规则的第三子规则中，分别确定每个节点对应的异动值；第三子规则用于结合所有与节点存在关联关系的节点对应的影响值对节点的波动值进行迭代优化。
可选的，第三子规则基于以下公式确定：
H1←θS′+d
H2←θH1+d
...
Hn←θHn-1+d
其中，H表示迭代过程的中间变量，Hn表示第n轮迭代结果，n的大小根据Hn和Hn-1间的欧式距离大小决定，一般当Hn和Hn-1间的欧式距离<0.0001即可停止迭代。θ表示初始异动迭代矩阵，S′表示所有节点的波动值的集合，S′＝{S1，S2，……，SK}，d为非零调节系数，i，j为正整数。
最终节点的异动值分布为Hn为其中节点1的异动值为H1 n即向量Hn的第一个元素。
可选的，电子设备还可以对所有的节点对应的异动值从大到小进行排序，获得排序后的所有的节点的异动值。例如，请参见图7，图7为本发明实施例提供的一种计算节点对应的异动值的示意图。其中，图7中的四边形图案用于表征交易主体为收单机构的节点、五边形图案用于表征交易主体为支付子公司的节点、六边形图案用于表征交易主体为支付总公司的节点。
步骤303：当第一节点对应的异动值大于预设阈值时，确定第一节点为异动节点，并将第一节点所指示的交易主体确定为异动交易主体。
在本发明实施例中，当获得所有节点对应的异动值之后，可以根据历史经验确定预设阈值，该预设阈值例如为0.5。还可以基于获得的所有节点对应的异动值的排序信息，将排序前4个的中间值作为预设阈值，当然，还可以是基于其他方式确定预设阈值，本发明实施例中对此不做限定。
在本发明实施例中，当电子设备确定预设阈值之后，可以筛选出所有节点对应的异动值大于预设阈值的第一节点，并将第一节点作为异动节点。也就是说，第一节点可以是一个节点，也可以是一群节点。
在本发明实施例中，当确定异动节点之后，还可以将异动节点放回到构建的图关联结构进行还原，从而可以得到清晰的关联追溯路径，以提升交易主体归因分析的便利性。
在本发明实施例中，电子设备可以基于图关联结构，筛选包括第一节点的候选路径，将候选路径作为异动路径；对异动路径进行分析，获得异动分析结果；异动分析结果用于指示与异动节点关联的影响节点，并基于异动节点所对应的业务信息对影响节点对应的交易主体的业务进行优化。
例如，参见图8所示，图8为本发明实施例提供的一种异动路径的示意图。其中，图8中的四边形图案用于表征交易主体为收单机构的节点、五边形图案用于表征交易主体为支付子公司的节点、六边形图案用于表征交易主体为支付总公司的节点。图8中被完全填充的四边形图案所表征的节点为第一节点，且该节点与被完全填充的五边形图案所表征的节点，以及被完全填充的六边形图案所表征的节点组成一条异动路径。
在本发明实施例中，借助了图关联结构的优势进一步还原了归因分析的关联追溯路径，即异动路径，提升了交易主体进行异动归因分析的便利性，进而提升对实际业务的策略优化效果。
基于相同的发明构思，本发明实施例还提供一种数据处理装置。如图9所示，其为数据处理装置900的结构示意图，可以包括：
构建单元901，用于构建以目标业务场景中的交易主体为节点、交易主体间的关联关系为边的图关联结构；
确定单元902，用于基于所述图关联结构中每个所述节点所指示的交易主体的业务信息、交易主体间的关联关系和预设异动分析规则，确定每个所述节点对应的异动值；其中，每个所述异动值用于指示一个节点所指示交易主体交易的异常波动程度；所述异常波动程度基于交易主体的自身业务信息以及与其具备关联关系的其他交易主体的业务信息所确定；
处理单元903，用于当第一节点对应的异动值大于预设阈值时，确定所述第一节点为异动节点，并将所述第一节点所指示的交易主体确定为异动交易主体。
在一种可能的实施方式中，所述确定单元902，具体用于：
分别基于所述图关联结构中每个所述节点所指示的交易主体的业务信息和所述预设异动分析规则中的第一子规则，确定每个所述节点的波动值；所述第一子规则用于对基于不同量级的业务信息所获得节点的初始波动值进行量级归一化处理；
分别基于所述交易主体间的关联关系和所述预设异动分析规则中的第二子规则，确定每个所述节点的业务信息的波动受其他节点影响的影响值；所述第二子规则用于计算下层节点被上层节点的波动所影响的程度，所述下层节点和上层节点基于交易主体间的关联关系所确定；
根据每个所述节点的波动值和对应的影响值，确定每个所述节点对应的异动值。
在一种可能的实施方式中，所述确定单元902，具体用于：
分别将每个所述节点所指示交易主体的业务信息输入预设时序归因模型，获得所述预设时序归因模型输出的每个所述节点对应的初始波动值；所述预设时序归因模型基于一个交易主体在预设时间段内的业务信息和预设量级波动评价规则，确定所述交易主体的初始波动值；所述预设量级波动评价规则包括多条映射关系，不同映射关系包括不同量级业务信息对应的数值范围，以及与所述数值范围对应的初始波动值；
对每个所述交易主体对应的初始波动值进行归一化处理，获得每个所述节点的波动值。在一种可能的实施方式中，所述归一化处理基于以下方式实现：
其中，Si表示节点的波动值，ri表示节点对应的初始波动值，K用于表示所述图关联结构中的节点总数量。
在一种可能的实施方式中，所述第二子规则，基于以下公式确定：
其中，epij表示节点i相对于节点j的影响值，Δi表示节点i的两个时刻间的业务信息值的变化值，Δj表示节点j的两个时刻间的业务信息值的变化值，eit表示t时刻节点i的业务信息值，eit’表示t’时刻节点i的业务信息值，ejt表示t时刻节点j的业务信息值，ejt’表示t’时刻节点j的业务信息值，节点i和节点j为所述图关联结构中任意节点。
在一种可能的实施方式中，所述确定单元902，具体用于：
将与一个所述节点存在关联关系的一个关联节点的影响值，作为一个矩阵因素，构建初始异动迭代矩阵；
根据所述初始异动迭代矩阵和每个所述节点对应的波动值代入所述预设异动分析规则的第三子规则中，分别确定每个所述节点对应的异动值；所述第三子规则用于结合所有与节点存在关联关系的节点对应的影响值对节点的波动值进行迭代优化。
在一种可能的实施方式中，所述第三子规则基于以下公式确定：
Hn←θHn-1+d
其中，Hn表示所有节点的异动值的集合，n用于表征迭代轮数，当n等于1时，H1←θS′+d，S′表示所有节点的波动值的集合，S′＝{S1，S2，……，SK}，θ表示初始异动迭代矩阵，θi,j为θ中的矩阵因素，epij表示节点i相对于节点j的影响值，节点i和节点j为所述图关联结构中任意节点，Sk表示节点k的波动值，d为非零调节系数，i，j为正整数。
在一种可能的实施方式中，确定所述第一节点为异动节点之后，所述装置还包括优化单元，用于：
基于所述图关联结构，筛选包括第一节点的候选路径，将所述候选路径作为异动路径；
对所述异动路径进行分析，获得异动分析结果；所述异动分析结果用于指示与所述异动节点关联的影响节点，并基于所述异动节点所对应的业务信息对所述影响节点对应的交易主体的业务进行优化。
为了描述的方便，以上各部分按照功能划分为各模块(或单元)分别描述。当然，在实施本发明时可以把各模块(或单元)的功能在同一个或多个软件或硬件中实现。
在介绍了本发明示例性实施方式的数据处理方法和装置之后，接下来，介绍根据本发明的另一示例性实施方式的电子设备。
所属技术领域的技术人员能够理解，本发明的各个方面可以实现为系统、方法或程序产品。因此，本发明的各个方面可以具体实现为以下形式，即：完全的硬件实施方式、完全的软件实施方式(包括固件、微代码等)，或硬件和软件方面结合的实施方式，这里可以统称为“电路”、“模块”或“系统”。
关于上述实施例中的装置，其中各个模块的具体执行方式已经在有关该方法的实施例中进行了详细描述，此处将不做详细阐述说明。
与本发明上述方法实施例基于同一发明构思，本发明实施例中还提供了一种电子设备，该电子设备解决问题的原理与上述实施例的方法相似，因此该电子设备的实施可以参见上述方法的实施，重复之处不再赘述。
参阅图10所示，图10是根据一示例性实施例示出的一种电子设备1000的框图，本发明实施例中的电子设备包括至少一个处理器1001，以及与至少一个处理器1001连接的存储器1002，本发明实施例中不限定处理器1001与存储器1002之间的具体连接介质，图10中是以处理器1001和存储器1002之间通过总线连接为例，总线在图10中以粗线表示，其它部件之间的连接方式，仅是进行示意性说明，并不引以为限。总线可以分为地址总线、数据总线、控制总线等，为便于表示，图10中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。
在本发明实施例中，存储器1002存储有可被至少一个处理器1001执行的指令，至少一个处理器1001通过执行存储器1002存储的指令，可以执行前述的数据处理方法中所包括的步骤。
其中，处理器1001是电子设备的控制中心，可以利用各种接口和线路连接整个故障检测设备的各个部分，通过运行或执行存储在存储器1002内的指令以及调用存储在存储器1002内的数据，电子设备的各种功能和处理数据，从而对电子设备进行整体监控。可选的，处理器1001可包括一个或多个处理单元，处理器1001可集成应用处理器和调制解调处理器，其中，处理器1001主要处理操作系统、用户界面和应用程序等，调制解调处理器主要处理无线通信。可以理解的是，上述调制解调处理器也可以不集成到处理器1001中。在一些实施例中，处理器1001和存储器1002可以在同一芯片上实现，在一些实施例中，它们也可以在独立的芯片上分别实现。
处理器1001可以是通用处理器，例如中央处理器(CPU)、数字信号处理器、专用集成电路、现场可编程门阵列或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件，可以实现或者执行本发明实施例中公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者任何常规的处理器等。结合本发明实施例所公开的方法的步骤可以直接体现为硬件处理器执行完成，或者用处理器中的硬件及软件模块组合执行完成。
存储器1002作为一种非易失性计算机可读存储介质，可用于存储非易失性软件程序、非易失性计算机可执行程序以及模块。存储器1002可以包括至少一种类型的存储介质，例如可以包括闪存、硬盘、多媒体卡、卡型存储器、随机访问存储器(Random Access Memory，RAM)、静态随机访问存储器(Static Random Access Memory，SRAM)、可编程只读存储器(Programmable Read Only Memory，PROM)、只读存储器(Read Only Memory，ROM)、带电可擦除可编程只读存储器(Electrically Erasable Programmable Read-Only Memory，EEPROM)、磁性存储器、磁盘、光盘等等。存储器1002是能够用于携带或存储具有指令或数据结构形式的期望的程序代码并能够由计算机存取的任何其他介质，但不限于此。本发明实施例中的存储器1002还可以是电路或者其它任意能够实现存储功能的装置，用于存储程序指令和/或数据。
基于同一发明构思，本发明实施例还提供了一种电子设备的又一示意图，参阅图11所示，该电子设备104包括显示单元1140、处理器1180以及存储器1120，其中，显示单元1140包括显示面板1141，用于显示由用户输入的信息或提供给用户的信息以及电子设备104的各种对象选择界面等，在本发明实施例中主要用于显示电子设备104中已安装的分析系统的相关操作界面、快捷窗口等。可选的，可以采用LCD(Liquid Crystal Display，液晶显示器)或OLED(Organic Light-Emitting Diode,有机发光二极管)等形式来配置显示面板1141。
处理器1180用于读取计算机程序，然后执行计算机程序定义的方法，例如处理器1180读取分析系统的应用程序，从而在该电子设备104上运行分析系统，在显示单元1140上显示分析系统的相关操作界面。处理器1180可以包括一个或多个通用处理器，还可包括一个或多个DSP(Digital Signal Processor，数字信号处理器)，用于执行相关操作，以实现本发明实施例所提供的技术方案。
存储器1120一般包括内存和外存，内存可以为随机存储器(RAM)，只读存储器(ROM)，以及高速缓存(CACHE)等。外存可以为硬盘、光盘、USB盘、软盘或磁带机等。存储器1120用于存储计算机程序和其他数据，该计算机程序包括各个软件对应的应用程序等，其他数据可包括操作系统或应用程序被运行后产生的数据，该数据包括系统数据(例如操作系统的配置参数)和用户数据。本发明实施例中程序指令存储在存储器1120中，处理器1180执行存储器中1120中的程序指令，实现前文论述的数据处理方法的功能。
此外，电子设备104还可以包括显示单元1140，用于接收输入的数字信息、字符信息或接触式触摸操作/非接触式手势，以及产生与电子设备104的用户设置以及功能控制有关的信号输入等。具体地，本发明实施例中，该显示单元1140可以包括显示面板1141。显示面板1141例如触摸屏，可收集用户在其上或附近的触摸操作(比如目标对象使用手指、触笔等任何适合的物体或附件在显示面板1141上或在显示面板1141的操作)，并根据预先设定的程式驱动相应的连接装置。可选的，显示面板1141可包括触摸检测装置和触摸控制器两个部分。其中，触摸检测装置用户的触摸方位，并检测触摸操作带来的信号，将信号传送给触摸控制器；触摸控制器从触摸检测装置上接收触摸信息，并将它转换成触点坐标，再送给处理器1180，并能接收处理器1180发来的命令并加以执行。在本发明实施例中，若用户对关联子程序进行选中操作，则在显示面板1141中的触摸检测装置检测到触摸操作，则将检测到的触摸操作对应的信号发送的触摸控制器，触摸控制器将信号转换成触点坐标发送给处理器1180，处理器1180根据接收到的触点坐标确定用户选中的目标业务场景，并控制显示面板1141显示目标业务场景中的交易主体。
其中，显示面板1141可以采用电阻式、电容式、红外线以及表面声波等多种类型实现。除了显示单元1140，电子设备104还可以包括输入单元1130，输入单元1130可以包括但不限于物理键盘、功能键(比如音量控制按键、开关按键等)、轨迹球、鼠标、操作杆等中的一种或多种。图11中是以输入单元1130包括图像输入设备1131和其它输入设备1132为例。
除以上之外，电子设备104还可以包括用于给其他模块供电的电源1190、音频电路1160、近场通信模块1170和RF电路1110。电子设备104还可以包括一个或多个传感器1150，例如加速度传感器、光传感器、压力传感器等。音频电路1160具体包括扬声器1161和麦克风1162等，例如用户可以使用语音控制，电子设备104可以通过麦克风1162采集用户的声音，可以用户的声音进行控制，并在需要提示用户业务信息中存在异动表现时，通过扬声器1161播放对应的提示音。
在示例性实施例中，还提供了一种包括操作的存储介质，例如包括操作的存储器1002，上述操作可由电子设备1000的处理器1001执行以完成上述方法。可选地，存储介质可以是非临时性计算机可读存储介质，例如，所述非临时性计算机可读存储介质可以是ROM、随机存取存储器(RAM)、CD-ROM、磁带、软盘和光数据存储设备等。
与上述方法实施例基于同一发明构思，本发明提供的数据处理方法的各个方面还可以实现为一种程序产品的形式，其包括程序代码，当程序产品在电子设备上运行时，程序代码用于使电子设备执行本说明书上述描述的根据本发明各种示例性实施方式的数据处理方法中的步骤，例如，电子设备可以执行如图3所示的步骤。
程序产品可以采用一个或多个可读介质的任意组合。可读介质可以是可读信号介质或者可读存储介质。可读存储介质例如可以是但不限于电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。可读存储介质的更具体的例子(非穷举的列表)包括：具有一个或多个导线的电连接、便携式盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。
本发明的实施方式的程序产品可以采用便携式紧凑盘只读存储器(CD-ROM)并包括程序代码，并可以在服务器上运行。然而，本发明的程序产品不限于此，在本文件中，可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被命令执行系统、装置或者器件使用或者与其结合使用。
可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了可读程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。可读信号介质还可以是可读存储介质以外的任何可读介质，该可读介质可以发送、传播或者传输用于由命令执行系统、装置或者器件使用或者与其结合使用的程序。
可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于无线、有线、光缆、RF等等，或者上述的任意合适的组合。
尽管已描述了本发明的优选实施例，但本领域内的技术人员一旦得知了基本创造性概念，则可对这些实施例做出另外的变更和修改。所以，所附权利要求意欲解释为包括优选实施例以及落入本发明范围的所有变更和修改。
显然，本领域的技术人员可以对本发明进行各种改动和变型而不脱离本发明的精神和范围。这样，倘若本发明的这些修改和变型属于本发明权利要求及其等同技术的范围之内，则本发明也意图包含这些改动和变型在内。

Claims (12)

  1. 一种数据处理方法，其中，所述方法包括：
    构建以目标业务场景中的交易主体为节点、交易主体间的关联关系为边的图关联结构；
    基于所述图关联结构中每个所述节点所指示的交易主体的业务信息、交易主体间的关联关系和预设异动分析规则，确定每个所述节点对应的异动值；其中，每个所述异动值用于指示一个节点所指示交易主体交易的异常波动程度；所述异常波动程度基于交易主体的自身业务信息以及与其具备关联关系的其他交易主体的业务信息所确定；
    当第一节点对应的异动值大于预设阈值时，确定所述第一节点为异动节点，并将所述第一节点所指示的交易主体确定为异动交易主体。
  2. 如权利要求1所述的方法，其中，基于所述图关联结构中每个所述节点所指示的交易主体的业务信息、交易主体间的关联关系和预设异动分析规则，确定每个所述节点对应的异动值，包括：
    分别基于所述图关联结构中每个所述节点所指示的交易主体的业务信息和所述预设异动分析规则中的第一子规则，确定每个所述节点的波动值；所述第一子规则用于对基于不同量级的业务信息所获得节点的初始波动值进行量级归一化处理；
    分别基于所述交易主体间的关联关系和所述预设异动分析规则中的第二子规则，确定每个所述节点的业务信息的波动受其他节点影响的影响值；所述第二子规则用于计算下层节点被上层节点的波动所影响的程度，所述下层节点和上层节点基于交易主体间的关联关系所确定；
    根据每个所述节点的波动值和对应的影响值，确定每个所述节点对应的异动值。
  3. 如权利要求2所述的方法，其中，分别基于所述图关联结构中每个所述节点所指示的交易主体的业务信息和所述预设异动分析规则中的第一子规则，确定每个所述节点的波动值，包括：
    分别将每个所述节点所指示交易主体的业务信息输入预设时序归因模型，获得所述预设时序归因模型输出的每个所述节点对应的初始波动值；所述预设时序归因模型基于一个交易主体在预设时间段内的业务信息和预设量级波动评价规则，确定所述交易主体的初始波动值；所述预设量级波动评价规则包括多条映射关系，不同映射关系包括不同量级业务信息对应的数值范围，以及与所述数值范围对应的初始波动值；
    对每个所述交易主体对应的初始波动值进行归一化处理，获得每个所述节点的波动值。
  4. 如权利要求3所述的方法，其中，所述归一化处理基于以下方式实现：
    其中，Si表示节点的波动值，ri表示节点对应的初始波动值，K用于表示所述图关联结构中的节点总数量。
  5. 如权利要求2所述的方法，其中，所述第二子规则，基于以下公式确定：
    其中，epij表示节点i相对于节点j的影响值，Δi表示节点i的两个时刻间的业务信息值的变化值，Δj表示节点j的两个时刻间的业务信息值的变化值，eit表示t时刻节点i的业务信息值，eit’表示t’时刻节点i的业务信息值，ejt表示t时刻节点j的业务信息值，ejt’表示t’时刻节点j的业务信息值，节点i和节点j为所述图关联结构中任意节点。
  6. 如权利要求2-5任一所述的方法，其中，根据每个所述节点的波动值和对应的影响值，确定每个所述节点对应的异动值，包括：
    将与一个所述节点存在关联关系的一个关联节点的影响值，作为一个矩阵因素，构建初始异动迭代矩阵；
    根据所述初始异动迭代矩阵和每个所述节点对应的波动值代入所述预设异动分析规则的第三子规则中，分别确定每个所述节点对应的异动值；所述第三子规则用于结合所有与节点存在关联关系的节点对应的影响值对节点的波动值进行迭代优化。
  7. 如权利要求6所述的方法，其中，所述第三子规则基于以下公式确定：
    Hn←θHn-1+d
    其中，Hn表示所有节点的异动值的集合，n用于表征迭代轮数，当n等于1时，H1←θS′+d，S′表示所有节点的波动值的集合，S′＝{S1，S2，……，SK}，θ表示初始异动迭代矩阵，θi,j为θ中的矩阵因素，epij表示节点i相对于节点j的影响值，节点i和节点j为所述图关联结构中任意节点，Sk表示节点k的波动值，d为非零调节系数，i，j为正整数。
  8. 如权利要求1所述的方法，其中，确定所述第一节点为异动节点之后，所述方法还包括：
    基于所述图关联结构，筛选包括第一节点的候选路径，将所述候选路径作为异动路径；
    对所述异动路径进行分析，获得异动分析结果；所述异动分析结果用于指示与所述异动节点关联的影响节点，并基于所述异动节点所对应的业务信息对所述影响节点对应的交易主体的业务进行优化。
  9. 一种数据处理装置，其中，所述装置包括：
    构建单元，用于构建以目标业务场景中的交易主体为节点、交易主体间的关联关系为边的图关联结构；
    确定单元，用于基于所述图关联结构中每个所述节点所指示的交易主体的业务信息、交易主体间的关联关系和预设异动分析规则，确定每个所述节点对应的异动值；其中，每个所述异动值用于指示一个节点所指示交易主体交易的异常波动程度；所述异常波动程度基于交易主体的自身业务信息以及与其具备关联关系的其他交易主体的业务信息所确定；
    处理单元，用于当第一节点对应的异动值大于预设阈值时，确定所述第一节点为异动节点，并将所述第一节点所指示的交易主体确定为异动交易主体。
  10. 一种电子设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其中，所述处理器执行所述计算机程序时实现权利要求1-8任一所述的方法的步骤。
  11. 一种计算机可读存储介质，其中，其包括程序代码，当程序产品在电子设备上运行时，所述程序代码用于使所述电子设备执行权利要求1-8中任一所述的方法的步骤。
  12. 一种计算机程序产品，其中，所述计算机程序产品包括：计算机程序代码，当所述计算机程序代码在计算机上运行时，使得计算机执行上述如权利要求1-8中任一项所述的方法。
PCT/CN2024/142042 2024-04-10 2024-12-24 一种数据处理方法、装置、电子设备及存储介质 Pending WO2025213865A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202410432948.8A CN118505382A (zh) 2024-04-10 2024-04-10 一种数据处理方法、装置、电子设备及存储介质
CN202410432948.8 2024-04-10

Publications (1)

Publication Number Publication Date
WO2025213865A1 true WO2025213865A1 (zh) 2025-10-16

Family

ID=92245790

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2024/142042 Pending WO2025213865A1 (zh) 2024-04-10 2024-12-24 一种数据处理方法、装置、电子设备及存储介质

Country Status (3)

Country Link
CN (1) CN118505382A (zh)
TW (1) TW202540945A (zh)
WO (1) WO2025213865A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118505382A (zh) * 2024-04-10 2024-08-16 中国银联股份有限公司 一种数据处理方法、装置、电子设备及存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220188424A1 (en) * 2020-12-14 2022-06-16 International Business Machines Corporation Anomaly detection with impact assessment
CN116204838A (zh) * 2022-12-12 2023-06-02 支付宝(杭州)信息技术有限公司 一种异常业务识别的方法、装置、存储介质及电子设备
CN116319405A (zh) * 2023-04-21 2023-06-23 中国工商银行股份有限公司 流量数据异常检测方法、装置及计算机设备
CN116681497A (zh) * 2023-06-20 2023-09-01 远光软件股份有限公司 基于图神经网络的资金风险识别方法、计算机装置及计算机可读存储介质
CN116894634A (zh) * 2023-05-25 2023-10-17 支付宝(杭州)信息技术有限公司 一种业务系统的异常处理方法、电子装置、设备及存储介质
CN118505382A (zh) * 2024-04-10 2024-08-16 中国银联股份有限公司 一种数据处理方法、装置、电子设备及存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220188424A1 (en) * 2020-12-14 2022-06-16 International Business Machines Corporation Anomaly detection with impact assessment
CN116204838A (zh) * 2022-12-12 2023-06-02 支付宝(杭州)信息技术有限公司 一种异常业务识别的方法、装置、存储介质及电子设备
CN116319405A (zh) * 2023-04-21 2023-06-23 中国工商银行股份有限公司 流量数据异常检测方法、装置及计算机设备
CN116894634A (zh) * 2023-05-25 2023-10-17 支付宝(杭州)信息技术有限公司 一种业务系统的异常处理方法、电子装置、设备及存储介质
CN116681497A (zh) * 2023-06-20 2023-09-01 远光软件股份有限公司 基于图神经网络的资金风险识别方法、计算机装置及计算机可读存储介质
CN118505382A (zh) * 2024-04-10 2024-08-16 中国银联股份有限公司 一种数据处理方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
TW202540945A (zh) 2025-10-16
CN118505382A (zh) 2024-08-16

Similar Documents

Publication Publication Date Title
TWI718643B (zh) 異常群體識別方法及裝置
US11232122B2 (en) Method for data retrieval and dispersement using an eligibility engine
US11061934B1 (en) Method and system for characterizing time series
US20150278813A1 (en) Determining a temporary transaction limit
CN105793874B (zh) 用于管理团体信息的方法和系统
US11500933B2 (en) Techniques to generate and store graph models from structured and unstructured data in a cloud-based graph database system
US10937073B2 (en) Predicting delay in a process
WO2020087828A1 (zh) 预售风险评估方法、系统、计算机装置及可读存储介质
US9342796B1 (en) Learning-based data decontextualization
US12608405B2 (en) Model generation based on modular storage of training data
WO2025213865A1 (zh) 一种数据处理方法、装置、电子设备及存储介质
CN118886986A (zh) 产品推荐方法、装置、设备及存储介质
US11263224B2 (en) Identifying and scoring data values
CN111325372A (zh) 预测模型的建立方法、预测方法、装置、介质及设备
CN113779967B (zh) 企业转型信息生成方法及装置、存储介质、电子设备
US20230017358A1 (en) Automatically provisioned tag schema for hybrid multicloud cost and chargeback analysis
HK40113049A (zh) 一种数据处理方法、装置、电子设备及存储介质
CN108985908A (zh) 不动产信息共享方法、装置、计算机可读存储介质
US12602413B1 (en) Managing generative artificial intelligence (AI) model outputs using explainability reports
KR102878911B1 (ko) 기업의 적정 가치 제공 방법 및 이를 이용한 장치
CN110264306A (zh) 基于大数据的产品推荐方法、装置、服务器及介质
KR20240077029A (ko) 추천 종목 도출 방법 및 이를 이용한 장치
KR102780974B1 (ko) 차트 분석 방법 및 이를 이용한 차트 분석 제공 디바이스
US20240005235A1 (en) Method and system for dynamically recommending commands for performing a product data management operation
KR20230166412A (ko) 공시 자료를 이용한 주식 추천 방법 및 시스템

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 24934928

Country of ref document: EP

Kind code of ref document: A1