Method and device for monitoring the interaction process between a user terminal and a node device
By analyzing the historical interaction data of the user terminal and evaluating its credibility, combining with the geographical location set, the interaction mode between the user terminal and the node device is determined, and the problem of obtaining accurate transactions and registering locations is solved, and an accurate judgment of abnormal interaction mode is achieved. The ability to improve the credibility and efficiency of monitoring.
Patent Information
- Application Number
- CN202210540224.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-05-18
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2042-05-18
AI Technical Summary
During the interaction between the user terminal and the node device, it is difficult to obtain the accurate transaction location and registration location, resulting in inaccurate judgment results and the early warning prompt information cannot be reported in a timely manner.
By analyzing the historical interaction data of the user terminal, evaluating its credibility level, and combining the set of geographical locations, the matching between the interaction mode and the credibility is determined, thereby judging the normal or abnormality of the interaction mode.
It improves the credibility and accuracy of geographical location judgment, can identify abnormal interaction patterns in a timely and accurate manner, and reduces implementation costs.
Smart Images

Figure CN115474200B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to big data analysis technology, and in particular to a method for monitoring the interaction process between a user terminal and a node device, and an apparatus and a computer-readable storage medium for implementing the method. Background Art
[0002] In many application scenarios, it is necessary to monitor the interaction process between the user terminal and the node device. For example, in a retail scenario, when a card transaction is performed on a sales terminal POS, it is necessary to obtain the current location sent by the POS and the registered location of the POS terminal obtained by the POS terminal number and the corresponding merchant code; then determine whether the transaction location and the registered location match, and determine whether to report the warning prompt information based on the judgment result.
[0003] However, in some cases, the accurate transaction location and registration location cannot be obtained, for example, the mobile terminal provides false or tampered location data or the registration address of the POS terminal is incomplete. Summary of the invention
[0004] According to one aspect of the present application, a method for monitoring an interaction process between a user terminal and a node device comprises the following steps:
[0005] A. obtaining the credibility levels of the multiple user terminals from the historical interaction data of the multiple user terminals;
[0006] B. obtaining a set of geographical locations associated with a node device group based on the historical interaction data and the credibility level; and
[0007] C. Determine the matching of the interaction pattern between one or more of the plurality of user terminals and the node device group within the current period with the credibility level and the set of geographic locations.
[0008] According to another aspect of the present application, a method for monitoring an interaction process between a user terminal and a node device comprises the following steps:
[0009] A. obtaining the credibility levels of multiple user terminals from historical interaction data of multiple user terminals;
[0010] B. obtaining a geographic location associated with a designated node device from the historical interaction data and the credibility level; and
[0011] C. Determine the matching of the interaction between one or more of the plurality of user terminals and the designated node device within the current period with the credibility level and the geographic location.
[0012] According to another aspect of the present application, an apparatus for monitoring an interaction process between a user terminal and a node device includes:
[0013] Memory;
[0014] at least one processor; and
[0015] A computer program stored on the memory and executable on the processor, the execution of which results in the following operations:
[0016] A. obtaining the credibility levels of the multiple user terminals from the historical interaction data of the multiple user terminals;
[0017] B. obtaining a set of geographical locations associated with a node device group based on the historical interaction data and the credibility level; and
[0018] C. Determine the matching of the interaction pattern between one or more of the plurality of user terminals and the node device group within the current period with the credibility level and the set of geographic locations.
[0019] According to another aspect of the present application, an apparatus for monitoring an interaction process between a user terminal and a node device includes:
[0020] Memory;
[0021] at least one processor; and
[0022] A computer program stored on the memory and executable on the processor, the execution of which results in the following operations:
[0023] A. obtaining the credibility levels of multiple user terminals from historical interaction data of multiple user terminals;
[0024] B. obtaining a geographic location associated with a designated node device from the historical interaction data and the credibility level; and
[0025] C. Determine the matching of the interaction between one or more of the plurality of user terminals and the designated node device within the current period with the credibility level and the geographic location.
[0026] According to another aspect of the present application, a computer readable storage medium stores a computer program, which implements the method described above when executed by a processor.
[0027] In some embodiments of the present application, the geographical location of a node device group or a specified node device is determined based on the historical interaction location and the user terminal credibility level, which improves the credibility and accuracy of the geographical location judgment, so that abnormal interaction patterns can be judged in a timely and accurate manner. In addition, in some embodiments of the present application, the method of determining the geographical location based on the interaction location and the user terminal credibility level can be completed using only the existing historical interaction data, so it has the advantages of strong feasibility and low implementation cost. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] The above and / or other aspects and advantages of the present application will become clearer and easier to understand through the following description of various aspects in conjunction with the accompanying drawings, in which the same or similar units are represented by the same reference numerals. The accompanying drawings include:
[0029] Figure 1 The present invention is a flowchart of a method for monitoring an interaction process between a user terminal and a node device according to some embodiments of the present application.
[0030] Figure 2 The present invention is a flowchart of a method for obtaining the credibility level of a user terminal according to some other embodiments of the present application.
[0031] Figure 3 The present invention is a flowchart of a method for obtaining a set of geographical locations associated with a node device group according to some other embodiments of the present application.
[0032] Figure 4 The present invention is a flowchart of a method for obtaining a set of geographical locations associated with a node device group according to some other embodiments of the present application.
[0033] Figure 5 The present invention is a flowchart of a method for determining the matching of an interaction pattern with a credibility level and a set of geographic locations according to some other embodiments of the present application.
[0034] Figure 6 The present invention is a flowchart of a method for monitoring an interaction process between a user terminal and a node device according to some embodiments of the present application.
[0035] Figure 7 The present invention is a flowchart of a method for obtaining a geographic location associated with a specified node device according to some other embodiments of the present application.
[0036] Figure 8 The present invention is a flowchart of a method for constructing an association network according to some other embodiments of the present application.
[0037] Fig. 9 An example of an association network constructed in the above manner is shown in the figure.
[0038] Fig.10The present invention is a flowchart of a method for obtaining a geographic location associated with a specified node device according to some other embodiments of the present application.
[0039] Fig.11 A schematic block diagram of a typical computer system. DETAILED DESCRIPTION
[0040] The present application is described more fully below with reference to the accompanying drawings in which illustrative embodiments of the present application are illustrated. However, the present application may be implemented in different forms and should not be interpreted as being limited to the embodiments given herein. The above embodiments are given to make the disclosure herein comprehensive and complete, so as to more fully convey the scope of protection of the present application to those skilled in the art.
[0041] In this specification, terms such as "comprise" and "include" indicate that in addition to the units and steps directly and explicitly stated in the specification and claims, the technical solution of the present application does not exclude the situation where there are other units and steps that are not directly or explicitly stated.
[0042] Terms such as "first" and "second" do not indicate the order of the units in terms of time, space, size, etc., but are only used to distinguish the units.
[0043] Figure 1 The present invention is a flowchart of a method for monitoring an interaction process between a user terminal and a node device according to some embodiments of the present application.
[0044] Exemplarily, the user terminal may be a mobile terminal (such as a mobile phone, a tablet computer, a portable computer, and a wearable device, etc.), the node device group may be a plurality of transaction processing devices (such as POS terminals) distributed in different geographical locations and having the same merchant code and terminal code, and the interaction between the user terminal and the node device group may involve, for example, transactions between a user and a merchant, etc.
[0045] Figure 1 The method flow shown includes the following steps that can be implemented by a computer system (such as a server, a cloud computing device, and a personal computer, etc.):
[0046] Step S101: n user terminals U1...U n The historical interaction data (such as bank card transaction data and device fingerprint data) with a node device group (or merchant) M obtains the credibility level of these user terminals.
[0047] In one example, for example, a comparison analysis is performed between cardholders who have been marked with location anomalies such as virtual positioning and normal cardholders to extract corresponding feature vectors. These feature vectors include, for example, the user's preferential transaction ratio, the number of cities where the user's daily transactions belong, the number of provinces where the user's daily transactions belong, the number of GPS teleports of the user in a single day, and other interactive behavior characteristics, as well as device characteristics such as user device type, whether it is jailbroken or rooted, operating system version number, whether it is a simulator, mobile phone baseband version number, installed application list, device elevation angle, gyroscope, IP address, and application version number. Based on the above interactive behavior characteristics, device characteristics, and user tags, a classification algorithm such as XGBOOST and GBDT can be used to train the model to obtain a cardholder credibility scoring model. Subsequently, the trained cardholder credibility scoring model is used to score the credibility of users or user terminals involved in the historical interaction data, thereby obtaining the credibility level of each user terminal.
[0048] Step S102: Obtaining a geographical location set {L1...L k}.
[0049] Step S103: determining the matching of the interaction mode between one or more of the n user terminals and the node device group M within the current period with the credibility level and the geographical location set.
[0050] Step S104: If they match, then it is determined that the interaction mode between one or more of the n user terminals and the node device group M in the current period is a normal mode; otherwise, it is determined that the interaction mode is an abnormal mode.
[0051] The following Figure 1 The individual steps in are further described.
[0052] Acquisition of credibility level
[0053] For example, in step S101, Figure 2 The method flow shown is used to obtain the credibility level of the user terminal. Specifically, Figure 2 The process shown includes the following steps:
[0054] Step S201: extracting from the historical interaction data the information of multiple user terminals U1 ...... U n Associated interactive behavior characteristics and device characteristics (hereinafter also referred to as device fingerprints).
[0055] Optionally, each user terminal U iThe interaction behavior characteristics include one or more of the following: the interaction location of the user terminal when interacting, the proportion of the number of specified types of interactions performed by the user terminal in its total number of interactions, the proportion of the number of interactions performed by the user terminal in one or more cycles in the total number of interactions within its geographical range, and the number of times the location of the user terminal changes within a unit of time.
[0056] Alternatively, each user terminal U i The device characteristics include one or more of the following: device type, whether the user terminal is rooted, the version number of the operating system, whether the user terminal is running in simulator mode, the version number of the mobile phone baseband, the list of installed applications, the elevation angle of the user terminal, the gyroscope, the IP address and the application version number.
[0057] Step S202: Based on the extracted interactive behavior features and device features, a classification training algorithm is used to obtain a credibility scoring model of n user terminals. Optionally, the classification algorithm training model includes XGBOOST, GBDT, random forest, and graph neural network.
[0058] Step S203: For each user terminal U i , using the obtained credibility scoring model to obtain the corresponding credibility level S i (0 i ≤1).
[0059] Determination of geographical location collection
[0060] For example, in step S102, Figure 3 The method flow shown is used to obtain a geographical location set associated with a node device group. Specifically, Figure 3 The process shown includes the following steps:
[0061] Step S301: extract n user terminals U1...U n Multiple interaction locations when interacting with the node device group M. For example, for any user terminal U i , and its corresponding interaction position can be recorded as L ij (j=1,…,m).
[0062] Step S302: clustering the extracted multiple interaction locations using a clustering algorithm to obtain a geographical location set {L1...L k}.
[0063] For example, in step S102, Figure 4 The method flow shown is used to obtain a geographical location set associated with a node device group. Specifically, Figure 4 The process shown includes the following steps:
[0064] Step S401: extract n user terminals U1...U n Multiple interaction locations when interacting with the node device group M. Similarly, for any user terminal U i , and its corresponding interaction position can be recorded as L ij (j=1,…,m).
[0065] Step S402: For any user terminal U i Each of the multiple interaction positions (for example, denoted as L ij ), based on the user terminal U i The location weight component corresponding to the user terminal is determined based on the credibility level of the user terminal and the number of times the user terminal completes the specified type of interaction and the non-specified type of interaction at the interaction location.
[0066] The following is for the position weight component W ij The determination method is further described.
[0067] Assume that the set of user terminals that transact with the node device group M and have location data in the historical interaction data is U i (i=1,…,n), and the user terminal U i The set of interaction positions is L ij (j=1,…,m).
[0068] If the user terminal U i The credibility level is S i (0 i ≤1), and the user terminal U i At position L ij The number of non-specified type interactions (such as non-discount transactions) at ij1 , the number of interactions of a specified type (such as preferential transactions) is N ij2 , then the user terminal U i At position L ij The position weight component W ij Calculate according to the following formula:
[0069] W ij =N ij1 +S i ×N ij2 (1)
[0070] Step S403: The weight components W of each position obtained in step S402 ij A position weight value of each of a plurality of interaction positions is obtained.
[0071] For example, assume that the interaction location set Ω where n user terminals interact with a node device group (merchant) M is {L a (a=1,…,K)}, then for any position L in the set a , its position weight value W a It can be determined as follows:
[0072]
[0073] Step S404: Based on the position weight value W of each of the multiple interaction positions a Determine whether to set the interactive position L a Included in the geographical location set. Optionally, in this step, if the location weight value W of the interaction location a is greater than a preset first threshold TH1, then the interaction position L a Contained in the geolocation collection.
[0074] Taking the above example, assuming the interaction position L a The position weight value W a >TH1, then the interaction position L a The geographical location set Ω that will be included in the node device group or merchant M, where the value of the threshold TH1 can be adjusted according to actual conditions.
[0075] On top Figure 3 and 4 In the method flow shown, multiple types of location data of historical interaction data can be used to obtain multiple interaction locations when multiple user terminals interact with a node device group. Exemplarily, the types of location data include, but are not limited to, satellite positioning data of the user terminal, IP address, location with the most interactions with the node device group, location of the mobile phone number, and location of the user ID number. Optionally, various types of location data are used to determine multiple interaction locations in the following order of priority: satellite positioning data of the user terminal, IP address, location with the most interactions with the node device group, location of the mobile phone number, and location of the user ID number. For example, assuming that the historical interaction data also contains location data such as satellite positioning data of the user terminal, IP address, location with the most interactions with the node device group, location of the mobile phone number, and location of the user ID number, then since the satellite positioning data of the user terminal has the highest priority, it is used to determine the interaction location.
[0076] Matching judgment
[0077] For example, in step S103, Figure 5The method flow shown is to determine the matching of the interaction mode between one or more of the multiple user terminals and the node device group within the current period with the credibility level and the geographical location set. Specifically, Figure 5 The process shown includes the following steps:
[0078] Step S501: If the interaction locations of the specified type of interaction (eg, preferential transactions) of multiple user terminals in the current period belong to a geographical location set, it is determined that the interaction matches the credibility level and the geographical location set.
[0079] Step S502: If one of the following conditions is met, it is determined that the interaction between multiple user terminals and the node device group does not match the credibility level and the geographic location set: i) the number of interactions performed by user terminals with a credibility level lower than the second threshold TH2 in the current time period is greater than the third threshold TH3; or ii) the number of interactions in which the interaction location exceeds the geographic location set in the current time period is greater than the fourth threshold TH4.
[0080] Figure 6 The present invention is a flowchart of a method for monitoring an interaction process between a user terminal and a node device according to some other embodiments of the present application.
[0081] Exemplarily, the user terminal is a mobile terminal (such as a mobile phone, tablet computer, portable computer, and wearable device), the node device is a transaction processing device (such as a POS terminal) distributed at a geographical location, and the interaction between the user terminal and the node device involves, for example, transactions between a user and a merchant. Figure 6 The method shown can determine the address of the node device based on historical interaction data, and can be applied to situations where the registered address of the node device (such as a POS terminal) is incomplete.
[0082] Figure 6 The method flow shown includes the following steps that can be implemented by a computer system (such as a server, a cloud computing device, and a personal computer, etc.):
[0083] Step S601: n user terminals U1...U n The historical interaction data with multiple node devices obtains the credibility level of these user terminals.
[0084] Step S602: Obtaining a geographic location L associated with a specified node device or merchant M' from historical interaction data and credibility level M’ .
[0085] Step S603: Determine n user terminals U1...U n The matching of the interaction mode between one or more and the designated node device M' with the credibility level and the geographical location.
[0086] Step S604: If matched, it is determined that the interaction mode between one or more of the n user terminals and the designated node device M' in the current period is a normal mode; otherwise, it is determined that the interaction mode is an abnormal mode.
[0087] The following Figure 6 The individual steps in are further described.
[0088] Acquisition of credibility level
[0089] For example, in step S601, Figure 2 To avoid redundancy, no further detailed description is given here.
[0090] Determination of geographical location
[0091] For example, in step S602, Figure 7 The method flow shown is used to obtain the geographical location L associated with the specified node device M' M’ Specifically, Figure 7 The process shown includes the following steps:
[0092] Step S701: construct an associated network including n user terminals, a designated node device M' and other node devices based on historical interaction data.
[0093] For example, it can be Figure 8 The method flow shown is used to construct the association network.
[0094] Specifically, in step S801, n user terminals, designated node devices M' and other node devices associated with historical interaction data are taken as network nodes, and the credibility levels of the user terminals and the locations (interaction locations) where these user terminals interact with the node devices (designated node devices and other node devices) are taken as attributes of the corresponding network nodes.
[0095] Then, step S802 is entered, and the edge connecting the user terminal and the node device is constructed in the following manner: i When an interaction occurs with a node device (including a designated node device and other node devices), the association is represented by an edge connecting the corresponding user terminal and the node device.
[0096] Then enter step S803, and construct the edge connecting the specified node device and the node device in the following manner: if a user terminal interacts with the specified node device and other node devices successively within a time interval T that is less than the set time length, the association is represented by an edge connecting the specified node device and the corresponding other device nodes, and the time interval T is used as the attribute of the edge.
[0097] Fig. 9 An example of an association network constructed in the above manner is shown in the figure.
[0098] Step S702: Determine the geographic location of the designated node device based on the attributes of the sub-network containing the designated node device in the associated network.
[0099] For example, it can be Fig.10 The method flow shown is to determine the geographic location L of the designated node device M' M’ Specifically, Fig.10 The method flow shown includes the following steps:
[0100] Step S1001: extracting a neighbor user terminal set and a neighbor node device set of a designated node device M' from an associated network.
[0101] Exemplarily, the set M of neighboring node devices or neighboring merchants of a specified node device or merchant M' can be obtained in the following manner: i′j′ ,(i=1,…n,j=1…,m): If the shortest path weight (sum of the time of each edge) from merchant M' to a neighboring merchant is less than a threshold (e.g. 30 minutes), then the neighboring merchant is included in the subnetwork or the set of neighboring merchants. The setting of the threshold can prevent the unlimited expansion of the subnetwork of merchant M'.
[0102] Step S1002: Determine location weight values of a neighboring user terminal set and a neighboring node device set at an interaction location.
[0103] Exemplarily, the location weight value of the neighboring user terminal of the designated node device M' may be determined in the following manner:
[0104] Assume that the interaction location set Ω' where n user terminals interact with the specified node device M' is {L a′ (a=1,…,K)}, then for any position L in the set a’ , its position weight value W a’ It can be determined as follows:
[0105]
[0106] Among them, W ijis the position weight component of the i-th user terminal at the j-th interaction position, which can be calculated using the above formula (1).
[0107] Exemplarily, the location weight value of the neighboring node device of the designated node device M may be determined in the following manner:
[0108] Assume that the j'th geographical location of the i'th neighbor node device is recorded as L Mi’j’ , then the corresponding position weight value Determine as follows:
[0109]
[0110] In the above formula, α, β, γ are correction parameters, ST i’j’ For the specified node device M to node device M i’j’ The shortest path (or connecting the specified node device M and node device M i’j’ The weight and edge weight of PG i’j’ Node device M i’j’ The PageRank value or importance of a page can be calculated using the PageRank algorithm.
[0111] Step S1003: Determine the overall position weight value of each of the multiple interaction positions based on the position weight values of the neighbor user terminal set and the neighbor node device set at the interaction position determined in step S1002.
[0112] For example, it is assumed that the interaction position set Ω of the specified node device M' is {L a (a=1,…,I2)}, then the specified node device M can be determined in the following way. a The total value of the position weight W a :
[0113]
[0114] In the above formula, δ is the correction parameter.
[0115] Step S1004: Determine the position corresponding to the maximum overall position weight value as the geographical location of the designated node device M.
[0116] Taking the above example, for each interaction position L of the specified node device M' a (a=1,…,I2), the corresponding position weight is W a (a=1,…,I2), if W i is the maximum value, then the position L corresponding to the maximum value i The geographical location of the designated node device M' is determined.
[0117] Matching judgment
[0118] Exemplarily, in step S603, the matching of the interaction pattern between one or more of the multiple user terminals and the designated node device group in the current period with the credibility level and the set of geographical locations can be determined in the following manner. Specifically, if one of the following conditions is met, it is determined that the interaction between the multiple user terminals and the designated node device group does not match the credibility level and the set of geographical locations: i) the number of interactions between the user terminals with a credibility level lower than a set level and the designated node device in the current period is greater than the set number; or ii) the number of times the interaction location of the interaction with the designated node device in the current period does not match the geographical location is greater than the set threshold.
[0119] Fig.11 A schematic block diagram of a typical computer system. Fig.11 Examples of the computer system shown include, but are not limited to, servers, cloud computing devices, personal computers, and the like.
[0120] See also Fig.11 The computer system 1100 includes a communication unit 1110, a memory 1120 (e.g., a non-volatile memory such as a flash memory, a ROM, a hard disk drive, a magnetic disk, an optical disk, etc.), a processor 1130, and a computer program 1140 stored on the memory 1120 and executable on the processor 1130.
[0121] The communication unit 1110 serves as a communication interface and is configured to establish a communication connection between the computer system and an external device or network (eg, the user terminal and the node device mentioned above).
[0122] The memory 1120 stores a computer program 1140 that can be executed by the processor 1130. The processor 1130 is configured to execute the computer program 1140 to implement the above Figure 1-10 The method flow described.
[0123] According to another aspect of the present application, a computer readable storage medium is provided, on which a computer program suitable for running on a computer system is stored. When the computer program is executed on a processor of the computer system, the following can be executed: Figure 1-10 The method steps are shown.
[0124] The computer-readable storage medium referred to in this application includes various types of computer storage media, which can be any available medium that a general or special-purpose computer can access. For example, a computer-readable storage medium can include RAM, ROM, EPROM, E2PROM, register, hard disk, removable disk, CD-ROM or other optical disk storage, disk storage or other magnetic storage device, or can be used to carry or store a desired program code unit with an instruction or data structure form and can be accessed by a general or special-purpose computer, or a general or special-purpose processor. Any other temporary or non-temporary medium. The above combination should also be included in the protection scope of the computer-readable storage medium. An exemplary storage medium is coupled to a processor so that the processor can read and write information from / to the storage medium. In an alternative, a storage medium can be integrated into a processor. The processor and the storage medium can reside in an ASIC. The ASIC can reside in a user terminal. In an alternative, the processor and the storage medium can reside in a user terminal as discrete components.
[0125] Those skilled in the art will appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described herein may be implemented as electronic hardware, computer software, or a combination of both.
[0126] In order to show the interchangeability between hardware and software, various schematic components, blocks, modules, circuits and steps are generally described above according to their functionality. Such functionality is implemented in hardware form or software form depending on the specific application and the design restrictions imposed on the overall system. Those skilled in the art can implement the described functionality in a variable manner for specific specific applications, but such implementation decisions should not be understood as causing deviations from the scope of the present application.
[0127] Although only some of the specific embodiments of the present application are described, it should be understood by those skilled in the art that the present application can be implemented in many other forms without departing from its subject matter and scope. Therefore, the examples and embodiments shown are considered to be illustrative rather than restrictive, and the present application may include various modifications and substitutions without departing from the spirit and scope of the present application as defined in the appended claims.
[0128] The embodiments and examples set forth herein are provided to best illustrate embodiments according to the present technology and its specific applications, and thereby enable those skilled in the art to implement and use the present application. However, those skilled in the art will appreciate that the above description and examples are provided only for ease of illustration and example. The description set forth is not intended to cover all aspects of the present application or to limit the present application to the precise form disclosed.
Claims
1. A method for monitoring the interaction process between a user terminal and a node device, characterized in that: It includes the following steps: A. obtaining the credibility levels of the multiple user terminals from the historical interaction data of the multiple user terminals; B. obtaining a set of geographical locations associated with a node device group based on the historical interaction data and the credibility level; as well as C. determining the matching of the interaction mode between one or more of the plurality of user terminals and the node device group within the current period with the credibility level and the set of geographical locations, Wherein, step A comprises: A1. extracting interaction behavior features and device features associated with the multiple user terminals from the historical interaction data; A2. Based on the extracted interactive behavior features and device features, using a classification training algorithm to obtain a credibility scoring model for the multiple user terminals; and A3. For each of the plurality of user terminals, using the obtained credibility scoring model to obtain a corresponding credibility level, Wherein, step C comprises: C1. If the interaction locations of the specified type of interaction of the multiple user terminals in the current period belong to the geographical location set, determining that the interaction matches the credibility level and the geographical location set; C2. If one of the following conditions is met, it is determined that the interaction between the multiple user terminals and the node device group does not match the credibility level and the geographic location set: i) the number of interactions performed by user terminals with a credibility level lower than the second threshold in the current time period is greater than the third threshold; or ii) the number of interactions in which the interaction location exceeds the geographic location set in the current time period is greater than the fourth threshold.
2. The method of claim 1, wherein: Further comprising the steps of: D. If they match, then it is determined that the interaction mode between one or more of the multiple user terminals and the node device group in the current period is a normal mode; otherwise, it is determined that the interaction mode is an abnormal mode.
3. The method of claim 1, wherein: The user terminal is a mobile terminal, the node device group is a transaction processing device distributed in multiple geographical locations and having the same merchant code and terminal code, and the interaction between the user terminal and the node device group involves a transaction between the user and the merchant.
4. The method of claim 1, wherein: The interaction behavior characteristics of each user terminal include one or more of the following: the interaction location of the user terminal when interacting, the proportion of the number of specified types of interactions performed by the user terminal in its total number of interactions, the proportion of the number of interactions performed by the user terminal in one or more cycles in the total number of interactions within its geographical range, and the number of times the user terminal's location changes within a unit of time.
5. The method of claim 1, wherein: The device characteristics of each user terminal include one or more of the following: device type, whether the user terminal is rooted, operating system version number, whether the user terminal is running in simulator mode, mobile phone baseband version number, installed application list, user terminal elevation angle, gyroscope, IP address and application version number.
6. The method of claim 1, wherein: The classification training algorithms include XGBOOST, GBDT, random forest and graph neural network.
7. The method of claim 1, wherein: Step B includes: B1. extracting multiple interaction positions when the multiple user terminals interact with the node device group from historical interaction data; B2. Using a clustering algorithm, cluster the extracted multiple interaction locations to obtain a set of geographical locations associated with the node device group.
8. The method of claim 1, wherein: Step B includes: B1. extracting multiple interaction positions when the multiple user terminals interact with the node device group from historical interaction data; B2. for each of the plurality of interaction locations, determining a location weight component corresponding to the user terminal based on a credibility level of each user terminal and a number of times the user terminal completes a specified type of interaction and a non-specified type of interaction at the interaction location; B3. obtaining a position weight value of each of the plurality of interaction positions from the position weight component; B4. Determine whether to include the interaction location in the geographic location set based on the location weight value of each of the multiple interaction locations.
9. The method of claim 8, wherein: In step B3, if the location weight value of the interaction location is greater than a preset first threshold, the interaction location is included in the geographical location set.
10. The method according to claim 7 or 8, wherein: In step B1, the multiple types of location data in the historical interaction data are used to determine the multiple interaction locations when the multiple user terminals interact with the node device group in the following priority order: satellite positioning data of the user terminal, IP address, the location with the most interactions with the node device group, the location of the mobile phone number and the location of the user ID number.
11. A method for monitoring the interaction process between a user terminal and a node device, characterized in that: It includes the following steps: A. obtaining the credibility levels of multiple user terminals from historical interaction data of multiple user terminals; B. obtaining a geographic location associated with a designated node device based on the historical interaction data and the credibility level; as well as C. determining the matching of the interaction between one or more of the plurality of user terminals and the designated node device within the current period with the credibility level and the geographical location, Wherein, step A comprises: A1. extracting interaction behavior features and device features associated with the multiple user terminals from the historical interaction data; A2. Based on the extracted interactive behavior features and device features, using a classification training algorithm to obtain a credibility scoring model for the multiple user terminals; and A3. For each of the plurality of user terminals, using the obtained credibility scoring model to obtain a corresponding credibility level, Wherein, step C comprises: If one of the following conditions is met, the interaction is judged to be inconsistent with the credibility level and the geographic location: i) the number of interactions between the user terminal with a credibility level lower than the set level and the designated node device in the current time period is greater than the set number; or ii) the number of times the interaction location of the interaction with the designated node device in the current time period does not match the geographic location is greater than the set threshold.
12. The method of claim 11, wherein: Further comprising the steps of: D. If there is a match, then the interaction mode between one or more of the multiple user terminals and the designated node device in the current time period is determined to be a normal mode; otherwise, then the interaction mode is determined to be an abnormal mode.
13. The method of claim 11, wherein: The user terminal is a mobile terminal, the designated node device is a transaction processing device distributed at a geographical location, and the interaction between the user terminal and the designated node device involves a transaction between the user and the merchant.
14. The method of claim 11, wherein: The interaction behavior characteristics of each user terminal include one or more of the following: the interaction location of the user terminal when interacting, the proportion of the number of specified types of interactions performed by the user terminal in its total number of interactions, the proportion of the number of interactions performed by the user terminal in one or more cycles in the total number of interactions within its geographical range, and the number of times the user terminal's location changes within a unit of time.
15. The method of claim 11, wherein: The device characteristics of each user terminal include one or more of the following: device type, whether the user terminal is rooted, operating system version number, whether the user terminal is running in simulator mode, mobile phone baseband version number, installed application list, user terminal elevation angle, gyroscope, IP address and application version number.
16. The method of claim 11, wherein: The classification training algorithms include XGBOOST, GBDT, random forest and graph neural network.
17. The method of claim 11, wherein: Step B includes: B1. constructing an associated network including the plurality of user terminals, the designated node device and other node devices based on the historical interaction data; B2. Determine the geographic location of the designated node device based on the attributes of the subnetwork containing the designated node device in the associated network.
18. The method of claim 17, wherein: Step B1 includes: B11. The plurality of user terminals, the designated node devices and other node devices are regarded as network nodes, and the credibility levels and interaction positions of the user terminals are regarded as attributes of the corresponding network nodes; B12. The interactions between the plurality of user terminals and the designated node device or other node devices are represented by edges connecting the corresponding user terminals and the node devices; B13. The interactions of the multiple user terminals with the designated node device and other node devices in a time interval less than the set time length are represented by edges connecting the corresponding device nodes, and the time interval is used as an attribute of the edges connecting the corresponding device nodes.
19. The method of claim 18, wherein: Step B2 includes: B21. extracting a neighbor user terminal set and a neighbor node device set of the designated node device from the associated network; B22. Determine a location weight value of each neighbor user in the neighbor user terminal and each neighbor node device in the neighbor node device set for multiple interaction locations; B23, determining an overall position weight value of each of the plurality of interactive positions based on the position weight values; B24. Determine the position corresponding to the maximum overall position weight value as the geographical location of the designated node device.
20. A device for monitoring an interaction process between a user terminal and a node device, comprising: Memory; at least one processor; and A computer program stored on the memory and executable on the processor, the execution of which results in the following operations: A. obtaining the credibility levels of the multiple user terminals from the historical interaction data of the multiple user terminals; B. obtaining a set of geographical locations associated with a node device group based on the historical interaction data and the credibility level; as well as C. determining the matching of the interaction mode between one or more of the plurality of user terminals and the node device group within the current period with the credibility level and the set of geographical locations, Wherein, operation A includes: A1. extracting interaction behavior features and device features associated with the multiple user terminals from the historical interaction data; A2. Based on the extracted interactive behavior features and device features, using a classification training algorithm to obtain a credibility scoring model for the multiple user terminals; and A3. For each of the plurality of user terminals, using the obtained credibility scoring model to obtain a corresponding credibility level, Among them, operation C includes: C1. If the interaction locations of the specified type of interaction of the multiple user terminals in the current period belong to the geographical location set, determining that the interaction matches the credibility level and the geographical location set; C2. If one of the following conditions is met, it is determined that the interaction between the multiple user terminals and the node device group does not match the credibility level and the geographic location set: i) the number of interactions performed by user terminals with a credibility level lower than the second threshold in the current time period is greater than the third threshold; or ii) the number of interactions in which the interaction location exceeds the geographic location set in the current time period is greater than the fourth threshold.
21. The device of claim 20, wherein: The execution of the computer program also results in the following operations: D. If they match, then it is determined that the interaction mode between one or more of the multiple user terminals and the node device group in the current period is a normal mode; otherwise, it is determined that the interaction mode is an abnormal mode.
22. The device of claim 20, wherein: The user terminal is a mobile terminal, the node device group is a transaction processing device distributed in multiple geographical locations and having the same merchant code and terminal code, and the interaction between the user terminal and the node device group involves a transaction between the user and the merchant.
23. The device of claim 20, wherein: The interaction behavior characteristics of each user terminal include one or more of the following: the interaction location of the user terminal when interacting, the proportion of the number of specified types of interactions performed by the user terminal in its total number of interactions, the proportion of the number of interactions performed by the user terminal in one or more cycles in the total number of interactions within its geographical range, and the number of times the user terminal's location changes within a unit of time.
24. The apparatus of claim 20, wherein: The device characteristics of each user terminal include one or more of the following: device type, whether the user terminal is rooted, operating system version number, whether the user terminal is running in simulator mode, mobile phone baseband version number, installed application list, user terminal elevation angle, gyroscope, IP address and application version number.
25. The apparatus of claim 20, wherein: The classification training algorithms include XGBOOST, GBDT, random forest and graph neural network.
26. The apparatus of claim 20, wherein: Operation B includes: B1. extracting multiple interaction positions when the multiple user terminals interact with the node device group from historical interaction data; B2. Using a clustering algorithm, cluster the extracted multiple interaction locations to obtain a set of geographical locations associated with the node device group.
27. The apparatus of claim 20, wherein: Operation B includes: B1. extracting multiple interaction positions when the multiple user terminals interact with the node device group from historical interaction data; B2. for each of the plurality of interaction locations, determining a location weight component corresponding to the user terminal based on a credibility level of each user terminal and a number of times the user terminal completes a specified type of interaction and a non-specified type of interaction at the interaction location; B3. obtaining a position weight value of each of the plurality of interaction positions from the position weight component; B4. Determine whether to include the interaction location in the geographic location set based on the location weight value of each of the multiple interaction locations.
28. The apparatus of claim 27, wherein: In operation B3, if the location weight value of the interaction location is greater than a preset first threshold, the interaction location is included in the geographical location set.
29. The device of claim 26 or 27, wherein: In operation B1, the multiple types of location data in the historical interaction data are used to determine the multiple interaction locations when the multiple user terminals interact with the node device group in the following priority order: satellite positioning data of the user terminal, IP address, the location with the most interactions with the node device group, the location of the mobile phone number and the location of the user ID number.
30. A device for monitoring the interaction process between a user terminal and a node device, characterized in that: Include: Memory; at least one processor; and A computer program stored on the memory and executable on the processor, the execution of which results in the following operations: A. obtaining the credibility levels of multiple user terminals from historical interaction data of multiple user terminals; B. obtaining a geographic location associated with a designated node device based on the historical interaction data and the credibility level; as well as C. determining the matching of the interaction between one or more of the plurality of user terminals and the designated node device within the current period with the credibility level and the geographical location, Wherein, operation A includes: A1. extracting interaction behavior features and device features associated with the multiple user terminals from the historical interaction data; A2. Based on the extracted interactive behavior features and device features, using a classification training algorithm to obtain a credibility scoring model for the multiple user terminals; and A3. For each of the plurality of user terminals, using the obtained credibility scoring model to obtain a corresponding credibility level, Among them, operation C includes: If one of the following conditions is met, the interaction is judged to be inconsistent with the credibility level and the geographic location: i) the number of interactions between the user terminal with a credibility level lower than the set level and the designated node device in the current time period is greater than the set number; or ii) the number of times the interaction location of the interaction with the designated node device in the current time period does not match the geographic location is greater than the set threshold.
31. The apparatus of claim 30, wherein: Execution of the computer program also results in the following operations: D. If there is a match, then the interaction mode between one or more of the multiple user terminals and the designated node device in the current time period is determined to be a normal mode; otherwise, then the interaction mode is determined to be an abnormal mode.
32. The apparatus of claim 30, wherein: The user terminal is a mobile terminal, the designated node device is a transaction processing device distributed at a geographical location, and the interaction between the user terminal and the designated node device involves a transaction between the user and the merchant.
33. The apparatus of claim 30, wherein: The interaction behavior characteristics of each user terminal include one or more of the following: the interaction location of the user terminal when interacting, the proportion of the number of specified types of interactions performed by the user terminal in its total number of interactions, the proportion of the number of interactions performed by the user terminal in one or more cycles in the total number of interactions within its geographical range, and the number of times the user terminal's location changes within a unit of time.
34. The apparatus of claim 30, wherein: The device characteristics of each user terminal include one or more of the following: device type, whether the user terminal is rooted, operating system version number, whether the user terminal is running in simulator mode, mobile phone baseband version number, installed application list, user terminal elevation angle, gyroscope, IP address and application version number.
35. The apparatus of claim 30, wherein: The classification training algorithms include XGBOOST, GBDT, random forest and graph neural network.
36. The apparatus of claim 30, wherein: Operation B includes: B1. constructing an associated network including the plurality of user terminals, the designated node device and other node devices based on the historical interaction data; B2. Determine the geographic location of the designated node device based on the attributes of the subnetwork containing the designated node device in the associated network.
37. The apparatus of claim 36, wherein: Operation B1 includes: B11. The plurality of user terminals, the designated node devices and other node devices are regarded as network nodes, and the credibility levels and interaction positions of the user terminals are regarded as attributes of the corresponding network nodes; B12. The interactions between the plurality of user terminals and the designated node device or other node devices are represented by edges connecting the corresponding user terminals and the node devices; B13. The interactions of the multiple user terminals with the designated node device and other node devices in a time interval less than the set time length are represented by edges connecting the corresponding device nodes, and the time interval is used as an attribute of the edges connecting the corresponding device nodes.
38. The apparatus of claim 37, wherein: Operation B2 includes: B21. Extracting a set of neighboring user terminals and neighboring node devices of the designated node device from the associated network; B22. Determine a location weight value of each neighbor user in the neighbor user terminal and each neighbor node device in the neighbor node device set for multiple interaction locations; B23, determining an overall position weight value of each of the plurality of interactive positions based on the position weight values; B24. Determine the position corresponding to the maximum overall position weight value as the geographical location of the designated node device.
39. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 19 are implemented.
Citation Information
Patent Citations
A method and device for identifying offline merchants
CN110659961A
Credit evaluation method and device and computer readable storage medium
CN113362158A
