A fraud behavior analysis method, device and medium

Through DPI technology, FaceTime call traffic is analyzed and modeled to identify fraudulent behaviors, solving the problems of lagging identification of fraudulent behaviors and limited coverage in the existing technology, realizing accurate analysis and fraud warning of FaceTime calls, and improving user property and Network security protection.

CN118631537BActive Publication Date: 2024-12-03WUHAN HONGWU INFORMATION TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202410779910.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-06-17
Publication Date
2024-12-03
Estimated Expiration
2044-06-17

AI Technical Summary

Technical Problem

The existing fraudulent behavior identification technology relies on users' subjective reporting and passive monitoring, with lagging reactions and limited coverage, making it difficult to accurately identify fraudulent behaviors in instant messaging tools such as FaceTime, resulting in the fraudulent behavior being not discovered and stopped in a timely manner.

Method used

Through DPI technology, FaceTime call traffic is analyzed, key information is extracted, and a fraudster behavior recognition model is built. The caller's behavior score is calculated using the call frequency, duration, dispersion, fraud-related application associations and special scenarios to output fraudster clues.

Benefits of technology

It realizes accurate analysis and identification of FaceTime calls, improves the accuracy and response speed of fraudulent behavior, and can prevent fraudulent behavior in a timely manner, protect user property and network security.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118631537B_ABST
    Figure CN118631537B_ABST
Patent Text Reader

Abstract

This application relates to the field of call security technology, and discloses a method, device, and medium for analyzing fraudulent behavior. It uses DPI technology to analyze FaceTime call traffic and extract key information from the FaceTime call traffic; calculates the FaceTime caller ID based on the key information; obtains FaceTime detection logs based on the FaceTime caller ID; constructs a FaceTime fraudster behavior identification model based on the FaceTime detection logs; the features of the fraudster behavior identification model include caller ID frequency calculation, caller ID duration calculation, caller ID dispersion calculation, fraudulent application association calculation, and fraudulent special scenario calculation; determines a fraudster behavior scoring formula based on the features of the fraudster behavior identification model; and identifies and outputs fraudster clues based on the fraudster behavior scoring formula. This at least addresses the problem of the inability to effectively analyze and judge fraudulent behavior.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of call security technology, and in particular to a fraud behavior analysis method, device and medium. Background Art

[0002] With the rapid development of communication technology and the widespread popularity of smart devices, various instant messaging tools, such as FaceTime, have become an important means of daily communication for people. However, the ensuing communication fraud has brought serious threats to the property safety and privacy protection of the majority of users. Communication fraud mainly uses instant messaging tools to carry out illegal activities, such as disguising identities to commit fraud and inducing users to transfer funds.

[0003] Existing fraud identification technologies mainly rely on users' subjective reports and passive monitoring, and have defects such as delayed response and limited coverage. At the same time, due to its limited parsing ability, traditional network traffic monitoring technology is difficult to accurately identify and judge fraud in instant messaging tools such as FaceTime. These problems have led to many frauds not being discovered and stopped in time, resulting in financial losses to users. Therefore, how to use more accurate and efficient technical means to comprehensively parse and analyze FaceTime call traffic and timely identify and judge fraud has become an urgent problem to be solved. Summary of the invention

[0004] One purpose of the present application is to provide a fraudulent behavior analysis method, device and medium to solve the problem of being unable to effectively analyze and judge fraudulent behavior.

[0005] To achieve the above objectives, some embodiments of the present application provide the following aspects:

[0006] In the first aspect, some embodiments of the present application also provide a fraud behavior analysis method, which analyzes FaceTime call traffic through DPI technology to extract key information of the FaceTime call traffic; calculates the FaceTime caller based on the key information; obtains a FaceTime detection log based on the FaceTime caller; builds a FaceTime fraudster behavior recognition model based on the FaceTime detection log; the features of the fraudster behavior recognition model include caller call frequency calculation, caller call duration calculation, caller discreteness calculation, fraud-related application association calculation and fraud-related special scenario calculation; based on the features of the fraudster behavior recognition model, determines a fraudster behavior scoring formula; based on the fraudster behavior scoring formula, judges and outputs fraudster clues.

[0007] In a second aspect, some embodiments of the present application further provide an electronic device, comprising: one or more processors; and a memory storing computer program instructions, wherein the computer program instructions, when executed, cause the processor to perform the steps of the method described above.

[0008] In a third aspect, some embodiments of the present application further provide a computer-readable medium having computer program instructions stored thereon, wherein the computer program instructions can be executed by a processor to implement the method as described above.

[0009] Compared with the related art, the solution provided in the embodiment of the present application records the key information during the FaceTime call through DPI technology and generates a FaceTime detection log. By performing model analysis on the FaceTime detection log, a FaceTime fraudster behavior recognition model is established. The model uses data mining technology to model and analyze the FaceTime log, identify fraud-related behaviors, and output fraud clues. The public security or operators can jointly deal with the mobile phone numbers of fraud clues, which can effectively prevent fraud and protect the rights and interests of users and network security. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0011] Figure 1 This is a schematic diagram of an exemplary process of a fraud behavior analysis method provided according to an embodiment of the present application;

[0012] Figure 2 This is a schematic diagram of an exemplary process of another fraud behavior analysis method provided according to an embodiment of the present application;

[0013] Figure 3 This is a schematic diagram of an exemplary structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0014] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0015] First embodiment

[0016] The first embodiment of the present application relates to a fraud behavior analysis method. Figure 1 As shown, the method may include the following steps:

[0017] S101, parsing FaceTime call traffic by using DPI technology to extract key information of the FaceTime call traffic;

[0018] S102, calculating the FaceTime caller according to the key information; and obtaining a FaceTime detection log according to the FaceTime caller;

[0019] S103, constructing a FaceTime fraudster behavior recognition model based on the FaceTime detection log; the features of the fraudster behavior recognition model include the calculation of caller call frequency, the calculation of caller call duration, the calculation of caller dispersion, the calculation of fraud-related application association, and the calculation of fraud-related special scenarios;

[0020] S104, determining a fraudster behavior scoring formula according to the characteristics of the fraudster behavior identification model;

[0021] S105, judging and outputting the scammer clues according to the scammer behavior scoring formula.

[0022] The following is a detailed description of each of the above steps.

[0023] S101: Analyze FaceTime call traffic through DPI technology to extract key information of FaceTime call traffic; In this step, the FaceTime call data packets are analyzed in detail through deep packet inspection (DPI) technology to extract key information including call duration, number of uplink bytes, number of downlink bytes, number of uplink packets, number of downlink packets, destination IP address, user mobile phone number, etc. This information provides basic data support for subsequent analysis.

[0024] S102: Calculate the FaceTime caller based on the key information; obtain the FaceTime detection log based on the FaceTime caller; calculate the calling status of each FaceTime call based on the key information extracted in step S101. By analyzing the average uplink message length and the number of uplink messages within a specified time, the possibility of the caller can be determined and a FaceTime detection log can be generated. The detection log records the detailed data of each call, including the identification of the two parties in the call, the calling and called status, the call duration, and the number and type of data packets to provide data support for subsequent model construction.

[0025] S103: Construct a FaceTime fraudster behavior identification model based on the FaceTime detection log; the features of the fraudster behavior identification model include the calculation of caller call frequency, caller call duration, caller dispersion, fraud-related application association, and fraud-related special scenario calculation; in this step, the fraudster behavior identification model is constructed by analyzing the FaceTime detection log. The model includes the following features: caller call frequency calculation, measuring the number of FaceTime calls initiated by the user within a specific time period; caller call duration calculation, recording the duration of each FaceTime call and scoring it according to the preset duration threshold; caller dispersion calculation, measuring the dispersion of the caller user's call objects, and calculating the dispersion score by the call frequency ratio; fraud-related application association calculation, analyzing the applications installed or used by the user before and after the call, and evaluating their correlation with fraudulent behavior; fraud-related special scenario calculation, considering the risks of specific call environments such as late-night calls and high-risk calls, and scoring;

[0026] S104: Determine a fraudster behavior scoring formula based on the characteristics of the fraudster behavior identification model; determine a fraudster behavior scoring formula based on the fraudster behavior identification model constructed in step S103. The formula combines the scores of the above-mentioned characteristics, determines the weight of each feature through model training, and generates a comprehensive score for evaluating the user's fraud risk.

[0027] S105: According to the fraudster behavior scoring formula, judge and output fraudster clues. In this step, the fraudster behavior scoring formula is applied to score the user's call behavior. When the score exceeds the preset threshold, the user is determined to be a suspected fraudster. The system outputs fraudster clues, including the fraudster's mobile phone number, fraud level, time, mobile location and other information, for subsequent disposal by the public security or operator.

[0028] It is not difficult to find that compared with the related art, the solution provided in the embodiment of the present application is based on the DPI FaceTime fraud behavior analysis method, which effectively improves the recognition accuracy and response speed of fraud behavior through precise data extraction, multi-dimensional behavior analysis, flexible scoring mechanism and real-time early warning response. This method can not only comprehensively record call details data and analyze user behavior from multiple angles, but also flexibly adjust the scoring mechanism to adapt to different fraud methods, provide timely and reliable fraud warning and response methods, protect user privacy and improve system resource utilization, and has important practical application value.

[0029] Second embodiment

[0030] The second embodiment of the present application relates to a fraud victim behavior analysis method. The second implementation is an improvement on the first embodiment, and the specific improvements are:

[0031] like Figure 2 As shown in the figure, DPI parses FaceTime call traffic, extracts key information from the data packet header, and records key information such as call duration, uplink bytes, downlink words, number of uplink packets, number of downlink packets, destination IP affiliation, user mobile phone number, etc.

[0032] FaceTime calls are calculated based on the specified time in the traffic, the average uplink message length ul_avg within the specified time, and the number of uplink messages ul_pkt. The shorter the unit time, the larger the average uplink message length and number, and the greater the possibility of a call. The calculation formula is as follows:

[0033] =(2- )* +(ul_avg-950)* + (ul_pkt-2)* ;

[0034] in Usually [0.3,0.4], Usually [0.2,0.3], Usually [0.6,0.7]; when the calling user >1.5, the calling user is considered as the FaceTime caller;

[0035] Output FaceTime detection log, FaceTime detection log includes the key information extracted by DPI technology and the calculated FaceTime caller information. For example, call duration records the start and end time of each FaceTime call; uplink bytes record the number of data bytes sent from the caller during each call; downlink bytes record the number of data bytes received from the called party during each call; uplink packet count records the number of data packets sent from the caller during each call; downlink packet count records the number of data packets received from the called party during each call; destination IP attribution records the destination IP address and its attribution information of each call; user mobile phone number: records the mobile phone number of the user participating in the FaceTime call; caller ID records whether each call is the caller ID (based on the above FaceTime caller calculation results); call frequency records the call frequency of the user within a specified time; call duration statistics the cumulative call duration of the user within a specified time.

[0036] Based on the FaceTime detection log, a FaceTime fraudster behavior recognition model is established. The model includes caller call frequency, caller call duration, caller dispersion, caller application association, special scenario bonus, etc. The specific indicators of the model are calculated as follows:

[0037] Call frequency calculation: measures the number of FaceTime calls initiated by the calling user in a specific time period (such as the past hour, day, week, etc.). A higher call frequency may mean that the user has active social activities and may be related to fraudulent behavior, because fraudsters may initiate calls frequently to find potential victims.

[0038] =log(1+ ), where a logarithmic function is used to smooth the score so that the score does not grow indefinitely even in the case of high-frequency calls.

[0039] Caller call duration calculation: This metric records the duration of each FaceTime call by the calling user. Abnormal call duration (too long or too short) may indicate that the call has a special purpose. For example, a very short call may be a scammer trying to confirm whether the target is online or check whether the phone number is valid; while a very long call may indicate that the scammer is trying to persuade the victim to make a transaction or provide sensitive information.

[0040] =max(0,min(1,( - )( - )));

[0041] in, is the current call duration, and are the preset minimum and maximum duration thresholds.

[0042] Caller dispersion calculation: This indicator measures the degree of dispersion of the call objects of the calling user. Users with high dispersion (i.e., frequent calls with different contacts) indicate that the user is trying to reach different users widely. Users with low dispersion (i.e., mainly calling a few contacts) may indicate that the user has fixed social relationships, but further analysis is also needed to rule out fraud risks. First, the frequency of calls with each contact is collected, where the number of calls with each contact is recorded. Next, calculate the proportion of the frequency of calls to each contact (p_i). This is usually achieved by dividing the number of calls to each contact by the total number of calls. In this way, we get a probability distribution, where each probability p_i represents the frequency proportion of calls with contact i.

[0043] =-SUM(p_i*log2(p_i)); where p_i is the frequency ratio of calls with contact i.

[0044] Fraudulent application association: This indicator focuses on the applications installed or used by the caller before and after the call. The potential risk of the caller is assessed by analyzing the types, functions and correlation of these applications with fraudulent behavior. For example, a user who has installed multiple applications related to fraudulent activities may have a higher risk of fraud;

[0045] = SUM( ); Common fraud-related applications are shown in Table 1:

[0046]

[0047] Table 1, Common fraud-related applications

[0048] Calculation of special scenarios involving fraud: mainly considers some specific call environments or conditions that may increase the risk of fraud. Special scenarios include but are not limited to: late night calls. Calls during late night hours (such as 1 am to 5 am) may increase the risk of fraud because most people are resting and more susceptible to deception; high-risk calls. International calls from unknown or high-risk areas may be related to fraud, which may be difficult to track or have lower law enforcement efficiency. By analyzing these special scenarios, potential fraud can be identified more accurately and corresponding measures can be taken to protect users from losses.

[0049] =SUM( ), where the single application risk score for late night calls is 10; and the single application risk score for high-risk calls is 10.

[0050] Combining the features of the above scammer behavior identification model, a scammer behavior scoring formula is constructed. This formula combines the above mentioned features to discover potential scammers in FaceTime calls. The calculation formula is as follows:

[0051] ;

[0052] W1, W2, W3, W4, and W5 are the weights of each feature, which need to be determined through model training. These weights represent the importance of each feature to the final risk score. According to the training situation, W1, W2, W3, W4, and W5 are 0.2, 0.3, 0.3, 0.15, and 0.05 respectively; if >2, it means the user is highly suspected of being a fraudster; if 1< <2, it means the user is a suspected scammer. Output scammer clues, including scammer's mobile phone number, scam level, time, mobile location, etc.

[0053] In addition, some embodiments of the present application also provide an electronic device. The electronic device may be a digital computer in various forms, such as a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, etc. The electronic device may also be a mobile device in various forms, such as a personal digital processing, a cellular phone, a smart phone, a wearable device, and other similar computing devices.

[0054] The electronic device includes: one or more processors; and a memory storing computer program instructions, wherein when the computer program instructions are executed, the processor executes the steps of the method provided in any one or more of the above embodiments. Figure 3 An exemplary structural diagram of the electronic device is disclosed. Figure 3 As shown, the electronic device includes: one or more processors 1101, a memory 1102, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some other embodiments, if necessary, multiple processors and / or multiple buses can be used with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Among them, the components shown in this article, their connections and relationships, and their functions are only examples, and are not intended to limit the implementation of the present application described and / or required herein.

[0055] The electronic device may further include: an input device 1103 and an output device 1104. The processor 1101, the memory 1102, the input device 1103 and the output device 1104 may be connected via a bus or other means. Figure 3 The example of connecting through bus is taken in the following.

[0056] The input device 1103 can receive input digital or character information, and generate key signal input related to the user settings and function control of the electronic device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator rod, one or more mouse buttons, a trackball, a joystick and other input devices. The output device 1104 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display and a plasma display. In some embodiments, the display device may be a touch screen.

[0057] To provide interaction with a user, the electronic device may be a computer. The computer has: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball), through which the user can provide input to the computer. Other types of devices may also be used to provide interaction with a user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0058] In the embodiments of the present application, a computer program / instruction is stored on a computer-readable medium, and when the computer program / instruction is executed by a processor, the steps of the method provided by any one or more of the above embodiments are implemented. The computer-readable medium may be included in the electronic device described in the above embodiments; or it may exist independently without being assembled into the device. The above computer-readable medium carries one or more computer-readable instructions.

[0059] The memory 1102 can be used as a non-transient computer-readable storage medium, which can be used to store non-transient software programs, non-transient computer executable programs and modules. The processor 1101 executes various functional applications and data processing of the server by running the non-transient software programs, instructions and modules stored in the memory 1102, so as to implement the program instructions / modules corresponding to the method provided by any one or more embodiments in the embodiments of the present application.

[0060] The memory 1102 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 1102 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory 1102 may optionally include a memory remotely arranged relative to the processor 1101, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0061] It should be noted that the computer-readable medium described in this application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer 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 of the above. In this application, a computer-readable medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device.

[0062] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, modules of programs or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0063] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0064] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. For example, an application specific integrated circuit (ASIC), a general-purpose computer or any other similar hardware device may be used to implement the embodiments. In some embodiments, the software program of the present application may be executed by a processor to implement the above steps or functions. Similarly, the software program of the present application (including related data structures) may be stored in a computer-readable recording medium, such as a RAM memory, a magnetic or optical drive or a floppy disk and the like. In addition, some steps or functions of the present application may be implemented by hardware, for example, as a circuit that cooperates with a processor to perform various steps or functions.

[0065] The computer program product provided in the embodiment of the present application includes one or more computer programs / instructions, and when the computer program / instructions are executed by the processor, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a server, or a data center to another website site, a computer, a server, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk (SSD)), etc.

[0066] The flow chart or block diagram in the accompanying drawings shows the possible architecture, function and operation of the equipment, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated system for hardware that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0067] The scope of the present application is defined by the appended claims rather than the above description, and it is intended that all changes that fall within the meaning and scope of the equivalent elements of the claims are included in the present application. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim may also be implemented by one unit or device through software or hardware. The words "first", "second", etc. are only used to distinguish the description, and do not indicate any particular order, nor can they be understood as indicating or implying relative importance.

[0068] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily mention changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims, and the above embodiments should be regarded as exemplary and non-restrictive.

Claims

1. A fraud behavior analysis method, It is characterized in that The method comprises: Analyze FaceTime call traffic using DPI technology to extract key information of the FaceTime call traffic; Calculating the FaceTime caller according to the key information, wherein the key information includes an average uplink message length and a number of uplink messages within a specified time; calculating the FaceTime caller according to the average uplink message length and the number of uplink messages; and obtaining a FaceTime detection log according to the FaceTime caller; Constructing a FaceTime fraudster behavior recognition model based on the FaceTime detection log; the features of the fraudster behavior recognition model include the calculation of caller call frequency, the calculation of caller call duration, the calculation of caller dispersion, the calculation of fraud-related application association, and the calculation of fraud-related special scenarios; Determine a fraudster behavior scoring formula based on the characteristics of the fraudster behavior identification model; determine potential fraudsters of the FaceTime call and output potential fraudster clues based on the fraudster behavior scoring formula; The fraudster behavior scoring formula is as follows: ; The fraudster behavior scoring formula includes the frequency of calls with the caller. , Call duration , calling dispersion , Fraudulent application association and special scenarios involving fraud The corresponding risk weights are W1, W2, W3, W4, and W5; the risk weights W1, W2, W3, W4, and W5 are determined by the fraudster behavior recognition model training, and are 0.2, 0.3, 0.3, 0.15, and 0.05 respectively; if >2, the calling user is considered to be a highly suspected fraudster; if 1< <2, the calling user is judged to be a suspected fraudster.

2. The method according to claim 1, It is characterized in that The calling call frequency calculation includes: The number of FaceTime calls initiated by the calling user within a specific time period is calculated; and the call frequency of the calling user is smoothed using a logarithmic function.

3. The method according to claim 2, It is characterized in that The calling call duration calculation includes: The duration of each FaceTime call of the calling user is recorded; and the call duration of the calling user is scored and calculated using a preset minimum duration threshold and a maximum duration threshold.

4. The method according to claim 3, It is characterized in that The calling dispersion calculation includes: Measures the dispersion of the callers' call partners; the dispersion score is calculated by the frequency ratio of the caller's calls to each contact.

5. The method according to claim 4, It is characterized in that The fraud-related application association calculation includes: Analyze the apps installed or used by the caller before and after the call; calculate app scores associated with fraudulent behavior.

6. The method according to claim 5, It is characterized in that The calculation of the special fraud scenarios includes: Analyze the special scenarios in which the calls occurred and calculate the scores of special fraud scenarios; the special fraud scenarios include late night calls and high-risk calls.

7. An electronic device, It is characterized in that The electronic device comprises: one or more processors; and A memory storing computer program instructions, which, when executed, cause the processor to perform the steps of the method as claimed in any one of claims 1 to 6.

8. A computer readable medium having a computer program / instructions stored thereon, It is 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 6 are implemented.

Citation Information

Patent Citations

  • ARIMA-based fraud phone prediction method and prediction system

    CN110062114A

  • Telephone fraud prevention and control method, device and equipment and computer program product

    CN114285943A