Fraud risk detection method and device based on FaceTime and medium

By obtaining and analyzing the voice call list, SMS details list and APP usage records of FaceTime users, using AI models to identify fraud risks, solving the accuracy and timeliness of the identification of fraud risks in the existing technology, and realizing the fraud number The accurate identification and traceability of gang numbers has improved the detection accuracy and the crackdown efforts of the public security organs.

CN118945265APending Publication Date: 2024-11-12EVERSEC BEIJING TECH +1
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411365071.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-27
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The existing technology is difficult to accurately identify the fraud risks in FaceTime calls, especially in the era when users’ mobile phone numbers and emails are frequently used, and traditional methods are difficult to monitor and manage abnormal calls initiated by the Internet, resulting in criminals being able to take advantage of the situation to commit fraud. .

Method used

By obtaining the voice list, SMS details list and APP usage records of the numbers to be detected, extracting abnormal characteristics, and using AI models to judge fraud risks, identifying new fraud-related numbers and fraud gang numbers to avoid false alarms to normal users , improve the detection accuracy and trace similar fraud-related numbers based on the detection results.

Benefits of technology

It realizes accurate identification and traceability of fraud risks in FaceTime calls, and identifies newly added fraud-related numbers and fraud gang numbers, which improves the accuracy of fraud risk detection, reduces false alarms for normal users, and facilitates public security organs Crack down and deal with it.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118945265A_ABST
    Figure CN118945265A_ABST
Patent Text Reader

Abstract

The invention discloses a fraud risk detection method and device based on FaceTime and a medium. The method comprises the following steps: acquiring use data information of a number to be detected at a current moment and in a historical period before the current moment, wherein the use data information comprises a voice ticket, a short message detailed ticket and an APP use record; counting abnormal features in the use data information according to a historical rule of a FaceTime fraud scene; and judging whether the to-be-detected number has a fraud risk or not according to an AI model generated by training the abnormal features and the sample data. According to the embodiment of the invention, the method comprises the steps: associating the use data information, extracting the abnormal features of the numbers under different data types, detecting the fraud risk according to an AI model generated through the training of a machine learning technology, and recognizing a newly-added fraud-related number and a corresponding device with the fraud risk; false alarms to normal users are avoided; the fraud risk detection accuracy is improved, and similar fraud-related numbers can be obtained based on detection result traceability.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of information security technology, and in particular to a fraud risk detection method, device and medium based on FaceTime. Background Art

[0002] At present, FaceTime is widely used as a real-time video call software. More and more people rely on FaceTime for communication, and the rapid development of technology has caused many FaceTime users to suffer from telecommunications fraud. Compared with traditional telecommunications fraud based on SIM card number outbound calls, as long as you know the other party's mobile phone number or email address, and both parties are in the Internet environment, you can initiate a point-to-point FaceTime video call. Therefore, in today's era of the Internet of Everything, the user's mobile phone number and email address are used quite frequently, and they are more easily obtained by criminals. Then users are exposed to the environment where criminals commit illegal and criminal activities, and face a very high risk of being defrauded. In fact, from the perspective of operators, it is difficult to monitor and manage the above-mentioned abnormal call behaviors initiated through the Internet, and it is impossible to judge the fraud risk based on regular SIM card call behaviors. To a certain extent, it gives criminals the opportunity to take advantage of the situation. Summary of the invention

[0003] The present invention provides a fraud risk detection method, device and medium based on FaceTime.

[0004] According to a first aspect of the present invention, a fraud risk detection method based on FaceTime is provided, the method comprising:

[0005] Obtain usage data information of the number to be detected at the current time and in the historical period before the current time, the usage data information includes voice call records, SMS details and APP usage records;

[0006] Counting abnormal features in the usage data information based on historical patterns of FaceTime fraud scenarios;

[0007] Determine whether the number to be detected has a fraud risk based on the AI ​​model generated by training the abnormal features and sample data.

[0008] According to a second aspect of the present invention, there is provided an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor implements the FaceTime-based fraud risk detection method as described in any embodiment of the present invention.

[0009] According to a third aspect of the present invention, a computer-readable storage medium is provided, wherein the computer instructions are used to cause the computer to execute the FaceTime-based fraud risk detection method as described in any embodiment of the present invention.

[0010] In order to make the features and advantages of the present application more obvious and understandable, some embodiments are given below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and are used together with the specification to illustrate the technical solutions of the present application. It should be understood that the following drawings only illustrate certain embodiments of the present application and should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can also be obtained based on these drawings without creative work.

[0012] Figure 1 This is an application scenario diagram of a fraud risk detection method based on FaceTime provided in an embodiment of the present application;

[0013] Figure 2 is a flowchart of a fraud risk detection method based on FaceTime provided in an embodiment of the present application;

[0014] Figure 3 It is a block diagram of an electronic device used to implement the FaceTime-based fraud risk detection method of an embodiment of the present application. DETAILED DESCRIPTION

[0015] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0016] The term "and / or" herein only describes an association relationship, indicating that three relationships may exist. For example, A and / or B may represent the following three situations: A exists alone, A and B exist at the same time, and B exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C may represent including any one or more elements selected from the set consisting of A, B, and C.

[0017] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0018] According to research, there are usually two ways to identify the risk of FaceTime call fraud, including: tracing and finding based on black IMEI codes and identifying based on FaceTime traffic. Among them, the specific steps of tracing and finding based on black IMEI codes are as follows: through the historical FaceTime fraud case data, extract the corresponding IMEI code used in the fraud of the corresponding number involved in the case as black IMEI data. Then, based on the black IMEI data, search in the real-time traffic details to find the newly used related numbers on these black IMEI devices. The operation of identifying based on FaceTime traffic is as follows: by analyzing the network traffic data generated by the FaceTime software during the call, extracting the key features of the call behavior, and based on this, realizing the identification of the use of the FaceTime software from the traffic data, the numbers using more FaceTime traffic are identified and detected. It can be seen that if the detection scheme of tracing and finding based on the black IMEI code relies on the historical accumulation of the existing data involved in the case, it has the disadvantages of poor timeliness, long update cycle, and difficulty in timely discovery of newly involved devices and corresponding numbers. If the detection scheme is based on FaceTime traffic, it is easy to misjudge the number of a user who uses FaceTime normally as a fraud number. Therefore, if the fraud risk is identified only by FaceTime traffic usage behavior, it is difficult to accurately determine whether the number to be detected is a fraud number that implements FaceTime fraud. Therefore, how to comprehensively and accurately implement fraud risk detection based on FaceTime has become a technical problem that needs to be solved urgently.

[0019] Based on the above research, the FaceTime-based fraud risk detection method provided by the present disclosure obtains the voice call bill, SMS detailed bill and traffic data corresponding to the number to be detected, extracts the corresponding behavioral characteristics under different data sources, trains the corresponding AI recognition model based on historical data, and solidifies the model online to realize the identification and judgment of fraud numbers with fraud risks in FaceTime calls. It can not only identify newly added fraud numbers and corresponding devices with fraud risks; avoid false alarms for normal users; improve the detection accuracy of fraud risks, but also trace back to similar fraud numbers based on the detection results.

[0020] The defects existing in the above solutions are the results obtained by the applicant after practice and careful research. Therefore, the process of discovering the above problems and the solutions proposed by this application for the above problems below should be the contributions made by the applicant to this application during the application process.

[0021] According to an embodiment of the present application, a schematic diagram 100 of an application scenario of a fraud risk detection method based on FaceTime is provided. Figure 1 As shown, the application scenario includes: the terminal device is used to use the user number and log in to the mailbox; based on the historical rules of FaceTime video call fraud scenarios, the acquired voice call bills, SMS details and APP usage records are combined to statistically analyze abnormal features, and then the AI ​​model is trained, and the fraud risks detected during the FaceTime call are output according to the AI ​​model, including fraudulent numbers and similar fraudulent numbers. Among them, the similar fraudulent numbers are traced to the source of the fraudulent numbers, and potential similar fraudulent numbers are found through base stations or imei codes, and the similar fraudulent numbers are output as fraud gang numbers. The FaceTime-based fraud risk detection method of the present application can not only detect fraudulent numbers but also other numbers of fraud gangs, which is beneficial for public security organs to conduct on-site investigations, and also facilitates subsequent fraudulent number association processing.

[0022] Those skilled in the art will appreciate that the above Figure 1 What is shown is only an example based on the application scenario of the present application and is not limiting.

[0023] Embodiment 1

[0024] According to an embodiment of the present application, a fraud risk detection method based on FaceTime is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than that shown here. Figure 2As shown, the FaceTime-based fraud risk detection method includes the following steps: S210, S220 and S230.

[0025] S210: Obtain usage data information of the number to be detected at the current time and in a historical period before the current time, wherein the usage data information includes voice call records, SMS details and APP usage records.

[0026] Obtain relevant usage data of the number to be tested on the day of testing and the N days before the day of testing, including at least but not limited to SMS details, voice call records, APP usage records, etc. Among them, the call record content at least includes the calling and called direction, local number, remote number, call start time, call duration, lac location, signaling cellid, imei and other fields; SMS details at least include SMS sending and receiving identification, local number, remote number, SMS sending time and other fields; APP usage records at least include local number, app name, start time, end time, local location.

[0027] S220. Count abnormal features in the usage data information based on historical patterns of FaceTime fraud scenarios.

[0028] Optionally, the method of counting abnormal features in the usage data information according to historical rules of FaceTime fraud scenarios includes: extracting first feature information of the voice call record, the first feature information including: calling and called direction, local number, opposite number, call start time, call duration, location area code, signaling positioning, and imei code; counting the total number of calls to the calling customer service number within the historical period, the total call duration to the calling customer service number within the historical period, the ratio of the total number of calls to the calling customer service number within the historical period to the total number of calls, whether there is any imei code change between the current time and the historical period, and whether the phone has been switched to a low-end Apple model based on the first feature information.

[0029] The relevant features that need to be counted based on voice call records include but are not limited to: the total number of calls to Apple's customer service number in the past few days, the total call duration of calls to Apple's customer service number in the past few days, the proportion of calls to Apple's customer service number in the past few days to the total number of calls, whether there is any change in imei behavior between the current time and the previous N days, whether the phone has been switched to a low-end Apple model, etc.

[0030] Optionally, the counting of abnormal features in the usage data information based on historical patterns of FaceTime fraud scenarios also includes: extracting second feature information of the SMS details, the second feature information including: SMS sending / receiving identifier, local number, peer number, SMS sending time; counting the number of times the verification code is received within the historical period, the median of the time interval for receiving the verification code within the historical period, and the difference between the first time the verification code is received and the account opening time within the historical period based on the second feature information.

[0031] Based on the peer number port, identify that the peer number port belongs to the relevant SMS for receiving the Apple verification code. The relevant features that need to be counted based on the SMS details include but are not limited to: counting the number of times the Apple verification code is received in multiple historical days, the median time interval for receiving the Apple verification code in multiple historical days, the time difference in seconds between the first receipt of the Apple verification code and the account opening time in multiple historical days, etc.

[0032] Optionally, counting abnormal features in the usage data information according to historical patterns of FaceTime fraud scenarios also includes: extracting third feature information of the APP usage record, the third feature information including: local phone number, APP name, start time of usage, end time of usage, and local location; counting the number of FaceTime calls within the historical period, the number of FaceTime calls on the day, and the proportion of the number of FaceTime usages on the day within the historical period based on the third feature information.

[0033] The relevant features that need to be counted based on the APP usage records include but are not limited to: the number of FaceTime calls in the previous N days, the number of FaceTime calls on the current day, the proportion of FaceTime usage on the current day to the number of calls in the last X days, etc.

[0034] S230. Determine whether the number to be detected has a fraud risk based on an AI model generated by training the abnormal features and sample data.

[0035] Optionally, judging whether the number to be detected has a fraud risk based on an AI model generated by training the abnormal features and sample data includes: counting abnormal features of the FaceTime user's number to calculate a target feature set; inputting the target feature set into the AI ​​model to obtain a fraud detection result for the user's number.

[0036] Analyze the numbers that use FaceTime on the Internet and identify the user numbers that are at risk of fraud: First, perform real-time feature statistics. For numbers that use FaceTime, calculate the relevant features corresponding to the numbers based on the abnormal feature statistics process. Second, perform algorithm model detection. Input the statistical relevant features into the previously trained AI model, call the AI ​​model for prediction, and determine whether the user number is a fraudulent number based on the model prediction results.

[0037] Among them, the AI ​​model is generated according to the abnormal features and sample data training, including: marking user numbers containing historical fraudulent behavior as positive samples in the sample data using FaceTime, and marking user numbers with normal usage behavior as negative samples; inputting the positive samples, the negative samples and the corresponding abnormal feature statistics into a binary classification machine learning model, training and generating an initial model; testing the initial model, selecting a model with the best evaluation parameters as the AI ​​model, and solidifying the AI ​​model into a local model file.

[0038] It should be noted that by testing and verifying different algorithm models, the algorithm model with the best evaluation parameter performance is selected as the final AI model. The selectable models include but are not limited to random forest, gradient boosting tree, and support vector machine. The trained AI model data is solidified into a local model file to facilitate model calling in the process of detecting fraud risks.

[0039] Furthermore, after inputting the target feature set into the AI ​​model to obtain the fraud detection result of the user number, it also includes: obtaining the fraud number in the fraud detection result; performing tracing analysis based on the imei code of the device last used by the fraud number, and determining that other used numbers under the same imei code have a history of silent phone change behavior as the same type of fraud numbers; screening the remaining numbers that have used FaceTime multiple times under the same base station within a historical period, and determining that the numbers with roaming phone change or sudden use of FaceTime traffic are the same type of fraud numbers.

[0040] It can be understood that: according to the AI ​​model, the fraud-related numbers are detected and traced, and the potential remaining fraud gang numbers are traced through base stations or imei, etc., wherein the similar fraud-related numbers are the fraud gang numbers. Exemplarily, the imei of the Apple device last used by the number is traced and analyzed, and the remaining numbers used under the same imei are associated. If the number has a history of abnormal behaviors such as silent phone changes, it is detected as a gang number. Optionally, the base station where the number actively uses FaceTime is traced and analyzed, and the remaining numbers that have used FaceTime multiple times under the same base station are screened out in combination with historical app usage data. If the number has abnormal behaviors such as roaming phone changes or sudden use of FaceTime traffic, it is detected as a gang number.

[0041] Optionally, the FaceTime-based fraud risk detection method also includes: outputting the fraud-related number and its corresponding active base station and IMEI code according to the fraud-related detection result output by the AI ​​model; outputting abnormal features corresponding to the same type of fraud-related numbers and the associated source number.

[0042] The fraudulent numbers detected by the AI ​​model and the similar fraudulent numbers detected based on the tracing results of the fraud gangs associated with them are output, and relevant feature indicators are added to facilitate the subsequent reporting to the public security to the scene for crackdown and disposal. Specifically, the detection results are output: for numbers judged as fraudulent by the model, the numbers and related abnormal features are output, including the number corresponding to the active base station, the number corresponding to the use of imei and other fields; the tracing results are output: for similar fraudulent numbers output by the fraud gangs through analysis and tracing, in addition to outputting the relevant abnormal features of similar fraudulent numbers, the source fraudulent numbers based on which the similar fraudulent numbers are detected need to be output together, so as to facilitate subsequent manual analysis and judgment.

[0043] The present application discloses a fraud risk detection method based on FaceTime. The method includes: obtaining usage data information of the number to be detected within the historical period before and at the current moment, the usage data information including voice call bills, SMS details and APP usage records; counting abnormal features in the usage data information according to the historical laws of FaceTime fraud scenarios; judging whether the number to be detected has a fraud risk based on the AI ​​model generated by training the abnormal features and sample data. The embodiment of the present application associates the usage data information, extracts abnormal features of numbers under different data types, detects fraud risks based on the AI ​​model generated by machine learning technology training, identifies newly added fraudulent numbers and corresponding devices with fraud risks; avoids false alarms for normal users; improves the detection accuracy of fraud risks, and can also trace back to obtain similar fraudulent numbers based on the detection results. Potential fraud gangs are discovered based on the similar fraudulent numbers, which facilitates the association and processing of the fraudulent numbers.

[0044] Embodiment 2

[0045] Reference below Figure 3 , which shows a block diagram of an electronic device 300 suitable for implementing an embodiment of the present application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0046] like Figure 3 As shown, the electronic device 300 may include a processing device 310, which may perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 320 or a program loaded from a storage device 380 into a random access memory (RAM) 330. The processing device 310 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processing device 310 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processing device 310 performs the various methods and processes described above.

[0047] In the RAM 330, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 310, the ROM 320, and the RAM 330 are connected to each other through a bus 340. An input / output (I / O) interface 350 is also connected to the bus 340.

[0048] Typically, the following devices may be connected to the I / O interface 350: an input device 360 ​​including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 370 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 380 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 390. The communication device 390 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0049] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through a communication device 390, or installed from a storage device 380, or installed from a ROM 320. When the computer program is executed by the processing device 310, the above functions defined in the method of the embodiment of the present application are executed. Alternatively, in other embodiments, the processing device 310 can be configured to execute the method in any other appropriate manner (for example, by means of firmware): obtaining the usage data information of the number to be detected within the historical period before the current moment and the current moment, and the usage data information includes voice call bills, SMS details and APP usage records; according to the historical laws of FaceTime fraud scenarios, the abnormal features in the usage data information are counted; according to the AI ​​model generated by the training of the abnormal features and sample data, it is judged whether the number to be detected has a fraud risk.

[0050] Embodiment 3

[0051] The computer-readable medium mentioned above in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage 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 the present application, a computer-readable storage 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. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0052] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0053] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0054] The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains usage data information of the number to be detected within the current moment and the historical period before the current moment, and the usage data information includes voice call records, text message details and APP usage records; counts abnormal features in the usage data information according to the historical laws of FaceTime fraud scenarios; and determines whether the number to be detected has a fraud risk based on an AI model generated by training the abnormal features and sample data.

[0055] 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, but not limited to, 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 cases involving 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).

[0056] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square 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 square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square 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 square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0057] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of a module does not, in some cases, constitute a limitation on the module itself.

[0058] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof, etc.

[0059] The program code for implementing the method of the present application can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, implements the functions / operations specified in the flow chart and / or block diagram. The program code can be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0060] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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 foregoing.

[0061] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: 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 pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0062] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0063] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services. The server may also be a server of a distributed system, or a server combined with a blockchain.

[0064] Artificial intelligence is a discipline that studies how to use computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.). It includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, machine learning / deep learning technology, big data processing technology, knowledge graph technology, and other major directions.

[0065] Cloud computing refers to a technology system that uses network access to elastically scalable shared physical or virtual resource pools. Resources can include servers, operating systems, networks, software, applications, and storage devices, and can be deployed and managed on demand and in a self-service manner. Cloud computing technology can provide efficient and powerful data processing capabilities for technical applications such as artificial intelligence and blockchain, as well as model training.

[0066] The embodiments described above are part of the embodiments of the present application, but not all of them. Based on the embodiments in the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the embodiments of the present application.

[0067] In the description of the embodiments of the present application, it should be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc. indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, or are the positions or positional relationships in which the product of the application is usually placed when in use. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the electric vehicle or component referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0068] In the description of the embodiments of the present application, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0069] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A fraud risk detection method based on FaceTime, characterized in that: The method comprises: Obtain usage data information of the number to be detected at the current time and in the historical period before the current time, the usage data information includes voice call records, SMS details and APP usage records; Counting abnormal features in the usage data information based on historical patterns of FaceTime fraud scenarios; Determine whether the number to be detected has a fraud risk based on the AI ​​model generated by training the abnormal features and sample data.

2. The method according to claim 1, characterized in that: The abnormal features in the usage data information are counted based on the historical rules of FaceTime fraud scenarios, including: Extracting first characteristic information of the voice call record, the first characteristic information including: calling and called directions, local end number, remote end number, call start time, call duration, location area code, signaling location, and IMEI code; According to the first characteristic information, statistics are collected on the total number of calls to the customer service number within the historical period, the total call duration to the customer service number within the historical period, the ratio of the total number of calls to the customer service number within the historical period to the total number of calls, whether there is any change in the IMEI code between the current time and the historical period, and whether the phone has been switched to a low-end Apple model.

3. The method according to claim 1, characterized in that The counting of abnormal features in the usage data information based on the historical rules of FaceTime fraud scenarios also includes: Extracting second characteristic information of the SMS details, the second characteristic information including: SMS sending / receiving identifier, local end number, peer end number, and SMS sending time; The number of times the verification code is received within the historical period, the median of the time interval for receiving the verification code within the historical period, and the difference between the time of first receiving the verification code and the time of account opening within the historical period are counted according to the second characteristic information.

4. The method according to claim 1, characterized in that: The counting of abnormal features in the usage data information based on the historical rules of FaceTime fraud scenarios also includes: Extracting the third characteristic information of the APP usage record, the third characteristic information including: local terminal number, APP name, start time of usage, end time of usage, and location of the local terminal; The number of FaceTime calls in the historical period, the number of FaceTime calls on the current day, and the proportion of the number of FaceTime calls on the current day in the historical period are counted according to the third characteristic information.

5. The method according to claim 1, characterized in that: The determining whether the number to be detected has a fraud risk based on the AI ​​model generated by training the abnormal features and sample data includes: Count the abnormal features of FaceTime users' numbers and calculate the target feature set; The target feature set is input into the AI ​​model to obtain a fraud detection result of the user number.

6. The method according to claim 5, characterized in that The AI ​​model is generated according to the abnormal features and sample data training, including: In the sample data of FaceTime usage, user numbers with a history of fraudulent behavior are marked as positive samples, and user numbers with normal usage behavior are marked as negative samples; Inputting the positive samples, the negative samples and the corresponding abnormal feature statistics into a binary classification machine learning model to train and generate an initial model; The initial model is tested, a model with optimal evaluation parameters is selected as the AI ​​model, and the AI ​​model is solidified into a local model file.

7. The method according to claim 5, characterized in that After the target feature set is input into the AI ​​model to obtain the fraud detection result of the user number, the method further includes: Obtaining a fraudulent number from the fraudulent detection result; According to the IMEI code of the device last used by the fraudulent number, a traceability analysis is performed to determine that other numbers with the same IMEI code that have a history of silent device switching are similar fraudulent numbers; Filter the remaining numbers that have used FaceTime multiple times on the same base station during the historical period, and determine that the numbers that have roamed or suddenly used FaceTime traffic are similar fraudulent numbers.

8. The method according to claim 7, characterized in that The method further comprises: According to the fraud detection result output by the AI ​​model, the fraud number and its corresponding active base station and imei code are output; Output the abnormal features corresponding to the same type of fraudulent numbers and the associated source numbers.

9. An electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor implements the method as described in any one of claims 1-8.

10. A computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-8.

Citation Information

Cited By

  • Abnormal information sending method and device, electronic equipment and computer readable medium

    CN120934978A