A method, device, equipment and storage medium for identifying telephone fraudsters
By analyzing communication data and calculating correlation of target numbers, and verifying with communication feedback data, the telecommunications fraud chain can be identified and cut off, solving the problem of incomplete identification of fraudsters in existing technologies and protecting the property security of legitimate users.
Patent Information
- Application Number
- CN202111521013.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-12-13
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2041-12-13
AI Technical Summary
Current technologies rely solely on piecemeal handling of individual fraudulent numbers, lacking comprehensive, end-to-end correlation analysis and detection, making it difficult to effectively identify and combat fraudsters.
By obtaining the communication data of the target number, it is determined whether it is a telephone fraud number, and the correlation is calculated to obtain the number of suspected fraudsters. Combined with communication feedback data for verification, it is determined whether they are telephone fraudsters.
It enables the effective identification and interception of fraudsters in telecommunications networks, reduces the possibility of legitimate users being defrauded, and protects the property security of legitimate users.
Smart Images

Figure CN114363463B_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present invention relate to the field of network communication technology, and in particular to a method, device, equipment and storage medium for identifying telephone fraudsters. Background Art
[0002] In the existing technology, it only relies on the scattered handling of individual fraud numbers, lacks all-round and full-chain correlation analysis and detection and disposal, and it is difficult to effectively identify and crack down on fraudsters. Summary of the invention
[0003] The embodiments of the present invention provide a method, device, equipment and storage medium for identifying telephone fraudsters, which can identify telecommunications fraudsters, effectively cut off the fraud chain, reduce the possibility of legitimate users being defrauded, and protect the property safety of legitimate users.
[0004] In a first aspect, an embodiment of the present invention provides a method for identifying telephone fraudsters, the method comprising:
[0005] Obtaining target communication data of a target number, and determining whether the target number is a telephone fraud number based on the target communication data;
[0006] If the target number is a telephone fraud number, a correlation degree calculation is performed based on the target communication data to obtain a suspected fraudster number associated with the target number;
[0007] Obtain the communication feedback data of the suspected fraudster number, and verify it based on the communication feedback data to determine whether the suspected fraudster number is a telephone fraudster.
[0008] In a second aspect, an embodiment of the present invention further provides a device for identifying telephone fraudsters, the device comprising:
[0009] A telephone fraud number determination module, used to obtain target communication data of a target number, and determine whether the target number is a telephone fraud number based on the target communication data;
[0010] A suspected fraudster number acquisition module is used to calculate the association degree according to the target communication data if the target number is a telephone fraud number, and obtain the suspected fraudster number associated with the target number;
[0011] The telephone fraud personnel identification module is used to obtain the communication feedback data of the suspected fraud personnel number, and verify according to the communication feedback data to determine whether the suspected fraud personnel number is a telephone fraud personnel.
[0012] In a third aspect, an embodiment of the present invention further provides an electronic device, the device comprising:
[0013] one or more processors;
[0014] a storage device for storing one or more programs,
[0015] When the one or more programs are executed by the one or more processors, the one or more processors implement a method for identifying telephone fraudsters as described in any embodiment of the present invention.
[0016] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for identifying telephone fraudsters as described in any embodiment of the present invention.
[0017] The technical solution of the embodiment of the present invention obtains the target communication data of the target number, and determines whether the target number is a telephone fraud number based on the target communication data; if the target number is a telephone fraud number, the correlation degree is calculated based on the target communication data to obtain the suspected fraud number associated with the target number; the communication feedback data of the suspected fraud number is obtained, and verification is performed based on the communication feedback data to determine whether the suspected fraud number is a telephone fraud number, thereby solving the problem of fraud identification in the telecommunications network, achieving the effect of effectively discovering telecommunications fraud personnel, cutting off the fraud chain, reducing the possibility of legitimate users being defrauded, and protecting the property safety of legitimate users. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] Figure 1 This is a flow chart of a method for identifying telephone fraudsters provided in the first embodiment of the present invention;
[0019] Figure 2 This is a flow chart of a method for identifying telephone fraudsters provided in Embodiment 2 of the present invention;
[0020] Figure 3 This is a schematic diagram of the structure of a device for identifying telephone fraudsters provided in Embodiment 3 of the present invention;
[0021] Figure 4 It is a structural schematic diagram of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION
[0022] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.
[0023] Embodiment 1
[0024] Figure 1This is a flow chart of a method for identifying telephone fraudsters provided in the first embodiment of the present invention. This embodiment can be applied to the situation where fraudsters are mined based on fraudulent numbers in a telecommunications network, thereby combating fraudsters. The method can be executed by a telephone fraudster identification device, which can be implemented by software and / or hardware, and the device can be integrated in a mobile phone, a computer or a server, such as Figure 1 As shown, the method specifically includes:
[0025] Step 110: Obtain target communication data of the target number, and determine whether the target number is a telephone fraud number based on the target communication data.
[0026] The target number may be a telephone number in a telecommunications network that needs to be identified for telephone fraud. The target communication data may be relevant data on the operator side, such as a billing bill of the target number. Specifically, the target communication data may include target signaling behavior data and / or target user behavior data. The target signaling behavior data may include one or more of user profile information, account opening information, and location information. The target user behavior data may include one or more of payment information, power on / off feature information, and call feature information when calling the same called user.
[0027] In the embodiment of the present invention, multiple implementation methods can be used to determine whether the target number is a telephone fraud number. For example, the target communication data can be input into a pre-trained machine learning model to identify telephone fraud numbers; or, a blacklist and whitelist verification mechanism can be used to determine whether the target number is in the blacklist, and when the target number is in the blacklist, the target number is determined to be a telephone fraud number; or, the target communication data can be matched with the fraud communication data of telephone fraud events that already exist in the telecommunications network, and when the matching degree is greater than a preset matching threshold, the target number can be determined to be a telephone fraud number.
[0028] Step 120: If the target number is a telephone fraud number, a correlation calculation is performed based on the target communication data to obtain the suspected fraudster number associated with the target number.
[0029] Among them, the correlation degree may refer to the correlation relationship between the target communication data and the alternative communication data of each alternative number in the preset resource library. The higher the correlation degree, the more likely the corresponding alternative number is to be a suspected fraudster number. The correlation degree calculation can determine the correlation degree between the target communication data and the alternative communication data in multiple dimensions. For example, the correlation degree calculation can be performed from the perspective of signaling behavior data and / or user behavior data. According to the correlation value obtained from the perspective of signaling behavior data and / or user behavior data, the suspected fraudster number associated with the target number is determined.
[0030] Specifically, in an optional implementation of an embodiment of the present invention, the target communication data includes target signaling behavior data; a correlation calculation is performed based on the target communication data to obtain a suspected fraudster number associated with the target number, including: a correlation calculation is performed based on one or more of the user profile information, account opening information, and location information in the target signaling behavior data to obtain a suspected fraudster number associated with the target number.
[0031] Among them, the correlation calculation based on the user profile information can be: obtaining an alternative number under the same user name as the target number determined as a telephone fraud number; if the alternative number and the target number have the same or similar communication characteristics, the alternative number can be determined as a suspected fraud number. In this process, the same or similar communication characteristics can be understood as the alternative number and the target number have the same card usage location, the card usage location is fixed, or calls are made to the same user, etc.
[0032] The correlation calculation based on the account opening information can be: obtaining the alternative numbers purchased in the same order as the target number determined as the telephone fraud number; if the alternative number and the target number have the same or similar communication characteristics, the alternative number can be determined as the suspected fraud number. In this process, the same or similar communication characteristics can be understood as the target number's card purchase order address is different from the card usage address, and the alternative number's card purchase order address is also different from the card usage address.
[0033] The correlation calculation based on the location information can be: obtaining an alternative number used in the same location as the target number determined as a telephone fraud number; if the alternative number and the target number have the same or similar communication characteristics, the alternative number can be determined as a suspected fraud number. In this process, the same or similar communication characteristics can be understood as the alternative number and the target number using the same card location, the card location is fixed, and have the same or similar power on and off feature information, etc.
[0034] In the embodiment of the present invention, in order to further accurately determine the suspected fraudster number and avoid interference with the normal number, the association degree calculation can be performed through multiple items of user profile information, account opening information and location information to determine the suspected fraudster number associated with the target number. For example, an alternative number purchased under the same user name, in the same order, and used at the same location as the target number determined as the telephone fraud number can be determined as the suspected fraudster number associated with the target number.
[0035] Another specific embodiment, in an optional implementation of the embodiment of the present invention, the target communication data includes target user behavior data; a correlation calculation is performed based on the target communication data to obtain a suspected fraudster number associated with the target number, including: a correlation calculation is performed based on one or more of the payment information, power on and off feature information, and call feature information when calling the same called user in the target user behavior data to obtain a suspected fraudster number associated with the target number.
[0036] Among them, the correlation calculation based on the payment information can be: obtaining an alternative number that uses the same number as the target number determined as a telephone fraud number for recharge and payment; if the alternative number and the target number have the same or similar communication characteristics, the alternative number can be determined as a suspected fraudster number. In this process, the same or similar communication characteristics can be understood as the recharge and payment of the alternative number and the target number are both small recharges, the number of numbers present when recharging and paying is large, and the recharge and payment are frequent.
[0037] The correlation calculation based on the power-on and power-off feature information can be: obtaining alternative numbers that are powered on and off in the same time period as the target number determined as a telephone fraud number; if the alternative number and the target number have the same or similar communication features, the alternative number can be determined as a suspected fraudster number. In this process, the same or similar communication features can be understood as the alternative number and the target number are in the same and fixed position, etc.
[0038] The correlation calculation based on the call feature information when calling the same called user can be: obtaining an alternative number that has the same called user as the target number determined as a telephone fraud number; if the alternative number and the target number have the same or similar communication characteristics, the alternative number can be determined as a suspected fraudster number. In this process, the same or similar communication characteristics can be understood as the existence of high-frequency and high-discrete characteristics between the called users dialed by the alternative number and the target number, that is, the alternative number and the target number both use a higher frequency to make outgoing calls, and the outgoing phone numbers are discontinuous and have a strong randomness. By determining the suspected fraudster number based on the correlation calculation based on the call feature information when calling the same called user, the script-like chain-link type of telephone fraudsters can be identified to ensure the safety of user property.
[0039] In an embodiment of the present invention, in order to further accurately determine the suspected fraudster number and avoid interfering with the normal number, the suspected fraudster number associated with the target number can be determined by calculating the correlation between payment information, power on / off feature information, and multiple call feature information when calling the same called user. For example, the target number determined as a telephone fraud number can be determined as a suspected fraudster number associated with the target number if the target number is charged and paid with the same number, is powered on and off in the same time period, and has an alternative number with the same called user.
[0040] Further, in order to improve the method for determining the suspected fraudster number of the embodiment of the present invention, the target signaling behavior data and the target user behavior data can be combined to perform correlation calculation to determine the suspected fraudster number associated with the target number. For example, the target number determined as the telephone fraud number can be determined as a suspected fraudster number associated with the target number under the same user name, purchased in the same order, used in the same location, using the same number for recharge and payment, turned on in the same time period and turned off in the same time period, and there is an alternative number of the same called user. In some optional implementations, the target signaling behavior data and the target user behavior data are combined to perform correlation calculation. When determining the suspected fraudster number associated with the target number, a certain weight coefficient can be assigned to the correlation determined according to the target signaling behavior data and the target user behavior data, and the suspected fraudster number associated with the target number can be determined according to the correlation and the corresponding weight coefficient.
[0041] Step 130: Obtain the communication feedback data of the suspected fraudster's number, and verify it based on the communication feedback data to determine whether the suspected fraudster's number is a telephone fraudster.
[0042] Among them, the communication feedback data can be complaint data made by users based on the communication status of the suspected fraudster number. For example, certain communication status restrictions can be imposed on the suspected fraudster number, such as not allowing calls, not allowing text messages, or not allowing Internet access. Users can complain to the operator based on the communication status of the suspected fraudster number and generate communication feedback data. Based on the communication feedback data, it can be verified whether the suspected fraudster number is a telephone fraudster. For example, it can be determined based on the communication feedback data whether the user of the suspected fraudster number is consistent with the user of the target number determined to be a telephone fraudster number; if they are consistent, it can be determined whether the suspected fraudster number is a telephone fraudster.
[0043] Specifically, there are many implementation methods for determining the user of the suspected fraudster number based on the communication feedback data. For example, the communication feedback data may include the user's basic information, and the user of the suspected fraudster number is determined based on the user's basic information; or, the communication feedback data may include the identification information of the device used by the user, and the user of the suspected fraudster number is determined based on the identification information of the device; or, the communication feedback data may include the user's location information, and the user of the suspected fraudster number is determined based on the location information; or, the communication feedback data may include the user's voiceprint information, and the user of the suspected fraudster number is determined based on the voiceprint information, etc.
[0044] In an optional implementation of an embodiment of the present invention, communication feedback data of a suspected fraudster's number is obtained, including: shutting down the suspected fraudster's number and guiding the suspected fraudster's number to reconnect online; obtaining one or more of the International Mobile Equipment Identity (IMEI) information, location information, and voiceprint information of the suspected fraudster's number when the number is reconnected online as communication feedback data.
[0045] Among them, the shutdown process can be to stop the service of the suspected fraudster number through the operator. Online reactivation can be to send a text message or make a phone call to the suspected fraudster number after the suspected fraudster number is shut down, and guide the suspected fraudster number to perform relevant operations to verify the number in order to reactivate the number. During the online reactivation process, the user of the suspected fraudster number can be required to enter text and / or voice content in a specified form for submission, so that IMEI information, location information, voiceprint information, etc. can be obtained as communication feedback data.
[0046] In an optional implementation of an embodiment of the present invention, verification is performed based on communication feedback data to determine whether the number of the suspected fraudster is a telephone fraudster, including: verification based on one or more of IMEI information, location information, and voiceprint information; when it is determined that the number of the suspected fraudster and the target number are used by the same user, the number of the suspected fraudster is determined to be a telephone fraudster.
[0047] Among them, determining that the suspected fraudster number and the target number are used by the same user based on IMEI information can be: when determining that the suspected fraudster number and the target number use the same device for multi-card re-establishment based on IMEI information, determining that the suspected fraudster number and the target number are used by the same user.
[0048] Determining that the suspected fraudster's number and the target number are used by the same user based on location information can be: when determining that the suspected fraudster's number and the target number are located in the same position for multi-card resetting, determining that the suspected fraudster's number and the target number are used by the same user.
[0049] Determining based on the voiceprint information that the suspected fraudster's number and the target number are used by the same user can be: when it is determined based on the voiceprint information that the voiceprint information of the suspected fraudster's number is consistent with that of the target number and they belong to the same user, determining that the suspected fraudster's number and the target number are used by the same user.
[0050] In the embodiment of the present invention, in order to improve the accuracy of identifying telephone fraudsters, multiple pieces of information including IMEI information, location information, and voiceprint information can be used for verification to determine whether the suspected fraudster number is a telephone fraudster. For example, when it is determined that the suspected fraudster number and the target number are in the same location, the same device is used for multi-card re-use, and the voiceprint information is consistent, it can be determined that the suspected fraudster number and the target number are used by the same user, and the suspected fraudster number is determined to be a telephone fraudster.
[0051] The technical solution of this embodiment obtains the target communication data of the target number, and determines whether the target number is a telephone fraud number based on the target communication data; if the target number is a telephone fraud number, the correlation degree is calculated based on the target communication data to obtain the suspected fraud number associated with the target number; the communication feedback data of the suspected fraud number is obtained, and verification is performed based on the communication feedback data to determine whether the suspected fraud number is a telephone fraud number, which solves the problem of fraud identification in the telecommunications network and realizes the mining of telecommunications fraud personnel based on telephone fraud numbers, thereby effectively cutting off the fraud chain, reducing the possibility of legitimate users being defrauded, and protecting the property safety of legitimate users.
[0052] Embodiment 2
[0053] Figure 2 This is a flow chart of a method for identifying telephone fraudsters provided in Embodiment 2 of the present invention. This embodiment is a further refinement of the above technical solution, and the technical solution in this embodiment can be combined with each optional solution in one or more of the above embodiments.
[0054] Specifically, in an optional implementation of an embodiment of the present invention, determining whether the target number is a telephone fraud number based on the target communication data includes: inputting the target communication data into a pre-trained fraud number recognition model to determine whether the target number is a telephone fraud number.
[0055] like Figure 2 As shown, the method includes:
[0056] Step 210: Obtain target communication data of the target number, and input the target communication data into a pre-trained fraud number recognition model to determine whether the target number is a telephone fraud number.
[0057] The fraud number recognition model may be a pre-trained machine learning model. Specifically, the fraud number recognition model may be trained using an XGBOOST classifier model based on the fraud features of telephone fraud numbers.
[0058] Specifically, in an optional implementation of an embodiment of the present invention, before inputting the target communication data into a pre-trained fraud number recognition model, it also includes: obtaining fraud communication data of fraud numbers in historical telephone fraud cases, and extracting fraud features based on the fraud communication data to form positive samples; obtaining normal communication data of normal numbers, and extracting normal features based on the normal communication data to form negative samples; and using a machine learning model to perform model training based on the positive samples and negative samples to obtain a fraud number recognition model.
[0059] Among them, historical telephone fraud cases can be reported fraud cases or solved fraud cases. Fraudulent communication data can be communication data corresponding to historical telephone fraud cases, and can include user information, account opening information, call bill data, payment information, and signaling data. Fraud characteristics can be common communication characteristics of historical telephone fraud cases, or they can be characteristics that meet preset fraud identification. Normal communication data can be communication data corresponding to normal numbers such as whitelist numbers, and can include user information, account opening information, call bill data, payment information, and signaling data. Normal characteristics can be common communication characteristics of normal numbers, or they can be characteristics that meet preset normal identification.
[0060] Specifically, when generating positive and negative samples, fraud features and normal features can be extracted from angles such as the number of calls, call frequency, discreteness of called numbers, silence duration, power on and off patterns, location information, account opening location, first call location, active time period, IMEI change frequency, and the location of the base station where the number is located. This can improve the accuracy and effectiveness of feature extraction, thereby improving the recognition reliability of the fraud number recognition model.
[0061] Step 220: If the target number is a telephone fraud number, a correlation calculation is performed based on the target communication data to obtain the suspected fraudster number associated with the target number.
[0062] Optionally, the target communication data includes target signaling behavior data; performing a correlation calculation based on the target communication data to obtain a suspected fraudster number associated with the target number, including: performing a correlation calculation based on one or more of the user profile information, account opening information, and location information in the target signaling behavior data to obtain a suspected fraudster number associated with the target number.
[0063] Optionally, the target communication data includes target user behavior data; a correlation calculation is performed based on the target communication data to obtain a suspected fraudster number associated with the target number, including: a correlation calculation is performed based on one or more of the payment information, power on and off feature information, and call feature information when calling the same called user in the target user behavior data to obtain a suspected fraudster number associated with the target number.
[0064] Step 230: Shut down the number of the suspected fraudster and guide the suspected fraudster to restore the number online.
[0065] Step 240: Obtain one or more of the International Mobile Equipment Identity (IMEI) information, location information, and voiceprint information of the suspected fraudster's number when reconnecting the number online as communication feedback data.
[0066] Step 250: Verify based on one or more of the IMEI information, location information, and voiceprint information. When it is determined that the suspected fraudster's number and the target number are used by the same user, determine that the suspected fraudster's number is a telephone fraudster.
[0067] The technical solution of this embodiment determines whether the target number is a telephone fraud number by obtaining the target communication data of the target number and inputting the target communication data into a pre-trained fraud number recognition model; if the target number is a telephone fraud number, the correlation degree is calculated according to the target communication data to obtain the suspected fraud number associated with the target number; the suspected fraud number is shut down and the suspected fraud number is guided to resume online; one or more of the International Mobile Equipment Identity (IMEI) information, location information and voiceprint information of the suspected fraud number when the suspected fraud number resumes online are obtained as communication feedback data; verification is performed according to one or more of the IMEI information, location information and voiceprint information, and when it is determined that the suspected fraud number and the target number are used by the same user, the suspected fraud number is determined to be a telephone fraud number, which solves the problem of fraud identification in the telecommunications network and realizes the full-scale and full-chain mining of telecommunications fraud personnel based on telephone fraud numbers, thereby effectively cutting off the fraud chain, facilitating timely and effective control of fraud personnel, reducing the possibility of legitimate users being defrauded in multiple dimensions, protecting the property safety of legitimate users, and comprehensively improving the effect of Internet management and information security capabilities.
[0068] Embodiment 3
[0069] Figure 3 This is a schematic diagram of the structure of a device for identifying telephone fraudsters provided by Embodiment 3 of the present invention. Figure 3 The device includes: a telephone fraud number determination module 310, a suspected fraud number acquisition module 320 and a telephone fraud person determination module 330. Among them:
[0070] A telephone fraud number determination module 310 is used to obtain target communication data of a target number and determine whether the target number is a telephone fraud number based on the target communication data;
[0071] The suspected fraudster number acquisition module 320 is used to calculate the correlation degree according to the target communication data if the target number is a telephone fraud number, and obtain the suspected fraudster number associated with the target number;
[0072] The telephone fraud personnel identification module 330 is used to obtain the communication feedback data of the suspected fraud personnel number, and verify it according to the communication feedback data to determine whether the suspected fraud personnel number is a telephone fraud personnel.
[0073] Optionally, the target communication data includes target signaling behavior data;
[0074] The suspected fraudster number acquisition module 320 includes:
[0075] The first suspected fraudster number acquisition unit is used to calculate the correlation based on one or more of the user profile information, account opening information and location information in the target signaling behavior data to obtain the suspected fraudster number associated with the target number.
[0076] Optionally, the target communication data includes target user behavior data;
[0077] The suspected fraudster number acquisition module 320 includes:
[0078] The second suspected fraudster number acquisition unit is used to calculate the correlation based on one or more of the payment information, power on and off feature information in the target user behavior data and the call feature information when calling the same called user, to obtain the suspected fraudster number associated with the target number.
[0079] Optionally, the telephone fraud personnel identification module 330 includes:
[0080] An online re-calling guidance unit is used to shut down the numbers of suspected fraudsters and guide the numbers of suspected fraudsters to re-call online;
[0081] The communication feedback data acquisition unit is used to obtain one or more of the International Mobile Equipment Identity (IMEI) information, location information and voiceprint information of the suspected fraudster's number when reconnecting online as communication feedback data.
[0082] Optionally, the telephone fraud personnel identification module 330 includes:
[0083] The telephone fraud identification unit is used to verify based on one or more of the IMEI information, location information and voiceprint information. When it is determined that the suspected fraudster's number and the target number are used by the same user, the suspected fraudster's number is determined to be a telephone fraudster.
[0084] Optionally, the telephone fraud number determination module 310 includes:
[0085] The telephone fraud number determination unit is used to input the target communication data into a pre-trained fraud number recognition model to determine whether the target number is a telephone fraud number.
[0086] Optionally, the device further includes:
[0087] A positive sample forming module is used to obtain fraudulent communication data of fraudulent numbers in historical telephone fraud cases before inputting the target communication data into the pre-trained fraudulent number recognition model, and to extract fraud features based on the fraudulent communication data to form positive samples;
[0088] A negative sample forming module is used to obtain normal communication data of a normal number and extract normal features based on the normal communication data to form a negative sample;
[0089] The fraud number recognition model training module is used to perform model training using a machine learning model based on positive samples and negative samples to obtain a fraud number recognition model.
[0090] The telephone fraud person identification device provided in the embodiment of the present invention can execute the telephone fraud person identification method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0091] Embodiment 4
[0092] Figure 4 is a schematic diagram of the structure of an electronic device provided by Embodiment 4 of the present invention, such as Figure 4 As shown, the device includes:
[0093] one or more processors 410, Figure 4 A processor 410 is taken as an example;
[0094] Memory 420;
[0095] The device may further include: an input device 430 and an output device 440 .
[0096] The processor 410, memory 420, input device 430 and output device 440 in the device may be connected via a bus or other means. Figure 4 The example of connecting through bus is taken in the following.
[0097] The memory 420 is a non-transitory computer-readable storage medium that can be used to store software programs, computer executable programs, and modules, such as program instructions / modules corresponding to a method for identifying telephone fraudsters in an embodiment of the present invention (for example, the attached Figure 3 The processor 410 executes various functional applications and data processing of the computer device by running the software programs, instructions and modules stored in the memory 420, that is, a method for identifying telephone fraudsters in the above method embodiment, namely:
[0098] Obtaining target communication data of a target number, and determining whether the target number is a telephone fraud number based on the target communication data;
[0099] If the target number is a telephone fraud number, a correlation degree calculation is performed based on the target communication data to obtain a suspected fraudster number associated with the target number;
[0100] Obtain the communication feedback data of the suspected fraudster number, and verify it based on the communication feedback data to determine whether the suspected fraudster number is a telephone fraudster.
[0101] The memory 420 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 computer device, etc. In addition, the memory 420 may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 420 may optionally include a memory remotely arranged relative to the processor 410, and these remote memories may be connected to the terminal 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.
[0102] The input device 430 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the computer device. The output device 440 may include a display device such as a display screen.
[0103] Embodiment 5
[0104] Embodiment 5 of the present invention provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, a method for identifying telephone fraudsters provided in an embodiment of the present invention is implemented:
[0105] Obtaining target communication data of a target number, and determining whether the target number is a telephone fraud number based on the target communication data;
[0106] If the target number is a telephone fraud number, a correlation degree calculation is performed based on the target communication data to obtain a suspected fraudster number associated with the target number;
[0107] Obtain the communication feedback data of the suspected fraudster number, and verify it based on the communication feedback data to determine whether the suspected fraudster number is a telephone fraudster.
[0108] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A 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 thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: 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 thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or device.
[0109] Computer-readable signal media may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media 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.
[0110] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
[0111] Computer program code for performing the operations of the present invention 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 through 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., through the Internet using an Internet service provider).
[0112] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims
1. A method for identifying telephone fraudsters, characterized in that: The method comprises: Obtaining target communication data of a target number, and determining whether the target number is a telephone fraud number based on the target communication data; If the target number is a telephone fraud number, a correlation degree calculation is performed based on the target communication data to obtain a suspected fraudster number associated with the target number; Obtaining communication feedback data of the suspected fraudster number, and verifying based on the communication feedback data to determine whether the suspected fraudster number is a telephone fraudster; Wherein, obtaining the communication feedback data of the suspected fraudster number includes: shutting down the suspected fraudster number and guiding the suspected fraudster number to restore the number online; obtaining the International Mobile Equipment Identity (IMEI) information, location information and voiceprint information of the suspected fraudster number when restoring the number online as the communication feedback data; Verifying according to the communication feedback data to determine whether the suspected fraudster number is a telephone fraudster, including: when it is determined that the suspected fraudster number and the target number are in the same location, use the same device for multi-card re-enabling, and the voiceprint information is consistent, it is determined that the suspected fraudster number and the target number are used by the same user, and the suspected fraudster number is determined to be a telephone fraudster; If the target number is a telephone fraud number, an association degree is calculated based on the target communication data to obtain a suspected fraudster number associated with the target number, including: an alternative number with the same card usage position as the target number, a fixed card usage position, calling the same user, purchased in the same order as the target number, the card purchase order address is different from the card usage address, under the same user name as the target number, using the same number for recharge and payment, small recharges, a large number of numbers present when recharging and paying, and frequent recharge and payment features, the same called user as the target number, the called user has high frequency and high discrete features, and the alternative number is turned on and off in the same time period as the target number, and is determined as the suspected fraudster number associated with the target number.
2. The method according to claim 1, characterized in that The target communication data includes target signaling behavior data; The association degree is calculated according to the target communication data to obtain the suspected fraudster number associated with the target number, including: A correlation degree is calculated based on one or more of the user profile information, account opening information and location information in the target signaling behavior data to obtain a suspected fraudster number associated with the target number.
3. The method according to claim 1, characterized in that: The target communication data includes target user behavior data; The association degree is calculated according to the target communication data to obtain the suspected fraudster number associated with the target number, including: The suspected fraudster number associated with the target number is obtained by calculating the correlation degree based on one or more of the payment information, power on / off feature information and call feature information when calling the same called user in the target user behavior data.
4. The method according to any one of claims 1 to 3, characterized in that: Determining whether the target number is a telephone fraud number according to the target communication data includes: The target communication data is input into a pre-trained fraud number recognition model to determine whether the target number is a telephone fraud number.
5. The method according to claim 4, characterized in that Before inputting the target communication data into the pre-trained fraud number recognition model, the method further includes: Obtain fraudulent communication data of fraudulent numbers in historical telephone fraud cases, and extract fraud features based on the fraudulent communication data to form positive samples; Acquire normal communication data of a normal number, and extract normal features based on the normal communication data to form a negative sample; Based on the positive samples and the negative samples, a machine learning model is used to perform model training to obtain a fraud number recognition model.
6. A device for identifying telephone fraudsters, characterized in that: include: A telephone fraud number determination module, used to obtain target communication data of a target number, and determine whether the target number is a telephone fraud number based on the target communication data; A suspected fraudster number acquisition module is used to calculate the association degree according to the target communication data if the target number is a telephone fraud number, and obtain the suspected fraudster number associated with the target number; A telephone fraud personnel identification module is used to obtain the communication feedback data of the suspected fraud personnel number and verify it according to the communication feedback data to determine whether the suspected fraud personnel number is a telephone fraud personnel; Among them, the telephone fraud personnel identification module includes: an online re-calling guidance unit, which is used to shut down the suspected fraud personnel number and guide the suspected fraud personnel number to re-call online; a communication feedback data acquisition unit, which is used to acquire the International Mobile Equipment Identity code IMEI information, location information and voiceprint information of the suspected fraud personnel number when re-calling online as the communication feedback data; The telephone fraud personnel identification module includes: a telephone fraud personnel identification unit, which is used to determine that the suspected fraud personnel number and the target number are used by the same user when the suspected fraud personnel number and the target number are in the same location, use the same device for multi-card re-user, and have the same voiceprint information, and determine that the suspected fraud personnel number is a telephone fraud personnel; The module for obtaining the number of suspected fraudsters is specifically used to: determine as the suspected fraudster number associated with the target number an alternative number that has the same card usage position as the target number, a fixed card usage position, calls the same user, is purchased in the same order as the target number, the card purchase order address is different from the card usage address, is under the same user name as the target number, uses the same number for recharge and payment, the recharge and payment are all small recharges, a large number of numbers exist when recharging and paying, and the recharge and payment are frequent, has the same called user as the target number, the called user has high frequency and high discreteness, and the phone is turned on and off in the same time period as the target number.
7. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 5.
8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.
Citation Information
Patent Citations
System and method for preventing phone fraud, mobile terminal and cloud terminal analysis server
CN103458412A
Telephone fraud detection method, storage medium and electronic device
CN107197463A
Method and system for real-time detection of communication fraud base on suspicious behavior recognition
CN107222865A
Self-learning method for anti-fraud system based on voiceprint recognition and intention understanding technology
CN108882242A
The invention discloses a tTelecommunication fraud event detection method and system
CN109615116A
