An artificial intelligence-based telephone fraud early warning system

Abstract

The application provides an artificial intelligence-based telephone fraud early warning system, and relates to the field of electric digital data processing.The system comprises a communication channel monitoring module, a parameter collection and analysis module, an intelligent fraud analysis module and an early warning module.The communication channel monitoring module is used for monitoring call information of a communication channel.The parameter collection and analysis module is used for collecting call information of a communication channel of a calling number and performing preliminary analysis.The intelligent fraud analysis module performs in-depth analysis on the collected call information to determine whether it is telephone fraud.The early warning module sends early warning information when telephone fraud is detected.The system can intelligently analyze the communication relationship of a calling number, mine relevant communication subject information, compare the formed network structure, and effectively identify telephone fraud.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of digital data processing, in particular to a telephone fraud early warning system based on artificial intelligence. BACKGROUND

[0002] With the popularity of mobile phones, telephone fraud has become a very common fraud method, and at the same time, the fraud content is becoming more and more difficult to identify, therefore, a fraud early warning system that does not need to analyze the call content, but analyzes the communication data of the calling number, is needed to identify telephone fraud, effectively protect the property safety of users, and reduce the success rate of telephone fraud.

[0003] The foregoing discussion of the background of the application is merely intended to facilitate understanding of the present application. None of the discussion of the background of the application is a concession that any of the materials referred to is part of the prior art base or common general knowledge.

[0004] Now many fraud early warning systems have been developed, after a large amount of search and reference, it is found that the existing fraud early warning systems have systems disclosed in the system with publication number CN117202200A, these systems generally include establishing an anti-fraud application download data channel with an anti-telephone fraud server in the case of a calling number being a fraud call, the anti-fraud application download data channel is a channel established by adding a data channel SDP parameter in the session request signaling sent from the calling user end to the called user end, the data channel SDP parameter refers to the data channel negotiation SDP parameter of the anti-telephone fraud server; based on the anti-fraud application download data channel, telephone fraud early warning is carried out. But the system is a warning method under the known fraud call, but there is no specific method to identify the fraud call, so it cannot effectively identify the fraud call and reduce the success rate of telephone fraud. SUMMARY

[0005] The present application aims to address the existing deficiencies, and proposes a telephone fraud early warning system based on artificial intelligence.

[0006] The present application adopts the following technical solutions:

[0007] A telephone fraud early warning system based on artificial intelligence, comprising a communication channel monitoring module, a parameter collection and analysis module, an intelligent fraud analysis module, and an early warning prompt module;

[0008] The communication channel monitoring module is used to monitor the call information of the communication channel, the parameter collection and analysis module is used to collect the call information of the calling number communication channel and perform preliminary analysis, the intelligent fraud analysis module performs in-depth analysis based on the collected call information to determine whether it is a telephone fraud, and the early warning prompt module issues a warning information when a telephone fraud is detected;

[0009] The communication channel monitoring module comprises a session request recording unit and a call duration recording unit, the session request recording unit is used for recording session request information sent by each communication subject, and the call duration recording unit is used for recording call duration information of each communication subject in a successful connection state;

[0010] The parameter collection and analysis module comprises an activation query unit, an information storage unit and a primary detection unit, the activation query unit is used for querying call information of a calling number from the communication channel monitoring module when receiving session request information, the information storage unit is used for storing the queried call information, and the primary detection unit is used for analyzing the call information and judging whether to perform in-depth analysis;

[0011] The intelligent fraud analysis module comprises a subject screening unit, an intelligent analysis unit and a structure judgment unit, the subject screening unit is used for screening a communication subject closely related to the calling number, the intelligent analysis unit is used for intelligently analyzing the screened communication subject, and the structure judgment unit is used for analyzing and judging a mesh structure formed by the calling number and the screened communication subject;

[0012] Further, the primary detection unit comprises a pre-position statistical processor and a primary calculation processor, the pre-position statistical processor is used for classifying and counting the collected call information, and the primary calculation processor is used for calculating and analyzing the counting result and judging whether to perform in-depth analysis on the calling number;

[0013] The items counted by the pre-position statistical processor comprise a rejection number n1, an acceptance number n2, a subject number n3 and total call duration of each subject T i};

[0014] The primary calculation processor calculates a primary judgment value P according to the following formula:

[0015]

[0016] Wherein, T0 is a time base;

[0017] When the primary judgment value is greater than a primary threshold value, it is judged that in-depth analysis is needed, and the calling number information is sent to the intelligent fraud analysis module;

[0018] Further, the subject screening unit comprises an association calculation processor, a flow control processor and a subject recording processor, the association calculation processor is used for calculating an association degree between two communication subjects, the flow control processor is used for controlling the screening process of the communication subject, and the subject recording processor is used for recording the screened communication subject information;

[0019] Further, the intelligent analysis unit comprises a detection calling processor and an attribute judgment processor, the detection calling processor is used for calling the primary detection unit to calculate the primary judgment value of all communication subjects, and the attribute judgment processor analyzes and judges the attribute of each communication subject;

[0020] The attribute judgment processor calculates the command index Cm of the communication subject according to the following formula:

[0021]

[0022] Wherein, m is the number of other communication subjects associated with the communication subject, P i represents the primary judgment value of the ith associated communication subject, and P0 represents the primary judgment value of the communication subject itself;

[0023] The attribute judgment processor takes (m, Cm) as the attribute vector of the communication subject, and according to the attribute vector, corresponding attributes are given, the attributes include command, execution and normality;

[0024] Further, the early warning prompt module comprises a text display unit and a voice prompt unit, the text display unit is used for displaying fraud prompt information on the terminal before the call is connected, and the voice prompt unit is used for issuing fraud prompt voice after the call is connected.

[0025] The present application has the following beneficial effects:

[0026] The system divides the fraud recognition into two parts of primary recognition and in-depth recognition, the primary recognition can simply analyze and process data, filter a large number of normal calls, reduce the operation amount, the in-depth recognition can mine the communication relationship network behind the calling number, calculate and analyze the communication relationship network, judge the role of different communication subjects in the relationship network, and finally recognize the fraud network type, which can effectively recognize the telephone fraud and make early warning, and reduce the success rate of telephone fraud.

[0027] In order to further understand the features and technical contents of the present application, please refer to the following detailed description and drawings of the present application. However, the provided drawings are only used for reference and illustration, and are not used to limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0028] Figure 1 It is a schematic diagram of the overall structure framework of the present application;

[0029] Figure 2 It is a schematic diagram of the parameter acquisition and analysis module of the present application;

[0030] Figure 3 It is a schematic diagram of the intelligent fraud analysis module of the present application;

[0031] Figure 4 A schematic diagram of a primary detection unit of the present application is shown in Figure 1.

[0032] Figure 5 A schematic diagram of a screening unit of the present application is shown in Figure 2. DETAILED DESCRIPTION

[0033] The following embodiments are illustrative of how the application can be implemented and practiced. The advantages and effects of the present application can be understood from the disclosure of the embodiments. The present application can be implemented or applied in other different embodiments, and the details in the embodiments can be modified and changed in various ways based on different views and applications without departing from the spirit of the present application. In addition, the drawings of the present application are only simple schematic illustrations and are not drawn according to actual dimensions, and it is declared in advance. The following embodiments will further illustrate the related technical content of the present application, but the disclosed content is not intended to limit the protection scope of the present application.

[0034] Embodiment 1.

[0035] The present embodiment provides an artificial intelligence-based telephone fraud early warning system, which combines Figure 1 , including a communication channel monitoring module, a parameter acquisition and analysis module, an intelligent fraud analysis module, and an early warning module;

[0036] The communication channel monitoring module is used to monitor the call information of the communication channel, the parameter acquisition and analysis module is used to acquire the call information of the calling number communication channel and perform preliminary analysis, the intelligent fraud analysis module is used to perform in-depth analysis based on the acquired call information to determine whether it is telephone fraud, and the early warning module is used to issue early warning information when telephone fraud is detected;

[0037] The communication channel monitoring module includes a session request recording unit and a call duration recording unit, the session request recording unit is used to record the session request information sent by each communication subject, and the call duration recording unit is used to record the call duration information of each communication subject in the successful connection state;

[0038] The parameter acquisition and analysis module includes an activation query unit, an information storage unit, and a primary detection unit, the activation query unit is used to query the call information of the calling number from the communication channel monitoring module when receiving the session request information, the information storage unit is used to save the queried call information, and the primary detection unit is used to analyze the call information and determine whether to perform in-depth analysis;

[0039] The intelligent fraud analysis module comprises an object screening unit, an intelligent analysis unit and a structure judging unit, the object screening unit is used for screening a communication subject closely related to the calling number, the intelligent analysis unit is used for intelligently analyzing the screened communication subject, and the structure judging unit analyzes and judges a mesh structure formed by the calling number and the screened communication subject;

[0040] The primary detection unit comprises a pre-statistical processor and a primary calculation processor, the pre-statistical processor is used for classifying and counting the collected call information, and the primary calculation processor is used for calculating and analyzing the counting result and judging whether the calling number needs to be deeply analyzed;

[0041] The items counted by the pre-statistical processor include the number of rejections n1, the number of acceptances n2, the number of objects n3 and the total call duration of each object T i};

[0042] The primary calculation processor calculates a primary judgment value P according to the following formula:

[0043]

[0044] Wherein, T0 is a time base;

[0045] When the primary judgment value is greater than a primary threshold value, it is judged that deep analysis is needed, and the calling number information is sent to the intelligent fraud analysis module;

[0046] The object screening unit comprises an association calculation processor, a flow control processor and a subject record processor, the association calculation processor is used for calculating the association degree between two communication subjects, the flow control processor is used for controlling the screening process of the communication subject, and the subject record processor is used for recording the information of the screened communication subject;

[0047] The intelligent analysis unit comprises a detection calling processor and an attribute judging processor, the detection calling processor is used for calling the primary detection unit to calculate the primary judgment value of all communication subjects, and the attribute judging processor analyzes and judges the attributes of each communication subject;

[0048] The attribute judging processor calculates a command index Cm of the communication subject according to the following formula:

[0049]

[0050] Wherein, m is the number of other communication subjects associated with the communication subject, P i represents the primary judgment value of the i-th associated communication subject, and P0 represents the primary judgment value of the communication subject itself;

[0051] The attribute judgment processor takes (m, Cm) as an attribute vector of a communication subject, and attributes are given according to the attribute vector, including command, execution and common;

[0052] The early warning prompt module includes a text display unit and a voice prompt unit, the text display unit is used to display fraud prompt information on the terminal before the call is connected, and the voice prompt unit is used to issue fraud prompt voice after the call is connected.

[0053] Embodiment two.

[0054] This embodiment includes all the contents of embodiment one, and provides a telephone fraud early warning system based on artificial intelligence, including a communication channel monitoring module, a parameter collection and analysis module, an intelligent fraud analysis module and an early warning prompt module;

[0055] The communication channel monitoring module is used to monitor the call information of the communication channel, the parameter collection and analysis module is used to collect the call information of the calling number communication channel and perform preliminary analysis, the intelligent fraud analysis module performs in-depth analysis based on the collected call information to determine whether it is telephone fraud, and the early warning prompt module issues early warning information when telephone fraud is detected;

[0056] The communication channel monitoring module includes a session request recording unit and a call duration recording unit, the session request recording unit is used to record the session request information sent by each communication subject, and the call duration recording unit is used to record the call duration information of each communication subject in the successful connection state;

[0057] In combination Figure 2 , the parameter collection and analysis module includes an activation query unit, an information storage unit and a primary detection unit, the activation query unit is used to query the call information of the calling number from the communication channel monitoring module when receiving the session request information, the information storage unit is used to save the queried call information, and the primary detection unit is used to analyze the call information and determine whether to perform in-depth analysis;

[0058] In combination Figure 3 , the intelligent fraud analysis module includes an object screening unit, an intelligent analysis unit and a structure judgment unit, the object screening unit is used to screen out the communication subjects closely related to the calling number, the intelligent analysis unit is used to perform intelligent analysis on the screened communication subjects, and the structure judgment unit is used to analyze and judge the mesh structure formed by the calling number and the screened communication subjects;

[0059] The pre-warning prompting module comprises a text display unit and a voice prompting unit, the text display unit is used to display fraud warning information on the terminal before the conversation is connected, and the voice prompting unit is used to issue fraud warning voice after the conversation is connected;

[0060] The conversation request recording unit records conversation request information including a request object, a request time and a request result, and the request result is classified into rejection and acceptance;

[0061] The conversation request recording unit comprises a request number processor and a request information register, the request number processor is used to set a number for each conversation request information, and the request information register is used to save the conversation request information with each number;

[0062] The call duration recording unit comprises a number query processor and a call information register, the number query processor is used to query the corresponding number from the conversation request recording unit when the phone is connected, and the call information register is used to store the call duration information of the queried number;

[0063] The activation query unit comprises an activation response processor and a communication subject query processor, the activation response processor is used to respond to the conversation request information and obtain the caller number information, and the communication subject query processor is used to query the corresponding call information from the communication channel monitoring module with the caller number information as the communication subject;

[0064] The communication subject query processor only queries the call information within a fixed time, the fixed time refers to a fixed time length before the current time point, and the specific value of the fixed time length is set by itself;

[0065] In combination with Figure 4 , the primary detection unit comprises a pre-statistics processor and a primary calculation processor, the pre-statistics processor is used to statistically classify the collected call information, and the primary calculation processor is used to calculate and analyze the statistical results and determine whether the caller number needs to be further analyzed;

[0066] The items counted by the pre-statistics processor include the number of rejections n1, the number of acceptances n2, the number of objects n3 and the total call duration of each object T i};

[0067] The primary calculation processor calculates the primary judgment value P according to the following formula:

[0068]

[0069] Wherein, T0 is the time base;

[0070] When the primary judgment value is greater than the primary threshold value, it is judged that in-depth analysis is needed and the caller number information is sent to the intelligent fraud analysis module;

[0071] In combination Figure 5 The object screening unit includes an association calculation processor, a flow control processor and a subject record processor, the association calculation processor is used to calculate the association degree between two communication subjects, the flow control processor is used to control the screening process of the communication subjects, and the subject record processor is used to record the information of the screened communication subjects;

[0072] The working flow of the flow control processor includes the following steps:

[0073] S1, acquiring a communication subject having effective communication with the caller number;

[0074] S2, sending the caller number and one of the communication subjects acquired in step S1 as input parameters to the association calculation processor;

[0075] S3, receiving the feedback result of the association calculation processor, and sending the communication subject meeting the requirement to the subject record processor;

[0076] S4, repeating step S2 and step S3 until the communication subjects acquired in step S1 are all processed;

[0077] S5, acquiring one of the communication subjects in the subject record processor as an extended subject;

[0078] S6, acquiring a communication subject having effective communication with the extended subject;

[0079] S7, sending the extended subject and one of the communication subjects acquired in step S6 as input parameters to the association calculation processor;

[0080] S8, receiving the feedback result of the association calculation processor, and sending the communication subject meeting the requirement to the subject record processor;

[0081] S9, repeating step S7 and step S8 until the communication subjects acquired in step S6 are all processed;

[0082] S10, repeating step S5 to step S9 until all the communication subjects acquired from step S3 in the subject record processor are processed;

[0083] The association calculation processor calculates the association index As between two communication subjects according to the following formula:

[0084] As = lg(n·T);

[0085] Wherein, n is the number of communications between two communication subjects, T is the total communication duration between two communication subjects;

[0086] When the association index is greater than the association threshold, it indicates that the association degree of two communication subjects meets the requirements and has association;

[0087] The intelligent analysis unit includes a detection calling processor and an attribute judgment processor, the detection calling processor is used to call the primary detection unit to calculate the primary judgment value of all communication subjects, and the attribute judgment processor analyzes and judges the attribute of each communication subject;

[0088] The communication subjects processed by the intelligent analysis unit are all communication subjects recorded in the subject record processor;

[0089] The attribute judgment processor calculates the command index Cm of the communication subject according to the following formula:

[0090]

[0091] Wherein, m is the number of other communication subjects having association with the communication subject, P i Pi represents the primary judgment value of the ith communication subject having association, and P0 represents the primary judgment value of the communication subject itself;

[0092] The attribute judgment processor takes (m, Cm) as the attribute vector of the communication subject, and assigns the corresponding attribute according to the attribute vector, the attribute judgment processor is built-in with the attribute vector interval corresponding to different attributes, and the attributes include command, execution and common;

[0093] The structure judgment unit includes a network generation processor and a structure comparison processor, the network generation processor generates corresponding network connected information based on the attribute judgment result, and the structure comparison processor compares the generated network connected information with the fraud network structure;

[0094] The network generation processor retains the communication subjects with command and execution attributes, and connects the communication subjects based on association to obtain a network structure;

[0095] The structure comparison processor records a plurality of modes of fraud network structure, and compares them one by one with the generated network structure;

[0096] The i appearing in the above is an ordinal number used to represent the serial number.

[0097] The above disclosed content is only the preferred feasible embodiment of the present application, and does not limit the protection scope of the present application, so that any equivalent technical change made by applying the content of the present application and the drawings is included in the protection scope of the present application, and in addition, the elements can be updated as the technology develops.

Claims

1. An artificial intelligence-based telephone fraud early warning system, characterized in that, The application relates to a communication channel monitoring system for detecting telephone fraud. The communication channel monitoring module is used for monitoring the call information of the communication channel, the parameter acquisition and analysis module is used for acquiring the call information of the communication channel of the calling number and performing preliminary analysis, the intelligent fraud analysis module is used for performing deep analysis and judgment on whether the telephone fraud based on the acquired call information, and the early warning module is used for sending early warning information when detecting the telephone fraud. The communication channel monitoring module comprises a session request recording unit and a call duration recording unit, the session request recording unit is used for recording the session request information sent by each communication subject, and the call duration recording unit is used for recording the call duration information of each communication subject in the successful connection state. The parameter acquisition and analysis module comprises an activation query unit, an information storage unit and a primary detection unit, the activation query unit is used for querying the call information of the calling number from the communication channel monitoring module when receiving the session request information, the information storage unit is used for saving the queried call information, and the primary detection unit is used for analyzing the call information and judging whether deep analysis is needed. The intelligent fraud analysis module comprises an object screening unit, an intelligent analysis unit and a structure judgment unit, the object screening unit is used for screening the communication subjects closely related to the calling number, the intelligent analysis unit is used for intelligently analyzing the screened communication subjects, and the structure judgment unit is used for analyzing and judging the mesh structure formed by the calling number and the screened communication subjects. The primary detection unit comprises a preposition statistical processor and a primary calculation processor, the preposition statistical processor is used for classifying and counting the acquired call information, and the primary calculation processor is used for calculating and analyzing the statistical results and judging whether deep analysis is needed for the calling number. The items counted by the front-end statistics processor include the number of rejections n1, the number of acceptances n2, the number of objects n3, and the total call duration {T i} of each object. The primary calculation processor calculates the primary judgment value P according to the following formula: ； Wherein, T0 is the time base; When the primary judgment value is greater than the primary threshold value, it is judged that deep analysis is needed, and the calling number information is sent to the intelligent fraud analysis module; The intelligent analysis unit comprises a detection calling processor and an attribute judgment processor, the detection calling processor is used for calling the primary detection unit to calculate the primary judgment value of all the communication subjects, and the attribute judgment processor is used for analyzing and judging the attributes of each communication subject. The attribute judgment processor calculates the command index Cm of the communication subject according to the following formula: ； where m is the number of other communication subjects having relevance to the communication subject, P i Pi represents the primary judgment value of the ith communication subject having relevance, and P0 represents the primary judgment value of the communication subject itself; The attribute judgment processor takes (m, Cm) as the attribute vector of the communication subject, and assigns corresponding attributes according to the attribute vector, and the attributes include command, execution and common.

2. The AI-based telephone fraud early warning system of claim 1, wherein The object screening unit comprises an association calculation processor, a flow control processor and a subject recording processor, the association calculation processor is used for calculating the association degree between two communication subjects, the flow control processor is used for controlling the screening process of the communication subjects, and the subject recording processor is used for recording the information of the screened communication subjects.

3. The AI-based telephone fraud early warning system of claim 2, wherein The early warning prompting module comprises a text display unit and a voice prompting unit, the text display unit is used for displaying fraud prompting information on the terminal before the conversation is connected, and the voice prompting unit is used for issuing fraud prompting voice after the conversation is connected.

Images