Anti-fraud prompting method and device, equipment, storage medium and computer program product
By receiving and copying call audio stream data, voiceprint matching, real-time call risk and generating prompt information, the identification accuracy and prompt lag of existing telecom anti-fraud solutions are solved, and real-time fraud prevention for calls is achieved.
Patent Information
- Application Number
- CN202410952133.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-16
- Publication Date
- 2024-11-22
AI Technical Summary
The existing telecom anti-fraud schemes have poor identification accuracy and delayed prompts, and cannot identify and remind users in real time that there is a risk of fraud.
By receiving and copying the call audio stream data, voiceprint extraction is performed, matching the user's pre-stored voiceprint characteristics, determining whether there is a risk of fraud in the call in real time, and generating anti-fraud prompt information is sent to the user terminal.
It improves the real-time nature of anti-fraud prompts, and can promptly identify and warn users of potential fraud during the call, significantly reducing the risk of users being cheated.
Smart Images

Figure CN119012200A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of communication technology, and in particular to a telecommunications anti-fraud prompt method, device, equipment, storage medium and computer program product. Background Art
[0002] With the development of the Internet 5G+Artificial Intelligence (AI) era, the popularization of smart terminals and the cultivation of user habits, online shopping, online office and online communication have become a new lifestyle and trend.
[0003] In the Internet+ era, all aspects of people's lives are inseparable from wireless communication technology. However, while wireless communication technology brings convenience to users, it also comes with risks.
[0004] In order to reduce the possibility of users being defrauded as much as possible, some guard or housekeeper type application software for use on terminals have been developed.
[0005] However, the problems with traditional telecommunications anti-fraud solutions are: on the one hand, the existing anti-fraud solutions have poor recognition accuracy. For example, blacklist technology or expert rules, etc., their interception accuracy needs to rely on the expert rule library or blacklist established in the early stage, and it is difficult to identify fraudulent phone numbers with short active periods or newly appeared; on the other hand, the existing anti-fraud notification methods have a certain lag, and often prompt users only after the fraudulent call has been hung up.
[0006] It can be seen that there is an urgent need for a telecommunications anti-fraud solution that can monitor and warn calls in real time. Summary of the invention
[0007] The embodiment of the present application provides an anti-fraud reminder method to solve the problem that the existing anti-fraud reminder solution has a lag and cannot make anti-fraud reminders in real time.
[0008] The embodiment of the present application also provides an anti-fraud reminder device to solve the problem that the existing anti-fraud reminder solution has a lag and cannot make anti-fraud reminders in real time.
[0009] The embodiment of the present application also provides an anti-fraud reminder device to solve the problem that the existing anti-fraud reminder solution has a lag and cannot make anti-fraud reminders in real time.
[0010] The embodiment of the present application also provides a computer-readable storage medium to solve the problem that the existing anti-fraud reminder scheme has a lag and cannot make anti-fraud reminders in real time.
[0011] The embodiment of the present application also provides a computer program product to solve the problem that the existing anti-fraud reminder scheme has a lag and cannot make anti-fraud reminders in real time.
[0012] The present application embodiment adopts the following technical solutions:
[0013] An anti-fraud prompt method includes: receiving audio stream data uploaded by a first terminal; copying the audio stream data to obtain audio stream copy data corresponding to the audio stream data, and sending the audio stream data to a second terminal; performing voiceprint extraction on the audio stream copy data to obtain a main voiceprint feature corresponding to the audio stream copy data; determining a pre-stored voiceprint feature of a user corresponding to the first terminal, matching the main voiceprint feature with the pre-stored voiceprint feature, and determining whether there is a fraud risk in a current call; when the judgment result is yes, generating anti-fraud prompt information, and sending the anti-fraud prompt information to the second terminal.
[0014] An anti-fraud prompt device comprises: a data receiving unit, used to receive audio stream data uploaded by a first terminal; a data copying unit, used to copy the audio stream data, obtain audio stream copy data corresponding to the audio stream data, and send the audio stream data to a second terminal; a voiceprint extraction unit, used to extract voiceprints from the audio stream copy data, and obtain main voiceprint features corresponding to the audio stream copy data; an anti-fraud identification unit, used to determine the pre-stored voiceprint features of the user corresponding to the first terminal, match the main voiceprint features with the pre-stored voiceprint features, and determine whether there is a fraud risk in the current call; an anti-fraud prompt unit, used to generate anti-fraud prompt information when the judgment result obtained by the anti-fraud identification unit is yes, and send the anti-fraud prompt information to the second terminal.
[0015] An anti-fraud prompt device comprises: a processor; and a memory arranged to store computer-executable instructions, wherein when the executable instructions are executed, the processor performs the following operations: receiving audio stream data uploaded by a first terminal; copying the audio stream data to obtain audio stream copy data corresponding to the audio stream data, and sending the audio stream data to a second terminal; performing voiceprint extraction on the audio stream copy data to obtain a main voiceprint feature corresponding to the audio stream copy data; determining a pre-stored voiceprint feature of a user corresponding to the first terminal, matching the main voiceprint feature with the pre-stored voiceprint feature, and determining whether there is a fraud risk in the current call; when the judgment result is yes, generating anti-fraud prompt information, and sending the anti-fraud prompt information to the second terminal.
[0016] A computer-readable storage medium stores one or more programs, which, when executed by an electronic device including multiple application programs, enable the electronic device to perform the following operations: receive audio stream data uploaded by a first terminal; copy the audio stream data to obtain audio stream copy data corresponding to the audio stream data, and send the audio stream data to a second terminal; perform voiceprint extraction on the audio stream copy data to obtain a main voiceprint feature corresponding to the audio stream copy data; determine the pre-stored voiceprint feature of the user corresponding to the first terminal, match the main voiceprint feature with the pre-stored voiceprint feature, and determine whether there is a fraud risk in the current call; when the judgment result is yes, generate anti-fraud prompt information, and send the anti-fraud prompt information to the second terminal.
[0017] A computer program product comprises a computer program, which, when executed by a processor, implements the following steps: receiving audio stream data uploaded by a first terminal through a media stream data channel; copying the audio stream data to obtain audio stream copy data corresponding to the audio stream data, and sending the audio stream data to a second terminal; performing voiceprint extraction on the audio stream copy data to obtain a main voiceprint feature corresponding to the audio stream copy data; determining a pre-stored voiceprint feature of a user corresponding to the first terminal, matching the main voiceprint feature with the pre-stored voiceprint feature, and determining whether there is a fraud risk in a current call; and when the judgment result is yes, generating anti-fraud prompt information, and sending the anti-fraud prompt information to the second terminal.
[0018] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:
[0019] An anti-fraud prompt method provided in an embodiment of the present application is adopted. When making a call, the call terminal uploads the collected voice to the back-end call platform. After receiving the audio stream data uploaded by the first terminal through the media stream data channel, the call platform can copy the audio stream data to obtain audio stream copy data corresponding to the audio stream data, and send the audio stream data to the second terminal through the media stream data channel, thereby ensuring the normal progress of the call. Voiceprint extraction is performed on the audio stream copy data to obtain the main voiceprint feature corresponding to the audio stream copy data. According to the identification information of the user terminal, the pre-stored voiceprint feature of the user corresponding to the first terminal is determined in the voiceprint database, the main voiceprint feature is matched with the pre-stored voiceprint feature, and it is determined whether there is a fraud risk in the current call. When the judgment result is yes, anti-fraud prompt information is generated, and the anti-fraud prompt information is sent to the second terminal. By adopting the anti-fraud prompt method provided in the embodiment of the present application, the call voice uploaded by both parties of the call is copied to obtain two channels of voice data, one of which is transmitted normally to ensure the normal progress of the call; anti-fraud identification is performed on the other user, and anti-fraud prompt information is generated based on the identification result, and the anti-fraud prompt information can be sent to the other user terminal in real time during the current call. Compared with the existing anti-fraud prompt scheme that requires anti-fraud prompts to be performed after the call ends, the anti-fraud prompt method provided by the present application greatly improves the real-time nature of the anti-fraud prompt. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0021] Figure 1 A schematic diagram of the specific structure of a 5G new call platform provided in an embodiment of the present application;
[0022] Figure 2 A schematic diagram of a specific process of a telecommunications anti-fraud prompt method provided in an embodiment of the present application;
[0023] Figure 3 A schematic diagram of the specific structure of a telecommunications anti-fraud reminder device provided in an embodiment of the present application;
[0024] Figure 4 A schematic diagram of the specific structure of a telecommunications anti-fraud reminder device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0025] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.
[0026] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.
[0027] The embodiment of the present application provides a telecommunications anti-fraud reminder method to solve the problem that the existing anti-fraud reminder scheme has a lag and cannot make anti-fraud reminders in real time.
[0028] The executor of the telecommunications anti-fraud prompt method provided in the embodiment of the present application may be, but is not limited to, at least one of a communication server, an anti-fraud server, a call platform, and a call management server; in addition, the executor of the method may also be an application (Application, APP) running on these servers or the system itself.
[0029] For the convenience of description, the following text takes the executor of the method as an example of a 5G new call platform to introduce the telecommunications anti-fraud prompt method provided in the embodiment of the present application.
[0030] Simply put, 5G New Call is an enhanced voice call service based on 5G network. It provides more functions around the traditional voice call service, such as intelligent translation, fun calls, intelligent customer service, content sharing, remote assistance, etc. These functions can bring users a more interesting, vivid and diverse call experience, and also help commercial enterprises better reach users and provide services to users.
[0031] The working principle of the 5G new call platform is similar to that of the 4G-based voice call platform (Voice over LTE, VoLTE) and the voice call platform independently carried by the 5G network (Voice Over NR, VoNR). Both are multimedia services implemented by the IP Multimedia Subsystem (IP Multimedia Subsystem, IMS) built on the IP network. On the basis of traditional data services (Internet access services), a large channel is established between the terminal and IMS via the 4G / 5G network.
[0032] The large channel can be divided into small channels such as audio channel, video channel and signaling channel. Traditional VoLTE / VoNR audio and video call services are realized with the help of these small channels. The 5G new call service, based on these existing channels, introduces a new channel called Data Channel (DC). Through this new channel, it can be used to transmit text, pictures, videos, files, locations, actions, graffiti, menus, VR / AR and other data, and derives many interesting gameplays.
[0033] In the embodiment of the present application, the specific system architecture of the 5G new call platform is as follows: Figure 1 As shown, it mainly includes: access platform, IMS platform, VoNR+ media plane, VoNR+ capability platform and anti-fraud identification system, among which, the access platform, IMS platform, VoNR+ media plane and VoNR+ capability platform are used to provide users with normal communication functions. The working principles and working methods of these platforms belong to the common technical means in the relevant fields, and the embodiments of this application will not be repeated. It can be understood that the execution subject of the method is the 5G new call platform, which is only an exemplary description and should not be understood as a limitation of the method.
[0034] The specific implementation flow chart of the telecommunications anti-fraud prompt method provided in this application is as follows Figure 2 As shown, it mainly includes the following steps:
[0035] Step 11, receiving audio stream data uploaded by the first terminal;
[0036] During a voice call through the 5G new call platform, the terminal devices of both parties can upload the collected call voice to the 5G new call platform through the DC channel established between the terminal devices and the 5G new call platform (specifically, through the media stream DC channel therein). The 5G new call platform receives the audio stream data generated during the call through the access platform.
[0037] Step 12, copying the audio stream data obtained by executing step 11 to obtain audio stream copy data corresponding to the audio stream data, and sending the audio stream data to the second terminal;
[0038] The 5G new call platform copies the acquired audio stream data through the VoNR+ media interface to obtain the audio stream copy data corresponding to the audio stream data, and sends one of the audio stream data to the receiving terminal corresponding to the voice call through the media stream DC channel (for the convenience of description, in the embodiment of the present application, the terminal that uploads the voice during the voice call is called the first terminal, and the terminal that receives the voice is called the second terminal) to ensure the normal progress of the current voice call. For the other audio stream data obtained by copying, the 5G new call platform sends the audio stream copy data to the anti-fraud identification system through the VoNR+ media interface, and executes the following step 13.
[0039] Step 13, extracting the voiceprint of the audio stream copy data to obtain the main voiceprint feature corresponding to the audio stream copy data;
[0040] It should be noted that in an actual call, the following situations may occur: 1. Due to the noisy surrounding environment, during the call, the terminal device not only collects the voice of the calling user, but also the voices of other users around; 2. During the call, the calling user changes, for example, the phone is handed over to another user for the call, etc. In the embodiment of the present application, the user corresponding to the call terminal (for example, the user corresponding to the call terminal can be determined according to the unique identifier of the call terminal or the phone number corresponding to the call terminal) can be regarded as the main user of the current call, and then the voiceprint feature corresponding to the main user in the call voice is used as the main voiceprint feature.
[0041] In one implementation, the 5G new call platform can extract voiceprints from the audio stream copy data based on the anti-fraud identification system through the following sub-steps to obtain the main voiceprint features corresponding to the audio stream copy data, including:
[0042] Sub-step 1301, pre-processing the audio stream copy data to obtain human voice audio stream data;
[0043] It should be noted here that since the terminal device may collect environmental noise during a call, in order to avoid the impact of environmental noise on subsequent processing results, in an embodiment of the present application, the anti-fraud identification system can first pre-process the audio stream copy data, remove the environmental noise in the audio stream copy data, and then obtain the human voice audio stream data.
[0044] Sub-step 1302, extracting voiceprint from human voice audio stream data to obtain voiceprint information;
[0045] Specifically, collecting voiceprints from audio data is a common technical means in the relevant field, and the embodiments of the present application do not limit the specific method used for voiceprint extraction.
[0046] Sub-step 1303, determining the Euclidean distance between each voiceprint information, and determining the main voiceprint feature corresponding to the audio stream copy data based on the Euclidean distance.
[0047] Since the amount of voiceprint information contained in the entire audio stream data is large, if the entire audio stream data is directly analyzed and processed, it may lead to low processing efficiency and occupy more processing resources. In order to improve processing efficiency, in an embodiment of the present application, the anti-fraud identification system uses a fixed time interval as a preset sampling period, divides the audio stream copy data, and processes the audio data in each sampling period separately according to the preset sampling period.
[0048] Specifically, the anti-fraud identification system can split the audio stream copy data according to the preset sampling period, obtain the audio stream copy sub-data corresponding to each sampling period, and respectively determine the voiceprint features corresponding to each voiceprint information in each sampling period. Then, the anti-fraud identification system can calculate the Euclidean distance between each voiceprint feature in each sampling period according to the Euclidean distance calculation formula, and determine the number of Euclidean distances between each voiceprint feature in each sampling period that is less than a preset distance threshold; select a specific sampling period according to the order of the number of voiceprint features that are less than the preset distance threshold from high to low; determine the voiceprint feature whose Euclidean distance between voiceprint features in the specific sampling period is less than the preset distance threshold as the main voiceprint feature corresponding to the audio stream copy data.
[0049] For example, suppose the anti-fraud identification system determines that the voiceprint features within sampling period T1 are: v1, v2, v3, v4, v5, and the voiceprint features within sampling period T2 are: v1, v2, v3, v5, and the Euclidean distances between the five voiceprint features within sampling period T1 are calculated respectively to obtain 10 results, and the size relationship between these 10 results and the preset distance threshold X is:
[0050] v1-v2<X;
[0051] v1-v3<X;
[0052] v1-v4<X;
[0053] v1-v5>X;
[0054] v2-v3<X;
[0055] v2-v4<X;
[0056] v2-v5>X
[0057] v3-v4<X
[0058] v3-v5>X
[0059] v4-v5>X;
[0060] Among them, the number of voiceprint features whose Euclidean distances are less than the preset distance threshold X is 6, and the number of voiceprint features whose Euclidean distances are greater than the preset distance threshold X is 4.
[0061] The Euclidean distances between the four voiceprint features within the sampling period T2 are calculated respectively, and 6 results are obtained. The relationship between these 6 results and the preset distance threshold X is:
[0062] v1-v2<X;
[0063] v1-v3<X;
[0064] v1-v5>X;
[0065] v2-v3<X;
[0066] v2-v5>X
[0067] v3-v5>X
[0068] Among them, the number of voiceprint features whose Euclidean distances are less than the preset distance threshold X is 3, and the number of voiceprint features whose Euclidean distances are greater than the preset distance threshold X is 3.
[0069] After comparison, the number of voiceprint features whose Euclidean distances within the sampling period T1 are less than the preset distance threshold X is the largest. Therefore, the voiceprint features whose Euclidean distances within the sampling period T1 are less than the preset distance threshold, that is, the voiceprint features v1~v4, can be determined as the main voiceprint features corresponding to the audio stream copy data.
[0070] Step 14, determining the pre-stored voiceprint feature of the user corresponding to the first terminal, matching the main voiceprint feature with the pre-stored voiceprint feature, and determining whether there is a fraud risk in the current call;
[0071] In an embodiment of the present application, the anti-fraud identification system can determine the user corresponding to the first terminal based on the unique identifier of the first terminal or the telephone number corresponding to the call terminal, and query the pre-stored voiceprint features corresponding to the user in the voiceprint library, and then determine whether the current calling user is the user corresponding to the first terminal by matching the main voiceprint features determined by executing step 13 with the pre-stored voiceprint features. When the judgment result is yes, it means that the user has not changed during the current call, and then it is determined that there is no fraud risk in the current call, and the call data is monitored through the above steps.
[0072] When it is determined that the main voiceprint feature does not match the pre-stored voiceprint feature, it means that the user has changed during the current call, and then it is determined that there may be a fraud risk in the current call, and step 15 is executed.
[0073] Step 15: When the judgment result is yes, generate anti-fraud prompt information and send the anti-fraud prompt information to the second terminal.
[0074] When the 5G new call platform determines that there is a fraud risk in the current call through the anti-fraud identification system, the 5G new call platform can generate a variety of different forms of anti-fraud prompt information through the VoNR+ capability platform, and send it to the second terminal through the corresponding DC channel to prompt the user that there is a fraud risk in the current call. In one embodiment, the anti-fraud prompt information generated by the 5G new call platform may include but is not limited to the following types:
[0075] 1. Anti-fraud prompt audio. The 5G new call platform can send the generated anti-fraud prompt audio to the second terminal through the media stream DC channel, so that the second terminal plays the anti-fraud prompt audio during the call.
[0076] 2. Generate an anti-fraud prompt application instruction, and the 5G new call platform can send the anti-fraud prompt application instruction to the second terminal through the application flow DC channel;
[0077] The anti-fraud prompt application instruction is used to instruct the second terminal to execute a processing operation corresponding to the anti-fraud prompt application instruction, such as hanging up the phone.
[0078] 3. Generate an anti-fraud prompt video. The 5G new call platform can send the anti-fraud prompt video to the second terminal through the media stream DC channel, so that the second terminal plays the anti-fraud prompt audio in a specific video playback interface during the call.
[0079] An anti-fraud prompt method provided in an embodiment of the present application is adopted. When making a call, the call terminal uploads the collected voice to the back-end call platform. After receiving the audio stream data uploaded by the first terminal through the media stream data channel, the call platform can copy the audio stream data to obtain audio stream copy data corresponding to the audio stream data, and send the audio stream data to the second terminal, thereby ensuring the normal progress of the call. Voiceprint extraction is performed on the audio stream copy data to obtain the main voiceprint feature corresponding to the audio stream copy data. According to the identification information of the user terminal, the pre-stored voiceprint feature of the user corresponding to the first terminal is determined in the voiceprint database, the main voiceprint feature is matched with the pre-stored voiceprint feature, and it is determined whether there is a fraud risk in the current call. When the judgment result is yes, anti-fraud prompt information is generated, and the anti-fraud prompt information is sent to the second terminal. By adopting the anti-fraud prompt method provided in the embodiment of the present application, the call voice uploaded by both parties of the call is copied to obtain two channels of voice data, one of which is transmitted normally to ensure the normal progress of the call; anti-fraud identification is performed on the other user, and anti-fraud prompt information is generated based on the identification result, and the anti-fraud prompt information can be sent to the other user terminal in real time during the current call. Compared with the existing anti-fraud prompt scheme that requires anti-fraud prompts to be performed after the call ends, the anti-fraud prompt method provided by the present application greatly improves the real-time nature of the anti-fraud prompt.
[0080] In one implementation, the present application also provides a telecommunications anti-fraud reminder device to solve the problem that the existing anti-fraud reminder solution has a lag and cannot make anti-fraud reminders in real time. Figure 3 As shown, it includes: a data receiving unit 31, a data copying unit 32, a voiceprint extraction unit 33, an anti-fraud identification unit 34 and an anti-fraud prompt unit 35.
[0081] The data receiving unit 31 is used to receive the audio stream data uploaded by the first terminal;
[0082] A data copying unit 32, configured to copy the audio stream data, obtain audio stream copy data corresponding to the audio stream data, and send the audio stream data to the second terminal;
[0083] A voiceprint extraction unit 33 is used to extract voiceprints from the audio stream copy data to obtain a main voiceprint feature corresponding to the audio stream copy data;
[0084] The anti-fraud identification unit 34 is used to determine the pre-stored voiceprint feature of the user corresponding to the first terminal, match the main voiceprint feature with the pre-stored voiceprint feature, and determine whether there is a fraud risk in the current call;
[0085] The anti-fraud prompt unit 35 is used to generate anti-fraud prompt information when the judgment result obtained by the anti-fraud identification unit is yes, and send the anti-fraud prompt information to the second terminal.
[0086] In one embodiment, the voiceprint extraction unit 33 is specifically used to: pre-process the audio stream copy data to obtain human voice audio stream data; extract voiceprints from the human voice audio stream data to obtain voiceprint information; determine the Euclidean distance between each voiceprint information, and determine the main voiceprint feature corresponding to the audio stream copy data based on the Euclidean distance.
[0087] In one embodiment, the voiceprint extraction unit 33 is specifically used to: split the audio stream copy data according to a preset sampling period to obtain audio stream sub-copy data corresponding to each sampling period; determine the voiceprint features corresponding to each voiceprint information in each sampling period; respectively calculate the Euclidean distance between each voiceprint feature in each sampling period; determine the number of Euclidean distances between each voiceprint feature in each sampling period that is less than a preset distance threshold; and determine the main voiceprint feature corresponding to the audio stream copy data based on the number that is less than the preset distance threshold.
[0088] In one embodiment, the voiceprint extraction unit 33 is specifically used to: select a specific sampling period according to the order from high to low of the number that is less than the preset distance threshold; determine the voiceprint feature whose Euclidean distance between the voiceprint features in the specific sampling period is less than the preset distance threshold as the main voiceprint feature corresponding to the audio stream copy data.
[0089] In one embodiment, the anti-fraud prompt unit 35 is specifically used to: generate anti-fraud prompt audio, and send the anti-fraud prompt audio to the second terminal through the media stream data channel; and / or generate anti-fraud prompt application instructions, and send the anti-fraud prompt application instructions to the second terminal through the application stream data channel, wherein the anti-fraud prompt application instructions are used to instruct the second terminal to perform a processing operation corresponding to the anti-fraud prompt application instructions; and / or generate an anti-fraud prompt video, and send the anti-fraud prompt video to the second terminal through the media stream data channel.
[0090] An anti-fraud prompt device provided by an embodiment of the present application is used. When a call is made, the call terminal uploads the collected voice to the back-end call platform. After receiving the audio stream data uploaded by the first terminal through the media stream data channel, the call platform can copy the audio stream data to obtain audio stream copy data corresponding to the audio stream data, and send the audio stream data to the second terminal, thereby ensuring the normal conduct of the call. Voiceprint extraction is performed on the audio stream copy data to obtain the main voiceprint feature corresponding to the audio stream copy data. According to the identification information of the user terminal, the pre-stored voiceprint feature of the user corresponding to the first terminal is determined in the voiceprint database, the main voiceprint feature is matched with the pre-stored voiceprint feature, and it is determined whether there is a fraud risk in the current call. When the judgment result is yes, anti-fraud prompt information is generated, and the anti-fraud prompt information is sent to the second terminal. By adopting the anti-fraud prompt method provided in the embodiment of the present application, the call voice uploaded by both parties of the call is copied to obtain two channels of voice data, one of which is transmitted normally to ensure the normal progress of the call; anti-fraud identification is performed on the other user, and anti-fraud prompt information is generated based on the identification result, and the anti-fraud prompt information can be sent to the other user terminal in real time during the current call. Compared with the existing anti-fraud prompt scheme that requires anti-fraud prompts to be performed after the call ends, the anti-fraud prompt method provided by the present application greatly improves the real-time nature of the anti-fraud prompt.
[0091] Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 4 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.
[0092] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0093] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.
[0094] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a telecommunications anti-fraud prompt device at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations: receiving audio stream data uploaded by the first terminal; copying the audio stream data to obtain audio stream copy data corresponding to the audio stream data, and sending the audio stream data to the second terminal through the media stream data channel; performing voiceprint extraction on the audio stream copy data to obtain the main voiceprint feature corresponding to the audio stream copy data; determining the pre-stored voiceprint feature of the user corresponding to the first terminal, matching the main voiceprint feature with the pre-stored voiceprint feature, and determining whether there is a fraud risk in the current call; when the judgment result is yes, generating anti-fraud prompt information, and sending the anti-fraud prompt information to the second terminal.
[0095] The above application Figure 4The method performed by the telecommunications anti-fraud prompt electronic device disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in software form. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.
[0096] Of course, in addition to software implementation methods, the electronic device of the present application does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc. That is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.
[0097] The embodiment of the present application also provides a computer-readable storage medium, which stores one or more programs, wherein the one or more programs include instructions, which, when executed by a portable electronic device including a plurality of application programs, enable the portable electronic device to execute Figure 1 The method of the embodiment shown is specifically used to perform the following operations:
[0098] Receive audio stream data uploaded by a first terminal; copy the audio stream data to obtain audio stream copy data corresponding to the audio stream data, and send the audio stream data to a second terminal; perform voiceprint extraction on the audio stream copy data to obtain a main voiceprint feature corresponding to the audio stream copy data; determine the pre-stored voiceprint feature of the user corresponding to the first terminal, match the main voiceprint feature with the pre-stored voiceprint feature, and determine whether there is a fraud risk in the current call; when the judgment result is yes, generate anti-fraud prompt information, and send the anti-fraud prompt information to the second terminal.
[0099] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0100] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0101] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0102] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1The steps for the functions specified in one or more boxes.
[0103] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0104] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0105] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0106] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0107] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.
[0108] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims
1. A telecommunications anti-fraud prompt method, characterized in that: include: Receiving audio stream data uploaded by the first terminal; Copying the audio stream data to obtain audio stream copy data corresponding to the audio stream data, and sending the audio stream data to the second terminal; Performing voiceprint extraction on the audio stream copy data to obtain a main voiceprint feature corresponding to the audio stream copy data; Determine a pre-stored voiceprint feature of a user corresponding to the first terminal, match the main voiceprint feature with the pre-stored voiceprint feature, and determine whether there is a fraud risk in the current call; When the judgment result is yes, anti-fraud prompt information is generated and sent to the second terminal.
2. The method according to claim 1, characterized in that The extracting voiceprint from the audio stream copy data to obtain the main voiceprint feature corresponding to the audio stream copy data specifically includes: Preprocessing the audio stream copy data to obtain human voice audio stream data; Extracting voiceprint from the human voice audio stream data to obtain voiceprint information; The Euclidean distance between each voiceprint information is determined, and the main voiceprint feature corresponding to the audio stream copy data is determined according to the Euclidean distance.
3. The method according to claim 2, characterized in that The determining of the Euclidean distance between each voiceprint information, and determining the main voiceprint feature corresponding to the audio stream copy data according to the Euclidean distance, specifically includes: According to a preset sampling period, the audio stream replication data is split into data to obtain audio stream replication sub-data corresponding to each sampling period; Determine the voiceprint features corresponding to each voiceprint information in each sampling period; Calculating the Euclidean distance between each of the voiceprint features within each of the sampling periods respectively; Determine the number of times in each sampling period that the Euclidean distance between the voiceprint features is less than a preset distance threshold; According to the number less than the preset distance threshold, a main voiceprint feature corresponding to the audio stream copy data is determined.
4. The method according to claim 3, characterized in that The determining, according to the number less than the preset distance threshold, the main voiceprint feature corresponding to the audio stream copy data specifically includes: Selecting a specific sampling period according to the order of the number of values less than the preset distance threshold from high to low; According to the voiceprint feature whose Euclidean distance between the voiceprint features in the specific sampling period is less than a preset distance threshold, it is determined as the main voiceprint feature corresponding to the audio stream copy data.
5. The method according to claim 1, characterized in that The generating the anti-fraud prompt information and sending the anti-fraud prompt information to the second terminal specifically includes: generating an anti-fraud prompt audio, and sending the anti-fraud prompt audio to the second terminal through the media stream data channel; and / or Generate an anti-fraud prompt application instruction, and send the anti-fraud prompt application instruction to the second terminal through the application stream data channel, wherein the anti-fraud prompt application instruction is used to instruct the second terminal to perform a processing operation corresponding to the anti-fraud prompt application instruction; and / or Generate an anti-fraud prompt video, and send the anti-fraud prompt video to the second terminal through the media stream data channel.
6. A telecommunications anti-fraud reminder device, characterized in that: include: A data receiving unit, configured to receive audio stream data uploaded by the first terminal through a media stream data channel; a data copying unit, configured to copy the audio stream data, obtain audio stream copy data corresponding to the audio stream data, and send the audio stream data to a second terminal; A voiceprint extraction unit, configured to extract voiceprints from the audio stream copy data to obtain a main voiceprint feature corresponding to the audio stream copy data; an anti-fraud identification unit, configured to determine a pre-stored voiceprint feature of a user corresponding to the first terminal, match the main voiceprint feature with the pre-stored voiceprint feature, and determine whether there is a fraud risk in the current call; The anti-fraud prompt unit is used to generate anti-fraud prompt information when the judgment result obtained by the anti-fraud identification unit is yes, and send the anti-fraud prompt information to the second terminal.
7. The device according to claim 6, characterized in that The voiceprint extraction unit is specifically used for: Preprocessing the audio stream copy data to obtain human voice audio stream data; Extracting voiceprint from the human voice audio stream data to obtain voiceprint information; The Euclidean distance between each voiceprint information is determined, and the main voiceprint feature corresponding to the audio stream copy data is determined according to the Euclidean distance.
8. A telecommunications anti-fraud reminder device, comprising: processor; as well as a memory arranged to store computer executable instructions which, when executed, cause the processor to: Receiving audio stream data uploaded by the first terminal through the media stream data channel; Copying the audio stream data to obtain audio stream copy data corresponding to the audio stream data, and sending the audio stream data to the second terminal; Performing voiceprint extraction on the audio stream copy data to obtain a main voiceprint feature corresponding to the audio stream copy data; Determine a pre-stored voiceprint feature of a user corresponding to the first terminal, match the main voiceprint feature with the pre-stored voiceprint feature, and determine whether there is a fraud risk in the current call; When the judgment result is yes, anti-fraud prompt information is generated and sent to the second terminal.
9. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, enables the electronic device to execute the telecommunications anti-fraud alert method as described in any one of claims 1 to 5.
10. A computer program product, characterized in that It includes a computer program, which, when executed by a processor, implements the telecommunications anti-fraud prompt method as described in any one of claims 1 to 5.
Citation Information
Cited By
Communication method, electronic device, chip system, and storage medium
WO2026148881A1
Communication method, electronic device, chip system, and storage medium
WO2026148882A1
