Call anomaly detection method and device and related equipment
By triggering the terminal to play target audio during the call and perform abnormal detection, combined with risk assessment, the problem of low success rate of call abnormal detection in the prior art is solved, the call security is improved, and the occurrence of AIGC fraud is prevented.
Patent Information
- Application Number
- CN202411088388.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-08
- Publication Date
- 2024-11-12
AI Technical Summary
The existing call abnormality detection model is difficult to balance universality in practical applications, resulting in a low detection success rate and the inability to effectively prevent AIGC fraud in audio and video calls.
By triggering the terminal to play the target audio during the call, and determining whether there are abnormalities in the call based on the audio information and detection results, combining risk assessment and preset conditions to interrupt or remind abnormal situations, the detection accuracy is improved.
It effectively improves the success rate of call abnormality detection, enhances call security, and prevents AIGC fraud.
Smart Images

Figure CN118945264A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to the field of communication technology, and in particular, to a call anomaly detection method, apparatus, and related equipment. Background Art
[0002] At present, there are cases of fraud in which people use artificial intelligence (AIGC) to change faces and voices to fake the images and voices of friends, colleagues, and leaders during audio and video calls, which requires targeted prevention. One technical solution is to use AI technology to train a detection model to perform anomaly detection.
[0003] However, the trained model focuses on universality and is difficult to balance in terms of actual effect, resulting in a low detection success rate. Summary of the invention
[0004] The embodiments of the present application provide a call anomaly detection method, apparatus, and related equipment to more effectively detect whether a call is abnormal and improve the detection success rate.
[0005] In order to solve the above problems, this application is implemented as follows:
[0006] In a first aspect, an embodiment of the present application provides a call anomaly detection method, which is executed by a network device and includes:
[0007] During a call, trigger the terminal to play the target audio;
[0008] Receiving audio information and / or call anomaly detection results sent by the terminal according to the target audio;
[0009] Whether there is any abnormality in the call is determined according to the audio information and / or the call anomaly detection result.
[0010] Optionally, judging whether the call is abnormal according to the audio information and / or the call abnormality detection result includes:
[0011] Based on the audio information and / or the call anomaly detection result, determining whether the audio collected by the terminal includes the target audio and the voice of the corresponding user; wherein the terminal includes a calling terminal and / or a called terminal;
[0012] When a preset condition is met, determining that the call is abnormal; wherein the preset condition includes at least one of the following:
[0013] The audio collected by the calling terminal does not include the target audio;
[0014] The audio collected by the calling terminal does not include the voice of the first user, and the first user is the user of the calling terminal;
[0015] The audio collected by the called terminal does not include the target audio;
[0016] The audio collected by the called terminal does not include the voice of the second user, where the second user is the user of the calling terminal.
[0017] Optionally, the method further comprises:
[0018] In the case where there is an abnormality in the call, a risk assessment is performed based on the audio information and / or the call abnormality detection result to obtain an assessment result value;
[0019] If the evaluation result value is greater than a first threshold, interrupting the call;
[0020] If the evaluation result value is less than or equal to the first threshold, an abnormal reminder message is sent to the terminal.
[0021] Optionally, the method comprises:
[0022] Creating a second channel for the call;
[0023] The triggering terminal to play the target audio includes:
[0024] An audio trigger instruction is sent to the terminal through the second channel.
[0025] Optionally, the method further comprises:
[0026] Triggering the camera of the terminal to start;
[0027] Receive the image captured by the camera and sent by the terminal.
[0028] Optionally, the preset condition also includes at least one of the following:
[0029] The image captured by the calling terminal does not match the image during the current call:
[0030] The image captured by the called terminal does not match the image during the current call.
[0031] In a second aspect, an embodiment of the present application provides a call anomaly detection method, which is executed by a terminal and includes:
[0032] During a call, respond to the trigger of the network device to play the target audio;
[0033] Acquiring audio information when playing the target audio;
[0034] The audio information is sent to the network device, and / or a call anomaly detection result is determined based on the audio information and the call anomaly detection result is sent to the network device.
[0035] Optionally, determining a call anomaly detection result according to the audio information and sending the call anomaly detection result to the network device includes:
[0036] Based on the audio information, determine whether the audio collected by the terminal includes the target audio and the voice of the corresponding user, and generate the call anomaly detection result; wherein the call anomaly detection result is used to indicate whether the audio collected by the terminal includes the target audio and the voice of the user of the terminal.
[0037] Optionally, the method further comprises:
[0038] Receive abnormal reminder information sent by the network device, where the abnormal reminder information is used to remind the terminal that an abnormality exists in the current call.
[0039] Optionally, the method further comprises:
[0040] In response to the trigger of the network device, the camera is started;
[0041] The image captured by the camera is sent to the network device.
[0042] In a third aspect, an embodiment of the present application provides a call anomaly detection device, comprising:
[0043] The first processing module is used to trigger the terminal to play the target audio during a call;
[0044] A receiving module, used to receive the audio information and / or call anomaly detection result sent by the terminal according to the target audio;
[0045] The second processing module is used to determine whether there is any abnormality in the call according to the audio information and / or the call abnormality detection result.
[0046] Optionally, the second processing module includes:
[0047] A first processing unit, configured to determine whether the audio collected by the terminal includes the target audio and the voice of the corresponding user based on the audio information and / or the call anomaly detection result; wherein the terminal includes a calling terminal and / or a called terminal;
[0048] The second processing unit is configured to determine that the call is abnormal if a preset condition is met; wherein the preset condition includes at least one of the following:
[0049] The audio collected by the calling terminal does not include the target audio;
[0050] The audio collected by the calling terminal does not include the voice of the first user, and the first user is the user of the calling terminal;
[0051] The audio collected by the called terminal does not include the target audio;
[0052] The audio collected by the called terminal does not include the voice of the second user, where the second user is the user of the calling terminal.
[0053] Optionally, the device further comprises:
[0054] A fifth processing module, configured to, when the call is abnormal, perform risk assessment based on the audio information and / or the call abnormality detection result to obtain an assessment result value;
[0055] A sixth processing module, configured to interrupt the call if the evaluation result value is greater than a first threshold;
[0056] The seventh processing module is used to send abnormal reminder information to the terminal if the evaluation result value is less than or equal to the first threshold.
[0057] Optionally, the device further comprises:
[0058] An eighth processing module, configured to create a second channel for the call;
[0059] The first processing module is also used for:
[0060] An audio trigger instruction is sent to the terminal through the second channel.
[0061] Optionally, the device further comprises:
[0062] A ninth processing module, used for triggering the camera of the terminal to start;
[0063] The tenth processing module is used to receive the image captured by the camera and sent by the terminal.
[0064] Optionally, the preset condition also includes at least one of the following:
[0065] The image captured by the calling terminal does not match the image during the current call:
[0066] The image captured by the called terminal does not match the image during the current call.
[0067] In a fourth aspect, an embodiment of the present application provides a call anomaly detection device, including:
[0068] The third processing module is used to respond to the trigger of the network device to play the target audio during the call;
[0069] A fourth processing module, used for acquiring audio information when playing the target audio;
[0070] A sending module is used to send the audio information to the network device, and / or determine a call anomaly detection result based on the audio information and send the call anomaly detection result to the network device.
[0071] Optionally, the sending module is further used for:
[0072] Based on the audio information, determine whether the audio collected by the terminal includes the target audio and the voice of the corresponding user, and generate the call anomaly detection result; wherein the call anomaly detection result is used to indicate whether the audio collected by the terminal includes the target audio and the voice of the user of the terminal.
[0073] Optionally, the device further comprises:
[0074] The abnormal reminder information receiving module is used to receive the abnormal reminder information sent by the network device, and the abnormal reminder information is used to remind the terminal that there is an abnormality in the current call.
[0075] Optionally, the device further comprises:
[0076] A camera activation module, used to activate the camera in response to a trigger of the network device;
[0077] An image sending module is used to send the image captured by the camera to the network device.
[0078] In the fifth aspect, an embodiment of the present application provides a call anomaly detection device, comprising: a memory, a processor, and a program stored in the memory and executable on the processor; the processor is used to read the program in the memory to implement the steps in the call anomaly detection method as described above.
[0079] In a sixth aspect, an embodiment of the present application provides a readable storage medium for storing a program, which, when executed by a processor, implements the steps in the call anomaly detection method as described above.
[0080] In a seventh aspect, a computer program product is provided, comprising computer instructions, which, when executed by a processor, implement the steps of the method described in the first aspect or the second aspect.
[0081] In the embodiment method of the present application, the network device can trigger the terminal to play the target audio during a call, so that the terminal collects audio information and / or determines the call anomaly detection result based on the target audio. If the network device receives audio information, it determines whether the call is abnormal based on the audio information; if the network device receives the call anomaly detection result, it determines whether the call is abnormal based on the call anomaly detection result. In this way, by adding target audio interference during a call and collecting audio information to detect call anomalies, the accuracy of identifying call anomalies is improved and the security of the call is guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS
[0082] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0083] Figure 1 A flowchart of a method for detecting abnormal calls according to an embodiment of the present application is shown;
[0084] Figure 2 A communication diagram showing a communication server and a terminal;
[0085] Figure 3 A schematic diagram showing a specific application process of the call anomaly detection method according to an embodiment of the present application;
[0086] Figure 4 A second flowchart of the call anomaly detection method according to an embodiment of the present application is shown;
[0087] Figure 5 express Figure 1 A schematic diagram of the module structure of the device corresponding to the method;
[0088] Figure 6 express Figure 4 A schematic diagram of the module structure of the device corresponding to the method;
[0089] Figure 7 A schematic diagram showing the structure of a call anomaly detection device according to an embodiment of the present application. DETAILED DESCRIPTION
[0090] In order to make the technical problems, technical solutions and advantages to be solved by the application clearer, the following will be described in detail in conjunction with the accompanying drawings and specific embodiments. In the following description, specific details such as specific configurations and components are provided only to help fully understand the embodiments of the application. Therefore, it should be clear to those skilled in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the application. In addition, for clarity and brevity, the description of known functions and structures has been omitted.
[0091] It should be understood that the references to "one embodiment" or "an embodiment" throughout the specification mean that the specific features, structures, or characteristics associated with the embodiment are included in at least one embodiment of the present application. Therefore, the references to "in one embodiment" or "in an embodiment" appearing throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
[0092] In various embodiments of the present application, it should be understood that the order of execution of the following processes does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. In addition, the terms "system" and "network" are often used interchangeably in this article.
[0093] For ease of understanding, some contents involved in the embodiments of the present application are described below:
[0094] There are two main technical aspects of AIGC fraud during audio and video communication: offline video files processed by AIGC + virtual camera (newly added); virtual camera (fake replacement) + real-time AIGC.
[0095] In the first technique, the video is prepared in advance according to the fraud script, and the face and voice are changed multiple times through the AIGC model (mostly universal), and the best one is selected after comparing the effects. Then, the video stream is sent to the communication software port through a virtual camera during the fraud. Due to its relatively low threshold, it has become the most commonly used method for fraud.
[0096] Another technology is that the virtual camera replaces the physical camera of the current system, so that the system can only see this camera. The audio and video of the physical camera will be transmitted to the virtual camera first and then transmitted to the communication software (communication port) after AIGC processing. Another difficulty is real-time AIGC, which places very high requirements on the computing power and model robustness of the scammer.
[0097] like Figure 1 As shown, an embodiment of the present application provides a call anomaly detection method, which is executed by a network device and includes:
[0098] Step 101, during a call, triggering the terminal to play target audio;
[0099] Step 102, receiving audio information and / or call anomaly detection result sent by the terminal according to the target audio;
[0100] Step 103: Determine whether there is any abnormality in the call based on the audio information and / or the call abnormality detection result.
[0101] In the method of the embodiment of the present application, according to the above steps 101-103, the network device can trigger the terminal to play the target audio during the call. The terminal collects audio information and / or determines the call anomaly detection result based on the target audio. If the network device receives audio information, it determines whether the call is abnormal based on the audio information; if the network device receives the call anomaly detection result, it determines whether the call is abnormal based on the call anomaly detection result. In this way, by adding target audio interference during the call and collecting audio information to detect call anomalies, the accuracy of identifying call anomalies is improved and the security of the call is guaranteed.
[0102] Among them, after the terminal collects audio information based on the target audio, it can directly send the audio information to the network device; or, after collecting the audio information, the terminal can also perform self-detection based on the audio information, obtain the call anomaly detection result, and send the call anomaly detection result to the network device.
[0103] As an optional implementation, in order to facilitate the terminal to collect audio information for call anomaly detection, the network triggers the terminal to play the target audio.
[0104] It should be noted that the network device executes the method of the embodiment of the present application by default, or the network device is set to execute the method of the embodiment of the present application when an abnormality may occur (such as transfer or payment information appears during a call).
[0105] Optionally, in this embodiment, the call is an audio or video call, and the terminal is at least one of a calling terminal and a called terminal.
[0106] Optionally, in this embodiment, the method includes:
[0107] Creating a second channel for the call;
[0108] The triggering terminal to play the target audio includes:
[0109] An audio trigger instruction is sent to the terminal through the second channel.
[0110] That is, when a first channel is created for a current call, in order to avoid affecting the call, the network device will create a second channel for the current call. The network device can send an audio trigger instruction to the terminal through the second channel to trigger the terminal to play the target audio.
[0111] like Figure 2 As shown, the network device is a communication server, and the network device triggers at least one of the calling terminal and the called terminal of the call to play the target audio through the second channel. Here, the calling terminal and / or the called terminal can authorize the network device to directly trigger the terminal to play the audio before the call. The calling terminal and / or the called terminal sends audio information and / or call anomaly detection results to the network device.
[0112] Optionally, the second channel is also used for transmitting other information besides the current call, such as: the terminal sends audio information and / or call anomaly detection results to the network device; the network device sends target audio to the terminal; the terminal sends target audio to the network device, etc.
[0113] Optionally, in this embodiment, the type of the target audio includes at least one of the following:
[0114] Random interference audio generated and sent by network equipment;
[0115] The terminal matches the local interference audio based on reference values such as the current time and location;
[0116] Interference audio generated by the endpoint in real time.
[0117] As an optional implementation, the network device obtains the terminal resource status before or after triggering the terminal to play the target audio. In this way, the network device can issue an audio playback policy according to the terminal resource status, and the audio playback policy includes the type indication of the target audio, the playback volume, etc. For example, if the terminal resource status indicates that the terminal resources are sufficient, the audio playback policy issued can indicate that the type of the target audio is the interference audio generated by the terminal in real time; if the terminal resource status indicates that the terminal resources are insufficient, the audio playback policy issued can indicate that the type of the target audio is the local interference audio matched by the terminal based on the reference values such as the current time and location; if the terminal resource status indicates that the terminal resources are between sufficient and insufficient, the audio playback policy issued can indicate the random interference audio generated and issued by the network device.
[0118] The audio playback strategy may be carried through the audio trigger instruction.
[0119] In addition to the audio playback strategy indicating the playback volume of the target audio, the terminal can also calculate the playback volume by itself. As an optional implementation, the playback volume of the target audio is adjusted according to the detected voice volume of the calling user, for example, the playback volume of the target audio does not exceed 60% of the human voice volume to increase the interference to the possible AIGC.
[0120] In this embodiment, after the terminal is triggered to play the target audio, the voices of the two parties on the call, the target audio and the surrounding sounds are mixed into the same audio input and transmitted, which reduces the possibility of being tampered with by AIGC and increases the possibility of being identified, including the possibility of being identified by the scammer whether there is a problem with the sound. Therefore, during a normal call, after the terminal is triggered to play the target audio, the audio information collected through the input audio includes: the voices of the two parties on the call, the target audio and the surrounding sounds. In an abnormal call (such as the implementation of AIGC fraud), the terminal on the side of the implementer of the abnormal call cannot play the target audio, or the pre-trained audio stream cannot be consistent with the audio information of a normal call process due to reasons such as the lack of real-person calls. Therefore, judging whether the call is abnormal based on the audio information and / or the call anomaly detection results includes:
[0121] Based on the audio information and / or the call anomaly detection result, determining whether the audio collected by the terminal includes the target audio and the voice of the corresponding user; wherein the terminal includes a calling terminal and / or a called terminal;
[0122] When a preset condition is met, determining that the call is abnormal; wherein the preset condition includes at least one of the following:
[0123] The audio collected by the calling terminal does not include the target audio;
[0124] The audio collected by the calling terminal does not include the voice of the first user, and the first user is the user of the calling terminal;
[0125] The audio collected by the called terminal does not include the target audio;
[0126] The audio collected by the called terminal does not include the voice of the second user, where the second user is the user of the calling terminal.
[0127] Wherein, based on the audio information, it is determined whether the audio collected by the terminal includes the target audio and the voice of the corresponding user, that is, whether the audio information includes the target audio and the voice of the corresponding user is detected. Wherein, if the audio information does not include the audio of the corresponding user, or if there are differences in multiple samplings of the audio of the corresponding user in the audio information, it can be regarded that the audio information does not include the voice of the corresponding user.
[0128] The call anomaly detection result is determined by the terminal based on the audio information, that is, the call anomaly detection result can indicate whether the audio collected by the terminal includes the target audio and the voice of the corresponding user.
[0129] In this way, after determining whether the audio collected by the terminal includes the target audio and the voice of the corresponding user based on the audio information and / or call anomaly detection results, the network device can make a judgment on the current call based on the preset conditions defined for the call anomaly.
[0130] Optionally, in this embodiment, the method further includes:
[0131] In the case where there is an abnormality in the call, a risk assessment is performed based on the audio information and / or the call abnormality detection result to obtain an assessment result value;
[0132] If the evaluation result value is greater than a first threshold, interrupting the call;
[0133] If the evaluation result value is less than or equal to the first threshold, an abnormal reminder message is sent to the terminal.
[0134] That is, in the embodiment of the present application, when an abnormal call is detected, the appropriate processing strategy will be determined for different risk levels (that is, the comparison between the evaluation result value and the risk threshold (first threshold)) through risk assessment. For high-risk calls (the evaluation result value is greater than the first threshold), the current communication is directly interrupted; for low-risk calls (the evaluation result value is less than or equal to the first threshold), an abnormal reminder message is sent to remind the user, and the user makes the decision by himself.
[0135] Optionally, in this embodiment, a risk assessment is performed based on the audio information and / or call anomaly detection results to obtain an assessment result value. The preset conditions can be referred to, a corresponding weight can be set for each condition, and then the weighted sum is used to calculate the assessment result value.
[0136] In addition, optionally, in an embodiment of the present application, the method further includes:
[0137] Triggering the camera of the terminal to start;
[0138] Receive the image captured by the camera and sent by the terminal.
[0139] That is, the network device can start the camera (physical camera) of the terminal (calling terminal and / or called terminal) so that the camera can capture images in real time, and the network device receives the images captured by the camera for call abnormality judgment.
[0140] Optionally, the preset condition also includes at least one of the following:
[0141] The image captured by the calling terminal does not match the image during the current call:
[0142] The image captured by the called terminal does not match the image during the current call.
[0143] That is to say, the network device can determine whether the call is abnormal based on at least one of the received audio information, the call abnormality detection result, and the image captured by the camera.
[0144] The network device may create a third channel for the call, and send a camera trigger instruction to the terminal via the third channel. Of course, the image captured by the camera may be transmitted to the network device via the third channel.
[0145] Next, combine Figure 3 The application of the method of the embodiment of the present application is described. It is worth noting that the figure only shows the specific process steps of the network device (communication server) triggering terminal B to play the target audio and judging whether the call is abnormal based on terminal B, but the communication server can also trigger terminal A to play the target audio and judge whether the call is abnormal based on terminal A or terminal A + terminal B:
[0146] Step 1: The communication server sends an audio trigger instruction to terminal B.
[0147] Step 2: After receiving the audio trigger instruction, terminal B turns on the sound speaker. Terminal B can also detect local resources and return the local resource status while returning the result corresponding to the audio trigger instruction.
[0148] Step 3: The communication server sends an audio playback policy to terminal B. The audio playback policy may be determined according to the local resource status of terminal B.
[0149] Step 4: Terminal B calculates the target audio playback volume and plays the target audio.
[0150] Step 5: Terminal B collects audio information. Here, terminal B can obtain audio information by collecting audio input data.
[0151] In step 6a, terminal B uploads the collected audio information to the communication server. Alternatively, in step 6b-1, terminal B determines whether the call is abnormal based on the audio information and obtains the call abnormality detection result; in step 6b-2, terminal B uploads the call abnormality detection result.
[0152] Step 7: The communication server determines whether there is any abnormality in the call based on the audio information and / or the call abnormality detection result.
[0153] Step 8: When the communication server finds that there is an abnormality in the call, it sends an abnormality reminder message to terminal A and terminal B to remind users to pay attention to call safety.
[0154] In summary, the method of the embodiment of the present application, by triggering the terminal to play the target audio and adding audio verification to confirm whether the communication environment is safe, can more effectively detect whether the call is abnormal, thereby improving the accuracy of detection.
[0155] like Figure 4 As shown, a call anomaly detection method according to an embodiment of the present application is executed by a terminal, including:
[0156] Step 401, during a call, responding to a trigger of a network device to play a target audio;
[0157] Step 402, obtaining audio information when playing the target audio;
[0158] Step 403: sending the audio information to the network device, and / or determining a call anomaly detection result based on the audio information and sending the call anomaly detection result to the network device.
[0159] In this way, the terminal plays the target audio in response to the triggering of the network device during the call, and then obtains the audio information when playing the target audio. Afterwards, the terminal can directly send the audio information to the network device, so that the network device receives the audio information, and then judges whether the call is abnormal based on the audio information; the terminal can also determine the call abnormality detection result based on the audio information and send the call abnormality detection result to the network device. In this way, by adding target audio interference during the call and collecting audio information to detect call abnormalities, the accuracy of identifying call abnormalities is improved and the security of the call is guaranteed.
[0160] The terminal may be a calling terminal and / or a called terminal of a call.
[0161] Optionally, determining a call anomaly detection result according to the audio information and sending the call anomaly detection result to the network device includes:
[0162] Based on the audio information, determine whether the audio collected by the terminal includes the target audio and the voice of the corresponding user, and generate the call anomaly detection result; wherein the call anomaly detection result is used to indicate whether the audio collected by the terminal includes the target audio and the voice of the user of the terminal.
[0163] Optionally, the method further comprises:
[0164] Receive abnormal reminder information sent by the network device, where the abnormal reminder information is used to remind the terminal that an abnormality exists in the current call.
[0165] After receiving the audio information and / or the call anomaly detection result, the network device can determine whether the call is abnormal in combination with the preset conditions. In addition, if the call is abnormal, a risk assessment is performed based on the audio information and / or the call anomaly detection result to obtain an assessment result value; when the assessment result value is less than or equal to the first threshold, an abnormal reminder message is sent to the terminal. The terminal receives the abnormal reminder message and can remind the user to pay attention to the safety of the current call.
[0166] The preset condition includes at least one of the following:
[0167] The audio collected by the calling terminal does not include the target audio;
[0168] The audio collected by the calling terminal does not include the voice of the first user, and the first user is the user of the calling terminal;
[0169] The audio collected by the called terminal does not include the target audio;
[0170] The audio collected by the called terminal does not include the voice of the second user, where the second user is the user of the calling terminal.
[0171] Of course, if the evaluation result value is greater than the first threshold, the network device will interrupt the call.
[0172] Optionally, the method further comprises:
[0173] In response to the trigger of the network device, the camera is started;
[0174] The image captured by the camera is sent to the network device.
[0175] That is, the terminal will start the camera in response to the trigger of the network device, and send the image collected by the camera so that the image can be used for call abnormality judgment.
[0176] Optionally, the preset condition also includes at least one of the following:
[0177] The image captured by the calling terminal does not match the image during the current call:
[0178] The image captured by the called terminal does not match the image during the current call.
[0179] That is to say, the network device can determine whether the call is abnormal based on at least one of the received audio information, the call abnormality detection result, and the image captured by the camera.
[0180] It should be noted that the method of the embodiment of the present application is implemented in conjunction with the method executed by the above-mentioned network device. The implementation method of the above-mentioned method embodiment is applicable to this method and can achieve the same technical effect.
[0181] like Figure 5 As shown, the embodiment of the present application further provides a call abnormality detection device 500, comprising:
[0182] The first processing module 510 is used to trigger the terminal to play the target audio during a call;
[0183] The receiving module 520 is used to receive the audio information and / or the call anomaly detection result sent by the terminal according to the target audio;
[0184] The second processing module 530 is used to determine whether there is any abnormality in the call according to the audio information and / or the call abnormality detection result.
[0185] Optionally, the second processing module includes:
[0186] A first processing unit, configured to determine whether the audio collected by the terminal includes the target audio and the voice of the corresponding user based on the audio information and / or the call anomaly detection result; wherein the terminal includes a calling terminal and / or a called terminal;
[0187] The second processing unit is configured to determine that the call is abnormal if a preset condition is met; wherein the preset condition includes at least one of the following:
[0188] The audio collected by the calling terminal does not include the target audio;
[0189] The audio collected by the calling terminal does not include the voice of the first user, and the first user is the user of the calling terminal;
[0190] The audio collected by the called terminal does not include the target audio;
[0191] The audio collected by the called terminal does not include the voice of the second user, where the second user is the user of the calling terminal.
[0192] Optionally, the device further comprises:
[0193] A fifth processing module, configured to, when the call is abnormal, perform risk assessment based on the audio information and / or the call abnormality detection result to obtain an assessment result value;
[0194] A sixth processing module, configured to interrupt the call if the evaluation result value is greater than a first threshold;
[0195] The seventh processing module is used to send abnormal reminder information to the terminal if the evaluation result value is less than or equal to the first threshold.
[0196] Optionally, the device further comprises:
[0197] An eighth processing module, configured to create a second channel for the call;
[0198] The first processing module is also used for:
[0199] An audio trigger instruction is sent to the terminal through the second channel.
[0200] Optionally, the device further comprises:
[0201] A ninth processing module, used for triggering the camera of the terminal to start;
[0202] The tenth processing module is used to receive the image captured by the camera and sent by the terminal.
[0203] Optionally, the preset condition also includes at least one of the following:
[0204] The image captured by the calling terminal does not match the image during the current call:
[0205] The image captured by the called terminal does not match the image during the current call.
[0206] The device can trigger the terminal to play the target audio during a call, so that the terminal collects audio information and / or determines the call anomaly detection result according to the target audio. If the network device receives the audio information, it determines whether the call is abnormal according to the audio information; if the network device receives the call anomaly detection result, it determines whether the call is abnormal according to the call anomaly detection result. In this way, by adding target audio interference during a call and collecting audio information to detect call anomalies, the accuracy of identifying call anomalies is improved and the security of the call is guaranteed.
[0207] It should be noted that the device is a device that applies the above-mentioned call anomaly detection method executed by the network device. The implementation process of the above-mentioned call anomaly detection method embodiment is applicable to the device and can also achieve the same technical effect.
[0208] like Figure 6 As shown, the embodiment of the present application further provides a call abnormality detection device 600, comprising:
[0209] The third processing module 610 is used to respond to the triggering of the network device to play the target audio during the call;
[0210] The fourth processing module 620 is used to obtain audio information when playing the target audio;
[0211] The sending module 630 is used to send the audio information to the network device, and / or determine the call anomaly detection result according to the audio information and send the call anomaly detection result to the network device.
[0212] Optionally, the sending module is further used for:
[0213] Based on the audio information, determine whether the audio collected by the terminal includes the target audio and the voice of the corresponding user, and generate the call anomaly detection result; wherein the call anomaly detection result is used to indicate whether the audio collected by the terminal includes the target audio and the voice of the user of the terminal.
[0214] Optionally, the device further comprises:
[0215] The abnormal reminder information receiving module is used to receive the abnormal reminder information sent by the network device, and the abnormal reminder information is used to remind the terminal that there is an abnormality in the current call.
[0216] Optionally, the device further comprises:
[0217] A camera activation module, used to activate the camera in response to a trigger of the network device;
[0218] An image sending module is used to send the image captured by the camera to the network device.
[0219] The device plays the target audio in response to the triggering of the network device during the call, and then obtains audio information when playing the target audio. Afterwards, the device can directly send the audio information to the network device, so that the network device receives the audio information, and then judges whether the call is abnormal based on the audio information; the device can also determine the call abnormality detection result based on the audio information and send the call abnormality detection result to the network device. In this way, by adding target audio interference during the call and collecting audio information to detect call abnormalities, the accuracy of identifying call abnormalities is improved and the security of the call is guaranteed.
[0220] It should be noted that the device is a device that applies the above-mentioned call anomaly detection method executed by the network device. The implementation process of the above-mentioned call anomaly detection method embodiment is applicable to the device and can also achieve the same technical effect.
[0221] The implementation principle and technical effect of the device in the embodiment of the present application are similar, and this embodiment will not be repeated here.
[0222] like Figure 7As shown, an embodiment of the present application also provides a call anomaly detection device, including: a processor 701, a memory 702, and a computer program stored in the memory 702 and executable on the processor 701, and the processor 701 implements the steps of the above-mentioned call anomaly detection method when executing the computer program.
[0223] The call anomaly detection device provided in the embodiment of the present application can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be repeated in this embodiment.
[0224] Those skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or may be accomplished by instructing relevant hardware through a computer program, wherein the computer program includes instructions for executing part or all of the steps of the above method; and the computer program may be stored in a readable storage medium, and the storage medium may be any form of storage medium.
[0225] In addition, the specific embodiment of the present application further provides a readable storage medium on which a program is stored, and when the program is executed by a processor, the steps in the above-mentioned call anomaly detection method are implemented. And the same technical effect can be achieved, so in order to avoid repetition, it will not be repeated here.
[0226] The present application also provides a computer program product, including computer instructions, which, when executed by a processor, implement the above Figure 1 or Figure 4 The various processes of the method embodiment shown can achieve the same technical effect, and will not be described again here to avoid repetition.
[0227] In the several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0228] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may be physically included separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.
[0229] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform some steps of the sending and receiving methods described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store program codes.
[0230] The above is a preferred embodiment of the present application. It should be pointed out that for ordinary personnel in this technical field, several improvements and modifications can be made without departing from the principles described in the present application. These improvements and modifications are also within the scope of protection of the present application.
Claims
1. A method for detecting abnormal calls, characterized in that: Performed by network devices, including: During a call, trigger the terminal to play the target audio; Receiving audio information and / or call anomaly detection results sent by the terminal according to the target audio; Whether there is any abnormality in the call is determined according to the audio information and / or the call anomaly detection result.
2. The method according to claim 1, characterized in that The determining, based on the audio information and / or the call anomaly detection result, whether the call is abnormal includes: Based on the audio information and / or the call anomaly detection result, determining whether the audio collected by the terminal includes the target audio and the voice of the corresponding user; wherein the terminal includes a calling terminal and / or a called terminal; When a preset condition is met, determining that the call is abnormal; wherein the preset condition includes at least one of the following: The audio collected by the calling terminal does not include the target audio; The audio collected by the calling terminal does not include the voice of the first user, and the first user is the user of the calling terminal; The audio collected by the called terminal does not include the target audio; The audio collected by the called terminal does not include the voice of the second user, where the second user is the user of the calling terminal.
3. The method according to claim 2, characterized in that The method further comprises: In the case where there is an abnormality in the call, a risk assessment is performed based on the audio information and / or the call abnormality detection result to obtain an assessment result value; If the evaluation result value is greater than a first threshold, interrupting the call; If the evaluation result value is less than or equal to the first threshold, an abnormal reminder message is sent to the terminal.
4. The method according to claim 1, characterized in that The method comprises: Creating a second channel for the call; The triggering terminal to play the target audio includes: An audio trigger instruction is sent to the terminal through the second channel.
5. The method according to claim 2, characterized in that: The method further comprises: Triggering the camera of the terminal to start; Receive the image captured by the camera and sent by the terminal.
6. The method according to claim 5, characterized in that The preset condition also includes at least one of the following: The image captured by the calling terminal does not match the image during the current call: The image captured by the called terminal does not match the image during the current call.
7. A method for detecting abnormal calls, characterized in that: Executed by the terminal, including: During a call, respond to the trigger of the network device to play the target audio; Acquiring audio information when playing the target audio; The audio information is sent to the network device, and / or a call anomaly detection result is determined based on the audio information and the call anomaly detection result is sent to the network device.
8. The method according to claim 7, characterized in that The determining the call anomaly detection result according to the audio information and sending the call anomaly detection result to the network device comprises: Based on the audio information, determine whether the audio collected by the terminal includes the target audio and the voice of the corresponding user, and generate the call anomaly detection result; wherein the call anomaly detection result is used to indicate whether the audio collected by the terminal includes the target audio and the voice of the user of the terminal.
9. The method according to claim 7, characterized in that: The method further comprises: Receive abnormal reminder information sent by the network device, where the abnormal reminder information is used to remind the terminal that there is an abnormality in the current call.
10. The method according to claim 7, characterized in that The method further comprises: In response to the trigger of the network device, the camera is started; The image captured by the camera is sent to the network device.
11. A call abnormality detection device, characterized in that: include: The first processing module is used to trigger the terminal to play the target audio during a call; A receiving module, used to receive the audio information and / or call anomaly detection result sent by the terminal according to the target audio; The second processing module is used to determine whether there is any abnormality in the call according to the audio information and / or the call abnormality detection result.
12. A call abnormality detection device, characterized in that: include: The third processing module is used to respond to the trigger of the network device to play the target audio during the call; A fourth processing module, used for acquiring audio information when playing the target audio; A sending module is used to send the audio information to the network device, and / or determine a call anomaly detection result based on the audio information and send the call anomaly detection result to the network device.
13. A call anomaly detection device, comprising: A memory, a processor, and a program stored in the memory and executable on the processor; characterized in that: The processor is used to read the program in the memory to implement the steps in the call abnormality detection method as described in any one of claims 1 to 6, or the steps in the call abnormality detection method as described in any one of claims 7 to 10.
14. A readable storage medium for storing a program, characterized in that: When the program is executed by a processor, the steps of the call abnormality detection method according to any one of claims 1 to 6 or the steps of the call abnormality detection method according to any one of claims 7 to 10 are implemented.
15. A computer program product, characterized in that The method comprises computer instructions, which, when executed by a processor, implement the steps in the call anomaly detection method as claimed in any one of claims 1 to 6, or the steps in the call anomaly detection method as claimed in any one of claims 7 to 10.
Citation Information
Patent Citations
Video call method and related products
CN107770478A
Call person abnormity detection method and device
CN109769099A
Anomaly checking method and device for audio playing equipment and storage medium
CN112669883A
Method, device and equipment for identifying AI clone sound
CN118072741A
