Call object identification method

Abstract

The embodiment of the invention provides a call object identification method, and the method comprises the steps: collecting first feature information of a call object communicating with a first terminal through the first terminal, and determining whether the call object is a target object or not according to the first feature information; when it is determined that the call object is the target object, a first instruction is sent to a second terminal associated with the target object, and the first instruction is used for obtaining call state information of the second terminal; and determining whether the current call terminal communicating with the first terminal is the second terminal or not according to the obtained call state information of the second terminal, thereby solving the problem that a user cannot accurately identify a call object due to disguised as a relative in the call process, and improving the efficiency and accuracy of identifying the call object.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of communications, and in particular, to a method for identifying a call object. Background Art

[0002] When a user makes a voice or video call, some network personnel will use the voice or image of the user's relatives to perform voice conversion or face replacement through artificial intelligence (AI), and deceive by disguising as the user's relatives. Some network personnel will also disguise a phone number as a virtual number of a relative, causing the user to mistakenly believe that the call object is a relative and thus be deceived.

[0003] Regarding the problem that the user cannot accurately identify the call object due to being disguised as a relative during a call, no effective solution has been proposed in the related art. Summary of the Invention

[0004] Embodiments of the present invention provide a method for identifying a call object, so as to at least solve the problem in the related art that the user cannot accurately identify the deception behavior of network personnel disguising as relatives during a call.

[0005] According to an embodiment of the present invention, there is provided a method for identifying a call object, including:

[0006] A first terminal collects first feature information of a call object communicating with it, and determines whether the call object is a target object according to the first feature information;

[0007] When it is determined that the call object is a target object, a first instruction is sent to a second terminal associated with the target object, where the first instruction is used to obtain call status information of the second terminal;

[0008] It is determined whether the current call terminal communicating with the first terminal is the second terminal according to the obtained call status information of the second terminal.

[0009] In an exemplary embodiment, after determining whether the current call terminal communicating with the first terminal is the second terminal according to the obtained call status information of the second terminal, it further includes:

[0010] When it is determined that the current call terminal is the second terminal, a second instruction is sent to the second terminal, where the second instruction is used to instruct the second terminal to collect second feature information and feedback it to the first terminal;

[0011] It is determined whether the current user of the second terminal is the target object according to the feedback second feature information.

[0012] According to another embodiment of the present invention, there is also provided a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the steps in any one of the above method embodiments when running.

[0013] According to another embodiment of the present invention, there is also provided an electronic device including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0014] With the present invention, during a call, the first terminal collects first feature information of the call object with which it is communicating, and determines whether the call object is the target object according to the first feature information. In the case where the call object is determined to be the target object, a first instruction is sent to the second terminal associated with the target object, and it is determined whether the current call terminal communicating with the first terminal is the second terminal according to the obtained call status information of the second terminal. When the current call terminal is a terminal used by a network person to perform face swapping and voice changing using artificial intelligence or a terminal using the phone number of a virtual relative, the user may be deceived by the network person after face swapping and voice changing. By sending an instruction from the user terminal to the terminal of the real relative when the user receives a call, and obtaining the call status information of the real relative's terminal through the instruction, it is thus verified whether the call terminal is the terminal of the real relative. Obviously, a network person disguising as a relative cannot change the call status of the real relative's terminal, and thus it is possible to identify whether the current call object terminal is the terminal of the real relative, improving the efficiency and accuracy of identifying the call object. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a hardware structure block diagram of a mobile terminal of a call object recognition method according to an embodiment of the present invention;

[0016] Figure 2 is a flowchart of a call object recognition method according to an embodiment of the present invention;

[0017] Figure 3 is a flowchart of determining whether the current user of the second terminal is the target object through Method 1 according to an embodiment of the present invention;

[0018] Figure 4 is a flowchart of determining whether the current user of the second terminal is the target object through Method 2 according to an embodiment of the present invention;

[0019] Figure 5 is a flowchart of determining whether the current user of the second terminal is the target object through Method 3 according to an embodiment of the present invention;

[0020] Figure 6It is the overall flowchart of a call object recognition method according to an embodiment of the present invention;

[0021] Figure 7 It is the block diagram of the device structure of a call object recognition method according to an embodiment of the present invention;

[0022] Figure 8 It is the flowchart of a call object recognition method according to an embodiment of the present invention in a specific application scenario. Detailed implementation manners

[0023] In the following, embodiments of the present invention will be described in detail with reference to the accompanying drawings and in conjunction with the embodiments.

[0024] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence.

[0025] The method embodiments provided in the embodiments of the present application can be executed on a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 It is the hardware block diagram of a mobile terminal of a call object recognition method according to an embodiment of the present invention. As Figure 1 shown, the mobile terminal may include one or more ( Figure 1 only one is shown in the figure) processors 102 (the processor 102 may include, but is not limited to, processing devices such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Among them, the above-mentioned mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those of ordinary skill in the art can understand that Figure 1 the structure shown in the figure is only schematic and does not limit the structure of the above-mentioned mobile terminal. For example, the mobile terminal may further include more or fewer components than Figure 1 shown in the figure, or have a different configuration from Figure 1 shown in the figure.

[0026] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to a call object recognition method in an embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above-mentioned method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some instances, the memory 104 may further include a memory remotely disposed relative to the processor 102, and these remote memories can be connected to the mobile terminal through a network. Examples of the above-mentioned network include but are not limited to the Internet, enterprise intranet, local area network, mobile communication network, and combinations thereof.

[0027] The transmission device 106 is used to receive or send data via a network. Specific examples of the above-mentioned network may include a wireless network provided by a communication provider of the mobile terminal. In one instance, the transmission device 106 includes a network adapter (Network Interface Controller, abbreviated as NIC), which can be connected to other network devices through a base station and thus can communicate with the Internet. In one instance, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0028] In this embodiment, a call object recognition method is provided. Figure 2 It is a flowchart of a call object recognition method according to an embodiment of the present invention, as Figure 2 shown, and this process includes the following steps:

[0029] Step S202, the first terminal collects first feature information of a call object with which it is communicating, and determines whether the call object is a target object according to the first feature information;

[0030] Step S204, when it is determined that the call object is a target object, send a first instruction to a second terminal associated with the target object, where the first instruction is used to obtain call status information of the second terminal;

[0031] Step S206, determine whether the current call terminal communicating with the first terminal is the second terminal according to the obtained call status information of the second terminal.

[0032] Through the above steps, the user may be deceived by the cyber personnel with face-swapped and voice-changed identities. When receiving a call, the user terminal sends an instruction to the terminal of the real relative, and obtains the call status information of the real relative's terminal through the instruction, so as to verify whether the call terminal is the terminal of the real relative. Obviously, the cyber personnel pretending to be relatives cannot change the call status of the real relative's terminal, and thus it is possible to identify whether the current call object terminal is the terminal of the real relative, improving the efficiency and accuracy of identifying the call object.

[0033] In an exemplary embodiment, determining whether the call object is the target object according to the obtained first feature information includes:

[0034] Comparing the first feature information with the pre-stored feature data of the target object to determine whether the call object is the target object, where the first feature information includes at least one of the following: the mobile phone number of the call object, the image information of the call object, the voiceprint information of the call object; the feature data includes at least one of the following: the appearance feature data of the target object, the voiceprint feature data, and the mobile phone number associated with the target object.

[0035] In an exemplary embodiment, comparing the first feature information with the pre-stored feature data of the target object to determine whether the call object is the target object includes one of the following:

[0036] In the case where the current call is a video call, comparing the collected image information of the call object and / or the voiceprint information of the call object with the appearance feature data and / or the voiceprint feature data in the pre-stored feature data of the target object to determine whether the call object is the target object;

[0037] In the case where the current call is a voice call, comparing the collected mobile phone number of the call object and / or the voiceprint information of the call object with the mobile phone number and / or the voiceprint feature data in the pre-stored feature data of the target object to determine whether the call object is the target object.

[0038] In an exemplary embodiment, the above step S206 includes:

[0039] Determining whether the current call terminal is the second terminal according to whether the obtained call status information of the second terminal is consistent with the call status information of the current call terminal of the first terminal call, where the call status information of the second terminal includes the machine factory identity identifier of the second terminal;

[0040] In the case where the current call is a video call, the call status information of the second terminal further includes one of the following: the call connection status, the application in the call;

[0041] When the current call is a voice call, the call status information of the second terminal further includes one of the following: call connection status, the mobile phone number of the current call object of the second terminal.

[0042] In an optional embodiment, after the above step S206, the following is further included:

[0043] When the machine factory identity identifier of the second terminal is inconsistent with the current call status, and the rest of the call status information of the second terminal is consistent with the current call status, send verification information to the mobile phone number of the target object, and based on the feedback information of the verification information received for the mobile phone number of the target object, determine again whether the call object is the target object.

[0044] When it is determined that the call object is not the target object, display a prompt on the first terminal that the current call object is not the target object.

[0045] In an exemplary embodiment, the verification information includes one of the following: a temporary verification code, a key window.

[0046] In an optional embodiment, the method further includes:

[0047] Step S208, when it is determined that the current call terminal is the second terminal, determine whether the current user of the second terminal is the target object through the following three methods, and any one of the three methods can be selected.

[0048] Figure 3 It is a flowchart for determining whether the current user of the second terminal is the target object by method 1 in the embodiment of the present invention, as Figure 3 shown, method 1 includes the following steps:

[0049] Step S301, when it is determined that the current call terminal is the second terminal, send a second instruction to the second terminal, where the second instruction is used to instruct the second terminal to collect second feature information and feedback it to the first terminal;

[0050] Step S302, determine whether the current user of the second terminal is the target object according to the feedback second feature information.

[0051] Figure 4 It is a flowchart for determining whether the current user of the second terminal is the target object by method 2 in the embodiment of the present invention, as Figure 4 shown, method 2 includes the following steps:

[0052] S401. When it is determined that the current call terminal is the second terminal, send a third instruction to a third terminal associated with the target object through the second terminal, where the third terminal is a device paired and successfully connected to the second terminal, and the third instruction is used to instruct the third terminal to collect second feature information and feedback it to the first terminal;

[0053] S402. Determine whether the current user of the second terminal is the target object according to the feedback second feature information.

[0054] Figure 5 It is a flowchart for determining whether the current user of the second terminal is the target object by method 3 in an embodiment of the present invention. As Figure 5 shown, method 3 includes the following steps:

[0055] Step S501. When it is determined that the current call terminal is the second terminal, determine whether the current user of the second terminal is the target object according to the connection status between the second terminal and a fourth terminal associated with the target object, where the fourth terminal is a device paired and successfully connected to the second terminal, and the connection status is obtained through the first instruction.

[0056] In an exemplary embodiment, determining whether the current user of the second terminal is the target object according to the connection status between the second terminal and a fourth terminal associated with the target object includes:

[0057] When the second terminal and the fourth terminal associated with the target object are in a disconnected state, send a fourth instruction to the second terminal, where the fourth instruction is used to instruct the second terminal to collect second feature information and feedback it to the first terminal;

[0058] Determine whether the current user of the second terminal is the target object according to the feedback second feature information.

[0059] In an exemplary embodiment, the second feature information at least includes one of the following: image information of the current user of the second terminal, voiceprint information, and surrounding environment information.

[0060] Next, the overall process of a method for identifying an object in an embodiment of the present invention is described. Figure 6 It is the overall flowchart of a call object identification method according to an embodiment of the present invention. As Figure 6 shown, the overall process is as follows:

[0061] When the user is alone, some network personnel will use the voices or images of the user's relatives to perform AI voice conversion or face swapping, and use the processed voices or images to conduct voice or video calls with the user for deception. Some network personnel will also use technical means to disguise a phone number as a virtual number of the user's relative, making the user mistake the call object for a relative and thus deceive the user.

[0062] Before adopting the method of this embodiment, a family affection module is added to the user terminal, and this family affection module can store information of the user's relatives, including the mobile phone numbers of the relatives, appearance feature data, voiceprint feature data, factory identification of the mobile phone, etc.

[0063] The embodiment of the present invention adopts the following steps to identify the call object:

[0064] Step S1, the first terminal collects first feature information of the call object with which it is having a call. Among them, the first feature information includes at least one of the following: the mobile phone number of the call object, the image information of the call object, and the voiceprint information of the call object.

[0065] Exemplarily, when the user answers a video call, the application program (APP) on the user's mobile phone collects the image information and the voice information of the call object on the call interface.

[0066] Step S2, compare the first feature information with the feature data of the target object stored in advance to determine whether the call object is the target object. If so, execute step S3; if not, do nothing.

[0067] The call methods in the embodiment of the present invention are divided into video calls and voice calls. In different call methods, the specific comparison methods are as follows: in the case where the current call is a video call, compare the collected image information of the call object and / or the voiceprint information of the call object with the appearance feature data and / or the voiceprint feature data in the feature data of the pre-stored target object to determine whether the call object is the target object; in the case where the current call is a voice call, compare the collected mobile phone number of the call object and / or the voiceprint information of the call object with the mobile phone number and / or the voiceprint feature data in the feature data of the pre-stored target object to determine whether the call object is the target object.

[0068] Among them, the feature data includes at least one of the following: the appearance feature data of the target object, the voiceprint feature data, and the mobile phone number associated with the target object. The feature data is pre-stored in the family affection module.

[0069] Exemplarily, taking video call as an example, after the user APP collects the image information, it compares with the appearance data features in the family module (face recognition) to determine which relative it is. For example, after face recognition, if it is determined that the current call object is relative A, then step S3 is executed. If it is recognized that it is not a relative, no processing is performed. In addition to using image information for comparison, voiceprint information can also be used for comparison. The two can be used separately or in combination, and no limitation is made here. In the case of a voice call, the information collected can also be the mobile phone number of the call object.

[0070] Step S3, when it is determined that the call object is the target object, a first instruction is sent to the second terminal associated with the target object. Wherein, the first instruction is used to obtain the call status information of the second terminal; the call status information of the second terminal includes the machine factory identity identifier of the second terminal, and also includes one of the following: call connection status, application in call.

[0071] Exemplarily, when the user APP determines that the call object is relative A, it sends an instruction to the mobile phone of relative A (the relatives of the user, including relative A, have all pre-installed the same APP and can send and receive instructions through the Internet). This instruction is used to obtain the machine factory identity identifier of relative A's mobile phone, the call connection status, and the application in call.

[0072] Step S4, determine whether the current call terminal is the second terminal according to whether the obtained call status information of the second terminal is consistent with the call status information of the current call terminal of the first terminal call. If not, then step S51 is executed. If so, then step S52 is executed.

[0073] The obtained call status information of the second terminal and the call status information of the current call terminal of the first terminal call are in the following situations:

[0074] Situation 1, the machine factory identity identifier of the second terminal is inconsistent with the current call status, and the remaining call status information of the second terminal is consistent with the current call status; then step S51 is executed to further identify the call object.

[0075] Exemplarily, taking video call as an example, the machine factory identity identifier is inconsistent, the call status is in the video call state, and the application name of the video call is the same. This situation may be that relative A has changed to a new mobile phone, and the new mobile phone has installed the same APP. This situation needs to be further verified. If it is in the way of a voice call, the machine factory identity identifier is inconsistent, the call status is in the voice call state, and the number of the voice call object is the same as the user's number. This situation may be that relative A has changed to a new mobile phone, and the new mobile phone has installed relative A's original mobile phone number. Similarly, further verification is required.

[0076] In Case 2, if the machine factory identity identifier of the second terminal is inconsistent with the current call status and the remaining call status information of the second terminal is inconsistent with the current call status, it can be determined that the terminal of the current call object is not the terminal of relative A, but a network person who disguises as relative A to deceive.

[0077] In Case 3, if the call status information of the second terminal is consistent with the call status information of the current call terminal of the first terminal, then step S52 is executed to further identify the call object.

[0078] In this case, the reason for further identification is that the network person obtained the mobile phone of relative A and used the mobile phone of relative A to disguise as relative A to make a call with the user. Therefore, it is necessary to further identify whether the current call object is the real relative A himself.

[0079] Step S51, use Method 1 to determine again whether the call object is the target object. Method 1 includes the following sub-steps:

[0080] Sub-step S511, when the machine factory identity identifier of the second terminal is inconsistent with the current call status and the remaining call status information of the second terminal is consistent with the current call status, send a verification message to the mobile phone number of the target object, and based on the feedback message of the verification message received for the mobile phone number of the target object, determine again whether the call object is the target object; where the verification message includes one of the following: temporary verification code, key window;

[0081] Exemplarily, in the case corresponding to the above Case 1, it can be determined that the mobile phone of the current call is not the personal mobile phone of relative A, but the current call object may be relative A. The reason is that relative A may have changed to a new mobile phone, and the new mobile phone also installs the same APP and the original mobile phone number. At this time, further verification is required. Through the mobile phone number of relative A pre-stored in the user's family member module, send a verification message to relative A, and determine whether the current call object is relative A according to the feedback message.

[0082] The method of sending the verification message can be to send a verification code temporarily input by the user to the mobile phone number of relative A through the 5G data channel, and require the current call object to orally state the verification code, or the family member module pre-stores a prefabricated key, and send a family member key window to the APP on the terminal of relative A, and require the current call object to input the key.

[0083] Sub-step S512, when it is determined that the call object is not the target object, display a prompt on the first terminal that the current call object is not the target object.

[0084] Exemplarily, if the verification code or key cannot be correctly input for verification, the user will be reminded that the identity of the other party cannot be verified and it may be a spoofed number fraud; and next, the call time of this call will be recorded, and at the same time, the user's relative A will be notified from the APP that the user may be a victim of spoofed number fraud, showing care for the user.

[0085] Step S52, use Method 2 to determine again whether the call object is the target object. Method 2 includes the following three alternative methods, and one of them can be selected when executing.

[0086] Method 1 includes the following sub-steps:

[0087] Sub-step 1, when it is determined that the current call terminal is the second terminal, send a second instruction to the second terminal, where the second instruction is used to instruct the second terminal to collect second feature information and feedback it to the first terminal; where the second feature information at least includes one of the following: image information of the current user of the second terminal, voiceprint information, and surrounding environment information.

[0088] Exemplarily, when it is determined that the call is from the mobile phone of relative A himself, the user APP sends a second instruction to the mobile phone APP of relative A through the Internet, and this instruction is used to instruct the mobile phone of relative A to collect image information, voiceprint information, and surrounding environment information of relative A.

[0089] Sub-step 2, determine whether the current user of the second terminal is the target object according to the feedback second feature information.

[0090] Exemplarily, the user APP determines whether the image information and voiceprint information fed back by the APP of relative A are consistent with the appearance feature data and voiceprint feature data of relative A stored in the user's relative module. If they are consistent, it can be determined that the mobile phone of relative A himself is being used by relative A himself. In addition to the image information and voiceprint information collected by the mobile phone of relative A himself, the second feature information can also be the environment around the mobile phone of relative A collected by the mobile phone of relative A himself. For example, by comparing the collected surrounding environment with the environment information stored in the user's relative module, if it is determined to be a trustworthy environment (relative A's home), it can be determined that the mobile phone of relative A himself is being used by relative A himself. If it is a strange environment, other methods will be used for confirmation.

[0091] Method 2 includes the following sub-steps:

[0092] Sub-step 1: When it is determined that the current call terminal is the second terminal, send a third instruction to a third terminal associated with the target object through the second terminal. The third terminal is a device paired and successfully connected to the second terminal, and the third instruction is used to instruct the third terminal to collect second feature information and provide feedback to the first terminal. The second feature information at least includes one of the following: image information of the current user of the second terminal, voiceprint information, and surrounding environment information.

[0093] Exemplarily, when it is determined that the call is made from the mobile phone of relative A himself, the user APP uses the Internet to send a third instruction to devices associated with relative A through the mobile phone APP of relative A himself, such as his smart wearable device, smart home, etc. The third instruction is used to instruct the smart wearable device or smart home to collect image information, voiceprint information, and surrounding environment information of the current user of relative A's mobile phone and provide feedback. The smart wearable device and smart home are devices paired and successfully connected to relative A's mobile phone. For example, relative A's mobile phone has been connected to a smart watch via Bluetooth. After receiving the third instruction, the smart watch calls the camera to collect the current image information, voiceprint information, and surrounding environment of relative A and feeds them back to the user APP.

[0094] Sub-step 2: Determine whether the current user of the second terminal is the target object according to the feedback of the second feature information.

[0095] Method 3 includes the following sub-steps:

[0096] Sub-step 1: When it is determined that the current call terminal is the second terminal, determine whether the current user of the second terminal is the target object according to the connection status between the second terminal and a fourth terminal associated with the target object. The fourth terminal is a device paired and successfully connected to the second terminal in the past, and the connection status is obtained through the first instruction.

[0097] Exemplarily, when it is determined that the call is made from the mobile phone of relative A himself, determine that relative A's mobile phone is being used by relative A himself according to the connection status between relative A's mobile phone and devices associated with him, such as his smart wearable device and smart home. The connection status is obtained through the first instruction.

[0098] For example, when the user sends the first instruction, the instruction also includes obtaining the connection status of the Bluetooth watch paired with the mobile phone of relative A. The user APP obtains the feedback information of the first instruction. When the Bluetooth watch and the mobile phone of relative A are in a connected state in the feedback information, it can be determined that the mobile phone of relative A is being used by relative A himself. This is because the Bluetooth watch and relative A can only be in a connected state within a short distance. Therefore, when in a connected state, it can be confirmed that relative A is within the short-distance range of his mobile phone, and further, it can be determined that the mobile phone of relative A is being used by relative A himself.

[0099] Sub-step 2, in the case where the second terminal and the fourth terminal associated with the target object are in a disconnected state, send a fourth instruction to the second terminal, where the fourth instruction is used to instruct the second terminal to collect second feature information and feedback it to the first terminal;

[0100] Exemplarily, when the Bluetooth watch in the feedback information is in a disconnected state from the mobile phone of relative A, the user APP sends a fourth instruction to the mobile phone of relative A, and this instruction is used to instruct the mobile phone of relative A to collect the image information, voiceprint information or surrounding environment information of relative A.

[0101] Sub-step 3, determine whether the current user of the second terminal is the target object according to the feedback second feature information.

[0102] Exemplarily, the user APP determines whether the image information, voiceprint information or surrounding environment information feedback by the mobile phone APP of relative A is consistent with the appearance feature data, voiceprint feature data and environment feature data of relative A stored in the relative module of the user. If they are consistent, it can be determined that the mobile phone of relative A is being used by relative A himself. If they are inconsistent, it is determined that the current call object is not the real relative A.

[0103] Figure 7 It is a structural block diagram of a device for a call object recognition method according to an embodiment of the present invention, including a family affection module, a recorder module, an image processing module and a smart application APP.

[0104] The family affection module pre-collects data of relevant personnel such as the user's relatives (including phone numbers, voiceprints, portraits, etc.) and saves them.

[0105] The recorder module collects the voiceprint of the other party during a voice call or a video call and sends it to the family affection module for processing.

[0106] The image processing module collects the portrait on the call interface and sends it to the family affection module for processing.

[0107] Intelligent application APP. When the user wears peripheral devices such as a wearable handset or connects to smart home devices, the mobile terminal installs the corresponding intelligent application APP. Each time a video call is made, the user APP activates the recorder and image processing module to collect the portrait and audio of the call interface, and compares the collected data with the data in the preset family module. If it is determined that the person is a family member, the following technical solutions are then used to determine whether it is a call from the family member's own device. Specifically as follows:

[0108] Solution for determining a call from a family member's own device: The user APP (which has pre-set family numbers for each family member) sends a command to the corresponding family member's APP, checks the call status, the call recipient's number, and the name of the application in use on the family member's terminal, and transmits the information back to the user APP via the Internet. It is determined whether the call application and the call status are consistent. If they are consistent, it is determined that it is a call from the family member's own device; otherwise, it is determined that it is not a call from the family member's own device.

[0109] Anti-deception measures after determining a non-family member's own device call: In the case of the user's own number, a verification code temporarily entered by the user is sent to the family member's phone number through the 5G data channel, and the current call recipient is required to orally state the verification code. Alternatively, if the family module stores a pre-set key, a family key window is sent to the terminal of the family member's number, and the current call recipient is required to enter the key. Next, the time of this call is recorded, and the family member is notified through the APP that the user may have been deceived by an AI face swap pretending to be a family member.

[0110] Anti-deception measures after determining a call from a family member's own device: The user APP and the family member's terminal APP send commands to each other through the network. The family member's APP receives the command and activates the recorder and camera on the local device, or its smart wearable device or smart home device, to collect secondary information (voiceprint, portrait, surrounding environment, or family member's biometric features), and transmits the information back to the user APP via the Internet. The secondary collected information is compared with the information reserved in the family module to determine whether it is the family member himself / herself. If it is determined that it is not the family member himself / herself, the user terminal or the call interface prompts the user that the call recipient is not a family member, and this call will be interrupted.

[0111] Figure 8 It is a flowchart of a call object recognition method according to an embodiment of the present invention in a specific application scenario.

[0112] When the elderly are at home alone, cybercriminals will use the voices or images of the elderly's relatives to perform AI voice or face swapping, and then use the processed voices or images to conduct voice or video calls with the elderly to deceive them. Some cybercriminals will also use technical means to disguise phone numbers as virtual numbers of relatives, making users mistake the callers for their relatives and thus deceive them. How to manage the terminal security of these group users is a problem that needs to be solved. Smart terminals are becoming more and more popular, including wearable devices and smart homes, etc. Set the application scenario as the user wearing a wearable device, and the terminal is connected to some small Internet of Things such as smart furniture. As Figure 8 shown, it specifically includes the following steps:

[0113] Step S01: The kinship module pre-stores relative information.

[0114] Step S02: The intelligent application calls the recording machine and the image processing module.

[0115] Step S03: Collect the portrait and voiceprint of the call interface.

[0116] Step S04: The kinship module determines whether the call object is a relative.

[0117] Specifically, an anti-fraud kinship module is added to the user's mobile phone. The data of the anti-fraud kinship module is the data of the user's relatives (including phone numbers, mobile phone identifiers emmcid, voiceprints, images, etc.) collected in advance and preset. The user wears a smartwatch, and the corresponding smartwatch APP is installed on the mobile phone terminal. After the user receives a call, first determine what type of call it is. If it is a video call, the user's local APP collects the image and voice of the interface during the video call; if it is a voice call, the call number and voice information are collected. Compare the collected information with the data in the preset anti-fraud kinship module. If it is determined to be a relative, the following technical solution is used to determine whether it is a call from the user's relative's own mobile phone.

[0118] Step S05: Determine whether it is a call from the relative's own mobile phone.

[0119] Specifically, the technical solution for determining whether it is a call from a user's relative's own device: The user's smartwatch APP has pre-set family numbers with each of the user's relatives, and sends an instruction to the same APP on the relative's terminal. The same APP on the relative's terminal has pre-set relevant permissions and can check the call status information of the relative's terminal, including the call status, the number of the call object, and the name of the application in the call. Then, the APP on the relative's terminal feeds back the call status information of the relative's terminal to the user's smartwatch APP via the Internet. If it is determined that the call status of the relative's terminal is the same as that of the user, that is, they are in a call state, the number of the call object is the same as the user's number, and the application in the call is the same as the user's application name, then it is determined that the terminal the user is calling is the relative's own terminal; if not, it is determined that the terminal the user is calling is not the relative's own terminal. Additionally, if the smart peripheral is connected to the relative's terminal, it can be directly determined that it is a call from the relative's own device.

[0120] Step S051: Adopt anti-fraud means for non-relative's own device.

[0121] Specifically, when it is determined that the call is not from the user's relative's own device but from the relative's own number, a verification code temporarily input by the user can be sent to the other party's phone number through the 5G data channel, and the other party is required to orally state the verification code. Or there is a pre-set key in the newly added family module, and a family key window is sent to the terminal of the other party's number, and the other party is required to input the key. If the verification code or key verification cannot be completed, the user is reminded that the identity of the other party cannot be verified and it may be a spoofed number fraud; and the call time of this call is recorded next, and at the same time, the relative is notified from the APP that the user may have encountered spoofed number fraud, and the user is cared for.

[0122] Step S052: Adopt anti-fraud means for relative's own device.

[0123] Specifically, when it is determined that the call is from the user's relative's own device, there are the following two identification methods: automatic identification and manual assisted identification.

[0124] If it is a call from the relative's own device, instructions are sent to each other through the networked APP. The APP on the relative's terminal receives the instruction and calls the recorder and camera of the relative's own device or its smart wearable or smart home to collect secondary information (voiceprint and portrait), and transmits it back to the user's APP through the network. The secondary collected information is compared with the information reserved in the family module to determine whether the smartwatch worn by the user uses voice broadcast or the call interface to prompt the user to verify that the call recipient is not a non-relative, and this call will be immediately interrupted. If it is determined to be a relative, no processing is done. (Belongs to automatic identification)

[0125] If a local call is made, it is also possible. First, when it is determined that the intelligent peripheral and the other party's terminal are in a connected state, combined with the positioning obtained by the intelligent peripheral APP, it is judged. If the other party's relative's local machine is in a connected state with a certain intelligent peripheral and the GPS address of the intelligent peripheral or the network IP address of the terminal and the peripheral or the hotspot name, etc., and the user is in a familiar and determinable state by the relatives, it can be directly determined that it is the relative himself. If the other party's relative's certain intelligent peripheral is not in a connected state as transmitted by the peer APP, and the user APP has been paired and connected with the intelligent device before, only by connecting to the network, the user APP can also send instructions to the corresponding relative-end intelligent peripheral (such as a home camera, a Bluetooth watch) to take pictures, and can adjust the shooting angle to capture the unique features of the relative (such as scars on the hand, birthmarks on the arm or ornaments on the chest, etc.) or large household items and landmark buildings in the nearby environment, etc., for the user to manually identify that the other party is the relative himself, so as to carefully handle this call.

[0126] (Belongs to manual identification).

[0127] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases, the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that makes a contribution to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc), and includes several instructions for causing a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in various embodiments of the present invention.

[0128] An embodiment of the present invention also provides a computer-readable storage medium, in which a computer program is stored, and the computer program is configured to execute the steps in any one of the above method embodiments when running.

[0129] In an exemplary embodiment, the above computer-readable storage medium may include, but is not limited to: USB flash drive, read-only memory (abbreviated as ROM), random access memory (abbreviated as RAM), mobile hard disk, magnetic disk or optical disc, etc., various media that can store computer programs.

[0130] An embodiment of the present invention also provides an electronic device, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0131] In an exemplary embodiment, the above electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the above processor, and the input / output device is connected to the above processor.

[0132] Specific examples in this embodiment may refer to the examples described in the above embodiments and exemplary embodiments, and will not be repeated here.

[0133] Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the present invention can be implemented by a general-purpose computing device. They can be concentrated on a single computing device or distributed on a network composed of multiple computing devices. They can be implemented by program codes executable by the computing device. Thus, they can be stored in a storage device and executed by the computing device. And in some cases, the steps shown or described can be executed in a different order from here, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module to implement. In this way, the present invention is not limited to any specific combination of hardware and software.

[0134] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A call object recognition method, characterized in that, it includes: The first terminal collects the first feature information of the call object that is having a call with it, and determines whether the call object is the target object according to the first feature information; When it is determined that the call object is the target object, a first instruction is sent to the second terminal associated with the target object, where the first instruction is used to obtain the call status information of the second terminal; Determine whether the current call terminal having a call with the first terminal is the second terminal according to the obtained call status information of the second terminal.

2. The method according to claim 1, characterized in that, after determining whether the current call terminal having a call with the first terminal is the second terminal according to the obtained call status information of the second terminal, it further includes: When it is determined that the current call terminal is the second terminal, a second instruction is sent to the second terminal, where the second instruction is used to instruct the second terminal to collect second feature information and feedback it to the first terminal; Determine whether the current user of the second terminal is the target object according to the feedback second feature information.

3. The method according to claim 1, characterized in that, after determining whether the current call terminal having a call with the first terminal is the second terminal according to the obtained call status information of the second terminal, it further includes: When it is determined that the current call terminal is the second terminal, a third instruction is sent to the third terminal associated with the target object through the second terminal, where the third terminal is a device paired and successfully connected with the second terminal, and the third instruction is used to instruct the third terminal to collect second feature information and feedback it to the first terminal; Determine whether the current user of the second terminal is the target object according to the feedback second feature information.

4. The method according to claim 1, characterized in that, determining whether the call object is the target object according to the obtained first feature information includes: Comparing the first feature information with the pre-stored feature data of the target object to determine whether the call object is the target object, where the first feature information at least includes one of the following: the mobile phone number of the call object, the image information of the call object, the voiceprint information of the call object; the feature data at least includes one of the following: the appearance feature data of the target object, the voiceprint feature data, the mobile phone number associated with the target object.

5. The method according to claim 4, characterized in that, comparing the first feature information with the pre-stored feature data of the target object to determine whether the call object is the target object includes one of the following: In the case of a video call for the current call, comparing the collected image information of the call object and / or the voiceprint information of the call object with the appearance feature data and / or the voiceprint feature data in the pre-stored feature data of the target object to determine whether the call object is the target object; When the current call is a voice call, compare the collected mobile phone number of the call object and / or the voiceprint information of the call object with the mobile phone number and / or the voiceprint feature data in the pre-stored feature data of the target object to determine whether the call object is the target object.

6. The method according to claim 1, wherein, determining whether the current call terminal communicating with the first terminal is the second terminal according to the obtained call status information of the second terminal includes: determining whether the current call terminal is the second terminal according to whether the obtained call status information of the second terminal is consistent with the call status information of the current call terminal communicating with the first terminal, wherein the call status information of the second terminal includes the machine factory identity identifier of the second terminal; when the current call is a video call, the call status information of the second terminal further includes one of the following: call connection status, application in call; when the current call is a voice call, the call status information of the second terminal further includes one of the following: call connection status, mobile phone number of the current call object of the second terminal.

7. The method according to claim 6, wherein, further includes: when the machine factory identity identifier of the second terminal is inconsistent with the current call status and the remaining call status information of the second terminal is consistent with the current call status, send verification information to the mobile phone number of the target object, and determine whether the call object is the target object again according to the feedback information of the target object's mobile phone number based on the verification information.

8. The method according to claim 7, wherein, wherein, the verification information includes one of the following: temporary verification code, key window.

9. The method according to claim 7 or 8, wherein, further includes: when it is determined that the call object is not the target object, display a prompt on the first terminal indicating that the current call object is not the target object.

10. The method according to claim 1, wherein, after determining whether the current call terminal communicating with the first terminal is the second terminal according to the obtained call status information of the second terminal, further includes: when it is determined that the current call terminal is the second terminal, determine whether the current user of the second terminal is the target object according to the connection status between the second terminal and the fourth terminal associated with the target object, wherein the fourth terminal is a device paired with and successfully connected to the second terminal, and the connection status is obtained through the first instruction.

11. The method according to claim 10, wherein, determining whether the current user of the second terminal is the target object according to the connection status between the second terminal and the fourth terminal associated with the target object includes: When the second terminal and the fourth terminal associated with the target object are in a disconnected state, send a fourth instruction to the second terminal, where the fourth instruction is used to instruct the second terminal to collect second feature information and feedback it to the first terminal; Determine whether the current user of the second terminal is the target object according to the feedback second feature information.

12. The method according to any one of claims 2, 3, and 11, characterized in that the second feature information at least includes one of the following: image information, voiceprint information, and surrounding environment information of the current user of the second terminal.

13. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, where when the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 12 are implemented.

14. An electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that when the processor executes the computer program, the steps of the method described in any one of claims 1 to 12 are implemented.

Images