Information processing method

Abstract

The invention discloses an information processing method, which is applied to the technical field of communication. The method comprises the steps that under the condition that a video call is carried out with a calling user, first audio information in the video call process is acquired, and the first audio information comprises a first fraud-related keyword; sending call information to an anti-fraud server, wherein the call information is used by the anti-fraud server to verify whether the calling user is a preset user; receiving early warning information sent by the 5G message server, wherein the early warning information comprises early warning text information used for representing the risk degree of the video call with the calling user; and displaying the early warning text information on the first 5G call interface. According to the method, the video call can be determined to be a suspected fraud call with suspected face change and sound change, and the called user is reminded, so that the risk that the called user encounters fraud is reduced.

Description

Technical Field

[0001] The present application belongs to the field of communication technology, and in particular, relates to an information processing method. Background Art

[0002] The fifth generation mobile communication technology (5G) service not only provides video call services to users, but also provides fun call services. Fun call services include face-changing services and voice-changing services.

[0003] However, criminals may take advantage of the fun call service of 5G services to change faces and voices, replacing the calling user's profile picture and voice with the profile picture and voice of the called user's relatives and friends, making it difficult for the called user to distinguish the authenticity of the calling user's identity, increasing the risk of the called user being defrauded. Summary of the invention

[0004] The embodiments of the present application provide an information processing method, apparatus, device, storage medium and program product, which can determine that a video call is a suspected fraud call with suspected face and voice changes, and send a reminder to the called user to reduce the risk of the called user being defrauded.

[0005] In a first aspect, an embodiment of the present application provides an information processing method, which is applied to a first electronic device. The information processing method includes:

[0006] In case of a video call with a calling user, obtaining first audio information during the video call;

[0007] In the case where the first audio information includes the first fraud-related keyword, sending call information to the anti-fraud server, the call information is used by the anti-fraud server to verify whether the calling user is the preset user, and the call information includes image information of the first 5G call interface during the video call with the calling user and second audio information;

[0008] Receive warning information sent by the 5G message server, including warning text information used to characterize the risk level of making a video call with the calling user. The warning information is determined by the 5G message server based on the policy information provided by the anti-fraud server. The policy information is determined by the anti-fraud server based on the verification result that the calling user is the preset user and the feedback information provided by the verification feedback user. The verification feedback user is determined based on the identity information of the preset user;

[0009] The warning text message is displayed on the first 5G call interface.

[0010] In a second aspect, an embodiment of the present application provides an information processing method, which is applied to an anti-fraud service end. The information processing method includes:

[0011] In the case of receiving call information sent by the first electronic device, verifying whether the calling user is a preset user according to the call information, the call information including image information and second audio information of a first 5G call interface during a video call between the first electronic device and the calling user, the call information being obtained by the first electronic device when determining that the first audio information during the video call with the calling user includes a first fraud-related keyword;

[0012] In the case where the target verification result is used to characterize that the calling user is a preset user, the policy information is determined according to the feedback information provided by the verification feedback user, and the verification feedback user is determined according to the identity information of the preset user;

[0013] Policy information is sent to the 5G message server. The policy information is used by the 5G message server to determine whether to send warning information to the first electronic device. The warning information includes warning text information used to characterize the risk level of making a video call with the calling user. The warning text information is displayed in the first 5G call interface.

[0014] In a third aspect, an embodiment of the present application provides an information processing device, the information processing device comprising:

[0015] A first acquisition module is used to acquire first audio information during a video call with a calling user;

[0016] A first sending module is used to send call information to the anti-fraud server when the first audio information includes the first fraud-related keyword, the call information is used by the anti-fraud server to verify whether the calling user is a preset user, and the call information includes image information of the first 5G call interface during the video call with the calling user and second audio information;

[0017] A first receiving module is used to receive warning information sent by the 5G message server, where the warning information includes warning text information used to characterize the risk level of making a video call with the calling user. The warning information is determined by the 5G message server based on the policy information provided by the anti-fraud server. The policy information is determined by the anti-fraud server based on the verification result that the calling user is a preset user and the feedback information provided by the verification feedback user. The verification feedback user is determined based on the identity information of the preset user;

[0018] The first display module is used to display warning text information on the first 5G call interface.

[0019] In a fourth aspect, an embodiment of the present application provides an information processing device, the information processing device comprising:

[0020] A first verification module, upon receiving call information sent by the first electronic device, verifies whether the calling user is a preset user according to the call information, wherein the call information includes image information and second audio information of a first 5G call interface during a video call between the first electronic device and the calling user, and the call information is obtained by the first electronic device when it is determined that the first audio information during the video call with the calling user includes a first fraud-related keyword;

[0021] A second determination module is used to determine the policy information according to the feedback information provided by the verification feedback user when the target verification result is used to characterize that the calling user is a preset user, and the verification feedback user is determined according to the identity information of the preset user;

[0022] The third sending module is used to send policy information to the 5G message server. The policy information is used by the 5G message server to determine to send warning information to the first electronic device. The warning information includes warning text information for characterizing the risk level of making a video call with the calling user. The warning text information is displayed in the first 5G call interface.

[0023] In a fifth aspect, an embodiment of the present application provides an electronic device, comprising: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, an information processing method as described in any one of the first and second aspects is implemented.

[0024] In a sixth aspect, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon. When the computer program instructions are executed by a processor, an information processing method as in any one of the first and second aspects is implemented.

[0025] In a seventh aspect, an embodiment of the present application provides a computer program product, which includes a computer program or instructions, and when the computer program or instructions are executed by a processor, an information processing method as described in any one of the first and second aspects is implemented.

[0026] The information processing method, device, equipment, storage medium and program product of the embodiments of the present application can, when determining that the first audio information involves fraud, send call information including image information of the first 5G call interface and the second audio information to the anti-fraud service end, so that the anti-fraud service end can preliminarily verify the identity of the calling user. If the verification result shows that the calling user is a preset user, it means that the calling user may have the possibility of impersonating the preset user. Then, based on the feedback information provided by the verification feedback user, the authenticity of the calling user's identity is further verified. Furthermore, the anti-fraud service end determines the corresponding policy information based on the verification result and the feedback information of the preset user, and the 5G message service end generates warning information based on these policy information, and sends the generated warning information to the first electronic device of the called user. Then, the warning text information is displayed on the first 5G call interface, and the warning text information can show the called user the risk level of the video call and remind the called user to be careful to prevent fraud. In this way, by utilizing the communication between the first electronic device, the anti-fraud service end, the 5G message service end and the preset user, it is possible to identify whether there is a suspected fraud call with suspected face or voice changing in the video call, and when it is determined that the video call is a suspected fraud call with suspected face or voice changing, a reminder is sent to the called user to reduce the risk of the called user being defrauded. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0028] Figure 1 A schematic diagram showing a flow chart of an information processing method provided by some embodiments of the present application being applied to a first electronic device;

[0029] Figure 2 A schematic diagram showing a flow chart of a method for acquiring call information in an information processing method provided in some embodiments of the present application;

[0030] Figure 3 A schematic diagram showing a flow chart of a method for sending call record information to an anti-fraud service end in an information processing method provided in some embodiments of the present application;

[0031] Figure 4 A schematic diagram showing a flow chart of an information processing method provided in some embodiments of the present application applied to an anti-fraud server;

[0032] Figure 5 A schematic diagram showing a flow chart of a method for determining a preset user in an information processing method provided in some embodiments of the present application;

[0033] Figure 6A flowchart showing a specific implementation of step 410 provided in some embodiments of the present application is shown;

[0034] Figure 7 A schematic diagram showing a flow chart of a method for generating and sending prompt information in an information processing method provided in some embodiments of the present application;

[0035] Figure 8 An interface display diagram of a second 5G call interface of a second electronic device in an information processing method provided in some embodiments of the present application is shown;

[0036] Fig. 9 A flowchart showing a specific implementation of step 420 provided in some embodiments of the present application is shown;

[0037] Fig.10 A schematic diagram showing a flow chart of applying the information processing method provided by some embodiments of the present application to an information processing system;

[0038] Fig.11 A schematic diagram showing the structure of an information processing device provided by some embodiments of the present application is shown;

[0039] Fig.12 A schematic diagram showing the structure of an information processing device provided by other embodiments of the present application is shown;

[0040] Fig.13 A schematic diagram of the structure of an electronic device provided in some embodiments of the present application is shown. DETAILED DESCRIPTION

[0041] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0042] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "include..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0043] It should be noted that the acquisition, storage, use and processing of data in the embodiments of the present application are in compliance with the relevant provisions of national laws and regulations.

[0044] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0045] Before explaining the technical solutions provided by the embodiments of the present application, in order to facilitate the understanding of the embodiments of the present application, the present application first specifically describes the related technologies involved.

[0046] Fun calls include face-changing services and voice-changing services. Face-changing services refer to the use of artificial intelligence (AI) technology to change the faces of users in video calls, allowing users in video calls to use different facial features or images for video calls. Voice-changing services refer to the use of AI technology to change the voices of users in video calls, allowing users in video calls to use different voices for video calls. Although the application of face-changing services and voice-changing services increases the fun of video calls, there are also potential hazards. For example, criminals can use face-changing services and voice-changing services to pretend to be the relatives or friends of the called user and make a video call with the called user, making it difficult for the called user to distinguish the authenticity of the calling user's identity, increasing the risk of the called user being defrauded.

[0047] In order to solve the above-mentioned problems in the related art, the embodiments of the present application provide an information processing method, device, equipment, storage medium and program product. Figure 1 To Attachment Fig.10 , the information processing method provided by the embodiment of the present application is described in detail through specific embodiments and their application scenarios.

[0048] Figure 1 FIG. 1 is a flow chart showing an information processing method provided by some embodiments of the present application. Figure 1 As shown, the information processing method is applied to a first electronic device, the first electronic device refers to a device that executes the information processing method, including but not limited to a mobile phone, a tablet computer, a laptop computer, a PDA, a vehicle-mounted electronic device, a mobile Internet device (Mobile Internet Device, MID), and the embodiment of the present application is not specifically limited, and the called user makes a video call through the first electronic device. The information processing method may include steps 110 to 140.

[0049] Step 110: When making a video call with a calling user, obtain first audio information during the video call.

[0050] Step 120, when the first audio information includes the first fraud-related keyword, a call information is sent to the anti-fraud server. The call information is used by the anti-fraud server to verify whether the calling user is a preset user. The call information includes image information of the first 5G call interface and the second audio information during the video call with the calling user.

[0051] Step 130, receiving the warning information sent by the 5G message server, the warning information includes warning text information used to characterize the risk level of making a video call with the calling user, the warning information is determined by the 5G message server based on the policy information provided by the anti-fraud server, the policy information is determined by the anti-fraud server based on the verification result that the calling user is a preset user and the feedback information provided by the verification feedback user, and the verification feedback user is determined based on the identity information of the preset user.

[0052] Step 140: Display a warning text message on the first 5G call interface.

[0053] Thus, when the called user makes a video call with the calling user, the first electronic device first processes the first audio information during the video call, identifies whether the first audio information includes the preset first fraud-related keyword, and implements a preliminary risk screening of the calling user. Secondly, when it is determined that the first audio information is fraudulent, the call information including the image information of the first 5G call interface and the second audio information is sent to the anti-fraud service end, so that the anti-fraud service end uses image recognition and sound comparison technology to preliminarily verify the identity of the calling user. If the verification result shows that the calling user is the preset user, it means that the calling user may have the possibility of impersonating the preset user. Then, the feedback information provided by the verification feedback user is used to further verify the authenticity of the calling user's identity. Subsequently, the anti-fraud service end determines the corresponding strategy information based on the verification result and the feedback information of the preset user, and the 5G message service end generates warning information based on these strategy information, and sends the generated warning information to the first electronic device of the called user. Then, the warning text information is displayed on the first 5G call interface, and the warning text information can show the risk level of the video call to the called user, reminding the called user to pay attention to preventing fraud. In this way, by utilizing the communication between the first electronic device, the anti-fraud service end, the 5G message service end and the preset user, it is possible to identify whether there is a suspected fraud call with suspected face or voice changing in the video call, and when it is determined that the video call is a suspected fraud call with suspected face or voice changing, a reminder is sent to the called user to reduce the risk of the called user being defrauded.

[0054] The above steps are described in detail below, as shown below.

[0055] First, with respect to S110, in the embodiment of the present application, the calling user refers to the party that actively initiates the video call, that is, the party that makes the video call with the called user. The first audio information refers to the audio data captured from the calling parties or the calling user during the video call.

[0056] In some embodiments of the present application, in order to ensure the security of the call content, obtaining the first audio information during the video call in the above step 110 may specifically include obtaining the first audio information during the video call when the first electronic device includes configuration information that the called user authorizes the first electronic device to collect call information of the first 5G call interface.

[0057] Exemplarily, the first audio information can be obtained by capturing audio data in a video call through a microphone of the first electronic device.

[0058] In one example, before the video call occurs, the called user can pre-set whether to allow the call content to be analyzed in real time through the setting interface of the first electronic device or the privacy setting part of the 5G call application.

[0059] In another example, during a video call between the called user and the calling user, when the first electronic device detects that real-time analysis of the call content may be required, such as using a specific call function, a dialog box automatically pops up on the first 5G call interface of the first electronic device, asking the called user whether he agrees to real-time analysis of the call content. The called user can choose to agree or refuse according to his own wishes.

[0060] Therefore, with the authorization of the called user, the video call content between the called user and the calling user can be obtained, which can effectively protect the privacy of the called user.

[0061] The first fraud-related keyword is used to determine whether the content of the current video call is fraud-related. The first audio information and the first preset fraud-related keyword pre-stored in the first electronic device can be used to evaluate whether the content of the current call is fraud-related. Based on this, before the above step 120, if Figure 2 As shown, the information processing method may further include steps 210 to 230.

[0062] Step 210: Perform speech recognition on the first audio information to obtain first text information.

[0063] Exemplarily, the speech content in the first audio information is converted into text form using speech recognition technology.

[0064] Step 220: Determine a first fraud-related keyword corresponding to the first text information from a plurality of first preset fraud-related keywords.

[0065] Exemplarily, a plurality of first preset fraud-related keywords can be stored in the fraud-related keyword library of the first electronic device. The fraud-related keyword library can be common fraud words obtained by the anti-fraud server based on statistics, and the anti-fraud server can update the fraud-related keyword library in real time, and synchronize the frequently occurring common fraud words to the fraud-related keyword library on the first electronic device regularly or in real time. In this way, the first electronic device can use a string matching algorithm such as a regular expression, a fuzzy match, etc. to find out whether the first text information includes the first preset fraud-related keyword in the fraud-related keyword library, and then determine the first fraud-related keyword corresponding to the first text information.

[0066] Step 230, when the first fraud-related keyword meets the first preset condition, obtain call information; wherein the first preset condition includes at least one of the following: the number of the first fraud-related keywords within the first preset time period is greater than the preset number, and the number of the first fraud-related keywords within the first preset time period is greater than the preset number.

[0067] The first preset condition is a set of conditions for determining whether the current video call may involve fraud. The call information refers to the complete data during the video call with the calling user, including but not limited to the image information of the first 5G call interface and the second audio information during the video call with the calling user.

[0068] For example, when the first fraud-related keyword corresponding to the first text information meets a certain quantity or frequency condition, the video call is considered to be likely to involve fraud, and the complete call information is obtained for further analysis or processing. For example, if the number of first fraud-related keywords determined within 2 minutes exceeds 3, and the number of repetitions of a first fraud-related keyword exceeds 2 times, it means that the first fraud-related keyword meets the first preset condition.

[0069] Thus, through voice recognition of the first audio information and matching of the first fraud-related keyword with the first text information, the fraud-related risk assessment of the video call content is achieved. Specifically, the first electronic device can automatically identify the first fraud-related keyword that may be involved in fraud during the call, and obtain the call information when the first fraud-related keyword meets the first preset condition, effectively improving the efficiency and accuracy of identifying the fraudulent behavior of the calling user.

[0070] Secondly, step 120 is involved. In the embodiment of the present application, the anti-fraud service end may be a server-side application specifically used to identify fraudulent behavior. The anti-fraud service end can analyze call information and provide risk assessment and warning. The call information includes but is not limited to image information and second audio information during the video call, which is used by the anti-fraud service end to authenticate the calling user. The first 5G call interface refers to a video call interface implemented using 5G technology to provide audio and video call services to the called user. The second audio information may be more complete audio data than the first audio information.

[0071] In some embodiments of the present application, before the aforementioned step 120, as Figure 3 As shown, the information processing method may further include steps 310 to 320.

[0072] Step 310, obtaining call record information of the called user, the call record information including call details information of the user who has had a video call with the called user, the user's reference audio information and the user's reference image information.

[0073] The call details may include the call time, call duration, user communication identification, etc. between the called user and the user. The reference audio information may be the sound data emitted by the called user during the video call with the user. The reference image information may be the image data of the called user during the video call with the user.

[0074] For example, the user's call details can be obtained through an application programming interface provided by the operating system of the first electronic device or directly from the operator of the first electronic device. For the user's reference audio information and reference image information, the recording function needs to be enabled in advance in the application corresponding to the video call and stored locally or in the cloud.

[0075] Step 320, sending call record information to the anti-fraud server, the call record information is used by the anti-fraud server to verify whether the calling user is a preset user, and the preset user is determined according to the user's call details information.

[0076] The preset users refer to a group of users who are considered safe or trustworthy, such as the family members, friends and electronic devices of the family members and friends of the called user.

[0077] For example, the call record information can be encrypted and sent to the anti-fraud server through a network communication protocol. After receiving the call record information, the anti-fraud server can use the call record information to analyze whether the calling user has a fraud risk. For example, by comparing the image information and the second audio information in the call information with the reference audio information in the call record information and the user's reference image information, the identity of the calling user can be identified.

[0078] Therefore, the anti-fraud service end can identify the suspected identity of the calling user by referring to the audio information and the reference image information, and use the suspected identity of the calling user to verify whether the calling user has a fraud risk.

[0079] In some embodiments of the present application, the above step 310 may specifically include that the anti-fraud service terminal proactively initiates a request to the first electronic device of the called user to obtain the call record information of the first electronic device. After receiving the request, the first electronic device will decide whether to provide the call record information to the anti-fraud service terminal according to the privacy settings and authorization of the called user. If the called user has authorized and the privacy settings allow, the first electronic device will transmit the call record information to the anti-fraud service terminal.

[0080] In other embodiments of the present application, the above step 310 may specifically include that the first electronic device automatically retrieves and organizes the historical call record information of the called user regularly, such as every day, every week or every month, and then sends the call record information to the anti-fraud service end.

[0081] Next, step 130 is involved. In an embodiment of the present application, the warning information is generated by the 5G message server based on the policy information sent by the anti-fraud server, and is used to inform the called user of the possible risks of the current video call. Warning text information refers to warning information displayed in text form, which is directly displayed on the first 5G call interface to remind the called user. The policy information is information generated by the anti-fraud server based on the verification results and feedback information provided by the verification feedback user determined based on the identity information of the preset user, such as the preset user himself, the preset user's family, etc. The verification feedback user can be a designated user set by the called user and related to the identity information of the preset user, or it can be a verification feedback user specified by the preset user during the setting process.

[0082] It is understandable that the identity information of the preset user is the personal information provided by the preset user during the registration or setting process, such as name, ID number, mobile phone number, etc. Exemplarily, when the anti-fraud service verifies that the calling user is suspected to be the preset user, the anti-fraud service will determine the verification feedback user such as the preset user himself, family, etc. based on the identity information of the preset user, and send information to the verification feedback user to confirm the accuracy of the verification result. Then, involving step 140, in an embodiment of the present application, the warning text information can be presented in a variety of forms, including but not limited to warning pop-ups, SMS notifications, and application push. For example, directly displaying the warning text information in the form of a warning pop-up window on the first 5G call interface of the first electronic device can effectively remind the called user to pay attention to the call risk.

[0083] Next, the above steps will be further described in detail by assuming that the called user is Zhang San and the calling user is Li Si.

[0084] Suppose Zhang San is using his smartphone to make a 5G video call with his "friend" Li Si. During the video call, Zhang San's smartphone captured the audio information during the video call and identified fraud-related keywords. As a result, Zhang San's smartphone automatically obtains the call information with Li Si, such as screenshots and audio data of the video call interface, and sends the call information to the anti-fraud server for verification. The anti-fraud server determines that Li Si is not Zhang San's real friend through the list of preset users and the feedback information of his friend Li Si, but may be an illegal element who impersonates Li Si. Based on this, the anti-fraud server generates corresponding strategy information and sends an early warning message to Zhang San's smartphone through the 5G message server, informing Zhang San that there is a risk in the current call. After receiving the early warning message, Zhang San's smartphone immediately displays the early warning text message on the 5G call interface of the smartphone, such as "Attention! There is a risk of fraud in the current call, please communicate with caution!" In this way, Zhang San can immediately realize the problem and take corresponding preventive measures to avoid economic losses.

[0085] It is worth noting here that in the embodiments of the present application, the description of each embodiment has its own focus. For the parts that are not described in detail in a certain embodiment, please refer to the detailed description of the information processing method in the context, and will not be repeated here.

[0086] In some embodiments of the present application, the information processing method can be applied to an anti-fraud service end. Figure 4 As shown, the information processing method provided in the embodiment of the present application may include steps 410 to 430.

[0087] Step 410, upon receiving call information sent by the first electronic device, verify whether the calling user is a preset user based on the call information, the call information including image information and second audio information of a first 5G call interface during a video call between the first electronic device and the calling user, the call information is obtained by the first electronic device when it is determined that the first audio information during the video call with the calling user includes a first fraud-related keyword.

[0088] Step 420, when the target verification result is used to characterize that the calling user is a preset user, determine the policy information according to the feedback information provided by the verification feedback user, and the verification feedback user is determined according to the identity information of the preset user.

[0089] Step 430: Send policy information to the 5G message server. The policy information is used by the 5G message server to determine whether to send warning information to the first electronic device. The warning information includes warning text information that characterizes the risk level of making a video call with the calling user. The warning text information is displayed in the first 5G call interface.

[0090] Therefore, after receiving the call information sent by the first electronic device when it detects that the video call includes fraud-related keywords, the anti-fraud service end can use the dual information of image and audio in the call information to authenticate the identity of the calling user. This multi-dimensional information verification method improves the accuracy of identifying the identity of the calling user. Then, when it is determined that the calling user is a preset user, strategy information is formulated based on the feedback information of the verification feedback user to effectively warn the called user, that is, the 5G message service end can send early warning information to the first electronic device based on the strategy information, and then warn the called user through the early warning text information displayed in the 5G call interface. In this way, the first anti-fraud service end can more accurately determine the identity of the calling user, and can identify potential fraud risks in real time, effectively reducing the possibility of users being defrauded.

[0091] In some embodiments of the present application, in order to implement identity authentication of the calling user, before the aforementioned step 410, it is necessary to determine the information of the preset user associated with the called user. Figure 5As shown, the information processing method may further include steps 510 to 520.

[0092] Step 510, receiving call record information of the called user sent by the first electronic device, the call record information including call details information of the user who has had a video call with the called user, the user's reference audio information and the user's reference image information.

[0093] Step 520, based on the call details information, determine the user who meets the second preset condition as the preset user, the second preset condition includes at least one of the following: the call duration is greater than the preset duration, the number of calls is greater than the preset number, the call interval is greater than the preset duration, there are a preset number of common users between the called user and the user, and the called user and the user belong to the same group communication service participants.

[0094] Exemplarily, taking the call duration being greater than the preset duration as an example, a user whose total call minutes with the called user within a year exceed 60 minutes is determined as a preset user; taking the number of calls being greater than the preset number as an example, a user whose number of calls with the called user within a year is greater than 10 times is determined as a preset user; taking the call interval being greater than the preset duration as an example, a user whose earliest call record with the called user was one year ago is determined as a preset user; taking the existence of a preset number of common users between the called user and the user as an example, if there are at least 3 common users between the called user and the user, the user is determined as a preset user; taking the called user and the user as participants of the same group communication service as an example, a user who is in the same home network service and the same short number service as the called user is determined as a preset user.

[0095] Therefore, by setting a second preset condition such as call duration, number of times, interval, common users, group communication services, etc., users who have close, long-term and frequent contact with the called user can be screened out. These preset users may be relatives, friends or important contacts of the called user, so that the anti-fraud service end can realize identity authentication of the calling user based on these preset users.

[0096] In some embodiments of the present application, after determining the preset user, the anti-fraud service end can establish a mapping relationship between the preset user's communication identifier and the reference audio information and reference image information based on the preset user, the preset user's reference audio information, and the preset user's reference image information, so as to construct a database of relatives and friends of the called user. In this way, during the subsequent call process of the called user, the anti-fraud service end can quickly compare and verify the identity of the calling user through the database of relatives and friends, so as to quickly identify the identity of the calling user by comparing the calling user's voice, head portrait and other biometric information.

[0097] It is worth noting that the friends and relatives database information can be updated periodically, such as storing the latest 30 minutes of call information. For the stored information, different time points can be selectively retained, such as storing 10 minutes of call information from 3 months, 6 months, and 1 year ago. This not only ensures the timeliness of the data in the friends and relatives database information, but also reduces the storage pressure on the anti-fraud service end. At the same time, data retention strategies for different time periods help improve the accuracy of fraud identification. The friends and relatives database information also allows the called user to maintain the information in the friends and relatives database by himself, including adding and deleting the preset user's communication identification, reference audio information, reference image information, etc., to increase the called user's participation and control.

[0098] In some embodiments of the present application, Figure 6 As shown, the above step 410 may specifically include steps 4101 to 4103.

[0099] Step 4101, based on the voiceprint feature in the second audio information and the reference voiceprint feature in the reference audio information of the preset user, calculate a first similarity value between the voiceprint feature and the reference voiceprint feature.

[0100] The voiceprint feature refers to a feature obtained by analyzing the sound signal that can uniquely or approximately uniquely identify the identity of the calling user, such as fundamental frequency, resonance peak, spectrum envelope, etc. The reference voiceprint feature refers to a feature obtained by analyzing the sound signal that can uniquely or approximately uniquely identify the identity of the preset user. The first similarity value refers to a quantitative value of the similarity between the voiceprint feature of the calling user and the reference voiceprint feature of the preset user.

[0101] For example, the voiceprint features in the second audio information can be extracted by voiceprint recognition technology and compared with the reference voiceprint features of the preset user. The comparison process can involve matching of feature vectors, distance calculation such as Euclidean distance, cosine similarity, etc.

[0102] Step 4102, based on the facial features in the image information and the reference facial features in the reference image information of the preset user, calculate a second similarity value between the facial features and the reference facial features.

[0103] The facial features refer to information extracted from the video call image by image recognition technology that can describe the facial features of the calling user, such as the position of the facial features, face shape, etc. The reference facial features refer to the facial features of the preset user. The second similarity value refers to a quantitative value of the similarity between the facial features of the calling user in the current call and the reference facial features of the preset user.

[0104] Exemplarily, the image information includes a plurality of video frames, and the reference facial features include facial features and face shape features. The above step 4102 may specifically include steps 41021 to 41023.

[0105] Step 41021, image information preprocessing. First, through facial recognition technology, video frames with frontal orientation and including human faces are screened out from multiple video frames. Then, for these video frames, a deep learning model is used to crop the face area to obtain a face image, and then the face image is input into a pre-trained image segmentation model to extract the facial features and face shape in the face image. At the same time, for the portrait image of the preset user's reference image information, the same preprocessing process is also performed to obtain the corresponding reference facial features and reference face shape.

[0106] Step 41022, similarity evaluation. In order to quantify the similarity between the facial features in the image information and the reference facial features in the reference image information, two hash algorithms such as mean hash for face shape and perceptual hash for facial features can be used to calculate the second similarity value. Specifically, for the face shape cutout and facial features cutout obtained based on the image information, their mean hash values ​​and perceptual hash values ​​are calculated respectively. Correspondingly, for the reference facial features cutout and reference face shape cutout of the reference image information, their reference mean hash values ​​and reference perceptual hash values ​​are also calculated respectively. Subsequently, the mean hash value and perceptual hash value are compared with the reference mean hash value and reference perceptual hash value corresponding to each reference image information, and the face shape similarity S1 and facial features similarity S2 between the facial features and the reference facial features are evaluated by calculating the distance between the hash values.

[0107] Step 41023, calculate the second similarity value. Perform weighted sum processing on the face shape similarity S1 and the facial features similarity S2. Taking the weight of the face shape similarity S1 as a1 and the weight of the facial features similarity S2 as a2 as an example, the second similarity value S can be obtained by the following formula (1).

[0108] S=a1×S1+a2×S2…(1)

[0109] In the formula, a1+a2=1.

[0110] The specific values ​​of weights a1 and a2 may be based on industry experience, user feedback, or the results of large-scale model training to ensure the accuracy and rationality of the final similarity evaluation.

[0111] Therefore, through sophisticated cutout and hash matching technology, in-depth analysis and comparison of facial features are achieved, improving the accuracy of calling user identity authentication.

[0112] Step 4103, when at least one of the following conditions is met, the verification result of whether the calling user is a preset user is determined as the target verification result, and at least one of the following conditions is met: the first similarity is greater than or equal to the first similarity threshold, and the second similarity is greater than or equal to the second similarity threshold.

[0113] Among them, the first similarity threshold and the second similarity threshold are respectively used to determine whether the similarity between the voiceprint feature and the facial feature is high enough, so as to determine whether the calling user is the preset user.

[0114] In some embodiments of the present application, the preset user includes multiple preset users, the reference audio information of the preset user includes reference audio information of each preset user in the multiple preset users, and the reference image information of the preset user includes reference image information of each preset user in the multiple preset users.

[0115] Therefore, through voiceprint feature comparison and facial feature comparison, the accuracy of the identity authentication of the calling user in the video call is achieved. When the voiceprint or facial features of the calling user are highly similar to the reference features of the preset user, the anti-fraud server can accurately identify and make corresponding processing such as sending early warning information to the preset user who has successfully matched, which effectively improves the effectiveness and accuracy of the early warning information.

[0116] In some embodiments of the present application, after verifying whether the calling user is a preset user based on the call information and obtaining the verification result, the anti-fraud service end may also send a push notification including the verification result to the first electronic device. The push notification may include the verification result, instructions for the called user to operate, such as "Please confirm the identity of the other party", and a list of verification feedback users that the called user can select. After receiving the push notification, the called user can interact through the user interface of the first electronic device and manually select the verification feedback user, that is, the real preset user, from the verification feedback user list. After receiving the response operation of the second electronic device of the verification feedback user based on the push notification, the anti-fraud service end can adjust the verification result based on the response operation.

[0117] In some embodiments of the present application, before the above step 420, as Figure 7 As shown, the information processing method may further include steps 610 to 640.

[0118] Step 610: Generate a second text message based on the second fraud-related keyword in the call information.

[0119] The second fraud-related keyword refers to a keyword or phrase related to fraud contained in the call information, such as borrowing money, remittance, etc. The second text information refers to text information generated based on the second fraud-related keyword in the call information, which is used to provide reminders about call risks to the verification feedback user.

[0120] Exemplarily, speech recognition technology can be used to convert the speech content in the second audio information into a third text message. Then, the second fraud-related keyword corresponding to the third text message is determined from a plurality of second preset fraud-related keywords. Among them, the plurality of second preset fraud-related keywords can be a fraud-related keyword library pre-stored in the anti-fraud server. After determining the second fraud-related keyword, the second fraud-related keyword can be converted into a brief second text message through natural language processing technology. Taking the second fraud-related keywords as "accident" and "remittance" as examples, Figure 8 As shown, the generated second text message may be "Requesting XX user to remit money due to an accident", wherein XX user is the called user.

[0121] Step 620: Generate prompt information according to the second text information and display configuration information corresponding to the preset user, where the display configuration information includes a display status of the second text information on the second electronic device of the verification feedback user.

[0122] The display configuration information refers to configuration information about how the second text information is displayed on the second electronic device of the preset user, including but not limited to font size, color, position, brightness, display duration, etc. The prompt information refers to specific information generated by combining the second text information and the display configuration information.

[0123] Exemplarily, the display configuration information can be determined based on the personal characteristic data of the preset user, such as age, gender, preference, etc. For example, when the preset user is over 50 years old, the default text size is modified according to the preset rule, such as increasing by 50%. In this way, the font size is automatically adjusted according to the personal characteristic data of the preset user to adapt to the vision requirements of users of different age groups, thereby improving the readability of the call interface and the comfort of the user, especially for the older preset users, the enlarged font can reduce the reading difficulty of the preset users.

[0124] Step 630, sending a prompt message to the 5G message server, the prompt message is used by the 5G message server to generate an inquiry message, the inquiry message is used to verify the feedback user to determine whether the calling user is the preset user, and the inquiry message is displayed in the second 5G call interface of the second electronic device.

[0125] Among them, the inquiry information is generated by the 5G message server based on the prompt information, and is used to ask the verification feedback user whether to confirm that the calling user is the preset user.

[0126] Exemplarily, the prompt information is sent to the 5G message server, which generates query information including basic prompt text and its specific text format according to preset rules and the prompt information, and assembles interactive pop-up information based on the query information. Subsequently, the 5G message server can send the pop-up information to the second electronic device via the 5G network. Figure 8 As shown, when the second electronic device receives this pop-up message, a pop-up window corresponding to the pop-up information is displayed in the second 5G call interface of the second electronic device, so that the verification feedback user can not only intuitively see the inquiry information displayed in the form of a pop-up window, but also directly respond to the inquiry information by clicking operation buttons such as "Yes" and "No" in the pop-up window.

[0127] Step 640: receiving feedback information based on the inquiry information sent by the second electronic device.

[0128] The feedback information refers to the reply information given by the verification feedback user, ie, the user of the second electronic device, based on the judgment after receiving the inquiry information, and is used to confirm or deny whether the current calling user is the preset user.

[0129] Referring to the above example, feedback information from the second electronic device is received and parsed, and the feedback is generated based on the inquiry information sent to the verification feedback user. The feedback information directly reflects the verification feedback user, that is, the user of the second electronic device,'s attitude of confirming or denying the identity of the calling user. Specifically, the verification feedback user expresses his or her attitude of confirming or denying the identity of the calling user through preset operations such as clicking a "yes" or "no" button, and sends the feedback information to the anti-fraud server, so that the anti-fraud server transmits the feedback information to the first electronic device of the called user through the 5G message server.

[0130] Thus, by sending inquiry information to the verification feedback user and receiving feedback information from the verification feedback user, the identity of the calling user is directly verified. The anti-fraud server can more accurately determine whether there is a fraud risk in the current video call process. At the same time, through the flexible configuration of the display configuration information, the anti-fraud server can adjust the display method of the prompt information according to different situations to adapt to the needs and preferences of different verification feedback users.

[0131] In some embodiments of the present application, the policy information refers to the instructions or rules for warning information formulated by the anti-fraud service end based on the call information and feedback information, including but not limited to the display method and sending time of the warning information. The policy information may include a target warning information display policy. The target warning information display policy is used to specify the display method of the warning information on the first electronic device, including but not limited to the display position, display duration, display style, etc. Based on this, if Fig. 9 As shown, the above step 420 may specifically include step 4201 and step 4202.

[0132] Step 4201: Determine, based on the feedback information, a target risk level corresponding to the feedback information from a plurality of preset risk levels.

[0133] The multiple preset risk levels refer to different levels of risk classification preset in the anti-fraud service end, which are used to indicate the possibility that the calling user is determined to be a fraud suspect, and may include multiple levels such as low, medium, and high. The target risk level refers to the specific risk level related to the current calling user determined from the multiple preset risk levels based on the feedback information.

[0134] Step 4202, determining a target warning information display strategy associated with a target risk level according to association information between a preset risk level and a preset warning information display strategy.

[0135] Referring to the above example, the feedback information may include a verification feedback user's response to an inquiry or verification request issued by the anti-fraud server, including an explicit denial such as clicking "No", a lack of contact such as no response within a preset time window, etc.

[0136] If the verification feedback user explicitly denies it, such as clicking "No", the feedback information directly indicates that there is a suspicion that the calling user is impersonating the preset user in the current video call, and the corresponding target risk level is high. The anti-fraud server sends a high-level anti-fraud reminder to the called user based on the target risk level to warn the called user of potential risks.

[0137] If the verification feedback user does not respond within the preset time window, it is considered as "no contact" and the corresponding target risk level is high, which is also sent to the anti-fraud server as feedback information. The anti-fraud server sends a medium anti-fraud reminder to the called user to remind the called user to be cautious about the current call and consider further verifying the identity of the calling user.

[0138] Therefore, the anti-fraud service end can evaluate the risk level of the calling user by real-time monitoring of call information and feedback information, and provide personalized warning information to the called user according to the target risk level and the preset warning information display strategy to increase the user's vigilance. In this way, by directly displaying the warning text information on the first 5G message interface and reminding users of potential risks, the risk of users being defrauded can be reduced.

[0139] In some embodiments of the present application, the feedback information includes the first feedback information or the second feedback information, the first feedback information includes the second electronic device receiving the response operation of the verification feedback user to the inquiry information, and the response operation indicates that the identity of the calling user is not a preset user, and the second feedback information includes the second electronic device not receiving the response operation of the verification feedback user to the inquiry information within a second preset time period. The target risk level includes the first risk level corresponding to the first feedback information or the second risk level corresponding to the second feedback information, and the first risk level is higher than the second risk level.

[0140] For example, the first feedback information indicates that the verification feedback user has confirmed that the preset user did not initiate the video call, indicating that the current video call has a high risk of fraud, and therefore corresponds to the first risk level with a higher risk. The second feedback information may be that the verification feedback user did not see, understand, or deliberately ignore the inquiry information, but in either case, it has not been explicitly denied by the verification feedback user, indicating that the current video call has a certain risk of fraud, which is lower than the risk of the first feedback information, and therefore corresponds to the second risk level with a lower risk.

[0141] The target warning information display strategy includes a first strategy corresponding to a first risk level or a second strategy corresponding to a second risk level, the first strategy includes first prompt text information and a first display state of the first prompt text information, the second strategy includes second prompt text information and a second display state of the second prompt text information, the warning level of the first prompt text information is higher than the warning level of the second prompt text information, and the warning level of the first display state is higher than the warning level of the second display state.

[0142] For example, the first strategy is a warning information display strategy corresponding to the first risk level. The warning level of the first prompt text information is high, aiming to attract the called user's strong attention; the warning level of the first display state is also high, which may include flashing, highlighting, full-screen display and other effects. The second strategy is a warning information display strategy corresponding to the second risk level. The warning level of the second prompt text information is relatively low, but it will still remind the user to pay attention; the warning level of the second display state is also low, which can be just a simple pop-up window or notification.

[0143] In an embodiment of the present application, the anti-fraud service end first receives feedback information from the verification feedback user to evaluate whether there is a fraud risk in the video call of the first electronic device. Then, the anti-fraud service end determines the risk level of the video call according to the specific type of feedback information. Once the risk level is determined, the anti-fraud service end will select a warning information display strategy that matches the risk level. Then, based on the determined warning information display strategy, the anti-fraud service end will send a warning message to the called user through the 5G message end. Taking the warning pop-up window as an example, when the reminder level is "medium", the pop-up window will contain information content to remind the user to pay attention, such as "unconfirmed object, beware of fraud", and display it at a higher brightness for a predetermined time such as 20 seconds to attract the attention of the called user. When the reminder level is "high", in addition to similar reminder content, the pop-up window will also flash in eye-catching colors such as red and yellow, such as flashing once per second, flashing 10 times in a row and pausing for 10 seconds, and repeating this process again, alerting the user to the potential high risk in a more intense way.

[0144] Therefore, by distinguishing the first feedback information from the second feedback information, the anti-fraud service end can more accurately assess the fraud risk of the video call and provide differentiated warning information to the called user according to the different risk levels. In this way, by providing timely and accurate warning information to the called user, the risk of the called user being defrauded can be more effectively reduced, and the user's property and information security can be protected.

[0145] The embodiment of the present application provides an information processing method, which is applied to an information processing system, wherein the information processing system includes a first electronic device, a second electronic device, an anti-fraud server, and a 5G message server. Fig.10 As shown, the information processing method may specifically include steps 701 to 716.

[0146] Step 701: When a first electronic device is making a video call with a calling user, the first electronic device obtains first audio information during the video call.

[0147] Step 702: When the first electronic device determines that the first audio information includes the first fraud-related keyword, the first electronic device obtains call information, where the call information includes image information of the first 5G call interface and second audio information during the video call between the called user and the calling user.

[0148] Step 703: The first electronic device sends call information to the anti-fraud service end.

[0149] Step 704: the anti-fraud service end verifies whether the calling user is the preset user based on the call information.

[0150] Step 705: When the verification result indicates that the calling user is a preset user, the anti-fraud server determines the verification feedback user according to the identity information of the preset user, and generates prompt information according to the call information.

[0151] Step 706: The anti-fraud server sends a prompt message to the 5G message server.

[0152] Step 707, the 5G message server generates inquiry information based on the prompt information.

[0153] Step 708: The 5G message server sends an inquiry message to the second electronic device of the verification feedback user.

[0154] Step 709: The second electronic device displays the inquiry information in the second 5G call interface.

[0155] Step 710: The second electronic device generates feedback information according to the response operation of the verification feedback user to the inquiry information.

[0156] Step 711: The second electronic device sends feedback information to the anti-fraud service end.

[0157] Step 712: The anti-fraud server determines the policy information based on the feedback information.

[0158] Step 713: The anti-fraud server sends policy information to the 5G message server.

[0159] Step 714, the 5G message server generates warning information based on the policy information.

[0160] Step 715, the 5G message server sends a warning message to the first electronic device of the calling user, and the warning message includes a warning text message.

[0161] Step 716: The first electronic device displays a warning text message on the first 5G call interface.

[0162] Thus, when the first electronic device of the called user makes a video call with the calling user, it captures and analyzes the first audio information in the video call in real time. When the first audio information contains a preset fraud-related keyword, call information is further obtained, and the call information includes image information and second audio information of the video call between the called user and the calling user. Secondly, the first electronic device sends the call information to the anti-fraud service end, so that the anti-fraud service end uses the call information to verify whether the identity of the calling user is consistent with the preset user claimed or presented by it. Specifically, the anti-fraud service end sends the prompt information to the 5G message service end, so that the 5G message service end generates the inquiry information according to the prompt information, and sends it to the second electronic device of the verification feedback user through the 5G network. Then, the second electronic device displays the inquiry information in the second 5G call interface, prompting the verification feedback user to confirm the identity of the calling user. The second electronic device generates and sends feedback information to the anti-fraud service end according to the response operation of the verification feedback user to the inquiry information, so that the anti-fraud service end determines the corresponding policy information according to the feedback information such as the confirmation or denial of the verification feedback user. After that, the anti-fraud server sends the policy information to the 5G message server, so that the 5G message server generates specific warning information according to the policy information. Then, the 5G message server sends the specific warning information to the first electronic device, so that the first electronic device displays the warning text information in the first 5G call interface, reminding the called user to pay attention to potential risks, effectively reducing the risk of the called user encountering fraud.

[0163] Based on the information processing method provided in the above embodiments, the present application also provides a specific implementation of the information processing device. Please refer to the following embodiments.

[0164] The information processing method provided in the embodiment of the present application is executed by the information processing device 800, see Fig.11 , the information processing device 800 includes:

[0165] A first acquisition module 810 is used to acquire first audio information during a video call with a calling user;

[0166] A first sending module 820 is used to send call information to the anti-fraud server when the first audio information includes the first fraud-related keyword, the call information is used by the anti-fraud server to verify whether the calling user is a preset user, and the call information includes image information of the first 5G call interface during the video call with the calling user and second audio information;

[0167] The first receiving module 830 is used to receive the warning information sent by the 5G message server, the warning information includes warning text information used to characterize the risk level of making a video call with the calling user, the warning information is determined by the 5G message server based on the policy information provided by the anti-fraud server, the policy information is determined by the anti-fraud server based on the verification result that the calling user is a preset user and the feedback information provided by the verification feedback user, and the verification feedback user is determined according to the identity information of the preset user;

[0168] The first display module 840 is used to display warning text information on the first 5G call interface.

[0169] Thus, the first electronic device uses the first acquisition module 810 to obtain the first audio information, and when determining that the first audio information involves fraud, sends the call information including the image information of the first 5G call interface and the second audio information to the anti-fraud service end through the first sending module 820, so that the anti-fraud service end uses the image recognition and sound comparison technology to preliminarily verify the identity of the calling user. If the verification result shows that the calling user is the preset user, it means that the calling user may have the possibility of impersonating the preset user. Then, the feedback information provided by the verification feedback user is used to further verify the authenticity of the calling user's identity. Subsequently, the anti-fraud service end determines the corresponding policy information based on the verification result and the feedback information of the preset user, and the 5G message service end generates warning information based on these policy information, and sends the generated warning information to the first electronic device of the called user. Then, the warning information is received through the first receiving module 830, and the warning text information is displayed on the first 5G call interface through the first display module 840. The warning text information can show the risk level of the video call to the called user and remind the called user to pay attention to preventing fraud. In this way, by utilizing the communication between the first electronic device, the anti-fraud service end, the 5G message service end and the preset user, it is possible to identify whether there is a suspected fraud call with suspected face or voice changing in the video call, and when it is determined that the video call is a suspected fraud call with suspected face or voice changing, a reminder is sent to the called user to reduce the risk of the called user being defrauded.

[0170] In some embodiments of the present application, the information processing device 800 may further include:

[0171] A first recognition module, used for performing voice recognition on the first audio information to obtain first text information before sending the call information to the anti-fraud service end;

[0172] A first determination module, configured to determine a first fraud-related keyword corresponding to the first text information from a plurality of first preset fraud-related keywords;

[0173] The second acquisition module is used to acquire call information when the first fraud-related keyword meets the first preset condition; wherein the first preset condition includes at least one of the following: the number of the first fraud-related keyword within the first preset time period is greater than the preset number, and the number of times the first fraud-related keyword appears within the first preset time period is greater than the preset number.

[0174] In some embodiments of the present application, the first acquisition module 810 can be specifically used to obtain the first audio information during the video call when the first electronic device includes configuration information that the called user authorizes the first electronic device to collect call information of the first 5G call interface.

[0175] In some embodiments of the present application, the information processing device 800 may further include:

[0176] The third acquisition module is used to obtain the call record information of the called user before sending the call information to the anti-fraud server, the call record information including the call details of the user who has made a video call with the called user, the user's reference audio information and the user's reference image information;

[0177] The second sending module is used to send call record information to the anti-fraud server. The call record information is used by the anti-fraud server to verify whether the calling user is a preset user. The preset user is determined based on the user's call details information.

[0178] The various modules of the information processing device 800 provided in the embodiment of the present application can implement Figure 1 The functions of each step of the information processing method are provided, and the corresponding technical effects can be achieved. For the sake of concise description, they will not be repeated here.

[0179] The information processing method provided in the present embodiment is executed by the information processing device 900, see Fig.12 , the information processing device 900 includes:

[0180] The first verification module 910, upon receiving call information sent by the first electronic device, verifies whether the calling user is a preset user according to the call information, wherein the call information includes image information and second audio information of a first 5G call interface during a video call between the first electronic device and the calling user, and the call information is obtained by the first electronic device when it is determined that the first audio information during the video call with the calling user includes a first fraud-related keyword;

[0181] A second determination module 920 is used to determine policy information according to feedback information provided by a verification feedback user when the target verification result is used to characterize that the calling user is a preset user, and the verification feedback user is determined according to the identity information of the preset user;

[0182] The third sending module 930 is used to send policy information to the 5G message server. The policy information is used by the 5G message server to determine to send warning information to the first electronic device. The warning information includes warning text information for characterizing the risk level of making a video call with the calling user. The warning text information is displayed in the first 5G call interface.

[0183] In some embodiments of the present application, the information processing device 800 may further include:

[0184] A second receiving module is used to receive call record information of the called user sent by the first electronic device before verifying whether the calling user is the target user according to the call information, the call record information including call details information of the user who has had a call with the called user, the user's reference audio information and the user's reference image information;

[0185] The third determination module is used to determine the user who meets the second preset condition as the preset user according to the call details information, and the second preset condition includes at least one of the following: the call duration is greater than the preset duration, the number of calls is greater than the preset number, the call interval is greater than the preset duration, there are a preset number of common users between the called user and the user, and the called user and the user belong to the same group communication service participants.

[0186] In some embodiments of the present application, the first verification module 910 may be specifically used for:

[0187] Calculating a first similarity value between the voiceprint feature and the reference voiceprint feature according to the voiceprint feature in the second audio information and the reference voiceprint feature in the reference audio information of the preset user;

[0188] Calculating a second similarity value between the facial feature and the reference facial feature based on the facial feature in the image information and the reference facial feature in the reference image information of the preset user;

[0189] When at least one of the following conditions is met, the verification result of whether the calling user is a preset user is determined as the target verification result. The following at least one of the following conditions is met: the first similarity is greater than or equal to the first similarity threshold, and the second similarity is greater than or equal to the second similarity threshold.

[0190] In some embodiments of the present application, the information processing device 800 may further include:

[0191] A first generating module is used to generate second text information according to a second fraud-related keyword in the call information before determining the strategy information according to the feedback information provided by the verification feedback user;

[0192] A second generating module, configured to generate prompt information according to the second text information and display configuration information corresponding to a preset user, wherein the display configuration information includes a display state of the second text information on a second electronic device of the verification feedback user;

[0193] A fourth sending module is used to send a prompt message to the 5G message server, the prompt message is used for the 5G message server to generate an inquiry message, the inquiry message is used to verify whether the feedback user determines that the calling user is a preset user, and the inquiry message is displayed in a second 5G call interface of the second electronic device;

[0194] The third receiving module is used to receive feedback information based on the inquiry information sent by the second electronic device.

[0195] In some embodiments of the present application, the strategy information includes a target warning information display strategy; the second determination module 920 is specifically used to determine, based on the feedback information, a target risk level corresponding to the feedback information from multiple preset risk levels; and determine the target warning information display strategy associated with the target risk level based on the association information between the preset risk level and the preset warning information display strategy.

[0196] Each module of the information processing device 900 provided in the embodiment of the present application can realize Figure 1 The functions of each step of the information processing method are provided, and the corresponding technical effects can be achieved. For the sake of concise description, they will not be repeated here.

[0197] Fig.13 A schematic diagram of the hardware structure of an electronic device provided in some embodiments of the present application is shown.

[0198] The electronic device may include a processor 1001 and a memory 1002 storing computer program instructions.

[0199] Specifically, the processor 1001 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0200] The memory 1002 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 1002 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 1002 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 1002 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 1002 is a non-volatile solid-state memory.

[0201] In a particular embodiment, the memory 1002 may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Therefore, generally, the memory 1002 includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the data processing method according to the first aspect of the present application.

[0202] The processor 1001 implements any one of the information processing methods in the above embodiments by reading and executing computer program instructions stored in the memory 1002 .

[0203] In one example, the electronic device may further include a communication interface 1010 and a bus 1003. Fig.13 As shown, the processor 1001, the memory 1002, and the communication interface 1010 are connected via a bus 1003 and communicate with each other.

[0204] The communication interface 1010 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0205] Bus 1003 includes hardware, software or both, and the parts of electronic equipment are coupled to each other.For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In suitable cases, bus 1003 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.

[0206] The electronic device can execute the information processing method in the embodiment of the present application, thereby realizing the combination Figures 1 to 13 Described information processing method and device.

[0207] In addition, in combination with the information processing method in the above embodiment, the embodiment of the present application may provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the information processing methods in the above embodiment is implemented. Examples of computer-readable storage media include non-transitory computer-readable storage media, such as portable disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, etc.

[0208] In addition, in combination with the information processing method in the above embodiment, the embodiment of the present application may provide a computer program product for implementation. The program product is stored in a storage medium, and may specifically include a computer program or instruction, which implements any one of the information processing methods in the above embodiment when executed by a processor. The program product is executed by at least one processor to implement the various processes of the above data processing method embodiment, and can achieve the same technical effect, so it will not be repeated here to avoid repetition.

[0209] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0210] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0211] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0212] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0213] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. An information processing method, characterized in that: Applied to a first electronic device, the method includes: In case of a video call with a calling user, obtaining first audio information during the video call; In the case where the first audio information includes the first fraud-related keyword, sending call information to the anti-fraud server, the call information is used by the anti-fraud server to verify whether the calling user is a preset user, and the call information includes image information of the first 5G call interface during the video call with the calling user and second audio information; Receive warning information sent by the 5G message server, the warning information including warning text information used to characterize the risk level of making a video call with the calling user, the warning information is determined by the 5G message server based on the policy information provided by the anti-fraud server, the policy information is determined by the anti-fraud server based on the verification result that the calling user is the preset user and the feedback information provided by the verification feedback user, the verification feedback user is determined according to the identity information of the preset user; The warning text information is displayed on the first 5G call interface.

2. The method according to claim 1, characterized in that Before sending the call information to the anti-fraud service end, the method further includes: Performing speech recognition on the first audio information to obtain first text information; Determining a first fraud-related keyword corresponding to the first text information from a plurality of first preset fraud-related keywords; When the first fraud-related keyword satisfies a first preset condition, acquiring the call information; Among them, the first preset condition includes at least one of the following: the number of the first fraud-related keywords within the first preset time period is greater than a preset number, and the number of times the first fraud-related keywords appear within the first preset time period is greater than a preset number.

3. The method according to claim 1, characterized in that The obtaining of the first audio information during the video call includes: When the first electronic device includes configuration information in which the called user authorizes the first electronic device to collect call information of the first 5G call interface, the first audio information during the video call is obtained.

4. The method according to claim 1 or 3, characterized in that: Before sending the call information to the anti-fraud service end, the method further includes: Acquire call record information of the called user, the call record information including call details information of a user who has conducted a video call with the called user, reference audio information of the user, and reference image information of the user; The call record information is sent to the anti-fraud service end, and the call record information is used by the anti-fraud service end to verify whether the calling user is a preset user, and the preset user is determined according to the call details information of the user.

5. An information processing method, characterized in that: Applied to the anti-fraud server, the method includes: In the case of receiving call information sent by the first electronic device, verifying whether the calling user is a preset user according to the call information, the call information including image information and second audio information of a first 5G call interface during a video call between the first electronic device and the calling user, the call information being obtained by the first electronic device when determining that the first audio information during the video call with the calling user includes a first fraud-related keyword; In the case where the target verification result is used to characterize that the calling user is the preset user, determining the policy information according to feedback information provided by a verification feedback user, the verification feedback user being determined according to the identity information of the preset user; The policy information is sent to the 5G message server, and the policy information is used by the 5G message server to determine whether to send warning information to the first electronic device, wherein the warning information includes warning text information used to characterize the risk level of making a video call with the calling user, and the warning text information is displayed in the first 5G call interface.

6. The method according to claim 5, characterized in that Before verifying whether the calling user is a target user according to the call information, the method further includes: Receiving call record information of a called user sent by the first electronic device, the call record information including call details information of a user who has had a call with the called user, reference audio information of the user, and reference image information of the user; According to the call details information, a user who meets the second preset condition is determined as a preset user, and the second preset condition includes at least one of the following: the call duration is greater than the preset duration, the number of calls is greater than the preset number, the call interval is greater than the preset duration, there are a preset number of common users between the called user and the user, and the called user and the user belong to the same group communication service participants.

7. The method according to claim 6, characterized in that The verifying whether the calling user is a preset user according to the call information includes: Calculating a first similarity value between the voiceprint feature and the reference voiceprint feature according to the voiceprint feature in the second audio information and the reference voiceprint feature in the reference audio information of the preset user; Calculating a second similarity value between the facial feature and the reference facial feature according to the facial feature in the image information and the reference facial feature in the reference image information of the preset user; When at least one of the following conditions is met, the verification result of whether the calling user is the preset user is determined as the target verification result, and the meeting of at least one of the following conditions includes: the first similarity is greater than or equal to a first similarity threshold, and the second similarity is greater than or equal to a second similarity threshold.

8. The method according to claim 5, characterized in that Before determining the policy information according to the feedback information provided by the verification feedback user, the method further includes: generating a second text message according to a second fraud-related keyword in the call information; Generate prompt information according to the second text information and display configuration information corresponding to the preset user, wherein the display configuration information includes a display state of the second text information on a second electronic device of the verification feedback user; Sending the prompt information to the 5G message server, the prompt information is used by the 5G message server to generate inquiry information, the inquiry information is used by the verification feedback user to determine whether the calling user is the preset user, and the inquiry information is displayed in the second 5G call interface of the second electronic device; Receive feedback information based on the inquiry information sent by the second electronic device.

9. The method according to claim 8, characterized in that The strategy information includes a target warning information display strategy; the strategy information is determined based on the feedback information provided by the verification feedback user, including: According to the feedback information, determining a target risk level corresponding to the feedback information from a plurality of preset risk levels; According to the association information between the preset risk level and the preset warning information display strategy, a target warning information display strategy associated with the target risk level is determined.

10. The method according to claim 9, characterized in that The feedback information includes first feedback information or second feedback information, the first feedback information includes that the second electronic device receives a response operation of the verification feedback user to the inquiry information, and the response operation indicates that the identity of the calling user is not the preset user, and the second feedback information includes that the second electronic device does not receive a response operation of the verification feedback user to the inquiry information within a second preset time period; The target risk level includes a first risk level corresponding to the first feedback information or a second risk level corresponding to the second feedback information, and the first risk level is higher than the second risk level; The target warning information display strategy includes a first strategy corresponding to the first risk level or a second strategy corresponding to the second risk level, the first strategy includes first prompt text information and a first display state of the first prompt text information, the second strategy includes second prompt text information and a second display state of the second prompt text information, the warning level of the first prompt text information is higher than the warning level of the second prompt text information, and the warning level of the first display state is higher than the warning level of the second display state.

Images