Information security method and device, computer equipment and storage medium

Abstract

The invention relates to an information security method and device, computer equipment, a storage medium and a computer program product, and relates to the technical field of information security. The method comprises the following steps: in response to an article extraction request, receiving facial image data and sound data of a target user sent by a mobile terminal; the article extraction request comprises target article data needing to be extracted by a target user; based on the target article data, the face image data and the sound data, performing identity verification on the target user to obtain an initial verification result; under the condition that the initial verification result is successful, obtaining network state data, and generating an identity verification code based on the network state data and a verification code algorithm; performing identity verification on the target user based on the identity verification code to obtain a verification result, and sending the verification result to the mobile terminal; the verification result is used for extracting the target article. By adopting the method, the efficiency of the information security method can be improved.

Description

Technical Field

[0001] The present application relates to the field of information security technology, and in particular, to an information security method, device, computer device, storage medium, and computer program product. Background Art

[0002] In the current investment market, the scale of the precious metal investment market is getting larger and larger. More and more users will buy precious metals in banks and store the precious metals in banks. When a user needs to use the precious metals, the user will perform identity verification through an information security method and withdraw the precious metals from the bank after the identity verification is passed.

[0003] The current information security method requires the target user to carry an identity certificate and go to the bank in person. The staff will verify the identity of the target user based on the identity certificate of the target user and the item extraction information of the target user. When the verification is successful, the target item corresponding to the item extraction information will be given to the target user.

[0004] However, in the current information security method, when there are multiple users who need to perform identity verification at the same time, the method of manually verifying the identity of the users will consume a lot of time. Therefore, the efficiency of the current information security method is low. Summary of the Invention

[0005] Based on this, it is necessary to provide an information security method, device, computer device, computer-readable storage medium, and computer program product for the above technical problems.

[0006] In a first aspect, the present application provides an information security method, which is applied to a terminal and includes:

[0007] In response to an item extraction request, receiving facial image data and voice data of a target user sent by a mobile terminal; the item extraction request includes target item data that the target user needs to extract;

[0008] Based on the target item data, the facial image data, and the voice data, performing identity verification on the target user to obtain an initial verification result;

[0009] When the initial verification result is passed, obtaining network status data, and generating an identity verification code based on the network status data and a verification code algorithm;

[0010] Performing identity verification on the target user based on the identity verification code to obtain a verification result, and sending the verification result to the mobile terminal; the verification result is used to extract the target item.

[0011] In one embodiment, in response to an item extraction request, facial image data and voice data of a target user sent by a mobile device are received, including:

[0012] In response to the item extraction request of the target user, a video call connection with the mobile device is established;

[0013] The detection result of the collector sent by the mobile device is received, and when the detection result is normal, a question template is sent to the mobile device;

[0014] Based on the question template and the video call connection, the facial image data and voice data of the target user sent by the mobile device are received.

[0015] In one embodiment, the method for authenticating the identity of the target user based on the target item data, the facial image data, and the voice data to obtain an initial authentication result includes:

[0016] The target user is verified for being a real person and for lying based on the facial image data to obtain a first verification result;

[0017] When the first verification result is successful, feature extraction is respectively performed on the facial image data and the voice data to obtain facial image feature data and voiceprint feature data;

[0018] The voice data is converted into text to obtain answer text data;

[0019] Based on the answer text data, the target item data, the facial image feature data, and the voiceprint feature data, an initial verification result is determined.

[0020] In one embodiment, the method for determining the initial verification result based on the answer text data, the target item data, the facial image feature data, and the voiceprint feature data includes:

[0021] The original facial image feature data and the original voiceprint feature data of the target user are obtained based on the target user identifier of the target user;

[0022] It is judged whether the target item data and the answer text data are consistent to obtain a first judgment result;

[0023] The first similarity between the original facial image feature data and the facial image feature data is calculated, and the second similarity between the original voiceprint feature data and the voiceprint feature data is calculated;

[0024] It is judged whether the first similarity and the second similarity reach a preset similarity condition to obtain a second judgment result;

[0025] Determine an initial verification result based on the first determination result and the second determination result.

[0026] In one embodiment, after performing identity verification on the target user based on the target item data, the facial image data, and the voice data to obtain an initial verification result, the method further includes:

[0027] In the case where the initial verification result is not passed, update the verification count;

[0028] Determine whether the verification count reaches a preset verification count threshold;

[0029] In the case where the verification count does not reach the verification count threshold, perform the step of receiving the facial image data and voice data of the target user sent by the mobile terminal.

[0030] In one embodiment, generating an identity verification code based on the network status data and a verification code algorithm includes:

[0031] Determine whether the network status data indicates that the network of the terminal is unobstructed;

[0032] If the network status data indicates that the network of the terminal is unobstructed, determine the verification code algorithm as a jigsaw verification code algorithm, and generate an identity verification code based on the jigsaw verification code algorithm;

[0033] If the network status data indicates that the network of the terminal is congested, determine the verification code algorithm as a digital verification code algorithm, and generate an identity verification code based on the digital verification code algorithm.

[0034] In one embodiment, generating an identity verification code based on the jigsaw verification code algorithm includes:

[0035] Randomly generate verification digits, and determine verification pictures in a picture database;

[0036] Segment the verification pictures to obtain respective verification picture regions, and establish an association relationship between each of the verification digits and each of the verification picture regions;

[0037] Combine the verification digits on each verification picture region in the order of the verification pictures to obtain a verification answer;

[0038] Randomly sort each of the verification picture regions to obtain an identity verification code.

[0039] In one embodiment, performing identity verification on the target user based on the identity verification code to obtain a verification result includes:

[0040] Send the identity verification code to the mobile device and establish a voice call connection with the mobile device;

[0041] Based on the voice call connection, obtain voice data, and perform feature extraction and text conversion on the voice data to obtain voiceprint feature data and voice text data;

[0042] Calculate the third similarity between the voiceprint feature data and the original voiceprint feature data of the target user;

[0043] Determine whether the voice text data is consistent with the verification answer corresponding to the identity verification code, and determine whether the third similarity reaches a preset third similarity threshold to obtain a third judgment result;

[0044] Determine the verification result based on the third judgment result.

[0045] In a second aspect, the present application provides an information security method, which is applied to a mobile device and includes:

[0046] Construct an item extraction request based on the user information of the target user and the target item data, and send the item extraction request to the terminal;

[0047] Collect the facial image data and voice data of the target user based on a collector, and send the facial image data and voice data to the terminal;

[0048] Receive the verification result of the target user, and execute the extraction process of the target item when the verification result is passed.

[0049] In a third aspect, the present application further provides an information security device, including:

[0050] A receiving module, configured to receive the facial image data and voice data of the target user sent by the mobile device in response to an item extraction request; the item extraction request includes the target item data that the target user needs to extract;

[0051] A first verification module, configured to perform identity verification on the target user based on the target item data, the facial image data, and the voice data to obtain an initial verification result;

[0052] A generating module, configured to obtain network status data when the initial verification result is passed, and generate an identity verification code based on the network status data and a verification code algorithm;

[0053] A second verification module, configured to perform identity verification on the target user based on the identity verification code to obtain a verification result, and send the verification result to the mobile device; the verification result is used to extract the target item.

[0054] In a fourth aspect, the present application further provides an information security device, including:

[0055] A construction module, configured to construct an item extraction request based on the user information of the target user and the target item data, and send the item extraction request to the terminal;

[0056] A sending module, configured to collect the facial image data and voice data of the target user based on a collector, and send the facial image data and voice data to the terminal;

[0057] An execution module, configured to receive the verification result of the target user, and execute the extraction process of the target item when the verification result is passed.

[0058] In a fifth aspect, the present application further provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0059] In response to an item extraction request, receive the facial image data and voice data of the target user sent by a mobile terminal; the item extraction request includes the target item data that the target user needs to extract;

[0060] Based on the target item data, the facial image data, and the voice data, perform identity verification on the target user to obtain an initial verification result;

[0061] When the initial verification result is passed, obtain network status data, and generate an identity verification code based on the network status data and a verification code algorithm;

[0062] Based on the identity verification code, perform identity verification on the target user to obtain a verification result, and send the verification result to the mobile terminal; the verification result is used to extract the target item.

[0063] In a sixth aspect, the present application further provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0064] Based on the user information of the target user and the target item data, construct an item extraction request, and send the item extraction request to the terminal;

[0065] Based on a collector, collect the facial image data and voice data of the target user, and send the facial image data and voice data to the terminal;

[0066] Receive the verification result of the target user, and execute the extraction process of the target item when the verification result is passed.

[0067] In a seventh aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0068] In response to an item extraction request, receive the facial image data and voice data of the target user sent by the mobile terminal; the item extraction request includes the target item data that the target user needs to extract;

[0069] Based on the target item data, the facial image data, and the voice data, authenticate the identity of the target user to obtain an initial verification result;

[0070] When the initial verification result is passed, obtain network status data, and generate an identity verification code based on the network status data and the verification code algorithm;

[0071] Authenticate the identity of the target user based on the identity verification code to obtain a verification result, and send the verification result to the mobile terminal; the verification result is used to extract the target item.

[0072] In an eighth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0073] Based on the user information of the target user and the target item data, construct an item extraction request, and send the item extraction request to the terminal;

[0074] Collect the facial image data and voice data of the target user based on a collector, and send the facial image data and voice data to the terminal;

[0075] Receive the verification result of the target user, and execute the extraction process of the target item when the verification result is passed.

[0076] In a ninth aspect, the present application further provides a computer program product, including a computer program. When the computer program is executed by a processor, the following steps are implemented:

[0077] In response to an item extraction request, receive the facial image data and voice data of the target user sent by the mobile terminal; the item extraction request includes the target item data that the target user needs to extract;

[0078] Based on the target item data, the facial image data, and the voice data, authenticate the identity of the target user to obtain an initial verification result;

[0079] When the initial verification result is passed, obtain network status data, and generate an identity verification code based on the network status data and the verification code algorithm;

[0080] Authenticate the target user based on the identity verification code to obtain a verification result, and send the verification result to the mobile terminal; the verification result is used to extract the target item.

[0081] In a tenth aspect, the present application further provides a computer program product, including a computer program, which when executed by a processor, implements the following steps:

[0082] Construct an item extraction request based on the user information of the target user and the target item data, and send the item extraction request to the terminal;

[0083] Collect the facial image data and voice data of the target user by the collector, and send the facial image data and voice data to the terminal;

[0084] Receive the verification result of the target user, and execute the extraction process of the target item when the verification result is passed.

[0085] The above information security method, device, computer device, storage medium and computer program product, in response to an item extraction request, receive the facial image data and voice data of the target user sent by the mobile terminal; the item extraction request includes the target item data required by the target user; based on the target item data, the facial image data and the voice data, authenticate the target user to obtain an initial verification result; when the initial verification result is passed, obtain network status data, and generate an identity verification code based on the network status data and the verification code algorithm; authenticate the target user based on the identity verification code to obtain a verification result, and send the verification result to the mobile terminal; the verification result is used to extract the target item. By using this method, the identity of the target user is initially verified through the facial image data, target item data and voice data. Then, an identity verification code is generated through the network status data and the verification code algorithm, and the target user is verified again based on the identity verification code, realizing online automatic multi-factor authentication of the target user, reducing the identity verification time, and improving the efficiency of the information security method. Description of the Drawings

[0086] To more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for the description of the embodiments or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0087] Figure 1 It is an application environment diagram of the information security method in an embodiment;

[0088] Figure 2 It is a schematic flowchart of the information security method in an embodiment;

[0089] Figure 3 It is a schematic flowchart of receiving facial image data and voice data in an embodiment;

[0090] Figure 4 It is a schematic flowchart of determining the initial verification result in an embodiment;

[0091] Figure 5 It is a schematic flowchart of determining the first judgment result and the second judgment result in an embodiment;

[0092] Figure 6 It is a schematic flowchart of updating the verification times in an embodiment;

[0093] Figure 7 It is a schematic flowchart of generating an identity verification code in an embodiment;

[0094] Figure 8 It is a schematic flowchart of generating an identity verification code in the form of a jigsaw puzzle in an embodiment;

[0095] Figure 9 It is a schematic flowchart of determining the verification result in an embodiment;

[0096] Figure 10 It is a schematic flowchart of the information security method in another embodiment;

[0097] Figure 11 It is an execution flowchart of the gold extraction method in an embodiment;

[0098] Figure 12 It is a structural block diagram of the gold extraction device in an embodiment;

[0099] Figure 13 It is a structural block diagram of the information security device in an embodiment;

[0100] Figure 14 It is a structural block diagram of the information security device in another embodiment;

[0101] Figure 15 It is the internal structure diagram of a computer device in an embodiment. Specific implementation manners

[0102] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0103] The information security method provided by the embodiments of the present application can be applied to, for example, Figure 1 the information security system 100 shown in the figure. Among them, the mobile terminal 102 communicates through the network terminal 104. The data storage system can store the data that the terminal 104 needs to process. The data storage system can be integrated on the server 104, or can be placed in the cloud or other network servers. Among them, the mobile terminal 102 can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The terminal 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0104] In an exemplary embodiment, as Figure 2 shown in the figure, an information security method is provided. Taking the method applied to Figure 1 the terminal 104 in the figure (hereinafter abbreviated as the terminal for short) as an example, the method includes the following steps 202 to 208. Among them:

[0105] Step 202, in response to an item extraction request, receive the facial image data and voice data of the target user sent by the mobile terminal.

[0106] Among them, the item extraction request includes the target item data that the target user needs to extract. The target item is the item that the target user needs to extract.

[0107] In implementation, when the target user needs to extract the target item, the target user will initiate an item extraction request through the mobile terminal. The mobile terminal sends the item extraction request to the terminal. In response to the item extraction request, the terminal establishes a video call connection with the mobile terminal. Then, the mobile terminal collects the facial image data and voice data of the target user through the collector and sends them to the terminal through the video call connection. The terminal receives the facial image data and voice data of the target user.

[0108] Optionally, the target item can be, but is not limited to, precious metals, porcelain, etc. The embodiments of the present application do not limit the target item.

[0109] Step 204, based on the target item data, facial image data and voice data, authenticate the target user to obtain an initial authentication result.

[0110] In implementation, the terminal performs a real-person verification and a lie verification on the target user based on the facial image data to obtain a first verification result. Then, the terminal determines whether the first verification result is successful. When the first verification result is successful, the terminal processes the facial image data to obtain facial image feature data. At the same time, the terminal processes the voice data to obtain answer text data and voiceprint feature data. Then, the terminal performs an identity verification on the target user based on the answer text data, the voiceprint feature data, the facial image data, and the target item data to obtain an initial verification result. The terminal determines whether the initial verification result is passed. If the initial verification result is passed, the terminal executes step 206 below. If the initial verification result is not passed, the terminal executes step 602 below.

[0111] Step 206, when the initial verification result is passed, obtain network status data and generate an identity verification code based on the network status data and the verification code algorithm.

[0112] Among them, the network status data represents that the network of the terminal is unobstructed or congested.

[0113] In implementation, when the initial verification result is passed, the terminal obtains network status data. The terminal determines whether the network status data represents that the network of the terminal is unobstructed. If the network status data represents that the network of the terminal is unobstructed, the terminal generates an identity verification code in the form of a jigsaw puzzle based on the verification code algorithm. If the network status data represents that the network of the terminal is congested, the terminal generates an identity verification code in the form of numbers based on the verification code algorithm.

[0114] Step 208, perform an identity verification on the target user based on the identity verification code to obtain a verification result, and send the verification result to the mobile terminal.

[0115] Among them, the verification result is used to extract the target item.

[0116] In implementation, the terminal sends the identity verification code to the mobile terminal and establishes a voice call connection with the mobile terminal. Then, the terminal obtains the voice data of the target user based on the voice call and processes the voice data to obtain voiceprint feature data and voice text data. The terminal performs an identity verification on the target user again based on the voiceprint feature data and the voice text data to obtain a verification result. Then, the terminal sends the verification result to the mobile terminal so that the mobile terminal executes the item extraction process.

[0117] In the above information security method, the identity of the target user is initially verified through facial image data, target item data, and voice data. Then, an identity verification code is generated based on network status data and a verification code algorithm, and the target user is verified again based on the identity verification code, realizing multiple identity verifications of the target user online automatically, reducing the identity verification time, and improving the efficiency of the information security method.

[0118] In an exemplary embodiment, as Figure 3 shown, the specific processing procedure of step 102 includes steps 302 to 306. Among them:

[0119] Step 302, in response to the item extraction request of the target user, establish a video call connection with the mobile terminal.

[0120] In implementation, the terminal, in response to the item extraction request of the target user, sends a video call connection establishment request to the mobile terminal. The mobile terminal, in response to the video call connection establishment request, establishes a video call connection with the terminal.

[0121] Step 304, receive the detection result of the collector sent by the mobile terminal, and when the detection result is normal, send the question template to the mobile terminal.

[0122] Among them, a collector is set on the mobile terminal. The question template contains questions for asking about the target item data.

[0123] In implementation, the mobile terminal will perform a status detection on the collector, obtain the detection result, and send the detection result to the terminal. The terminal receives the detection result of the collector sent by the mobile terminal. The terminal judges whether the detection result is normal. If the detection result is normal, the terminal sends the preset question template to the mobile terminal.

[0124] In an optional embodiment, if the detection result is abnormal, the terminal ends the execution of the information security method and sends information about ending the identity verification process due to the abnormal collector to the mobile terminal.

[0125] Optionally, the content of the question template varies according to different target items. And, the question template may but is not limited to contain questions for asking about the target item data, and may also contain questions for asking about the target user information, which are set according to different extraction requirements and extraction scenarios. The embodiments of the present application do not limit the question template.

[0126] Step 306, based on the question template and the video call connection, receive the facial image data and voice data of the target user sent by the mobile terminal.

[0127] In implementation, the mobile device will display a question template and collect facial image data and voice data of the target user when answering the question template through a collector. Then, the mobile device sends the facial image data and voice data of the target user to the terminal through a video call connection. The terminal receives the facial image data and voice data of the target user through the video call connection.

[0128] In this embodiment, by receiving the detection result of the collector, the status of the collector is clarified, and based on the status of the collector, the facial image data and voice data sent by the mobile device are received, which is convenient for subsequent identity verification according to the facial image data and voice data. Moreover, by obtaining the facial image data and voice data online, the step-by-step collection is avoided, and the efficiency of the information security method and the user experience are improved.

[0129] In an exemplary embodiment, as Figure 4 shown, the specific processing process of step 104 includes steps 402 to 408. Among them:

[0130] Step 402, perform a real-person verification and a lie verification on the target user based on the facial image data to obtain a first verification result.

[0131] In implementation, a real-person verification model and a lie verification model are pre-set in the terminal. The terminal inputs the facial image data into the real-person verification model, and the real-person verification model processes the image data to obtain a real-person verification result. At the same time, the terminal inputs the facial image data into the lie verification model, and the lie verification model processes the facial image data to obtain a lie verification result. Then, the terminal determines the first verification result based on the real-person verification result and the lie verification result. The terminal judges whether the first verification result is successful.

[0132] Specifically, if the real-person verification result indicates that the target user is a real person and the lie verification result indicates that the target user does not lie, the terminal determines that the first verification result is successful. If the real-person verification result indicates that the target user is not a real person and / or the lie verification result indicates that the target user lies, the terminal determines that the first verification result is failed.

[0133] In an alternative embodiment, if the first verification result is failed, the terminal executes the following step 602.

[0134] Optionally, the real-person verification model can be but is not limited to a face recognition model or a live detection model, and the lie verification model can be but is not limited to a behavior analysis model. The embodiments of the present application do not limit the real-person verification model and the lie verification model.

[0135] Step 404, in the case where the first verification result is successful, extract features from the facial image data and the voice data respectively to obtain facial image feature data and voiceprint feature data.

[0136] In implementation, a preset biometric algorithm in the terminal. When it is recognized that the first verification result is successful, the terminal preprocesses the facial image data to obtain the preprocessed facial image data. Then, the terminal extracts features from the preprocessed facial image features through the biometric algorithm to obtain facial image feature data. At the same time, the terminal extracts features from the voice data through the biometric algorithm to obtain voiceprint feature data.

[0137] Optionally, the biometric algorithm can be but is not limited to a convolutional neural network (CNN, Convolutional Neural Networks), and the embodiments of the present application do not limit the biometric algorithm.

[0138] Step 406: Perform text conversion on the voice data to obtain answer text data.

[0139] In implementation, the terminal performs text conversion on the voice data according to a preset speech recognition model to obtain answer text data.

[0140] Optionally, the speech recognition model can be but is not limited to a recurrent neural network (Recurrent Neural Networks, RNN) or a natural language processing model (Natural Language Processing, NLP), and the embodiments of the present application do not limit the speech recognition model.

[0141] Step 408: Determine an initial verification result based on the answer text data, the target item data, the facial image feature data, and the voiceprint feature data.

[0142] In implementation, the terminal obtains the original facial image feature data and the original voiceprint feature data of the target user. The terminal determines whether the answer text data and the target item data are consistent to obtain a first determination result. At the same time, the terminal determines a second determination result based on the original facial image feature data, the facial image feature data, the original voiceprint feature data, and the voiceprint feature data. Then, the terminal determines the initial verification result according to the first determination result and the second determination result.

[0143] In this embodiment, the target user is verified for authenticity and lies through the facial image data, and the target user is verified again through the facial image data and the voice data to obtain an initial verification result, improving the security of the information security method.

[0144] In an exemplary embodiment, as Figure 5 shown, the specific processing process of step 408 includes steps 502 to 510. Among them:

[0145] Step 502: Obtain the original facial image feature data and original voiceprint feature data of the target user based on the target user identifier of the target user.

[0146] Among them, the item extraction information contains the user information of the target user, and the user information contains the target user identifier.

[0147] In implementation, the terminal obtains the original facial image feature data and original voiceprint feature data of the target user from the database according to the target user identifier of the target user. Among them, the original facial image feature data and original voiceprint feature data are pre-obtained and stored in the database.

[0148] Step 504: Determine whether the target item data and the answer text data are consistent to obtain a first determination result.

[0149] In implementation, the terminal compares the target item data and the answer text data, and determines whether the target item data and the answer text data are the same to obtain a first determination result.

[0150] Step 506: Calculate a first similarity between the original facial image feature data and the facial image feature data, and calculate a second similarity between the original voiceprint feature data and the voiceprint feature data.

[0151] In implementation, the terminal calculates the first similarity between the original facial image feature data and the facial image feature data according to a preset similarity algorithm. Then, the terminal calculates the second similarity between the original voiceprint feature data and the voiceprint feature data according to this similarity algorithm.

[0152] Optionally, the similarity algorithm can be but is not limited to the cosine similarity algorithm or the BERT (Bidirectional Encoder Representations from Transformers) algorithm. The embodiments of the present application do not limit the similarity algorithm.

[0153] Step 508: Determine whether the first similarity and the second similarity reach a preset similarity condition to obtain a second determination result.

[0154] Among them, the similarity condition is that the first similarity reaches a first similarity threshold and the second similarity reaches a second similarity threshold.

[0155] In implementation, a first similarity threshold and a second similarity threshold are preset in the terminal. The terminal determines whether the first similarity reaches the first similarity threshold and whether the second similarity reaches the second similarity threshold. If the first similarity reaches the first similarity threshold and the second similarity reaches the second similarity threshold, the terminal determines that the second judgment result is that the first similarity and the second similarity reach the similarity condition. If the first similarity does not reach the first similarity threshold and / or the second similarity does not reach the second similarity threshold, the terminal determines that the second judgment result is that the first similarity and the second similarity do not reach the similarity condition.

[0156] Optionally, the first similarity threshold and the second similarity threshold may be the same or different. The first similarity threshold may but is not limited to being set to 90% (percent sign) or 95%, and the second similarity threshold may but is not limited to being set to 90% or 95%. The first similarity threshold and the second similarity threshold are determined according to the identity verification requirements, and the embodiments of the present application do not limit the first similarity threshold and the second similarity threshold.

[0157] Step 510, based on the first judgment result and the second judgment result, determine the initial verification result.

[0158] In implementation, if the first judgment result is the same and the second judgment result is that the first similarity and the second similarity reach the similarity condition, the terminal determines that the initial verification result is passed. If the first judgment result is different and / or the second judgment result is that the first similarity and the second similarity do not reach the similarity condition, the terminal determines that the initial verification result is not passed.

[0159] In this embodiment, by determining whether the target item data and the answer text data are consistent, whether the original facial image feature data and the facial image feature data are similar, and whether the voiceprint feature data and the original voiceprint feature data are similar, the initial verification result is obtained, realizing automatic identity verification of the target user and improving the efficiency of the information security method. Moreover, based on the interactive verification of the target item data, facial recognition, and voiceprint recognition, the security factor is high, improving the security of the information security method.

[0160] In an exemplary embodiment, when the initial verification result is not passed, it is necessary to perform the initial identity verification again. As Figure 6 shown, after step 104 is executed, the specific processing process of this information security method includes steps 602 to 606. Among them:

[0161] Step 602, when the initial verification result is not passed, update the verification times.

[0162] In implementation, a verification count is preset in the terminal. The verification count is preset to 0. When the initial verification result fails, the terminal increments the verification count by 1 to obtain the updated verification count.

[0163] Step 604: Determine whether the verification count has reached a preset verification count threshold.

[0164] In implementation, a verification count threshold is preset in the terminal. The terminal determines whether the verification count is greater than or equal to the verification count threshold.

[0165] Optionally, the verification count threshold can be set to 3 times or 2 times. The embodiments of the present application do not limit the verification count threshold.

[0166] In an optional embodiment, when the verification count reaches the verification count threshold, the terminal ends the execution of the information security method and sends a message indicating that the verification count has reached the upper limit to the mobile terminal.

[0167] Step 606: When the verification count has not reached the verification count threshold, execute the step of receiving the facial image data and voice data of the target user sent by the mobile terminal.

[0168] In implementation, when the verification count has not reached the verification count threshold, the terminal executes step 102 above. The specific processing process of step 102 has been described in the above embodiments and will not be elaborated herein in the embodiments of the present application.

[0169] In this embodiment, when the verification fails and the verification count has not reached the verification count threshold, the facial image data and voice data of the target user are received again, and verification is performed quickly again, improving the user experience.

[0170] In an exemplary embodiment, as Figure 7 shown, the specific processing process of generating the identity verification code based on the network status data and the verification code algorithm in step 106 includes steps 702 to 706. Among them:

[0171] Step 702: Determine whether the network status data indicates that the network of the terminal is unobstructed.

[0172] In implementation, the terminal determines whether the network status data indicates that the network of the terminal is unobstructed.

[0173] Step 704: If the network status data indicates that the network of the terminal is unobstructed, determine the verification code algorithm as the jigsaw verification code algorithm, and generate the identity verification code based on the jigsaw verification code algorithm.

[0174] In implementation, if the network status data indicates that the network of the terminal is unobstructed, the terminal determines that the verification code algorithm is the jigsaw verification code algorithm. Then, the terminal determines a verification picture from the picture database, and generates an identity verification code in the form of a jigsaw puzzle based on the verification picture and the jigsaw verification code algorithm.

[0175] Step 706, if the network status data indicates that the network of the terminal is congested, determine that the verification code algorithm is the digital verification code algorithm, and generate an identity verification code based on the digital verification code algorithm.

[0176] In implementation, if the network status data indicates that the network of the terminal is congested, the terminal determines that the verification code algorithm is the data verification code algorithm. Then, the terminal randomly generates a preset number of verification digits according to the digital verification code algorithm. Then, the terminal combines each verification digit to obtain an identity verification code in digital form.

[0177] In this embodiment, different forms of identity verification codes are sent to the mobile terminal based on the network status, so that the target user can quickly receive the identity verification code, and then quickly start the next identity verification, improving the efficiency of the information security method.

[0178] In an exemplary embodiment, as Figure 8 shown, the specific processing procedure for generating an identity verification code based on the network status data and the verification code algorithm in step 106 includes steps 802 to 808. Among them:

[0179] Step 802, randomly generate verification digits, and determine a verification picture in the picture database.

[0180] In implementation, the terminal randomly generates a preset number of verification digits. Then, the terminal randomly determines a picture in the picture database as the verification picture.

[0181] Step 804, divide the verification picture to obtain each verification picture area, and establish an association relationship between each verification digit and each verification picture area.

[0182] In implementation, the terminal evenly divides the verification picture according to a preset number to obtain each verification picture area. Then, the terminal places each verification digit on the verification picture area, and establishes an association relationship between the verification digit and the verification picture area.

[0183] Step 806, combine the verification digits on each verification picture area in the order of the verification picture to obtain a verification answer.

[0184] In implementation, the terminal combines the verification digits on each verification picture area in the order from top to bottom and from left to right in each verification area of the verification picture to obtain a verification answer.

[0185] Step 808: Randomly sort each verification picture area to obtain an identity verification code.

[0186] In implementation, the terminal randomly sorts each verification picture to obtain the sorted verification picture areas. Then, the terminal combines the sorted verification picture areas to obtain a target verification picture and determines the target verification picture as the identity verification code.

[0187] In this embodiment, by combining the verification picture and the verification number to construct an identity verification code in the form of a jigsaw puzzle, the difficulty of cracking the verification code is increased, and the security of the information security method is further improved.

[0188] In an exemplary embodiment, as Figure 9 shown, the specific processing process of performing identity verification on the target user based on the identity verification code in step 108 to obtain a verification result includes steps 902 to 910. Among them:

[0189] Step 902: Send the identity verification code to the mobile terminal and establish a voice call connection with the mobile terminal.

[0190] In implementation, the terminal sends the identity verification code to the mobile terminal. Then, the terminal sends a voice call connection establishment request to the mobile terminal. The mobile terminal responds to the voice call connection establishment request and establishes a voice call connection with the terminal.

[0191] Step 904: Based on the voice call connection, obtain voice data, and perform feature extraction and text conversion on the voice data to obtain voiceprint feature data and voice text data.

[0192] In implementation, the mobile terminal collects voice data through a collector and sends the voice data to the terminal based on the voice call connection. The terminal receives the voice data based on the voice call connection. Then, the terminal receives the voice data based on the voice call connection. Then, the terminal extracts the voiceprint features in the voice data based on a preset biometric algorithm to obtain voiceprint feature data. At the same time, the terminal performs text conversion on the voice data based on a preset speech recognition model to obtain voice text data. Among them, the biometric algorithm is the biometric algorithm in step 404 above. The speech recognition model is the speech recognition model in step 406 above.

[0193] Step 906: Calculate the third similarity between the voiceprint feature data and the original voiceprint feature data of the target user.

[0194] In implementation, the terminal obtains the original voiceprint feature data of the target user according to the target user identifier of the target user. Then, the terminal calculates the third similarity between the voiceprint feature data and the original voiceprint feature data according to a preset similarity algorithm. Among them, the similarity algorithm is the similarity algorithm in step 506 above.

[0195] Step 908: Determine whether the voice text data is consistent with the verification answer corresponding to the identity verification code, and determine whether the third similarity reaches a preset third similarity threshold to obtain a third judgment result.

[0196] In implementation, the terminal compares the voice text data with the verification answer corresponding to the identity verification code to determine whether the voice text data is consistent with the verification answer. At the same time, the terminal determines whether the third similarity reaches a preset third similarity threshold to obtain a third judgment result.

[0197] Optionally, the third similarity threshold can be set to 85% or 90%, which is determined according to the identity verification requirements. The embodiments of the present application do not limit the third similarity threshold.

[0198] Step 910: Determine the verification result based on the third judgment result.

[0199] In implementation, if the third judgment result indicates that the voice text data is consistent with the verification answer and the third similarity reaches the third similarity threshold, the terminal determines that the verification result is passed. If the third judgment result indicates that the voice text data is inconsistent with the verification answer and / or the third similarity does not reach the third similarity threshold, the terminal determines that the verification result is not passed.

[0200] In this embodiment, based on the original voiceprint feature data and identity verification code of the target user, the target user is verified both for voiceprint and verification code, which has non-replicability, can increase the difficulty of cracking, and thus improves the security of the information security method.

[0201] In an exemplary embodiment, as Figure 10 shown, an information security method is provided. Taking the case where this method is applied to Figure 1 the mobile terminal 102 (hereinafter abbreviated as the mobile terminal for short by omitting the reference numerals) as an example, it includes the following steps 1002 to 1006. Wherein:

[0202] Step 1002: Based on the user information of the target user and the target item data, construct an item extraction request and send the item extraction request to the terminal.

[0203] In implementation, when the target user needs to extract the target item, the target user operates the display screen of the mobile terminal and determines the target item to be extracted. Then, the target user clicks the extraction component. In response to the click operation of the extraction component, the mobile terminal constructs an item extraction request based on the user information of the target user and the target item data. Then, the mobile terminal sends the item extraction request to the terminal.

[0204] Step 1004, collect the facial image data and voice data of the target user based on the collector, and send the facial image data and voice data to the terminal.

[0205] In implementation, after establishing a video call connection between the mobile device and the terminal, the mobile device detects the status of the collector to obtain a detection result, and sends the detection result to the terminal. The mobile device receives the question template sent by the terminal and displays the question template. Then, the mobile device collects the facial image data and voice data of the target user based on the collector, and sends the facial image data and voice data to the terminal.

[0206] Optionally, the collector includes an image collector and a voice collector. The image collector can be a camera, and the voice collector can be a microphone. The embodiments of the present application do not limit the collector.

[0207] Step 1006, receive the verification result of the target user, and execute the extraction process of the target item when the verification result is passed.

[0208] In implementation, the mobile device receives the verification result of the target user and determines whether the verification result is passed. When the verification result is passed, the mobile device executes the extraction process of the target item.

[0209] Specifically, the mobile device displays the extraction page of the target supplies. Among them, the extraction page contains various pending extraction methods. The pending extraction methods include offline extraction and express delivery extraction. The target user determines the target extraction method among the various pending extraction methods and clicks on the target extraction method. If the target extraction method is express delivery extraction, the mobile device, in response to the click operation of the target extraction method, displays an address editing page and obtains the target address of the target user based on the address editing page. Then, the mobile device constructs the express delivery extraction information of the target item based on the target user information, target address, and target item data of the target user, and sends the express delivery extraction information to the express delivery system. If the target extraction method is express delivery extraction, the mobile device, in response to the click operation of the target extraction method, obtains the current address of the target user, and determines the initial target offline address among the various offline addresses based on the current address. The mobile device displays the initial target offline address and determines the target offline address based on the initial target offline address. Then, the mobile device constructs the offline extraction information of the target user based on the target user information and target item data, and sends the offline extraction information to the offline system corresponding to the target offline address.

[0210] In an optional embodiment, if the verification result is not passed, the mobile device displays that the verification result is not passed and ends the execution of this information security method.

[0211] In this embodiment, by sending an item extraction request, facial image data and voice data are collected and sent to the terminal, facilitating identity verification by the terminal, achieving remote online identity verification, replacing manual labor, and reducing the input of human resources.

[0212] In an exemplary embodiment, the information security method is used to extract precious metals of customers, forming a gold extraction method. Figure 11 The flowchart for the execution of the gold extraction method includes:

[0213] Step 1101: Through the language communication during the dynamic video of the customer and the intelligent AI, preprocess the dynamic video data, and use the gold extraction information extraction algorithm to extract the customer's gold extraction information (target item data) from the dynamic video.

[0214] Step 1102: Use the biometric algorithm to extract the customer feature values required for recognition from the facial expression information, use the biometric algorithm to extract the customer feature values required for recognition from the sound wave spectrum, and transmit them to the information processing module for data comparison.

[0215] Step 1103: When the three types of information, namely the gold extraction information, facial expression information, and voiceprint information, are consistent in comparison, the SMS sending mechanism will be triggered. If any one is inconsistent, the process will terminate. The user reads the verification code in the SMS for double verification of voiceprint + numerical code, and the information processing module analyzes and matches the information read by the user. After successful matching, the gold extraction process can be completed.

[0216] Step 1104: The customer information storage module stores the authenticated customer information, including questions and answers and biometrics, and the data is saved in the effective area.

[0217] Based on the above gold extraction method, as Figure 12 shown, a gold extraction device 1200 is provided. The gold extraction device 1200 includes: an AI interaction module 1201, a biometric recognition processing module 1202, an information processing module 1203, and an information storage module 1204.

[0218] The AI interaction module 1201 is used to extract gold extraction information such as the customer's gold purchase order number, gold purchase variety, gold purchase date, and gold purchase quantity. Through the language communication during the dynamic video of the customer and the intelligent AI, preprocess the dynamic video data, including operations such as color space conversion, cropping, and scaling, to improve the robustness of the model. Based on the gold extraction information extraction algorithm, extract the customer's gold extraction information from the dynamic video. The extracted gold extraction information should be consistent with the order information of the customer stored in the system. If the comparison is successful, continue with the subsequent biometric authentication; if the comparison fails, a re-verification prompt will pop up, and if the comparison fails again, exit the current transaction.

[0219] The biometric processing module 1202 includes facial expression recognition processing and voiceprint recognition processing. First, it checks whether the facial collector and voice collector of the customer device (mobile terminal) are normal. If they are normal, the following process can continue; otherwise, it cannot be used. When the customer faces the front camera of the mobile device, the mobile device screen can display the facial recognition position area. When the customer deviates from the recognition area, the customer is guided to adjust the facial position. Facial expression recognition requires the mobile phone camera to collect facial expressions, collect the facial expressions of the customer when answering the gold withdrawal question, transmit the collected dynamic information to the preprocessing software of the facial expression recognition system, extract the customer feature values required for recognition from the facial expression information using biometric algorithms, and transmit them to the information processing module for data comparison. Voiceprint recognition is transmitted through the microphone, collects the voices of the customer during the dynamic video with the intelligent AI and during voiceprint verification and signature, extracts the sound wave spectrum and transmits it to the preprocessing software of the voice recognition system, extracts the customer feature values required for recognition from the sound wave spectrum using biometric algorithms, encrypts and packages them and transmits them to the information processing module for data comparison. Biometric algorithms use convolutional neural networks (CNNs) to extract facial expression data and sound wave spectra, and both are compared with the initial facial expression information during user registration.

[0220] The information processing module 1203 is used to receive the information transmitted by the AI interaction module and the biometric processing module for comparison. When the three types of information, namely the gold withdrawal information, facial expression information, and voiceprint information, are consistent, the SMS sending mechanism will be triggered. If any one of them is inconsistent, the process will terminate. The user reads the verification code in the SMS for dual verification of voiceprint + numerical code. The information processing module analyzes and matches the information read by the user. After successful matching, a pop-up window will appear, allowing the user to select the gold withdrawal method (on-site gold withdrawal or express gold withdrawal); if the customer information does not match, the authentication process fails and the transaction terminates.

[0221] The customer information storage module 1204 stores the authenticated customer information, including questions and answers and biometrics. The data is saved in the effective area. Remote calls do not rule out the impact of network instability and noise on voiceprint extraction. Ensure that the network environment is stable and there is no noise interference, and the process can continue; if any influencing factor appears, the completed information will be stored. After the influencing factor disappears, if it is within the information storage time, continue the verification; if it is outside the information storage time, cancel the entire verification process. The effective area data management sets rules. Set the data valid time to 10 minutes in the effective area. For customer information that exceeds the data valid time, it will be removed from the effective area, and the customer identity information needs to be extracted again. That is, if there is a network interruption or the customer deals with other things midway, the verification can continue within 10 minutes. If it exceeds 10 minutes, the video call will be interrupted, and the customer needs to wait for the intelligent customer service to redial the video call.

[0222] It should be understood that although the steps in the flowcharts involved in the above embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0223] Based on the same inventive concept, an embodiment of the present application further provides an information security device for implementing the information security method involved above. The implementation solution provided by this device to solve problems is similar to the implementation solution described in the above method. Therefore, the specific limitations in one or more embodiments of the information security device provided below can refer to the limitations on the information security method in the above text, and will not be repeated here.

[0224] In an exemplary embodiment, as Figure 13 shown, an information security device 1300 is provided, including: a receiving module 1301, a first verification module 1302, a generating module 1303, and a second verification module 1304, where:

[0225] The receiving module 1301 is configured to receive the facial image data and voice data of the target user sent by the mobile terminal in response to an item extraction request; the item extraction request includes the target item data that the target user needs to extract.

[0226] The first verification module 1302 is configured to perform identity verification on the target user based on the target item data, facial image data, and voice data to obtain an initial verification result.

[0227] The generating module 1303 is configured to obtain network status data when the initial verification result is passed, and generate an identity verification code based on the network status data and the verification code algorithm.

[0228] The second verification module 1304 is configured to perform identity verification on the target user based on the identity verification code to obtain a verification result, and send the verification result to the mobile terminal; the verification result is used to extract the target item.

[0229] In an exemplary embodiment, the receiving module 1301 includes:

[0230] The first establishment sub-module is configured to establish a video call connection with the mobile terminal in response to the item extraction request of the target user.

[0231] The first receiving sub-module is configured to receive the detection result of the collector sent by the mobile terminal, and send the problem template to the mobile terminal when the detection result is normal;

[0232] The second receiving sub-module is configured to receive the facial image data and voice data of the target user sent by the mobile terminal based on the problem template and the video call connection.

[0233] In an exemplary embodiment, the first verification module 1302 includes:

[0234] The first verification sub-module is configured to perform a real-person verification and a lie verification on the target user based on the facial image data, and obtain a first verification result.

[0235] The first extraction sub-module is configured to, when the first verification result is successful, extract features from the facial image data and the voice data respectively, and obtain facial image feature data and voiceprint feature data.

[0236] The first conversion sub-module is configured to convert the voice data into text to obtain answer text data.

[0237] The first determination sub-module is configured to determine an initial verification result based on the answer text data, the target item data, the facial image feature data, and the voiceprint feature data.

[0238] In an exemplary embodiment, the first determination sub-module includes:

[0239] The first acquisition sub-module is configured to obtain the original facial image feature data and the original voiceprint feature data of the target user based on the target user identifier of the target user.

[0240] The first judgment sub-module is configured to judge whether the target item data and the answer text data are consistent, and obtain a first judgment result.

[0241] The first calculation sub-module is configured to calculate a first similarity between the original facial image feature data and the facial image feature data, and calculate a second similarity between the original voiceprint feature data and the voiceprint feature data.

[0242] The second judgment sub-module is configured to judge whether the first similarity and the second similarity reach a preset similarity condition, and obtain a second judgment result.

[0243] The second determination sub-module is configured to determine an initial verification result based on the first judgment result and the second judgment result.

[0244] In an exemplary embodiment, the information security device 1300 further includes:

[0245] An update module, configured to update the verification times in case the initial verification result fails.

[0246] A judgment module, configured to judge whether the verification times reach a preset verification times threshold.

[0247] A second execution module, configured to execute the step of receiving the facial image data and voice data of the target user sent by the mobile terminal in case the verification times do not reach the verification times threshold.

[0248] In an exemplary embodiment, the generation module 1303 includes a second acquisition sub-module and a first generation sub-module. Among them, the first generation sub-module includes:

[0249] A third judgment sub-module, configured to judge whether the network status data indicates that the network of the terminal is unobstructed.

[0250] A second generation sub-module, configured to determine the verification code algorithm as the jigsaw verification code algorithm if the network status data indicates that the network of the terminal is unobstructed, and generate an identity verification code based on the jigsaw verification code algorithm.

[0251] A third generation sub-module, configured to determine the verification code algorithm as the digital verification code algorithm if the network status data indicates that the network of the terminal is congested, and generate an identity verification code based on the digital verification code algorithm.

[0252] In an exemplary embodiment, the second generation sub-module includes a third determination sub-module and a fourth generation sub-module. Among them, the fourth generation sub-module includes:

[0253] A fourth determination sub-module, configured to randomly generate verification digits and determine verification pictures in the picture database.

[0254] A segmentation sub-module, configured to segment the verification pictures to obtain each verification picture area, and establish an association relationship between each verification digit and each verification picture area.

[0255] A combination sub-module, configured to combine the verification digits on each verification picture area in the order of the verification pictures to obtain a verification answer.

[0256] A sorting sub-module, configured to randomly sort each verification picture area to obtain an identity verification code.

[0257] In an exemplary embodiment, the second verification module 1304 includes a second verification sub-module and a first sending sub-module. Among them, the second verification sub-module includes:

[0258] A second establishment sub-module, configured to send the identity verification code to the mobile terminal and establish a voice call connection with the mobile terminal.

[0259] The second extraction sub-module is used to obtain voice data based on a voice call connection, and perform feature extraction and text conversion on the voice data to obtain voiceprint feature data and voice text data.

[0260] The second calculation sub-module is used to calculate the third similarity between the voiceprint feature data and the original voiceprint feature data of the target user.

[0261] The fourth judgment sub-module is used to judge whether the voice text data is consistent with the verification answer corresponding to the identity verification code, and judge whether the third similarity reaches a preset third similarity threshold to obtain a third judgment result.

[0262] The fifth determination sub-module is used to determine the verification result based on the third judgment result.

[0263] In an exemplary embodiment, as Figure 14 shown, an information security device 1400 is provided, including: a construction module 1401, a sending module 1402, and an execution module 1403, where:

[0264] The construction module 1401 is used to construct an item extraction request based on the user information of the target user and the target item data, and send the item extraction request to the terminal.

[0265] The sending module 1402 is used to collect the facial image data and voice data of the target user based on a collector, and send the facial image data and voice data to the terminal.

[0266] The execution module 1403 is used to receive the verification result of the target user, and execute the extraction process of the target item when the verification result is passed.

[0267] Each module in the above information security device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0268] In an exemplary embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 15As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the data used by the information security method. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. The computer program, when executed by the processor, implements an information security method.

[0269] Those skilled in the art can understand that Figure 15 the structure shown in is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0270] In one embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0271] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0272] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0273] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0274] The information collected in this application is information and data authorized by the user or fully authorized by all parties. For the processing of relevant data, such as collection, storage, use, processing, transmission, provision, disclosure, and application, all comply with the relevant laws, regulations, and standards of relevant countries and regions. Necessary confidentiality measures are taken, which do not violate public order and good customs, and corresponding operation entrances are provided for users to choose to authorize or refuse.

[0275] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0276] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as within the scope described in this specification.

[0277] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. An information security method, characterized in that, The method is applied to a terminal, and the method includes: In response to an item extraction request, receiving facial image data and voice data of a target user sent by a mobile terminal; the item extraction request includes target item data that the target user needs to extract; Based on the target item data, the facial image data, and the voice data, performing identity verification on the target user to obtain an initial verification result; When the initial verification result is passed, obtaining network status data, and generating an identity verification code based on the network status data and a verification code algorithm; Performing identity verification on the target user based on the identity verification code to obtain a verification result, and sending the verification result to the mobile terminal; the verification result is used to extract the target item.

2. The method according to claim 1, wherein The step of, in response to an item extraction request, receiving facial image data and voice data of a target user sent by a mobile terminal includes: In response to an item extraction request of the target user, establishing a video call connection with the mobile terminal; Receiving a detection result of a collector sent by the mobile terminal, and when the detection result is normal, sending a question template to the mobile terminal; Based on the question template and the video call connection, receiving the facial image data and the voice data of the target user sent by the mobile terminal.

3. The method according to claim 1, wherein The step of, based on the target item data, the facial image data, and the voice data, performing identity verification on the target user to obtain an initial verification result includes: Performing a real person verification and a lie verification on the target user based on the facial image data to obtain a first verification result; When the first verification result is successful, respectively extracting features from the facial image data and the voice data to obtain facial image feature data and voiceprint feature data; Performing text conversion on the voice data to obtain answer text data; Based on the answer text data, the target item data, the facial image feature data, and the voiceprint feature data, determining the initial verification result.

4. The method according to claim 3, characterized in that, The step of, based on the answer text data, the target item data, the facial image feature data, and the voiceprint feature data, determining the initial verification result includes: Obtaining original facial image feature data and original voiceprint feature data of the target user based on a target user identifier of the target user; Judging whether the target item data and the answer text data are consistent to obtain a first judgment result; Calculating a first similarity between the original facial image feature data and the facial image feature data, and calculating a second similarity between the original voiceprint feature data and the voiceprint feature data; Judging whether the first similarity and the second similarity reach a preset similarity condition to obtain a second judgment result; Based on the first judgment result and the second judgment result, determining the initial verification result.

5. The method according to claim 1, characterized in that, After performing identity verification on the target user based on the target item data, the facial image data, and the voice data to obtain an initial verification result, the method further includes: When the initial verification result is not passed, updating the verification times; Determine whether the number of verifications reaches a preset verification times threshold; In the case where the number of verifications does not reach the verification times threshold, execute the step of receiving the facial image data and voice data of the target user sent by the mobile terminal.

6. The method according to claim 1, characterized in that The generating the identity verification code based on the network status data and the verification code algorithm includes: Determine whether the network status data indicates that the network of the terminal is unobstructed; If the network status data indicates that the network of the terminal is unobstructed, determine the verification code algorithm as the jigsaw verification code algorithm, and generate the identity verification code based on the jigsaw verification code algorithm; If the network status data indicates that the network of the terminal is congested, determine the verification code algorithm as the digital verification code algorithm, and generate the identity verification code based on the digital verification code algorithm.

7. The method according to claim 6, wherein The generating the identity verification code based on the jigsaw verification code algorithm includes: Randomly generate verification numbers, and determine verification pictures in the picture database; Segment the verification pictures to obtain each verification picture area, and establish an association relationship between each verification number and each verification picture area; Combine the verification numbers on each verification picture area in the order of the verification pictures to obtain a verification answer; Randomly sort each verification picture area to obtain the identity verification code.

8. The method according to claim 1, wherein The performing the identity verification on the target user based on the identity verification code to obtain a verification result includes: Send the identity verification code to the mobile terminal, and establish a voice call connection with the mobile terminal; Based on the voice call connection, obtain voice data, and perform feature extraction and text conversion on the voice data to obtain voice print feature data and voice text data; Calculate a third similarity between the voice print feature data and the original voice print feature data of the target user; Judge whether the voice text data is consistent with the verification answer corresponding to the identity verification code, and judge whether the third similarity reaches a preset third similarity threshold to obtain a third judgment result; Determine the verification result based on the third judgment result.

9. An information security method, characterized in that, The method is applied to a mobile terminal, and the method includes: Construct an item extraction request based on the user information of the target user and the target item data, and send the item extraction request to the terminal; Collect the facial image data and voice data of the target user based on a collector, and send the facial image data and voice data to the terminal; Receive the verification result of the target user, and execute the extraction process of the target item in the case where the verification result is passed.

10. An information security device, characterized in that, The device includes: A receiving module, configured to receive the facial image data and voice data of the target user sent by the mobile terminal in response to an item extraction request; the item extraction request includes the target item data that the target user needs to extract; A first verification module, configured to perform identity verification on the target user based on the target item data, the facial image data, and the voice data to obtain an initial verification result; A generating module, configured to, in the case where the initial verification result is passed, obtain network status data, and generate an identity verification code based on the network status data and a verification code algorithm; A second verification module, configured to perform identity verification on the target user based on the identity verification code, obtain a verification result, and send the verification result to the mobile terminal; the verification result is used to extract the target item.

11. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 or 9 are implemented.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 or 9 are implemented.

Images