Group Chat Component Method, System, Device and Medium Based on Encrypted Identity

Abstract

The present invention discloses a method, system, device and medium for group chat components based on encrypted identities, which relates to the technical field of identity authentication. It includes obtaining the user's account information, trusted address and multiple groups of audio data, analyzing the multiple groups of audio data, and outputting a feature picture; obtaining a login request, judging the verification information, and outputting address analysis information or account risk information; judging the requested address, and outputting secure login information or performing voiceprint recognition processing based on feature information. The present invention is used to solve the problem in the prior art that due to the lack of analysis of encrypting identity information using the user's biometric characteristics, when the user's device is lost and the password information is cracked, the asymmetric encryption method cannot prevent others from viewing chat information, resulting in the leakage of important information in practical applications.

Description

Technical Field

[0001] The present invention relates to the technical field of identity authentication, and specifically to a method, system, device and medium for group chat components based on encrypted identities. Background Art

[0002] Identity authentication technology is an effective solution generated in the process of confirming the identity of an operator in a computer network; all information in the computer network world, including the identity information of users, is represented by a specific set of data. Computers can only recognize the digital identity of users. How to ensure that the operator who operates with a digital identity is the legal owner of this digital identity is what identity authentication technology aims to solve. As the first line of defense for protecting network assets, identity authentication plays a crucial role.

[0003] Existing improvements for identity encryption usually involve increasing the complexity of encrypting identity information, making it more difficult for attackers to crack all the identity information. For example, in the Chinese patent with the publication number CN112511310A, a method for obfuscating encrypted identity blind signatures is disclosed. This solution generates a private key that is difficult to obtain through cracking by using asymmetric encryption. However, the existing improvement methods lack an analysis of encrypting identity information using the user's biometric characteristics. This can lead to the situation where when the user's device is lost and the password information is cracked, the asymmetric encryption method cannot prevent others from viewing chat information, resulting in the leakage of important information in practical applications. In view of this, it is necessary to improve the existing identity encryption. Summary of the Invention

[0004] The present invention aims to solve at least one of the technical problems in the existing technology to some extent. By improving identity encryption, it is used to solve the problem in the existing technology that due to the lack of analysis of encrypting identity information using the user's biometric characteristics, when the user's device is lost and the password information is cracked, the asymmetric encryption method cannot prevent others from viewing chat information, resulting in the leakage of important information in practical applications.

[0005] To achieve the above object, in a first aspect, the present invention provides a method for group chat components based on encrypted identities, including:

[0006] Obtain the user's account information, trusted address, and multiple sets of audio data, analyze the multiple sets of audio data, and output feature information based on the analysis results;

[0007] Obtain a login request, where the login request includes verification information and a request address, judge the verification information based on the account information, and output address analysis information or account risk information based on the judgment result;

[0008] Judge the request address based on the address analysis information and the trusted address, output the secure login information based on the judgment result, or perform voiceprint recognition processing based on the feature information, and output the secure login information or the account risk information based on the voiceprint recognition processing result.

[0009] Further, the account information includes the registered account and the registered password. Obtain the user's account information, trusted address, and multiple groups of audio data, analyze the multiple groups of audio data, and the feature information output based on the analysis result includes:

[0010] When the user uses the intelligent device to perform the registration operation, obtain the registered account and the registered password input by the user, associate the registered account with the registered password, and jointly mark them as the account information;

[0011] Store the account information in the account information database;

[0012] Obtain the IP address used by the intelligent device and mark it as the trusted address;

[0013] Perform voiceprint acquisition processing, and the voiceprint acquisition processing includes:

[0014] Set fixed acquisition samples, and the acquisition samples include a first quantity of text; display the acquisition samples and the acquisition button on the display screen of the intelligent device, and use prompt words to remind the user to interact with the acquisition button and read aloud the acquisition samples;

[0015] When the user interacts with the acquisition button, start recording, and when the user ends the interaction with the acquisition button, stop recording; upload the recorded audio data to the server, and the audio data also includes the duration;

[0016] Perform the voiceprint acquisition processing of the first quantity again.

[0017] Further, the feature information includes the average duration, feature pictures, maximum amplitude, number of feature peaks, and feature area. Analyze multiple groups of voiceprint information, and the feature information output based on the analysis result also includes:

[0018] Obtain the duration of each audio information and mark them as the acquisition time respectively;

[0019] Combine all the acquisition times in pairs to obtain multiple time combinations;

[0020] Calculate the absolute value of the difference between the acquisition times in the time combination and mark it as the time difference;

[0021] Calculate the average value of the time differences and mark it as the average time difference;

[0022] When the average time difference is greater than the time difference threshold, output the duration invalid information;

[0023] When the average time difference is less than or equal to the time difference threshold, calculate the average value of all acquisition times, mark it as the average duration, and output the average duration.

[0024] Furthermore, analyzing multiple groups of voiceprint information, the feature information output based on the analysis results further includes:

[0025] Convert all audio data into a voiceprint waveform diagram, where the voiceprint waveform diagram includes a coordinate system with the horizontal axis as time and the vertical axis as amplitude, and a sound wave picture in the coordinate system;

[0026] Obtain the maximum amplitude in any one voiceprint waveform diagram, and mark it as the maximum amplitude;

[0027] Use the peak straight line y = (1 - k)×Vm to divide the voiceprint waveform diagram to obtain multiple discontinuous regions above the peak straight line, and mark them as peak regions; where Vm is the maximum amplitude and k is a constant;

[0028] Obtain the number of peak regions, and mark it as the peak number;

[0029] For other voiceprint waveform diagrams, use the peak straight line y = (1 - k)×Vm to divide the voiceprint waveform diagram and obtain the peak numbers in other voiceprint waveform diagrams;

[0030] Calculate the average value of all peak numbers, and mark it as the characteristic peak number; calculate the absolute value of the difference between all peak numbers and the characteristic peak number respectively, and mark it as the floating value;

[0031] Mark the largest floating value as the floating threshold;

[0032] Select any one voiceprint waveform diagram and mark it as the initial diagram; place other voiceprint waveform diagrams in the coordinate system of the initial diagram in turn to obtain the final characteristic picture;

[0033] Specify that the area of a single pixel point is 1, calculate the area of the characteristic picture, and mark it as the characteristic area.

[0034] Furthermore, obtain a login request, judge the verification information based on the account information, and the address analysis information or account risk information output based on the judgment result includes:

[0035] Set the login times i with an initial value of 0;

[0036] Execute the login judgment process, and the login judgment process includes:

[0037] Obtain the verification information input by the user and the IP address of the intelligent device, and mark the IP address as the verification address; the verification information includes a verification account and a verification password;

[0038] Query the account information database to check if there is a registered account identical to the verified account. If not, output blank account information;

[0039] If so, retrieve the password associated with the registered account identical to the verified account;

[0040] Compare whether the password is the same as the comparison information. If they are the same, output address analysis information; if not, increment i by one;

[0041] Judge whether i is equal to the login count threshold. When i is less than the login count threshold, perform the login judgment process again;

[0042] When i is equal to the login count threshold, output account risk information.

[0043] Furthermore, based on the address analysis information and the trusted address, judge the request address, and based on the judgment result, output secure login information or perform voiceprint recognition processing based on the feature information. Based on the voiceprint recognition processing result, output secure login information or account risk information, including:

[0044] When receiving the address analysis information, judge whether the verification address is the same as the trusted address;

[0045] If they are the same, output secure login information; if not, perform voiceprint recognition processing and output secure login information or account risk information based on the voiceprint recognition processing result.

[0046] Furthermore, the voiceprint recognition processing includes:

[0047] Display the acquisition sample and the acquisition button on the display screen of the intelligent device, and use a prompt word to remind the user to interact with the acquisition button and read the acquisition sample aloud;

[0048] When the user interacts with the acquisition button, start recording. When the user ends the interaction with the acquisition button, stop recording; mark the recorded audio data as detection data and upload the detection data to the server; the detection data includes the detection duration;

[0049] Convert the detection data into a voiceprint waveform diagram and mark it as the detection waveform diagram;

[0050] Use the peak straight line y=(1 - k)×Vm to divide the detection waveform diagram to obtain the number of peaks in the detection waveform diagram;

[0051] Calculate the difference between the number of peaks and the characteristic peak number, and mark it as the characteristic quantity difference;

[0052] Compare the size of the characteristic quantity difference with the floating threshold. When the characteristic quantity difference is greater than the floating threshold, output account risk information and end the voiceprint recognition processing; when the characteristic quantity difference is less than or equal to the floating threshold, enter the subsequent analysis step;

[0053] Calculate the area of the detected waveform diagram, marked as the detected area;

[0054] Place the detected waveform diagram in the coordinate system where the feature picture is located, calculate the overlapping area between the detected waveform diagram and the feature picture, and mark the overlapping area;

[0055] Calculate the area of the feature picture that does not overlap with the detected waveform diagram, marked as the difference area;

[0056] Calculate the ratio of the overlapping area to the detected area, marked as the overlapping judgment value;

[0057] Calculate the ratio of the difference area to the feature area, marked as the difference judgment value;

[0058] When receiving invalid duration information, perform area judgment processing, and the area judgment processing includes:

[0059] When the overlapping judgment value is greater than or equal to the overlapping judgment threshold and the difference judgment value is less than the difference judgment threshold, output secure login information; when the overlapping judgment value is less than the overlapping judgment threshold or the difference judgment threshold is greater than or equal to the difference judgment threshold, output account risk information;

[0060] When receiving the average duration, calculate the absolute value of the difference between the detected duration and the average duration, marked as the detected difference; when the detected difference is less than or equal to the time difference threshold, perform area judgment processing; when the detected difference is greater than the time difference threshold, output account risk information.

[0061] In a second aspect, the present invention further provides a group chat component system based on encrypted identities, including an account registration module, a login detection module, and an identity verification module; the account registration module is used to obtain the user's account information, trusted address, and multiple sets of voiceprint information;

[0062] The login detection module is used to obtain a login request, the login request includes verification information and a request address, judge the verification information based on the account information, and output address analysis information or account risk information based on the judgment result;

[0063] The identity verification module is used to analyze multiple sets of voiceprint information and output feature information based on the analysis result; judge the request address based on the address analysis information and the trusted address, and output secure login information based on the judgment result or perform voiceprint recognition processing based on the feature information, and output secure login information or account risk information based on the voiceprint recognition processing result.

[0064] In a third aspect, the present application provides an electronic device, including a processor and a memory, the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the above method are run.

[0065] In a fourth aspect, the present application provides a storage medium, on which a computer program is stored. When the computer program is executed by a processor, it runs the steps in the above method.

[0066] Advantages of the present invention: By obtaining the user's IP address and multiple sets of audio data of the user during user registration, setting the IP address as a trusted address, then calculating and analyzing the duration of the audio data, determining whether the durations between multiple sets of audio data are stable, and outputting an average duration based on the calculation and analysis results; the advantage of this is that by setting a trusted address, when the user logs in while connected to a trusted network, they only need to enter the correct account and password to log in successfully, without the need to verify the user's identity, improving the intelligence of identity verification; by analyzing the duration of the audio data, it is possible to determine whether the user's reading is regular. If it is determined that there is regularity, the duration is also analyzed during the identity authentication process, which can improve the accuracy of identity authentication;

[0067] The present invention also analyzes the audio data, outputs the characteristic information of the audio data, performs voiceprint recognition processing based on the characteristic information, and finally determines the security of the login operation according to the voiceprint recognition processing result; the advantage of this is that voiceprint features are similar to fingerprint features and facial features. Different users have their unique voiceprint features, and users may store photos containing their own facial features. In the case of device loss, static facial features are relatively easy to leak; while there are still significant differences between the voiceprint features of others who deliberately imitate and the user's own voiceprint features. Using voiceprint information for identity authentication improves the security of identity encryption. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 is a schematic block diagram of the system of the present invention;

[0069] Figure 2 is a flowchart of the steps of the method of the present invention;

[0070] Figure 3 is a schematic diagram of the characteristic picture of the present invention;

[0071] Figure 4 is a schematic diagram of the detection waveform diagram of the present invention;

[0072] Figure 5 is a schematic diagram of the superposition of the characteristic picture and the detection waveform diagram of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0073] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0074] Example 1, in the first aspect, please refer to Figure 1 As shown, the present invention provides a group chat component system based on encrypted identities, including an account registration module, a login detection module, and an identity authentication module; the account registration module is used to obtain the user's account information, trusted address, and multiple groups of voiceprint information;

[0075] The account registration module is configured with an account registration policy, and the account registration policy includes:

[0076] When the user uses a smart device for registration operations, obtain the registration account and registration password input by the user, associate the registration account and the registration password, and jointly mark them as account information;

[0077] Store the account information in the account information database;

[0078] Obtain the IP address used by the smart device and mark it as the trusted address;

[0079] It should be noted that taking a home router and a WiFi network as an example, when the user uses a mobile phone to connect to the network, the router will receive a request for the mobile phone to connect to the network and automatically assign a fixed IP address within the range restricted by the router rules to the mobile phone according to the protocol, that is, the DHCP function; if the mobile phone also enables the DCHP function, it will automatically receive the IP address assigned by the router. As long as the user does not select "Forget Network" and reconnect to the network, this IP address is fixed; combined with the fact that the signal coverage of existing routers for home or enterprise use is usually small, it can be proved that there is no risk of logging in from a different location when connecting to a saved WiFi network;

[0080] On the other hand, for users using a mobile network, due to the continuous change of the location and signal strength of the mobile device, the network operator may frequently change the IP address of the device to maintain a stable network connection;

[0081] By setting a trusted IP address, the user can directly log in in a safe environment without identity authentication; for example, when connecting to a company network or a home network, the user only needs to enter the correct account and password to log in; in addition, the present invention also provides a trusted address setting function, enabling the user to set other IP addresses as trusted addresses when connecting to a trusted network.

[0082] Perform voiceprint acquisition and processing, where the voiceprint acquisition and processing includes:

[0083] Set fixed acquisition samples, where the acquisition samples include a first quantity of characters; display the acquisition samples and an acquisition button on the display screen of the intelligent device, and use a prompt word to remind the user to interact with the acquisition button and read aloud the acquisition samples;

[0084] It should be noted that the acquisition samples are set to 10 Chinese characters that are semantically incoherent. The purpose of being semantically incoherent is to have obvious pauses between each Chinese character, facilitating highlighting the user's unique reading habits, and thus making the feature pictures obtained in subsequent steps representative.

[0085] A preferred prompt word is: "Please long-press and click the button, and read aloud the text displayed on the screen. Stop clicking after finishing reading.";

[0086] When the user interacts with the acquisition button, start recording. When the user finishes interacting with the acquisition button, stop recording; upload the recorded audio data to the server, and the audio data also includes the duration;

[0087] Perform the voiceprint acquisition and processing for the first number of times again;

[0088] In specific implementation, the first number is set to 4, and a total of 5 groups of audio data can be obtained; the time interval between two voiceprint acquisition and processing operations should be no less than 5 s to prevent the user's speech rate from changing due to continuous repeated reading of the same content for multiple times, thus affecting the analyzed feature information.

[0089] The login detection module is used to obtain a login request, where the login request includes verification information and a request address, judge the verification information based on the account information, and output address analysis information or account risk information based on the judgment result;

[0090] The login detection module is configured with a login detection strategy, and the login detection strategy includes:

[0091] Set the login count i with an initial value of 0;

[0092] Perform login judgment processing, where the login judgment processing includes:

[0093] Obtain the verification information input by the user and the IP address of the intelligent device, and mark the IP address as the verification address; the verification information includes a verification account and a verification password;

[0094] Query in the account information database whether there is a registered account identical to the verification account. If not, output account blank information;

[0095] If it exists, retrieve the password associated with the registered account identical to the verification account;

[0096] Compare whether the password is the same as the comparison information. If they are the same, output the address analysis information; if not, increment i by one.

[0097] Determine whether i is equal to the login count threshold. When i is less than the login count threshold, perform the login judgment process again.

[0098] When i is equal to the login count threshold, output the account risk information.

[0099] In specific implementation, the login count threshold is set to 5. When the account is entered incorrectly, it is impossible to determine whether the password is incorrect, and there is no value in analysis. Therefore, when the account is entered incorrectly, only the account blank information is output to prompt the user that the account does not exist, and no subsequent analysis is performed. In addition, considering that the user may accidentally touch or confuse with other passwords, resulting in incorrect password input, the login count threshold is set to 5, providing 5 password attempt opportunities. When all 5 attempts are incorrect, it is sufficient to determine that there is a risk with the account.

[0100] The identity authentication module is used to analyze multiple groups of voiceprint information and output a feature picture based on the analysis result; judge the request address based on the address analysis information and the trusted address, and output the secure login information based on the judgment result or perform voiceprint recognition processing based on the feature picture, and output the secure login information or the account risk information based on the voiceprint recognition processing result.

[0101] The identity authentication module is configured with a speech rate analysis strategy, and the speech rate analysis strategy includes:

[0102] Obtain the duration of each audio information and mark it as the acquisition time respectively.

[0103] Combine all the acquisition times in pairs to obtain multiple time combinations.

[0104] Calculate the absolute value of the difference between the acquisition times in the time combination and mark it as the time difference.

[0105] Calculate the average value of the time differences and mark it as the average time difference.

[0106] When the average time difference is greater than the time difference threshold, output the duration invalid information.

[0107] In specific implementation, the time difference threshold is set to 2s. Based on the user's reading habit, theoretically, when reading the same text discontinuously, the required time difference is about 1s. When the time difference threshold is set to 2s, when the average time difference is greater than 2s, it is sufficient to prove that the user's reading speed is irregular and there is a situation of being sometimes fast and sometimes slow. At this time, output the duration invalid information and do not analyze the duration in subsequent analysis; conversely, when the average time difference is less than 2s, it means that the user's reading speed fluctuates within a small range and there is a pattern, and the average duration can be calculated and the duration will be included in the analysis in subsequent analysis.

[0108] When the average time difference is less than or equal to the time difference threshold, calculate the average value of all acquisition times, mark it as the average duration, and output the average duration.

[0109] Please refer to Figure 3 as shown in Figure 3 where L2 is the peak region of the voiceprint waveform diagram, and L1 is the peak straight line; from Figure 3 it can be seen that there are a total of 4 peak numbers in the voiceprint waveform diagram;

[0110] The identity authentication module is also configured with a voiceprint analysis strategy, and the voiceprint analysis strategy includes:

[0111] Convert all audio data into a voiceprint waveform diagram. The voiceprint waveform diagram includes a coordinate system with the horizontal axis as time and the vertical axis as amplitude, and the sound wave picture in the coordinate system;

[0112] It should be noted that libraries such as librosa in Python can be used to process audio data, and plotting libraries such as matplotlib in Python can be used to draw the voiceprint waveform diagram;

[0113] Obtain the maximum amplitude in any voiceprint waveform diagram and mark it as the maximum amplitude;

[0114] Use the peak straight line y = (1 - k) × Vm to divide the voiceprint waveform diagram to obtain multiple discontinuous regions above the peak straight line, and mark them as peak regions; where Vm is the maximum amplitude and k is a constant;

[0115] In specific implementation, k is taken as 0.1;

[0116] Obtain the number of peak regions and mark it as the peak number;

[0117] For other voiceprint waveform diagrams, use the peak straight line y = (1 - k) × Vm to divide the voiceprint waveform diagram and obtain the peak numbers in other voiceprint waveform diagrams;

[0118] Calculate the average value of all peak numbers and mark it as the characteristic peak number; calculate the absolute value of the difference between each peak number and the characteristic peak number respectively, and mark it as the floating value;

[0119] Mark the largest floating value as the floating threshold;

[0120] Select any voiceprint waveform diagram and mark it as the initial diagram; sequentially place other voiceprint waveform diagrams in the coordinate system of the initial diagram to obtain the final characteristic picture;

[0121] Specify that the area of a single pixel point is 1, calculate the area of the characteristic picture, and mark it as the characteristic area;

[0122] It should be noted that when the boundary of the acoustic wave picture is located in a certain pixel point, this point is also included in the calculation of the feature area.

[0123] The authentication module is also configured with an address analysis policy, and the address analysis policy includes:

[0124] When receiving the address analysis information, determine whether the verification address is the same as the trusted address;

[0125] If they are the same, output the secure login information; if they are different, perform voiceprint recognition processing, and output the secure login information or account risk information based on the voiceprint recognition processing result.

[0126] The authentication module is also configured with a voiceprint verification policy, and the voiceprint verification policy includes:

[0127] Display the collected sample and the collection button on the display screen of the intelligent device, and use prompt words to remind the user to interact with the collection button and read aloud the collected sample;

[0128] When the user interacts with the collection button, start recording. When the user ends the interaction with the collection button, stop recording; mark the recorded audio data as the detection data and upload the detection data to the server; the detection data includes the detection duration.

[0129] Please refer to Figure 4 as shown Figure 4 The result obtained by dividing the detection waveform diagram using the same peak straight line as the voiceprint waveform diagram. It can be seen from the figure that the number of peaks in the figure is 2;

[0130] Convert the detection data into a voiceprint waveform diagram and mark it as the detection waveform diagram;

[0131] Use the peak straight line y=(1-k)×Vm to divide the detection waveform diagram to obtain the number of peaks in the detection waveform diagram;

[0132] Calculate the difference between the number of peaks and the characteristic peak number, and mark it as the characteristic number difference;

[0133] Compare the size of the characteristic number difference with the floating threshold. When the characteristic number difference is greater than the floating threshold, output the account risk information and end the voiceprint recognition processing; when the characteristic number difference is less than or equal to the floating threshold, enter the subsequent analysis step;

[0134] Calculate the area of the detection waveform diagram and mark it as the detection area;

[0135] Place the detection waveform diagram in the coordinate system where the feature picture is located, calculate the overlapping area between the detection waveform diagram and the feature picture, and mark the overlapping area;

[0136] Calculate the area of the feature picture that does not overlap with the detection waveform diagram, and mark it as the difference area;

[0137] Calculate the ratio of the overlapping area to the detected area, and mark it as the overlapping judgment value;

[0138] Calculate the ratio of the difference area to the feature area, and mark it as the difference judgment value;

[0139] When receiving invalid duration information, perform area judgment processing, and the area judgment processing includes:

[0140] When the overlapping judgment value is greater than or equal to the overlapping judgment threshold and the difference judgment value is less than the difference judgment threshold, output secure login information; when the overlapping judgment value is less than the overlapping judgment threshold or the difference judgment value is greater than or equal to the difference judgment threshold, output account risk information;

[0141] In specific implementation, the overlapping judgment threshold is set to 90%, and the difference judgment value is set to 10%;

[0142] It should be noted that since the vertical axis of the coordinate system in the voiceprint waveform diagram is amplitude, when the amplitudes of the detected waveform diagrams are all small amplitudes, the situation where all the detected waveform diagrams overlap with the feature pictures will occur. At this time, the overlapping judgment value is equal to 100%, as Figure 5 shown; Figure 5 In, T1 is the difference area region, and T2 is the overlapping area region. It can be seen from the information in the figure that the detected waveform diagram is completely included in the feature picture. The calculated overlapping judgment value is 1, but there are many regions in the feature picture that do not overlap with the detected waveform diagram, and it can be judged that the voiceprint features are not similar; therefore, when implementing the voiceprint verification strategy, it is necessary to comprehensively judge by combining the analysis of the overlapping judgment value and the difference judgment value;

[0143] When receiving the average duration, calculate the absolute value of the difference between the detected duration and the average duration, and mark it as the detection difference; when the detection difference is less than or equal to the time difference threshold, perform area judgment processing; when the detection difference is greater than the time difference threshold, output account risk information.

[0144] Embodiment 2, Second aspect, please refer to Figure 2 shown, the present invention also provides a group chat component method based on encrypted identity, including:

[0145] Step S1, obtain the user's account information, trusted address, and multiple groups of audio data, analyze the multiple groups of audio data, and output feature information based on the analysis results; Step S1 further includes the following sub-steps:

[0146] Step S1011, when the user uses a smart device to perform a registration operation, obtain the registration account and registration password input by the user, associate the registration account and the registration password, and jointly mark them as account information; store the account information in the account information database;

[0147] Step S1012: Obtain the IP address used by the intelligent device and mark it as a trusted address;

[0148] Step S1013: Perform voiceprint acquisition processing, and the voiceprint acquisition processing includes:

[0149] Step S1014: Set fixed acquisition specimens, and the acquisition specimens include a first quantity of characters; display the acquisition specimens and an acquisition button on the display screen of the intelligent device, and use prompt words to remind the user to interact with the acquisition button and read aloud the acquisition specimens;

[0150] Step S1015: When the user interacts with the acquisition button, start recording, and when the user ends the interaction with the acquisition button, stop recording; upload the recorded audio data to the server, and the audio data also includes the duration;

[0151] Step S1016: Perform the voiceprint acquisition processing for the first number of times again.

[0152] Step S1021: Obtain the duration of each audio information and mark them as acquisition times respectively;

[0153] Step S1022: Combine all the acquisition times in pairs to obtain multiple time combinations;

[0154] Step S1023: Calculate the absolute value of the difference between the acquisition times in the time combination and mark it as the time difference;

[0155] Step S1024: Calculate the average value of the time differences and mark it as the average time difference; when the average time difference is greater than the time difference threshold, output duration invalid information; when the average time difference is less than or equal to the time difference threshold, calculate the average value of all the acquisition times and mark it as the average duration, and output the average duration;

[0156] Step S1031: Convert all the audio data into a voiceprint waveform diagram, and the voiceprint waveform diagram includes a coordinate system with the horizontal axis as time and the vertical axis as amplitude and a sound wave picture in the coordinate system;

[0157] Step S1032: Obtain the maximum amplitude in any one of the voiceprint waveform diagrams and mark it as the maximum amplitude;

[0158] Step S1033: Use the peak straight line y = (1 - k)×Vm to divide the voiceprint waveform diagram to obtain multiple discontinuous regions above the peak straight line and mark them as peak regions; where Vm is the maximum amplitude and k is a constant;

[0159] Step S1034: Obtain the number of peak regions and mark it as the peak number;

[0160] Step S1035: For other voiceprint waveform diagrams, use the peak straight line y = (1 - k) × Vm to divide the voiceprint waveform diagrams, and obtain the number of peaks in the other voiceprint waveform diagrams;

[0161] Step S1036: Calculate the average value of all the number of peaks, and mark it as the characteristic peak number; calculate the absolute value of the difference between all the number of peaks and the characteristic peak number respectively, and mark it as the floating value;

[0162] Step S1037: Mark the maximum floating value as the floating threshold;

[0163] Step S1038: Select any one voiceprint waveform diagram and mark it as the initial diagram; sequentially place the other voiceprint waveform diagrams in the coordinate system of the initial diagram to obtain the final characteristic picture;

[0164] Step S1039: Specify that the area of a single pixel point is 1, calculate the area of the characteristic picture, and mark it as the characteristic area.

[0165] Step S2: Obtain a login request. The login request includes verification information and a request address. Judge the verification information based on the account information, and output address analysis information or account risk information based on the judgment result; Step S2 also includes the following sub-steps:

[0166] Step S201: Set the login times i with an initial value of 0;

[0167] Step S202: Execute the login judgment process. The login judgment process includes:

[0168] Obtain the verification information input by the user and the IP address of the intelligent device, and mark the IP address as the verification address; the verification information includes a verification account and a verification password;

[0169] Query in the account information database whether there is a registered account the same as the verification account. If not, output account blank information;

[0170] If it exists, retrieve the password associated with the registered account the same as the verification account;

[0171] Compare whether the password is the same as the comparison information. If it is the same, output address analysis information; if it is not the same, increment i by one;

[0172] Judge whether i is equal to the login times threshold. When i is less than the login times threshold, execute the login judgment process again;

[0173] When i is equal to the login times threshold, output account risk information.

[0174] Step S3: Based on the address analysis information and the trusted address, judge the request address, and output secure login information based on the judgment result, or perform voiceprint recognition processing based on the feature information, and output secure login information or account risk information based on the voiceprint recognition processing result. Step S3 further includes the following sub-steps:

[0175] Step S3011: When receiving the address analysis information, judge whether the verification address is the same as the trusted address;

[0176] Step S3012: If they are the same, output secure login information; if they are different, perform voiceprint recognition processing, and output secure login information or account risk information based on the voiceprint recognition processing result;

[0177] The voiceprint recognition processing includes:

[0178] Step S3021: Display the acquisition sample and the acquisition button on the display screen of the intelligent device, and use prompt words to remind the user to interact with the acquisition button and read the acquisition sample;

[0179] Step S3022: When the user interacts with the acquisition button, start recording, and when the user ends the interaction with the acquisition button, stop recording; mark the recorded audio data as detection data, and upload the detection data to the server; the detection data includes the detection duration;

[0180] Step S3023: Convert the detection data into a voiceprint waveform diagram and mark it as a detection waveform diagram;

[0181] Use the peak straight line y = (1 - k) × Vm to divide the detection waveform diagram to obtain the number of peaks in the detection waveform diagram;

[0182] Calculate the difference between the number of peaks and the number of characteristic peaks, and mark it as the characteristic quantity difference;

[0183] Compare the size of the characteristic quantity difference with the floating threshold. When the characteristic quantity difference is greater than the floating threshold, output account risk information and end the voiceprint recognition processing; when the characteristic quantity difference is less than or equal to the floating threshold, calculate the area of the detection waveform diagram and mark it as the detection area;

[0184] Step S3024: Place the detection waveform diagram in the coordinate system where the characteristic picture is located, calculate the overlapping area between the detection waveform diagram and the characteristic picture, and mark the overlapping area;

[0185] Step S3025: Calculate the area of the characteristic picture that does not overlap with the detection waveform diagram, and mark it as the difference area;

[0186] Step S3026: Calculate the ratio of the overlapping area to the detection area, and mark it as the overlapping judgment value; calculate the ratio of the difference area to the characteristic area, and mark it as the difference judgment value;

[0187] Step S3027, when the duration invalid information is received, perform area judgment processing, and the area judgment processing includes:

[0188] When the coincidence judgment value is greater than or equal to the coincidence judgment threshold and the difference judgment value is less than the difference judgment threshold, output secure login information; when the coincidence judgment value is less than the coincidence judgment threshold or the difference judgment threshold is greater than or equal to the difference judgment threshold, output account risk information;

[0189] Step S3028, when the average duration is received, calculate the absolute value of the difference between the detection duration and the average duration, and mark it as the detection difference; when the detection difference is less than or equal to the time difference threshold, perform area judgment processing; when the detection difference is greater than the time difference threshold, output account risk information.

[0190] Embodiment 3, In a third aspect, the present application provides an electronic device, including a processor and a memory, the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the above method are run. Through the above technical solution, the processor and the memory are interconnected and communicate with each other through a communication bus and / or other forms of connection mechanisms. The memory stores a computer program executable by the processor. When the electronic device runs, the processor executes the computer program to execute the method in any optional implementation manner of the above embodiment to achieve the following functions: obtain the user's account information, trusted address, and multiple groups of audio data, analyze the multiple groups of audio data, and output a feature picture; obtain a login request, judge the verification information, and output address analysis information or account risk information; judge the requested address, and output secure login information or perform voiceprint recognition processing based on the feature information.

[0191] Embodiment 4, In a fourth aspect, the present application provides a storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method are run. Through the above technical solution, when the computer program is executed by the processor, the method in any optional implementation manner of the above embodiment is executed to achieve the following functions: obtain the user's account information, trusted address, and multiple groups of audio data, analyze the multiple groups of audio data, and output a feature picture; obtain a login request, judge the verification information, and output address analysis information or account risk information; judge the requested address, and output secure login information or perform voiceprint recognition processing based on the feature information.

[0192] In the above embodiments of the present application, the descriptions of each embodiment have their own emphases. For the parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0193] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. Among them, the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. These computer program instructions can also be stored in a computer-readable memory capable of guiding a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured article including an instruction device, and the instruction device implements the functions specified in the process Figure 1 in one process or multiple processes and / or blocks Figure 1 in one block or multiple blocks.

[0194] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For another example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections between each other can be through some communication interfaces. The indirect couplings or communication connections of the devices or units can be electrical, mechanical or other forms.

Claims

1. Method for group chat component based on encrypted identity, characterized in that Including: Obtain the user's account information, trusted address, and multiple groups of audio data, analyze the multiple groups of audio data, and output feature information based on the analysis results; Obtain a login request, where the login request includes verification information and a request address, judge the verification information based on the account information, and output address analysis information or account risk information based on the judgment result; Judge the request address based on the address analysis information and the trusted address, output secure login information based on the judgment result or perform voiceprint recognition processing based on the feature information, and output secure login information or account risk information based on the voiceprint recognition processing result; The account information includes a registered account and a registered password. Obtaining the user's account information, trusted address, and multiple groups of audio data, and analyzing the multiple groups of audio data, and outputting feature information based on the analysis results includes: When the user uses a smart device to perform a registration operation, obtain the registered account and registered password input by the user, associate the registered account and the registered password, and jointly mark them as account information; Store the account information in the account information database; Obtain the IP address used by the smart device and mark it as the trusted address; Perform voiceprint collection processing, and the voiceprint collection processing includes: Set fixed collection specimens, where the collection specimens include a first quantity of text; display the collection specimens and a collection button on the display screen of the smart device, and use prompt words to remind the user to interact with the collection button and read the collection specimens aloud; When the user interacts with the collection button, start recording, and when the user ends the interaction with the collection button, stop recording; upload the recorded audio data to the server, and the audio data also includes the duration; Perform the voiceprint collection processing of the first quantity again; The feature information includes the average duration, feature pictures, maximum amplitude, number of feature peaks, and feature area. Analyzing the multiple groups of voiceprint information, and outputting feature information based on the analysis results also includes: Obtain the duration of each audio information and mark them as collection times respectively; Combine all the collection times in pairs to obtain multiple time combinations; Calculate the absolute value of the difference between the collection times in the time combination and mark it as the time difference; Calculate the average value of the time differences and mark it as the average time difference; When the average time difference is greater than the time difference threshold, output duration invalid information; When the average time difference is less than or equal to the time difference threshold, calculate the average value of all the collection times, mark it as the average duration, and output the average duration; Analyzing the multiple groups of voiceprint information, and outputting feature information based on the analysis results also includes: Convert all the audio data into voiceprint waveform diagrams, where the voiceprint waveform diagrams include a coordinate system with the horizontal axis as time and the vertical axis as amplitude and the sound wave pictures in the coordinate system; Obtain the maximum amplitude in any one of the voiceprint waveform diagrams and mark it as the maximum amplitude; Use the peak straight line y = (1 - k) × Vm to divide the voiceprint waveform diagram to obtain multiple discontinuous regions above the peak straight line and mark them as peak regions; where Vm is the maximum amplitude and k is a constant; Obtain the number of peak regions and mark it as the number of peaks; For other voiceprint waveform diagrams, use the peak straight line y = (1 - k) × Vm to divide the voiceprint waveform diagram and obtain the number of peaks in other voiceprint waveform diagrams; Calculate the average value of all peak numbers and mark it as the characteristic peak number; calculate the absolute value of the difference between all peak numbers and the characteristic peak number respectively, and mark it as the floating value; Mark the largest floating value as the floating threshold; Select any one voiceprint waveform diagram and mark it as the initial diagram; place other voiceprint waveform diagrams in the coordinate system of the initial diagram in turn to obtain the final characteristic picture; Specify that the area of a single pixel is 1, calculate the area of the characteristic picture, and mark it as the characteristic area.

2. The method for an encrypted identity-based group chat component according to claim 1, wherein Obtain a login request, judge the verification information based on the account information, and output address analysis information or account risk information based on the judgment result, including: Set the login count i with an initial value of 0; Execute the login judgment process, and the login judgment process includes: Obtain the verification information input by the user and the IP address of the intelligent device, and mark the IP address as the verification address; the verification information includes the verification account and the verification password; Query in the account information database whether there is a registered account identical to the verification account. If not, output the account blank information; If it exists, retrieve the password associated with the registered account identical to the verification account; Compare whether the password is the same as the comparison information. If it is the same, output the address analysis information; if it is not the same, increment i by one; Judge whether i is equal to the login count threshold. When i is less than the login count threshold, execute the login judgment process again; When i is equal to the login count threshold, output the account risk information.

3. The method for an encrypted identity-based group chat component according to claim 2, wherein Judge the request address based on the address analysis information and the trusted address, and output the secure login information based on the judgment result or perform voiceprint recognition processing based on the characteristic information, and output the secure login information or account risk information based on the voiceprint recognition processing result, including: When receiving the address analysis information, judge whether the verification address is the same as the trusted address; If it is the same, output the secure login information; if it is different, perform voiceprint recognition processing and output the secure login information or account risk information based on the voiceprint recognition processing result.

4. The method for an encrypted identity-based group chat component according to claim 3, wherein The voiceprint recognition processing includes: Display the collection sample and the collection button on the display screen of the intelligent device, and use a prompt word to remind the user to interact with the collection button and read aloud the collection sample; When the user interacts with the collection button, start recording. When the user ends the interaction with the collection button, stop recording; mark the recorded audio data as the detection data and upload the detection data to the server; the detection data includes the detection duration; Convert the detection data into a voiceprint waveform diagram and mark it as the detection waveform diagram; Use the peak straight line y = (1 - k) × Vm to divide the detection waveform diagram and obtain the number of peaks in the detection waveform diagram; Calculate the difference between the peak number and the characteristic peak number and mark it as the characteristic quantity difference; Compare the size of the characteristic quantity difference and the floating threshold. When the characteristic quantity difference is greater than the floating threshold, output the account risk information and end the voiceprint recognition processing; when the characteristic quantity difference is less than or equal to the floating threshold, enter the subsequent analysis step; Calculate the area of the detection waveform diagram and mark it as the detection area. Place the detected waveform diagram in the coordinate system where the feature picture is located, calculate the overlapping area between the detected waveform diagram and the feature picture, and mark the overlapping area; Calculate the area of the feature picture that does not overlap with the detected waveform diagram, and mark it as the difference area; Calculate the ratio of the overlapping area to the detected area, and mark it as the overlapping judgment value; Calculate the ratio of the difference area to the feature area, and mark it as the difference judgment value; When receiving invalid duration information, perform area judgment processing, and the area judgment processing includes: When the overlapping judgment value is greater than or equal to the overlapping judgment threshold and the difference judgment value is less than the difference judgment threshold, output secure login information; when the overlapping judgment value is less than the overlapping judgment threshold or the difference judgment value is greater than or equal to the difference judgment threshold, output account risk information; When receiving the average duration, calculate the absolute value of the difference between the detected duration and the average duration, and mark it as the detection difference; when the detection difference is less than or equal to the time difference threshold, perform area judgment processing; when the detection difference is greater than the time difference threshold, output account risk information.

5. An encrypted identity-based group chat component system, applicable to the encrypted identity-based group chat component method according to any one of claims 1-4, characterized in that, It includes an account registration module, a login detection module, and an identity verification module; the account registration module is used to obtain the user's account information, trusted address, and multiple groups of voiceprint information; The login detection module is used to obtain a login request, the login request includes verification information and a request address, judge the verification information based on the account information, and output address analysis information or account risk information based on the judgment result; The identity verification module is used to analyze multiple groups of voiceprint information and output feature information based on the analysis result; Judge the request address based on the address analysis information and the trusted address, output secure login information based on the judgment result or perform voiceprint recognition processing based on the feature information, and output secure login information or account risk information based on the voiceprint recognition processing result.

6. An electronic device, characterized in that, It includes a processor and a memory, and the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps in the method according to any one of claims 1-4 are run.

7. A storage medium, on which a computer program is stored, characterized in that, When the computer program is executed by the processor, the steps in the method according to any one of claims 1-4 are run.

Images