WO2020206906A1

WO2020206906A1 - Registration information processing method and apparatus, computer device, and storage medium

Info

Publication number: WO2020206906A1
Application number: PCT/CN2019/102575
Authority: WO
Inventors: 郭荣
Original assignee: 平安科技（深圳）有限公司
Priority date: 2019-04-12
Filing date: 2019-08-26
Publication date: 2020-10-15
Also published as: CN110099047A; CN110099047B

Abstract

A registration information processing method, comprising: randomly generating first verification information according to a registration request sent by a terminal, and generating second verification information on the basis of the first verification information; sending the first verification information and the second verification information to the terminal; receiving first voice information corresponding to the first verification information and second voice information corresponding to the second verification information returned by the terminal; extracting a first voiceprint feature corresponding to the first voice information and a second voiceprint feature corresponding to the second voice information; calculating a voiceprint error between the first voiceprint feature and the second voiceprint feature; determining a user type according to user information carried in the registration request, and determining whether the voiceprint error is within an error range corresponding to the corresponding user type; and if yes, completing account registration on the basis of the user information, obtaining a preset virtual resource, and transferring the virtual resource to an account.

Description

Registration information processing method, device, computer equipment and storage medium

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on April 12, 2019. The application number is 2019102956718 and the application name is "registered information processing methods, devices, computer equipment, and storage media". The entire content is by reference Incorporated in this application.

Technical field

This application relates to a registration information processing method, device, computer equipment and storage medium.

Background technique

At present, many application developers will promote applications based on marketing activities to attract new users to register and use them through marketing activities, thereby increasing the user activity of the application. For example, newly registered users can receive coupons, receive cash red envelopes, participate in discounts, etc. . In order to receive a large number of rewards for newly registered users, some malicious users perform batch spam registration on the application, which reduces the effectiveness of application information push and causes a waste of interactive resources.

Summary of the invention

According to various embodiments disclosed in the present application, a registration information processing method, apparatus, computer equipment, and storage medium are provided.

A registration information processing method, executed by a computer device, the method comprising: receiving a registration request sent by a terminal; the registration request carries user information; randomly generating first verification information according to the registration request, and generating a first verification information based on the first verification information 2. Verification information; sending the first verification information and the second verification information to the terminal; receiving the first voice information corresponding to the first verification information and the second verification information returned by the terminal Corresponding second voice information; extract the first voiceprint feature corresponding to the first voice information, and the second voiceprint feature corresponding to the second voice information; calculate the first voiceprint feature and the second voiceprint feature Voiceprint errors between voiceprint features; determine the user type according to the user information, obtain the error range corresponding to the user type, and determine whether the voiceprint error is within the error range; and if it is within the error range, Complete account registration based on the user information, obtain preset virtual resources, and transfer the virtual resources to the account.

In one of the embodiments, the registration request sent by the receiving terminal includes: monitoring the application review record generated by the target website displayed by the user browsing terminal; detecting whether the application review record contains user identification information; The user is marked as a target user; the application review record is analyzed to obtain the application requirement information of each target user; the target program link corresponding to each target user is generated according to the application requirement information; the target program link is pushed according to the user identification information To the terminal corresponding to the corresponding target user; and receiving the registration request sent by the terminal based on the target program link.

In one of the embodiments, the randomly generating the first verification information according to the registration request includes: obtaining the device verification information corresponding to the terminal according to the registration request; performing a hash operation on the device verification information to obtain the current hash; Identify whether the same device hash exists in the historical registration data; and if not, randomly generate the first verification information.

In one of the embodiments, the randomly generating the first verification information according to the registration request and generating the second verification information based on the first verification information includes: sending the randomly generated first verification information to the terminal according to the registration request; Receive the first voice information corresponding to the first verification information returned by the terminal; extract the first voiceprint feature corresponding to the first voice information; identify whether there is a similarity to the first voiceprint feature in the historical registration data User's voiceprint feature whose degree exceeds the threshold; and if not, generating second verification information based on the first verification information.

In one of the embodiments, the extracting the first voiceprint feature corresponding to the first voice information includes: parsing the first voice information to obtain a corresponding acoustic wave signal; framing the acoustic wave signal to obtain A plurality of single-frame acoustic wave signals; Fourier transform is performed on each single-frame acoustic wave signal to obtain a corresponding frequency spectrum. Extracting a single-frame voiceprint feature from the frequency spectrum; and generating a first voiceprint feature corresponding to the first voice information according to the single-frame voiceprint feature of each frame.

In one of the embodiments, after transferring the virtual resource to the account, the method further includes: receiving an assistance request sent by a terminal; the assistance request carries an application program identifier; and sending the assistance request to the terminal according to the assistance request Return to the authorization application page; monitor the selection of multiple assistance options of the terminal on the authorization application page; and when the selected assistance option is a synchronous observation option, call the assistance component to the user’s page based on the application During the operation, screen recording is performed, and the recording information is synchronized to the assisting terminal corresponding to the application identifier, so that the assisting terminal performs abnormal location based on the recording information.

A registration information processing device, the device comprising: a registration request module for receiving a registration request sent by a terminal; the registration request carries user information; a registration verification module for randomly generating first verification information based on the registration request; The first verification information generates second verification information; sending the first verification information and the second verification information to the terminal; receiving the first voice information corresponding to the first verification information returned by the terminal, and Second voice information corresponding to the second verification information; extract the first voiceprint feature corresponding to the first voice information, and the second voiceprint feature corresponding to the second voice information; calculate the first voice The voiceprint error between the fingerprint feature and the second voiceprint feature; determine the user type according to the user information, obtain the error range corresponding to the user type, and determine whether the voiceprint error is within the error range; And a resource transfer module, configured to complete account registration based on the user information, obtain a preset virtual resource, and transfer the virtual resource to the account if it is within the error range.

In one of the embodiments, the registration request module is also used to monitor the application review record generated by the target website displayed by the user browsing terminal; detect whether the application review record contains user identification information; if so, mark the user For the target user; analyze the application review records to obtain the application demand information of each target user; generate the target program link corresponding to each target user according to the application demand information; push the target program link to the corresponding target according to the user identification information A terminal corresponding to the user; and receiving a registration request sent by the terminal based on the target program link.

A computer device includes a memory and one or more processors. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps of the registration information processing method provided in any embodiment of the present application are implemented.

One or more non-volatile computer-readable storage media storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors implement any one of the embodiments of the present application. Provide the steps of the registration information processing method.

The details of one or more embodiments of the application are set forth in the following drawings and description. Other features and advantages of this application will become apparent from the description, drawings and claims.

Description of the drawings

In order to more clearly describe the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

Fig. 1 is an application scenario diagram of the registration information processing method according to one or more embodiments.

Fig. 2 is a schematic flowchart of a method for processing registration information according to one or more embodiments.

Fig. 3 is a schematic flowchart of steps of generating first verification information according to one or more embodiments.

Fig. 4 is a schematic flowchart of the steps of generating verification information according to one or more embodiments.

Fig. 5 is a structural block diagram of a registration information processing device according to one or more embodiments.

Figure 6 is a block diagram of a computer device according to one or more embodiments.

detailed description

In order to make the technical solutions and advantages of the present application clearer, the following further describes the present application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the application, and not used to limit the application.

The registration information processing method provided in this application can be applied to the application environment shown in FIG. 1. The terminal 102 and the server 104 communicate through the network. The terminal 102 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The server 104 may be implemented by an independent server or a server cluster composed of multiple servers.

When the user needs to register an application, the terminal 102 can send a registration request to the server 104. The registration request carries user information, such as gender and age. The server 104 randomly generates the first verification information according to the registration request, and sends the first verification information to the terminal 102. The user enters the first voice information corresponding to the first verification information through the terminal 102, and the terminal 102 sends the first voice information to the server 104. The server 104 extracts the first voiceprint feature corresponding to the first voice information, and recognizes whether there is a baseline voiceprint feature whose similarity to the first voiceprint feature exceeds a threshold in the historical registration data. If it does not exist, the server 104 generates second verification information based on the first verification information, and sends the second verification information to the terminal 102. The user enters the second voice information corresponding to the second verification information through the terminal 102, and the terminal 102 sends the second voice information to the server 104. The server 104 extracts the second voiceprint feature corresponding to the second voice information, and calculates the voiceprint error between the first voiceprint feature and the second voiceprint feature. The server 104 pre-stores error intervals corresponding to multiple user types. The server 104 determines the user type of the registered user according to the user information, obtains the error interval corresponding to the user type, and determines whether the voiceprint error is within the error interval. If it is within the error interval, the server 104 obtains the corresponding virtual resource and transfers the virtual resource to the account 102. In the above application registration process, based on multiple voice verifications, malicious registration situations such as multiple registrations of the same person or bots pretending to register can be accurately identified, thereby improving the effectiveness of application information push and saving interactive resources.

In one of the embodiments, as shown in FIG. 2, a method for processing registration information is provided. Taking the method applied to the server in FIG. 1 as an example for description, the method includes the following steps:

Step 202: Receive a registration request sent by the terminal; the registration request carries user information.

Step 204, randomly generating first verification information according to the registration request, and generating second verification information based on the first verification information; sending the first verification information and the second verification information to the terminal.

The first verification information may be randomly generated text information, such as a string formed by splicing multiple characters. The characters can be at least one of numbers, Chinese characters, or letters. The first verification information may also be a randomly generated reading audio containing text information, such as a reading audio of one or more words and sentences. The sentence to be read can be collected from a variety of data sources. The first verification information may also be a randomly generated reading video containing text information. It is easy to understand that if the first verification information is a reading audio or a reading video, the first verification information also includes tone information of the text information.

The second verification information includes other text information that is different from the first verification information. The second verification information may also be randomly generated text information, reading audio or reading video. In order to improve the recognition rate of malicious registration, there is a big difference between the second verification information and the first verification information for the registered user's reading tone requirements.

Step 206: Receive the first voice information corresponding to the first verification information and the second voice information corresponding to the second verification information returned by the terminal.

Step 208: Extract the first voiceprint feature corresponding to the first voice information and the second voiceprint feature corresponding to the second voice information; calculate the voiceprint error between the first voiceprint feature and the second voiceprint feature.

In one of the embodiments, extracting the first voiceprint feature corresponding to the first voice information includes: parsing the first voice information to obtain the corresponding acoustic wave signal; framing the acoustic wave signal to obtain multiple single-frame acoustic wave signals; Each single-frame sound wave signal is Fourier transformed to obtain the corresponding frequency spectrum. Extract the single-frame voiceprint feature from the frequency spectrum; generate the first voiceprint feature corresponding to the first voice information according to the single-frame voiceprint feature of each frame.

The sound wave signal is information about the frequency and amplitude of the sound wave. The sound wave signal specifically uses the frequency of the sound as the ordinate and time as the abscissa, reflecting the information that the frequency of the sound changes with time. Framing is to set consecutive time points as one frame. Framing the sound wave signal may specifically be to divide the sound wave signal into a number of sound wave signals whose abscissa interval is the frame length according to a preset frame length.

Fourier transform is a way to convert a time domain function into a frequency domain function. The frequency spectrum is information about the frequency distribution of sound. The frequency spectrum specifically takes the frequency of the sound as the abscissa, and the amplitude and phase of the frequency components as the ordinate, which represents the distribution of the amplitude of each frequency sine wave at a static time point. The Fourier transform is performed on the sound wave signal of each frame to obtain the corresponding frequency spectrum. Specifically, the corresponding trigonometric function of the sound wave signal of each frame is converted into the frequency spectrum within each frame time.

Step 210: Determine the user type according to the user information, obtain the error range corresponding to the user type, and determine whether the voiceprint error is within the error range.

The voiceprint error is used to describe the matching degree of the voiceprint features contained in the voice information entered twice before and after the registered user. The server calculates the voiceprint error by superimposing the frequency spectrum of the first voiceprint feature and the frequency spectrum of the second voiceprint feature. For example, the frequency spectrum of the first voiceprint feature and the frequency spectrum of the second voiceprint feature can be overlapped and displayed, the single-frame difference of the corresponding amplitude and phase at each same sound frequency can be identified, and the preset logic of multiple single-frame differences can be performed Operation, the operation result is recorded as the voiceprint error between the first voiceprint feature and the second voiceprint feature. The preset logic operation can be summation or overlap addition based on preset weights. It is easy to understand that the voiceprint error can also be calculated in other ways, and there is no restriction on this. User information includes age, gender, etc. According to the user information, the server can determine the user type of the registered user. The server pre-stores the error range of voiceprint features corresponding to multiple user types. The server obtains the error range corresponding to the user type of the currently registered user, and determines whether the voiceprint error is within the obtained error range.

Step 212: If within the error range, complete account registration based on user information, obtain preset virtual resources, and transfer the virtual resources to the account.

If the voiceprint error of different voice messages inputted multiple times exceeds the upper limit of the error range, it means that the two voice messages may come from different registered users, making it difficult for the server to subsequently perform user identity verification based on voiceprint characteristics. In this case, in order to avoid shutting out the real registered users, the server can re-send the randomly generated verification information to the terminal in the above-mentioned manner, that is, give the user a chance to register again.

If the voiceprint error of different voice messages input multiple times is lower than the lower limit of the error range, it means that the two voice messages are exactly the same, which may come from batch malicious registration of robots. In this case, the server can permanently or temporarily cancel the registration authority of the corresponding terminal.

If the voiceprint error of different voice information input multiple times is within the error range, it means that the registered user has passed the validity check. The server completes the account registration based on the user information, obtains the preset virtual resources, and transfers the virtual resources to the account. Comparing the voiceprint error of different voice information input multiple times with the error range, compared with the traditional registration verification method, it can provide the registration verification accuracy rate.

In this embodiment, the first verification character can be randomly generated according to the registration request sent by the terminal; the second verification character can be generated based on the first verification character; the first verification character and the second verification character are sent to the terminal, and the terminal return can be received The first voice information corresponding to the first verification character and the second voice information corresponding to the second verification character can be extracted to obtain the first voiceprint feature corresponding to the first voice information and the second voice information corresponding to the second voice information. Fingerprint characteristics; according to the user information carried in the registration request, the user type can be determined; by calculating the voiceprint error between the first voiceprint feature and the second voiceprint feature, and obtaining the error range corresponding to the user type, the voiceprint error can be judged Whether it is within the error range; if it is within the error range, you can obtain the preset virtual resources and transfer the virtual resources to the account. The user is authenticated by comparing the voiceprint error of different voice messages entered multiple times with the error range. Only through the authentication can the virtual resources be transferred to the registered user, which can increase the user registration threshold and reduce malicious registration to obtain rewards. Risks, thereby improving the effectiveness of application information push and saving interactive resources.

In one of the embodiments, receiving the registration request sent by the terminal includes: monitoring the application review record generated by the target website displayed by the user browsing the terminal; detecting whether the application review record contains user identification information; if so, marking the user as the target user Analyze the application review records to obtain the application demand information of each target user; generate the target program link corresponding to each target user according to the application demand information; push the target program link to the terminal corresponding to the corresponding target user according to the user identification information; The registration request sent by the receiving terminal based on the target program link.

Users with app registration intentions may leave app review records on the target website. The target website can be an application download platform or a browser. The application review record may be a user's search record for application-related information on the target website, or a consultation record for the application provider's customer service. In order to be able to actively discover the target user, the server crawls the application review records of different users from the specified target website according to a preset time frequency.

The server parses the application review record and detects whether the application review record contains user identification information. User identification information refers to information that can uniquely identify a user, such as mobile phone number, mailbox number, social account number, etc. In another embodiment, the user identification information may also be a terminal identification, such as a hardware identification code or an IP address. If the application review record contains user identification information, the corresponding user is marked as the target user.

It should be noted that the depth of application review by different users on the target website and the level of detail of the corresponding application review records are different, so that the relevant information of the target user obtained by analysis can be different, for example, the application requirement information other than the user identification information can be obtained by analysis . Application demand information refers to information that can characterize which types of applications the user is interested in, or the application functions that the user expects to be able to achieve.

The server determines each target application that may be of interest to the target user according to the application requirement information, and pushes the target program link corresponding to the target application to the terminal corresponding to the target user based on the user identification information. The target user can send a registration request to the server based on the target program link.

In this embodiment, actively discovering target customers by crawling application review records can not only speed up the efficiency of target users in acquiring target applications, but also improve the pertinence of application information push, thereby improving the effectiveness of application information push.

In one of the embodiments, as shown in FIG. 3, randomly generating the first verification information according to the registration request, and the steps of generating the first verification information include:

Step 302: Obtain device verification information corresponding to the terminal according to the registration request.

The device verification information includes a variety of terminal identifications, such as IP addresses, hardware identification codes, etc.

Step 304: Perform a hash operation on the device verification information to obtain the current hash.

The multiple terminal identifiers are spliced in a preset format to obtain a spliced string, and the spliced string is hashed.

Step 306: Identify whether the same device hash exists in the historical registration data.

Step 308, if not, randomly generate first verification information.

In this embodiment, not only the voiceprint features are used to verify the registered users, but also the registered device is verified, which can improve the accuracy of malicious registration identification; in addition, compared to the traditional method of restricting the number of IP address access registrations to prevent malicious registration, it will be more The registration verification after the terminal identification is spliced can increase the cost of malicious registration and can further improve the accuracy of malicious registration identification.

In one of the embodiments, as shown in Figure 4, the first verification information is randomly generated according to the registration request, and the second verification information is generated based on the first verification information, that is, the step of generating verification information includes:

Step 402: Send randomly generated first verification information to the terminal according to the registration request.

Step 404: Receive the first voice information corresponding to the first verification information returned by the terminal.

Step 406: Extract the first voiceprint feature corresponding to the first voice information.

It is easy to understand that if the first voiceprint feature has been extracted here, there is no need to repeat the extraction in step 208.

Step 408: Identify whether there is a user's voiceprint feature whose similarity to the first voiceprint feature exceeds a threshold in the historical registration data.

Step 410, if not, generate second verification information based on the first verification information.

The historical registration data includes not only the voiceprint characteristics of users who have successfully registered, but also the voiceprint characteristics of users who have failed to register. First, identify whether there is a user's voiceprint feature whose similarity to the first voiceprint feature exceeds a threshold in the historical registration data, that is, identify whether someone has already registered based on the voiceprint feature. If it exists, it can already signify that the current registered user has the risk of "multiple registrations by the same person". In order to save server resources, the server no longer generates the second verification information to continue verification at this time. Only when there is no user voiceprint feature whose similarity exceeds the threshold in the historical registration data, the server generates the second verification information based on the first verification information.

In this embodiment, only when there is no user's voiceprint feature whose similarity exceeds the threshold in the historical registration data, the second verification information is generated to reduce unnecessary verification process, improve registration verification efficiency, and save server resources.

In one of the embodiments, after the virtual resource is transferred to the account, it further includes: receiving the assistance request sent by the terminal; the assistance request carries the application identifier; returning the authorization application page to the terminal according to the assistance request; monitoring the terminal in the authorization application page Selection operation of multiple assistance options; when the selected assistance option is a synchronous observation option, the assistance component is called to screen the user's application-based page operation process, and the recording information is synchronized to the assistance terminal corresponding to the application identifier. Enable the assisting terminal to locate abnormalities based on the recorded information.

The user uses the application program on the terminal (denoted as the "first terminal"). When the application program is abnormal, the application program can send a remote assistance request to the second terminal corresponding to one or more preset developers. In another embodiment, the user sends a remote assistance request to the server based on the application at the first terminal, and the server forwards the remote assistance request to the designated second terminal.

If the developer does not respond to the remote assistance request triggered by the user for a long time, the user needs to re-initiate the remote assistance request at another time, and the user may forget the abnormal problem at this time, which reduces the efficiency of abnormal location. In order to be able to respond to the remote assistance request triggered by the user in a timely manner, the server forwards the remote assistance request. After the server forwards the remote assistance request to the preset second terminal corresponding to one or more developers, it detects whether there is a second terminal responding to the remote assistance request within the preset time. The preset time can be set freely according to actual needs, such as 10 minutes.

If the second terminal does not respond to the remote assistance request within the preset time, the server responds to the remote assistance request in time and sends a screen recording request to the first terminal. When the user authorizes the screen recording request on the first terminal, the first terminal calls the first component to screen the user's application-based page operation process, and sends the recording information to the server for storage. The subsequent developers can use the second The terminal reads the recorded information from the server, and then locates the abnormality, which avoids the cumbersome feedback of the abnormality by the user multiple times.

The remote assistance request carries the user's corresponding application account. When a developer responds to the remote assistance request based on the second terminal within the preset time, the second terminal sends a remote connection request to the first terminal according to the application account, and after the remote connection, the second terminal sends an authorization application page to the first terminal. The authorization application page includes simultaneous observation options and remote control options.

The user can select options on the first terminal, and then authorize the developer to synchronously observe or remotely control the running status of the application on the first terminal. The first terminal captures the user's selected operation on the authorization application page, and adopts a corresponding abnormal location strategy based on the selected information. Specifically, the first component is pre-integrated in the application. The first component is used to perform screen recording of the user's application-based page operation process according to the user's selected operation on the synchronous observation option, and synchronously display the recorded information on the second terminal. Establishing a connection between the second terminal and the first terminal allows developers to view the flow of the user's operation of the application in real time. At the same time, the recording information can be screenshots and stored during the viewing process for repeated viewing.

In another embodiment, the second component is also pre-integrated in the application. The second component is used to synchronously display the window where the application program is located on the second terminal according to the user's selected operation on the remote control option, so that the second terminal can remotely control the application program and then perform abnormal location. If the developer finds that the application is abnormal due to an error in the operation process, he can initiate an authorization application to the first terminal again, so as to be able to remotely control the first terminal, and then provide operation guidance to the user to improve the efficiency of troubleshooting.

In this embodiment, since the user only needs to operate the application on his own terminal, the abnormality of the application can be displayed to the developer in real time, which saves the user from repeating the cumbersome description of the abnormality and improves the problem location of the developer. The efficiency and accuracy of the application program, thereby improving the effectiveness of application information promotion.

It should be understood that although the various steps in the flowcharts of FIGS. 2 to 4 are displayed in sequence as indicated by the arrows, these steps are not necessarily performed in sequence in the order indicated by the arrows. Unless specifically stated in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least some of the steps in Figures 2 to 4 may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. These sub-steps or The execution order of the stages is not necessarily carried out sequentially, but may be executed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.

In one of the embodiments, as shown in FIG. 5, a registration information processing device is provided, including: a registration request module 502, a registration verification module 504, and a resource transfer module 506, wherein:

The registration request module 502 is used to receive a registration request sent by the terminal; the registration request carries user information.

The registration verification module 504 is configured to randomly generate first verification information according to the registration request, and generate second verification information based on the first verification information; send the first verification information and the second verification information to the terminal; The first voice information corresponding to the information, and the second voice information corresponding to the second verification information; extract the first voiceprint feature corresponding to the first voice information, and the second voiceprint feature corresponding to the second voice information; calculate the first The voiceprint error between the voiceprint feature and the second voiceprint feature; determine the user type according to the user information, obtain the error range corresponding to the user type, and determine whether the voiceprint error is within the error range.

The resource transfer module 506 is configured to complete account registration based on user information, obtain preset virtual resources, and transfer the virtual resources to the account if it is within the error range.

In one of the embodiments, the registration request module 502 is also used to monitor the application review records generated by the target website displayed on the user browsing terminal; detect whether the application review records contain user identification information; if so, mark the user as the target user; The application review records are analyzed to obtain the application requirement information of each target user; the target program link corresponding to each target user is generated according to the application requirement information; the target program link is pushed to the terminal corresponding to the corresponding target user according to the user identification information; the receiving terminal A registration request sent based on the target program link.

In one of the embodiments, the registration verification module 504 is further configured to obtain device verification information corresponding to the terminal according to the registration request; perform a hash operation on the device verification information to obtain the current hash; and identify whether the same device exists in the historical registration data. Greek; if not, the first verification information is randomly generated.

In one of the embodiments, the registration verification module 504 is further configured to send randomly generated first verification information to the terminal according to the registration request; receive the first voice information corresponding to the first verification information returned by the terminal; and extract the first voice information corresponding to the The first voiceprint feature; identify whether there is a user's voiceprint feature whose similarity with the first voiceprint feature exceeds the threshold in the historical registration data; if not, generate second verification information based on the first verification information.

In one of the embodiments, the registration verification module 504 is also used to parse the first voice information to obtain the corresponding acoustic wave signal; divide the acoustic wave signal into frames to obtain multiple single-frame acoustic wave signals; perform Fourier Fourier on each single-frame acoustic wave signal Transform to get the corresponding frequency spectrum. Extract the single-frame voiceprint feature from the frequency spectrum; generate the first voiceprint feature corresponding to the first voice information according to the single-frame voiceprint feature of each frame.

In one of the embodiments, the device further includes an application assistance module 508 for receiving an assistance request sent by the terminal; the assistance request carries the application program identifier; the authorization application page is returned to the terminal according to the assistance request; the monitoring terminal is in the authorization application page Selection operation of multiple assistance options; when the selected assistance option is a synchronous observation option, the assistance component is called to screen the user's application-based page operation process, and the recording information is synchronized to the assistance terminal corresponding to the application identifier. Enable the assisting terminal to locate abnormalities based on the recorded information.

Regarding the specific limitation of the registration information processing device, please refer to the above limitation of the registration information processing method, which will not be repeated here. Each module in the above-mentioned registered information processing device may be implemented in whole or in part by software, hardware, and a combination thereof. The foregoing modules may be embedded in the form of hardware or independent of the processor in the computer device, or may be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the foregoing modules.

In one of the embodiments, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. 6. The computer equipment includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide calculation 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, computer readable instructions and a database. The internal memory provides an environment for the operation of the operating system and computer-readable instructions in the non-volatile storage medium. The database of the computer equipment is used to store historical verification data. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer-readable instruction is executed by the processor to realize a registration information processing method.

Those skilled in the art can understand that the structure shown in FIG. 6 is only a block diagram of part of the structure 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 Including more or fewer parts than shown in the figure, or combining some parts, or having a different arrangement of parts.

One or more non-volatile storage media storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors realize the registration provided in any embodiment of the present application Information processing method steps.

Persons of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by computer-readable instructions to instruct relevant hardware. The computer-readable instructions can be stored in a non-volatile computer readable. In the storage medium, when the computer-readable instructions are executed, they may include the procedures of the above-mentioned method embodiments. Wherein, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and/or volatile memory. Non-volatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not a limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Channel (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction between the combinations of these technical features, they should It is considered as the range described in this specification.

The above examples only express several implementation manners of the present application, and the description is relatively specific and detailed, but it should not be understood as a limitation on the scope of the invention patent. It should be pointed out that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can be made, and these all fall within the protection scope of this application. Therefore, the scope of protection of the patent of this application shall be subject to the appended claims.

Claims

A method for processing registration information, executed by a computer device, the method including:

Receiving a registration request sent by the terminal; the registration request carries user information;

Randomly generating first verification information according to a registration request, generating second verification information based on the first verification information; sending the first verification information and the second verification information to the terminal;

Receiving first voice information corresponding to the first verification information and second voice information corresponding to the second verification information returned by the terminal;

Extract the first voiceprint feature corresponding to the first voice information and the second voiceprint feature corresponding to the second voice information; calculate the voice between the first voiceprint feature and the second voiceprint feature Pattern error

Determine the user type according to the user information, obtain the error range corresponding to the user type, and determine whether the voiceprint error is within the error range; and

If it is within the error range, complete account registration based on the user information, obtain a preset virtual resource, and transfer the virtual resource to the account.
The method according to claim 1, wherein the receiving the registration request sent by the terminal comprises: monitoring application review records generated by the target website displayed by the user browsing the terminal;

Detecting whether the application review record contains user identification information;

If yes, mark the user as the target user;

Analyze the application review records to obtain the application requirement information of each target user;

Generating a target program link corresponding to each target user according to the application requirement information;

Push the target program link to the terminal corresponding to the corresponding target user according to the user identification information; and

The registration request sent by the receiving terminal based on the target program link.
The method according to claim 1, wherein the randomly generating the first verification information according to the registration request comprises:

Obtaining device verification information corresponding to the terminal according to the registration request;

Perform a hash operation on the device verification information to obtain the current hash;

Identify whether the same device hash exists in the historical registration data; and

If not, the first verification information is randomly generated.
The method according to claim 1, wherein said randomly generating first verification information according to a registration request and generating second verification information based on said first verification information comprises:

Sending randomly generated first verification information to the terminal according to the registration request;

Receiving the first voice information corresponding to the first verification information returned by the terminal;

Extracting the first voiceprint feature corresponding to the first voice information;

Identifying whether there is a user's voiceprint feature whose similarity to the first voiceprint feature exceeds a threshold in the historical registration data; and

If not, generate second verification information based on the first verification information.
The method according to claim 1, wherein the extracting the first voiceprint feature corresponding to the first voice information comprises:

Parse the first voice information to obtain a corresponding sound wave signal;

Framing the sound wave signal to obtain multiple single-frame sound wave signals;

Performing Fourier transform on each of the single-frame acoustic signals to obtain a corresponding frequency spectrum;

Extracting single-frame voiceprint features from the frequency spectrum; and

The first voiceprint feature corresponding to the first voice information is generated according to the single-frame voiceprint feature of each frame.
The method according to claim 1, wherein after the transferring the virtual resource to the account, the method further comprises:

Receiving an assistance request sent by the terminal; the assistance request carries an application program identifier;

Returning an authorization application page to the terminal according to the assistance request;

Monitor the selection of multiple assistance options of the terminal on the authorization application page; and

When the selected assistance option is the synchronous observation option, the assistance component is called to record the user's screen based on the page operation process of the application, and the recording information is synchronized to the assistance terminal corresponding to the application identifier, so that the assistance terminal Perform abnormal location based on recorded information.
A registration information processing device, characterized in that the device includes:

The registration request module is used to receive the registration request sent by the terminal; the registration request carries user information;

The registration verification module is configured to randomly generate first verification information according to a registration request, and generate second verification information based on the first verification information; send the first verification information and the second verification information to the terminal; receive The first voice information corresponding to the first verification information and the second voice information corresponding to the second verification information returned by the terminal; the first voiceprint feature corresponding to the first voice information is extracted, and the The second voiceprint feature corresponding to the second voice information; calculate the voiceprint error between the first voiceprint feature and the second voiceprint feature; determine the user type according to the user information, and obtain the user type correspondence Determine whether the voiceprint error is within the error range;

The resource transfer module is configured to complete account registration based on the user information if within the error range, obtain preset virtual resources, and transfer the virtual resources to the account.
The device according to claim 7, wherein the registration request module is further used to monitor the application review records generated by the target website displayed by the user browsing terminal; detect whether the application review records contain user identification information; if so, Then mark the user as the target user; analyze the application review record to obtain the application requirement information of each target user; generate the target program link corresponding to each target user according to the application requirement information; The program link is pushed to the terminal corresponding to the corresponding target user; the registration request sent by the terminal based on the target program link is received.
A computer device includes a memory and one or more processors. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the one or more processors, the one or more Each processor performs the following steps:

Receiving a registration request sent by the terminal; the registration request carries user information;

Randomly generating first verification information according to a registration request, generating second verification information based on the first verification information; sending the first verification information and the second verification information to the terminal;

Receiving first voice information corresponding to the first verification information and second voice information corresponding to the second verification information returned by the terminal;

Extract the first voiceprint feature corresponding to the first voice information and the second voiceprint feature corresponding to the second voice information; calculate the voice between the first voiceprint feature and the second voiceprint feature Pattern error

Determine the user type according to the user information, obtain the error range corresponding to the user type, and determine whether the voiceprint error is within the error range; and

If it is within the error range, complete account registration based on the user information, obtain a preset virtual resource, and transfer the virtual resource to the account.
The computer device according to claim 9, wherein the processor further executes the following steps when executing the computer-readable instruction:

Monitor the application access records generated by the target website displayed by the user browsing terminal;

Detecting whether the application review record contains user identification information;

If yes, mark the user as the target user;

Analyze the application review records to obtain the application requirement information of each target user;

Generating a target program link corresponding to each target user according to the application requirement information;

Push the target program link to the terminal corresponding to the corresponding target user according to the user identification information; and

The registration request sent by the receiving terminal based on the target program link.
The computer device according to claim 9, wherein the processor further executes the following steps when executing the computer-readable instruction:

Obtaining device verification information corresponding to the terminal according to the registration request;

Perform a hash operation on the device verification information to obtain the current hash;

Identify whether the same device hash exists in the historical registration data; and

If not, the first verification information is randomly generated.
The computer device according to claim 9, wherein the processor further executes the following step when executing the computer-readable instruction: sending randomly generated first verification information to the terminal according to a registration request;

Receiving the first voice information corresponding to the first verification information returned by the terminal;

Extracting the first voiceprint feature corresponding to the first voice information;

Identifying whether there is a user's voiceprint feature whose similarity to the first voiceprint feature exceeds a threshold in the historical registration data; and

If not, generate second verification information based on the first verification information.
The computer device according to claim 9, wherein the processor further executes the following steps when executing the computer-readable instruction:

Parse the first voice information to obtain a corresponding sound wave signal;

Framing the sound wave signal to obtain multiple single-frame sound wave signals;

Performing Fourier transform on each of the single-frame acoustic signals to obtain a corresponding frequency spectrum;

Extracting single-frame voiceprint features from the frequency spectrum; and

The first voiceprint feature corresponding to the first voice information is generated according to the single-frame voiceprint feature of each frame.
The computer device according to claim 9, wherein the processor further executes the following steps when executing the computer-readable instruction:

Receiving an assistance request sent by the terminal; the assistance request carries an application program identifier;

Returning an authorization application page to the terminal according to the assistance request;

Monitor the selection of multiple assistance options of the terminal on the authorization application page; and

When the selected assistance option is the synchronous observation option, the assistance component is called to record the user's screen based on the page operation process of the application, and the recording information is synchronized to the assistance terminal corresponding to the application identifier, so that the assistance terminal Perform abnormal location based on recorded information.
One or more non-volatile computer-readable storage media storing computer-readable instructions, which when executed by one or more processors, cause the one or more processors to perform the following steps:

Receiving a registration request sent by the terminal; the registration request carries user information;

Randomly generating first verification information according to a registration request, generating second verification information based on the first verification information; sending the first verification information and the second verification information to the terminal;

Receiving first voice information corresponding to the first verification information and second voice information corresponding to the second verification information returned by the terminal;

Extract the first voiceprint feature corresponding to the first voice information and the second voiceprint feature corresponding to the second voice information; calculate the voice between the first voiceprint feature and the second voiceprint feature Pattern error

Determine the user type according to the user information, obtain the error range corresponding to the user type, and determine whether the voiceprint error is within the error range; and

If it is within the error range, complete account registration based on the user information, obtain a preset virtual resource, and transfer the virtual resource to the account.
The storage medium according to claim 15, wherein the following steps are further executed when the computer-readable instructions are executed by the processor:

Monitor the application access records generated by the target website displayed by the user browsing terminal;

Detecting whether the application review record contains user identification information;

If yes, mark the user as the target user;

Analyze the application review records to obtain the application requirement information of each target user;

Generating a target program link corresponding to each target user according to the application requirement information;

Push the target program link to the terminal corresponding to the corresponding target user according to the user identification information; and

The registration request sent by the receiving terminal based on the target program link.
The storage medium according to claim 15, wherein the following steps are further executed when the computer-readable instructions are executed by the processor:

Obtaining device verification information corresponding to the terminal according to the registration request;

Perform a hash operation on the device verification information to obtain the current hash;

Identify whether the same device hash exists in the historical registration data; and

If not, the first verification information is randomly generated.
The storage medium according to claim 15, wherein the following steps are further executed when the computer-readable instructions are executed by the processor:

Sending randomly generated first verification information to the terminal according to the registration request;

Receiving the first voice information corresponding to the first verification information returned by the terminal;

Extracting the first voiceprint feature corresponding to the first voice information;

Identifying whether there is a user's voiceprint feature whose similarity to the first voiceprint feature exceeds a threshold in the historical registration data; and

If not, generate second verification information based on the first verification information.
The storage medium according to claim 15, wherein the following steps are further executed when the computer-readable instructions are executed by the processor:

Parse the first voice information to obtain a corresponding sound wave signal;

Framing the sound wave signal to obtain multiple single-frame sound wave signals;

Performing Fourier transform on each of the single-frame acoustic signals to obtain a corresponding frequency spectrum;

Extracting single-frame voiceprint features from the frequency spectrum; and

The first voiceprint feature corresponding to the first voice information is generated according to the single-frame voiceprint feature of each frame.
The storage medium according to claim 15, wherein the following steps are further executed when the computer-readable instructions are executed by the processor:

Receiving an assistance request sent by the terminal; the assistance request carries an application program identifier;

Returning an authorization application page to the terminal according to the assistance request;

Monitor the selection of multiple assistance options of the terminal on the authorization application page; and

When the selected assistance option is the synchronous observation option, the assistance component is called to record the user's screen based on the page operation process of the application, and the recording information is synchronized to the assistance terminal corresponding to the application identifier, so that the assistance terminal Perform abnormal location based on recorded information.