WO2021135549A1

WO2021135549A1 - Service item processing permissions authorization method and apparatus, computer device, and storage medium

Info

Publication number: WO2021135549A1
Application number: PCT/CN2020/123209
Authority: WO
Inventors: 范灿华; 马骏; 王少军
Original assignee: 平安科技（深圳）有限公司
Priority date: 2020-05-22
Filing date: 2020-10-23
Publication date: 2021-07-08
Also published as: CN111711523B; CN111711523A

Abstract

The present application relates to artificial intelligence biometrics, and discloses a service item processing permissions authorization method and apparatus, a computer device, and a storage medium. If a user identity is confirmed by means of voiceprint recognition and the keyword set corresponding to user speech data includes a first keyword subset, obtaining the name of an authorized person, the verification code of the authorized person, and the title of the authorized service item; if current user speech data transmitted by a user terminal or another user terminal is received, obtaining the corresponding name of the current user and the current verification code; if the name of the current user is identical to the name of the authorized person and the current verification code is identical to the verification code of the authorized person, calling the corresponding current target service item process data and transmitting same to the user terminal or the other user terminal in order according to the process sequence. The method implements identity verification by means of voiceprint recognition, and enables voice authorization of the commission of a third party who is highly familiar with service item processing to help with the service item processing, thereby enhancing user data security and data processing efficiency.

Description

Matter handling authority authorization method, device, computer equipment and storage medium

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on May 22, 2020, the application number is 202010442306.8, and the application name is "method handling authority authorization method, device, computer equipment and storage medium". The entire content of the application is approved The reference is incorporated in this application.

Technical field

This application relates to the field of artificial intelligence biometric technology, and in particular to a method, device, computer equipment, and storage medium for authorization of matter handling authority.

Background technique

At present, intelligent dialogue systems using speech recognition technology have been more and more widely used. For example, in a telecom service scenario, when a user conducts a voice dialogue with an intelligent dialogue system, he can handle various telecom business-related matters, such as recharging phone bills, processing traffic packages, and so on. For example, in a banking business scenario, when a user conducts a voice dialogue with an intelligent dialogue system, he can handle various banking-related matters, such as deposit balance inquiry, appointment of large withdrawal time, and modification of withdrawal password.

The inventor realizes that the existing intelligent dialogue system has the following problems:

1) When the user's identity is identified, it is based on the user password entered by the user. If the password is leaked, the user data will also be at risk of leakage, which reduces the security of the user data;

2) The user's pronunciation standard and the user's proficiency in the system are relatively high, which leads to some users with non-standard pronunciation or low proficiency in the system when handling matters, the system cannot recognize their intention to handle matters. As a result, the operation time becomes longer and even the transaction cannot be successfully handled, which reduces the efficiency of data processing.

Summary of the invention

The embodiment of the application provides a method, device, computer equipment and storage medium for authorization of transaction handling authority, aiming to solve the problem that the intelligent dialogue system in the prior art recognizes the user's identity based on the user password, and the intelligent dialogue system pronounces the user The standards and system use proficiency are high, resulting in low user data security and low data processing efficiency.

In the first aspect, the embodiment of the application provides a method for authorization of transaction handling authority, which includes:

If the user voice data and the user communication identification code sent by the user terminal are received, perform voice recognition and voiceprint recognition on the user voice data to obtain voice text data and voice voiceprint characteristics corresponding to the user voice data;

Judging whether there is a voiceprint feature that is the same as the voice voiceprint feature in the local voiceprint database;

If there is a voiceprint feature that is the same as the voice voiceprint feature in the local voiceprint database, use the corresponding voiceprint feature as the target voiceprint feature to obtain the target user identity information corresponding to the target voiceprint feature;

If the user unique identification information corresponding to the user communication identification code has the same unique user identification code as the target user identification information, the corresponding keyword set is obtained by sequentially performing text segmentation and keyword extraction on the voice text data;

Judging whether the keyword set includes the first keyword sub-set corresponding to authorized others to handle it;

If the keyword set includes the first keyword sub-set corresponding to authorized others to handle, obtain the authorized person's name, the authorized person's verification code, and the authorized item name included in the first keyword sub-set;

According to the received current user voice data corresponding to the first keyword subset sent by the user terminal or other user terminals, call the corresponding current target item process data, and sequentially order the current target item process data according to the process sequence Send to the client or other clients; and

Receive current target item data corresponding to the current target item process data sent by the client or other client terminals.

In the second aspect, an embodiment of the present application provides a matter handling authority authorization device, which includes:

The user voice extraction unit is configured to perform voice recognition and voiceprint recognition on the user voice data if the user voice data and the user communication identification code sent by the user terminal are received to obtain the voice text data and the voice text data corresponding to the user voice data. Voice voiceprint characteristics;

The voiceprint feature comparison unit is used to determine whether there is a voiceprint feature that is the same as the voice voiceprint feature in the local voiceprint database;

The target user identity acquiring unit is configured to, if there is a voiceprint feature that is the same as the voice voiceprint feature in the local voiceprint database, use the corresponding voiceprint feature as the target voiceprint feature to obtain the corresponding voiceprint feature Target user identity information;

The voice keyword extraction unit is used to obtain the unique user identification code by sequentially performing text word segmentation and keyword extraction on the voice text data if the user unique identification information corresponding to the user communication identification code and the target user identification information have the same unique user identification code Corresponding keyword set;

The keyword judgment unit is used to judge whether the keyword set includes the first keyword sub-set corresponding to authorized others to handle;

The authorized person information obtaining unit is used to obtain the name of the authorized person and the authorized person included in the first keyword sub-set if the keyword set includes a first keyword sub-set corresponding to authorized others to handle Verification code and authorized item name;

The current target item process data sending unit is used to call the corresponding current target item process data according to the received current user voice data corresponding to the first keyword subset sent by the user terminal or other user terminals, and transfer the The current target item process data is sent to the client or other clients in sequence in the sequence of the process; and

The current target item data receiving unit is configured to receive the current target item data corresponding to the current target item process data sent by the user terminal or other user terminals.

In a third aspect, an embodiment of the present application provides a computer device, which includes a memory, a processor, and a computer program stored on the memory and running on the processor, and the processor executes the computer The following steps are implemented during the program:

In a fourth aspect, the embodiments of the present application also provide a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, which when executed by a processor causes the processor to perform the following operations :

The embodiment of the application provides a method, device, computer equipment, and storage medium for authorization of transaction handling authority, including if the server confirms the user's identity through voiceprint recognition, the keyword set corresponding to the user's user voice data includes the set of keywords that are related to authorized others to handle the transaction. Corresponding to the first keyword sub-set, obtain the authorized person name, authorized person verification code and authorized item name included in the first keyword sub-set, if the current user sent by the client or other client is received Voice data, obtain the current user’s name and current verification code corresponding to the current user’s voice data through voice recognition and keyword extraction, if the current user’s name is the same as the authorized person’s name and the current verification The code is the same as the authorized person’s verification code, calling the current target item process data stored locally and corresponding to the authorized item name, and sending the current target item process data to the client or other clients in sequence in the process sequence . The method realizes user identity verification based on voiceprint recognition, and can help others with high proficiency in handling entrusted matters by voice authorization, which not only improves the security of user data, but also improves the efficiency of data processing.

Description of the drawings

In order to explain the technical solutions of the embodiments of the present application more clearly, the following will briefly introduce the drawings used in the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present application. Ordinary technicians can obtain other drawings based on these drawings without creative work.

Fig. 1 is a schematic diagram of an application scenario of a method for authorization of matter handling authority provided by an embodiment of the application;

Figure 2 is a schematic flow chart of a method for authorization of matter handling authority provided by an embodiment of the application;

Fig. 3 is a schematic block diagram of a matter handling authority authorization device provided by an embodiment of the application;

Fig. 4 is a schematic block diagram of a computer device provided by an embodiment of the application.

Detailed ways

The technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of them. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

It should be understood that when used in this specification and appended claims, the terms "including" and "including" indicate the existence of the described features, wholes, steps, operations, elements and/or components, but do not exclude one or The existence or addition of multiple other features, wholes, steps, operations, elements, components, and/or collections thereof.

It should also be understood that the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in the specification of this application and the appended claims, unless the context clearly indicates other circumstances, the singular forms "a", "an" and "the" are intended to include plural forms.

It should be further understood that the term "and/or" used in the specification and appended claims of this application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations .

Please refer to Figure 1 and Figure 2. Figure 1 is a schematic diagram of the application scenario of the matter handling authority authorization method provided by an embodiment of the application, and Figure 2 is a schematic flow diagram of the matter handling authorization authorization method provided by an embodiment of the application. The method is applied to a server, and the method is executed by application software installed in the server.

As shown in Figure 2, the method includes steps S110 to S180.

S110: If the user voice data sent by the user terminal is received, perform voice recognition and voiceprint recognition on the user voice data to obtain voice text data and voice voiceprint characteristics corresponding to the user voice data.

In this embodiment, in order to understand the technical solution more clearly, the terminal involved in the specific implementation scenario is introduced in detail. This application describes the technical solution from the perspective of the server.

One is the user side. The user side is an intelligent terminal used by the user (such as a terminal such as a smart phone). The user can use the intelligent dialogue system provided by the user side and the server to communicate with each other to achieve specific matters. That is, the user terminal can send the collected user voice to the server.

The second is the server. The server handles various matters by combining the voice recognition function and voiceprint recognition function of the local intelligent dialogue system with the received user voice sent by the user terminal.

If the server receives the user voice data and the user communication identification code sent by the user terminal, it means that the user can communicate with the intelligent dialogue system deployed on the server side after establishing a connection with the server through the user terminal at this time. Since the user side generally uses phone calls or application software with communication functions (such as WeChat, etc.) to establish a connection with the intelligent dialogue system, the server side can recognize the user communication identification code (the communication identification code can be a phone number or It is the WeChat ID code, etc.). Since the user communication identification code is generally bound to the user's unique identification information (such as the ID number), the server side can use the user communication identification code to make the initial judgment of the user's identity.

In an embodiment, step S110 includes:

Perform voice recognition on the user voice data through a pre-trained N-ary model to obtain voice text data, and perform voiceprint recognition on the user voice data through a pre-trained mixed Gaussian-universal background model to obtain voice voiceprint features.

In this embodiment, when the server receives the user voice data sent by the user terminal, it can call a pre-stored voice recognition model (such as the N-gram voice recognition model, etc., where the N-gram voice recognition model is the N element Model) to perform voice recognition on the user voice data to obtain corresponding voice text data.

At the same time, the server also performs voiceprint recognition on the user's voice data by calling a pre-stored voiceprint recognition model (such as a mixed Gaussian-universal background model, etc.) to obtain voice voiceprint features. After text extraction and voiceprint recognition are performed on the user's voice data through the N-ary model and the mixed Gaussian-universal background model, the follow-up transaction processing process can be carried out based on these recognition results.

S120: Determine whether there is a voiceprint feature that is the same as the voice voiceprint feature in the local voiceprint database.

In this embodiment, since the voiceprint features of a large number of users are stored in the voiceprint database, and the voiceprint database is locally on the server, when the voice and voiceprint features of the current user are acquired, the user’s identity needs to be checked. Verify.

S130: If there is a voiceprint feature that is the same as the voice voiceprint feature in the local voiceprint database, use the corresponding voiceprint feature as the target voiceprint feature, and obtain target user identity information corresponding to the target voiceprint feature.

In this embodiment, if there is a voiceprint feature that is the same as the voiceprint feature in the server's local voiceprint database, it means that the user has previously stored his voiceprint feature data in the server and registered the voiceprint. The user identity information corresponding to the fingerprint feature data (such as the user's name and ID number). At this time, after the target voiceprint feature is acquired, the target user's identity information corresponding to the target voiceprint feature can be acquired.

In an embodiment, after step S120, the method further includes:

If there is no voiceprint feature that is the same as the voice voiceprint feature in the local voiceprint database, sending the first prompt message for recording the user's initial voice according to the voice template to the user terminal;

Receive the user's initial voice data sent by the user terminal according to the first prompt message; wherein the user's initial voice data includes the user's name and ID number;

Performing voiceprint recognition and text recognition according to the user's initial voice data to obtain user voiceprint features and user voice text data corresponding to the user's initial voice data;

Performing word segmentation and keyword extraction on the user voice text data to obtain user identity information corresponding to the user voice text data;

The user's voiceprint feature and the user's voice and text data are correspondingly data-bound to upload to the blockchain for storage.

In this embodiment, if there is no voiceprint feature that is the same as the voiceprint feature in the local voiceprint database, it means that the user may be communicating with the intelligent dialogue system deployed in the server for the first time. At this time, jump to execute the above The process of user registration of voiceprint features and user identity information.

For example, the server will ask the user to register the user for the first time with the text read aloud in the example and his real user identity. The example text is *** and the ID number is ***” to prompt the user to record the user according to the voice template The first prompt message of the initial voice is sent to the user terminal. After that, the user’s initial voice data sent by the user terminal according to the first prompt information is received by the server. At this time, the server performs voiceprint recognition and text recognition on the user’s initial voice data to obtain the user voiceprint corresponding to the user’s initial voice data. Features and user voice text data. Perform voiceprint recognition and text recognition on the user's initial voice data in the same manner as in step S110 to obtain user voiceprint features and user voice text data corresponding to the user's initial voice data. Finally, the user voice text data extracted based on the user voice text data and the previously obtained user voiceprint features are uploaded to the blockchain for storage after corresponding to the same user identity information. Through the above operations, the initial registration of the user's voiceprint characteristics and user identity information can be realized.

Wherein, the corresponding summary information is obtained based on the user's voiceprint features and the user's voice and text data. Specifically, the summary information is obtained by hashing the user's voiceprint features and the user's voice and text data, such as using Sha256 algorithm is processed. Uploading summary information to the blockchain can ensure its security and fairness and transparency to users. The user equipment can download the summary information from the blockchain to verify whether the user's voiceprint characteristics and the user's voice and text data have been tampered with. The blockchain referred to in this example is a new application mode of computer technology such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm. Blockchain, essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information for verification. The validity of the information (anti-counterfeiting) and the generation of the next block. The blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.

S140: If the user unique identification information corresponding to the user communication identification code has the same unique user identification code as the target user identification information, a corresponding keyword set is obtained by sequentially performing text word segmentation and keyword extraction on the voice text data.

In this embodiment, if the user's unique identification information corresponding to the user communication identification code has the same unique user identification code as the target user's identification information, it means that the user himself is communicating with the intelligent dialogue system, and the user himself can continue to do so. To handle business, you can also choose to entrust others to handle it (that is, to authorize others to handle matters). In order to truly understand the user's intention after it is determined that the user has passed the identity verification, it is necessary to perform semantic analysis on the voice text data corresponding to the user's voice data at this time.

In an embodiment, step S140 includes:

A text word segmentation result is obtained by performing text word segmentation on the voice text data based on a probability statistical word segmentation model, and a corresponding keyword set is obtained by keyword extraction on the text word segmentation result by a word frequency-inverse document frequency model.

In this embodiment, the speech text data is segmented by text content based on the probability statistical word segmentation model to obtain the corresponding text word segmentation result, and then the text word segmentation result is extracted by keyword extraction through the word frequency-inverse document frequency model The corresponding keyword set. Among them, the word segmentation model based on probability statistics and the word frequency-reverse document frequency model are relatively mature existing technologies, and will not be discussed here. Among them, what needs to be emphasized is when the word frequency-inverse document frequency model (also called the word frequency-inverse text frequency index model, that is, the TF-IDF model) is used to extract keywords from the text segmentation result to obtain the corresponding keyword set, The keyword segmentation results of the text are sorted in descending order of word frequency-inverse text frequency index, and keywords that are located before the preset ranking value are extracted to form a keyword set.

S150: Determine whether the keyword set includes a first keyword sub-set corresponding to authorized others to handle the processing.

In this embodiment, in order to determine whether the user communicates with the intelligent dialogue system this time is for the user to handle the matter, or to authorize others to handle the matter, it is necessary to check whether the keyword set includes the [authorization***Handle*** Matters authorized person verification code ***] the first keyword sub-collection. If the keyword set includes the first keyword sub-set, it means that the user clearly stated that other people are needed to handle the matter during the communication process, and the subsequent steps of entrusting others to handle the matter can be continued at this time. If the keyword set does not include the first keyword sub-set, it means that the user has not clearly stated that other people are required to handle the matter in the communication process, and the user himself will continue to handle the matter by default.

S160. If the keyword set includes a first keyword sub-set corresponding to authorized others to handle the processing, obtain the authorized person's name, authorized person verification code, and authorized item name included in the first keyword sub-set .

In this embodiment, if the keyword set includes the first keyword sub-set corresponding to authorized others, it means that the intelligent dialogue system in the server at this time knows that the current matter is that the principal authorizes the authorized person to help it. When processing, in order to verify the identity of the authorized person, there can be double verification, one is to obtain the authorized person's name, and the other is to obtain the authorized person's verification code. Among them, the name of the authorized person is included in the user's voice data formed by the authorized person during the conversation, and the user's voice data also includes the authorized person's verification code and the name of the authorized item.

Since the authorized person may be at the same place as the principal at this time, the authorized person can continue to use the client terminal of the principal to continue handling matters. This scenario is similar to that the user is not proficient in using the terminal or has a low level of professional knowledge. When the older users consult and handle business in a business hall, the staff of the business hall can directly tell the older users to say the text segment of the entrusted *** deal with the matters in the process of communicating with the intelligent dialogue system, and the business hall will work at this time The personnel can continue to use the user's client to continue to help them handle matters. Or, the staff of the business hall uses other user terminals (the other user terminals may be the user terminals used by the staff of the business hall themselves, and are not the same terminal as the client used by the client).

S170. According to the received current user voice data corresponding to the first keyword subset sent by the user terminal or other user terminals, call the corresponding current target item process data, and put the current target item process data in a process sequence Sequentially sent to the client or other clients.

In this embodiment, when the principal authorizes the authorized person to handle matters, the authorized person communicates with the intelligent dialogue system in the server through the client terminal of the principal or another client terminal used by the authorized person. , So as to send the current user's voice data to the server. At this time, the corresponding current target item process data is called in the server, and the current target item process data is sequentially sent to the user terminal or other user terminals in the sequence of the process, so as to realize the authorization of others to handle the item.

In an embodiment, step S170 includes:

If the current user voice data sent by the user terminal or other user terminals is received, through voice recognition and keyword extraction, the current user name and current verification code corresponding to the current user voice data are obtained;

If the name of the current user is the same as the name of the authorized person, and the current verification code is the same as the verification code of the authorized person, call the current target item process data stored locally and corresponding to the authorized item name, The process data of the current target item is sent to the client or other clients in sequence in the sequence of the process.

In this embodiment, if the current user voice data sent by the user terminal or other user terminals is received, in order to verify the identity of the authorized person at this time, the current user voice data corresponding to the current user’s voice data is obtained through voice recognition. Refer to step S140 for the process of user name and current verification code, voice recognition and keyword acquisition.

If the name of the current user is the same as the name of the authorized person, and the current verification code is the same as the verification code of the authorized person, it means that the identity of the authorized person has passed the system verification. At this time, the authorized person can follow the current target item process data sent by the server as a guide, so as to quickly handle the item.

S180: Receive current target item data corresponding to the current target item process data sent by the client or other client terminals.

In this embodiment, after the authorized person has completed the current item according to the current target item process data, the corresponding data is fed back to each sub-process in the current target item process data, and the corresponding current target item data is formed, At this time, the current target item data can be stored in the server.

Afterwards, voiceprint recognition can also be performed on the current user's voice data to obtain voiceprint features corresponding to the authorized person. Once the authorized person communicates with the intelligent dialogue system to handle matters at other times, there is no need to repeat the voiceprint feature registration of the authorized person. Generally, the principal can supplement the registration of his user identity information.

After that, the principal can continue to cancel the authorized person's authority to handle matters through the communication with the intelligent dialogue system, and can say "I want to remove the authority to handle **", then the previous authorized person cannot handle the authorized person's authority again matter.

In an embodiment, after step S180, the method further includes:

Upload the current target item process data to the blockchain network.

In this embodiment, the current target item process data that each user handles or entrusts others to handle can be uploaded to the blockchain network for storage, making full use of the non-tampering feature of the blockchain to realize the Matters deal with the storage of data.

In an embodiment, after step S150, the method further includes:

If the keyword set does not include the first keyword sub-set corresponding to authorized others to handle, obtain the second keyword sub-set corresponding to the item type included in the keyword set;

Call the target event process data stored locally and corresponding to the second keyword sub-set, and send the target event process data to the client in sequence according to the process sequence;

Obtain the target event data corresponding to the target event process data sent by the client, and upload it to the blockchain for storage.

In this embodiment, if the keyword set does not include the first keyword sub-set, it means that the user did not clearly indicate that other people are required to handle the matter during this communication process, and the user himself/herself will continue to handle the matter by default. When the user does not need to entrust others to handle matters, in order to make it more convenient to guide customers to handle the business, the second keyword sub-set corresponding to the item type included in the keyword set can be obtained, and the second keyword sub-set determines the user’s waiting list. Do things. Obtain target item flow data corresponding to the user's to-do items in the item flow data respectively corresponding to various to-do items stored in advance by the server.

Obtained the target item process data corresponding to the user's to-do items. These target process item data generally include many item handling steps. In each step, the user is prompted to make a yes or no choice, or provide some user information At this time, in order to guide the user to handle matters, the process data of the target matters are sent to the user terminal in sequence according to the process sequence.

More specifically, when the target item process data is sent to the user terminal in sequence according to the process sequence, the first sub-step data of the item therein is first sent to the user terminal, and the user terminal will give feedback on the first item step sub-data. (For example, for the first item step sub-data corresponding to the first item step sub-feedback data), then the second sub-step data of the item will continue to be pushed, and the subsequent processing process is analogous to that until the user completes the current item according to the target item process data .

After the user finishes the current item according to the target item process data, and feeds back the corresponding data for each sub-process in the target item process data, and composes the corresponding target item data, the target item data can be stored in the server at this time , The server can also upload the target item data to the blockchain network for storage.

The method realizes user identity verification based on voiceprint recognition, and can help others with high proficiency in handling entrusted matters by voice authorization, which not only improves the security of user data, but also improves the efficiency of data processing.

The embodiment of the present application also provides a matter handling authority authorization device, which is used to execute any embodiment of the aforementioned matter handling authority authorization method. Specifically, please refer to FIG. 3, which is a schematic block diagram of a matter handling authority authorization device provided in an embodiment of the present application. The matter handling authority authorization device 100 may be configured in a server.

As shown in FIG. 3, the matter handling authority authorization device 100 includes: a user voice extraction unit 110, a voiceprint feature comparison unit 120, a target user identity acquisition unit 130, a voice keyword extraction unit 140, a keyword judgment unit 150, and an authorized unit. The person information acquiring unit 160, the current goal item flow data sending unit 170, and the current goal item data receiving unit 180.

The user voice extraction unit 110 is used to determine whether a form start instruction is detected.

In this embodiment, if the server receives the user voice data and the user communication identification code sent by the user terminal, it means that the user can communicate with the intelligent dialogue system deployed on the server side after establishing a connection with the server through the user terminal at this time. Since the user side generally uses phone calls or application software with communication functions (such as WeChat, etc.) to establish a connection with the intelligent dialogue system, the server side can recognize the user communication identification code (the communication identification code can be a phone number or It is the WeChat ID code, etc.). Since the user communication identification code is generally bound to the user's unique identification information (such as the ID number), the server side can use the user communication identification code to make the initial judgment of the user's identity.

In an embodiment, the user voice extraction unit 110 is further configured to:

The voiceprint feature comparison unit 120 is used to determine whether there is a voiceprint feature that is the same as the voice voiceprint feature in the local voiceprint database.

The target user identity acquiring unit 130 is configured to, if there is a voiceprint feature that is the same as the voice voiceprint feature in the local voiceprint database, use the corresponding voiceprint feature as the target voiceprint feature to obtain the target voiceprint feature correspondence The identity information of the target user.

In an embodiment, the device 100 for authorization of transaction handling authority further includes:

The first prompt information sending unit is configured to send the first prompt information for recording the user's initial voice according to the voice template to the user terminal if there is no voiceprint feature that is the same as the voice voiceprint feature in the local voiceprint database;

The user's initial voice data receiving unit is configured to receive the user's initial voice data sent by the user terminal according to the first prompt information; wherein, the user's initial voice data includes the user's name and ID number;

An initial voice extraction unit, configured to perform voiceprint recognition and text recognition according to the user's initial voice data to obtain user voiceprint features and user voice text data corresponding to the user's initial voice data;

The initial voice keyword extraction unit is used to perform word segmentation and keyword extraction on the user voice text data to obtain user identity information corresponding to the user voice text data;

The initial data registration unit is used to bind the user's voiceprint characteristics and the user's voice and text data correspondingly to upload them to the blockchain for storage.

For example, the server will ask the user to register the user for the first time with the text read aloud in the example and his real user identity. The example text is *** and the ID number is ***" to prompt the user to record the user according to the voice template The first prompt message of the initial voice is sent to the user terminal. After that, the user’s initial voice data sent by the user terminal according to the first prompt information is received by the server. At this time, the server performs voiceprint recognition and text recognition on the user’s initial voice data to obtain the user voiceprint corresponding to the user’s initial voice data. Features and user voice text data. The voiceprint recognition and text recognition are performed on the user's initial voice data in the same manner with reference to the user voice extraction unit 110 to obtain user voiceprint features and user voice text data corresponding to the user's initial voice data. Finally, the user voice text data extracted based on the user voice text data and the previously obtained user voiceprint features are uploaded to the blockchain for storage after corresponding to the same user identity information. Through the above operations, the initial registration of the user's voiceprint characteristics and user identity information can be realized.

The voice keyword extraction unit 140 is configured to: if the user unique identification information corresponding to the user communication identification code has the same user unique identification code as the target user identification information, by sequentially performing text word segmentation and keyword extraction on the voice text data Get the corresponding keyword set.

In an embodiment, the speech keyword extraction unit 140 is further used for:

The keyword judgment unit 150 is used for judging whether the keyword set includes a first keyword sub-set corresponding to authorized others to handle processing.

The authorized person information obtaining unit 160 is configured to obtain the authorized person’s name and authorized person’s name and authorized person included in the first keyword sub-set if the keyword set includes the first keyword sub-set corresponding to the authorization of others. Person verification code and authorized item name.

The current target event process data sending unit 170 is configured to call the corresponding current target event process data according to the received current user voice data corresponding to the first keyword subset sent by the user terminal or other user terminals, and transfer all the current target event process data. The flow data of the current target item is sent to the client or other client in sequence in the sequence of the flow.

In an embodiment, the current target item process data sending unit 170 includes:

The current user voice data extraction unit is used to obtain the current user name and current verification corresponding to the current user voice data through voice recognition and keyword extraction if the current user voice data sent by the user terminal or other user terminals is received code;

The current target item process data calling unit is used to call if the current user’s name is the same as the authorized person’s name and the current verification code is the same as the authorized person’s verification code, call the locally stored and authorized The current target event process data corresponding to the event name is sent to the client or other client in sequence in the sequence of the process.

In this embodiment, if the current user voice data sent by the user terminal or other user terminals is received, in order to verify the identity of the authorized person at this time, the current user voice data corresponding to the current user’s voice data is obtained through voice recognition. For the user's name and current verification code, the process of voice recognition and keyword acquisition can refer to the voice keyword extraction unit 140.

The current target item data receiving unit 180 is configured to receive current target item data corresponding to the current target item process data sent by the client or other client terminals.

The data link unit is used to upload the current target item process data to the blockchain network.

The second keyword subset acquiring unit is configured to, if the keyword set does not include the first keyword subset corresponding to authorized others to handle, acquire the second key corresponding to the item type included in the keyword set Word sub-collection

The target event process data sending unit is used to call the target event process data stored locally and corresponding to the second keyword subset, and send the target event process data to the user terminal in sequence according to the process sequence;

The target item data on-chain unit is used to obtain the target item data corresponding to the target item process data sent by the client, and upload it to the blockchain for storage.

More specifically, when the target item process data is sent to the user terminal in sequence according to the process sequence, the first sub-step data of the item therein is first sent to the user terminal, and the user terminal will give feedback on the first item step sub-data. (For example, for the first item step sub-data corresponding to the first item step sub-feedback data), then the second sub-step data of the item will continue to be pushed, and the subsequent processing process is analogous to that until the user finishes the current item according to the target item process data .

The device realizes the identity verification of the user based on voiceprint recognition, and can voice authorization entrusted matters to be handled by others who are proficient in handling matters, which not only improves the security of user data, but also improves the efficiency of data processing.

The above-mentioned matter handling authority authorization device can be implemented in the form of a computer program, and the computer program can be run on the computer device as shown in FIG. 4.

Please refer to FIG. 4, which is a schematic block diagram of a computer device according to an embodiment of the present application. The computer device 500 is a server, and the server may be an independent server or a server cluster composed of multiple servers.

4, the computer device 500 includes a processor 502, a memory, and a network interface 505 connected through a system bus 501, where the memory may include a non-volatile storage medium 503 and an internal memory 504.

The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, the processor 502 can execute the method for authorization of transaction handling authority.

The processor 502 is used to provide calculation and control capabilities, and support the operation of the entire computer device 500.

The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute the method for authorization of transaction handling rights.

The network interface 505 is used for network communication, such as providing data information transmission. Those skilled in the art can understand that the structure shown in FIG. 4 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device 500 to which the solution of the present application is applied. The specific computer device 500 may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

Wherein, the processor 502 is configured to run a computer program 5032 stored in a memory, so as to implement the method for authorization of transaction handling rights disclosed in the embodiments of the present application.

Those skilled in the art can understand that the embodiment of the computer device shown in FIG. 4 does not constitute a limitation on the specific configuration of the computer device. In other embodiments, the computer device may include more or less components than those shown in the figure. Or some parts are combined, or different parts are arranged. For example, in some embodiments, the computer device may only include a memory and a processor. In such an embodiment, the structures and functions of the memory and the processor are consistent with the embodiment shown in FIG. 4, and will not be repeated here.

It should be understood that, in this embodiment of the application, the processor 502 may be a central processing unit (Central Processing Unit, CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (Digital Signal Processors, DSPs), Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor.

In another embodiment of the present application, a computer-readable storage medium is provided. The computer-readable storage medium may be non-volatile or volatile. The computer-readable storage medium stores a computer program, where the computer program, when executed by a processor, implements the method for authorization of transaction handling rights disclosed in the embodiments of the present application.

Those skilled in the art can clearly understand that, for the convenience and conciseness of description, the specific working process of the above-described equipment, device, and unit can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here. A person of ordinary skill in the art may be aware that the units and algorithm steps of the examples described in the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both, in order to clearly illustrate the hardware and software Interchangeability, in the above description, the composition and steps of each example have been generally described in accordance with the function. Whether these functions are executed by hardware or software depends on the specific application and design constraint conditions of the technical solution. Professionals and technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered beyond the scope of this application.

In the several embodiments provided in this application, it should be understood that the disclosed equipment, device, and method may be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, or the units with the same function may be combined into one. Units, for example, multiple units or components can be combined or integrated into another system, or some features can be omitted or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may also be electrical, mechanical or other forms of connection.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments of the present application.

In addition, the functional units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.

If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of this application is essentially or the part that contributes to the existing technology, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium. It includes several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), magnetic disk or optical disk and other media that can store program codes.

The above are only specific implementations of this application, but the protection scope of this application is not limited to this. Anyone familiar with the technical field can easily think of various equivalents within the technical scope disclosed in this application. Modifications or replacements, these modifications or replacements shall be covered within the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

A method of authorization for handling matters, including:

If the user voice data and the user communication identification code sent by the user terminal are received, perform voice recognition and voiceprint recognition on the user voice data to obtain voice text data and voice voiceprint characteristics corresponding to the user voice data;

Judging whether there is a voiceprint feature that is the same as the voice voiceprint feature in the local voiceprint database;

If there is a voiceprint feature that is the same as the voice voiceprint feature in the local voiceprint database, use the corresponding voiceprint feature as the target voiceprint feature to obtain the target user identity information corresponding to the target voiceprint feature;

If the user unique identification information corresponding to the user communication identification code has the same unique user identification code as the target user identification information, the corresponding keyword set is obtained by sequentially performing text segmentation and keyword extraction on the voice text data;

Judging whether the keyword set includes the first keyword sub-set corresponding to authorized others to handle it;

If the keyword set includes the first keyword sub-set corresponding to authorized others to handle, obtain the authorized person's name, the authorized person's verification code, and the authorized item name included in the first keyword sub-set;

According to the received current user voice data corresponding to the first keyword subset sent by the user terminal or other user terminals, call the corresponding current target item process data, and sequentially order the current target item process data according to the process sequence Send to the client or other clients; and

Receive current target item data corresponding to the current target item process data sent by the client or other client terminals.
The method of claim 1, wherein said performing voice recognition and voiceprint recognition on said user voice data to obtain voice text data and voice voiceprint characteristics corresponding to said user voice data comprises :

Perform voice recognition on the user voice data through a pre-trained N-ary model to obtain voice text data, and perform voiceprint recognition on the user voice data through a pre-trained mixed Gaussian-universal background model to obtain voice voiceprint features.
The matter handling authority authorization method according to claim 1, wherein after determining whether there is a voiceprint feature that is the same as the voice voiceprint feature in the local voiceprint database, the method further comprises:

If there is no voiceprint feature that is the same as the voice voiceprint feature in the local voiceprint database, sending the first prompt message for recording the user's initial voice according to the voice template to the user terminal;

Receive the user's initial voice data sent by the user terminal according to the first prompt message; wherein the user's initial voice data includes the user's name and ID number;

Performing voiceprint recognition and text recognition according to the user's initial voice data to obtain user voiceprint features and user voice text data corresponding to the user's initial voice data;

Performing word segmentation and keyword extraction on the user voice text data to obtain user identity information corresponding to the user voice text data;

The user's voiceprint feature and the user's voice and text data are correspondingly data-bound to upload to the blockchain for storage.
The method for authorization of transaction handling rights according to claim 1, wherein after said determining whether said keyword set includes a first keyword sub-set corresponding to authorized others to handle, the method further comprises:

If the keyword set does not include the first keyword sub-set corresponding to authorized others to handle the processing, obtain the second keyword sub-set corresponding to the item type included in the keyword set;

Call the target event process data stored locally and corresponding to the second keyword sub-set, and send the target event process data to the client in sequence according to the process sequence;

Obtain the target event data corresponding to the target event process data sent by the client, and upload it to the blockchain for storage.
The matter handling authority authorization method according to claim 1, wherein, according to the received current user voice data corresponding to the first keyword subset sent by the user terminal or other user terminals, the corresponding current target is called Event process data, which sends the current target event process data to the client or other clients in sequence in the sequence of the process, including:

If the current user voice data sent by the user terminal or other user terminals is received, through voice recognition and keyword extraction, the current user name and current verification code corresponding to the current user voice data are obtained;

If the name of the current user is the same as the name of the authorized person, and the current verification code is the same as the verification code of the authorized person, call the current target item process data stored locally and corresponding to the authorized item name, The process data of the current target item is sent to the client or other clients in sequence in the sequence of the process.
The matter handling authority authorization method according to claim 1, wherein the step of sequentially performing text segmentation and keyword extraction on the voice text data to obtain a corresponding keyword set includes:

A text word segmentation result is obtained by performing text word segmentation on the voice text data based on a probability statistical word segmentation model, and a corresponding keyword set is obtained by keyword extraction on the text word segmentation result by a word frequency-inverse document frequency model.
The matter handling authority authorization method according to claim 1, wherein after the receiving the current target item data corresponding to the current target item process data sent by the client or other client terminals, the method further comprises:

Upload the current target item process data to the blockchain network.
The matter handling authority authorization method according to claim 1, which further comprises:

Perform voiceprint recognition on the current user's voice data, and obtain the voiceprint characteristics corresponding to the authorized person.
The matter handling authority authorization method according to claim 1, further comprising:

If the permission-removed voice data sent by the user terminal is detected, the item permission corresponding to the authorized person is deleted.
A matter handling authority authorization device, which includes:

The user voice extraction unit is configured to perform voice recognition and voiceprint recognition on the user voice data if the user voice data and user communication identification code sent by the user terminal are received, to obtain the voice text data and the voice text data corresponding to the user voice data. Voice voiceprint characteristics;

The voiceprint feature comparison unit is used to determine whether there is a voiceprint feature that is the same as the voice voiceprint feature in the local voiceprint database;

The target user identity acquiring unit is configured to, if there is a voiceprint feature that is the same as the voice voiceprint feature in the local voiceprint database, use the corresponding voiceprint feature as the target voiceprint feature to obtain the corresponding voiceprint feature Target user identity information;

The voice keyword extraction unit is used to obtain the unique user identification code by sequentially performing text word segmentation and keyword extraction on the voice text data if the user unique identification information corresponding to the user communication identification code and the target user identification information have the same unique user identification code Corresponding keyword set;

The keyword judgment unit is used to judge whether the keyword set includes the first keyword sub-set corresponding to authorized others to handle;

The authorized person information obtaining unit is used to obtain the name of the authorized person and the authorized person included in the first keyword sub-set if the keyword set includes a first keyword sub-set corresponding to authorized others to handle Verification code and authorized item name;

The current target item process data sending unit is used to call the corresponding current target item process data according to the received current user voice data corresponding to the first keyword subset sent by the user terminal or other user terminals, and transfer the The current target item process data is sent to the client or other clients in sequence in the sequence of the process; and

The current target item data receiving unit is configured to receive the current target item data corresponding to the current target item process data sent by the user terminal or other user terminals.
A computer device includes a memory, a processor, and a computer program stored on the memory and capable of running on the processor, wherein the processor implements the following steps when the processor executes the computer program:

If the user voice data and the user communication identification code sent by the user terminal are received, perform voice recognition and voiceprint recognition on the user voice data to obtain voice text data and voice voiceprint characteristics corresponding to the user voice data;

Judging whether there is a voiceprint feature that is the same as the voice voiceprint feature in the local voiceprint database;

If there is a voiceprint feature that is the same as the voice voiceprint feature in the local voiceprint database, use the corresponding voiceprint feature as the target voiceprint feature to obtain the target user identity information corresponding to the target voiceprint feature;

If the user unique identification information corresponding to the user communication identification code has the same unique user identification code as the target user identification information, the corresponding keyword set is obtained by sequentially performing text segmentation and keyword extraction on the voice text data;

Judging whether the keyword set includes the first keyword sub-set corresponding to authorized others to handle it;

If the keyword set includes the first keyword sub-set corresponding to authorized others to handle, obtain the authorized person's name, the authorized person's verification code, and the authorized item name included in the first keyword sub-set;

According to the received current user voice data corresponding to the first keyword subset sent by the user terminal or other user terminals, call the corresponding current target item process data, and sequentially order the current target item process data according to the process sequence Send to the client or other clients; and

Receive current target item data corresponding to the current target item process data sent by the client or other client terminals.
The computer device according to claim 11, wherein said performing voice recognition and voiceprint recognition on said user voice data to obtain voice text data and voice voiceprint characteristics corresponding to said user voice data comprises:

Perform voice recognition on the user voice data through a pre-trained N-ary model to obtain voice text data, and perform voiceprint recognition on the user voice data through a pre-trained mixed Gaussian-universal background model to obtain voice voiceprint features.
11. The computer device according to claim 11, wherein after determining whether there is a voiceprint feature that is the same as the voice voiceprint feature in the local voiceprint database, the method further comprises:

If there is no voiceprint feature that is the same as the voice voiceprint feature in the local voiceprint database, sending the first prompt message for recording the user's initial voice according to the voice template to the user terminal;

Receive the user's initial voice data sent by the user terminal according to the first prompt message; wherein the user's initial voice data includes the user's name and ID number;

Performing voiceprint recognition and text recognition according to the user's initial voice data to obtain user voiceprint features and user voice text data corresponding to the user's initial voice data;

Performing word segmentation and keyword extraction on the user voice text data to obtain user identity information corresponding to the user voice text data;

The user's voiceprint feature and the user's voice and text data are correspondingly data-bound to upload to the blockchain for storage.
11. The computer device according to claim 11, wherein, after determining whether the keyword set includes a first keyword sub-set corresponding to authorized others to handle processing, the method further comprises:

If the keyword set does not include the first keyword sub-set corresponding to authorized others to handle the processing, obtain the second keyword sub-set corresponding to the item type included in the keyword set;

Call the target event process data stored locally and corresponding to the second keyword sub-set, and send the target event process data to the client in sequence according to the process sequence;

Obtain the target event data corresponding to the target event process data sent by the client, and upload it to the blockchain for storage.
11. The computer device according to claim 11, wherein, according to the received current user voice data corresponding to the first keyword subset sent by the user terminal or other user terminals, the corresponding current target item process data is called , And send the current target item process data to the client or other client in the sequence of the process, including:

If the current user voice data sent by the user terminal or other user terminals is received, through voice recognition and keyword extraction, the current user name and current verification code corresponding to the current user voice data are obtained;

If the name of the current user is the same as the name of the authorized person, and the current verification code is the same as the verification code of the authorized person, call the current target item process data stored locally and corresponding to the authorized item name, The process data of the current target item is sent to the client or other clients in sequence in the sequence of the process.
The computer device according to claim 11, wherein the step of sequentially performing text segmentation and keyword extraction on the voice text data to obtain the corresponding keyword set comprises:

A text word segmentation result is obtained by performing text word segmentation on the voice text data based on a probability statistical word segmentation model, and a corresponding keyword set is obtained by keyword extraction on the text word segmentation result by a word frequency-inverse document frequency model.
The computer device according to claim 11, wherein after the receiving the current target item data corresponding to the current target item process data sent by the client or other client terminals, the method further comprises:

Upload the current target item process data to the blockchain network.
The computer device according to claim 11, further comprising:

Perform voiceprint recognition on the current user's voice data, and obtain the voiceprint characteristics corresponding to the authorized person.
The computer device according to claim 11, further comprising:

If the permission-removed voice data sent by the user terminal is detected, the item permission corresponding to the authorized person is deleted.
A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program that, when executed by a processor, causes the processor to perform the following operations:

If the user voice data and the user communication identification code sent by the user terminal are received, perform voice recognition and voiceprint recognition on the user voice data to obtain voice text data and voice voiceprint characteristics corresponding to the user voice data;

Judging whether there is a voiceprint feature that is the same as the voice voiceprint feature in the local voiceprint database;

If there is a voiceprint feature that is the same as the voice voiceprint feature in the local voiceprint database, use the corresponding voiceprint feature as the target voiceprint feature to obtain the target user identity information corresponding to the target voiceprint feature;

If the user unique identification information corresponding to the user communication identification code has the same unique user identification code as the target user identification information, the corresponding keyword set is obtained by sequentially performing text segmentation and keyword extraction on the voice text data;

Judging whether the keyword set includes the first keyword sub-set corresponding to authorized others to handle it;

If the keyword set includes the first keyword sub-set corresponding to authorized others to handle, obtain the authorized person's name, the authorized person's verification code, and the authorized item name included in the first keyword sub-set;

According to the received current user voice data corresponding to the first keyword subset sent by the user terminal or other user terminals, call the corresponding current target item process data, and sequentially order the current target item process data according to the process sequence Send to the client or other clients; and

Receive current target item data corresponding to the current target item process data sent by the client or other client terminals.