WO2019100607A1

WO2019100607A1 - Voice recognition-based transaction method, server and computer readable storage medium

Info

Publication number: WO2019100607A1
Application number: PCT/CN2018/076137
Authority: WO
Inventors: 王健宗; 黄章成; 吴天博; 肖京
Original assignee: 平安科技（深圳）有限公司
Priority date: 2017-11-21
Filing date: 2018-02-10
Publication date: 2019-05-31
Also published as: CN108038687A; CN108038687B

Abstract

Disclosed is a voice recognition-based transaction method applied to a server. The method comprises: starting a user transaction window; selecting a transaction mode, wherein the transaction mode includes user face-to-face payment, proxy payment by other people and user group payment; receiving voice information of a transaction object; determining whether the received voice information of the transaction object matches the transaction mode; and if the voice information of the transaction object matches the transaction mode, starting the transaction. Further provided are a server and a computer readable storage medium. By means of the voice recognition-based transaction method, the server and the computer readable storage medium provided by the present application, the interaction processes between a user and a merchant can be reduced in different consumption transaction scenarios, and the transaction can be rapidly and accurately realized directly by means of a natural voice, thereby improving the user experience, and also promoting the development of the electronic consumption industry.

Description

Voice recognition based transaction method, server and computer readable storage medium

The present application claims the priority of the Chinese Patent Application filed on November 21, 2017, the Chinese Patent Office, Application No. 201711167774.3, entitled "Voice Recognition Based Transaction Method, Server and Computer Readable Storage Medium", the entire contents of which are hereby incorporated by reference. It is incorporated in the application by reference.

Technical field

The present application relates to the field of communications technologies, and in particular, to a voice recognition based transaction method, a server, and a computer readable storage medium.

Background technique

When you focus on one thing, you can't liberate your hands and eyes at the same time. The quickest and most effective way to get other relevant information in real time is voice interaction. It is a dialogue process itself, so the voice commands in a specific scene have special meaning. Most of the existing payment applications are completed through the interaction between the mobile phone and the merchant, and the process is relatively simple. Mainly through the scan code payment to complete. According to the merchant's signing situation, it is generally divided into two cases: the merchant sweeps the user and the user sweeps the merchant. Both of them require the user to complete the password and payment account verification on the mobile terminal. However, at present, this payment method still needs to be realized by a physical interaction between the user or the merchant, and the user experience needs further improvement.

Summary of the invention

In view of this, the present application proposes a voice recognition-based transaction method, a server, and a computer-readable storage medium, so as to reduce the interaction process between the user and the merchant in different consumption transaction scenarios, and directly through the natural voice mode. Accurate implementation of the transaction enhances the user experience and promotes the development of the electronic consumer industry.

First, in order to achieve the above object, the present application provides a server, wherein the server includes a memory and a processor, and the memory stores a voice recognition-based transaction program executable on the processor. The speech recognition based transaction program is executed by the processor to implement the following steps:

Open the user transaction window;

Selecting a transaction mode, the transaction mode includes a user paying in person, paying by others, and paying for a user group;

Receiving voice information of the transaction object;

Determining whether the received voice information of the transaction object matches the transaction mode; and

If the voice message matches the transaction mode, the transaction is opened.

In addition, in order to achieve the above object, the present invention further provides a voice recognition-based transaction method, which is applied to a server, and the method includes:

Open the user transaction window;

Receiving voice information of the transaction object;

Determining whether the received voice information matches the transaction mode; and

If the voice message matches the transaction mode, the transaction is opened.

Further, in order to achieve the above object, the present application further provides a computer readable storage medium storing a voice recognition based transaction program, the voice recognition based transaction program being configurable by at least one processor Executing to cause the at least one processor to perform the steps of the speech recognition based transaction method as described above.

Compared with the prior art, the server, the voice recognition based transaction method and the computer readable storage medium proposed by the present application firstly open a user transaction window; secondly, select a transaction mode, the transaction mode includes the user paying in person, others Paying, user group payment; again, receiving voice information; then, determining whether the received voice information matches the transaction mode; finally, if the voice information matches the transaction mode, the transaction is started. In this way, in different consumer transaction scenarios, the interaction process between the user and the merchant is reduced, and the transaction is performed quickly and accurately through the natural voice mode, thereby improving the user experience and promoting the development of the electronic consumer industry.

DRAWINGS

1 is a schematic diagram of an optional hardware architecture of the server of the present application;

2 is a program block diagram of a first embodiment of a speech recognition based transaction program of the present application;

3 is a flowchart of a first embodiment of a voice recognition based transaction method according to the present application;

4 is a flowchart of a second embodiment of a voice recognition based transaction method according to the present application;

5 is a flowchart of a third embodiment of a voice recognition based transaction method according to the present application;

FIG. 6 is a flowchart of a fourth embodiment of a voice recognition based transaction method according to the present application.

The implementation, functional features and advantages of the present application will be further described with reference to the accompanying drawings.

Detailed ways

In order to make the objects, technical solutions, and advantages of the present application more comprehensible, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are merely illustrative of the application and are not intended to be limiting. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without departing from the inventive scope are the scope of the present application.

It should be noted that the descriptions of "first", "second" and the like in the present application are for the purpose of description only, and are not to be construed as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. . Thus, features defining "first" or "second" may include at least one of the features, either explicitly or implicitly. In addition, the technical solutions between the various embodiments may be combined with each other, but must be based on the realization of those skilled in the art, and when the combination of the technical solutions is contradictory or impossible to implement, it should be considered that the combination of the technical solutions does not exist. Nor is it within the scope of protection required by this application.

Referring to FIG. 1, it is a schematic diagram of an optional hardware architecture of the server 1.

The server 1 may be a computing device such as a rack server, a blade server, a tower server, or a rack server. The server 1 may be a standalone server or a server cluster composed of multiple servers.

In this embodiment, the server 1 may include, but is not limited to, the memory 11, the processor 12, and the network interface 13 being communicably connected to each other through a system bus.

The server 1 connects to the network through the network interface 13 to obtain information. The network may be an intranet, an Internet, a Global System of Mobile communication (GSM), a Wideband Code Division Multiple Access (WCDMA), a 4G network, or a 5G network. Wireless or wired networks such as networks, Bluetooth, Wi-Fi, and call networks.

It is pointed out that Figure 1 only shows the server 1 with the components 11-13, but it should be understood that not all illustrated components are required to be implemented, and more or fewer components may be implemented instead.

The memory 11 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (eg, SD or DX memory, etc.), and a random access memory (RAM). , static random access memory (SRAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), magnetic memory, magnetic disk, optical disk, and the like. In some embodiments, the memory 11 may be an internal storage unit of the server 1, such as a hard disk or memory of the server 1. In other embodiments, the memory 11 may also be an external storage device of the server 1, such as a plug-in hard disk equipped with the server 1, a smart memory card (SMC), and a secure digital (Secure Digital). , SD) card, flash card (Flash Card), etc. Of course, the memory 11 can also include both the internal storage unit of the server 1 and its external storage device. In this embodiment, the memory 11 is generally used to store an operating system installed in the server 1 and various types of application software, such as program code of the voice recognition based transaction program 200. Further, the memory 11 can also be used to temporarily store various types of data that have been output or are to be output.

The processor 12 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 12 is typically used to control the overall operation of the server 1, such as performing data interaction or communication related control and processing, and the like. In this embodiment, the processor 12 is configured to run program code or process data stored in the memory 11, such as running the voice recognition based transaction program 200 and the like.

The network interface 13 may comprise a wireless network interface or a wired network interface, which is typically used to establish a communication connection between the server 1 and other electronic devices.

In this embodiment, a voice recognition based transaction program 200 is installed and run in the server 1. When the voice recognition based transaction program 200 is running, the server 1 opens a user transaction window; and selects a transaction mode, The transaction mode includes the user paying in person, paying by others, paying for the user group; receiving the voice information; determining whether the received voice information matches the transaction mode; if the voice information matches the transaction mode, opening the transaction. In this way, in different consumer transaction scenarios, the interaction process between the user and the merchant is reduced, and the transaction is performed quickly and accurately through the natural voice mode, thereby improving the user experience and promoting the development of the electronic consumer industry.

So far, the application environment of the various embodiments of the present application and the hardware structure and functions of related devices have been described in detail. Hereinafter, various embodiments of the present application will be proposed based on the above-described application environment and related devices.

First, the present application proposes a speech recognition based transaction program 200.

Referring to FIG. 2, it is a program module diagram of the first embodiment of the speech recognition based transaction program 200 of the present application.

In this embodiment, the server 1 includes a series of computer program instructions stored on the memory 11, that is, the voice recognition based transaction program 200, when the computer program instructions are executed by the processor 12, each of the present application can be implemented. Speech recognition based transaction operations of an embodiment. In some embodiments, the speech recognition based transaction program 200 can be divided into one or more modules based on the particular operations implemented by the various portions of the computer program instructions. For example, in FIG. 2, the voice recognition based transaction program 200 can be divided into a window opening module 201, a mode selection module 202, a voice receiving module 203, a determining module 204, and a transaction module 205. among them:

The window opening module 201 is configured to open a user transaction window.

In the present embodiment, since the transaction needs to be implemented by a voice recognition-based method, at the beginning of the transaction process, a user transaction window needs to be opened, and the user transaction window can be connected to the server through a user or a merchant. 1 The terminal is visually presented, that is, the server 1 opens the user transaction window and presents it on the terminal of the connection server 1 of the user or the merchant.

The mode selection module 202 is configured to select a transaction mode, where the transaction mode includes a user paying in person, paying by others, and paying for a user group.

In this embodiment, for the foregoing transaction mode, the user may include three modes: the user pays in person, the other party pays the payment, and the user group payment. Specifically, the user pays the face-to-face direct payment between the user and the merchant; Paying means that the user does not pay directly to the merchant, but the user asks the friend or relative of the user, that is, others to pay for it; the user group payment refers to the scene of certain dinner-type AA, that is, sending the payment list to a specific group of people The payment is completed by each of the specific people.

The voice receiving module 203 is configured to receive voice information of a transaction object.

In this embodiment, the voice receiving module 203 receives the voice information, and obtains the voice information through the voice collecting device on the terminal device of the user or the merchant terminal, and then transmits the voice information to the voice receiving module 203, such as a microphone on the user's mobile phone. After the transaction window is presented on the mobile phone, the user-specific voice information is collected by using its own microphone, and then the collected voice information is transmitted to the voice receiving module 203 on the server 1 through the network. In the present embodiment, the transaction object refers to a user who opens a user transaction window, such as a consumer who pays in person, or a user who pays a person, or even a transaction object selected in the group payment mode.

The determining module 204 is configured to determine whether the received voice information of the transaction object matches the transaction mode.

In this embodiment, since the matching voice information is different for different transaction modes, for example, the user pays the face-to-face payment mode, the user generally directly inputs the “how much money to pay” and the like to express the willingness to pay, while the other person pays the mode. Generally, the voice requesting others to pay such a request is input; and the user group payment necessarily includes at least two different payment voice information because of its special payment environment. In summary, after receiving the voice information, it is also necessary to determine whether the voice information matches the transaction mode.

In other embodiments, the determining, by the determining module 204, whether the received voice information of the transaction object matches the transaction mode may further include: determining, by using an I-vector, whether the received voice information of the transaction object is multi-person Voice information, if yes, determining that the voice information of the transaction object matches the transaction mode of the user group payment; if the voice information of the transaction object is voice information of one person, determining the received voice of the transaction object by I-vector Whether the information includes the digital information displayed by the user transaction window, and if so, determining that the voice information of the transaction object matches the transaction mode paid by the user in person; if not, determining the received message by the I-vector Whether the "paid" keyword is included in the voice information of the transaction object, and if so, it is determined that the voice information of the transaction object matches the transaction mode paid by others.

The transaction module 205 is configured to start a transaction when the voice information matches the transaction mode.

Specifically, according to the transaction mode in which the voice information is matched, the corresponding transaction is started, for example, in the mode of the user paying in person, paying by others, and paying by the user group, the corresponding transaction is started, and the specific content can be referred to later.

Through the above-mentioned program modules 201-205, the voice recognition-based transaction program 200 proposed by the present application opens a user transaction window; selects a transaction mode, which includes a user paying in person, paying by others, paying for a user group; receiving voice information Determining whether the received voice information matches the transaction mode; if the voice information matches the transaction mode, opening a transaction. In this way, in different consumer transaction scenarios, the interaction process between the user and the merchant is reduced, and the transaction is performed quickly and accurately through the natural voice mode, thereby improving the user experience and promoting the development of the electronic consumer industry.

Further, in this embodiment, when the transaction mode selected by the mode selection module 202 is paid by the user in person:

The determining module 204 further determines whether the distance of the user from the merchant is within a preset range. In the present embodiment, in the case of paying such a payment environment, the user and the merchant generally conduct transactions within a certain range, so that it can be effectively controlled by judging whether the user's example from the merchant is within a predetermined range. The trading behavior in this mode.

If the distance of the user from the merchant is within a preset range, the voice receiving module 203 turns on the voice receiving device. In this embodiment, once the user's distance from the merchant is within the preset range, it indicates that the transaction behavior can be performed at this time, that is, the voice receiving device can be turned on.

If the distance of the user from the merchant is not within a preset range, the voice receiving module 203 does not turn on the voice receiving device. In this embodiment, once the distance from the merchant is not within the preset range, the user does not need to conduct a transaction with the merchant at this time, thereby avoiding the opening of the voice receiving device at any time, thereby reducing energy consumption.

Specifically, by setting the distance between the user and the merchant, the user can effectively determine the application environment that the user pays in front, such as a restaurant, a supermarket, etc., and the voice receiving module 203 determines whether to enable the voice receiving device according to the distance, thereby avoiding the sound interference. The voice receiving device is frequently enabled, which consumes power consumption of the terminal, thereby reducing the user experience. The voice receiving device is a built-in microphone or a microphone of an external earphone.

Further, in this embodiment, when the transaction mode selected by the mode selection module 202 is paid by others:

The mode selection module 202 selects a paying friend; and sends a paying request to the paying friend, the paying request includes the received voice information, and the paying friend according to the voice message in the paying request Select whether to make a payment; at the same time, receive the payment information of the paid friend feedback.

In this embodiment, in the transaction mode of the above-mentioned others, firstly, a paying friend must be selected, and the paying friend can obtain the contact according to the address book on the user terminal or the instant messaging application, such as WeChat, QQ and so on. In this embodiment, since the payment request carries the voice information of the user, it is sent to the paying friend at this time, and the paying friend can accept the voice message, and determine whether it is a friend relationship, and then decide whether to perform it. Pay. When the payment information of the feedback received by the friend is agreed to be paid, the business account of the merchant and the friend is automatically associated with the real-time transaction; likewise, if the payment information of the feedback received by the friend is rejected, the payment is refused. In the case of the case, the transaction is terminated and the user is prompted to fail the transaction.

Further, in this embodiment, when the transaction mode selected by the mode selection module 202 is a user group payment, the mode selection module 202 further selects a transaction object of the user group payment, and sends a payment bill link to the transaction object.

In this embodiment, the transaction mode is a user group payment, and at this time, a transaction object that needs to be selected by the user group is required for the transaction behavior, for example, there are 4 people AA to eat, if the transaction mode of the user group payment is selected, then After the transaction window is opened, the four individuals are selected as the transaction objects for the user group payment.

In this embodiment, when the transaction object of the user group payment is selected, the link of the payment bill is sent to the selected transaction object, and the payment bill includes the amount payable by the corresponding transaction object, and the selected transaction object can be based on the payment. Billing links for trading.

In addition, the present application also proposes a transaction method based on speech recognition.

Referring to FIG. 3, it is a schematic flowchart of the implementation of the first embodiment of the voice recognition based transaction method of the present application. In this embodiment, the order of execution of the steps in the flowchart shown in FIG. 3 may be changed according to different requirements, and some steps may be omitted.

In step S301, the user transaction window is opened.

Step S302, selecting a transaction mode, the transaction mode includes a user paying in person, paying by others, and paying by user group.

Step S303, receiving voice information of the transaction object.

In this embodiment, the voice information is received by the voice collection device on the terminal device of the user or the merchant, for example, the microphone on the user's mobile phone. When the transaction window is presented on the mobile phone, the microphone is provided. The user-specific voice information is collected, and the collected voice information is transmitted to the server 1 through the network. In the present embodiment, the transaction object refers to a user who opens a user transaction window, such as a consumer who pays in person, or a user who pays a person, or even a transaction object selected in the group payment mode.

Step S304, determining whether the received voice information of the transaction object matches the transaction mode.

Step S305, when the voice information of the transaction object matches the transaction mode, the transaction is started.

Specifically, according to the transaction mode in which the voice information is matched, the corresponding transaction is started, for example, in a mode in which the user pays in person, pays by others, and pays for the user group, the corresponding transaction is started.

Through the above steps S301-305, the voice recognition based transaction method proposed by the present application firstly opens a user transaction window; secondly, selects a transaction mode, the transaction mode includes the user paying in person, paying by others, and paying for the user group; Receiving voice information of the transaction object; then, determining whether the received voice information matches the transaction mode; finally, if the voice information matches the transaction mode, opening the transaction. In this way, in different consumer transaction scenarios, the interaction process between the user and the merchant is reduced, and the transaction is performed quickly and accurately through the natural voice mode, thereby improving the user experience and promoting the development of the electronic consumer industry.

Referring to FIG. 4, it is a schematic flowchart of the implementation of the second embodiment of the voice recognition based transaction method of the present application. In this embodiment, the order of execution of the steps in the flowchart shown in FIG. 4 may be changed according to different requirements, and some steps may be omitted. When the selected transaction mode is paid by the user in person, the specific process is as follows:

In step S401, it is determined whether the distance of the user from the merchant is within a preset range. In the present embodiment, in the case of paying such a payment environment, the user and the merchant generally conduct transactions within a certain range, so that it can be effectively controlled by judging whether the user's example from the merchant is within a predetermined range. The trading behavior in this mode.

Step S402, if the distance of the user from the merchant is within a preset range, the voice receiving device is turned on. In the present embodiment, once the user's distance from the merchant is within the preset range, it indicates that the transaction behavior can be performed at this time, that is, the voice receiving device can be turned on.

Step S403: If the distance of the user from the merchant is not within a preset range, the voice receiving device is not turned on. In this embodiment, once the distance from the merchant is not within the preset range, the user does not need to conduct a transaction with the merchant at this time, thereby avoiding the opening of the voice receiving device at any time, thereby reducing energy consumption.

Through the above steps S401-403, by setting the distance between the user and the merchant, it is possible to effectively determine the application environment that the user pays in person, such as a restaurant, a supermarket, etc., depending on the distance, whether or not the voice receiving device is enabled, can avoid the voice caused by the sound interference. Frequent activation of the receiving device, loss of power consumption of the terminal, thereby reducing the user experience. The voice receiving device is a built-in microphone or a microphone of an external earphone.

Referring to FIG. 5, it is a schematic flowchart of the implementation of the third embodiment of the voice recognition based transaction method of the present application. In this embodiment, the order of execution of the steps in the flowchart shown in FIG. 5 may be changed according to different requirements, and some steps may be omitted. In this embodiment, when the selected transaction mode is paid by others:

In step S501, a paying friend is selected.

In this embodiment, in the transaction mode of the above-mentioned others, firstly, a paying friend must be selected, and the paying friend can obtain the contact according to the address book on the user terminal or the instant messaging application, such as WeChat, QQ and so on.

Step S502: Send a payment request to the payment buddy, the payment request includes the received voice information, and the payment buddy selects whether to perform payment according to the voice message in the payment request.

In this embodiment, the voice information of the user is carried in the payment request, and is sent to the paying friend at this time, and the paying friend can accept the voice message, and determine whether it is a friend relationship, and then decide whether to perform the voice message. Pay.

Step S503, receiving payment information of the paid friend feedback.

In this embodiment, when the payment payment information of the payment of the payment of the friend is agreed to be paid, the business account of the merchant and the friend is automatically associated with the real-time transaction; likewise, if the payment of the feedback of the friend is accepted, In the case where the payment information is rejected, the transaction is terminated and the user is prompted to fail the transaction.

In the above steps S501-503, the above-mentioned payment request further includes a payment bill link. The manner in which the paying friend determines whether the voice message in the payment request is the voice of the user may be the user's supervisor's judgment, and then determines whether to pay, or may be the paying friend to obtain the voice message in the payment request, and then use the voice message. The user's voice chat record is matched with various instant messaging software (such as WeChat) on the terminal to determine whether the voice message in the payment request is the user's voice. In the above description, if the paying friend completes the payment, the user terminal receives the feedback message of the payment success, and if the paying friend refuses to pay, the user terminal receives the feedback message of the payment rejection.

Referring to FIG. 6, it is a schematic flowchart of the implementation of the fourth embodiment of the voice recognition based transaction method of the present application. In this embodiment, the order of execution of the steps in the flowchart shown in FIG. 6 may be changed according to different requirements, and some steps may be omitted. In this embodiment, when the selected transaction mode is a user group payment:

In step S601, a transaction object of the user group payment is selected.

Step S602, sending a payment bill link to the transaction object.

In the above steps S601-602, the so-called user group payment is applicable to the consumption environment of the AA system. When one of the users selects the user group payment mode, the payment object for the group payment can be actively selected, and then the link of the payment bill can be Directly distributed to the selected other user's terminal, the user's terminal and other user's terminal start receiving voice messages and conduct transactions according to the received voice messages. In addition, the transaction mode of the user group payment may also be a group red envelope. After a user issues a red envelope, the user may select a transaction object capable of robbing the red envelope, and the red envelope carries the voice key of each transaction object, if each transaction object When the respective voice information is respectively received and the corresponding voice key is matched, the red envelope is automatically opened.

In this embodiment, the step of determining whether the received voice information matches the transaction mode is specifically implemented by an I-vector.

Specifically, speech recognition based on I-vector features is a commonly used technical means, namely, the uniqueness of voiceprint, and its general content is as follows:

The traditional joint factor analysis modeling process is mainly based on two different spaces: the speaker space defined by the eigenvoice space matrix, and the channel space defined by the eigenchannel space matrix. Inspired by the theory of joint factor analysis, Dehak proposed extracting a more compact vector called the I-Vector from the GMM mean supervector. Here I is the meaning of identity. For natural understanding, I-Vector is equivalent to the identity of the speaker.

The I-vector method uses a space instead of the two spaces. This new space can become a global difference space, which contains the difference between the speakers and the difference between the channels. Therefore, the I-Vector modeling process does not strictly distinguish between the influence of the speaker and the influence of the channel in the GMM mean supervector. The motivation for this modeling approach comes from another study by Dehak: the channel factor after JFA modeling includes not only the channel effect but also the speaker's information.

I-vector is obtained by Gaussian supervector based factor analysis. The i-vector is a single-space cross-channel algorithm that contains both speaker space and channel space information. Equivalent to using a factor analysis method to project speech from a high-order space to a low-dimensional. In summary, the i-vector can identify various voice information and key information in the corresponding voice information, such as some preset keywords.

In this embodiment, the I-vector is regarded as a feature, and can also be regarded as a simple model. The server 1 calculates the consine distance between the test speech I-vector and the I-vector of the model as the final Score.

The present application utilizes an I-vector to implement speech recognition, and then uses the acquired speech information to match the selected transaction mode, so that the transaction by voice becomes more accurate and effective.

The present application further provides another embodiment, that is, a computer readable storage medium storing a voice recognition based transaction program, the speech recognition based transaction program being at least one processed The apparatus is operative to cause the at least one processor to perform the steps of the speech recognition based transaction method as described above.

The serial numbers of the embodiments of the present application are merely for the description, and do not represent the advantages and disadvantages of the embodiments.

Through the description of the above embodiments, those skilled in the art can clearly understand that the foregoing embodiment method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be through hardware, but in many cases, the former is better. Implementation. Based on such understanding, the technical solution of the present application, which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM, disk, The optical disc includes a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the methods described in various embodiments of the present application.

The above is only a preferred embodiment of the present application, and is not intended to limit the scope of the patent application, and the equivalent structure or equivalent process transformations made by the specification and the drawings of the present application, or directly or indirectly applied to other related technical fields. The same is included in the scope of patent protection of this application.

Claims

A voice recognition based transaction method is applied to a server, characterized in that the method comprises the steps of:

Open the user transaction window;

Selecting a transaction mode, the transaction mode includes a user paying in person, paying by others, and paying for a user group;

Receiving voice information of the transaction object;

Determining whether the received voice information matches the transaction mode; and

If the voice message matches the transaction mode, the transaction is opened.
The speech recognition-based transaction method according to claim 1, wherein when the selected transaction mode is paid by the user in person, the method further comprises the steps of:

Determining whether the distance of the user from the merchant is within a preset range;

If the distance between the user and the merchant is within a preset range, the voice receiving device is turned on;

If the distance of the user from the merchant is not within a preset range, the voice receiving device is not turned on.
The speech recognition-based transaction method according to claim 1, wherein when the selected transaction mode is paid by another person, the method further comprises the steps of:

Choose to pay for a friend;

Sending a payment request to the payment buddy, the payment request includes voice information of the transaction object, and the payment buddy selects whether to perform payment according to the voice message of the transaction object in the payment request; and

Receiving payment information of the paid friend feedback.
The speech recognition-based transaction method according to claim 2, wherein when the selected transaction mode is paid by another person, the method further comprises the steps of:

Choose to pay for a friend;

Sending a payment request to the payment buddy, the payment request includes voice information of the transaction object, and the payment buddy selects whether to perform payment according to the voice message of the transaction object in the payment request; and

Receiving payment information of the paid friend feedback.
The speech recognition-based transaction method according to claim 1, wherein when the selected transaction mode is a user group payment, the method further comprises the step of the step of receiving the voice message of the transaction object. :

Select the transaction object to be paid by the user group; and

The payment payment bill is linked to the selected transaction object of the user group payment.
A speech recognition based transaction method according to claim 2, wherein when said selected transaction mode is a user group payment, said method further comprises the step of said step of receiving a voice message of the transaction object :

Select the transaction object to be paid by the user group; and

The payment payment bill is linked to the selected transaction object of the user group payment.
A speech recognition-based transaction method according to claim 3, wherein when said selected transaction mode is a user group payment, said method further comprises the step of said step of receiving a voice message of the transaction object :

Select the transaction object to be paid by the user group; and

The payment payment bill is linked to the selected transaction object of the user group payment.
The voice recognition-based transaction method according to claim 1, wherein the step of determining whether the received voice information of the transaction object matches the transaction mode comprises:

Determining, by the I-vector, whether the received voice information of the transaction object is voice information of multiple people, and if yes, determining that the voice information of the transaction object matches the transaction mode of the user group payment;

If the voice information of the transaction object is one-person voice information, determine whether the received voice information of the transaction object includes the digital information displayed by the user transaction window by using an I-vector, and if so, determine the transaction. The voice information of the object matches the transaction mode paid by the user in person;

If not included, determining, by the I-vector, whether the received voice information of the transaction object includes a “payment” keyword, and if so, determining that the voice information of the transaction object matches a transaction mode paid by another person. .
The voice recognition-based transaction method according to claim 2, wherein the step of determining whether the received voice information of the transaction object matches the transaction mode comprises:

Determining, by the I-vector, whether the received voice information of the transaction object is voice information of multiple people, and if yes, determining that the voice information of the transaction object matches the transaction mode of the user group payment;

If the voice information of the transaction object is one-person voice information, determine whether the received voice information of the transaction object includes the digital information displayed by the user transaction window by using an I-vector, and if so, determine the transaction. The voice information of the object matches the transaction mode paid by the user in person;

If not included, determining, by the I-vector, whether the received voice information of the transaction object includes a “payment” keyword, and if so, determining that the voice information of the transaction object matches a transaction mode paid by another person. .
The voice recognition-based transaction method according to claim 3, wherein the step of determining whether the received voice information of the transaction object matches the transaction mode comprises:

Determining, by the I-vector, whether the received voice information of the transaction object is voice information of multiple people, and if yes, determining that the voice information of the transaction object matches the transaction mode of the user group payment;

If the voice information of the transaction object is one-person voice information, determine whether the received voice information of the transaction object includes the digital information displayed by the user transaction window by using an I-vector, and if so, determine the transaction. The voice information of the object matches the transaction mode paid by the user in person;

If not included, determining, by the I-vector, whether the received voice information of the transaction object includes a “payment” keyword, and if so, determining that the voice information of the transaction object matches a transaction mode paid by another person. .
The speech recognition-based transaction method according to claim 5, wherein the step of determining whether the received voice information of the transaction object matches the transaction mode comprises:

Determining, by the I-vector, whether the received voice information of the transaction object is voice information of multiple people, and if yes, determining that the voice information of the transaction object matches the transaction mode of the user group payment;

If the voice information of the transaction object is one-person voice information, determine whether the received voice information of the transaction object includes the digital information displayed by the user transaction window by using an I-vector, and if so, determine the transaction. The voice information of the object matches the transaction mode paid by the user in person;

If not included, determining, by the I-vector, whether the received voice information of the transaction object includes a “payment” keyword, and if so, determining that the voice information of the transaction object matches a transaction mode paid by another person. .
A server, comprising: a memory, a processor, on which is stored a voice recognition based transaction program executable on the processor, the voice recognition based transaction program being The processor implements the following steps when it executes:

Open the user transaction window;

Selecting a transaction mode, the transaction mode includes a user paying in person, paying by others, and paying for a user group;

Receiving voice information of the transaction object;

Determining whether the received voice information matches the transaction mode; and

If the voice message matches the transaction mode, the transaction is opened.
The server according to claim 12, wherein said voice recognition based transaction program is executed by said processor, and when said selected transaction mode is paid by the user in person, the following steps are further implemented:

Determining whether the distance of the user from the merchant is within a preset range;

If the distance between the user and the merchant is within a preset range, the voice receiving device is turned on;

If the distance of the user from the merchant is not within a preset range, the voice receiving device is not turned on.
The server according to claim 12, wherein said voice recognition based transaction program is executed by said processor, and when said selected transaction mode is paid by others, the following steps are further implemented:

Choose to pay for a friend;

Sending a payment request to the paying friend, the paying request includes received voice information of the transaction object, and the paying friend selects whether to perform generation according to a voice message of the transaction object in the payment request Pay; and

Receiving payment information of the paid friend feedback.
The server according to claim 12, wherein said speech recognition based transaction program is executed by said processor, and when said selected transaction mode is a user group payment, prior to the step of receiving a voice message The following steps are also implemented:

Select the transaction object to be paid by the user group; and

The payment payment bill is linked to the selected transaction object of the user group payment.
The server according to claim 12, wherein the step of determining whether the received voice information of the transaction object matches the transaction mode comprises:

Determining, by the I-vector, whether the received voice information of the transaction object is voice information of multiple people, and if yes, determining that the voice information of the transaction object matches the transaction mode of the user group payment;

If the voice information of the transaction object is one-person voice information, determine whether the received voice information of the transaction object includes the digital information displayed by the user transaction window by using an I-vector, and if so, determine the transaction. The voice information of the object matches the transaction mode paid by the user in person;

If not included, determining, by the I-vector, whether the received voice information of the transaction object includes a “payment” keyword, and if so, determining that the voice information of the transaction object matches a transaction mode paid by another person. .
A computer readable storage medium storing a speech recognition based transaction program, the speech recognition based transaction program being executable by at least one processor to cause the at least one processor to execute Implement the following steps:

Open the user transaction window;

Selecting a transaction mode, the transaction mode includes a user paying in person, paying by others, and paying for a user group;

Receiving voice information of the transaction object;

Determining whether the received voice information matches the transaction mode; and

If the voice message matches the transaction mode, the transaction is opened.
A computer readable storage medium according to claim 17, wherein said speech recognition based transaction program is executed by said processor, and when said selected transaction mode is paid in person by the user, step:

Determining whether the distance of the user from the merchant is within a preset range;

If the distance between the user and the merchant is within a preset range, the voice receiving device is turned on;

If the distance of the user from the merchant is not within a preset range, the voice receiving device is not turned on.
A computer readable storage medium according to claim 17, wherein said speech recognition based transaction program is executed by said processor, and when said selected transaction mode is paid by another person, step:

Choose to pay for a friend;

Sending a payment request to the paying friend, the paying request includes received voice information of the transaction object, and the paying friend selects whether to perform generation according to a voice message of the transaction object in the payment request Pay; and

Receiving payment information of the paid friend feedback.
A computer readable storage medium according to claim 17, wherein said speech recognition based transaction program is executed by said processor, and when said selected transaction mode is a user group payment, receiving speech The steps of the message are also implemented as follows:

Select the transaction object to be paid by the user group; and

The payment payment bill is linked to the selected transaction object of the user group payment.