CN108960836B

CN108960836B - Voice payment method, device and system

Info

Publication number: CN108960836B
Application number: CN201711450685.XA
Authority: CN
Inventors: 李想; 吴本谷; 李宝祥; 王晓鹏
Original assignee: Beijing Orion Star Technology Co Ltd
Current assignee: Beijing Orion Star Technology Co Ltd
Priority date: 2017-12-27
Filing date: 2017-12-27
Publication date: 2021-09-14
Anticipated expiration: 2037-12-27
Also published as: CN108960836A

Abstract

The invention provides a voice payment method, a voice payment device and a voice payment system, wherein the method comprises the following steps: after receiving the payment instruction, sending payment follow-up content, wherein the content comprises: registering partial or all reading words and partial or all numbers in the reading content; receiving a payment voice signal, and respectively determining the probability that a word voice part and a digital voice part in the payment voice signal belong to each voiceprint account when the payment voice signal is matched with the payment follow-up reading content, so as to determine a voiceprint account to be paid, which is matched with the payment voice signal; and carrying out payment operation on the voiceprint account to be paid according to the payment instruction, wherein each probability is calculated, and the reading words and numbers in the registration reading content are adopted as the payment reading content, so that the recognition accuracy of the payment voice signal is improved, the payment reading content comprises the numbers, the possibility that other people steal the user record to carry out voice payment is avoided, and the safety of voice payment is improved.

Description

Voice payment method, device and system

Technical Field

The invention relates to the technical field of voice equipment, in particular to a voice payment method, device and system.

Background

The current voice device, such as an intelligent sound box, performs voice payment mainly by the background device corresponding to the voice device sending the preset follow-up reading content to the voice device, acquiring a voice signal monitored by the voice device, inputting the voice signal into the preset recognition model, and acquiring a corresponding voiceprint account for payment. However, in the voice payment method, the recognition model is trained through the randomly acquired user voice signal, and the correlation between the randomly acquired user voice signal and the read-after content is not high, so that the recognition accuracy of the recognition model is low, the possibility that other people steal the user recording to perform voice payment is difficult to avoid, and the safety of voice payment is reduced.

Disclosure of Invention

The present invention is directed to solving, at least to some extent, one of the technical problems in the related art.

Therefore, a first objective of the present invention is to provide a voice payment method, which is used to solve the problem of poor security of voice payment in the prior art.

The second purpose of the invention is to provide a voice payment method.

The third purpose of the invention is to provide a voice payment device.

A fourth object of the present invention is to provide a voice payment apparatus.

A fifth object of the present invention is to provide a voice payment system.

A sixth object of the present invention is to provide an electronic apparatus.

A seventh object of the present invention is to provide an electronic apparatus.

An eighth object of the present invention is to propose a non-transitory computer-readable storage medium.

A ninth object of the invention is to propose a non-transitory computer-readable storage medium.

A tenth object of the invention is to propose a computer program product.

An eleventh object of the invention is to propose a computer program product.

In order to achieve the above object, an embodiment of a first aspect of the present invention provides a voice payment method, including:

after receiving the payment instruction, sending payment follow-up reading content; the payment follow-up content comprises: registering part or all of the read-after words in the read-after content, and registering part or all of the digits in the read-after content;

receiving a payment voice signal, and when the payment voice signal is matched with the payment follow-up reading content, determining a first probability that a word voice part in the payment voice signal belongs to each voiceprint account and a second probability that a digital voice part in the payment voice signal belongs to each voiceprint account;

determining a voiceprint account to be paid matched with the payment voice signal according to the first probability and the second probability;

and carrying out payment operation on the voiceprint account to be paid according to the payment instruction.

Further, the method further comprises the following steps:

after receiving a registration instruction, sending registration follow-up reading content;

and receiving a registration voice signal, and creating a voiceprint account according to the registration instruction when the registration voice signal is matched with the registration follow-up content.

Further, the method further comprises the following steps:

training a word recognition model according to the word voice part in the registration voice signal and the corresponding voiceprint account; the word recognition model is used for determining a first probability that a word voice part in the payment voice signal belongs to each voiceprint account;

training a digital recognition model according to the digital voice part in the registration voice signal and the corresponding voiceprint account; the digital recognition model is used for determining a second probability that the digital voice part in the payment voice signal belongs to each voiceprint account.

Further, the registering and reading the number in the content comprises: all bit integers.

Further, the determining the voiceprint account to be paid matching the payment voice signal according to the first probability and the second probability includes:

for each voiceprint account, determining a weighted sum of the corresponding first probability and the corresponding second probability as a probability that the payment voice signal belongs to the voiceprint account;

and when the probability that the payment voice signal belongs to the voiceprint account meets a preset probability threshold value and the number of the voiceprint accounts meeting the preset probability threshold value is 1, determining that the voiceprint account is the voiceprint account to be paid matched with the payment voice signal.

Further, before performing a payment operation on the voiceprint account to be paid according to the payment instruction, the method further includes:

acquiring a currently logged user account;

judging whether the voiceprint account to be paid has the payment authority of the user account;

the payment operation of the voiceprint account to be paid according to the payment instruction comprises the following steps:

and when the voiceprint account to be paid has the payment authority of the user account, carrying out payment operation on the user account according to the payment instruction.

In the voice payment method provided by the embodiment, after a payment instruction is received, payment follow-up reading content is sent; the payment follow-up content comprises: registering part or all of the read-after words in the read-after content, and registering part or all of the digits in the read-after content; receiving a payment voice signal, and determining a first probability that a word voice part in the payment voice signal belongs to each voiceprint account and a second probability that a digital voice part in the payment voice signal belongs to each voiceprint account when the payment voice signal is matched with payment follow-up reading content; determining a voiceprint account to be paid matched with the payment voice signal according to the first probability and the second probability; and performing payment operation on the voiceprint account to be paid according to the payment instruction, wherein the probability that the word voice part belongs to each voiceprint account and the probability that the digital voice part belongs to each voiceprint account are calculated, and the read-after words and the numbers in the registration read-after content are adopted as the payment read-after content, so that the recognition accuracy of the payment voice signal is improved, the accuracy of voice payment is improved, the payment read-after content comprises the numbers, the possibility that other people steal the user record to perform voice payment is avoided, and the safety of voice payment is improved.

In order to achieve the above object, a second aspect of the present invention provides a voice payment method, including:

reporting a payment instruction;

receiving payment follow-up reading content; the payment follow-up content comprises: registering part or all of the read-after words in the read-after content, and registering part or all of the digits in the read-after content;

and acquiring a payment voice signal and reporting the payment voice signal.

Further, the method further comprises the following steps:

reporting a registration instruction;

receiving registration follow-up reading content;

and acquiring a registration voice signal and reporting the registration voice signal.

According to the voice payment method provided by the embodiment, a payment instruction is reported; receiving payment follow-up reading content; the payment follow-up content comprises: registering part or all of the read-after words in the read-after content, and registering part or all of the digits in the read-after content; the method comprises the steps of obtaining a payment voice signal, and reporting the payment voice signal, so that when the payment voice signal is matched with payment follow-up reading content, a background server determines a first probability that a word voice part in the payment voice signal belongs to each voiceprint account, and a second probability that a digital voice part in the payment voice signal belongs to each voiceprint account; determining a voiceprint account to be paid matched with the payment voice signal according to the first probability and the second probability; and payment operation is carried out on the voiceprint account to be paid according to the payment instruction, wherein the reading words and numbers in the registration reading content are used as the payment reading content, so that the recognition accuracy of the payment voice signal is improved, the accuracy of voice payment is improved, and the payment reading content comprises the numbers, so that the possibility that other people steal the user record to carry out voice payment is avoided, and the safety of voice payment is improved.

In order to achieve the above object, a third embodiment of the present invention provides a voice payment apparatus, including:

the sending module is used for sending the payment follow-up reading content after receiving the payment instruction; the payment follow-up content comprises: registering part or all of the read-after words in the read-after content, and registering part or all of the digits in the read-after content;

the determining module is used for receiving a payment voice signal, and determining a first probability that a word voice part in the payment voice signal belongs to each voiceprint account and a second probability that a digital voice part in the payment voice signal belongs to each voiceprint account when the payment voice signal is matched with the payment follow-up reading content;

the determining module is further configured to determine, according to the first probability and the second probability, a voiceprint account to be paid, which is matched with the payment voice signal;

and the payment module is used for carrying out payment operation on the voiceprint account to be paid according to the payment instruction.

Further, the device further comprises: a creation module;

the sending module is further used for sending the registration follow-up reading content after receiving the registration instruction;

and the creating module is used for receiving a registration voice signal and creating a voiceprint account according to the registration instruction when the registration voice signal is matched with the registration follow-up reading content.

Further, the device further comprises: a training module;

the training module is used for training a word recognition model according to a word voice part in the registration voice signal and a corresponding voiceprint account; the word recognition model is used for determining a first probability that a word voice part in the payment voice signal belongs to each voiceprint account;

the training module is also used for training a digital recognition model according to the digital voice part in the registration voice signal and the corresponding voiceprint account; the digital recognition model is used for determining a second probability that the digital voice part in the payment voice signal belongs to each voiceprint account.

Further, the determining module is specifically configured to,

Further, the device further comprises: the device comprises an acquisition module and a judgment module;

the acquisition module is used for acquiring a currently logged user account;

the judging module is used for judging whether the voiceprint account to be paid has the payment authority of the user account;

the payment module is specifically configured to perform payment operation on the user account according to the payment instruction when the voiceprint account to be paid has the payment right of the user account.

The voice payment device provided by the embodiment sends payment follow-up reading content after receiving the payment instruction; the payment follow-up content comprises: registering part or all of the read-after words in the read-after content, and registering part or all of the digits in the read-after content; receiving a payment voice signal, and determining a first probability that a word voice part in the payment voice signal belongs to each voiceprint account and a second probability that a digital voice part in the payment voice signal belongs to each voiceprint account when the payment voice signal is matched with payment follow-up reading content; determining a voiceprint account to be paid matched with the payment voice signal according to the first probability and the second probability; and performing payment operation on the voiceprint account to be paid according to the payment instruction, wherein the probability that the word voice part belongs to each voiceprint account and the probability that the digital voice part belongs to each voiceprint account are calculated, and the read-after words and the numbers in the registration read-after content are adopted as the payment read-after content, so that the recognition accuracy of the payment voice signal is improved, the accuracy of voice payment is improved, the payment read-after content comprises the numbers, the possibility that other people steal the user record to perform voice payment is avoided, and the safety of voice payment is improved.

In order to achieve the above object, a fourth aspect of the present invention provides a voice payment apparatus, including:

the reporting module is used for reporting the payment instruction;

the receiving module is used for receiving payment follow-up reading content; the payment follow-up content comprises: registering part or all of the read-after words in the read-after content, and registering part or all of the digits in the read-after content;

the reporting module is further configured to acquire a payment voice signal and report the payment voice signal.

Further, the reporting module is further configured to report a registration instruction;

the receiving module is further used for receiving registration read-after content;

the reporting module is further configured to acquire a registration voice signal and report the registration voice signal.

The voice payment device provided by the embodiment reports a payment instruction; receiving payment follow-up reading content; the payment follow-up content comprises: registering part or all of the read-after words in the read-after content, and registering part or all of the digits in the read-after content; the method comprises the steps of obtaining a payment voice signal, and reporting the payment voice signal, so that when the payment voice signal is matched with payment follow-up reading content, a background server determines a first probability that a word voice part in the payment voice signal belongs to each voiceprint account, and a second probability that a digital voice part in the payment voice signal belongs to each voiceprint account; determining a voiceprint account to be paid matched with the payment voice signal according to the first probability and the second probability; and payment operation is carried out on the voiceprint account to be paid according to the payment instruction, wherein the reading words and numbers in the registration reading content are used as the payment reading content, so that the recognition accuracy of the payment voice signal is improved, the accuracy of voice payment is improved, and the payment reading content comprises the numbers, so that the possibility that other people steal the user record to carry out voice payment is avoided, and the safety of voice payment is improved.

In order to achieve the above object, a fifth embodiment of the present invention provides a voice payment system, including:

the system comprises voice equipment and a background server connected with the voice equipment;

the background server is used for sending payment follow-up reading content to the voice equipment after receiving a payment instruction sent by the voice equipment; the payment follow-up content comprises: registering part or all words in the read-after content, and registering part or all numbers in the read-after content;

the background server is further used for receiving a payment voice signal sent by the voice device, and when the payment voice signal is matched with the payment follow-up content, determining a first probability that a word voice part in the payment voice signal belongs to each voiceprint account and a second probability that a digital voice part in the payment voice signal belongs to each voiceprint account; determining a voiceprint account to be paid matched with the payment voice signal according to the first probability and the second probability; and carrying out payment operation on the voiceprint account to be paid according to the payment instruction.

Further, the background server is also used for,

after receiving a registration instruction sent by the voice equipment, sending registration follow-up reading content to the voice equipment;

and the background server receives a registration voice signal sent by the voice equipment, and creates a voiceprint account according to the registration instruction when the registration voice signal is matched with the registration follow-up content.

Further, the background server is also used for,

Further, the background server is specifically configured to,

acquiring a currently logged user account;

To achieve the above object, a sixth aspect of the present invention provides an electronic device, including: memory, processor and computer program stored on the memory and executable on the processor, characterized in that the processor when executing the program implements a voice payment method as described in an embodiment of the first aspect.

To achieve the above object, a seventh embodiment of the present invention proposes an electronic apparatus, including: memory, processor and computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements a voice payment method as described in embodiments of the second aspect.

In order to achieve the above object, an eighth aspect of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the voice payment method according to the first aspect.

In order to achieve the above object, a ninth aspect of the present invention provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the voice payment method according to the second aspect.

In order to achieve the above object, a tenth aspect of the present invention provides a computer program product, wherein when being executed by an instruction processor, the computer program product executes the voice payment method according to the first aspect.

In order to achieve the above object, an eleventh embodiment of the present invention provides a computer program product, wherein when being executed by an instruction processor, the computer program product performs the voice payment method according to the second embodiment.

Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.

Drawings

The foregoing and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:

fig. 1 is a schematic flow chart of a voice payment method according to an embodiment of the present invention;

fig. 2 is a schematic flow chart of another voice payment method according to an embodiment of the present invention;

fig. 3 is a schematic flow chart of another voice payment method according to an embodiment of the present invention;

fig. 4 is a schematic structural diagram of a voice payment apparatus according to an embodiment of the present invention;

fig. 5 is a schematic structural diagram of another voice payment apparatus provided in the embodiment of the present invention;

fig. 6 is a schematic structural diagram of another voice payment apparatus provided in the embodiment of the present invention;

fig. 7 is a schematic structural diagram of a voice payment system according to an embodiment of the present invention;

fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.

The following describes a voice payment method, apparatus, and system according to an embodiment of the present invention with reference to the accompanying drawings.

Fig. 1 is a schematic flow chart of a voice payment method according to an embodiment of the present invention. As shown in fig. 1, the voice payment method includes the steps of:

s101, after receiving a payment instruction, sending payment follow-up reading content; the payment follow-up content comprises: some or all of the read-after words in the registration read-after content, and some or all of the digits in the registration read-after content.

The execution main body of the voice payment method provided by the invention is a voice payment device, and the voice payment device can be a background server corresponding to the voice equipment and can also be the voice equipment. The voice device may be, for example, a smart sound box, a smart air conditioner, a smart washing machine, a smart television, or the like, which may perform voice interaction with a user and perform corresponding operations according to an instruction of the user.

In this embodiment, in the case that the voice payment device is a background server corresponding to the voice device, the payment instruction may be obtained in a manner that, in the process of interaction between the voice device and the user, the payment voice instruction of the user is obtained by monitoring and then is directly sent to the background server; or the voice equipment performs voice recognition on the payment voice command to obtain text content, and sends the text content to the background server.

In this embodiment, in the case that the voice payment apparatus is a voice device, the payment instruction may be obtained in a manner that, in the process of interaction between the voice device and the user, the obtained payment voice instruction of the user is monitored, or text content obtained after voice recognition is performed on the payment voice instruction is monitored. The payment voice instruction may be a voice instruction including a payment related word. The payment related terms such as "pay", and "pay" may be set according to actual needs.

In this embodiment, the voice payment apparatus may have pre-stored therein the registration follow-up reading content. After receiving the payment instruction, the voice payment device may select a part of the read-after words or all of the read-after words from the registration read-after contents, select a part of the digits or all of the digits from the registration read-after contents, and determine the selected read-after words and digits as the payment read-after contents. Further, in order to further reduce the possibility that others steal the user's recording to perform voice payment, the voice payment device may randomly combine the selected numbers, and/or randomly combine the selected reading words to obtain the payment reading content. Wherein registering the number in the read-after content may include: all bit integers.

In this embodiment, in a case that the voice payment device is a background server corresponding to the voice device, the voice payment device may send the payment follow-up content to the voice device, so that the voice device plays the payment follow-up content to the user through a speaker and the like; or, the payment follow-up reading content can be displayed on the display screen of the voice device under the condition that the voice device is provided with the display screen; alternatively, in the case where the voice device communicates with other smart devices having display screens, the payment readafter content may be displayed on the display screens of the other smart devices.

In this embodiment, in the case that the voice payment device is a voice device, the voice payment device may play the payment follow-up content to the user through a speaker or the like; or, under the condition that the voice payment device is provided with the display screen, the payment follow-up reading content can be displayed on the display screen of the voice payment device; or, in the case that the voice payment apparatus communicates with other intelligent devices having display screens, the payment read-after content may be displayed on the display screens of the other intelligent devices. After the user reads the payment follow-up reading content, the voice payment device can control a microphone and the like to collect the payment voice signal of the user.

S102, receiving a payment voice signal, and when the payment voice signal is matched with the payment follow-up reading content, determining a first probability that a word voice part in the payment voice signal belongs to each voiceprint account and a second probability that a digital voice part in the payment voice signal belongs to each voiceprint account.

In this embodiment, after receiving the payment voice signal, the voice payment device may identify the payment voice signal, obtain text content corresponding to the payment voice signal, compare the text content with the payment follow-up reading content, and determine whether the text content is matched with the payment follow-up reading content; and if the text content is not matched with the payment follow-up reading content, the voice payment operation is not carried out.

In this embodiment, under the condition that the text content is matched with the payment follow-up reading content, the voice payment device can split the payment voice signal to obtain the word voice part and the digital voice part. Aiming at the word voice part, the voice payment device can input the word voice part into a pre-trained word recognition model and acquire a first probability that the word voice part output by the word recognition model belongs to each voiceprint account; the word recognition model can be obtained by training according to voice signals and voiceprint accounts of all users. Or, the voice payment device may compare the word voice part with pre-stored voice signals of each user, and determine a first probability that the word voice part belongs to each voiceprint account.

Aiming at the digital voice part, the voice payment device can input the digital voice part into a pre-trained digital recognition model and acquire a second probability that the digital voice part output by the digital recognition model belongs to each voiceprint account; the digital recognition model can be obtained by training according to voice signals and voiceprint accounts of all users. Or, the voice payment apparatus may compare the digital voice portion with pre-stored voice signals of each user, and determine the second probability that the digital voice portion belongs to each voiceprint account.

S103, determining the voiceprint account to be paid matched with the payment voice signal according to the first probability and the second probability.

In this embodiment, the process of the voice payment apparatus executing step 103 may specifically be that, for each voiceprint account, a weighted sum of the corresponding first probability and the corresponding second probability is determined as a probability that the payment voice signal belongs to the voiceprint account; and when the probability that the payment voice signal belongs to the voiceprint account meets a preset probability threshold value and the number of the voiceprint accounts meeting the preset probability threshold value is 1, determining that the voiceprint account is the voiceprint account to be paid matched with the payment voice signal.

In this embodiment, when the number of voiceprint accounts meeting the preset probability threshold is two or more, in order to avoid a matching error of the voiceprint accounts to be paid, the voice payment device does not perform payment operation. Furthermore, the voice payment device can also resend the payment follow-up reading content, and receive the payment voice signal again for judgment until the sending times of the payment follow-up reading content exceeds the preset number threshold.

And S104, carrying out payment operation on the voiceprint account to be paid according to the payment instruction.

In this embodiment, before step 104, the method may further include: acquiring a currently logged user account; and judging whether the voiceprint account to be paid has the payment authority of the user account. Correspondingly, step 104 may specifically be that, when the voiceprint account to be paid has the payment right of the user account, the payment operation is performed on the user account according to the payment instruction.

It should be noted that, in the case that the voice payment apparatus is a voice device, the voice payment apparatus may send the payment instruction to the background server corresponding to the voice device, so that the background server performs payment operation on the voiceprint account to be paid according to the payment instruction.

In this embodiment, one user account may correspond to multiple voiceprint accounts, and a user corresponding to the user account may set payment permissions for the multiple voiceprint accounts. For example, in a family scenario, each family member may have a voiceprint account, a user account may be registered by one of the family members, and the family member may set payment rights of other family members.

According to the voice payment method provided by the embodiment, the probability that the word voice part belongs to each voiceprint account and the probability that the digital voice part belongs to each voiceprint account are calculated, the read-after words and the numbers in the registration read-after content are used as the payment read-after content, the recognition accuracy of the payment voice signal is improved, the accuracy of voice payment is improved, the payment read-after content comprises the numbers, the possibility that other people steal user records to carry out voice payment is avoided, and therefore the safety of voice payment is improved.

Fig. 2 is a schematic flow chart of another voice payment method provided in the embodiment of the present invention, as shown in fig. 2, on the basis of the embodiment shown in fig. 1, the method may further include a registration flow:

and S105, after receiving the registration instruction, sending the registration follow-up reading content.

In this embodiment, in the case that the voice payment apparatus is a background server corresponding to the voice device, the registration instruction may be obtained in a manner that, in the process of interaction between the voice device and the user, the registration voice instruction of the user is obtained by monitoring and is directly sent to the background server; or the voice equipment performs voice recognition on the registered voice command to obtain text content, and sends the text content to the background server.

In this embodiment, in the case that the voice payment apparatus is a voice device, the registration instruction may be obtained in a manner that, in the process of interaction between the voice device and the user, the obtained registration voice instruction of the user is monitored, or text content obtained after voice recognition is performed on the registration voice instruction is monitored. The voice instruction for registration may be, for example, a voice instruction including a word related to registration. The registration related terms such as "register", "open an account", "open" and the like may be set according to actual needs.

In this embodiment, the voice payment apparatus may have pre-stored therein the registration follow-up reading content.

In this embodiment, in a case that the voice payment apparatus is a background server corresponding to the voice device, the voice payment apparatus may send the registration read-after content to the voice device, so that the voice device plays the registration read-after content to the user through a speaker and the like; or, the registration read-after content can be displayed on the display screen of the voice device under the condition that the voice device is provided with the display screen; alternatively, in the case where the voice device communicates with other smart devices having display screens, the registration read-after content may be displayed on the display screens of the other smart devices.

In this embodiment, in the case that the voice payment apparatus is a voice device, after receiving the registration instruction, the voice payment apparatus may play the registration follow-up content to the user through a speaker or the like; or, the registration read-after content can be displayed on the display screen of the voice payment device under the condition that the display screen is arranged on the voice payment device; or, in the case that the voice payment apparatus communicates with other intelligent devices having display screens, the registration read-after content may be displayed on the display screens of the other intelligent devices. After the user follows the registration and reading content, the voice payment device can control a microphone and the like to collect the registration voice signal of the user.

And S106, receiving the registration voice signal, and creating a voiceprint account according to the registration instruction when the registration voice signal is matched with the registration follow-up content.

In this embodiment, after the voice payment apparatus creates the voiceprint account, the voiceprint account and the corresponding registered voice signal may be saved. It should be noted that, in this embodiment, the voiceprint account created by the voice payment device is a voiceprint account that can uniquely identify the user and corresponds to the registered voice signal one to one.

S107, training a word recognition model according to a word voice part in the registered voice signal and a corresponding voiceprint account; the term recognition model is used to determine a first probability that a term speech portion in the payment speech signal belongs to a respective voiceprint account.

In this embodiment, because there is the difference in the registration voice signal that the user carried out many times with reading to registration with reading content and obtained, and the word recognition model needs a large amount of registration voice signals to train to guarantee the degree of accuracy of word recognition model recognition, therefore, in the registration process, voice payment device can send registration with reading content many times, obtain a large amount of registration voice signals, train word recognition model according to the voice print account and the word speech part in a large amount of registration voice signals that correspond, ensure the degree of accuracy of recognition of word recognition model.

S108, training a digital recognition model according to the digital voice part in the registered voice signal and the corresponding voiceprint account; the digital recognition model is used to determine a second probability that the digital voice portion of the payment voice signal belongs to the respective voiceprint account.

In this embodiment, the voice payment apparatus may train the digital recognition model according to the voiceprint account and the corresponding digital voice portions in the large number of registered voice signals, so as to ensure the recognition accuracy of the digital recognition model.

According to the voice payment method provided by the embodiment, the word recognition model and the digital recognition model are trained by adopting the registration and follow-up reading content, so that the safety of voice payment is further improved.

Fig. 3 is a schematic flow chart of another voice payment method according to an embodiment of the present invention, and as shown in fig. 3, the voice payment method includes the following steps:

301. and reporting the payment instruction.

The execution main body of the voice payment method provided by the invention is a voice payment device, and the voice payment device can be specifically a voice device. The voice device may be, for example, a smart sound box, a smart air conditioner, a smart washing machine, a smart television, or the like, which may perform voice interaction with a user and perform corresponding operations according to an instruction of the user.

In this embodiment, the payment instruction may be obtained in a manner that, in the process of interaction between the voice device and the user, the obtained payment voice instruction of the user is monitored, or text content obtained after voice recognition is performed on the payment voice instruction is obtained. The payment voice instruction may be a voice instruction including a payment related word. The payment related terms such as "pay", and "pay" may be set according to actual needs.

In this embodiment, after obtaining the payment instruction, the voice payment device may send the payment instruction to the backend server, and after receiving the payment instruction, the backend server may select a part of the read-after words or all the read-after words from the registration read-after contents, select a part of the digits or all the digits from the registration read-after contents, and determine the selected read-after words and digits as the payment read-after contents. Further, in order to further reduce the possibility that others steal the user's recording to perform voice payment, the background server may randomly combine the selected numbers and/or randomly combine the selected reading words to obtain the payment reading content. Wherein registering the number in the read-after content may include: all bit integers.

302. Receiving payment follow-up reading content; the payment follow-up content comprises: some or all of the read-after words in the registration read-after content, and some or all of the digits in the registration read-after content.

In this embodiment, after receiving the payment follow-up reading content, the voice payment device may play the payment follow-up reading content to the user through a speaker or the like; or, under the condition that the voice payment device is provided with the display screen, the payment follow-up reading content can be displayed on the display screen of the voice payment device; or, in the case that the voice payment apparatus communicates with other intelligent devices having display screens, the payment read-after content may be displayed on the display screens of the other intelligent devices. After the user reads the payment follow-up reading content, the voice payment device can control a microphone and the like to collect the payment voice signal of the user.

303. And acquiring a payment voice signal and reporting the payment voice signal.

In this embodiment, after obtaining the payment voice signal, the voice payment device may send the payment voice signal to the background server for processing. After receiving the payment voice signal, the background server can identify the payment voice signal, acquire text content corresponding to the payment voice signal, compare the text content with the payment follow-up reading content, and judge whether the text content is matched with the payment follow-up reading content; and if the text content is not matched with the payment follow-up reading content, the voice payment operation is not carried out.

In this embodiment, under the condition that the text content is matched with the payment follow-up reading content, the background server may split the payment voice signal to obtain the word voice part and the digital voice part. Aiming at the word voice part, the background server can input the word voice part into a pre-trained word recognition model, and obtain a first probability that the word voice part output by the word recognition model belongs to each voiceprint account; the word recognition model can be obtained by training according to voice signals and voiceprint accounts of all users. Aiming at the digital voice part, the background server can input the digital voice part into a pre-trained digital recognition model and acquire a second probability that the digital voice part output by the digital recognition model belongs to each voiceprint account; the digital recognition model can be obtained by training according to voice signals and voiceprint accounts of all users.

After a first probability that the word voice part belongs to each voiceprint account and a second probability that the digital voice part belongs to each voiceprint account are obtained, for each voiceprint account, the background server can determine the weighted sum of the corresponding first probability and the corresponding second probability as the probability that the payment voice signal belongs to the voiceprint account; when the probability that the payment voice signal belongs to the voiceprint account meets a preset probability threshold value and the number of the voiceprint accounts meeting the preset probability threshold value is 1, determining the voiceprint account as a voiceprint account to be paid, which is matched with the payment voice signal; and carrying out payment operation on the voiceprint account to be paid according to the payment instruction.

Further, on the basis of the above embodiment, the method may further include: reporting a registration instruction; receiving registration follow-up reading content; and acquiring a registration voice signal and reporting the registration voice signal.

The acquisition mode of the registration instruction may be that, in the process of interaction between the voice device and the user, the acquired registration voice instruction of the user is monitored, or text content obtained after voice recognition is performed on the registration voice instruction is obtained. The voice instruction for registration may be, for example, a voice instruction including a word related to registration. The registration related terms such as "register", "open an account", "open" and the like may be set according to actual needs.

In this embodiment, after the voice payment device obtains the registration instruction, the voice payment device may report the registration instruction to the background server, so that the background server obtains the pre-stored registration read-after content and sends the pre-stored registration read-after content to the voice payment device.

In this embodiment, the voice payment device may play the registration follow-up content sent by the background server to the user through a speaker or the like; or, the registration read-after content can be displayed on the display screen of the voice payment device under the condition that the display screen is arranged on the voice payment device; or, under the condition that the voice payment device is communicated with other intelligent equipment with a display screen, the registration read-after content can be displayed on the display screens of other intelligent equipment; so that the user can read the registration read-after content to obtain the registration voice signal.

In this embodiment, the voice payment device may collect a registration voice signal of the user through a microphone and the like, and report the registration voice signal to the background server, so that the background server creates a voiceprint account according to the registration instruction when the registration voice signal matches the registration follow-up reading content; training a word recognition model according to a word voice part in the registered voice signal and a corresponding voiceprint account; the word recognition model is used for determining a first probability that a word voice part in the payment voice signal belongs to each voiceprint account; training a digital recognition model according to a digital voice part in the registered voice signal and a corresponding voiceprint account; the digital recognition model is used to determine a second probability that the digital voice portion of the payment voice signal belongs to the respective voiceprint account.

The voice payment method provided by the embodiment improves the recognition accuracy of the payment voice signal, improves the accuracy of voice payment, and avoids the possibility that other people steal the user record to carry out voice payment because the payment follow-up reading content comprises numbers, thereby improving the safety of voice payment.

Fig. 4 is a schematic structural diagram of a voice payment apparatus according to an embodiment of the present invention. As shown in fig. 4, includes: a sending module 41, a determining module 42 and a payment module 43.

The sending module 41 is configured to send the payment follow-up content after receiving the payment instruction; the payment follow-up content comprises: registering part or all of the read-after words in the read-after content, and registering part or all of the digits in the read-after content;

a determining module 42, configured to receive a payment voice signal, and when the payment voice signal matches the payment readafter content, determine a first probability that a word voice part in the payment voice signal belongs to each voiceprint account, and a second probability that a digital voice part in the payment voice signal belongs to each voiceprint account;

the determining module 42 is further configured to determine, according to the first probability and the second probability, a voiceprint account to be paid, which matches the payment voice signal;

and the payment module 43 is configured to perform payment operation on the voiceprint account to be paid according to the payment instruction.

The voice payment device provided by the invention can be specifically a voice device or a background server corresponding to the voice device. The voice device may be, for example, a smart sound box, a smart air conditioner, a smart washing machine, a smart television, or the like, which may perform voice interaction with a user and perform corresponding operations according to an instruction of the user.

In the case that the voice payment device is a background server corresponding to the voice device, the payment instruction may be obtained in a manner that, in the process of interaction between the voice device and the user, the payment voice instruction of the user is obtained by monitoring and is directly sent to the background server; or the voice equipment performs voice recognition on the payment voice command to obtain text content, and sends the text content to the background server.

Further, on the basis of the foregoing embodiment, the determining module 42 is specifically configured to, for each voiceprint account, determine, as the probability that the payment voice signal belongs to the voiceprint account, a weighted sum of the corresponding first probability and the corresponding second probability; and when the probability that the payment voice signal belongs to the voiceprint account meets a preset probability threshold value and the number of the voiceprint accounts meeting the preset probability threshold value is 1, determining that the voiceprint account is the voiceprint account to be paid matched with the payment voice signal.

Further, on the basis of the above embodiment, the apparatus may further include: the device comprises an acquisition module and a judgment module;

the acquisition module is used for acquiring a user account currently logged in;

The voice payment device provided by the embodiment calculates the probability that the word voice part belongs to each voiceprint account and the probability that the digital voice part belongs to each voiceprint account, and adopts the read-after words and the number in the registration read-after content as the payment read-after content, so that the recognition accuracy of the payment voice signal is improved, the accuracy of voice payment is improved, the payment read-after content comprises the number, the possibility that other people steal the user record to carry out voice payment is avoided, and the safety of voice payment is improved.

Further, with reference to fig. 5, on the basis of the embodiment shown in fig. 4, the apparatus further includes: a creation module 44 and a training module 45;

the sending module 41 is further configured to send the registration read-after content after receiving the registration instruction;

the creating module 44 is configured to receive a registration voice signal, and create a voiceprint account according to the registration instruction when the registration voice signal matches the registration read-after content;

the training module 45 is configured to train a word recognition model according to a word voice part in the registration voice signal and a corresponding voiceprint account; the word recognition model is used for determining a first probability that a word voice part in the payment voice signal belongs to each voiceprint account;

the training module 45 is further configured to train a digital recognition model according to the digital voice part in the registration voice signal and the corresponding voiceprint account; the digital recognition model is used for determining a second probability that the digital voice part in the payment voice signal belongs to each voiceprint account.

In the case that the voice payment device is a background server corresponding to the voice device, the registration instruction may be obtained in a manner that, in the process of interaction between the voice device and the user, the registration voice instruction of the user is obtained by monitoring and is directly sent to the background server; or the voice equipment performs voice recognition on the registered voice command to obtain text content, and sends the text content to the background server.

In this embodiment, the voice payment apparatus may have pre-stored therein the registration follow-up reading content. Under the condition that the voice payment device is a voice device, after receiving the registration instruction, the voice payment device can play the registration read-after content to the user through a loudspeaker and the like; or, the registration read-after content can be displayed on the display screen of the voice payment device under the condition that the display screen is arranged on the voice payment device; or, in the case that the voice payment apparatus communicates with other intelligent devices having display screens, the registration read-after content may be displayed on the display screens of the other intelligent devices. After the user follows the registration and reading content, the voice payment device can control a microphone and the like to collect the registration voice signal of the user.

In this embodiment, because there is the difference in the registration voice signal that the user carried out many times with reading to registration with reading content and obtained, and the word recognition model needs a large amount of registration voice signals to train to guarantee the degree of accuracy of word recognition model recognition, therefore, in the registration process, voice payment device can send registration with reading content many times, obtain a large amount of registration voice signals, train word recognition model according to the voice print account and the word speech part in a large amount of registration voice signals that correspond, ensure the degree of accuracy of recognition of word recognition model. In addition, the voice payment device can train the digital recognition model according to the voiceprint account and the digital voice parts in the corresponding mass registration voice signals, and the recognition accuracy of the digital recognition model is ensured.

The voice payment device provided by the embodiment trains the word recognition model and the digital recognition model by adopting the registration and reading content, thereby further improving the safety of voice payment.

Fig. 6 is a schematic structural diagram of another voice payment apparatus according to an embodiment of the present invention. As shown in fig. 6, includes: a reporting module 61 and a receiving module 62.

The reporting module 61 is used for reporting a payment instruction;

a receiving module 62, configured to receive payment follow-up content; the payment follow-up content comprises: registering part or all of the read-after words in the read-after content, and registering part or all of the digits in the read-after content;

the reporting module 61 is further configured to acquire a payment voice signal and report the payment voice signal.

The voice payment device provided by the invention can be specifically a voice device. The voice device may be, for example, a smart sound box, a smart air conditioner, a smart washing machine, a smart television, or the like, which may perform voice interaction with a user and perform corresponding operations according to an instruction of the user.

Further, on the basis of the foregoing embodiment, the reporting module 61 is further configured to report a registration instruction;

the receiving module 62 is further configured to receive registration read-after content;

the reporting module 61 is further configured to acquire a registration voice signal and report the registration voice signal.

The voice payment device provided by the embodiment improves the recognition accuracy of the payment voice signal, improves the accuracy of voice payment, and avoids the possibility that other people steal the user record to carry out voice payment due to the fact that the payment is carried out with the reading content including the number, thereby improving the safety of voice payment.

Fig. 7 is a schematic structural diagram of a voice payment system according to an embodiment of the present invention. As shown in fig. 7, includes: a voice device 71 and a background server 72 connected to the voice device.

The background server 72 is configured to send payment follow-up content to the voice device after receiving a payment instruction sent by the voice device; the payment follow-up content comprises: registering part or all words in the read-after content, and registering part or all numbers in the read-after content;

the background server 72 is further configured to receive a payment voice signal sent by the voice device, and when the payment voice signal matches the payment follow-up content, determine a first probability that a word voice part in the payment voice signal belongs to each voiceprint account, and a second probability that a digital voice part in the payment voice signal belongs to each voiceprint account; determining a voiceprint account to be paid matched with the payment voice signal according to the first probability and the second probability; and carrying out payment operation on the voiceprint account to be paid according to the payment instruction. Wherein registering the number in the read-after content may include: all bit integers.

Further, the background server 72 is further configured to send registration read-after content to the voice device after receiving a registration instruction sent by the voice device; and the background server receives a registration voice signal sent by the voice equipment, and creates a voiceprint account according to the registration instruction when the registration voice signal is matched with the registration follow-up content.

Further, the background server 72 is further configured to train a word recognition model according to the word voice part in the registration voice signal and the corresponding voiceprint account; the word recognition model is used for determining a first probability that a word voice part in the payment voice signal belongs to each voiceprint account; training a digital recognition model according to the digital voice part in the registration voice signal and the corresponding voiceprint account; the digital recognition model is used for determining a second probability that the digital voice part in the payment voice signal belongs to each voiceprint account.

Further, the background server 72 is specifically configured to, for each voiceprint account, determine a weighted sum of the corresponding first probability and the corresponding second probability as a probability that the payment voice signal belongs to the voiceprint account; and when the probability that the payment voice signal belongs to the voiceprint account meets a preset probability threshold value and the number of the voiceprint accounts meeting the preset probability threshold value is 1, determining that the voiceprint account is the voiceprint account to be paid matched with the payment voice signal.

Further, the background server 72 is specifically configured to obtain a currently logged-in user account; judging whether the voiceprint account to be paid has the payment authority of the user account; and when the voiceprint account to be paid has the payment authority of the user account, carrying out payment operation on the user account according to the payment instruction.

It should be noted that, in this embodiment, for the specific function description of the voice device and the background server, reference may be made to the embodiments shown in fig. 1 to fig. 3, and a detailed description is not made here.

Fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. The electronic device includes:

memory 1001, processor 1002, and computer programs stored on memory 1001 and executable on processor 1002.

The processor 1002, when executing the program, implements a voice payment method as provided in the embodiment shown in fig. 1 or fig. 2, or implements a voice payment method as provided in the embodiment shown in fig. 3.

Further, the electronic device further includes:

a communication interface 1003 for communicating between the memory 1001 and the processor 1002.

A memory 1001 for storing computer programs that may be run on the processor 1002.

Memory 1001 may include high-speed RAM memory and may also include non-volatile memory (e.g., at least one disk memory).

A processor 1002, configured to execute the program to implement the voice payment method provided in the embodiment shown in fig. 1 or fig. 2, or to implement the voice payment method provided in the embodiment shown in fig. 3.

If the memory 1001, the processor 1002, and the communication interface 1003 are implemented independently, the communication interface 1003, the memory 1001, and the processor 1002 may be connected to each other through a bus and perform communication with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 8, but this is not intended to represent only one bus or type of bus.

Optionally, in a specific implementation, if the memory 1001, the processor 1002, and the communication interface 1003 are integrated on one chip, the memory 1001, the processor 1002, and the communication interface 1003 may complete communication with each other through an internal interface.

The processor 1002 may be a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement embodiments of the present invention.

The present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a voice payment method as in the embodiment shown in fig. 1 or fig. 2.

The present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a voice payment method as in the embodiment shown in fig. 3.

The invention also provides a computer program product characterized in that instructions in the computer program product, when executed by a processor, perform a voice payment method as in the embodiment shown in fig. 1 or fig. 2.

The invention also provides a computer program product characterized in that instructions in the computer program product, when executed by a processor, perform a voice payment method as in the embodiment shown in fig. 3.

In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.

Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.

The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.

It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.

It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.

In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.

The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.

Claims

1. A voice payment method, comprising:

receiving a payment voice signal, determining a first probability that a word voice part in the payment voice signal belongs to each voiceprint account based on a word recognition model when the payment voice signal is matched with the payment follow-up content, and determining a second probability that a digital voice part in the payment voice signal belongs to each voiceprint account based on a digital recognition model; wherein the input of the word recognition model is the word speech part; the input of the digital recognition model is the digital voice part;

2. The method of claim 1, further comprising:

3. The method of claim 2, further comprising:

4. The method of any of claims 1-3, wherein registering the number in the read-after content comprises: all bit integers.

5. The method of claim 1, wherein the determining the voiceprint account to be paid that matches the payment voice signal based on the first probability and the second probability comprises:

6. The method of claim 1, wherein before the payment operation is performed on the voiceprint account to be paid according to the payment instruction, the method further comprises:

acquiring a currently logged user account;

7. A voice payment method, comprising:

reporting a payment instruction;

the method comprises the steps of obtaining a payment voice signal, reporting the payment voice signal, determining a first probability that a word voice part in the payment voice signal belongs to each voiceprint account based on a word recognition model, determining a second probability that a digital voice part in the payment voice signal belongs to each voiceprint account based on a digital recognition model, further determining a voiceprint account to be paid matched with the payment voice signal, and carrying out payment operation; wherein the input of the word recognition model is the word speech part; the input of the digital recognition model is the digital speech portion.

8. The method of claim 7, further comprising:

reporting a registration instruction;

receiving registration follow-up reading content;

9. The method of claim 7 or 8, wherein registering the number in the read-after content comprises: all bit integers.

10. A voice payment device, comprising:

the determining module is used for receiving a payment voice signal, determining a first probability that a word voice part in the payment voice signal belongs to each voiceprint account based on a word recognition model when the payment voice signal is matched with the payment follow-up content, and determining a second probability that a digital voice part in the payment voice signal belongs to each voiceprint account based on a digital recognition model; wherein the input of the word recognition model is the word speech part; the input of the digital recognition model is the digital voice part;

11. The apparatus of claim 10, further comprising: a creation module;

12. The apparatus of claim 11, further comprising: a training module;

13. The apparatus of any of claims 10-12, wherein registering the number in the read-after content comprises: all bit integers.

14. The apparatus of claim 10, wherein the means for determining is configured to,

15. The apparatus of claim 10, further comprising: the device comprises an acquisition module and a judgment module;

the acquisition module is used for acquiring a currently logged user account;

16. A voice payment device, comprising:

the reporting module is used for reporting the payment instruction;

the reporting module is further configured to acquire a payment voice signal, report the payment voice signal, determine a first probability that a word voice part in the payment voice signal belongs to each voiceprint account based on a word recognition model, determine a second probability that a digital voice part in the payment voice signal belongs to each voiceprint account based on a digital recognition model, determine a voiceprint account to be paid, which is matched with the payment voice signal, and perform payment operation; wherein the input of the word recognition model is the word speech part; the input of the digital recognition model is the digital speech portion.

17. The apparatus of claim 16,

the reporting module is further configured to report a registration instruction;

18. The apparatus of claim 16 or 17, wherein registering the number in the read-after content comprises: all bit integers.

19. A voice payment system, comprising: the system comprises voice equipment and a background server connected with the voice equipment;

the background server is further used for receiving a payment voice signal sent by the voice device, determining a first probability that a word voice part in the payment voice signal belongs to each voiceprint account based on a word recognition model when the payment voice signal is matched with the payment follow-up content, and determining a second probability that a digital voice part in the payment voice signal belongs to each voiceprint account based on a digital recognition model; determining a voiceprint account to be paid matched with the payment voice signal according to the first probability and the second probability; carrying out payment operation on the voiceprint account to be paid according to the payment instruction; wherein the input of the word recognition model is the word speech part; the input of the digital recognition model is the digital speech portion.

20. The system of claim 19, wherein the backend server is further configured to,

21. The system of claim 20, wherein the backend server is further configured to,

22. The system of any of claims 19-21, wherein registering the number in the read-after content comprises: all bit integers.

23. The system of claim 19, wherein the backend server is specifically configured to,

24. The system of claim 19, wherein the backend server is specifically configured to,

acquiring a currently logged user account;

25. An electronic device, comprising: memory, processor and computer program stored on the memory and executable on the processor, which when executed by the processor implements a voice payment method as claimed in any one of claims 1 to 6.

26. An electronic device, comprising: memory, processor and computer program stored on the memory and executable on the processor, which when executed by the processor implements a voice payment method as claimed in any one of claims 7 to 9.

27. A non-transitory computer-readable storage medium having stored thereon a computer program, wherein the program, when executed by a processor, implements the voice payment method of any one of claims 1-6.

28. A non-transitory computer-readable storage medium having stored thereon a computer program, wherein the program, when executed by a processor, implements the voice payment method of any one of claims 7-9.