TWM635534U - Artificial intelligence voice controlled banking transaction system - Google Patents

Abstract

An artificial intelligence voice-activated bank transaction system includes an automatic teller machine, a computing device, a memory, and a voice receiving device. The computing device is used for identity verification operation and instruction confirmation operation, the memory is used for storing two voice messages, and a voice recognition model, registered identity data and command database, and the voice receiving device is used for receiving two voice messages and transmitting them to the memory. The identity verification operation includes extracting the pending identity data in the first voice message through the voice recognition model, and comparing and confirming that the pending identity data matches the registered identity data, and the command confirmation operation includes extracting a second voice message through the voice recognition model The pending instruction data in the command database, and an execution instruction data that compares and determines that the pending instruction data corresponds to a plurality of execution instruction data in the instruction database.

Description

Artificial intelligence voice-activated banking transaction system

This creation is about a bank transaction system, especially an artificial intelligence voice-activated bank transaction system.

Current banking transaction systems, such as automatic teller machine (ATM) transaction interfaces are mostly in the form of buttons or panels, which in some cases or for specific groups (such as visually impaired, mobility-impaired) has caused certain inconvenience sex.

In some systems, the voice function is often assisted, and needs to be matched with screen display and touch Braille. Therefore, for certain users, using assisted ATMs is often not as convenient as using online banking through mobile phones.

In view of the above, this creation provides an artificial intelligence voice-activated banking transaction system.

According to an embodiment of the invention, the artificial intelligence voice-activated bank transaction system includes an automatic teller machine, a computing device connected to the automatic teller machine, a memory connected to the computing device, and a voice receiving device connected to the memory. The automatic teller machine is used to allow the user to handle the bank counter service by himself, the computing device is used to perform an identity verification operation and an instruction confirmation operation on the user, and the memory is used to store a first and a second voice message, and store a voice recognition The model, a user's registered identity data and an instruction database, the voice receiving device is used to receive the user's first and second voice messages and transmit them to the memory. The identity verification operation performed by the computing device includes: using a voice recognition model to extract a pending message contained in the first voice message The identity data, and comparing the pending identity data with the registered identity data and confirming that the pending identity data conforms to the registered identity data, and the command confirmation operation performed by the computing device includes: extracting the information contained in a second voice message by a voice recognition model A pending order data, and comparing the pending order data with a plurality of execution order data in the order database to determine an execution order data corresponding to the pending order data.

With the above structure, the artificial intelligence voice-activated banking transaction system disclosed in this case can judge the content of the received voice message through the memory with the artificial intelligence voice recognition model and the computing device, so as to safely and effectively execute identity verification and instructions Confirmed function. Let the user only need to tell his identity or account information in front of the automatic teller machine to complete the verification, and then verbally express the banking service items he wants to perform. In this way, the general banking business can be completed completely through voice control. It is a convenient measure for the ethnic group.

The above description about the content of this disclosure and the following description of the implementation are used to demonstrate and explain the spirit and principle of this creation, and to provide a further explanation of the patent application scope of this creation.

1: Artificial intelligence voice-activated bank transaction system

10: Automatic teller machine

20: computing device

30,30',30",30''': memory

31: Speech Recognition Model

32: Registration of identity information

33: Command database

34: Facial feature detection model

35:Register facial features

36: Lip recognition model

37: The first trigger message

38: The second trigger message

40: Voice receiving device

50: Image capture device

C: user

S40: Identity verification operation

S400~S402,S500~S503,S600~S604,S700~S703,

Fig. 1a is a block diagram of an artificial intelligence voice-activated banking transaction system according to an embodiment of the invention.

FIG. 1 b is a block diagram of a usage scenario of an artificial intelligence voice-activated banking transaction system according to an embodiment of the present invention.

Fig. 1c is a schematic block diagram of receiving voice messages by the memory of the artificial intelligence voice-activated banking transaction system according to an embodiment of the present invention.

Fig. 2a is an operation flowchart of the identity verification performed by the artificial intelligence voice-activated banking transaction system according to an embodiment of the present invention.

Fig. 2b is an operation flow chart of the execution order confirmation of the artificial intelligence voice-activated banking transaction system according to an embodiment of the present invention.

FIG. 3 is another flow chart of the identity verification performed by the artificial intelligence voice-activated banking transaction system according to an embodiment of the present invention.

Fig. 4 is another operation flow chart showing the operation confirmation of the artificial intelligence voice-activated banking transaction system according to an embodiment of the present invention.

Fig. 5a is a block diagram of an artificial intelligence voice-activated banking transaction system according to another embodiment of the present invention.

Fig. 5b is a block diagram of a usage scenario of an artificial intelligence voice-activated banking transaction system according to another embodiment of the present invention.

Fig. 5c is a schematic block diagram of receiving voice messages and facial image data by the memory of the artificial intelligence voice-activated banking transaction system according to another embodiment of the present invention.

FIG. 6 is an operation flowchart of face recognition for identity verification performed by the artificial intelligence voice-activated banking transaction system according to another embodiment of the present invention.

FIG. 7 is a schematic block diagram of another memory receiving messages and data of the artificial intelligence voice-activated banking transaction system according to another embodiment of the present invention.

FIG. 8 is a flow chart of an operation of the artificial intelligence voice-activated bank transaction system performing lip recognition for order confirmation according to another embodiment of the present invention.

FIG. 9 is a block diagram of a usage scenario of an artificial intelligence voice-activated banking transaction system according to other embodiments of the present invention.

FIG. 10 is a schematic block diagram of receiving messages and data from other memories of the artificial intelligence voice-activated banking transaction system shown in other embodiments of the present invention.

FIG. 11 is a block flow diagram of the artificial intelligence voice-activated banking transaction system when triggered according to other embodiments of the present invention.

The detailed features and advantages of this creation are described in detail below in the implementation mode. The content is enough to enable anyone familiar with the relevant art to understand the technical content of this creation and implement it according to the content disclosed in this specification, the patent scope and drawings , anyone who is familiar with the related art can easily understand the purpose and advantages related to this creation. The following examples are to further describe the viewpoints of this creation in detail, but not to limit the scope of this creation in any way.

Please refer to Fig. 1a to Fig. 1c, Fig. 1a is a block diagram of an artificial intelligence voice-activated bank transaction system according to an embodiment of the invention, and Fig. 1b is an artificial intelligence voice-activated bank transaction system according to an embodiment of this creation 1c is a block diagram of receiving voice messages by the memory of the artificial intelligence voice-activated banking transaction system according to an embodiment of the present invention.

As shown in Figure 1a and Figure 1b, the artificial intelligence voice-activated banking transaction system 1 includes an automatic teller machine 10, a computing device 20 whose signal is connected to the automatic teller machine 10, a memory 30 whose signal is connected to the computing device 20, and a signal connected to the memory 30 The voice receiving device 40. The automatic teller machine 10 is used to allow the user C to handle bank counter services by himself, for example but not limited thereto, it can be an automatic teller machine (ATM) used by the general public. Computing device 20 is used for user C to carry out Perform an identity verification operation and an instruction confirmation operation, that is, verify the identity of the user C and determine the instruction the user intends to issue, wherein the computing device 20 can be a variety of processors with computing capabilities. The memory 30 is used to store a first and second voice message, and stores a voice recognition model 31, a registered identity data 32 of the user C and an instruction database 33, wherein the memory 30 can be various storage capacity. The voice receiving device 40 is used to receive the first and second voice messages of the user C and transmit them to the memory 30, wherein the voice receiving device 40 can be a microphone, and can be arranged adjacent to the automatic teller machine 10 to receive messages from the user C. voice.

Please refer to FIG. 1c together. The voice receiving device 40 transmits the first voice message and the second voice message to the memory 30 in the form of signal transmission. The above two voice messages will be analyzed and judged by the computing device 20 through the voice recognition model 31, and the first voice message and the second voice message are respectively corresponding to the registered identity data 32 and the instruction database 33, which will be described later. It should be noted that the connection lines between different blocks in Fig. 1a to Fig. 1c can be solid lines or dotted lines. Specifically, the signal connections between different blocks can be connected through physical signal lines or through wireless communication. This case is not limited. On the other hand, as those with ordinary knowledge of this case can understand, except that the voice receiving device 40 in FIG. For example, the computing device 20 can be a central processing unit, and the memory 30 can be a cloud database, etc. Of course, in some embodiments, the computing device 20 and the memory 30 can be arranged adjacent to the automatic teller machine 10 to achieve high-efficiency edge computing and prevent data interception, etc. This part will be described later and should not be Limitations in this case.

Regarding the speech recognition model 31 of this example, it can be a neural network trained by a deep learning method in advance. Specifically, the speech recognition model 31 can include automatic speech recognition (Automatic Speech Recognition, ASR) software, so that theoretically, the calculation The device 20 can perform the following steps through the automatic speech recognition software to complete the speech recognition function of this case. 1. The user sends a voice message to the voice receiving device. 2. Convert the voice message into a sound wave signal. 3. The filter in the voice receiving device filters out the noise in the sound wave signal. 4. Decompose the filtered sound wave signal into multiple groups of phonemes (Phonemes) (the so-called phonemes refer to the basic sound blocks that make up the sound of a language. In English, there are 44 phonemes such as "wh", "th" and "t ", etc., while the Chinese system lacks a unified standard and there is no fixed number). 5. Each phoneme can form a list (list), and can be statistically analyzed sequentially. 6. Can understand the meaning of a passage through automatic speech recognition software.

The speech recognition model 31 based on the above-mentioned automatic speech recognition can have two main variations, which are Directed Dialogue (Directed Dialogue) model and Natural Language Processing (NLP) model. In this article, a direct dialogue model will be used as an example, but in other embodiments, a natural language processing model may also be used, and this case is not limited thereto. The so-called direct dialogue model refers to the ability to directly provide users with a certain range of specific choice vocabulary, making it easier for machines to judge semantics than using natural language processing models.

Based on the above-mentioned artificial intelligence voice-activated banking transaction system 1 shown in FIG. 1a to FIG. 1c, please refer to FIG. 2a and FIG. 2b. FIG. Fig. 2b is an operation flow chart of confirming execution instructions of the artificial intelligence voice-activated banking transaction system according to an embodiment of the invention.

As shown in FIG. 2a, the identity verification operation S40 performed by the computing device includes, step S400: extract a pending identity data contained in the first voice message through the speech recognition model, step S401: compare the pending identity data with the registered identity data And confirm that the pending identity data matches the registered identity data, and step S402: when judging that the pending identity data matches the registered identity data, the computing device can perform an instruction confirmation operation for the user. For example, in step S400, the automatic teller machine can first send a message to the user: "Please tell me the user account number and password." The user then tells the voice receiving device the account number and password composed of English and numbers (ie The first voice message), the voice receiving device transmits the sound wave signal to the memory for analysis by the computing device. In this case, the computing device can actively use the phoneme model including English and numbers to analyze the sound wave signal, so as to obtain a series of input account numbers and input passwords (ie pending identity information). Of course, in other embodiments, the user does not need to tell the account number and password, but also information such as the user's name, ID card number or birthday, and the implementation method is the same as above and this case is not limited thereto. For example, in step S401, the computing device compares the input account number and input password with the pre-stored registration account number and registration password (ie registration identity information). Further, the computing device will first compare the account number to determine the corresponding password of the input account, and then compare the input password with the pre-stored registration password, and the identity verification operation will be passed if the two match. Of course, this step can also compare other information of the user, such as name, birthday, etc., which will not be repeated here.

As shown in Figure 2b, the command confirmation operation S50 performed by the computing device includes, step S500: the computing device extracts a pending command data contained in the second voice message through the voice recognition model, and step S501: compares the pending command data with the command A plurality of execution order data in the database, step S502: determine an execution order data corresponding to the pending order data, and step S503: transmit the execution order data to the automatic teller machine to execute related services. example For example, in step S500, the automatic teller machine can first send a message to the user: "Please tell us about the business you want to perform, including deposit, withdrawal, transfer...", wherein the business options can be included in the figure In the instruction database 33 of 1c, the user tells the voice receiving device about the business content to be executed (that is, the second voice message), and the voice receiving device transmits the sound wave signal to the memory for analysis by the computing device. In this case, the computing device can actively use the phoneme model containing relevant service content to analyze the sound wave signal to obtain relevant service options (ie pending command data). For example, in step S501, the computing device will combine the pending instruction data (such as "transfer") with the executed instruction data (such as "withdrawal", "transfer", "deposit", etc.) stored in the command database in advance The comparison is performed so that an execution instruction data (in this example, "transfer") can be determined in step S502, and the execution instruction data is sent to the automatic teller machine to execute related services.

Specifically, the user can describe the service item of "transfer", and the computing device can judge the execution instruction data as "transfer" and allow the automatic teller machine to provide the service. In other embodiments, the memory may further include a natural language processing model for the computing device to consider and use in a specific situation. For example, when the business item described by the user is "I want to receive money", the computing device can first capture the keyword "money" through the natural language model and reduce the weight of the less relevant "I want" to further understand "Receive money" is synonymous with the "withdrawal" command in the command database to avoid the situation that "I want to get money" cannot be corresponding to the "withdrawal" command.

It should be noted that, in this example, the execution of related services described in step S503 can be understood as the execution of transfer-related services, including requesting the transfer account number and amount from the user through the automatic teller machine, that is, the user will again submit the The voice receiving device sends out another second voice message, allowing the computing device to retrieve and analyze further data. In addition, step S503 is Optionally, for example, when the transaction is completed, the computing device may directly send the transaction record to the cloud server without sending the execution instruction data to the automatic teller machine.

Please refer to FIG. 3 . FIG. 3 is another operation flowchart of the identity verification performed by the artificial intelligence voice-activated banking transaction system according to an embodiment of the present invention. As shown in Figure 3, in the operation of identity verification (S60), when the computing device extracts a pending identity data contained in the first voice message through the voice recognition model (step S600), the computing device uses the automatic teller machine to The user sends an identity prompt message, and receives an identity confirmation message from the user through the voice receiving device (step S601). For example, when the user tells that the account number is "abc123", the automatic teller machine can respond to the identity prompt message of "abc123", allowing the user to confirm whether the voice message received by the system in this case is correct and respond with a "yes" or "no" (i.e. identity verification message). Then in step S602: the computing device determines whether the identity confirmation message is a positive message or a negative message. For example, when the automatic teller machine responds to the identity prompt message of "abc723", the user can respond with "No" (that is, a negative message), so that the system must re-execute the above identity verification operation to obtain another first voice message. The so-called re-execution of the identity verification operation means that the user needs to retell the first voice message with the identity data. Specifically, when the computing device determines that the identity confirmation message is a negative message, it sends a request through the automatic teller machine to request the user to provide another first voice message to update the pending identity information, and then returns to step S600. On the other hand, if the identity confirmation message is a positive message, the computing device maintains the pending identity data and executes step S603: the computing device compares the pending identity data with the registered identity data to determine that the pending identity data has passed the identity verification operation, and step S604: The computing device performs an instruction confirmation operation for the user. These two steps are the same as the above-mentioned step S401 and step S402, and will not be repeated here. Specifically, when the computing device determines that pending identity data is When the recorded identity data do not match and it is judged that the pending identity data has not passed the identity verification, the computing device may then wait for a new first voice message to be input or require the user to input a new first voice message through the ATM.

Please refer to FIG. 4 . FIG. 4 is another operation flow chart of an artificial intelligence voice-activated banking transaction system performing operation confirmation according to an embodiment of the present invention. As shown in Figure 4, in the operation of order confirmation (S70), when the computing device judges the execution command data corresponding to the pending command data (step S700), the computing device can send an instruction prompt message to the user through the automatic teller machine, And by receiving an instruction confirmation message from the user from the voice receiving device (step S701). For example, when the user says "I want two thousand yuan", the automatic teller machine can issue an instruction prompt message of "Do you want to withdraw money?", and the user can reply the instruction confirmation message of "Yes". For the method of how to correspond from "receiving two thousand yuan" to "withdrawing money", you can refer to the description of the above-mentioned direct dialogue model or natural language model, and will not go into details here. Then in step S702, the computing device judges that the instruction confirmation message is a positive message or a negative message, and if it is a positive message, the computing device can transmit the execution command data to the automatic teller machine to execute related services (step S703). Or, when the command confirmation message is a negative message, the command confirmation operation can be re-executed to obtain another execution command data. That is to say, when the computing device judges that the command confirmation message is an unapproved message, the computing device can send a request through the automatic teller machine to request the user to provide another second voice message to update the pending command data. For example: "Do you want to withdraw money?" (command prompt message), "No" (command confirmation message), "What kind of business do you want to do?" (Re-request the second voice message), "Transfer" (update Pending order information), "Do you want to transfer money?" (order prompt message), "Yes" (order confirmation message).

The identity verification in the variant embodiment of the system of this case may further include the image recognition function. Please refer to Fig. 5a to Fig. 5c, Fig. 5a is a block diagram of an artificial intelligence voice-activated bank transaction system according to another embodiment of this creation, and Fig. 5b is a block diagram of an artificial intelligence voice-activated bank according to another embodiment of this creation A block diagram of the usage scenario of the transaction system, FIG. 5c is a schematic block diagram of receiving voice messages and facial image data by the memory of the artificial intelligence voice-activated banking transaction system according to another embodiment of the present invention.

As shown in Figures 5a to 5c, the artificial intelligence voice-activated banking transaction system 1' includes not only the automatic teller machine 10, the computing device 20, the memory 30', and the voice receiving device 40, but also includes an image capture device 50 connected to the memory 30'. As shown in FIG. 5 b , the image capture device 50 can be, for example, a camera installed on the automatic teller machine 10 for capturing a face image data of the user C. As shown in FIG. As shown in FIG. 5c, the memory 30' further stores a facial feature detection model 34 and a registered facial feature 35 of the user in advance.

Please refer to FIG. 6 . FIG. 6 is an operation flowchart of face recognition for identity verification in an artificial intelligence voice-activated banking transaction system according to another embodiment of the present invention. As shown in FIG. 6, the identity verification operation performed by the computing device further includes a facial recognition operation, including step S900: using the facial feature detection model to extract a pending facial feature contained in the facial image data, Step S901: Compare the pending facial feature with the registered facial feature. Step S902: Determine whether the pending facial feature matches the registered facial feature. If the pending facial feature matches the registered facial feature, proceed to step S901. S903: the computing device executes other identity verification operations or the instruction confirmation operation, and if the pending facial features do not match the registered facial features, the computing device executes the identity verification operation again.

For example, after the image capture device captures the user's face image, it can transmit the image data to the memory, and the computing device can use the facial feature detection model to extract the features of the image data, wherein the face The internal feature detection model can be a neural network with deep learning capabilities (such as VGG-Face, Google FaceNet, OpenFace, etc.). Taking Google FaceNet as an example, instead of outputting classification results at the beginning, it outputs quantized feature values first. This operation can extract facial features such as contours into undetermined facial features, and then in the feature vector space Compare different facial photos to determine the similarity of different faces. In other words, the closer the two points in the feature vector space, the higher the similarity of the faces. In addition, the registered facial features stored in the memory are associated with the above-mentioned registered identity data. Specifically, after the user performs the identity data comparison as shown in step S401 of FIG. 2a, the identity data will correspond to a login face. internal features for comparison. In terms of comparing and judging facial features, the accuracy of recognition can be increased by capturing multiple images of the user, which will not be described here. It should be noted that when the computing device judges that the pending facial features do not match the registered facial features, it means that the user's identity information may be incorrect, and the identity verification operation needs to be performed again, so the above-mentioned facial recognition operation will be performed again. FIG. 6 does not show all identity verification operations, so the negative arrow in step S902 is indicated by pointing to step S900 , and this case is not limited thereto.

Please refer to FIG. 7 . FIG. 7 is a schematic block diagram of another memory receiving messages and data of an artificial intelligence voice-activated banking transaction system according to another embodiment of the present invention. As shown in Figure 7, the memory 30" stores a lip shape recognition model 36 (such as LipNet) in advance, and the computing device is further used to capture multiple lip images of the user through the image capture device 50 to obtain a lip shape recognition model 36 (such as LipNet). Dynamic lip shape data, and the instruction confirmation operation performed by the computing device 20 further includes a lip shape recognition operation.

Please refer to FIG. 8 . FIG. 8 is a flow chart of an operation of the artificial intelligence voice-activated banking transaction system performing lip recognition for order confirmation according to another embodiment of the present invention. As shown in FIG. 8 , the lip shape recognition operation S110 performed by the computing device includes step S1100: using the lip shape recognition model to extract a reference command data included in the dynamic lip shape data, step S1101: judging the pending command data and the reference command data Whether they are the same, and step S1102: keep the pending order data. In step S1101, if it is determined that the pending instruction data is the same as the reference instruction data, proceed to step S1102, if it is judged that the pending instruction data is different from the reference instruction data, it means that the pending instruction data obtained by the speech recognition model and the reference instruction obtained by the lip shape recognition model If the data is different, you can redo the above command confirmation operation. It should be noted that this figure does not show all the command confirmation operations, so the negative arrow indicating "re-perform the command confirmation operation" points to step S1100 (meaning that when the command confirmation operation is performed again, the lip shape recognition operation can also be performed again) , this case is not limited to this. Specifically, the principle of the lip shape recognition model is similar to the above-mentioned speech recognition model, which can decompose spoken language into lip shape elements corresponding to different pronunciations, and store them as a sequence for analysis by the computing device, which will not be described in detail here. It should be noted that the image capture device used in the foregoing embodiments may only have the function of shooting images, but in this embodiment, the image capture device must have the function of recording continuous videos or shooting high-speed continuous images to achieve lip shape identify.

Please refer to FIG. 9 . FIG. 9 is a block diagram of a usage scenario of an artificial intelligence voice-activated banking transaction system according to other embodiments of the present invention. As shown in FIG. 9 , the voice receiving device 40 can be a mobile device (such as a smart phone) of the user C, and the voice receiving device 40 can be further connected to the computing device 20 . In this example, the mobile phone of user C can be connected to the computing device 20 and the memory 30. Specifically, the mobile phone can be connected to the automatic teller machine 10, and then connected to The computing device 20 and the memory 30 are not limited in this case. User C can tell the personal information and the banking business to be performed to the mobile phone, making it difficult for others around to hear the private information. In the same way, the system can send a reminder message to user C through the mobile phone without being heard by the people around. In addition, the mobile phone can also be used to receive an encrypted prompt message from the system and convert the prompt message into a prompt tone and play it to the user, thereby increasing information security.

Please refer to FIG. 10 . FIG. 10 is a schematic block diagram of receiving messages and data from other memories of the artificial intelligence voice-activated banking transaction system shown in other embodiments of the present invention. As shown in FIG. 10 , the memory 30''' further stores a first trigger message 37 and a second trigger message 38 in advance, and is further used to receive a third voice message from the voice receiving device.

Please refer to FIG. 11 in conjunction with FIG. 10 . FIG. 11 is a block flow diagram of the artificial intelligence voice-activated banking transaction system according to other embodiments of the present invention when it is triggered. As shown in Figure 11, when the computing device receives a third voice message from the user through the voice receiving device, it can determine whether the third voice message matches the first trigger message or the second trigger message, if the third voice message matches the first trigger message Once the trigger message is received, the above identity verification operation is re-executed, and if the third voice message matches the second trigger message, the instruction confirmation operation is re-executed; otherwise, no additional operation is performed. Specifically, if a user finds that he/she wants to operate another account after completing the identity verification message, he/she can send a third voice message that matches the first trigger message to the voice receiving device (such as "re-authenticate "). Similarly, if a user says that he/she wants to transfer money and finds that he/she actually wants to withdraw money, he/she can send a third voice message (such as "re-transaction") that meets the second trigger message to the voice receiving device. Of course, as long as the user avoids talking about the first trigger message or the second trigger message during the process, the system will not be triggered by the third voice message and interrupt the transaction.

According to the disclosure of this article, a user situation described below can be achieved. It should be noted that this situation is only an example, and this case is not limited thereto. After the customer goes to the ATM, inserts the financial card according to the instructions or clicks the card-not-present transaction function, the ATM will play a voice instructing the customer to approach the microphone within a specified time, and tell the identity verification questions, such as birthday, phone number, account number, password and other personal information. The microphone receives the voice of the customer, filters the noise through noise reduction technology, and transmits it to the system of this case to determine the content of the customer's voice. The system determines that the identity verification is passed, and the voice will be played on the ATM to instruct the customer to approach the microphone within the specified time, and describe the transaction items (deposit/withdrawal/transfer) and transaction content (account number/amount). , return to the identity verification steps above. The microphone receives the customer's voice, and the system recognizes the customer's transaction content, and plays the voice again on the ATM to instruct the customer to approach the microphone within a specified time and reply to the transaction confirmation/modification/cancellation order. The system receives the customer's confirmation instruction and executes the transaction at the ATM. If the system receives the customer's modification instruction, it returns to the above corresponding process. If the system receives the customer's cancellation or the system transaction times out, it returns to the initial process. After the customer completes the transaction, the system sends the retained receipt by email and SMS.

With the above structure, the artificial intelligence voice-activated banking transaction system disclosed in this case can judge the content of the received voice message through the memory with the artificial intelligence recognition model and the computing device, so as to safely and effectively perform identity verification and command control function. Let users only need to tell their identity information in front of the ATM to complete the verification, and then verbally express the banking service items they want to perform. In this way, general banking services can be completed completely through voice control, and it is suitable for various ethnic groups. It is said that it is a convenient measure.

Although the invention is disclosed as above with the aforementioned embodiments, it is not intended to limit the invention. Without departing from the spirit and scope of this creation, all changes and modifications are The scope of patent protection for this creation. For the scope of protection defined by this creation, please refer to the attached scope of patent application.

1: Artificial intelligence voice-activated bank transaction system

10: Automatic teller machine

20: computing device

30: memory

40: Voice receiving device

Claims (10)

An artificial intelligence voice-activated bank transaction system, comprising: an automatic teller machine for allowing a user to handle bank counter services by himself; a computing device connected to the automatic teller machine for performing an identity verification operation and an instruction on the user confirming the operation; a memory connected to the computing device for storing a first voice message and a second voice message, and storing a voice recognition model, a registered identity data of the user and an instruction database in advance; and a voice receiving device connected to the memory for receiving the first voice message and the second voice message of the user and transmitting them to the memory, wherein the identity verification operation performed by the computing device includes: by extracting a pending identity data contained in the first voice message from the voice recognition model; and comparing the pending identity data with the registered identity data and confirming that the pending identity data conforms to the registered identity data, and the computing device executes The command confirmation operation includes: using the voice recognition model to extract a pending command data contained in the second voice message; and comparing the pending command data with a plurality of execution command data in the command database to determine the same An execution order data corresponding to the pending order data. The artificial intelligence voice-activated banking transaction system as described in claim 1, wherein the identity verification operation performed by the computing device further includes: When the computing device retrieves the pending identity data contained in the first voice message through the speech recognition model, it executes: sending an identity reminder message to the user through the automatic teller machine; The device receives an identity confirmation message from the user, and determines whether the identity confirmation message is a positive message or a negative message; if the identity confirmation message is the positive message, the computing device maintains the pending identity data; and if the identity The confirmation message is the negative message, and the computing device sends a request through the automatic teller machine to request the user to provide another first voice message to update the pending identity information. The artificial intelligence voice-activated banking transaction system as described in claim 1, wherein the instruction confirmation operation performed by the computing device further includes: when the computing device determines that the pending instruction data corresponds to an execution instruction data, execute: through the automatic teller machine Sending an instruction prompt message to the user; receiving an instruction confirmation message from the user from the voice receiving device, and judging whether the instruction confirmation message is an approval message or a non-agreement message; if the instruction confirmation message is the If the confirmation message of the instruction is the non-consent message, the computing device sends a request through the ATM to request the user to provide another second Voice message to update the pending order data. The artificial intelligence voice-activated banking transaction system as described in claim 1, wherein the instruction confirmation operation performed by the computing device further includes: when the computing device judges an execution instruction data corresponding to the pending instruction data, execute: the execution instruction The data is sent to the ATM to perform related services. The artificial intelligence voice-activated banking transaction system as described in claim 1 further includes an image capture device connected to the memory for capturing a facial image data of the user, and the memory further stores a A facial feature detection model and a registered facial feature of the user, and the registered facial feature is associated with the registered identity data, wherein the identity verification operation performed by the computing device further includes a facial recognition operation, including : Use the facial feature detection model to extract a pending facial feature contained in the facial image data; compare the pending facial feature with the registered facial feature to determine whether the pending facial feature matches the Registered facial features; if the pending facial features match the registered facial features, the computing device performs other identity verification operations or the command confirmation operation; if the pending facial features do not match the registered facial features, the computing device through The automatic teller machine sends a request to require the user to provide another first voice message to update the pending identity information and the registered identity information. The artificial intelligence voice-activated banking transaction system as described in claim 5, wherein the memory further stores a lip shape recognition model, and the computing device is further used to use the image capture device The device captures a plurality of lip images of the user to obtain a dynamic lip shape data, and the command confirmation operation performed by the computing device further includes a lip shape recognition operation, including: using the lip shape recognition model to capture the A reference command data included in the dynamic lip shape data; judging whether the pending command data is the same as the reference command data; if the pending command data is the same as the reference command data, retaining the pending command data; and if the pending command data is the same as the reference command data The reference command data is different, and the computing device sends a request through the automatic teller machine to request the user to provide another second voice message to update the pending command data. The artificial intelligence voice-activated banking transaction system as described in Claim 1, wherein the voice receiving device is a mobile device or an earphone device of the user. The artificial intelligence voice-activated banking transaction system as described in claim 1 further includes a mobile device of the user connected to the automatic teller machine for receiving an encrypted prompt message and converting the prompt message into a prompt tone for playback to the user. The artificial intelligence voice-activated banking transaction system as described in claim 1, wherein the memory further stores a first trigger message and a second trigger message, so that when the computing device receives a first trigger message from the user through the voice receiving device When there are three voice messages, judge whether the third voice message matches the first trigger message or the second trigger message, if the third voice message matches the first trigger message, re-execute the identity verification operation, if the third If the voice message matches the second trigger message, re-execute the instruction confirmation operation; otherwise, no additional operation is performed. The artificial intelligence voice-activated banking transaction system as described in Claim 1, wherein the voice receiving device has a filter for filtering noises in the first voice message and the second voice message.

Images