TWM606215U - Bank counter system based on artificial intelligence - Google Patents

Abstract

A bank counter system based on artificial intelligence includes a voice recognition device, a processing device and a business machine. The voice recognition device obtains voiceprint characteristics, transaction item information, and transaction parameter information based on at least one voice input. The processing device is connected to the voice recognition device, determines that the voiceprint feature matches the pre-stored identity information, determines the form format based on the transaction item information, and generates a form file based on the form format, pre-stored identity information and transaction parameter information. The business machine is connected to the processing device to receive and print form files.

Description

Bank counter system based on artificial intelligence

This creation is about a bank counter system, especially a bank counter system based on artificial intelligence.

Under the current banking operation mode, customers are usually required to manually fill in the transaction form, and then submit it to the counter clerk. The counter clerk enters the transaction information such as the transaction items and amount filled in the form. Such a bank counter transaction service not only takes a long time to work, but it is even difficult to avoid login errors during the input process of the clerk, resulting in incorrect transaction information being input to the back-end system.

In view of the above, this creation provides a bank counter system based on artificial intelligence.

The bank counter system based on artificial intelligence according to an embodiment of this creation includes a voice recognition device, a processing device and a business machine. The voice recognition device obtains voiceprint characteristics, transaction item information, and transaction parameter information based on at least one voice input. The processing device is connected to the voice recognition device, determines that the voiceprint feature matches the pre-stored identity information, determines the form format based on the transaction item information, and generates a form file based on the form format, pre-stored identity information and transaction parameter information. The business machine is connected to the processing device to receive and print form files.

With the above structure, the bank counter system based on artificial intelligence disclosed in this case can link the printing operation through the voice recognition mechanism, replacing the traditional way of filling out the form manually, saving customers time, reducing the error rate of clerk login and improving service efficiency effect.

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

The detailed features and advantages of this creation will be described in detail in the following implementations. The content is sufficient to enable anyone familiar with relevant skills to understand the technical content of this creation and implement it accordingly, and in accordance with the content disclosed in this specification, the scope of patent application and the drawings. , Anyone who is familiar with relevant skills can easily understand the purpose and advantages of this creation. The following examples further illustrate the viewpoint of this creation in detail, but do not limit the scope of this creation by any viewpoint.

Please refer to FIG. 1, which is a functional block diagram of a bank counter system based on artificial intelligence drawn according to an embodiment of the present creation. As shown in FIG. 1, the bank counter system 1 based on artificial intelligence includes a voice recognition device 11, a processing device 13, and a business machine 15. The processing device 13 can be connected to the voice recognition device 11 and the business machine 15 in a wireless or wired manner. The voice recognition device 11 can obtain the user's voiceprint characteristics, transaction item information, and transaction parameter information based on at least one voice input of the user (for example, a customer who wants to perform a financial transaction). Among them, the user’s voiceprint features represent the user’s identity, which can be used in subsequent identification procedures; transaction information includes the financial transaction that the user wants to conduct, such as loans, remittances, deposits, withdrawals, etc.; transaction parameter information is It may include the amount corresponding to the financial transaction item that the user wants to perform, such as 2,000 yuan, 100,000 yuan, etc., and the transaction parameter information may also include the object of the financial transaction item that the user wants to perform, such as a remittance account.

Furthermore, the voice recognition device 11 may include a voice input interface 111, a vocabulary database 113, and a processor 115. The voice input interface 111 is, for example, a microphone such as a microphone for receiving voice input to be recognized. The so-called voice input is, for example, a voice signal emitted by a user. The vocabulary database 113 at least stores a plurality of pre-stored transaction item vocabularies and a plurality of pre-stored number of vocabularies. Furthermore, the vocabulary database 113 can store a plurality of pre-stored target vocabularies. The vocabulary database 113 may be composed of one or more non-volatile storage media such as flash memory, read-only memory, magnetic memory, and so on. For example, the above-mentioned pre-stored transaction item vocabulary and pre-stored number vocabulary can be respectively stored in two independent non-volatile storage media. For another example, the above-mentioned pre-stored transaction item vocabulary and pre-stored number vocabulary can be stored in different sectors in the same non-volatile storage medium, or in different storage blocks defined by computer programs. The vocabulary database 113 may be a memory (such as a cloud drive) that is remote from the voice input interface 111 and the processor 115, or it may be located on one or both of the voice input interface 111 and the processor 115 The memory in the same case. The processor 115 is, for example, a central processing unit, a microcontroller, a programmable logic controller, etc., and can be connected to the voice input interface 111 and the vocabulary database 113 in a wireless or wired manner. The processor 115 of the voice recognition device 11 can perform voiceprint extraction and voice recognition on the voice input received by the voice input interface 111 to obtain voiceprint characteristics, transaction item information and transaction parameter information from the voice input, and obtain the information It is sent to the processing device 13, and the detailed identification process will be described later. In addition, in addition to the above-mentioned components, the voice recognition device 11 may further include an output interface (such as a speaker, a screen, etc.) for outputting a voice input request through sound or screen display.

The processing device 13 is, for example, a computer host, which can transmit signals to and from the voice recognition device 11 in a wireless or wired manner. The processing device 13 may determine the form format according to the transaction item information obtained by the voice recognition device 11 when determining that the voiceprint features obtained by the voice recognition device 11 match the pre-stored identity information, and according to the determined form format and pre-stored identity information And transaction parameter information to generate a form file. Furthermore, the processing device 13 may include a voiceprint database and a form format database. The voiceprint database stores multiple pre-stored identity information and the corresponding voiceprint features of each pre-stored identity information. For example, the voiceprint database can store the names of multiple users as the pre-stored identity information and the voiceprints of those users Features, and the correspondence between each user’s name and voiceprint features. Among them, the voiceprint feature is, for example, the waveform feature of the user's voice signal, including multiple of formant frequency bandwidth, pitch contour, syllable duration, long-term average power spectrum parameter, and long-term average tone parameter. The form format database can store a variety of form formats, each of which corresponds to a different financial transaction item. For example, the internal memory of the processing device 13 can store form formats suitable for loans, remittances, deposits, and withdrawals, respectively. The voiceprint database and the form format database can be composed of one or more non-volatile storage media, such as flash memory, read-only memory, magnetic memory, etc. For example, the voiceprint database and the form database are two non-volatile storage media respectively. For another example, the voiceprint database and the form-format database are respectively different sectors in the same non-volatile storage medium, or different storage blocks defined by computer programs.

The processing device 13 may further include one or more internal processors (for example, a central processing unit, a microcontroller, a programmable logic controller, etc.), which processes two programs of voiceprint recognition and form format determination. The processing device 13 may first execute the voiceprint recognition process to determine whether the voiceprint features obtained by the voice recognition device 11 conform to the pre-stored identity information, and execute the form format determination process when determining compliance. Furthermore, the internal processor of the processing device 13 can compare the voiceprint features obtained by the voice recognition device 11 with the voiceprint features pre-stored in the voiceprint database. When the internal processor can search from the voiceprint database When the matching voiceprint feature is reached, it is determined that the voiceprint feature has matching pre-stored identity information, and then the form format determination process is executed. In particular, as mentioned above, the voiceprint feature may include multiple parameters, and when the processing device 13 determines that the captured voiceprint feature is more than 80% identical to the voiceprint feature in a pre-stored identity information, it is determined The voiceprint feature matches the pre-stored identity information. The form format determination process includes selecting the form format corresponding to the financial transaction item contained in the transaction item information obtained by the voice recognition device 11 from a variety of form formats in the form format database, and pre-stored identity information (such as user name) and Fill in the text corresponding to the transaction parameter information (such as amount, transaction object) into the document with the form format, and then use this document as a form file, or use it as a form file after format conversion.

The MFP 15 is, for example, a multifunction MFP, which can be connected to the processing device 13 in a wireless or wired manner to receive form files from the processing device 13 and print out the form files. Furthermore, the processing device 13 will then send the form file to the MFP 15 after generating the form file, and will also send a printing command so that the MFP 15 will perform the printing operation after receiving the form file. In particular, the document printed by the MFP 15 includes the form corresponding to the form format and the text corresponding to the pre-stored identity information and transaction parameter information. In one embodiment, in addition to the above operations, the MFP 15 can also perform scanning according to a new command, wherein the new command can be triggered by the user through a button of the MFP 15. For an implementation scenario, when there is a new form format, the bank clerk can press the newly added button on the MFP 15 to scan the document with the new form format to generate a new form format scan file. In this embodiment, the processing device 13 has an optical character recognition function, and the processing device 13 can perform optical character recognition on the scanned file of the new form format, and use the result of the optical character recognition as a new financial transaction item , And use the scanned file of the new form format as the newly added form format, and store the two and the corresponding relationship between the two in the form format database.

In addition to the above-mentioned devices, the bank counter system mentioned in this case may further include other optional devices. Please refer to FIG. 2, which is a functional block diagram of a bank counter system based on artificial intelligence according to another embodiment of the present creation. As shown in FIG. 2, the bank counter system 1'includes a voice recognition device 11, a processing device 13, a business machine 15, a verification information acquisition device 17, and a display device 19. Among them, the connection relationship and cooperative operation of the recognition device 11, the processing device 13 and the MFP 15 are the same as those of the voice recognition device 11, the processing device 13 and the MFP 15 in the previous embodiment of FIG. 1, and will not be repeated here. .

The verification information acquisition device 17 is an optional device and can be connected to the processing device 13 in a wireless or wired manner. The verification information capture device 17 is, for example, a signature pad with a speaker or a screen or a biometric (fingerprint, iris, etc.) capture device, which can be controlled by the processing device 13 to output verification requests to the outside (for example, users) and capture Verification information (such as signatures, biometrics, etc.). In addition to the operation described in the embodiment in FIG. 1, the processing device 13 can also store a list of high-risk types, recording one or more high-risk transaction information (such as loans) or transaction parameter information (such as more than 1 million Amount or unknown transaction partner). In addition, in addition to storing the voiceprint characteristics, the processing device 13 may also store the respective signatures, biometrics or other verification information corresponding to multiple pre-stored identity information and the correspondence between the pre-stored identity information and the verification information.

The processing device 13 can determine whether the transaction item information or transaction parameter information belongs to the high-risk type before generating the form file, and when the determination result is yes, the processing device 13 controls the verification information capture device 17 to display by voice or screen The verification request is output to the user. When the verification information capture device 17 retrieves the verification information provided by the user and returns it, it determines whether the verification information conforms to the pre-stored identity information, and generates the form when the judgment result is yes file. Thereby, the bank counter system 1'can improve the accuracy of identity verification and the security of the system through the multi-stage identity verification process of voiceprint recognition and verification information confirmation.

In another embodiment, in addition to being connected to the processing device 13, the verification information capturing device 17 is also connected to the MFP 15 in a wireless or wired manner. In this embodiment, after the form file is generated and before the form file is sent to the MFP 15, the processing device 13 can control the verification information capture device 17 to output verification requests to the user through voice or screen display, and the information to be verified When the retrieval device 17 retrieves the information to be verified provided by the user and returns it, it determines whether the information to be verified matches the pre-stored identity information, and only sends the form file to the office machine 15 when the judgment result is yes. In this way, in addition to improving the accuracy of identity verification and the security of the system through the multi-stage identity verification process, the bank counter system 1'can first transmit confidential documents (that is, the aforementioned form files) from one device to another. The necessity of confirming the transmission can reduce unnecessary transmissions and reduce the risk of robbery in the transmission process compared with the identity verification procedure that is executed after the standby secret file is output.

The display device 19 is also an optional device, which can be connected to the voice recognition device 11 in a wireless or wired manner. The display device 19 is, for example, a liquid crystal display, which is used to display one or more of the voiceprint feature, transaction item information, and transaction parameter information obtained by the voice recognition device 11. In this embodiment, in addition to the operation described in the embodiment in FIG. 1, the voice recognition device 11 can also display voiceprint characteristics, transaction item information, and transaction parameter information through the display device 19, and will sound after receiving a confirmation command. The pattern characteristics, transaction item information, and transaction parameter information are sent to the processing device 13. The confirmation instruction is, for example, a voice input indicating confirmation, and may originate from the user. Alternatively, the voice recognition device 11 may include other input interfaces such as a touch screen, buttons, etc., to receive a user's touch or pressing action and treat it as a confirmation command. Through the setting and operation of the display device 19, the accuracy of identity verification can be improved. In addition, the confirmation command can also be used as a reference basis for calibrating the internal algorithm of the voice recognition device 11, thereby increasing the accuracy of voice recognition.

Please refer to FIGS. 1 to 3 together. FIG. 3 is a flowchart of the operation method of the bank counter system according to an embodiment of the invention. The operation method shown in FIG. 3 is applicable to the bank counter systems 1 and 1'described in the foregoing embodiments in FIGS. 1 and 2. In step S1, the bank counter system 1 or 1'uses the voice recognition device 11 to obtain voiceprint characteristics, transaction item information, and transaction parameter information based on at least one voice input of a user (for example, a customer who wants to perform a financial transaction). In step S3, the bank counter system 1 or 1'uses the processing device 13 to determine that the voiceprint feature matches the pre-stored identity information, determines the form format based on the transaction item information, and generates a form file based on the form format, pre-stored identity information and transaction parameter information . In step S5, the bank counter system 1 or 1'uses the MFP 15 to receive and print the form file from the processing device 13 for the user to confirm. After confirming the information on the document printed based on the form file, the user can sign and seal the document, and hand the document to the bank clerk for transaction. With the above operation method, the customer only needs to confirm the transaction information on the form and then sign and seal, no need to write the form, which can improve convenience and save transaction time, and the staff does not need to choose which form to use, and the system automatically determines the transaction item After printing, it can reduce the error rate of crew login and improve work efficiency.

In particular, in one embodiment, after the voice recognition device 11 transmits the acquired voiceprint characteristics, transaction item information, and transaction parameter information to the processing device 13, the voice input, voiceprint characteristics, and transaction item information are deleted. And transaction parameter information, and the MFP 15 will also delete the form file after printing. In this way, the bank counter system 1 or 1'can reduce confidential data (such as the aforementioned voice input, voiceprint characteristics, transaction item information and transaction parameter information records) stored in the peripheral devices of the system (such as the aforementioned voice recognition device 11 and 15) time of the business machine, thereby reducing the risk of theft of confidential information and enhancing the security of the system.

The detailed execution content of the above step S3 is the same as the operation of the processing device 13 described in the previous embodiment, and the detailed execution content of the step S5 is also the same as the operation of the MFP 15 described in the previous embodiment, which will not be repeated here. The step S1 is further explained, that is, the step performed by the voice recognition device 11 to obtain voiceprint characteristics, transaction item information, and transaction parameter information based on at least one voice input. The voice input may be a user's voice signal, and the voice recognition device 11 may capture the waveform characteristics of the voice signal, such as formant frequency bandwidth, pitch contour, syllable duration, long-term average power spectrum parameter, and long-term average tone parameter Many of them are used as voiceprint features. In particular, the voice recognition device 11 can perform voiceprint feature extraction for each received voice input.

As for the acquisition of transaction item information and transaction parameter information, please refer to FIGS. 1 to 4, where FIG. 4 is a flowchart of voice recognition in a bank counter system operating method according to an embodiment of the invention. In step S11, the processor 115 of the voice recognition device 11 uses the voice signal received from the voice input interface 111 as a voice input to be recognized, and uses the voice input to be recognized as the execution target of the subsequent recognition process. In step S13, the processor 115 of the voice recognition device 11 executes an identification procedure on the execution object. The identification procedure includes judging whether the execution object contains the target transaction item vocabulary and the target number vocabulary, wherein the target transaction item vocabulary is a vocabulary database One of a plurality of pre-stored transaction item vocabulary, and the target number vocabulary is one of a plurality of pre-stored number vocabulary in the vocabulary database. Furthermore, the processor 115 converts the voice signal input as the voice input to be recognized into a pinyin string, uses multiple pre-stored transaction vocabularies in the vocabulary database as a judgment target one by one, and judges whether the pinyin string has a judgment target, When the judgment result is yes, the current judgment target is used as the target trading item vocabulary. The judgment of the target number vocabulary is similar to the judgment of the target transaction item vocabulary mentioned above, so it will not be repeated here.

When the processor 115 determines that the execution object includes the target transaction item vocabulary and the target number vocabulary, it will use the target transaction item vocabulary as the transaction item information and the target number vocabulary as the transaction parameter information (step S15), and complete the transaction item information and transaction parameters Information acquisition. Conversely, when the processor 115 determines that the execution object does not include one or both of the target transaction item vocabulary and the target number vocabulary, it will output a voice input request to receive another voice input to be recognized, and transfer the other voice to be recognized Input and the previously determined voice input to be recognized as the execution target (step S17), and then execute the aforementioned recognition procedure (step S13). And so on, until the transaction item information and transaction parameter information are obtained from all the voice inputs to be recognized.

Further explain the content of the voice input requirements. In one embodiment, when the voice recognition device 11 determines that the execution object does not include the target transaction item vocabulary, the voice recognition device 11 will generate a voice input request including the keyword corresponding to the transaction item information; and when the execution object does not include the target number When using vocabulary, the voice recognition device 11 generates a voice input request containing keywords corresponding to transaction parameter information. For example, when the execution object includes the target transaction item vocabulary of "loan" but does not include the target number vocabulary, the content of the voice input request can include "please enter the desired transaction amount". For another example, when the execution object contains the target number vocabulary of "1 million" but does not include the target transaction item vocabulary, the content of the voice input request can include "Please enter the item to be traded". The above-mentioned voice input request can be output in the form of sound or screen display through the output interface of the voice recognition device 11 such as a speaker or a screen.

In another embodiment, the internal memory of the processing device 13 stores common transaction items and common numbers corresponding to each pre-stored identity information, wherein the common transaction items are the vocabulary of multiple pre-stored transaction items in the voice recognition device 11 At least one of, and the common number is at least one of a plurality of pre-stored vocabularies in the speech recognition device 11. When the voice recognition device 11 determines that the execution object does not contain the vocabulary of the target transaction item, the voice recognition device 11 may first provide the acquired voiceprint feature to the processing device 13 to determine the pre-stored identity information corresponding to the voiceprint feature, and the processing device 13 then pre-stores according to The identity information selects its corresponding common transaction item to generate a voice input request, and sends it back to the voice recognition device 11 for output; when the voice recognition device 11 determines that the execution object does not contain the target number of words, the voice recognition device 11 can first obtain The voiceprint feature is provided to the processing device 13 to determine the pre-stored identity information corresponding to the voiceprint feature. The processing device 13 then selects the corresponding common number according to the pre-stored identity information to generate a voice input request, and sends it back to the voice recognition device 11 for Output. For example, the processing device 13 can store a user’s common numbers as "1000 yuan" and "2000 yuan" according to the previous usage record. When the voice recognition device 11 determines that the execution object contains the target transaction vocabulary of "withdrawal" but not When the target number vocabulary is included and the processing device 13 determines that the voiceprint recognition belongs to the above-mentioned user, the processing device 13 can generate a voice input request including "1000 yuan" and "2000 yuan", and the voice recognition device 11 can display voice or screen Output the options of "1000 yuan" and "2000 yuan" in a way for users to choose. By generating voice input requests based on common transaction items and common numbers, the voice recognition device 11 can predict the content of the voice input to be recognized for the next input, thereby reducing the amount of calculation for the next recognition process and increasing the execution speed.

With the above structure, the bank counter system based on artificial intelligence disclosed in this case can link the printing operation through the voice recognition mechanism, replacing the traditional way of filling out the form manually, saving customers time, reducing the error rate of clerk login and improving service efficiency effect.

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

1. 1’: Bank counter system 11: Voice recognition device 111: Voice input interface 113: Vocabulary Database 115: processor 13: Processing device 15: Business Machine 17: Verify the information retrieval device 19: display device

FIG. 1 is a functional block diagram of a bank counter system based on artificial intelligence drawn according to an embodiment of the present creation. Fig. 2 is a functional block diagram of a bank counter system based on artificial intelligence drawn according to another embodiment of the invention. FIG. 3 is a flowchart of the operation method of the bank counter system according to an embodiment of the present creation. FIG. 4 is a flowchart of voice recognition in the operating method of the bank counter system according to an embodiment of the creation.

1: Bank counter system

11: Voice recognition device

111: Voice input interface

113: Vocabulary Database

115: processor

13: Processing device

15: Business Machine

Claims (9)

A bank counter system based on artificial intelligence includes: a voice recognition device for obtaining a voiceprint feature, transaction item information, and transaction parameter information based on at least one voice input; a processing device connected to the voice recognition device to determine the The voiceprint feature conforms to a pre-stored identity information, a form format is determined based on the transaction item information, and a form file is generated based on the form format, the pre-stored identity information, and the transaction parameter information; and a business machine connected to the processing device, Receive and print the form file. The bank counter system of claim 1, wherein the voice recognition device includes a vocabulary database, the vocabulary database stores a plurality of pre-stored transaction item vocabulary and a plurality of pre-stored number vocabulary, and the voice recognition device is executed based on the Obtaining the transaction item information and the transaction parameter information by at least one voice input includes: receiving a voice input to be recognized, executing a recognition process, and using the voice input to be recognized as an execution object of the recognition process, wherein the recognition process includes determining the Whether the execution object contains a target trading item vocabulary in the pre-stored trading item vocabulary and a target number vocabulary in the pre-stored number vocabulary; when the execution object does not contain the target trading item vocabulary or does not contain the target number vocabulary, Output a voice input request to receive another voice input to be recognized, use the voice input to be recognized and the other voice input to be recognized as the execution target and execute the recognition program; and when the execution target includes the target transaction item vocabulary and When the target number vocabulary is used, the target transaction item vocabulary is used as the transaction item information and the target number vocabulary is used as the transaction parameter information. The bank counter system according to claim 2, wherein when the execution object does not include the target transaction item vocabulary, the voice input request includes keywords corresponding to the transaction item information, and when the execution object does not include the target number For vocabulary, the voice input request contains keywords corresponding to the transaction parameter information. The bank counter system according to claim 2, wherein the processing device selects at least one of the pre-stored transaction item vocabulary according to the pre-stored identity information when the execution object does not contain the target transaction item vocabulary, and according to the The at least one of the pre-stored transaction item vocabulary generates the voice input request, and the processing device selects at least one of the pre-stored number vocabulary according to the pre-stored identity information when the execution object does not contain the target number vocabulary, and The voice input request is generated according to the at least one of the pre-stored number of words. The bank counter system according to claim 1, wherein the voice recognition device further deletes the voice input, the voiceprint feature, and the voiceprint feature after transmitting the voiceprint feature, the transaction item information, and the transaction parameter information to the processing device. The transaction item information and the transaction parameter information, and the MFP will delete the form file after printing. The bank counter system according to claim 1, wherein the MFP further performs scanning according to a new command and generates a new form format scan file, the processing device performs optical character recognition on the new form format scan file, and The result of the optical character recognition, the scanned file of the new form format and the corresponding relationship between the two are stored. The bank counter system of claim 1, further comprising a verification information acquisition device connected to the processing device, wherein the processing device determines that the transaction item information or the transaction parameter information is high before generating the form file For the risk type, control the verification information capturing device to output a verification request, receive a piece of information to be verified corresponding to the verification request, and generate the form file after judging that the information to be verified matches the pre-stored identity information. The bank counter system according to claim 1, further comprising a verification information acquisition device connected to the processing device and the transaction machine, wherein the processing device further controls the verification information acquisition device to output one after generating the form file The verification request receives a piece of information to be verified corresponding to the verification request, and sends the form file to the business machine after judging that the information to be verified matches the pre-stored identity information. The bank counter system of claim 1, further comprising a display device connected to the voice recognition device, wherein the voice recognition device further displays the acquired voiceprint feature, the transaction item information, and the transaction parameter through the display device Information, and after receiving a confirmation command, the voiceprint feature, the transaction item information, and the transaction parameter information are sent to the processing device.

Images