TW202030626A - Cross-channel artificial intelligence dialogue platform and operation method thereof - Google Patents

Abstract

A cross-channel artificial intelligence dialogue platform comprises three internal servers. The voice input interface of the first internal server receives the first voice signal. The private-data-hiding module deletes the personal data of the first voice signal to generate the second voice signal. The speech-to-text interface and the semantic recognition module of the first internal server respectively converts the second voice signal to the first text signal and obtaining the intent signal according to the first text signal. The dialogue module and the application module respectively generates the response signal and the control instruction according to the intent signal. The text-to-speech interface of the first internal server converts the response signal to the third voice signal. The output interface outputs the third voice signal and the control instruction.

Description

Cross-channel artificial intelligence dialogue platform and its operation method

The invention relates to a dialogue platform and an operation method of the dialogue platform, in particular to a cross-channel artificial intelligence dialogue platform and an operation method thereof.

With the popularization of various digital marketing channels, people who encounter any transaction problems often hope to get a reply as soon as possible.

However, for financial institutions that provide customer service, increasing the number of customer service staff will inevitably lead to a substantial increase in labor costs. In addition, it takes a certain amount of time to train an excellent customer service staff. When a large number of customers come in suddenly, the customer service staff who can calmly deal with various customer problems are often overwhelmed. The customer service staff who have recently arrived may not be able to meet the various customer needs. problem. Therefore, for financial institutions that are unable to provide good services, the public’s evaluation will drop significantly, which will affect the public’s trust in and willingness to participate in other projects of the financial institution.

In view of this, the present invention proposes a cross-channel artificial intelligence (AI) dialogue platform. The said channels include: digital channels, customer service centers and business units. Through the introduction of speech recognition system, artificial intelligence dialogue system and artificial intelligence dialogue backend, combined with a new generation of dialogue artificial intelligence technology, including: natural language processing (Natural Language Processing, NLP), dynamic learning mechanism, multi-round situational dialogue design and Dynamic information collection mechanisms, etc., establish a customer dialogue analysis backstage to enhance the user experience and market influence of digital channels.

A cross-channel artificial intelligence dialogue platform according to an embodiment of the present invention includes: a first internal server, including: a voice input interface, a voice-to-text interface, a semantic recognition interface, a text-to-speech interface, and an output Interface, wherein the voice input interface is used to receive a first voice signal; a second internal server, which is communicatively connected to the first internal server, includes: a client audio database for storing a plurality of audio files, the The content of the audio file corresponds to a plurality of personal data respectively; and an information hiding module is electrically connected to the customer audio database, and the information hiding module is used to divide the first voice signal into a plurality of voice fragments, and When the information hiding module determines that any one of the voice segments matches any one of the audio files, the information hiding module deletes the audio information corresponding to the voice segment from the first voice signal, And the first voice signal of the audio data of the deleted voice segment is returned to the first internal server as a second voice signal; wherein the voice-to-text interface of the first internal server is used according to the second voice signal The voice signal generates a first text signal; the semantic recognition interface is used to generate an intention signal based on the first text signal; and a third internal server, which is communicatively connected to the first internal server, includes: a dialogue module for Selectively generating a reply signal according to the intention signal; and an application module for generating a control command corresponding to the intention analysis signal; wherein the text-to-speech interface of the first internal server is used according to the reply The signal generates a third voice signal; the output interface of the first internal server is used to output the third voice signal and the control command.

An operating method of a cross-channel artificial intelligence dialogue platform according to an embodiment of the present invention includes: receiving a first voice signal through a voice input interface of a first internal server; and receiving a client from a second internal server The audio database stores a plurality of audio files, and the contents of the audio files respectively correspond to a plurality of personal data, wherein the second internal server is connected to the first internal server; one of the second internal servers is hidden The module divides the first voice signal into a plurality of voice segments, wherein the information hiding module is electrically connected to the customer audio database, and when the information hiding module determines any one of the voice segments When it matches any one of the audio files, delete the audio information corresponding to the voice segment from the first voice signal by using the information hiding module; using the information hiding module to return a second voice signal to the A voice-to-text interface of the first internal server, wherein the second voice signal is a first voice signal that deletes audio data of the voice segment; and the voice-to-text interface generates a first text signal according to the second voice signal; A semantic recognition interface of the first internal server generates an intent signal based on the first text signal; a dialogue module of a third internal server generates a reply signal based on the intent signal, wherein the third internal server Communicatively connect to the first internal server; use a text-to-speech interface of the first internal server to generate a third voice signal based on the reply signal; use one of the three servers to generate a control command based on the intention signal ; And output the third voice signal and the control command with an output interface of the first internal server.

The above description of the content of the disclosure and the description of the following embodiments are used to demonstrate and explain the spirit and principle of the present invention, and to provide a further explanation of the patent application scope of the present invention.

The detailed features and advantages of the present invention are described in detail in the following embodiments, and the content is sufficient to enable anyone familiar with the relevant art to understand the technical content of the present invention and implement it accordingly, and according to the content disclosed in this specification, the scope of patent application and the drawings Anyone who is familiar with the relevant art can easily understand the related purpose and advantages of the present invention. The following examples further illustrate the viewpoints of the present invention in detail, but do not limit the scope of the present invention by any viewpoint.

Please refer to FIG. 1, which shows an architecture diagram 100 of a cross-channel artificial intelligence dialogue platform according to an embodiment of the present invention. The cross-channel artificial intelligence dialogue platform 100 includes a first internal server 2, a second internal server 4 and a third internal server 6. As shown in FIG. 1, the second internal server 4 and the third internal server 6 are respectively communicatively connected to the first internal server 2. In addition, the components in the first internal server 2 communicate with the client device 91, the first external server 93, the second external server 95, and the third external server 97, respectively.

In practice, the first internal server 2, the second internal server 4, and the third internal server 6 are, for example, Blade Servers, Rack Servers, or vertical servers deployed in the computer room of financial institutions. Servers (Pedestal Servers), the present invention does not limit the hardware types of the first, second, and third internal servers 2, 4, and 6.

The first internal server 2, the second internal server 4, and the third internal server 6 each have a memory to implement various functions described later. The above-mentioned memory can be, for example, random access memory, read-only memory, or flash memory. In one embodiment, the first internal server 2, the second internal server 4, and the third internal server 6 further include communication devices supporting wired networks, wireless networks, mobile networks, and/or wireless communications. In one embodiment, the first internal server 2, the second internal server 4, and the third internal server 6 each include a processing circuit, which can perform the functions described below. Processing circuits such as microcontrollers, microprocessors, processors, central processing units (CPU), digital signal processors, special application integrated circuits (application specific integrated circuit, ASIC), digital logic circuit, field programmable gate array (FPGA) and/or other hardware components with arithmetic processing functions. The present invention has no effect on the hardware type of the processing circuit. To limit.

Please continue to refer to Figure 1. The first internal server 2 includes a voice input interface 21, a voice-to-text interface 23, a semantic recognition interface 25, a text-to-speech interface 27, and an output interface 29. The voice input interface 21 is communicatively connected to the client device 91. The client device 91 is, for example, a smart phone or a tablet computer with a mobile banking App (application) installed by the user, or a smart speaker or a smart robot at the counter of a smart branch. For the user, The department talks with the client device 91. In practice, the user's voice will be generated by the microphone (such as a microphone) of the client device 91 to generate a first voice signal, and then the communication component of the client device 91 will send the first voice signal to the first internal server 2 voice input interface 21. In short, when the user needs to perform financial-related operations, he can directly speak to the client device 91 to generate a first voice signal, and then the first voice signal will be sent to the voice input interface 21 for processing.

Please refer to the second internal server 4 of FIG. 1 first, which includes a customer audio database 41 and a personal information hiding module 43 that are electrically connected to each other. The customer audio database 41 stores a plurality of audio files, and the contents of the audio files correspond to the plurality of personal data respectively. In practice, the second internal server may further include a dynamic information learning module. The dynamic information learning module uses, for example, a financial institution’s manual customer service recordings as training data in advance, and uses machine learning methods from the customer service recordings. The audio fragments belonging to the customer's personal information are automatically identified, and then these audio fragments are stored in the customer audio database 41. The dynamic information learning module can also update the records in the client audio database according to the first voice signal obtained from the voice input interface 21 each time, which is not limited by the present invention.

Please continue to refer to the second internal server 4 in FIG. 1. The individual information hiding module 43 is electrically connected to the customer audio database 41 and communicatively connected to the voice-to-text interface 23 of the first internal server 2. The data hiding module 43 is used to divide the first voice signal into a plurality of voice segments, and when the data hiding module 43 determines that any one of these voice segments matches the plurality of audio files stored in the customer information database 41 In any of them, the personal information hiding module 43 deletes the audio information corresponding to the voice segment from the first voice signal, and returns the first voice signal of the audio data of the deleted voice segment as the second voice signal. The voice-to-text interface 23 of the first internal server 2. When the personal information hiding module 43 performs comparison, for example, a fuzzy comparison algorithm can be used. In addition, when the compared user profile is divided into multiple voice segments, the profile hiding module 43 reorganizes these voice segments with the user profile to extract the complete audio belonging to the user profile. data. Through the processing mechanism of the above-mentioned personal information hiding module 43, the private data belonging to the user can be restricted to the first internal server 2 and the second internal server 4 set in the computer room of the financial institution. During identification, the user's personal information will not be leaked to the Internet.

Please refer to Figure 1. The voice-to-text interface 23 of the first internal server 2 is respectively communicatively connected to the personal information hiding module 43 of the second internal server 4 and the first external server 93, and the semantic recognition interface 25 is communicatively connected to the second external server 95. The voice-to-text interface 23 generates a first text signal based on the second voice signal, and the semantic recognition interface 25 generates an intention signal based on the first text signal. In other words, the speech-to-text interface 23 converts the voice data containing the user's personal information into text, and the semantic recognition interface 25 interprets the user's intention from the text. For example, when the first text signal is: "I want to transfer 1,000 yuan", the semantic recognition module 25 can learn from it that "the user wants to transfer" and the two intentions of "the transfer amount is 1,000 yuan" . In practice, the speech-to-text interface 23 and the semantic recognition interface 25 are, for example, an application programming interface (API), and the first external server 93 is, for example, a Google Cloud speech-to-text (STT) external server. Device. The second external server 95 is, for example, an IBM Watson external server, which can provide various Watson cognitive computing services, including natural language processing (NLP) services to determine customer intentions. ) Machine learning mechanism to improve the accuracy of semantic understanding.

Please refer to Figure 1. The third internal server 6 includes a dialogue module 61 and an application module 63 that are communicatively connected to the semantic recognition interface 25. The dialogue module 61 selectively generates a reply signal based on the intention signal. The application module 63 can generate a control command corresponding to the intent analysis signal. In practice, the dialogue module 61 of the third internal server 6 can provide a dynamic learning mechanism through a machine learning model, thereby greatly improving maintenance efficiency. The dialogue module 61 further has a multi-round situational dialogue design. In practice, for example, by pre-training a dialogue analysis model on the Watson platform from the human customer service records to be analyzed, and then storing the trained dialogue analysis model in the database of the dialogue module 61, the dialogue module 61 can provide Interactive contextual dialogue design, and has the effect of context coherence. For example, when the user says: "I want to transfer a thousand yuan", the dialogue module 61 obtains from the semantic recognition interface 25 the two items including "the user wants to transfer" and "the transfer amount is 1,000 yuan". In addition to the intent signal of intent, it can also provide the user with reply signals such as "ask the user who wants to transfer the account" and "ask the user to use the account to transfer the account" to the client device. The mobile banking app running on 91 can collect enough information to complete subsequent transfer operations. In addition, the dialogue module 61 further has a dynamic information collection mechanism, which can quickly set parameters for rapid deployment and improve user experience. When the dialogue module 61 cannot identify the user's intention signal, the dialogue module 61 can be transferred to the manual customer service system, and the online customer service staff can respond to the user's question.

Please continue to refer to Figure 1. The text-to-speech interface 27 of the first internal server 2 communicates with the dialogue module 61 of the third internal server 6 and the third external server 97 respectively. The text-to-speech interface 27 is used to generate a third voice signal based on the reply signal; in other words, the reply generated by the dialogue module 61 is converted into a computer voice that the user can understand, and then output by the output interface 29 of the first internal server 2 The third voice signal is sent to the client device 91 so that the speaker or speaker of the client device 91 can play the third voice signal for the user to listen to. In practice, the third external server 97 is, for example, a text-to-speech web service external server of the Industrial Technology Research Institute, which can provide text-to-speech (TTS) web services, and the server provides SOAP (Simple Object Access Protocol) protocol network service, the input text is converted into voice for output. It should be noted that although the first, second, and third external servers 93, 95, and 97 of the present invention are in the above-mentioned embodiment, the first internal server 2 is connected to various cloud services through the Internet. However, in another embodiment, the above-mentioned external server can also be purchased by the financial institution itself with a text-to-speech function and semantic understanding function and set up in the local computer room. The present invention does not limit the first to third external servers. Servers 93~97 must be connected to the cloud to achieve the above functions.

Please continue to refer to Figure 1. The output interface 29 of the first internal server 2 is communicatively connected to the application module 63 of the third internal server 6 and the client device 91. In addition to outputting the third voice signal, the output interface 29 also outputs control commands generated by the application module 63. The control instruction is, for example, an instruction to control the mobile bank App to complete the transfer operation.

According to the content of the above-mentioned cross-channel artificial intelligence dialogue platform 100, in practice, the cross-channel artificial intelligence dialogue platform 100 can be communicatively connected to a user's smartphone or a smart speaker at a smart branch counter as required. In this way, the user can complete the desired financial transaction operation item through a dialogue with the client device 91.

Please refer to Figure 1 and Figure 2 together. FIG. 2 illustrates the operation method of the cross-channel artificial intelligence dialogue platform according to an embodiment of the present invention, which is suitable for the aforementioned cross-channel artificial intelligence dialogue platform 100. Please refer to step S11, the voice input interface 21 receives the first voice signal. In detail, the client device 91 transmits the user's voice by wired or wireless communication, and then is received by the voice input interface 21 of the first internal server 2. Please refer to step S21, the data hiding module 43 of the second internal server 4 divides the first voice signal into a plurality of voice segments. Please refer to step S23, the personal information hiding module 43 compares the voice fragment with the audio file in the customer audio database 41. Please refer to step S25, the information hiding module 43 determines whether any voice segment matches any audio file. If it does, continue to step S27. Otherwise, return to step S23. Please refer to step S27. The information hiding module 43 returns a second voice signal S27. The second voice signal is to delete the audio data of the voice segment (for example, the waveform signal representing the user's personal information). A voice signal. Please refer to step S13. The speech-to-text interface 23 of the first internal server 2 generates a first text signal according to the second speech signal, specifically, it converts audio data that does not contain the user's personal data into text data. Please refer to step S15. The semantic recognition interface 25 of the first internal server 2 generates an intention signal S15 based on the first text signal, for example, the text signal is analyzed by a semantic understanding server that provides cloud services to obtain the user's intention. Please refer to step S31. The dialogue module 61 of the third internal server 6 generates a reply signal according to the intention signal. In other words, the dialogue module 61 can identify the user’s intention from the reply signal to provide personalized service or response. . In practice, if the customer's question is not within the response range of the dialogue module 61, the dialogue module 61 can be transferred to the manual customer service system for subsequent customer service. Please refer to step S17. The text-to-speech interface 27 of the first internal server 2 generates a third voice signal S17 based on the reply signal, which converts the reply given to the user by the system into a computer voice that the user can hear. Please refer to step S33. The application module 63 generates a control command S33 according to the intention signal. The control command is used to perform an operation corresponding to the user's voice on the client device. Please refer to step S35, the output interface 29 outputs the third voice signal and the control command to the client device 91, for example, the system reply is played to the user for listening, so as to realize the dialogue interaction with the user to obtain the operation required by the user. Other parameters, or execute control commands to complete the financial transaction operation items the user wants.

In summary, the cross-channel artificial intelligence dialogue platform disclosed in the present invention provides services for completing financial transaction operations through dialogue with users, so that customers can feel the best experience and service, and can prevent users from personal Private information is leaked to the cloud to protect users' personal information. In addition, the cross-channel artificial intelligence dialogue platform is connected to mobile banking apps, smart branch counters, or smart personal financial services, which can reduce the manpower required by financial institutions to hire and train personnel who can provide the above financial services. And time cost.

Although the present invention is disclosed in the foregoing embodiments, it is not intended to limit the present invention. All changes and modifications made without departing from the spirit and scope of the present invention fall within the scope of patent protection of the present invention. For the scope of protection defined by the present invention, please refer to the attached patent scope.

100: Cross-channel artificial intelligence dialogue platform 2: The first internal server 21: Voice input interface 23: Voice-to-text interface 25: Semantic Recognition Interface 27: Text-to-speech interface 29: output interface 4: The second internal server 41: Customer Audio Database 43: Personal information hidden module 6: Third internal server 61: Dialogue Module 63: Application Module 91: client device 93: The first external server 95: second external server 97: Third external server S11~S35: steps

FIG. 1 is a diagram illustrating the structure of a cross-channel artificial intelligence dialogue platform according to an embodiment of the present invention. FIG. 2 is a flowchart of a method for operating a cross-channel artificial intelligence dialogue platform according to an embodiment of the present invention.

100: Cross-channel artificial intelligence dialogue platform

2: The first internal server

21: Voice input interface

23: Voice-to-text interface

25: Semantic Recognition Interface

27: Text-to-speech interface

29: output interface

4: The second internal server

41: Customer Audio Database

43: Personal information hidden module

6: Third internal server

61: Dialogue Module

63: Application Module

91: client device

93: The first external server

95: second external server

97: Third external server

Claims (7)

A cross-channel artificial intelligence dialogue platform, including: a first internal server, including: a voice input interface, a voice-to-text interface, a semantic recognition interface, a text-to-speech interface, and an output interface, wherein the voice input interface Used to receive a first voice signal; a second internal server, communicatively connected to the first internal server, including: a client audio database for storing a plurality of audio files, the contents of the audio files correspond to A plurality of personal data; and a data hiding module, which is electrically connected to the customer audio database, the data hiding module is used to divide the first voice signal into a plurality of voice segments, and when the data hiding module When it is determined that any one of the voice fragments matches any one of the audio files, the information hiding module deletes the audio information corresponding to the voice fragment from the first voice signal, and will delete the voice fragment The first voice signal of the audio data is returned to the first internal server as a second voice signal; wherein the voice-to-text interface of the first internal server is used to generate a first text signal based on the second voice signal ; The semantic recognition interface is used to generate an intention signal based on the first text signal; and a third internal server, which is communicatively connected to the first internal server, includes: a dialogue module for selectively based on the intention signal Generate a reply signal; and an application module for generating a control command corresponding to the intent analysis signal; wherein the text-to-speech interface of the first internal server is used for generating a third voice signal based on the reply signal ; The output interface of the first internal server is used to output the third voice signal and the control command. The cross-channel artificial intelligence dialogue platform according to claim 1, wherein the speech-to-text interface is connected to the Google Cloud speech-to-text external server, and the semantic recognition interface is connected to the IBM Watson external server, and The text-to-speech interface is a communication link to the external server of the ITRI text-to-speech web service. The cross-channel artificial intelligence dialogue platform according to claim 1, wherein the dialogue module is further communicatively connected to an online customer service system, and when the dialogue module cannot recognize the intent signal, the dialogue module forwards the intent signal To this online customer service system. The cross-channel artificial intelligence dialogue platform according to claim 1, wherein the second internal server further includes a dynamic information learning module, and the dynamic information learning module is used for learning from a customer service recording record and using machine learning. The audio files associated with the personal data are retrieved from the customer service recording record, and the audio files are stored in the customer audio database. The cross-channel artificial intelligence dialogue platform according to claim 1, wherein when the information hiding module determines that there are a plurality of voice fragments in the first voice signal that respectively match the plurality of audio files in the customer audio database, The information hiding module is further used to reorganize the voice fragments to retrieve a complete personal data of the personal data. An operating method of a cross-channel artificial intelligence dialogue platform includes: receiving a first voice signal through a voice input interface of a first internal server; using a resource hiding module of the second internal server to transfer the first voice signal The voice signal is divided into a plurality of voice segments, wherein the information hiding module is electrically connected to the customer audio database, and when the information hiding module determines that any one of the voice segments meets the second internal servo When any one of a plurality of audio files stored in a client audio database of one of the devices, the audio information corresponding to the voice segment is deleted from the first voice signal by the information hiding module, wherein the second internal server Communicatively connect to the first internal server; use the data hiding module to return a second voice signal to a voice-to-text interface of the first internal server, wherein the second voice signal deletes the audio of the voice fragment The first voice signal of the data; the voice-to-text interface generates a first text signal based on the second voice signal; the semantic recognition interface of the first internal server generates an intention signal based on the first text signal; The dialogue module of one of the three internal servers generates a reply signal according to the intention signal, wherein the third internal server is communicatively connected to the first internal server; a text-to-speech interface of the first internal server is used according to the reply signal A third voice signal is generated; an application module of the three servers generates a control command according to the intention signal; and an output interface of the first internal server is used to output the third voice signal and the control command. The operating method of the cross-channel artificial intelligence dialogue platform according to claim 6, wherein before receiving the first voice signal, it further includes: using a dynamic information learning module of the second internal server to learn from Obtain the audio files associated with the personal data from a customer service recording record; and use the dynamic information learning module to store the audio files in the customer audio database.

Images