System and method for simultaneously connecting audio and web channels

Abstract

Systems, methods, and other embodiments relating to the simultaneous linking of audio and web channels are described. In one embodiment, the method includes establishing an audio session for communication over an audio channel, in which a live agent communicates an audio signal with a user. In response to identifying a problem from the user, the agent sends a navigation link, which, when activated, navigates the browser to a web page associated with the problem. A web session is established for communication between the browser and the web page. The audio and web sessions associated with the user are linked together. A call controller can communicate with both channels simultaneously because both channels are connected, thereby allowing the live agent to disconnect from the audio channel.

Description

Technical Field

[0001] Field This specification describes a system and method for controlling the connection between a telephone call (e.g., audio communication) on a voice channel and a web page access (e.g., network content access) on a web channel to provide an intelligent cooperative connection and navigation function between two different channels.

Background Art

[0002] Background Companies or enterprises that provide services and / or products to customers may provide customer service in the form of a customer service call center. A call center is a complex technical system that includes a server, a database system, a telephone system, advanced software applications, and live agents for handling telephone calls from customers. Human live agents are usually trained to handle telephone calls and answer as many questions as quickly as possible.

[0003] In any enterprise, the number of live agents is limited, and the time of live agents is a precious resource. A live agent can only handle a certain number of telephone calls at any given time. To reduce the use of live agents and handle customer interactions, an automated system has been implemented. An automated chat system (or chatbot) is designed to interact with customers by using natural language processing (NLP) to provide human-like responses to customer questions.

[0004] However, many customers quickly become disillusioned with automated systems if chatbots are unable to answer questions or provide incorrect responses. To reduce call center system resources and improve call handling, it would be desirable to have a system with real-time functional tools that combine telephone calls on voice systems with digital tools on web systems. [Overview of the Initiative]

[0005] overview In one embodiment, a method performed by a computer is described. The method includes a voice server receiving a phone call from a user and establishing a voice session for communication over an audio channel, and a live agent communicating an audio voice signal with the user over the audio channel. The method further includes, in response to identifying a problem from the user, sending a navigation link to a remote device associated with the user, the navigation link, when activated, navigating a browser on the remote device to a web page associated with the problem. The method further includes, in response to the user navigating to the web page via the navigation link, establishing a web session on a web server including a web channel for communication between the remote device and the web page, and a call controller automatically linking the voice session and web session associated with the user, and activating a bot that operates with the web page and monitors at least one user action on the web page, the bot communicating one or more user actions to the call controller. The method further includes, the call controller generating and transmitting an audio voice signal with the user over the audio channel based on at least one or more user actions, and simultaneously communicating digital data to the web page over the web session while the user is interacting with the web page.

[0006] In another embodiment, a method is disclosed. This method includes: establishing an audio session on a first server for communicating audio speech in response to receiving a telephone call from a user over a network; connecting the audio session to a live agent to communicate with the user over the telephone call; converting the audio speech to text data; extracting multiple data components from the text data using natural language processing; and navigating a remote device associated with the user to a web page, the web page including an interactive form associated with a subject determined from the text data. The method further includes: establishing a web session on a second server to enable the user to interact with the web page via a remote device; a call controller connecting the audio session from the first server to a web session from the second server to enable simultaneous communication between them; the call controller generating and transmitting an audio prompt in the audio session requesting data input to a first data field in the interactive form; and, in the web session, extracting data values ​​from the audio response in response to receiving an audio response from the user from the audio session; and transferring the data values ​​to the first data field in the interactive form via the web session.

[0007] In another embodiment, a computing system is disclosed. The computing system comprises at least one processor connected to at least one memory and a non-temporary computer-readable medium containing stored instructions. When executed by at least one processor, the instructions cause the processor to simultaneously establish, via session connections, an audio channel established from a telephone call from a first user device associated with a user and a web channel established from a browser on a second user device associated with the user navigating to a web page, a navigation link sent to the second user device, which, when invoked, navigates the browser to the web page. The instructions cause the processor to monitor user interactions on the web page via the web channel and generate voice responses via the audio channel based on user interactions from the web channel to provide assistance to the user in relation to the content of the web page.

[0008] In another embodiment, the computing system comprises one or more computers, and the computing system is configured by computer executable instructions to perform any operation of the methods described herein.

[0009] In another embodiment, the embodiment can be implemented using a computer program product comprising a computer program and / or computer instructions, which, when executed by at least the processor of a computer, cause the processor (and / or other computer components) to perform any operation of the method described herein.

[0010] In another embodiment, the embodiment may be implemented using one or more non-temporary computer-readable media storing computer-executable instructions, the computer-executable instructions being configured to cause one or more computers to perform any operation of the method described herein when the computer-executable instructions are executed.

[0011] The accompanying drawings incorporated herein and constituting part thereof illustrate various systems, methods, and other embodiments of the present disclosure. It will be understood that the boundaries of elements shown in the drawings (e.g., boxes, groups of boxes, or other shapes) represent one embodiment of the boundary. In some embodiments, one element may be implemented as multiple elements, or multiple elements may be implemented as one element. In some embodiments, an element shown as an internal component of another element may be implemented as an external component, and vice versa. Furthermore, elements may not be depicted to actual size. [Brief explanation of the drawing]

[0012] [Figure 1] This figure shows one embodiment of a system related to the connection of voice channels and web channels. [Figure 2] This figure shows one embodiment of a method related to connecting voice channels and web channels during a telephone call. [Figure 3] This figure shows one embodiment of a method related to identifying and generating candidate navigation links. [Figure 4] This figure shows an embodiment of a method related to connecting independent audio and web channels and inserting audio data into an interactive form. [Figure 5] This figure shows an embodiment of a computing system configured in an exemplary system and / or manner as disclosed. [Modes for carrying out the invention]

[0013] Detailed explanation This specification describes a system and method for controlling connections between telephone calls on a voice channel and web page access on a web channel. In one embodiment, the system coordinates telephone calls from a user so that they are processed simultaneously by an automated system, while the user also interacts with web pages on the web channel at the same time. For example, the coordinated connection function of the system enables coordinated and coordinated communication for the user on both channels simultaneously by combining the voice channel with the web channel.

[0014] Conventional call systems did not coordinate voice and web channels, especially when the two channels were established at different times. Rather, conventional call systems operated the two channels separately and independently of each other, resulting in redundant and / or excessive functionality. The two separate channels could not cooperate with each other. Other conventional systems disconnected or terminated one of the channels, communicating on only one channel and resulting in limited functionality and performance for interacting with the user. This system improves upon these conventional systems by combining two independent channels and, in some embodiments, providing additional functional tools in real time based on predictions made by the system, as discussed herein.

[0015] In one embodiment, the system combines voice and web channels, allowing an automated response system (e.g., a call controller) to gain simultaneous access to both the voice and web channels connected to the customer / user. This enables simultaneous interaction with the customer / user on both channels. Furthermore, it is possible to transfer telephone calls handled by live customer service agents to the call controller, thereby reducing resources, including the amount of time required for live agents to answer calls (e.g., call processing time).

[0016] In one embodiment, the call control system can be implemented in a call center system that handles customer issues for a company (e.g., a utility company, another service company, a product company, etc.). A call center in a utility company is a complex technical system that includes servers, database systems, telephone systems, advanced software applications, and live agents for handling customer calls. These resources are costly, and this system can reduce complexity and costs by improving these technologies.

[0017] Average call processing time (ERP) is a metric used in the call center industry. Live agents spend a significant amount of time helping customers understand invoices, make changes to their accounts, investigate issues, navigate complex user interface screens, order products, and enter customer information—all of which occur while the live agent and the customer are speaking on the phone.

[0018] Research indicates that customers prefer to speak on the phone and are likely to continue using voice channels (phone calls) as a means of communicating with companies to resolve issues. The more customers use phone calls, the more likely they are to use them again for subsequent issues. Therefore, migrating these customers to digital channels (e.g., web channels, web page interfaces) to reduce call volume has become an industry focus.

[0019] Research also indicates that customers are typically near a smart device or computer when making a call to a call center. Therefore, the system implements a mechanism to combine and / or connect voice channels (telephone calls) with digital web channels in order to complete tasks, or at least parts of tasks, digitally rather than solely by telephone.

[0020] In another embodiment, the system is configured to analyze a customer's telephone conversation with a call center in real time, predict and / or identify the topic of the conversation, identify the issues discussed, and / or identify other data. Based on the predicted topic or issues, the system can generate insights and provide functional tools, tips, and / or proposed next best actions (e.g., on a graphical user interface). The generated tools can help live agents be more productive and reduce call handling times. The system can also provide contextually relevant shortcuts and / or navigation links that help live agents complete internal processes more quickly, saving time on phone calls in real time.

[0021] Definition When used in one or more embodiments, "voice channel" includes, but is not limited to, a communication channel that conveys audio / speech data in an audio format at the source and destination of the channel. For example, a telephone call initiated from one telephone (source) to another telephone (destination) creates a voice channel for communicating voice signals between them. Each telephone includes at least a microphone and a speaker for receiving and transmitting the audio sound of the voice, as well as network communication capabilities. The telephone includes, but is not limited to, a handheld device or computing device that originates and receives calls via wireless communication, landline communication, a combination of both, or digital IP-based telephone services (e.g., Voice over IP technology). The voice channel may include portions of the channel that convey signals in digital form, but the input and output of the voice channel include audio signals.

[0022] When used in one or more embodiments, a "web channel" includes a network communication channel that connects one computing device (e.g., a client device) to another computing device (e.g., a server) through a network connection that may include, but is not limited to, multiple network components. The web channel provides digital communication between two devices. For example, the web channel can provide a remote user device with access to content on a server, such as a web page, via an Internet connection.

[0023] System embodiments Referring to FIG. 1, one embodiment of a call control system 100 related to the control of connections between a telephone call on a voice channel and a web page access on a web channel is shown. The system 100 includes a call controller 105 and a session connection 110 configured to link or otherwise connect a voice session to a web session for a particular customer / client / user. Similar connections can be established for multiple customers / clients / users for a call center that may have hundreds or thousands of active telephone calls during any given time period.

[0024] The voice server 115 is configured to handle telephone calls between voice devices 120 (e.g., client devices, mobile phones, etc.). In one embodiment, the voice server 115 is configured to establish a voice session for each telephone call received by or transmitted from the voice server. Each voice session is assigned and associated with a voice channel assigned to a voice identity / identifier associated with the voice device 120 (associated with a particular user identity or identifier, user ID).

[0025] For example, when user 1 uses voice device 120 to make a phone call to a phone number belonging to or processed by voice server 115, the phone call is received by voice server 115. A connection is established (e.g., a voice channel for the phone call), and a voice session and voice identity / identifier that uniquely identify voice device 120 (e.g., user 1) are assigned. Each voice session established in voice server 115 can be identified, for example, by a voice session ID and a unique voice identifier that identifies at least the user and / or the user's voice channel (e.g., user ID, phone number, etc.). Voice server 115 maintains a list of active voice sessions along with these identifiers (e.g., called voice session data).

[0026] The web server 130 is configured to handle internet connectivity and remote access to the web server 130. The web server 130 is configured to provide and allow clients / users (operating web devices 135) to access web pages controlled by the web server 130. In one embodiment, the web server 130 is configured to establish a web session for each remote web device 135, which includes a web channel for communication between the remote web device 135 and the content within the web server 130. This may include a user account and access to one or more web pages.

[0027] Each web session is uniquely assigned to a specific web device 135 and client / user making a connection to the web server 130. For example, a web identity / identifier can be used to uniquely associate a client / user with a web session, distinguishing each user and each web session from other users and web sessions. Each web session established on the web server 130 is identified by at least the user (user ID) and a unique web identifier (web ID) assigned to that web channel / session. The web server 130 maintains a list of active web sessions along with these identifiers (e.g., called web session data).

[0028] The web device 135 can be any computing device capable of communicating with the Internet and / or a private communication network. The web device may include, but is not limited to, a smartphone, a computer, or any other computing device with network capabilities.

[0029] In one embodiment, the web server 130 can be configured to launch a bot 140 to interact with a specific web device 135 during a web session. The bot 140 can be an embedded bot, and can be selected from several available bots based, for example, on the type of web page and the corresponding functionality of the bot. The bot 140 can be configured to monitor and listen to events occurring on the web page, for example, user actions that occur. The bot 140 can also be configured to automate input and output actions on the web page and communicate with a call controller 105.

[0030] In one embodiment, the call controller 105 may include a conversation orchestrator component that is part of the call controller 105 or can operate in conjunction with the call controller 105. The conversation orchestrator component may include applications such as speech recognition technology and natural language processing (NLP) technology for understanding and processing voice conversations. The system 100 may also include a conversation library 145 which contains programmed responses used to generate voice prompts and / or actions corresponding to web pages based on certain conditions.

[0031] For example, based on the type of event or condition detected, the call controller 105 can identify a corresponding response defined in the conversation library 145 and generate that response for the user. The library 145 can be programmed with voice prompts that request certain data from the user based on the web page or form the user is interacting with. For example, a particular web page may have a set of programmed responses associated with the web page's content and / or user actions that occur when the user interacts with the web page.

[0032] The conversation library 145 can also be programmed with answers to questions related to the content of a webpage. For example, for a user asking a question about the content of webpage XYZ, "[What is data field ABC?]", the programmed response could include a response describing the content of data field ABC. This response is passed to the call controller 105 to generate a voice response to the user. Using the customer data database 150, the responses and / or actions generated can be personalized for specific clients / users involved in voice sessions and / or web sessions.

[0033] With respect to session connections 110, the call controller 105 is configured to link and combine an independent voice session from the voice server 115 with an independent web session from the web server 130, so that both sessions belong to the same client / user. In one embodiment, the session connection may include mapping or assigning a unique voice identity / identifier 175 and a unique web identity / identifier 180 together in a database or other data structure. In this way, the call controller 105 and other system components can determine which web session belongs to which voice session for a particular user by accessing the database and identifying the combined / linked IDs.

[0034] Based on knowing which channels are coupled / linked together, this allows, for example, the call controller 105 to communicate audio signals with the user via the audio channel (via a phone call) and simultaneously communicate digital data to the web page via the web session while the user is interacting with the web page and during a phone call. Thus, the call controller 105 acts as a linkage that passes communication between both channels for a particular user / customer based on the link. In this way, the user can browse the web page and see the actions taken by the call controller 105 and / or the bot 140 (which occur via the web session), and the user can speak to and listen to the call controller 105 via the audio session.

[0035] As mentioned earlier, connecting these two independent sessions had not been done in conventional systems. Therefore, this system provides improved communication efficiency and cooperative capabilities by combining these channels. This will be explained in more detail below.

[0036] In one exemplary embodiment, the call controller 105 is configured to simultaneously connect an audio channel to a web channel in the server. The audio channel is established from a phone call from a user device (via the audio device 120), and the web channel is established from a browser navigating to a web page (via the web device 135). Although the phone call and browser are operated by the same user, they are on two independent communication channels. The call controller 105 is configured to identify the two independent communication channels (e.g., an audio session and a web session) assigned to the same user and to connect the two channels. In one embodiment, the audio session ID and the web session ID are connected / linked together in the session connection 110. This allows the call controller 105 to communicate and transfer data to both channels simultaneously by knowing which channel belongs to the same user. Thus, the call controller 105 can interact with the user in an audio response (via the audio channel) and interact with the content of the web page (via the web channel). This will be further explained below.

[0037] Therefore, since both channels are connected to the same user, the call controller 105 can interact with and communicate with both channels simultaneously. For example, the bot 140 can be configured to monitor and detect certain types of user interactions and conditions occurring on the web channel. Interactions may include both actual actions and the absence of actions. In response, the bot 140 can communicate the detected user actions and conditions to the call controller 105. The call controller 105 can then determine and retrieve a corresponding response from the conversation library 145 that matches the detected action / condition, which forms the basis of the voice response. The call controller 105 can then simultaneously generate and transmit voice responses via the voice channel to provide assistance to the user in relation to the content of the web page and / or in relation to the type of detected user interaction.

[0038] In this way, the user can enjoy talking on the phone call to receive an audio response, and the call controller 105 and bot 140 can also systematically provide assistance via the web channel to resolve the user's problem. One advantage is that, in response to establishing a web session and / or after transferring the phone call to the call controller 105 and / or bot 140, the live agent can be disconnected from the phone call in order to reduce the call processing time for the live agent.

[0039] Furthermore, when this system 100 is implemented in a call center system (for example, a call center of a public utility company), the system 100 can reduce overall call center costs by providing a set of functional tools in real time to both live agents and customers during a call. This will be explained below.

[0040] Process Embodiment Referring to Figure 2, one embodiment of Method 200 relating to the connection of independent voice channels and web channels is shown. Method 200 is also described with reference to System 100 in Figure 1 and its operation in a call center system.

[0041] In block 210, the voice server 115 receives a phone call from a user using a voice device 120 (e.g., a mobile phone). When the phone call is answered, a connection is established with the mobile phone and an audio channel for communication is created.

[0042] In block 220, a voice session is established in the voice server 115 for the user to communicate via an audio channel. Once established, the live agent may connect to the voice session and communicate audio signals with the user via the audio channel (talk via a telephone call).

[0043] Typically, a user calls a company because of some problem the customer is having with their account and / or because they are trying to perform some task with the company. For example, a utility customer may have moved from their home, changed their home address, and need to transfer their utility services to their new home address. A live agent is involved to help the user accomplish these changes through the company's internal processes. During the initial conversation on the phone, the live agent can identify the customer's problem and the reason for the call.

[0044] In one embodiment, the system may simultaneously perform speech recognition or natural language processing (NLP) applications to identify the subject of the conversation and other data components associated with the user. This may include collecting audio speech signals from a phone call and converting them into text data, understanding what the text is, and automatically extracting certain portions of the data. The extracted portions of data may include, but are not limited to, the customer's name, address, and the reason for the phone call. By understanding the conversation, the system can then predict what the problem is and evaluate other parameters such as the customer's emotions.

[0045] One premise is that customers are typically near a smart device or computer when they call a call center. Therefore, this can be used to leverage web channels in conjunction with phone calls (voice channels) to perform tasks to resolve customer issues. For example, a live agent and system might attempt to navigate a customer / user to a specific webpage or website on their computing device. One objective here is to have the customer interact with an automated system component associated with the webpage, allowing the live agent to disconnect from the phone call.

[0046] In block 230, in response to identifying a problem from the user, a navigation link can be sent to a remote device associated with the user. In one embodiment, when the navigation link is activated (e.g., selected or clicked by the user), it navigates the browser on the remote device to the web page associated with the problem.

[0047] For example, based on a customer's issue, a live agent might inform the user that they can fill out a specific form to resolve the problem. In the above example, where a customer is changing their home address, they might need to complete a change of address form. One objective here is to reduce the amount of time the live agent spends on phone calls. Therefore, instead of the live agent interacting with the customer and processing details via phone calls, the system would hand over the assistance to a bot or other automated response system configured to directly assist the customer with form completion using a web page. Thus, navigation links would be configured to point to specific forms on specific web pages within the system (e.g., a web page containing a change of address form).

[0048] In one embodiment, based on a customer problem identified or predicted from a phone conversation by an NLP application, the system can identify one or more tools that address the predicted problem. Then, to resolve the problem more quickly, one or more tools can be displayed on a graphical user interface (GUI) on a device operated by a live agent. For example, a tool may include suggested navigation links that the system predicts are related to a specific online form or other web page that addresses the predicted problem. Thus, one or more suggested navigation links can be displayed in a list to the live agent and made available for selection. This is also illustrated with reference to Figure 3.

[0049] Next, the live agent can select a navigation link from the GUI that they believe is related to the customer's issue. The live agent can also search for additional links if the correct link is not in the displayed list. After a navigation link is selected (for example, a link to an online address change form), an electronic message containing the navigation link is generated and addressed to the device associated with the customer.

[0050] In one embodiment, the navigation link is sent to the user via electronic message. This can be done by sending the navigation link to the user via SMS message, via email associated with the user, and / or in another electronic format. Upon receiving the message, the user can activate the navigation link, which will navigate the user's device to the associated webpage.

[0051] Furthermore, since user identity can be obtained during a phone call, navigation links can be configured to include pre-authentication data or other credentials associated with the user. This allows the web server to automatically authenticate the user and log them into their assigned account when the navigation link is activated and the web page on the web server is accessed.

[0052] Continuing to refer to Figure 2, in block 240, a web session is established in web server 130 (Figure 1) in response to the user navigating to a web page via a navigation link. As previously mentioned, in one embodiment, web server 130 is separate from voice server 115 and handles website access. The web session may include a web channel for communication between the user's remote device 135 and the web page associated with the navigation link. The web session may include a web session ID assigned to the user ID associated with the user.

[0053] After the live agent navigates the user to a specific web page or online form via a navigation link, the live agent can provide a description of the online form via a telephone call. At this point, two separate communication channels are open: a telephone call on a voice channel (via the voice server 115) and a web channel on which the user is accessing a web page (via the web server 130). In one embodiment, the voice device 120 (e.g., the user's telephone) and the web device 135 (e.g., the user's computer) are two separate devices operated simultaneously by the user.

[0054] In another embodiment, the user may be operating a single device, such as a smartphone, that makes phone calls using a telephone application and also navigates to web pages using an internet browser application. In both cases, the voice channel and the web channel are still established from two different servers on the backend, and the channels are operated independently of each other. However, the call controller 105 automatically combines the two channels by linking the user's voice session and the user's web session together.

[0055] In block 250, the call controller 105 automatically links the voice session and web session associated with the user. This can be triggered by the establishment of a web session for the user. In response, the call controller 105 can identify the corresponding voice session ID assigned to the same user from the voice server and / or the user's web session ID from the web server (and vice versa). Once the voice session ID and web session ID are identified, the system maps or otherwise assigns them together in the session connection 110 (see Figure 1). As previously mentioned, each voice session established in the voice server 115 can be identified, for example, by the voice session ID and a unique voice identifier (e.g., user ID, phone number, etc.) that identifies at least the user and / or the user's voice channel. Each web session established in the web server 130 is identified by at least the user (user ID) and a unique web identifier that identifies their web channel / session.

[0056] For example, by assigning / mapping their IDs to each other in session connection 110, two sessions / channels become associated with each other, allowing the call controller 105 and other system components to determine which channel belongs to the same user. This also identifies which channel belongs to a particular user / customer based on matching user IDs.

[0057] In one embodiment, once a web session is established, the call controller 105 is configured to search and identify whether a corresponding voice session exists for the same user ID associated with the web session. The web session contains user identification information (e.g., user ID). The call controller 105 can retrieve the user identification information from the web session data. It can then query and search the voice session data from the voice server 115 to find a matching user ID that has an active voice session. If a match is found, the call controller 105 links the matching voice session ID and web session ID, both associated with the same user ID, in the session connection 110. As a result, the call controller 105 (and other system components) recognize that a particular user ID has two active channels, which enables data to be communicated and transferred between the two channels.

[0058] In block 260, after the user navigates to the webpage associated with the navigation link, the bot is activated and can work with the webpage to provide assistance to the user while the user interacts with the webpage. As previously mentioned, the bot can be configured to monitor user actions and report them to the call controller 105. Due to the connection of the audio session and the web session, the call controller 105 can communicate audio responses with the user via the audio channel and simultaneously communicate digital data to the bot and / or webpage via the web session while the user interacts with the webpage. Thus, while the user is entering data on the webpage on the web channel or interacting with the webpage, the call controller 105 can speak with the user simultaneously via the phone call to respond to user actions occurring on the web channel and provide assistance.

[0059] After a web session is established with the user, the live agent and the user can still connect and communicate via a telephone call (voice session). Furthermore, as the user navigates to a webpage, the live agent can provide the user with several assurances and inform them that the bot will assist the user by processing forms to resolve the issue. In one embodiment, once the user gives consent or authorization to work with the bot, the live agent can trigger a disconnect option that disconnects the live agent from the telephone call (voice session). In another embodiment, in response to establishing a web session and / or activating / running the bot to work with the webpage, the call controller 105 can disconnect the live agent from the voice session after some defined time interval. Disconnecting may include placing the live agent's voice channel connection on hold in the telephone call (voice session), or completely disconnecting and terminating the live agent from the telephone call. In any scenario in which the live agent is disconnected from the voice session, the voice session remains open and active with the user, allowing the call controller 105 to provide an audio response to the user. At this point, the user's telephone call is not on hold.

[0060] For example, after a live agent transfers a customer / user to a webpage, the live agent can explain that the customer fills out an associated online form, puts the live agent's phone call on hold, and reconnects once the customer completes the online form. Thus, the live agent is no longer actively engaged with the customer. While the live agent is on hold (disconnected), the customer's voice session remains open, and any questions asked by the customer are handled by the call controller 105 using NLP as described herein.

[0061] The bot can be configured to monitor the progress of a customer filling out an online form. A completion condition is triggered when the form is completed or nearly completed. The webpage may also have a completion button (e.g., a submit button), which, when activated by the customer, also triggers the completion condition. In response, the bot may send a completion message or alert signal back to the call controller 105. In response, the call controller 105 may generate an alert and / or pass a completion message signal to the live agent to warn the agent to reconnect to the voice session.

[0062] In another embodiment, in response to a completion condition indicating that a user has completed interacting with a web page, the system can automatically reconnect a live agent to a voice session with the customer. By reconnecting to the voice session, the live agent can finalize any remaining issues with the customer. If the live agent is disconnected or placed in a pending status, the system can be configured to generate and send a completion message / signal to the live agent. The completion message / signal may indicate that a particular user has completed filling out an online form and prompts the live agent to reconnect to the voice session, for example by selecting a reconnect option on the GUI. The system then reconnects the live agent's device to the voice session.

[0063] Overall, this system improves upon conventional call systems by combining / linking independently established voice and web sessions. This allows the call controller 105 to monitor and communicate simultaneously through both channels, rather than having multiple components monitor and communicate separately for each channel. Thus, the number of components in the call system can be reduced. The system also offers advantages to the call system, for example, by disconnecting live agents from phone calls much earlier in the process of handling customer phone calls. Thus, the amount of time a live agent spends on a particular phone call is reduced, and the live agent can process more phone calls within a given time period.

[0064] Navigation Link Embodiment Referring to Figure 3, one embodiment of Method 300 relating to the identification and generation of candidate navigation links to assist a live agent is shown. Method 300 is one embodiment of actions performed after an audio session is established in block 220 of Figure 2 and before block 230, which includes the system sending a navigation link to a remote device associated with the user.

[0065] In block 310, in one embodiment, a natural language processing (NLP) application can be run at the first moment of a phone conversation between a customer / user and a live agent during a voice session. The NLP application is configured to analyze and understand the conversation / topic from the audio speech signal from the voice session. This may include converting the audio speech signal into text data and extracting content from the text data. Based on understanding the conversation, the NLP can predict the issue the user is calling about.

[0066] In block 320, based on the predicted problem, the system identifies content in the database related to the problem. The system can then identify and retrieve from the database one or more candidate navigation links that point to one or more web pages containing content to resolve the predicted problem. For example, if a customer is trying to add a second user to their account, the system searches the database for relevant content (e.g., one or more forms related to adding a user to an account) and retrieves the navigation links associated with each form or web page. These links are called candidate links because the system predicts which links are potentially relevant to the customer's problem and can resolve it.

[0067] In block 330, the system generates and displays a list of one or more candidate navigation links on the computing device associated with the live agent. The list is created, including a description of each link, and sent to the live agent's device. The list is then displayed in real time on the graphical user interface (GUI) during a phone call. The list is made up of selectable links to allow the live agent to select the link most appropriate for the customer's problem. The selected link is also called the target navigation link.

[0068] In block 340, in response to the live agent selecting a target navigation link from the list, the system prepares the target navigation link for transmission to the remote device associated with the user. For example, an electronic message containing the target navigation link is generated and addressed to the device associated with the customer. The electronic message may be an SMS message pushed to the customer's phone and / or an email sent to the customer's email address. Upon receipt, the customer's device is navigated to the target navigation link when the customer selects / opens / activates the target navigation link.

[0069] Implementation of voice-to-web form submission Referring to Figure 4, one embodiment of Method 400 is shown, relating to connecting independent voice and web channels and inserting digital data into an interactive form based on voice data. In one embodiment, Method 400 is performed by the call system 100 in Figure 1 or a similar system, enabling the transfer of data between two connected channels.

[0070] In block 410, in response to receiving a telephone call from a user, the system establishes a voice session on the first server for communicating audio. The voice session is established in the same manner as described above.

[0071] In block 420, the system connects a voice session to a live agent in order to communicate with the user via a telephone call. This may involve identifying and connecting the live agent from multiple agents that are not currently active in another telephone call.

[0072] In block 430, when the user and the live agent speak to each other, the system converts the audio into text data and uses natural language processing (NLP) to extract multiple data components from the text data. The NLP function can be performed in the same manner as described above.

[0073] In block 440, the system causes a remote device associated with the user to navigate to a web page. For example, the web page includes an interactive form associated with a subject determined from text data. This step may include, but is not limited to, actions similar to block 230 in Figure 2, including identifying relevant navigation links based on the user / customer's problem, generating an electronic message containing the navigation links, and sending the electronic message to the user's device.

[0074] In block 450, in response to the activation of the navigation link, the user's remote device is navigated to the web page associated with the link, which contains an interactive form. The system then establishes a web session on a second server to allow the user to interact with the web page via the remote device. These functions may include similar functions to those described in block 240 of Figure 2.

[0075] In block 460, the system connects an audio session from the first server to a web session from the second server, enabling simultaneous communication between them. For example, as previously mentioned, the call controller 105 can identify the audio session associated with a user (e.g., an audio session ID) and also identify the web session associated with the same user (e.g., a web session ID). Then, in the session connection 110 (see Figure 1), the audio session ID and the web session ID can be mapped / assigned to each other. The two sessions, and therefore the two channels, are joined together in the system as previously mentioned. Thus, the call controller 105 functions as a coordinating connection that passes communication between both channels for a particular user / customer.

[0076] In block 470, once the voice session and web session are connected, functions and communications that were previously impossible can be performed simultaneously between the two sessions. This includes transferring data between the two sessions (e.g., from voice data to web page data, and from web page data to voice data). For example, in the voice session, the call controller 105 can generate and send an automated voice prompt to the user requesting data entry for a first data field in an interactive form within the web session. The automated voice prompt can correspond to a specific data field and / or can be generated by the system based on user actions detected on the interactive form. Thus, actions / events detected in the web session can be forwarded to the call controller 105 to trigger a voice response in the voice session.

[0077] Furthermore, after the user's voice and web sessions are connected, the user can continue working in both sessions to resolve the issue with assistance from the call controller 105. As in the previous example, the user may be filling out a form on a web page via the web session, and the call controller 105 may be providing a response to the user. While this is happening, the agent can disconnect from the voice session (for example, by putting it on hold or ending it) to allow the live agent to perform other tasks and / or handle other phone calls.

[0078] In another embodiment, the system can start and operate an embedded bot along with an interactive form within a web session. The embedded bot is configured to operate as described above, which includes monitoring user actions, automating input and output to the interactive form, and communicating with the call controller 105.

[0079] In one embodiment, the interactive form includes one or more blank data fields that can receive input data. An embedded bot is configured to monitor user actions and events occurring on the interactive form. When a certain detected action or event occurs, the embedded bot can send corresponding data back to the call controller 105. Based on the received data, the call controller 105 can generate voice prompts / responses via the phone call (within the voice session) requesting data input for one or more blank data fields in the interactive form. Voice prompts / responses can be identified and retrieved from a conversation library 145 programmed with responses to specific events / conditions. The call controller 105 can be configured to verbally ask the user to provide answers to the blank data fields based on the user's mouse or cursor position on the interactive form.

[0080] In block 480, upon receiving a user's voice response to an automated voice prompt from the call controller, the voice response is converted into text data. Other NLP functions can be applied to determine which parts are actual data values. Data values ​​corresponding to the answer to a specific data field are extracted from the text data. For example, in the voice response "My name is John," the data value is "John," which corresponds to the input field "Name." The data value is then sent to the web session and populated by the embedded bot into a specific data field in an interactive form within the web session.

[0081] Therefore, by combining the two sessions / channels and transferring data from the phone call to an embedded bot operating on the web page, the call controller 105 can communicate voice responses to the user via the voice session and simultaneously interact with the web page via the web session. Thus, the user can continue communicating via the phone (which the user may prefer), and the live agent can disconnect from the phone call as the call controller, along with the embedded bot, takes over the interaction.

[0082] Therefore, improvements are obtained in this system for single-channel systems and for systems with multiple individual channels. This also helps to reduce call processing time for live agents. By combining voice and web channels as described herein, the automated response system (e.g., call controller) gains simultaneous access to both the voice and web channels to which the customer / user is connected. This enables simultaneous interaction with the customer / user on both channels and allows data to be coordinated / shared between both channels. As described herein, telephone calls processed by live customer service agents are forwarded to the call controller 105, which can also work with an embedded bot, thereby reducing resources, including the amount of time required for live agents to answer the phone (e.g., call processing time).

[0083] Embedded Bot Implementation In one embodiment, the embedded bot can be an executable input / output model. Regarding the bot's operation, in one embodiment, the bot can be configured to monitor user interactions with a web page over a web session. For example, the bot can detect certain events / conditions from the user interaction and its context. One type of event / condition may include detecting input hesitation from the user interaction. Input fields on the web page associated with the input hesitation or other user interactions are also identified. In response to the bot detecting input hesitation, the bot can be configured to communicate the detected event / condition to the call controller 105. Based on the type of event / condition, the call controller 105 can determine a corresponding response defined in the conversation library 145 (see Figure 1).

[0084] When a corresponding response is found, the response is converted into speech, and the call controller 105 can generate and transmit an oral assistance message about the input field via the audio channel to provide voice assistance to the user.

[0085] For example, based on monitored actions, a bot can detect certain types of actions, such as when a user hesitates or takes too long while entering data into a specific input field on a webpage. These actions can be determined by monitoring the mouse or cursor position on the webpage. The cursor position typically identifies a particular input field or content located on the webpage at the same position. The timing of the user action can indicate whether the user is hesitating to enter data into an input field. For example, if the cursor does not move and / or no input is made for a threshold amount of time (e.g., 5-10 seconds), the user may be hesitating to enter data because they do not understand what the input should be.

[0086] Because two channels are connected to the same user, the call controller 105 can interact and communicate with both channels simultaneously. For example, in response to a certain type of user interaction detected, the call controller 105 can simultaneously generate and send voice responses via the voice channel to provide assistance to the user in relation to the content of the web page. If the bot detects that the user is hesitating while entering data in the address field on a form, the bot communicates this event to the call controller 105. The call controller 105 can generate and send a voice response such as, "It seems you are having trouble with the address field. Please enter your home address." In one embodiment, various responses can be defined for a particular web page or web form and associated with one or more fields on the web page / form or other content on the web page / form. These responses can be maintained in the conversation library 145 or other appropriate database.

[0087] In one embodiment, the response in library 145 is configured to explain what data belongs to a particular input field in order to assist the customer. The call controller 105 may further ask for input data in the voice response via the voice session (e.g., "What is your name?"). The customer can verbally provide the input in the voice response via the voice session. The voice response can then be converted to text input and forwarded to the web session to be received by the embedded bot. Thus, the voice response is forwarded from the voice session to the bot in the web session, thereby enabling both channels to be used in coordination.

[0088] Next, the bot can automatically insert text input into the name field via the web session. The call controller 105 can also be programmed to answer questions related to the content of the web page, which may be something other than an fillable form. Such answers are defined and maintained in the conversation library 145.

[0089] Therefore, the call controller 105 can be configured with response actions based on what is happening on the website / page (for example, what user actions are doing on the website GUI). This is possible because the system links / connects audio channels (telephone calls, voice sessions) with digital web channels (websites, web sessions). Thus, this connection allows the call controller to work collaboratively with the user through audio and web sessions.

[0090] This call system 100 allows live agents during a phone call to more quickly disconnect from the call once the customer navigates to a specific webpage that helps resolve the user's issue. This reduces the call processing time for human agents and frees them from the need to collect basic information from the customer. Instead, a bot collects information from the customer and provides automated assistance simultaneously through voice and web sessions via the call controller 105.

[0091] NLP, implementation of speech-to-form transformation In one embodiment, the call control system 100 can acquire initial data from a telephone call (voice session) and then transfer this to a web session for automatic input into an online form.

[0092] As mentioned above, speech recognition or natural language processing (NLP) applications can be used in conjunction with the call system. Voice sessions can be recorded in real time, and the audio can be converted into text data using, for example, a speech-to-text conversion function. NLP can then analyze the text, recognize what the text is, and extract certain portions of the data that are identified as corresponding to one or more known data fields. The extracted data may include, but is not limited to, the customer's first and last name, home address, email address, reason for the phone call, etc.

[0093] Subsequently, once a web session is established for the customer and the customer navigates to the online form, the extracted data can be transferred to the web session. The bot can then automatically populate the corresponding input fields within the online form with the extracted data. In this way, parts of the online form are filled out based on the voice conversation, without the customer having to manually enter all the data.

[0094] In another embodiment, by analyzing a phone conversation between a customer and a call center agent, an NLP application can determine the context and / or topic of the conversation. Based on the context and / or topic, the system can predict the type of problem the customer is calling about and take action accordingly. For example, based on the predicted problem, the system can identify and provide tools, tips, and / or features (accessible on the user interface) that help both the agent and the customer be more productive in resolving the problem. This helps to complete phone calls more quickly and reduce overall call time.

[0095] In another embodiment, NLP can be configured to perform real-time sentiment analysis. For example, it can determine the emotions of both the live agent and the customer from the conversation. It can also calculate the level of emotion or sentiment, such as anger or empathy. This can be recorded and stored to provide feedback to the live agent for training purposes. The system can also generate a pop-up window on the live agent's device in real time containing suggestions for responding to certain detected emotions.

[0096] In one embodiment, if the emotion detected during a call escalates beyond a threshold level (for example, if the customer is angry beyond a certain threshold), the system can send an alert message to the supervisor to intervene. The system can provide a link that allows the supervisor's device to automatically connect to the corresponding voice session.

[0097] Cloud or enterprise implementation In one embodiment, the call system 100 is a computing / data processing system comprising an application or a collection of distributed applications for an enterprise organization. The applications and computing system 100 can be configured to work with, or be implemented as, a cloud-based networking system, a software-as-a-service (SaaS) architecture, or other type of networked computing solution. In one embodiment, the call system 100 is a centralized server-side application that provides at least the functions disclosed herein and is accessed by a large number of users via computing devices / terminals that communicate with the call system 100 (acting as a server) over a computer network.

[0098] In one embodiment, one or more of the components described herein are configured as program modules stored in a non-temporary computer-readable medium. The program module consists of stored instructions that, when executed by at least a processor, cause a computing device to perform the corresponding functions described herein.

[0099] Computing device embodiment Figure 5 shows an exemplary computing device configured and / or programmed as a dedicated computing device having one or more of the exemplary systems and methods and / or equivalents described herein. The exemplary computing device may be a computer 500 including at least one hardware processor 502, memory 504, and input / output ports 510, which are operably connected by bus 508. In one example, the computer 500 may include call controller logic 530 configured to facilitate the processing and connection of telephone calls between telephone calls on voice channels and web page accesses on web channels, similar to the call control system 100 shown in Figure 1, and / or related processes and their equivalents in Figures 2-4.

[0100] In different examples, logic 530 may be implemented in hardware, a non-temporary computer-readable medium 537 storing instructions, firmware, and / or a combination thereof. Although logic 530 is shown as a hardware component attached to bus 508, it should be understood that in other embodiments, logic 530 may be implemented in processor 502, stored in memory 504, or stored on disk 506.

[0101] In one embodiment, the logic 530 or computer is a means (e.g., structure, hardware, non-temporary computer-readable medium, firmware) for performing the described actions. In some embodiments, the computing device may be a server operating within a cloud computing system, a server configured in a software-as-a-service (SaaS) architecture, a smartphone, a laptop, a tablet computing device, etc.

[0102] The means may be implemented, for example, as an ASIC programmed to perform the functions of the call control system 100. The means may also be implemented as a stored computer executable instruction, which is temporarily stored in memory 504 and then presented to computer 500 as data 516 executed by processor 502.

[0103] The logic 530 may also provide means for performing the functions of the call control system 100 (e.g., hardware, a non-temporary computer-readable medium for storing executable instructions, firmware).

[0104] In general, an exemplary configuration of computer 500 is described, where the processor 502 can be a wide variety of processors, including dual microprocessors and other multiprocessor architectures. Memory 504 may include volatile memory and / or non-volatile memory. Non-volatile memory may include, for example, ROM, PROM, etc. Volatile memory may include, for example, RAM, SRAM, DRAM, etc.

[0105] The storage disk 506 can be operably connected to the computer 500, for example, via an input / output (I / O) interface (e.g., a card, device) 518 and an input / output port 510 controlled by at least an input / output (I / O) controller 540. The disk 506 may be, for example, a magnetic disk drive, a solid-state disk drive, a floppy disk drive, a tape drive, a Zip drive, a flash memory card, a memory stick, etc. Furthermore, the disk 506 may be a CD-ROM drive, a CD-R drive, a CD-RW drive, a DVD-ROM, etc. The memory 504 can store, for example, a process 514 and / or data 516. The disk 506 and / or the memory 504 can store an operating system that controls and allocates the resources of the computer 500.

[0106] The computer 500 interacts with and controls, and / or is controlled by, input / output (I / O) devices via an input / output (I / O) controller 540, an I / O interface 518, and input / output ports 510. The I / O devices may include, for example, one or more displays 570, a printer 572 (such as an inkjet, laser, or 3D printer), an audio output device 574 (such as a speaker or headphones), a text input device 580 (such as a keyboard), a cursor control device 582 for pointing and selection input (such as a mouse, trackball, touchscreen, joystick, pointing stick, electronic stylus, or electronic pen tablet), an audio input device 584 (such as a microphone or external audio player), a video input device 586 (such as a video and still camera, or an external video player), an image scanner 588, a video card (not shown), a disk 506, a network device 520, and the like. The input / output ports 510 may include, for example, a serial port, a parallel port, and a USB port.

[0107] Computer 500 can operate within a network environment and, therefore, can connect to a network device 520 via the I / O interface 518 and / or I / O port 510. Through the network device 520, computer 500 can interact with network 560. Through the network, computer 500 can logically connect to a remote computer 565. The networks that computer 500 can interact with include, but are not limited to, LANs, WANs, and other networks.

[0108] Definitions and Other Embodiments In another embodiment, the described method and / or equivalent thereof may be carried out using computer-executable instructions. Thus, in one embodiment, a non-temporary computer-readable / storage medium, when executed by a machine, is configured with stored computer-executable instructions of an algorithm / executable application that causes the machine (and / or associated components) to carry out the method. Exemplary machines include, but are not limited to, processors, computers, servers operating within a cloud computing system, servers configured in a software-as-a-service (SaaS) architecture, smartphones, and the like. In one embodiment, a computing device is carried out using one or more executable algorithms configured to perform any of the disclosed methods.

[0109] In one or more embodiments, the disclosed method or its equivalents are executed by either computer hardware configured to perform the method, or by computer instructions embodied in modules stored in a non-temporary computer-readable medium, the instructions being configured, at least, as executable algorithms configured to perform the method when executed by the processor of a computing device.

[0110] For the sake of brevity, the methods shown in the diagrams are illustrated and described as a series of blocks of algorithms, but it should be understood that the methods are not limited by the order of the blocks. Some blocks may be performed in a different order than those illustrated and described, and / or simultaneously with other blocks. Furthermore, the number of blocks used to implement the exemplary methods may be fewer than all the blocks illustrated. Blocks may be combined or separated into multiple actions / components. In addition, additional and / or alternative methods may utilize additional actions not shown in the blocks.

[0111] The following includes definitions of optional terms used herein. The definitions include various examples and / or forms of components that fall within the scope of the terms and can be used for embodiments. The examples are not intended to be limiting. Both singular and plural forms of terms may exist within the definitions.

[0112] References to “one embodiment,” “one example,” “one instance,” etc., indicate that the embodiments or examples described in that way may include certain features, structures, characteristics, properties, elements, or limitations, but not all embodiments or examples necessarily include those specific features, structures, characteristics, properties, elements, or limitations. Furthermore, when the phrase “in one embodiment” is used repeatedly, it does not necessarily refer to the same embodiment, although it may.

[0113] When used herein, "data structure" refers to an organization of data within a computing system stored in memory, a storage device, or other computerized system. A data structure may be, for example, any one of the following: a data field, a data file, a data array, a data record, a database, a data table, a graph, a tree, a linked list, etc. A data structure may be formed from and include many other data structures (for example, a database contains many data records). Other examples of data structures are possible according to other embodiments.

[0114] When used herein, “computer-readable medium” or “computer storage medium” refers to a non-temporary medium that stores instructions and / or data configured to perform one or more of the disclosed functions at runtime. In some embodiments, the data may function as instructions. Computer-readable medium can take forms including, but are not limited to, non-volatile and volatile media. Non-volatile media may include, for example, optical discs, magnetic discs, etc. Volatile media may include, for example, semiconductor memory, dynamic memory, etc. Common forms of computer-readable medium may include, but are not limited to, floppy disks, flexible disks, hard disks, magnetic tapes, other magnetic media, application-specific integrated circuits (ASICs), programmable logic devices, compact disks (CDs), other optical media, random-access memory (RAM), read-only memory (ROM), memory chips or cards, memory sticks, solid-state storage devices (SSDs), flash drives, and other media on which a computer, processor, or other electronic device can function together. Each type of medium may, when selected for implementation in one embodiment, contain stored instructions for an algorithm configured to perform one or more of the disclosed and / or claimed functions.

[0115] When used herein, “logic” refers to a component implemented using a computer or electrical hardware, an executable application or program module instruction storage medium, and / or a combination thereof, for the purpose of performing any of the functions or actions disclosed herein, and / or causing a function or action from another logic, method, and / or system to be performed as disclosed herein. Equal logic can include firmware, a microprocessor programmed with an algorithm, a separate logic (e.g., an ASIC), at least one circuit, an analog circuit, a digital circuit, a programmed logic device, a memory device containing an algorithm instruction, and any of these can be configured to perform one or more of the disclosed functions. In one embodiment, logic can include one or more gates, combinations of gates, or other circuit components configured to perform one or more of the disclosed functions. Where multiple logics are described, it may be possible to combine multiple logics into one logic. Similarly, where a single logic is described, it may be possible to distribute that single logic among multiple logics. In one embodiment, one or more of these logics are corresponding structures associated with the implementation of the disclosed and / or claimed function. The choice of the type of logic to implement may be based on desired system conditions or specifications. For example, if higher speed is a consideration, hardware may be selected to implement the function. If lower cost is a consideration, stored instruction / executable applications may be selected to implement the function.

[0116] An "operable connection," or a connection to which an entity is "operable connected," is a connection to which signals, physical communications, and / or logical communications can be transmitted and / or received. An operable connection may include physical interfaces, electrical interfaces, and / or data interfaces. An operable connection may include different combinations of interfaces and / or connections sufficient to enable operable control. For example, two entities may be operable connected to communicate signals to each other directly or through one or more intermediate entities (e.g., a processor, operating system, logic, or non-transient computer-readable medium). Logic and / or physical communication channels can be used to create operable connections.

[0117] When used herein, "user" includes, but is not limited to, one or more persons, a computer or other device, or a combination thereof.

[0118] While the disclosed embodiments are described in considerable detail, the applicant does not intend to restrict or limit the scope of the appended claims in any way to such detail. Naturally, it is impossible to describe all possible combinations of components or methods for the purpose of illustrating various aspects of the subject matter. Therefore, this disclosure is not limited to the specific details or examples illustrated and described. Accordingly, this disclosure is intended to encompass alternative, modified, and variant forms that fall within the scope of the appended claims and their equivalents.

[0119] To the extent that the terms “include” or “contain” are used in the detailed description or claims, such terms are intended to be inclusive, similar to how the term “equip” is interpreted when used as a transitional term in the claims.

[0120] Where used in the detailed description or claims (e.g., A or B), the term “or” is intended to mean “A or B or both.” When the applicant intends to indicate “A or B only, but not both,” the phrase “A or B only, but not both” is used. Thus, the use of the term “or” in this specification is inclusive, not exclusive.

Claims

1. A method by which a computer performs an action. The voice server receives phone calls from users, This includes establishing an audio session for communication over an audio channel, wherein the live agent communicates an audio signal with the user over the audio channel. The aforementioned method, In response to identifying a problem from the user, the further includes sending a navigation link to a remote device associated with the user, the navigation link, when activated, navigating a browser on the remote device to a web page associated with the problem. The aforementioned method, In response to the user navigating to the web page via the navigation link, the web server establishes a web session including a web channel for communication between the remote device and the web page. In response to the establishment of the aforementioned web session, the call controller links the voice session associated with the user with the web session, The further includes launching a bot that operates with the aforementioned webpage and monitoring at least user actions on the webpage, wherein the bot communicates one or more user actions to the call controller. The aforementioned method, A method further comprising the call controller generating and transmitting audio signals to and from the user via the voice session based on at least one or more user actions from the web session, and simultaneously communicating digital data to the web page via the web session while the user is interacting with the web page.

2. Identifying the problem from the user and transmitting the navigation link are, The audio signal from the aforementioned audio session is analyzed using natural language processing to predict the problem from the user, Based on the predicted problem, the database is searched for one or more candidate navigation links associated with one or more web pages containing content to resolve the predicted problem. To generate and display the list of one or more candidate navigation links on the computing device associated with the live agent, In response to the live agent selecting a target navigation link from the list, the target navigation link is transmitted to the remote device associated with the user. The method according to claim 1, further comprising:

3. Analyzing the aforementioned audio signal means Converting the aforementioned audio signal into text data, To predict the problem from the user, extract content from the text data, At least based on the predicted problem, identify candidate forms associated with the predicted problem, Obtaining one or more candidate navigation links corresponding to each of the candidate forms, The method according to claim 2, further comprising:

4. The web page associated with the web session includes an interactive form, and the method is Receiving voice input from the user via the aforementioned voice session, Converting the aforementioned voice input into text input, The call controller transfers the text input from the voice session to the bot in the web session, The bot automatically inserts the text input into the data field within the interactive form, The method according to any one of claims 1 to 3, further comprising:

5. The aforementioned method, In response to the activation of the bot to work with the aforementioned webpage, the live agent is disconnected from the audio session while the audio session remains open for communication with the user. In response to a completion condition indicating that the user has completed interacting with the web page, the live agent is reconnected to the audio session with the user. The method according to any one of claims 1 to 4, further comprising:

6. The method according to any one of claims 1 to 5, wherein the navigation link includes pre-authentication of the user, and by pre-authentication, the web server can automatically authenticate the user and log in to the account assigned to the user.

7. The aforementioned method, Based on the monitoring of the user interaction by the bot, the bot detects hesitation in input from the user interaction and identifies the input field on the web page associated with the user interaction. The bot transmits the hesitation to input and the data associated with the input field to the call controller. The call controller generates and transmits an oral support message regarding the input field via the audio channel, The method according to any one of claims 1 to 6, further comprising:

8. One or more non-temporary computer-readable media storing computer-executable instructions, wherein the computer-executable instructions are configured to cause one or more computers to perform an operation including the operation described in any one of claims 1 to 7 when the computer-executable instructions are executed.

9. A computing system comprising one or more computers, wherein the computing system is configured by computer executable instructions to perform operations including the operations described in any one of claims 1 to 7.

10. A computer program product comprising a computer program, wherein, when the computer program is executed by at least the processor of a computer, the computer program causes the processor to perform an operation including the operation described in any one of claims 1 to 7.

11. A processor connected to at least one memory, The system comprises a non-temporary computer-readable medium containing stored instructions, and when the instructions are executed by the processor, the processor receives The server simultaneously establishes, via session connection, an audio channel established from a telephone call from a first user device associated with the user, and a web channel established from the browser of a second user device associated with the user navigating to a web page. A navigation link is sent to the second user device, and when activated, the navigation link navigates the browser to the web page. The user interaction on the web page is monitored via the aforementioned web channel. A computing system that generates an audio response via an audio channel based on the user interaction from the web channel in order to provide assistance to the user in relation to the content of the web page.

12. When the aforementioned instruction is executed by at least the processor, the processor will be instructed to: Connect the agent device associated with the live agent to the voice channel of the telephone call. In response to the connection of the audio channel and the web channel together, the agent device is disconnected from the audio channel. The computing system according to claim 11, further comprising an instruction to cause the agent device to reconnect to the voice channel with the user in response to a completion condition indicating that the user has completed interacting with the web page.

13. The instruction for connecting the audio channel from the first server to the web channel from the second server, once executed by the processor, causes the processor to: To identify the user and the corresponding audio session identifier associated with the audio channel, To identify the user and the web session identifier associated with the corresponding web channel, A computing system according to any one of claims 11 to 12, comprising an instruction for combining the voice session identifier and the web session identifier in a session connection that maps the voice session identifier and the web session identifier to each other.

14. When executed by at least the aforementioned processor, the aforementioned processor will The audio signal from the aforementioned audio channel is analyzed using natural language processing to predict the user's problem. Based on the predicted problem, the database is searched for one or more candidate navigation links associated with one or more web pages containing content to solve the predicted problem. A computing device associated with the live agent generates and displays the list of one or more candidate navigation links, and the computing device is connected to the voice channel with the user. The computing system according to any one of claims 11 to 13, further comprising an instruction to cause the live agent to transmit the target navigation link to the second user device associated with the user in response to the live agent selecting a target navigation link from the list.

15. When executed by at least the aforementioned processor, the aforementioned processor will The audio signal from the aforementioned audio channel is converted into text data. Identify multiple data components from the aforementioned text data, One or more of the aforementioned data components are associated with one or more associated input fields in an interactive form that are likely to correspond to the aforementioned one or more components. The computing system according to any one of claims 11 to 14, further comprising instructions for causing one or more components to be automatically entered into the associated input fields in the interactive form via the web channel.

Images