Systems and methods for conducting a live-agent conversation

Abstract

A method for conducting a live-agent conversation with a live consumer is disclosed. The method may include receiving a live conversation initialization request between a consumer device and a live-agent device, the consumer device being remotely located from the live-agent device; receiving from the consumer device, a user-initiated selection requesting to transfer the live conversation to an artificial intelligence (AI) chatbot; receiving, from the consumer device, a free-form natural language text query eliciting an AI generated response from the AI chatbot, the free-form natural language text query identifying a query context for the free-form natural language text query and a question for the AI chatbot; and determining a query response for the AI chatbot based at least in part on the query context and the question, wherein a content of the query response is determined based at least in part on the query context.

Description

TITLE: SYSTEMS AND METHODS FOR CONDUCTING A LIVE-AGENTCONVERSATIONFIELD

[0001] This application relates to the field of live-agent conversation systems and methods for conducting a live-agent conversation.INTRODUCTION

[0002] Customer service, including support and sales inquiries are typically addressed by human agents. For example, if a customer needs an answer to a query, the customer may contact a customer service or support agent via telephone or through a web-based or in-app chat. Conventional customer service is however resource and labor intensive, in addition to being inefficient.DRAWINGS

[0003] FIG. 1A is a block diagram of an example live-agent conversation system in communication with external components, in accordance with an embodiment;

[0004] FIG. 1 B is a block diagram of an example live-agent conversation system in communication with external components, in accordance with an embodiment;

[0005] FIG. 2 is a block diagram of an example consumer computing device, in accordance with an embodiment;

[0006] FIG. 3 is a flowchart of an example method for conducting a live-agent conversation with a live consumer, in accordance with an embodiment;

[0007] FIG. 4 is a flowchart of an example method for conducting a live-agent conversation with a live consumer, in accordance with an embodiment;

[0008] FIG. 5 is a flowchart of an example method for conducting a live-agent conversation with a live consumer, in accordance with an embodiment;

[0009] FIG. 6A is a screenshot of an example graphical user interface (GUI) of the example live-agent conversation system of FIGS. 1A and 1 B, in accordance with an embodiment;

[0010] FIG. 6B is another screenshot of an example graphical user interface (GUI) of the example live-agent conversation system of FIGS. 1A and 1 B, in accordance with an embodiment;

[0011] FIG. 60 is another screenshot of an example graphical user interface (GUI) of the example live-agent conversation system of FIGS. 1A and 1 B, in accordance with an embodiment;

[0012] FIG. 7 is another screenshot of an example graphical user interface (GUI) of the example live-agent conversation system of FIGS. 1A and 1 B, in accordance with an embodiment;

[0013] FIG. 8 is another screenshot of an example graphical user interface (GUI) of the example live-agent conversation system of FIGS. 1A and 1 B, in accordance with an embodiment;

[0014] FIG. 9 is another screenshot of an example graphical user interface (GUI) of the example live-agent conversation system of FIGS. 1A and 1 B, in accordance with an embodiment;

[0015] FIG. 10A is another screenshot of an example graphical user interface (GUI) of the example live-agent conversation system of FIGS. 1 A and 1 B, in accordance with an embodiment;

[0016] FIG. 10B is another screenshot of an example graphical user interface (GUI) of the example live-agent conversation system of FIGS. 1 A and 1 B, in accordance with an embodiment;

[0017] FIG. 11A is another screenshot of an example graphical user interface (GUI) of the example live-agent conversation system of FIGS. 1 A and 1 B, in accordance with an embodiment;

[0018] FIG. 11 B is another screenshot of an example graphical user interface (GUI) of the example live-agent conversation system of FIGS. 1 A and 1 B, in accordance with an embodiment; and

[0019] FIG. 12 is another screenshot of an example graphical user interface (GUI) of the example live-agent conversation system of FIGS. 1A and 1 B, in accordance with an embodiment.SUMMARY

[0020] The following is intended to introduce the reader to the detailed description that follows and not to define or limit the claimed subject matter.

[0021] In one aspect, a method is provided for conducting a live-agent conversation with a live consumer. The method may include one or more of the following steps: receiving a live conversation initialization request between a consumer device and a live-agent device, the consumer device being remotely located from the live-agent device; receiving from the consumer device, a user-initiated selection requesting to transfer the live conversation to an artificial intelligence (Al) chatbot; receiving, from the consumer device, a free-form natural language text query eliciting an Al generated response from the Al chatbot, the free-form natural language text query identifying a query context for the free-form natural language text query and a question for the Al chatbot; and determining a query response for the Al chatbot based at least in part on the query context and the question, wherein a content of the query response is determined based at least in part on the query context.

[0022] In another aspect, a system for conducting a live-agent conversation with a live consumer is provided. The system may include at least one processor and a memory storing computer readable instructions that when executed configure the at least one processor to collectively perform one or more of the following steps: receive a live conversation initialization request between a consumer device and a live-agent device, the consumer device being remotely located from the live-agent device;receive from the consumer device, a user-initiated selection requesting to transfer the live conversation to an artificial intelligence (Al) chatbot; receive, from the consumer device, a free-form natural language text query eliciting an Al generated response from the Al chatbot, the free-form natural language text query identifying a query context for the free-form natural language text query and a question for the Al chatbot; and determine a query response for the Al chatbot based at least in part on the query context and the question, wherein a content of the query response is determined based at least in part on the query context.

[0023] In another aspect, a method for conducting a live-agent conversation with a consumer is provided. The method may include one or more of the following steps: receiving a first live conversation initialization request between a consumer device and a first live-agent device, the consumer device being remotely located relative to the live-agent device; exchanging messages in a first live-agent conversation between the consumer device and the live-agent device; determining, from the first live-agent conversation, a query context; storing the determined query context in a memory in association with the consumer device or a consumer identifier associated with the consumer; receiving a second live conversation initialization request between the consumer device and a second live-agent device; receiving from the consumer device, a user-initiated selection requesting to transfer the live-agent conversation to an artificial intelligence (Al) chatbot; receiving, from the consumer device, a free-form natural language text query eliciting an Al generated response from the Al chatbot, the free-form natural language text query comprising a question; anddetermining a query response for the Al chatbot based at least in part on the stored query context and the question, wherein a content of the query response is determined based at least in part on the query context.

[0024] In another aspect, a method for conducting a live-agent conversation with a consumer is provided. The method may include one or more of the following steps: receiving a live conversation initialization request between a consumer device and a live-agent device, the consumer device being remotely located from the live-agent device; receiving from one device which is either the consumer device or the live-agent device, a user-initiated selection requesting to transfer the live conversation to an artificial intelligence (Al) chatbot; initializing a private conversation between the one device and the Al chatbot; receiving in the private conversation, from the one device, a free-form natural language text query eliciting an Al generated response from the Al chatbot, the freeform natural language text query identifying a query context for the free-form natural language text query and a question for the Al chatbot; determining a private query response for the Al chatbot based at least in part on the query context and the question, wherein a content of the query response is determined based at least in part on the query context; and privately transmitting the private query response to the one device; exchanging private messages, in the private conversation, between the one device and the Al chatbot; determining a shared response for the Al chatbot, wherein a content of the shared response is determined based at least in part on the private query response and the private messages; and transmitting, to the consumer device and the live-agent device the shared response.DESCRIPTION OF VARIOUS EMBODIMENTS

[0025] Numerous embodiments are described in this application, and are presented for illustrative purposes only. The described embodiments are not intended to be limiting in any sense. The invention is widely applicable to numerous embodiments, as is readily apparent from the disclosure herein. Those skilled in the art will recognize that the present invention may be practiced with modification and alteration without departing from the teachings disclosed herein. Although particular features of the present invention may be described with reference to one or more particular embodiments or figures, it should be understood that such features are not limited to usage in the one or more particular embodiments or figures with reference to which they are described.

[0026] The terms "an embodiment," "embodiment," "embodiments," "the embodiment," "the embodiments," "one or more embodiments," "some embodiments," and "one embodiment" mean "one or more (but not all) embodiments of the present invention(s)," unless expressly specified otherwise.

[0027] The terms "including," "comprising" and variations thereof mean "including but not limited to," unless expressly specified otherwise. A listing of items does not imply that any or all of the items are mutually exclusive, unless expressly specified otherwise. The terms "a," "an" and "the" mean "one or more," unless expressly specified otherwise.

[0028] As used herein and in the claims, two or more parts are said to be “coupled”, “connected”, “attached”, “joined”, “affixed”, or “fastened” where the parts are joined or operate together either directly or indirectly (i.e. , through one or more intermediate parts), so long as a link occurs. As used herein and in the claims, two or more parts are said to be “directly coupled”, “directly connected”, “directly attached”, “directly joined”, “directly affixed”, or “directly fastened” where the parts are connected in physical contact with each other. As used herein, two or more parts are said to be “rigidly coupled”, “rigidly connected”, “rigidly attached”, “rigidly joined”, “rigidly affixed”, or “rigidly fastened” where the parts are coupled so as to move as one while maintaining a constant orientation relative to each other. None of the terms “coupled”, “connected”, “attached”, “joined”, “affixed”, and “fastened” distinguish the manner in which two or more parts are joined together.

[0029] Further, although method steps may be described (in the disclosure and I or in the claims) in a sequential order, such methods may be configured to work in alternate orders. In other words, any sequence or order of steps that may be described does not necessarily indicate a requirement that the steps be performed in that order. The steps of methods described herein may be performed in any order that is practical. Further, some steps may be performed simultaneously.

[0030] As used herein and in the claims, a first element is said to be ‘communicatively coupled to’ or ‘communicatively connected to’ or ‘connected in communication with’ a second element where the first element is configured to send or receive electronic signals (e.g. data) to or from the second element, and the second element is configured to receive or send the electronic signals from or to the first element. The communication may be wired (e.g. the first and second elements are connected by one or more data cables), or wireless (e.g. at least one of the first and second elements has a wireless transmitter, and at least the other of the first and second elements has a wireless receiver). The electronic signals may be analog or digital. The communication may be one-way or two-way. In some cases, the communication may conform to one or more standard protocols (e.g. SPI, l2C, Bluetooth™, or IEEE™ 802.11 ).

[0031] As used herein and in the claims, a group of elements are said to ‘collectively’ perform an act where that act is performed by any one of the elements in the group, or performed cooperatively by two or more (or all) elements in the group.

[0032] Some elements herein may be identified by a part number, which is composed of a base number followed by an alphabetical or subscript-numerical suffix (e.g. 112a, or 112i). Multiple elements herein may be identified by part numbers that share a base number in common and that differ by their suffixes (e.g. 112i, 1122, and 112s). All elements with a common base number may be referred to collectively or generically using the base number without a suffix (e.g. 112).

[0033] Typically, customer service inquiries, including customer support inquiries and sales inquiries, are serviced by live, human agents (e.g., customer service representatives, personal assistants). Traditional customer service is, however, resourceintensive and inefficient since it requires employing and training live-agents. In addition,these live-agents are also often tasked with responding to the same or similar inquiries. Wait times associated with traditional customer service is also often long due to the limited number of live-agents.

[0034] Chatbots have been developed and used in various customer service applications to support live-agents. These chatbots are typically used in combination with live-agents to manage and balance the workload of live-agents and to respond to simple and / or frequently asked questions. When a chatbot is unable to respond to a consumer query due to its complexity, the chatbot typically refers the query to a live-agent who can then address the query in real-time, or generates a customer service ticket so that a live- agent can review and respond to the query at a later time.

[0035] Conventional systems that involve chatbots, however, typically either only allow the consumer to interact with a live-agent after conversing with the chatbot or do not allow the consumer to interact with a live-agent in real-time. In many cases, the consumer may be required to interact with a chatbot to access a live-agent, despite being aware that the chatbot cannot address the consumer’s query due to its complexity.

[0036] The described embodiments involve conducting a live-agent conversation with a consumer and transferring the conversation to an artificial intelligence (Al) chatbot in response to a user-initiated selection. An Al chatbot is a chatbot (i.e. a software application that can interact with human users through, e.g. text or voice interactions, and that can simulate a human conversation) that is trained using machine-learning algorithms to respond to open-ended questions, that may use one or various data sources to provide a response to a consumer query and that can learn from (or has been trained from) interactions with consumers to improve its responses. An Al chatbot can be built using large language models (LLMs), i.e., computational models that use deep learning techniques and large data sets to predict and generate natural language text. Unlike existing systems, the described embodiments involve the consumer initiating the transfer of a live conversation with a live-agent to a chatbot, rather than a chatbot transferring a conversation to a live-agent or a live-agent initiating the transfer. By enabling the consumer to initiate the transfer of a live conversation to a chatbot, the describedembodiments can allow queries the consumer thinks are best handled by the chatbot to be addressed more efficiently, more promptly, and / or more privately.

[0037] The live-agent conversations described herein can be any type of conversation that involves a question from a consumer and that involves a live-agent. For example, the live-agent conversation can include but is not limited to a customer service interaction, including a customer support interaction or a personal assistance interaction. A consumer can be any individual who is seeking a response to a question. For example, the consumer can be a customer of a business or other organized entity, or any individual consuming information.

[0038] The described embodiments also involve a chatbot determining a response to a natural language text query received from a consumer device based in at least in part on the query context of the text query.

[0039] At least some of the embodiments described herein involve determining the query context of a text query based on the live conversation between the consumer and the live-agent prior to the live conversation being transferred to the Al chatbot. For example, the live conversation between the consumer and the live-agent may involve a context that may be automatically determined by the Al chatbot when the conversation is transferred to the chatbot.

[0040] At least some of the embodiments described herein involve determining the query context of a text query based on at least one previous conversation with the consumer. For example, during a first live conversation facilitated by the embodiments described herein, the consumer may specify a query context for the live conversation and / or a query context for the live conversation may be determined. The query context may be saved for future retrieval. When the consumer engages in a subsequent live conversation, the query context may be retrieved instead of being determined again.

[0041] When compared to existing systems and methods, the described embodiments can determine query responses for a text query in a more efficient manner. When the context of a query can be determined from a previous conversation or from the conversation between the consumer and the live-agent before the conversation is transferred to the Al chatbot, the embodiments described herein can enable the Alchatbot to more efficiently respond to queries from the consumer, particularly when the queries omit the context necessary to respond to the question, since the chatbot can avoid generating follow-up questions to establish the context of the consumer’s queries. By reducing the number of follow-up questions that need to be generated and transmitted to the consumer, the embodiments described herein can save computational resources associated with generating messages and save network resources associated with transmitting messages to a consumer device of the consumer, in addition to reducing the time needed for a consumer to receive a response to their query. The embodiments described herein can also reduce the computational load of the consumer device, since the consumer device can transmit fewer messages in response to follow-up questions.

[0042] Referring first to FIG. 1 A, there is shown a block diagram 100a that includes a live-agent conversation system 110 in communication with a remote data storage 102, a consumer device 106 and a live-agent device 108 via a network 104. Although only one consumer device 106 is shown in FIG. 1A, the live-agent conversation system 110 can be in communication with a greater number of consumer devices 106. Similarly, though only one live-agent device 108 is shown in FIG. 1A, the live-agent conversation system 110 can be in communication with a greater number of live-agent devices 108. Further, although the live-agent device 108 is shown as being in communication with the live- agent conversation system 110 via the network 104, in some embodiments, the live-agent device 108 is in direct communication with the live-agent conversation system 110.

[0043] The live-agent conversation system 110 can communicate with the computing device(s) 106 and the live-agent device(s) 108 over a wide geographic area via the network 104.

[0044] The live-agent conversation system 110 includes at least a processor 112, storage 114 and a communication component 116. The live-agent conversation system 110 can be implemented with more than one computer server distributed over a wide geographic area and connected via the network 104. The processor 112, storage 114 and the communication component 116 may be combined into a fewer number of components or may be separated into further components.

[0045] The processor 112 can be implemented with any suitable processor, controller, digital signal processor, graphics processing unit, application specific integrated circuits (ASICs), and / or field programmable gate arrays (FPGAs) that can provide sufficient processing power for the configuration, purposes and requirements of live-agent conversation system 110. The processor 112 can include more than one processor with each processor being configured to perform different dedicated tasks.

[0046] The communication component 116 can include any interface that enables the live-agent conversation system 110 to communicate with various devices and other systems. For example, the communication component 116 can receive inputs (e.g., freeform natural language text, user-initiated selections) from the consumer device 106 and / or the live-agent device 108 and store the inputs in storage 114 and / or remote data storage 102. The processor 112 can then process the inputs according to the methods described herein.

[0047] The communication component 116 can include an interface to component via one or more of an Internet, Local Area Network (LAN), Ethernet, Firewire, modem, fiber, or digital subscriber line connection. Various combinations of these elements may be incorporated within the communication component 116. The communication component 116 can enable the live-agent conversation system 110 to communicate with the consumer device 106, the live-agent device 108 and the remote data storage 102 via the network.

[0048] Storage 114 can include RAM, ROM, one or more hard drives, one or more flash drives or some other suitable non-volatile data storage elements (e.g. computer readable mediums) such as disk drives. Storage 114 can store software modules including computer executable instructions to perform processing for the functions and methods described below. Storage 114 can also include one or more databases for storing inputs received from the consumer device 106 and / or the live-agent device 108, query contexts determined by the live-agent conversation system 110, transcripts of live conversations, summaries of live conversations, and any other information related to live conversations conducted by the live-agent conversation system 110.

[0049] Storage 114 can store the Al chatbot and / or algorithms for constructing the chatbot.

[0050] Alternatively, in some embodiments, as shown in FIG. 1 B which shows another block diagram 100b that includes a live-agent conversation system 110 in communication with the remote data storage 102, the consumer device 106, the live- agent device 108 and a remote system 118 via a network 104, the remote system 118 can store and execute an Al chatbot 120 and the remote system 118 can communicate with the live-agent conversation system 110 via the network 104 to transmit and receive messages.

[0051] The remote data storage 102 can store data similar to that of the storage 114. The remote data storage 102 can, in some embodiments, be used to store data that is less frequently used and / or older data. In some embodiments, the remote data storage 102 can be a third-party data storage that stores past live-agent conversations. In some embodiments, the remote data storage 102 is a cloud storage. The data stored in the remote data storage 102 can be retrieved by the live-agent conversation system 110 via the network 104. In some embodiments, the live-agent conversation system 110 only stores and retrieves data stored in the storage 114 and the live-agent conversation system 110 is not communication with a remote data storage 102.

[0052] The consumer device 106 can include any device capable of receiving inputs from a consumer and communicating with the live-agent conversation system 110 through a network such as the network 104 via a wired or wireless connection. A consumer can be any human individual that uses the live-agent conversation system 110 to obtain information (e.g., responses to queries).

[0053] The consumer device 106 can include a processor and memory, and may be an electronic tablet device, a personal computer, workstation, server, portable computer, mobile device, personal digital assistant, laptop, smart phone, an interactive television, video display terminals, gaming consoles, and portable electronic devices, any combination of these or any other device that can receive inputs from a consumer and that includes a display for displaying visual information to the consumer.

[0054] The live-agent device 108 can include any device capable of receiving inputs from a live-agent and communicating with the live-agent conversation system 110 through a network such as the network 104 via a wired or wireless connection. The live agent can be a human individual that can interact with consumers via the live-agent conversation system 110 to answer queries in real-time (e.g., a customer service representative). The live agent can be employed by a corporation or other organized entity (e.g. social club, government department) that uses the live-agent conversation system 110.

[0055] The live-agent device 108 can include a processor and memory, and may be an electronic tablet device, a personal computer, workstation, server, portable computer, mobile device, personal digital assistant, laptop, smart phone, an interactive television, video display terminals, gaming consoles, and portable electronic devices, any combination of these or any other device that can receive inputs from a live-agent and that includes a display for displaying visual information to the live-agent. The live-agent device 108 can be remotely located from the consumer device 106.

[0056] The network 104 can include any network capable of carrying data, including the Internet, Ethernet, plain old telephone service (POTS) line, public switch telephone network (PSTN), integrated services digital network (ISDN), digital subscriber line (DSL), coaxial cable, fiber optics, satellite, mobile, wireless (e.g. Wi-Fi, WiMAX), SS7 signaling network, fixed line, local area network, wide area network, and others, including any combination of these, capable of interfacing with, and enabling communication between, the live-agent conversation system 110, the remote data storage 102, the consumer device 106 and the live-agent device 108.

[0057] Referring next to FIG. 2, FIG. 2 shows an example schematic of a device 200. Device 200 can correspond to consumer device 106, live conversation system 110, and / or remote system 118 shown in FIGS. 1A and 1 B. Generally, device 200 can be an electronic tablet device, a personal computer, workstation, server, portable computer, mobile device, personal digital assistant, laptop, smart phone, an interactive television, video display terminals, gaming consoles, portable electronic devices or another computing device. Device 200 includes a connection with a network 104 such as a wiredor wireless connection to the Internet or to a private network. In some cases, network 218 includes other types of computer or telecommunication networks. Network 218 may correspond with network 104 shown in FIGS. 1A and 1 B.

[0058] In the example shown, device 200 includes a memory 202, an application 204, an output device 206, a display device 208, a secondary storage device 210, a processor 212, and an input device 214. In some embodiments, device 200 includes multiple of any one or more of memory 202, application 204, output device 206, display device 208, secondary storage device 210, processor 212, and input device 214. In some embodiments, device 200 does not include one or more of applications 204, second storage devices 210, network connections, input devices 214, output devices 206, and display devices 208.

[0059] Memory 202 can include random access memory (RAM) or similar types of memory. Also, in some embodiments, memory 202 stores one or more applications 204 for execution by processor 212. Applications 204 correspond with software modules including computer executable instructions to perform processing for the functions and methods described below. Secondary storage device 210 can include a hard disk drive, floppy disk drive, CD drive, DVD drive, Blu-ray drive, solid state drive, flash memory or other types of non-volatile data storage.

[0060] In some embodiments, device 200 stores information in a remote storage device, such as cloud storage, accessible across a network, such as network 216 or another network. In some embodiments, device 200 stores information distributed across multiple storage devices, such as memory 202 and secondary storage device 210 (i.e. each of the multiple storage devices stores a portion of the information and collectively the multiple storage devices store all of the information). Accordingly, storing data on a storage device as used herein and in the claims, means storing that data in a local storage device, storing that data in a remote storage device, or storing that data distributed across multiple storage devices, each of which can be local or remote.

[0061] Generally, processor 212 can execute applications, computer readable instructions or programs. The applications, computer readable instructions or programs can be stored in memory 202 or in secondary storage 210, or can be received from remotestorage accessible through network 216, for example. When executed, the applications, computer readable instructions or programs can configure the processor 212 (or multiple processors 212, collectively) to perform the acts described herein with reference to game server 102, client device 104 or content server 106, for example.

[0062] Input device 214 can include any device for entering information into device 200. For example, input device 214 can be a keyboard, key pad, cursor-control device, touch-screen, camera, or microphone. Input device 214 can also include input ports and wireless radios (e.g. Bluetooth®, or 802.11x) for making wired and wireless connections to external devices.

[0063] Display device 208 can include any type of device for presenting visual information such as a live conversation. For example, display device 208 can be a computer monitor, a flat-screen display, a projector or a display panel.

[0064] Output device 206 can include any type of device for presenting a hard copy of information, such as a printer for example. Output device 206 can also include other types of output devices such as speakers, for example. In at least one embodiment, output device 206 includes one or more of output ports and wireless radios (e.g. Bluetooth®, or 802.11x) for making wired and wireless connections to external devices.

[0065] FIG. 2 illustrates one example hardware schematic of a device 200. In alternative embodiments, device 200 contains fewer, additional or different components. In addition, although aspects of an implementation of device 200 are described as being stored in memory, one skilled in the art will appreciate that these aspects can also be stored on or read from other types of computer program products or computer-readable media, such as secondary storage devices, including hard disks, floppy disks, CDs, or DVDs; a carrier wave from the Internet or other network; or other forms of RAM or ROM.

[0066] Referring next to FIG. 3, FIG. 3 shows a flowchart illustrating a method 300 of conducting a live-agent conversation with a live consumer, in accordance with at least one embodiment. Method 300 can be implemented by the live-agent conversation system 110. The flowchart shown in FIG. 3 illustrates the steps of method 300 organized in a particular order. However, method 300 is not limited to the steps ordered as shown, andin some embodiments of method 300 some steps are practiced in a different order and some steps are practiced simultaneously.

[0067] At 310, the live-agent conversation system 110 receives a live conversation initialization request to initialize a live conversation between the consumer device 106 and the live-agent device 108. A live conversation can be characterized by messages being exchanged in real time.

[0068] The live conversation initialization request can be received from the consumer device 106 and can be initiated by the consumer through an interaction with the graphical user interface (GUI) of the consumer device 106. For example, the consumer may click on a button displayed on the GUI, which can launch a live conversation window, which can, in turn, cause the live conversation initialization request to be generated. As another example, the live conversation initialization request can be generated when the consumer device 106 transmits a message, for example, when the consumer types a message in the live conversation window. The live conversation can be an in-app conversation, a text message conversation, a telephone conversation or a video conversation.

[0069] The live-agent conversation system 110 can initialize a live conversation between the consumer device 106 and any available live-agent device 108 or a specific live-agent device 108. For example, as explained, the live-agent conversation device system 110 can be in communication with a number of live-agent devices 108. The live- agent conversation system 110 can initialize the live conversation with any live-agent device 108 in communication with the live-agent conversation device system 110, a live- agent device 108 not currently engaged in another live-agent conversation or engaged in the lowest number of live-agent conversations, or the live-agent device 108 associated with the lowest wait time.

[0070] In some embodiments, the live-agent conversation system 110 preferentially initiates the live conversation with a live-agent device 108 associated with a live-agent who has previously interacted with the consumer associated with the consumer device 106.

[0071] Once the live conversation is initialized between the consumer device 106 and the live-agent device 108, the consumer may interact with the live agent and exchange messages with the live-agent. That is, the consumer may interact with consumer device 106 to compose consumer message(s) (e.g. voice and / or text) that consumer device 106 transmits to live-agent device 108. The live-agent may review the consumer message(s) and similarly use live-agent device 108 to compose live-agent message(s) in reply that live-agent device 108 transmits to consumer device 106. Screenshot 600A of FIG. 6A shows an example GUI showing a live conversation window through which messages can be exchanged.

[0072] At 320, the live-agent conversation system 110 receives, from the consumer device 106 a request to transfer the conversation initialized at 310 to an artificial intelligence (Al) chatbot. For example, a consumer may wish to transfer the conversation to an Al chatbot when the consumer thinks that a response to their query can be obtained from an Al chatbot. As another example, a consumer may wish to transfer the conversation to an Al chatbot when the live-agent response time is likely to be long. For example, an estimated response time or wait time may be displayed on the GUI. The GUI can be displayed on the display device 208.

[0073] The request can be a user-initiated selection requesting to transfer the conversation. For example, the consumer can initiate the request to transfer the conversation by selecting (e.g. finger-tapping or mouse-clicking) an interactable GUI element (e.g. button), such as button 620 shown in the screenshots 600B, 600C of FIGS. 6B-6C, which show the button 620 before the button is pressed and after the button 620 is pressed, respectively. An indication that the live conversation has been transferred to the chatbot can be displayed on the GUI. For example, the consumer may use the input device 214 to select the interactable GUI element.

[0074] Transferring the conversation can involve rerouting the live conversation to the Al chatbot. The consumer device 106 may display an indication that the live-agent has been removed from the conversation and that the Al chatbot has joined the live conversation. For example, as shown in FIG. 7, which shows a screenshot 700 of the GUI of the live-agent conversation system 110, a conversation visibility indicator 740indicating that the live-agent cannot view the conversation can be displayed. The live- agent device 108 may receive an indication that the conversation has been transferred to an Al chatbot. For example, the live-agent conversation system 110 can display, in the live conversation window an indication viewable by the live-agent that the conversation has been transferred to an Al chatbot.

[0075] In at least one embodiment, transferring the conversation involves initiating a new, separate conversation with the Al chatbot, for example, in a separate window with or without terminating the conversation with the live-agent. In such cases, the contents of the live conversation and / or a summary of the contents of the live conversation can be transmitted to the Al chatbot so that the Al chatbot can interact with the consumer device 106 based in part on the previous messages exchanged between the consumer device 106 and the live-agent device 108.

[0076] In some embodiments, upon receiving a user-initiated selection requesting to transfer the conversation to the Al chatbot, the live-agent conversation system 110 adds the Al chatbot to the live-agent conversation initialized between the consumer device 106 and the live-agent device 108 as a third participant and the live-agent device 108 can remain in the live-conversation, for example, as an active participant (capable of sending messages to the conversion) or an inactive participant (incapable of sending messages to the conversation but still receiving messages sent by the consumer and the chatbot to the conversation). For example, the conversation between the consumer and the Al chatbot can be displayed in the same live conversation window as the live conversation window between the consumer and the live-agent. Screenshot 1200 of FIG. 12, for example, shows the GUI of an embodiment wherein the Al chatbot is added as a third participant in a live conversation between a consumer, “Damien Foxgrove” and a live-agent “James London”. In screenshot 1200, the live-agent device 108 remains in the live-conversation as an active participant.

[0077] In at least some embodiments where the Al chatbot is added as a third participant and the live-agent device remains in the live-conversation as an active participant, both the consumer and the live-agent device can interact with the Al chatbot.

[0078] In some embodiments where the Al chatbot is added to the live-agent conversation as a third participant, the live-agent conversation system 110 can initialize a separate, private conversation between the consumer device 106 and the Al chatbot without interrupting the live-conversation between the consumer device 106 and the live- agent device 108. The separate, private conversation can enable the consumer device 106 to exchange messages with the Al chatbot without the messages being transmitted to the live-agent device 108. For example, in embodiments where the live-agent conversation system 110 is used to facilitate sales, the consumer may wish to first obtain information about different products available for sale and exchange messages with the Al chatbot to obtain this information before engaging with the live-agent to place an order, or negotiate an order. As another example, when the live-agent response time to a query is likely to be long, the consumer may wish to first obtain responses to related queries that can be addressed by the Al chatbot while waiting for a live-agent response.

[0079] The private conversation can be displayed in the same live conversation window as the live conversation window displaying the live conversation between the consumer and the live-agent. However, the live-agent conversation system 110 may cause the private conversation to only be viewable by the consumer. For example, the live conversation window displayed to the consumer may include the private conversation between the consumer and the live-agent while the live conversation window displayed to the live-agent may not only include the conversation between the consumer and the Al chatbot. By not displaying the private conversation between the consumer and the Al chatbot, the live-agent conversation system 110 can avoid displaying information that is not required for the live-agent to converse with the consumer and / or that may not be relevant to the live-agent.

[0080] An indication that the conversation has been transferred to an Al chatbot can be displayed. For example, as shown in FIG. 7 and FIG. 10A, an Al chatbot recipient indicator 730 can be displayed with each message sent to the Al chatbot or the first message sent to the Al chatbot. In some embodiments where the Al chatbot is added to the live-agent conversation as a third participant, the Al chatbot recipient indicator 730 can be displayed so that it is visible to both the consumer and the live-agent. Screenshots 1000A and 1000B, which show the GUI showing the conversation from the perspectiveof the live-agent and from the perspective of the consumer, respectively, show the recipient indicator 730 indicating that the conversation has been transferred to an Al chatbot by the live-agent device 730.

[0081] In some embodiments, the live-agent conversation system 110 can recommend that the conversation be transferred to an Al chatbot, for example, based on the contents of the conversation. For example, the live-agent conversation system 110 can parse the conversation and based on the contents of the conversation, can determine that an Al chatbot is suited for conversing with the consumer and recommend that the conversation be transferred to the Al chatbot. As another example, the live-agent can determine that an Al chatbot is suited for conversing with the consumer. In such embodiments, the live-agent conversation system 110 can cause a recommendation to transfer the conversation to be displayed on the GUI of the consumer device 106 and the consumer can opt to transfer the conversation to an Al chatbot. As a further example, the live-agent conversation system 110 can determine that the wait time for the live-agent to respond to the consumer is expected to be high and exceeds a predetermined acceptable wait time threshold, based on the live-agent device’s 108 interactions with the live-agent conversation system 110 and recommend that the conversation be transferred to an Al chatbot instead. The wait time can be displayed on the GUI of the consumer device 106. By transferring the live conversation to an Al chatbot, the consumer may receive a response to their query more rapidly than if the consumer waits for a response from the live-agent, reducing the consumer device’s 106 and the live-agent conversation system’s 110 idle time.

[0082] At 330, the live-agent conversation system 110 receives a free-form natural language text query from the consumer device 106. The free-form natural language text query can identify a query context for the query and a question for the Al chatbot (i.e. the query context and question can be determined from the free-form natural language text query) and can elicit an Al generated response from the Al chatbot. The free-form natural language text query can be a query that is received at the GUI of the consumer device 106 and inputted by the consumer by typing the query on a keyboard (e.g. word by word) or inputted by the consumer using voice-to-text , for example using input device 214, and can correspond to a query for which the consumer desires a response.

[0083] The query context can include any relevant information that can assist the Al chatbot in responding to the question, including information used for establishing the meaning of the question or for establishing the circumstances in which the question is posed. For example, the query context can identify a field, a subject area or subject matter, or a scope of the question.

[0084] For example, the query context of a text query requesting instructions for performing an oil change on a vehicle, can include the make and model of the vehicle (e.g. 2024 Honda Civic). As another example, the query context of a text query including a question about resolving a mobile device glitch can include the model of the mobile device (e.g. Apple™ iPhone™ 16) and the operating system version of the mobile device (e.g. iOS™ 18.1 ). As a further example, the query context of a text query including a request to purchase a part for a dishwasher can include the brand and model number of the dishwasher (e.g., LG™ LDPN454HT).

[0085] In some embodiments where the live-agent conversation system 110 can recommend that the live-conversation be transferred to an Al chatbot, the live-agent conversation system 110 can parse the free-form natural language text query and based on the contents of the free-form natural language text query, the live-agent conversation system 110 can recommend that the conversation be transferred to an Al chatbot.

[0086] At 340, the live-agent conversation system 110 determines a query response for the Al chatbot based in part on the query context and the question, as shown in screenshot 800 of FIG.8, which shows query response 842. The content (i.e., substance) of the query response is determined based at least in part on the query context.

[0087] For example, the query response to a text query requesting instructions for performing maintenance on a vehicle can include a step-by-step guide for performing an oil change on the vehicle, taking into account the specificities of the make and model of the vehicle (i.e. the query context). For example, depending on the make and model of the vehicle, the location of the hood release lever, the type of engine oil required and the location of the engine oil tank may vary.

[0088] In some embodiments, the query response can include a source citation for the query response and in some cases a link to the source of information. For example, as shown in screenshot 900 of FIG. 9, if the text query involves a question about installing a part of a machine, the query response can include a response to the question and a reference to the relevant section of the installation manual and a link 944 to the installation manual.

[0089] In embodiments where the Al chatbot is stored and executed by a remote system 118, the Al chatbot determines a query response based in part on the query context and the question and the remote system 118 transmits the query response to the live-agent conversation system 110.

[0090] In at least some embodiments where the Al chatbot is added to the live- agent conversation as a third participant and the live-agent conversation system 110 initializes a separate, private conversation between the consumer device 106 and the Al chatbot, the live-agent conversation system 110 can display the query response of the Al chatbot in the live conversation window so that the query response is visible to the live- agent. Referring next to FIG. 4, shown therein is a flowchart illustrating a method 400 of conducting a live-agent conversation with a consumer, in accordance with another embodiment. Method 400 can be substantially similar to method 300. However, method 400 involves determining the query context for the question from a previous live-agent conversation.

[0091] At 410, the live-agent conversation system 110 receives a first live conversation initialization request to initialize a first live conversation between the consumer device 106 and the live-agent device 108. Step 410 can be substantially similar to step 310.

[0092] At 420, the live-agent conversation system 110 facilitates the exchange of messages between the consumer device 106 and the live-agent device 108 in a first live- agent conversation. For example, the consumer and the live agent can communicate with one another via free-form natural language text messages in a live conversation window.

[0093] At 430, the live-agent conversation system 110 determines a query context from the first live-agent conversation. For example, the live-agent conversation system110 can parse the messages exchanged between the consumer device 106 and the live- agent device 108 to determine the query context.

[0094] At 440, the live-agent conversation system 110 stores the query context determined at 430 in memory in association with the consumer device 106 and / or the consumer (e.g., with a consumer device identifier associated with the consumer device 106, with a consumer identifier associated with the consumer) . For example, the live- agent conversation system 110 can store the query context in the storage 114 or the remote data storage 102. As explained, the live-agent conversation system 110 can conduct live-agent conversations with a number of different consumer devices 106. Accordingly, the live-agent conversation system 110 can store the determined query context in association with the consumer device 106 (e.g. , in association with a consumer device identifier) and / or in association with a consumer identifier (e.g. consumer username, consumer account) so that when the live-agent conversation system 110 receives a subsequent live conversation initialization request from the consumer device 106 (or in association with the consumer identifier), the live-agent conversation system 110 can retrieve the query context associated with that particular consumer device 106 (or consumer identifier). A consumer identifier can be a unique identifier assigned to the consumer device 106 by the live-agent conversation system 110, by the network 104 or by the consumer device 106 itself that identifies the consumer device 106. A consumer identifier can be a unique identifier associated with the consumer. For example, the consumer may be associated with a unique user account or a unique username, that may be created during an on-boarding stage prior to the consumer device 106 requesting initialization of the first live conversation, or at the end of the first live conversation.

[0095] For example, based on the messages exchanged between the consumer device 106 and the live-agent device 108 at 320, the live-agent conversation system 110 may determine that the live conversation involves a discussion of the vehicle driven by the consumer and may identify the make and model of the vehicle by parsing the messages exchanged. For example, the live conversation may include a message sent by the consumer indicating the make and model of their vehicle. The live-agent conversation system 110 can store the make and model of the vehicle in memory, inassociation with the identifier for the consumer device 106 and / or in associated with a consumer identifier.

[0096] At 450, the live-agent conversation system 110 receives a second live conversation initialization request to initialize a live conversation between the consumer (e.g. the same consumer device 106 or the same consumer identifier) and a second live- agent device 108. The second live conversation initialization request occurs subsequent to the conclusion of the first live conversation. The second live-agent device 108 can be the same as the first live-agent device 108 or can be a different live-agent device 108. Step 350 can be substantially similar to step 310.

[0097] At 460, the live-agent conversation system 110 receives, from the consumer device 106 a request to transfer the second live conversation initialized at 350 to an artificial intelligence (Al) chatbot. The request can be a user-initiated selection requesting to transfer the live conversation. Step 360 can be substantially similar to step 220.

[0098] At 470, the live-agent conversation system 110 receives a free-form natural language text query from the consumer device 106. The free-form natural language text query can include a question for the Al chatbot and can elicit an Al generated response from the Al chatbot. Similar to step 330, the free-form natural language text query can be a query typed or spoken by the consumer on the consumer device 106.

[0099] At 480, the live-agent conversation system 110 determines a query response for the Al chatbot based at least in part on the stored query context, retrieved by the live-agent conversation system 110 and the question included in the free-form natural language text query received at 470. The content of the query response can be determined based at least in part on the query context.

[0100] Similar to 340, in embodiments where the Al chatbot is stored and executed by a remote system 118, the Al chatbot determines a query response based in part on the query context and the question and the remote system 118 transmits the query response to the live-agent conversation system 110.

[0101] For example, the first live conversation may involve the consumer requesting instructions for performing an oil change on their vehicle. During the first liveconversation, the consumer may specify the make and model of their vehicle and the live- agent conversation system 110 can store this information in memory, for example in the storage 114 and / or the remote data storage 102 as the query context. When, during the second live conversation, the consumer transmits a text query that includes a question about replacing the consumer’s vehicle battery, the live-agent conversation system 110 can determine that the text query relates to the consumer’s vehicle and retrieve the query context (i.e., the make and model of the vehicle) from memory. By retrieving the stored query context, the live-agent conversation system 110 can avoid requesting information from the consumer device 106 to establish the query context (e.g., can avoid transmitting a message requesting the make and model of the vehicle) and can accordingly generate a query response in a more computationally efficient manner, since fewer messages need to be transmitted by the Al chatbot to the consumer device 106. Since fewer messages can be transmitted to the consumer device 106, the consumer device 106 can also transmit fewer responses to the messages and accordingly, the consumer device 106 can also save computational resources. Further, the Al chatbot can avoid using computational resources to generate a request for a query context. The live-agent conversation system 110 can also provide an improved user experience for the consumer, who does not need to provide a query context for the text query each time the consumer engages with the live-agent conversation system 110.

[0102] Though method 400 is described with reference to a first live conversation and a second live conversation, method 400 can involve more than two live conversations. For example, the live-agent conversation system 110 can determine or update the query context each time the consumer device 106 requests to initialize a live conversation and exchanges messages with a live-agent device. That is, the query context can be determined based on more than one previous live conversation.

[0103] Referring next to FIG. 5, shown therein is a flowchart illustrating a method 500 of conducting a live-agent conversation with a consumer, in accordance with another embodiment. Method 500 can be substantially similar to methods 300 and 400. However, method 500 involves determining the query context from the live conversation between the consumer device 106 and the live-agent device 108.

[0104] At 510, the live-agent conversation system 110 receives a live conversation initialization request to initialize a live conversation between the consumer device 106 and the live-agent device 108. Step 510 can be substantially similar to steps 310 and 410.

[0105] At 520, messages are exchanged between the consumer device 106 and the live-agent device 108 in a live-agent conversation. Step 410 can be substantially similar to step 420.

[0106] At 530, the live-agent conversation system 110 receives, from the consumer device 106 a request to transfer the live conversation initialized at 510 to an artificial intelligence (Al) chatbot. The request can be a user-initiated selection requesting to transfer the live conversation. Step 530 can be substantially similar to step 320.

[0107] At 540, the live-agent conversation system 110 receives a free-form natural language text query from the consumer device 106. The free-form natural language text query can include a question for the Al chatbot and can elicit an Al generated response from the Al chatbot. Similar to step 330, the free-form natural language text query can be a query typed by the consumer on the consumer device 106.

[0108] At 550, the live-agent conversation system 110 determines, from the live- agent conversation, a query context. For example, the live-agent conversation system 110 can parse the messages exchanged between the consumer device 106 and the live- agent device 108 to determine the query context. In some embodiments, the live-agent conversation system 110 parses the messages exchanged between the consumer device 106 and the live-agent device 108 and the free-form natural language text query to determine the query context.

[0109] At 560, the live-agent conversation system 110 determines a query response for the Al chatbot based at least in part on the query context determined at 550, and the question included in the free-form natural language text query received at 540. The content of the query response is determined based at least in part on the query context.

[0110] Similar to 340 and 480, in embodiments where the Al chatbot is stored and executed by a remote system 118, the Al chatbot determines a query response based inpart on the query context and the question and the remote system 118 transmits the query response to the live-agent conversation system 110.

[0111] In some embodiments, the live-agent conversation system 110 is configured to receive a request to transfer the conversation initialized between the live- agent device 108 and the consumer device 106 to an Al chatbot from the live-agent device 108. For example, a live-agent may wish to transfer the conversation to an Al chatbot when the live-agent does not know the answer to the consumer’s query and / or thinks that the Al chatbot can answer the consumer’s query more rapidly or can formulate a better response to the consumer’s query. As another example, in embodiments where the live- agent conversation system 110 is used to facilitate sales, the live-agent may interact with the Al chatbot to prepare a financing offer, a purchase contract, a warranty, select items to offer to offer to the consumer, or prepare other sales-related document, or to obtain information that may be required for preparing these documents.

[0112] As shown in FIG. 10A, which shows a screenshot 1000A of the GUI of the live-agent conversation system 110 showing a conversation from the perspective of a live-agent, in response to the consumer’s query 1020, the live-agent device 108 can request to transfer the conversation to the Al chatbot.

[0113] In at least some of such embodiments, the live-agent conversation system 110 can initialize a separate, private conversation between the live-agent device 108 and the Al chatbot such that at least some of the messages exchanged between the live- agent device 108 and the Al chatbot are not transmitted to the consumer device 106. In screenshot 1000A shown in FIG. 10A, a private conversation 1050A, 1150A is initialized between the live-agent device 108 and the Al chatbot. The conversation visibility indicator 740 can indicate that the consumer cannot view the conversation between the live-agent and the Al chatbot can be displayed. In embodiments where the live-agent conversation system 110 is used to facilitate sales for example, the live-agent may interact with the Al chatbot in a separate, private conversation to obtain information or to prepare sales- related documents (e.g., financing offer, purchase contract, warranty, order form, etc.) so that the consumer cannot view the messages exchanged between the live-agent and the Al chatbot.

[0114] As shown in screenshot 1000B of FIG. 10B, which shows the GUI of the live-agent conversation system 110 showing the conversation of FIG. 10A from the perspective of the consumer, the private conversation 1050A between the live-agent and the Al chatbot is not displayed. An indicator 730 that the live-agent has requested to transfer the conversation to an Al chatbot may, however, be displayed. In other embodiments, indicator 730 is not displayed.

[0115] The information obtained from the Al chatbot may then be shared by the live-agent or by the Al chatbot in the live conversation between the live-agent and the consumer. For example, the live-agent may request that the Al chatbot shares a document (e.g., financing offer, purchase contract, warranty, order form, etc.) prepared by the Al chatbot with the consumer.

[0116] In some embodiments, the live-agent conversation system 110 can receive a request to transfer the conversation initialized between the live-agent device 108 and the consumer device 106 to an Al chatbot from both the consumer device 106 and the live-agent device 108. In at least some of such embodiments, the live-agent conversation system 110 can initialize a separate, private conversation between the consumer device 106 and an Al chatbot, and a separate, private conversation between the live-agent device 108 and an Al chatbot. The Al chatbots can be the same Al chatbot or can be different Al chatbots.

[0117] For example, as shown in FIGS. 11A-11 B, which show a screenshot 1100A of the GUI of the live-agent conversation system 110 showing a conversation from the perspective of the live-agent and a screenshot 1100B of the GUI of the live-agent conversation system 110 showing the conversation from the perspective of the consumer, respectively, the live-agent conversation system 110 can initialize a separate, private conversation 1150A between the live-agent device 108 and an Al chatbot when the live- agent conversation system 110 receives a request, from the live-agent device 108 to transfer the conversation to an Al chatbot and a separate, private conversation 1 150B between the consumer device 106 and an Al chatbot when the live-agent conversation system 110 receives a request, from the consumer device 106 to transfer the conversation to an Al chatbot. For example, as shown in screenshot 1100B, uponreceiving the Al chatbot’s query response 1 170, the consumer may ask a follow-up text query or a related text query.

[0118] In some embodiments, the live-agent conversation system 110 can determine whether the query response determined by the Al chatbot is satisfactory and if the query response is unsatisfactory, the live-agent conversation system 110 can retransfer the live conversation to a live-agent device 108. For example, the live-agent conversation system 110 may ask the consumer for feedback and in response to receiving feedback from the consumer device 106 indicating that the query response did not address the text query, transfer the live conversation back to a live-agent device 108. The live-agent device 108 may be the live-agent device 108 with which the live conversation is first initialized or another live-agent device 108. For example, the live- agent conversation system 110 can identify a live-agent from a pool of live-agents that is suitable for responding to the text query and transfer the live conversation to the live- agent device 108 associated with the identified agent. The identified live-agent may be an agent having the required knowledge to respond to the text query and / or any available agent.

[0119] In some embodiments, upon concluding the live conversation with the consumer device 106, the live-agent conversation system 110 generates a summary of the live conversation. The summary can be stored in a data storage, such as the storage 114 or the remote data storage 102 and can be provided to a live-agent device 108 when a subsequent live conversation initialization request is received from the consumer device 106. For example, the live-agent device 108 can be provided with a summary of one or more previous live conversations with the consumer device 106 so that the live-agent can provide more efficient support to the consumer. The raw non-summarized live conversation may also be stored in memory.

[0120] In some embodiments, prior to or subsequent to determining the query response, the Al chatbot generates one or more recommendations based on the text query and the live-conversation system 110 transmits the recommendation(s) to the consumer device 106. For example, after determining the query response, the Al chatbot can generate recommended actions or recommended related topics. For example, if thetext query includes a question about replacing the cabin filters of a vehicle, the Al chatbot may provide a recommendation to verify the vehicle’s air filters. As another example, the Al chatbot may generate a list of topics related to the text query and ask the consumer if they would like to obtain more information about one or more of the related topics. The recommendation may be displayed on the GUI of the consumer device 106.

[0121] In at least one embodiment, the recommendation includes a request to provide additional information. For example, the Al chatbot may determine that the text query is unclear and / or that the Al chatbot has insufficient information to respond to the text query and recommend that the consumer provides additional information. Based at least in part on the additional information provided by the consumer via the consumer device 106, and the text query, the Al chatbot may determine a query response.

[0122] While the above description provides examples of the embodiments, it will be appreciated that some features and / or functions of the described embodiments are susceptible to modification without departing from the spirit and principles of operation of the described embodiments. Accordingly, what has been described above has been intended to be illustrative of the invention and non-limiting and it will be understood by persons skilled in the art that other variants and modifications may be made without departing from the scope of the invention as defined in the claims appended hereto. The scope of the claims should not be limited by the preferred embodiments and examples, but should be given the broadest interpretation consistent with the description as a whole.ITEMSItem 1 : A method for conducting a live-agent conversation with a live consumer, the method comprising: receiving a live conversation initialization request between a consumer device and a live-agent device, the consumer device being remotely located from the live-agent device; receiving from the consumer device, a user-initiated selection requesting to transfer the live conversation to an artificial intelligence (Al) chatbot; receiving, from the consumer device, a free-form natural language text query eliciting an Al generated response from the Al chatbot, the free-form natural languagetext query identifying a query context for the free-form natural language text query and a question for the Al chatbot; and determining a query response for the Al chatbot based at least in part on the query context and the question, wherein a content of the query response is determined based at least in part on the query context.Item 2: The method of any of the other items, further comprising: in response to determining the query response is unsatisfactory, identifying an agent from a plurality of agents suitable for responding to the query; and transferring the conversation to a live-agent device associated with the identified live-agent.Item 3: The method of any of the other items determining a wait time of the live-agent device; and in response to determining the wait time exceeds a predetermined acceptable wait time threshold, displaying a recommendation to transfer the live conversation to the chatbot.Item 4: The method of any of the other items, further comprising: after determining the query response for the Al chatbot, generating a summary of the live conversation; and transmitting the summary to the live-agent device.Item 5: The method of any of the other items, further comprising determining a recommendation based on the live conversation.Item 6: The method of any of the other items, wherein the recommendation is one of a recommended action or a recommended related topic.Item 7: The method of any of the other items, wherein transferring the live-agent conversation comprises initiating a separate Al chatbot conversation with the Al chatbot.Item 8: The method of any of the other items, further comprising: generating a summary of the live-agent conversation prior to transferring the live- agent conversation to the Al chatbot; and transmitting the summary to the Al chatbot upon transferring the live-agent conversation to the Al chatbot.Item 9: A system for conducting a live-agent conversation with a live consumer, the system comprising at least one processor and a memory storing computer readable instructions that when executed configure the at least one processor to collectively: receive a live conversation initialization request between a consumer device and a live-agent device, the consumer device being remotely located from the live-agent device; receive from the consumer device, a user-initiated selection requesting to transfer the live conversation to an artificial intelligence (Al) chatbot; receive, from the consumer device, a free-form natural language text query eliciting an Al generated response from the Al chatbot, the free-form natural language text query identifying a query context for the free-form natural language text query and a question for the Al chatbot; and determine a query response for the Al chatbot based at least in part on the query context and the question, wherein a content of the query response is determined based at least in part on the query context.Item 10: The system of any of the other items, wherein the computer readable instructions when executed configure the at least one processor to collectively: in response to determining the query response is unsatisfactory, identify an agent from a plurality of agents suitable for responding to the query; and transfer the conversation to a live-agent device associated with the identified live- agent.Item 11 : The system of any of the other items, wherein the computer readable instructions when executed configure the at least one processor to collectively: determine a wait time of the live-agent device; andin response to determining the wait time exceeds a predetermined acceptable wait time threshold, display a recommendation to transfer the live conversation to the chatbot.Item 12: The system of any of the other items, wherein the computer readable instructions when executed configure the at least one processor to collectively: after determining the query response for the Al chatbot, generate a summary of the live conversation; and transmit the summary to the live-agent device.Item 13: The system of any of the other items, wherein the computer readable instructions when executed configure the at least one processor to collectively determine a recommendation based on the live conversation.Item 14: The system of any of the other items, wherein the recommendation is one of a recommended action or a recommended related topic.Item 15: The system of any of the other items, wherein the computer readable instructions when executed configure the at least one processor to collectively initiate a separate Al chatbot conversation with the Al chatbot to transfer the live-agent conversation.Item 16: The system of any of the other items, wherein the computer readable instructions when executed configure the at least one processor to collectively: generate a summary of the live-agent conversation prior to transferring the live-agent conversation to the Al chatbot; and transmit the summary to the Al chatbot upon transferring the live-agent conversation to the Al chatbot.Item 17: A method for conducting a live-agent conversation with a consumer, the method comprising:receiving a first live conversation initialization request between a consumer device and a first live-agent device, the consumer device being remotely located relative to the live-agent device; exchanging messages in a first live-agent conversation between the consumer device and the live-agent device; determining, from the first live-agent conversation, a query context; storing the determined query context in a memory in association with the consumer device or a consumer identifier associated with the consumer; receiving a second live conversation initialization request between the consumer device and a second live-agent device; receiving from the consumer device, a user-initiated selection requesting to transfer the live-agent conversation to an artificial intelligence (Al) chatbot; receiving, from the consumer device, a free-form natural language text query eliciting an Al generated response from the Al chatbot, the free-form natural language text query comprising a question; and determining a query response for the Al chatbot based at least in part on the stored query context and the question, wherein a content of the query response is determined based at least in part on the query context.Item 18: The method of any of the other items, wherein the first live-agent device and the second live-agent device are the same device.Item 19: The method of any of the other items, further comprising determining a recommendation based on the second live conversation.Item 20: The method of any of the other items, wherein the recommendation is one of a recommended action or a recommended related topic.Item 21 : The method of any of the other items, wherein transferring the live agent conversation comprises initiating a separate Al chatbot conversation with the Al chatbot.Item 22: The method of any of the other items, wherein transferring the live-agent conversation comprises rerouting the live-agent conversation to the Al chatbot.Item 23: A system for conducting a live-agent conversation with a consumer, the system comprising at least one processor and a memory storing computer readable instructions that when executed configure the at least one processor to collectively: receive a first live conversation initialization request between a consumer device and a first live-agent device, the consumer device being remotely located relative to the live-agent device; exchange messages in a first live-agent conversation between the consumer device and the live-agent device; determine, from the first live-agent conversation, a query context; store the determined query context in a memory in association with the consumer device; receive a second live conversation initialization request between the consumer device and a second live-agent device ; receive from the consumer device, a user-initiated selection requesting to transfer the live conversation to an artificial intelligence (Al) chatbot; receive, from the consumer device, a free-form natural language text query eliciting an Al generated response from the Al chatbot, the free-form natural language text query comprising a question; and determine a query response for the Al chatbot based at least in part on the stored query context and the question, wherein a content of the query response is determined based at least in part on the query context.Item 24: The system of any of the other items, wherein the first live-agent device and the second live-agent device are the same device.Item 25: The system of any of the other items, wherein the computer readable instructions when executed configure the at least one processor to collectively determine a recommendation based on the second live conversation.Item 26: The system of any of the other items wherein the recommendation is one of a recommended action or a recommended related topic.Item 27: The system of any of the other items, wherein the computer readable instructions when executed configure the at least one processor to collectively initiate a separate Al chatbot conversation with the Al chatbot to transfer the live-agent conversation.Item 28: The system of any of the other items, wherein the computer readable instructions when executed configure the at least one processor to collectively reroute the live-agent conversation to the Al chatbot to transfer the live-agent conversation.Item 29: A method for conducting a live-agent conversation with a consumer, the method comprising: receiving a live conversation initialization request between a consumer device and a first live-agent device, the consumer device being remotely located relative to the live- agent device; exchanging messages in a live-agent conversation between the consumer device and the live-agent device; receiving from the consumer device, a user-initiated selection requesting to transfer the live conversation to an artificial intelligence (Al) chatbot; receiving, from the consumer device, a free-form natural language text query eliciting an Al generated response from the Al chatbot, the free-form natural language text query comprising a question; after receiving the free-form natural language text query, determining, from the live-agent conversation, a query context for the free-form natural language text query; and determining a query response for the Al chatbot based at least in part on the determined query context and the question, wherein a content of the query response is determined based at least in part on the query context.Item 30: The method of any of the other items, further comprising: in response to determining the query response is unsatisfactory, identifying an agent from a plurality of agents suitable for responding to the query; andtransferring the conversation to a live-agent device associated with the identified live-agent.Item 31 : The method of any of the other items, further comprising: determining a wait time of the live-agent device; and in response to determining the wait time exceeds a predetermined acceptable wait time threshold, displaying a recommendation to transfer the live conversation to the chatbot.Item 32: The method of any of the other items, further comprising: after determining the query response for the Al chatbot, generating a summary of the live conversation; and transmitting the summary to the live-agent device.Item 33: The method of any of the other items, further comprising determining a recommendation based on the live conversation.Item 34: The method of any of the other items, wherein the recommendation is one of a recommended action or a recommended related topic.Item 35: The method of any of the other items, wherein transferring the live-agent conversation comprises initiating a separate Al chatbot conversation with the Al chatbot.Item 36: A system for conducting a live-agent conversation with a consumer, the system comprising at least one processor and a memory storing computer readable instructions that when executed configure the at least one processor to collectively: receive a live conversation initialization request between a consumer device and a first live-agent device, the consumer device being remotely located relative to the live- agent device; exchange messages in a live-agent conversation between the consumer device and the live-agent device;receive from the consumer device, a user-initiated selection requesting to transfer the live conversation to an artificial intelligence (Al) chatbot; receive, from the consumer device, a free-form natural language text query eliciting an Al generated response from the Al chatbot, the free-form natural language text query comprising a question; after receiving the free-form natural language text query, determine, from the live- agent conversation, a query context for the free-form natural language text query; and determine a query response for the Al chatbot based at least in part on the determined query context and the question, wherein a content of the query response is determined based at least in part on the query context.Item 37: The system of any of the other items, wherein the computer readable instructions when executed configure the at least one processor to collectively: in response to determining the query response is unsatisfactory, identify an agent from a plurality of agents suitable for responding to the query; and transfer the conversation to a live-agent device associated with the identified live- agent.Item 38: The system of any of the other items, wherein the computer readable instructions when executed configure the at least one processor to collectively: determine a wait time of the live-agent device; and in response to determining the wait time exceeds a predetermined acceptable wait time threshold, display a recommendation to transfer the live conversation to the chatbot.Item 39: The system of any of the other items, wherein the computer readable instructions when executed configure the at least one processor to collectively: after determining the query response for the Al chatbot, generate a summary of the live conversation; and transmit the summary to the live-agent device.Item 40: The system of any of the other items, wherein the computer readable instructions when executed configure the at least one processor to collectively determine a recommendation based on the live conversation.Item 41 : The system of any of the other items, wherein the recommendation is one of a recommended action or a recommended related topic.Item 42: The system of any of the other items, wherein the computer readable instructions when executed configure the at least one processor to collectively initiate a separate Al chatbot conversation with the Al chatbot to transfer the live-agent conversation.Item 43: The system of any of the other items, wherein the computer readable instructions when executed configure the at least one processor to collectively: generate a summary of the live-agent conversation prior to transferring the live-agent conversation to the Al chatbot; and transmit the summary to the Al chatbot upon transferring the live-agent conversation to the Al chatbot.Item 44: A method for enabling a live-agent conversation with a live-agent, the method comprising: receiving, at a graphical user interface of a consumer device, a live conversation initialization request between the consumer device and a live-agent device, the live-agent device being remotely located from the consumer device; displaying, at the graphical user interface, an interactable graphical user interface element for requesting to transfer the live-agent conversation to an artificial intelligence (Al) chatbot; receiving, at the graphical user interface, a user interaction with the interactable graphical user interface element; receiving, at the graphical user interface, a free-form natural language text query eliciting an Al generated response from the Al chatbot, the free-form natural languagetext query identifying a query context for the free-form natural language text query and a question for the Al chatbot; and receiving a query response from the Al chatbot based at least on the context and the question, wherein a content of the query response is determined based in part on the query context.Item 45: The method of any of the other items, wherein the interactable graphical user interface element is a button.Item 46: The method of any of the other items, further comprising, displaying, at the graphical user interface, a recommendation to transfer the live-agent conversation to the Al chatbot.Item 47: The method of any of the other items, further comprising, displaying, at the graphical user interface, a wait time associated with the live-agent device.Item 48: The method of any of the other items, wherein the free-form natural language text query is inputted using one of a keyboard and voice-to-text.Item 49: The method of any of the other items, further comprising receiving a recommendation from the Al chatbot based on the free-form natural language text query and displaying, at the graphical user interface, the recommendation.Item 50: A consumer device comprising at least one processor and a memory storing computer readable instructions that when executed configure the at least one processor to collectively: receive, at a graphical user interface of the consumer device, a user direction to initiate a live conversation between the consumer device and a live-agent device, the live- agent device being remotely located from the consumer device; display, at the graphical user interface, an interactable graphical user interface element for requesting to transfer the conversation to an artificial intelligence (Al) chatbot;receive, at the graphical user interface, a user interaction with the interactable graphical user interface element; receive, at the graphical user interface, a free-form natural language text query eliciting an Al generated response from the Al chatbot, the free-form natural language text query identifying a query context for the free-form natural language text query and a question for the Al chatbot; and receive a query response from Al chatbot based at least on the context and the question, wherein a content of the query response is determined based in part on the query context.Item 51 : The consumer device of any of the other items, wherein the interactable graphical user interface element is a button.Item 52: The consumer device of any of the other items, where in the computer readable instructions when executed configure the at least one processor to collectively display, at the graphical user interface, a recommendation to transfer the live-agent conversation to the Al chatbot.Item 53: The consumer device of any of the other items, where in the computer readable instructions when executed configure the at least one processor to display at the graphical user interface, a wait time associated with the live-agent device.Item 54: The consumer device of any of the other items, wherein the free-form natural language text query is inputted using one of a keyboard and voice-to-text.Item 55: The system of any of the other items, where in the computer readable instructions when executed configure the at least one processor to receive a recommendation from the Al chatbot based on the free-form natural language text query and display, at the graphical user interface, the recommendation.Item 56: A method for conducting a live-agent conversation with a live consumer, the method comprising: receiving a live conversation initialization request between a consumer device and a live-agent device, the consumer device being remotely located from the live-agent device; receiving from one device which is either the consumer device or the live-agent device, a user-initiated selection requesting to transfer the live conversation to an artificial intelligence (Al) chatbot; initializing a private conversation between the one device and the Al chatbot; receiving in the private conversation, from the one device, a free-form natural language text query eliciting an Al generated response from the Al chatbot, the free-form natural language text query identifying a query context for the free-form natural language text query and a question for the Al chatbot; determining a private query response for the Al chatbot based at least in part on the query context and the question, wherein a content of the query response is determined based at least in part on the query context; and privately transmitting the private query response to the one device; exchanging private messages, in the private conversation, between the one device and the Al chatbot; determining a shared response for the Al chatbot, wherein a content of the shared response is determined based at least in part on the private query response and the private messages; and transmitting, to the consumer device and the live-agent device the shared response.Item 57: The method of any of the preceding items, further comprising displaying a live conversation window in response to the live conversation initialization request and wherein the private query response is displayed in the live conversation window to only the one device.Item 58: The method of any of the preceding items, further comprising displaying at the one device, in the live conversation window, the private conversation between the one device and the Al chatbot. Item 59: The method of any of the preceding items, wherein the shared response is a document.Item 60: The method of any of the preceding items, wherein the document is one of a financing offer, a purchase contract, a warranty or an order form.

Claims

CLAIMS:1 . A method for conducting a live-agent conversation with a live consumer, the method comprising: receiving a live conversation initialization request between a consumer device and a live-agent device, the consumer device being remotely located from the live-agent device; receiving from the consumer device, a user-initiated selection requesting to transfer the live conversation to an artificial intelligence (Al) chatbot; receiving, from the consumer device, a free-form natural language text query eliciting an Al generated response from the Al chatbot, the free-form natural language text query identifying a query context for the free-form natural language text query and a question for the Al chatbot; and determining a query response for the Al chatbot based at least in part on the query context and the question, wherein a content of the query response is determined based at least in part on the query context.

2. The method of claim 1 , further comprising: in response to determining the query response is unsatisfactory, identifying an agent from a plurality of agents suitable for responding to the query; and transferring the conversation to a live-agent device associated with the identified live- agent.

3. The method of claim 1 , further comprising: determining a wait time of the live-agent device; and in response to determining the wait time exceeds a predetermined acceptable wait time threshold, displaying a recommendation to transfer the live conversation to the chatbot.

4. The method of claim 1 , further comprising determining a recommendation based on the live conversation.

5. The method of claim 4, wherein the recommendation is one of a recommended action or a recommended related topic.

6. The method of claim 1 , wherein transferring the live-agent conversation comprises initiating a separate Al chatbot conversation with the Al chatbot.

7. The method of claim 6, further comprising: generating a summary of the live-agent conversation prior to transferring the live- agent conversation to the Al chatbot; and transmitting the summary to the Al chatbot upon transferring the live-agent conversation to the Al chatbot.

8. A system for conducting a live-agent conversation with a live consumer, the system comprising at least one processor and a memory storing computer readable instructions that when executed configure the at least one processor to collectively: receive a live conversation initialization request between a consumer device and a live-agent device, the consumer device being remotely located from the live-agent device; receive from the consumer device, a user-initiated selection requesting to transfer the live conversation to an artificial intelligence (Al) chatbot; receive, from the consumer device, a free-form natural language text query eliciting an Al generated response from the Al chatbot, the free-form natural language text query identifying a query context for the free-form natural language text query and a question for the Al chatbot; and determine a query response for the Al chatbot based at least in part on the query context and the question, wherein a content of the query response is determined based at least in part on the query context.

9. The system of claim 8, wherein the computer readable instructions when executed configure the at least one processor to collectively: in response to determining the query response is unsatisfactory, identify an agent from a plurality of agents suitable for responding to the query; andtransfer the conversation to a live-agent device associated with the identified live- agent.

10. The system of claim 8, wherein the computer readable instructions when executed configure the at least one processor to collectively: determine a wait time of the live-agent device; and in response to determining the wait time exceeds a predetermined acceptable wait time threshold, display a recommendation to transfer the live conversation to the chatbot.

11. The system of claim 8, wherein the computer readable instructions when executed configure the at least one processor to collectively determine a recommendation based on the live conversation.

12. The system of claim 11 , wherein the recommendation is one of a recommended action or a recommended related topic.

13. The system of claim 8, wherein the computer readable instructions when executed configure the at least one processor to collectively initiate a separate Al chatbot conversation with the Al chatbot to transfer the live-agent conversation.

14. The system of claim 13, wherein the computer readable instructions when executed configure the at least one processor to collectively: generate a summary of the live-agent conversation prior to transferring the live-agent conversation to the Al chatbot; and transmit the summary to the Al chatbot upon transferring the live-agent conversation to the Al chatbot.

15. A method for conducting a live-agent conversation with a consumer, the method comprising: receiving a first live conversation initialization request between a consumer device and a first live-agent device, the consumer device being remotely located relative to the live-agent device;exchanging messages in a first live-agent conversation between the consumer device and the live-agent device; determining, from the first live-agent conversation, a query context; storing the determined query context in a memory in association with the consumer device or a consumer identifier associated with the consumer; receiving a second live conversation initialization request between the consumer device and a second live-agent device; receiving from the consumer device, a user-initiated selection requesting to transfer the live-agent conversation to an artificial intelligence (Al) chatbot; receiving, from the consumer device, a free-form natural language text query eliciting an Al generated response from the Al chatbot, the free-form natural language text query comprising a question; and determining a query response for the Al chatbot based at least in part on the stored query context and the question, wherein a content of the query response is determined based at least in part on the query context.

16. The method of claim 15, wherein the first live-agent device and the second live-agent device are the same device.

17. The method of claim 15, further comprising determining a recommendation based on the second live conversation.

18. The method of claim 17, wherein the recommendation is one of a recommended action or a recommended related topic.

19. The method of claim 15, wherein transferring the live-agent conversation comprises initiating a separate Al chatbot conversation with the Al chatbot.

20. The method of claim 15, wherein transferring the live-agent conversation comprises rerouting the live-agent conversation to the Al chatbot.

Images