JP7124151B2 - Improved interaction with the electronic chat interface - Google Patents

Description

This document relates to a chat interface that allows users to communicate with content providers that provide access to resources or content. Chat interfaces may not be consistent across content providers and may be implemented and presented differently. Furthermore, some or all of the functionality may be lost when traditional chat interfaces are presented on mobile devices. Additionally, when a chat session is disconnected, there is little to fall back on.

In general, one innovative aspect of the subject matter described herein is the step of receiving, by a communication server, a search request for content from a user; obtaining search results in the form of selectable content items, each selectable content item including a link to a respective web resource associated with the search request; It is possible to The method enables a communication server, based on information obtained from a database of characteristics of a plurality of web resources, to identify a particular web resource for live assistance by a particular third-party content provider through a particular chat user interface on the particular web resource. and automatically providing a chat interface on the display web page for the particular web resource, the chat interface providing functionality for each of the display web pages. Rendered and/or controlled by the communication server for display adjacent to selectable content items. In response to user interaction with the chat interface from the displayed web page, the communication server initiates a chat session between the user and the particular third party content provider associated with the particular web resource.

These and other embodiments can each optionally include one or more of the following features. In some implementations, the method includes populating a database with database entries for a plurality of web resources. The step of setting data in the database includes, for each of the plurality of web pages, receiving data indicating characteristics of each web resource in the communication server; that each web resource provides functionality for live assistance by a third party content provider through a chat user interface on each web resource; and storing an entry indicating that it has. The step of populating the database is performed periodically to acquire data for web pages not already included in the database.

In some implementations, the chat session includes a first session between the communication server and the user and a second session between the communication server and the third party content provider. In some implementations, the method comprises detecting, by the communication system, no chat session activity for a predetermined period of time; determining by the communication system that the user has not completed the chat session based on chat session contextual data; and storing in a database data indicative of the first session as a whole. initiating a third session between the communication server and the third party content provider as part of the chat session in response to detecting by the communication system that the second session has ended; providing the third party content provider with data indicative of at least a portion of the first session so that the user can resume the chat session with the third party content provider.

In some implementations, the method comprises receiving, at a communication server, input from a user through a chat user interface to a first session; and providing data indicative of user input of the. In some implementations, the request to access a particular web resource includes voice input. In some implementations, the method comprises the steps of: receiving, by a communication system, from a user, a second audio input in a first session; and receiving, by the communication system, text input from the third party content provider in a second session between the communication system and the third party content provider. and providing, by the communication system, to the user in the first session data indicative of a phonetic representation of the text input from the third party content provider.

In some implementations, the chat user interface is a chat widget. In some implementations, determining that a particular web resource provides functionality for live assistance by a particular third-party content provider through a particular chat user interface on the particular web resource comprises: accessing the web resource; identifying, by the communication system, a widget on the web resource; and identifying tags that indicate providing functionality for live assistance by party content providers.

In some implementations, live assistance is provided by a human representative of the particular third party content provider.

In some implementations, the method includes, for each of a plurality of chat sessions initiated for a particular web resource, a unique identifier for the content item that directed the user to the particular web resource by the communication system. determining a content item metric value for the chat session based on. The method comprises using the content item metric values by the communication system to generate a presentation of the content item metric values, and providing the presentation by the communication system to a third party content provider for display. include.

In some implementations, determining that a particular web resource provides functionality for live assistance by a particular third-party content provider through a particular chat user interface on the particular web resource comprises: accessing the web resource; determining by the communication system that a new window has been opened that is separate from the window in which the web resource is being accessed; and determining textual phrases indicative of providing functionality for live assistance by third-party content providers through the Internet.

In some implementations, users access chat sessions through networked devices. A networked device can be a mobile device. A networked device can be a desktop device. In some implementations, networked devices do not have screens.

In some implementations, initiating a chat session between the user and the particular third-party content provider includes obtaining, by the communication server, from the third-party content provider a first unique identifier for the first session of the chat session. receiving a session identifier; and providing, by the communication server, a first unique session identifier to a third party content provider to facilitate a second session.

Another innovative aspect of the subject matter described herein is a device communicatively connected to a network, a third party content provider server communicatively connected to the network, and implementing a method as described above. and a communication server operable to do so.

Yet another innovative aspect of the subject matter described herein is executable instructions that, when executed by at least one processor, cause the at least one processor to perform operations to implement a method as described above. can be embodied in at least one computer-readable storage medium encoded with

Another innovative aspect of the subject matter described herein is, for each of a plurality of web resources, receiving, at a communication server, data indicative of characteristics of the respective web resource; detecting, based on the received data, that each web resource provides functionality for live assistance by a third-party content provider through a chat user interface on each web resource; and storing an entry indicating that the web resources of have the same functionality. The method comprises the steps of: receiving, by a communication server, a request from a user to access a particular web resource hosted by a particular third-party content provider; determining that a particular web resource provides functionality for live assistance by a particular third-party content provider through a particular chat user interface on the particular web resource based on the communication server; initiating a chat session with the party content provider.

In some implementations, the chat session includes a first session between the communication server and the user and a second session between the communication server and the third party content provider. The method comprises the steps of: receiving, at a communication server, from a user through a chat user interface, input to a first session; and providing, by the communication server, data indicative of the user input to a second session to a third party content provider. providing and maintaining state information of a chat session between the user and the third party content provider. The method comprises detecting, by the communication system, no activity for a predetermined period of time; detecting, by the communication system, that at least one of the first session or the second session has ended; determining that the user has not completed the chat session based on chat session contextual data; storing in a database data indicative of the overall first session; initiating a third session between the communication server and the third party content provider as part of the chat session in response to detecting that the session has ended; providing data indicative of at least a portion of the first session so that the chat session with the third party content provider can be resumed.

In some implementations, the request to access a particular web resource comprises voice input. The method comprises the steps of: receiving, over a communication system, from a user in a first session a second spoken input; and providing a third party content provider with data indicative of a textual representation of the second spoken input in a second session. receiving, by the communication system, text input from the third-party content provider in a second session between the communication system and the third-party content provider; and providing data indicative of a phonetic representation of the text input from the third party content provider in the first session.

In some implementations, initiating, by the communication server, a chat session between the user and the third-party content provider includes, by the communication server, sending a first message from the third-party content provider to a first session of the chat session. receiving a unique session identifier; and providing, by a communication server, a first unique session identifier to a third party content provider to facilitate a second session.

In some implementations, the request is presented in response to a search request and served in response to selection of a content item that links to a particular web resource. A chat interface can be presented on a web page that displays content items and results in response to search requests.

In some implementations, the chat user interface is a chat widget. In some implementations, detecting that each web resource provides functionality for live assistance by a third-party content provider through a chat user interface on each web resource includes accessing the web resource via the communication system. identifying a widget on the web resource by the communication system; and code for the widget on the web resource by the communication system, wherein the web resource is communicated by a third party content provider through a chat user interface on the web resource. and identifying tags that indicate that they provide functionality for live assistance.

In some implementations, live assistance is provided by a human representative of the particular third party content provider. In some implementations, the method includes, for each of a plurality of chat sessions initiated for a particular web resource, a unique identifier for the content item that directed the user to the particular web resource by the communication system. using the content item metric values by the communication system to generate a presentation of the content item metric values; and transmitting by the communication system to the third party content provider , and providing the presentation for display.

In some implementations, detecting that each web resource provides functionality for live assistance by a third-party content provider through a chat user interface on each web resource includes accessing the web resource via the communication system. determining, by the communication system, that a new window has been opened that is separate from the window in which the web resource is being accessed; determining textual phrases indicative of providing functionality for live assistance by the provider.

In some implementations, users access chat sessions through networked devices. A networked device can be a mobile device. A networked device can be a desktop device. In some implementations, networked devices do not have screens.

Yet another innovative aspect of the subject matter described herein is a device communicatively connected to a network; a third party content provider server communicatively connected to the network; can be instantiated in a system containing The operation includes, for each of a plurality of web resources, receiving data indicative of characteristics of the respective web resource; and storing in a database an entry indicating that each web resource has the same functionality. The operation includes receiving a request from a user to access a particular web resource hosted by a particular third-party content provider; provide functionality for live assistance by certain third-party content providers through certain chat user interfaces on certain web resources; and initiating a session.

Another innovative aspect of the subject matter described herein is at least one computer readable storage encoded with executable instructions that, when executed by at least one processor, cause the at least one processor to perform operations. It can be embodied in a medium. The operation includes, for each of a plurality of web resources, receiving data indicative of characteristics of the respective web resource; and storing in a database an entry indicating that each web resource has the same functionality. The operation includes receiving a request from a user to access a particular web resource hosted by a particular third-party content provider; provide functionality for live assistance by certain third-party content providers through certain chat user interfaces on certain web resources; and initiating a session.

The subject matter described herein can be implemented in particular embodiments to achieve one or more of the following advantages. The proposed system for initiating and maintaining messaging sessions provides efficient and optimized techniques for identifying and interacting with the resources that provide the functionality of the chat interface. The proposed technology, in one aspect, provides a seamless, dependable implementation of user interface terminals or chat interface functionality provided by a resource or content provider, regardless of the browser capabilities, service provider or operating system in use by the user. To enable a chat interface that is both flexible and scalable, a chat interface is implemented that includes chat sessions drawn and managed by a controlling or communication server/gateway. The system reduces the number of computing resources used to initiate and maintain chat sessions between users and content providers. The system makes the chat interface more robust by maintaining separate sessions between users and gateways and between content providers and gateways and storing session data to re-establish disconnected chat sessions. to Additionally, the gateway can keep sessions open in the event of temporary connection loss, thus improving chat connection reliability. Even if the chat session cannot be kept open and must be re-established, the user can continuously and without having to enter redundant data already provided through a previously established chat session. , you can continue the chat session re-established. Additionally, by providing a chat interface without redirecting users to content provider pages, the system reduces network traffic associated with users seeking chat functionality. Because users can connect and communicate with content providers without frustration when looking for messaging functionality within each content provider's page or when disconnected from a content provider, the system , computer-related technology, improve the functionality of the chat interface.

Additionally, the gateway system improves the capabilities of computer-related technology by providing the ability to scale chat functionality to multiple content providers without requiring tight integration. The system allows content providers to maintain a degree of individuality and control over their chat interfaces. The system's ability to conduct chat conversations without the use of a screen enables hands-free communication and reduces the burden on the user. In addition, the system can post-process chats for further action in integrated applications. For example, if the response in the chat conversation is, "We have an appointment to meet at 5:00 pm." and can perform various other related tasks. Actions resulting from chat conversations can be logged and/or provided for analysis, and the results can be used to influence future chat interface presentations. The gateway system reduces user latency because users with slow network connections are no longer required to visit the content provider's web page and request that the page be rendered. Instead, only communications are transmitted, reducing network traffic and latency.

1 is a block diagram of an example environment in which users can contact content providers through various devices; FIG. FIG. 4 is an example user interface illustrated for providing a chat interface to a user. FIG. 4 is a flowchart of an example process for initiating and maintaining a chat session between a user and a third party content provider; 1 is a block diagram of an example computing system; FIG.

Like reference numbers and symbols in the various drawings indicate like elements.

This document describes methods, systems and devices for improving the connection strength and quality of communication sessions by providing a gateway between a user and the content provider with which the user is communicating. The gateway relays content (e.g., messages) received at one communication interface of the user to the other communication interface of the content provider, and establishes a session directly between the user and the content provider without maintaining session data. , so that a disconnection on either the user's or the content provider's end would terminate the chat session without the ability to re-establish it, rather than saving relevant data about the conversation between the user and the content provider. maintain session information by

In some situations, conversations between client devices may be interrupted or disconnected, causing frustration for the user seeking help and for the content provider seeking help. For example, a customer calling an Internet provider for assistance in handling an Internet connection problem may be disconnected from the person he or she was talking to. The customer can attempt to call back, but if connected with a different representative, the customer must explain the situation again, resulting in an overall inefficient and cumbersome experience for the customer. Here, the gateway stores certain data about the conversation between the user and the content provider in order to reduce the amount of time the user and content provider spend trying to recover the information and progress achieved prior to disconnection. Can be detected and stored. It is a computer-related technique by preventing the loss of data already communicated using the chat interface in the event of a failure of the chat interface (e.g., loss of connection or other disruption of the communication link). It also improves the electronic chat application/functionality.

An electronic document is data that presents a set of content on a client device. Examples of electronic documents include web pages, word processing documents, portable document format (PDF) documents, images, videos, search results pages and feed sources. Native applications (eg, "apps"), such as applications installed on mobile, tablet, or desktop computing devices, are also examples of electronic documents. Electronic documents include digital components that are presented for consumption by users.

As used throughout this document, the term "digital component" refers to a discrete unit of digital content or digital information (eg, video clip, audio clip, multimedia clip, image, text or another unit of content). A digital component can be stored electronically in a physical memory device as a single file or in a group of files, and the digital component takes the form of a video file, audio file, multimedia file, image file or text file. , and may contain advertising information, so that advertising is a kind of digital component. Generally, a digital component is defined by (or provided by) a single provider or source (e.g., an advertiser, publisher or other content provider), but is a combination of content from multiple sources. obtain. Digital components from multiple different sources can be combined into a single electronic document (e.g., a group of different digital components), and portions of different digital components from different sources can be combined into search results (or other (parts of content) can be combined into a single digital component.

Search engines can lead users to results that link to various web pages of content providers. A user can contact a content provider, for example, by calling the phone number provided on the corresponding web page for the particular content provider. In another example, a user can contact a content provider by emailing or mailing the content provider to a specific address listed on the corresponding web page for the specific content provider.

In some examples, a user may contact a content provider through a user interface provided on a particular content provider's web page. A user interface can be, for example, a chat interface that allows a user to communicate with a representative of a particular content provider. Many web pages have different formats, including different arrangements of interface elements that lead users to the chat interface. For example, a web page may contain a button that directs the user to a chat interface.

A chat interface typically includes a text box in which a user can provide input to be transmitted to the other party with whom he or she is communicating. Additionally, other user interface elements for submitting and editing user input may commonly be included in chat interfaces; such user interface elements are small elements that must be accessed by navigating through user interface menus. can be For example, commonly used interface elements include small buttons for sending messages or toggling keyboards, or menus for selecting content to be sent, such as pictures or video data.

Some web pages may require the user to navigate the website tree to reach the chat interface. For example, a user interface element may be displayed on a page other than the main page of the content provider's website that directs the user to a chat interface where the user can contact the content provider. User interface elements may be provided in obscure locations or sized such that it is cumbersome for a user to select a user interface element to access the chat interface.

Chat interfaces can be difficult to use on mobile devices because the screen area on mobile devices is generally smaller than on desktop client devices. For example, the screen area on smart phones is generally smaller than the screen area on desktop computers with monitors. User interface elements that are small on desktop client devices can be many times smaller and more difficult to select on mobile devices.

In some examples, a web page can provide a link to a chat interface that opens a new window. It can be difficult to interact with chat interfaces when viewed on mobile devices with small screens. A user may have little control over the chat interface to interact with it, causing frustration for the user and reducing the value of providing a chat interface for many content providers.

Once a chat session is initiated between a user and a content provider representative, disconnection of the chat session generally results in It means that the user must provide any information he has already provided to the content provider. For example, through a chat interface for a chat session, a user seeking support for a particular type of amateur radio may ask the manufacturer's representative for the amateur radio he is using to provide his registration number, his desired broadcast frequencies and a description of the problem you are having. Once the user's chat session with the manufacturer's representative is disconnected, the user typically navigates to the manufacturer's web page, finds a user interface element that directs them to the manufacturer's chat interface, and once again resumes the new chat session. is established, he again provides all of the information he had already provided to another representative of the manufacturer (i.e. his registration number, his desired broadcast frequency and a description of his problem). There must be.

This document describes methods, systems and devices that reduce the amount of computer resources used to conduct and restore chat sessions between users and content providers. In some situations, the content provider's website includes user interface elements that direct the user to a chat interface and initiate a chat session between the user and the content provider's representative. For example, a tractor company's website may include a button to connect the user to the tractor company's live representative. Buttons may appear as navigation menu items, notably as a primary feature on the support or contact page of the tractor company's website, or based on user behavior while visiting the tractor company's website. It can be displayed in a variety of ways, including as suggestions.

A system identifies that a content provider, such as a tractor company, offers an option to chat with a representative, and stores data indicating that the content provider's website offers an option to use the chat interface. Once a website is identified as providing the functionality of a chat session, such as a live chat session or an automated chat session where a library of answers is built using messaging machine learning models, the system will determine if the web page has chat functionality. can be shown to provide sexuality. For example, the system can indicate that the website offers chat session functionality in search results in which the website appears.

A messaging machine learning model may be a model that receives response data from users and from content providers as input. Messaging machine learning models include techniques such as decision trees, linear regression models, logistic regression models, neural networks, classifiers, support vector machines, inductive logic programming, model aggregation (e.g. bagging, boosting, random forests, etc.). ), genetic algorithms, Bayesian networks, etc., and any of a variety of models such as deep learning, perceptrons, associative rules, inductive logic, clustering, maximum entropy classification, learning classification, etc. can be trained using the method of In some examples, the messaging machine learning model may use supervised learning. In another example, the messaging machine learning model uses unsupervised learning.

A web page can provide user interface elements that allow a user to initiate a chat session with a content provider. Once a user selects a user interface element to initiate a chat session with a content provider, the system identifies chat session characteristics to use when initiating and facilitating a chat session. For example, the system may include a device identifier for a client device from which a user provides input to a chat interface, a session identifier for a specific session between the client device and a specific contact at the content provider, and a specific contact at the content provider. Device identifiers can be stored for devices that enter data into the chat interface.

The system can act as a gateway for chat sessions between users and content providers. The system conducts a first chat session with the user and a second separate chat session with the content provider, and uses data indicative of inputs provided in the first chat session and the second chat session. Relay messages between users and content providers.

Although text chat interfaces will be discussed throughout this document, the techniques discussed herein are applicable to voice chat sessions initiated using computing devices such as personal digital assistants. For example, the personal digital assistant receives audio input (e.g., verbal queries or commands) from the user through the personal digital assistant's microphone, and uses audio output by the personal digital assistant's speaker to display search results to the user. and/or other information may be provided. If the personal digital assistant is implemented in a computing device that includes a display or is connected (e.g., wirelessly or by wire) to a display or another device that presents information on a display, the personal digital assistant may display search results and/or visual information such as one or more of other information related to the audio input may also be presented. that personal digital assistants (PDAs) can be implemented across multiple different physical devices (e.g., mobile phones, tablets, audio/video streaming devices, tabletop PDA units and/or other devices) and that input is on one of the devices; (eg, a tabletop PDA unit) and the audio and/or visual output can be presented by a different one of the devices (eg, a mobile phone). Similarly, some of the information being provided in response to a query or command may be output by one of the devices (e.g., voice information output by a tabletop PDA unit), while a different portion of the information (e.g., , visual information) can be presented by a different one of the devices (eg, displays including mobile phones or audio/video streaming devices).

As part of the audio output and/or visual information, the PDA can present the user with the option of initiating a chat session. For example, the PDA may audibly ask the user if they would like to connect or chat with an agent who can provide them with more information, and the user affirms their desire to connect to the agent. and respond verbally (eg, by saying the word "yes" or the word "connect with an agent"). In response to the user confirming his or her desire to connect with an agent, the PDA can initiate a text chat session (eg, using a mobile device) and/or initiate a phone call to the agent (eg, Internet protocol (e.g., using mobile devices and/or tabletop PDA units) configured to make voice calls via telephone. Once a user is connected to an agent, the techniques discussed throughout this document can be used to maintain the state of a chat session (e.g., text or voice), thereby even if the chat session is interrupted. Allows chat sessions to continue seamlessly. For voice chat sessions, speech recognition technology can be used to convert voice dialogue to text, so the techniques discussed herein can also be used in those situations.

FIG. 1 is a block diagram of an example environment 100 in which users may communicate with content providers. The example environment 100 includes a mobile device 102 , a client device 104 , a screenless assistant device 106 (eg, a tabletop PDA unit), a gateway 110 , an example web page 120 and a content provider system 130 . Devices 102, 104 and 106 are connected to gateway 110 and to content provider system 130 through a network such as a local area network (LAN), wide area network (WAN), the Internet or combinations thereof.

Mobile device 102, client device 104 and screenless assistant device 106 are each electronic devices capable of requesting and receiving resources over a network. Examples of mobile devices 102 include cell phones, smart phones, tablets, and other handheld mobile devices that allow users to connect to content providers over networks. Example client devices 104 include personal computers, mobile workstations and laptop computers. Devices 102, 104, and 106 typically include user applications, such as web browsers, to facilitate sending and receiving data over networks, although native applications executed by client device 104 also facilitate sending and receiving data over networks. can promote.

A device 102, 104 or 106 can submit search queries to a search system, such as a search engine, over a network. In response, the search system accesses the search index to identify electronic documents that are related to the search query. The search system identifies electronic documents in the form of search results and returns the search results to device 102, 104 or 106 in a search results page.

A search result is data generated by a search system that identifies electronic documents that are responsive to (e.g., related to) a particular search query, and to a client device specified network in response to user interaction with the search result. Contains active links (eg, hypertext links) that cause data to be requested from a location (eg, URL). Examples of search results may include web page titles, snippets of text or image portions extracted from web pages, and web page URLs. Other example search results include the title of the downloadable application, a snippet of text describing the downloadable application, an image depicting the user interface of the downloadable application, and/or the application downloaded to the device 102, 104 or 106. It can contain a URL to a possible location.

In some circumstances, the search system uses an application store (or online portal), or interact with it. Like any other electronic document, a search results page may present one or more digital components (e.g., video clips, audio clips, images, or other digital components that can be formatted as advertisements). Can contain slots.

Gateway 110 facilitates chat sessions and includes backends and frontends. The backend of gateway 110 provides the infrastructure for chat sessions and communicates separately with content providers and users. For example, in addition to using data entered by a user through a client device to conduct a chat session with a content provider, the backend may use data entered by a representative of the content provider to conduct a chat session with the user. It can be carried out. The backend interface can be in a common format or package agreed upon by the user or content provider, such as a specific scripting application programming interface (API), a specific android application package (.apk) or various other suitable packages. .

The front end of gateway 110 can be an interface through which one of the user and content provider can provide input to be transmitted and presented to the other. For example, the front end can be a chat interface that is presented separately to users and content providers. The front end is customizable to the user and to the content provider, and can have default profile settings or be adjustable by the user or content provider. For example, the front end for the user may include larger text boxes and boldface, while the front end for the content provider may include additional functionality such as remote access and control of the user's device.

Gateway 110 identifies each web page that provides messaging functionality and stores data indicating that the web page provides that functionality. Identification of web pages that provide messaging functionality is generally done before the web pages are presented as search results, rather than at the time the search request is performed.

Web pages that provide messaging functionality typically include user interface elements that allow a user to initiate a messaging session, such as a button that initiates a chat session. For example, web page 120 is shown including a button 122 that a user can select to initiate a chat session with a content provider. Web page 120 may also include various other indications that messaging functionality is provided or supported, such as key text phrases. For example, web page 120 includes text that reads "Chat with someone now."

The gateway 110 also detects certain scripting features of the web page 120, such as code snippets that cause a new window to open when the user selects a particular user interface element, so that the web page 120 provides messaging or chat functionality. Then you can identify it. Another characteristic of web page 120 that may be used to determine whether web page 120 provides chat functionality is the number of characters displayed on web page 120 that link to different websites or providers. whether it contains widgets that For example, web page 120 probably provides chat functionality if it provides widgets that communicate with known chat service providers. Widgets may include identifiers for specific sessions in addition to other communication information, such as identifiers for specific client devices, specific instances, and the like.

A feature such as a link to a domain known to provide messaging services also indicates that web page 120 likely provides messaging functionality. For example, gateway 110 can mark web page 120 as supporting messaging functionality if the web page links to a known automated chat service.

When gateway 110 receives an initial search request, gateway 110 accesses stored data to determine whether the presented search results provide messaging functionality. If a particular web page provides messaging functionality, gateway 110 indicates the type of messaging functionality provided and, when selected, initiates a messaging session without directing the user to a search results web page. generate user interface elements that will be presented with the search results.

A content provider system 130 is associated with a particular content provider and can be a network destination that provides resources in response to search queries. For example, content provider system 130 can host resources, such as files, that users can download when searching for a particular query. The content provider system 130 includes a user interface that allows content provider personnel to interact with users. In some examples, the user interface is a chat interface through which agents can communicate with users in real time.

Gateway 110 reduces the number of computing resources used to initiate and maintain chat sessions between users and content providers. Additionally, by reducing the need for the user to navigate to the content provider's web page, the gateway 110 reduces the need for the user to seek chat functionality and having to transmit data regarding the content provider's web page. Reduce associated network traffic.

FIG. 2 is an example user interface 200 for a chat session between a user and a content provider. A chat session may be conducted by a system, such as system 100, that includes at least two devices communicatively connected by a network. Chat sessions can be initiated, facilitated, and maintained by communication gateways, such as gateway 110 .

A search query 202 is data entered by a user into a search system, such as a search engine, that indicates a query that the user is interested in seeing related results. A search engine can provide results 210, 220, 230 and 240 on a search results page. Each of results 210 , 220 , 230 and 240 are related to search query 202 and can be ranked based on relevance to search query 202 in some implementations.

Results 210, 220, 230 and 240 each include respective user interface elements 212, 222, 232 and 242 that direct the user to a chat interface with the relevant content provider. User interface elements 212, 222, 232 and 242 are customizable to the relevant content provider's web page on which each element is presented. Customization can be based on various attributes of the particular relevant web page, such as font, text size or color. For example, user interface elements 212 , 222 , 232 and 242 each have a theme associated with respective search results web pages 210 , 220 , 230 and 240 .

When the user selects one of the user interface elements 212, 222, 232 or 242, the gateway 110 initiates a chat session between the user and the content provider providing the corresponding search results web page 210, 220, 230 or 240. Start. In the example illustrated in FIG. 2, the user selects user interface element 212 associated with search results web page 210 . A chat session is thus rendered and thus managed by the gateway. This allows the gateway, or the server associated with the gateway, to perform chat sessions in a seamless manner regardless of the particular browser, operating system and any other user device or system currently in use by the user and/or content provider. It allows implementing control and any required protocols and data structures to ensure the scalability, security, reliability and storage associated with .

Once the user selects user interface element 212 , gateway 110 initiates a chat session with the content provider providing search results web page 210 . Gateway 110 identifies the user who selected web page 120 and element 212 and stores data indicating the identifier of web page 120 and the user. Gateway 110 can also store various other attributes of chat sessions, such as the length of the session, a first session identifier for chat sessions with users, and a second, separate session identifier for chat sessions with content providers.

In order to maintain sessions between users and content providers when gateway 110 manages many different conversations between many different users and content providers, gateway 110 may extract content from one session with a user. Direct the response to another session with the provider. Gateway 110 uses stored data indicative of session identifiers to properly transfer messages between users and content providers.

The gateway 110 can receive input in various formats, format the input, and provide input to chat sessions between users and content providers. For example, a user can send a text message to a particular phone number to initiate a chat with a content provider. A particular phone number can be associated with the content provider, and receipt of a text message at the particular phone number can trigger initiation of a chat session with the content provider. For example, receipt of a text message at a particular phone number can trigger the system to contact gateway 110 and provide user input as input to a chat session. Once the user receives a response from the content provider, gateway 110 can provide the response to the user as a text message. The user can also provide a response to the content provider via text message, or email, or various other suitable communication methods.

Gateway 110 can process input from users or content providers in a variety of formats. For example, if a user interacts with gateway 110 using mobile device 102 and selects user interface element 212 to initiate an email conversation with the content provider, a chat session with the content provider can be initiated. , and user input and responses can be presented within the email client interface.

In some implementations, given a conventional conversation, gateway 110 can provide a specific identifier, such as a phone number, to which the user can provide input. For example, if a user is already connected to a content provider, gateway 110 can detect user input depending on the content provider if the user input is provided to a different application, such as a text messaging application or an email client. The user's input can then be transformed into input that will be provided to the conversation.

When a session is established, a chat interface can be presented without directing the user to web page 210, thereby reducing the number of network calls and/or data transferred to establish a chat session. For example, a chat interface can be presented on search results page 204 . As noted above, the chat interface may include user interface elements that allow the user to enter data. For example, a chat interface may include text boxes that allow users to enter responses or questions that will be provided to the content provider, and buttons that allow users to submit their input. Additional interface elements may be provided within the chat interface, such as file attachments, screen sharing, and the like.

The chat interface can be rendered within the search results page 204 using various rendering methods, such as headless rendering. The chat interface receives input from users or content providers and provides the input to gateway 110 for transmission.

Once a session is established, certain metrics such as click-through rate, conversion rate, average traffic, time of access, etc. can be calculated for the chat interface method of communicating with the content provider. For example, click-through rates associated with chat functionality user interface elements can be calculated. In some implementations, content providers have access to reports generated using calculated metrics. For example, content providers may consider reporting on the performance of chat interface methods and adjusting campaign budgets for chat interfaces based on the reported metrics.

When the gateway 110 is used with the screenless assistant device 106, the screenless assistant device 106 uses the same infrastructure for chat sessions as the mobile device 102 and fixed client device 104 to communicate between users and content providers. It can facilitate conversation between However, since the screenless assistant device 106 does not include a screen, the method of receiving and outputting data includes additional steps. The screenless assistant device 106 can receive various types of suitable input, such as voice input or touch input. For example, the screenless assistant device 106 can receive verbal commands through the microphone of the screenless assistant device 106 . Verbal commands can be processed and text data representing the voice input can be extracted. In some implementations, the screenless assistant device 106 handles voice input, while in other implementations the gateway 110 or a remote system handles voice input.

Gateway 110 can then use the text data as input to sessions with content providers. When the gateway 110 receives a response from the content provider, the response can be processed to be output in the same format as the input to the screenless assistant device 106 was provided. For example, if the screenless assistant device 106 receives voice input, the screenless assistant device 106 can receive data for output, including voice data.

In an exemplary use of system 100, a user can provide voice input to mobile device 102 by saying, "I would like to speak to ABC Customer Service." The mobile device 102 can then display search results that may include web pages identified as providing messaging functionality along with user interface elements that allow the user to initiate a messaging session.

Users can continue conversations with content providers on different devices. For example, if a user initiates a messaging session with a content provider on mobile device 102 , the user can continue the conversation with the content provider on screenless assistant device 106 . Gateway 110 can detect the device from which the user is providing input or accessing the messaging session and select an appropriate output method such as text, voice, picture, or the like.

By maintaining a chat session using separate sessions with the user and with the content provider, the gateway 110 is required to re-enter and provide information already provided by either the user or the content provider. Reduce the amount of computing resources. For example, a user can continue a chat session without interruption and having to enter redundant data that has already been entered through an already established chat session. In addition, the gateway 110 improves chat session robustness by maintaining separate sessions between users and content providers so that temporary disconnection of either session does not terminate the chat session.

In some examples, the gateway 110 preserves conversations between users and content providers by storing data from the conversations as they occur. If the user and the content provider are disconnected, the gateway 110 stores at least some of the stored data for the conversation up to the point where the user and the content provider were disconnected in order to re-establish the conversation between the user and the content provider. use.

Once the chat session is re-established, the gateway 110 may converse with the content provider without further input from the user in order to catch up with the content provider to the point where the conversation with the user has already taken place. provide a previous chat session). For example, the gateway 110 may indicate that the next contact of the content provider to which the user is connected is informed of the user's status so that the user can continue his/her conversation with the contact without repeating information already provided. As such, it can automatically provide stored data indicative of the user's device information and problem description. The gateway 110 can autonomously determine the answer to the content provider's response using a machine learning model trained using the user's already provided answers. A machine learning model can take the content provider's response as input and output a variety of appropriate responses.

In some examples, the gateway 110 integrates with a traditional messaging service provider and stores specific session data that allows the user to resume the conversation from specific points such as when the user left the conversation. server-side integration by For example, once gateway 110 establishes a new messaging session, gateway 110 can provide stored data to a different content provider representative.

In some implementations, the gateway 110 cannot update the new contact to the point of the previous conversation. For example, a new agent's response to a particular piece of information may differ from a previous agent's response, and gateway 110 will cause gateway 110 to retrieve all of the information that the user was previously able to provide to the agent. You may not be able to move the conversation forward in a direction that you can offer. When the gateway 110 cannot provide all of the information the user has already provided, the gateway 110 can provide the user with context for conversations conducted without the user.

Gateway 110 can also provide client-side integration by storing session data or user input. The gateway 110 can provide stored data to the user when the conversation has caught up or the gateway 110 has been updated as much as possible, so that the user has context to the content provider personnel's understanding of the situation.

The gateway 110 can detect when the user is inactive or busy. For example, if a user goes to a meeting or leaves their device without notifying content provider personnel, the gateway 110 can mark the same instance as inactivity. Gateway 110 can determine whether the user is inactive based on various characteristics of the current conversation. Such characteristics may be a threshold period of time that elapses between the content provider's last response and the user's last response, certain phrases entered by the user, certain phrases entered by the content provider, or the gateway 110 Contains various event data associated with the accessing user. For example, if a meeting is scheduled while a user is talking, gateway 110 can determine that the user is in a meeting if the user does not respond within a threshold amount of time.

When the conversation is marked as inactive, the gateway 110 can notify the content provider that the user is away. For example, if the user is detected to be inactive, the gateway 110 provides a response to the content provider representative on behalf of the user asking the content provider representative to wait a few minutes and remain connected. can.

In some instances, gateway 110 may mark the case as resolved instead of inactive. For example, if the user does not respond for a threshold amount of time, but in the response provided by the user, there is an indication that the content provider has resolved the user's problem, such as the user responding, "Great, that's good enough, thank you." For example, gateway 110 can mark the conversation as resolved. The gateway 110 or device 102, 104 or 106 with which the user is communicating with the content provider may also request input from the user or content provider to indicate whether the problem has been resolved. For example, the screenless assistant device 106 can provide a voice output to the user asking if the problem has been resolved, separate from the conversation between the user and the content provider. If the user provides an affirmative response, the screenless assistant device 106 can provide the response to the gateway 110 and the gateway 110 can mark the conversation as resolved without prompting or otherwise eliciting further responses from the user. .

In some instances, gateway 110 may attempt to maintain a conversation with a content provider representative if the user is only temporarily unavailable. For example, if a user receives a call on mobile device 102, gateway 110 can provide a response to the content provider on behalf of the user, such as "I'll be right back, can you wait?" Gateway 110 may then attempt to maintain the chat session until the user's next response.

FIG. 3 is a flowchart of an example process 300 for initiating and maintaining a chat session between a user and a third party content provider. In some implementations, process 300 can be implemented by a messaging system, such as system 100 . For example, process 300 can be implemented by gateway 110 of FIG. In some implementations, process 300 can be implemented as instructions stored on a non-transitory computer-readable medium, and when the instructions are executed by one or more servers, the instructions may include one or more , the operations of step 300 can be performed.

Process 300 begins with, for each of a plurality of web resources, a communication server receiving 302 data indicative of characteristics of the respective web resource. For example, the gateway 110 can receive data indicating characteristics of a particular web page, including whether the web page contains particular phrases, widgets, snippets of code, and the like.

Step 300 continues with, for each of the plurality of web resources, the communication server activating the respective web resource for live assistance by a third party content provider through a chat user interface on the respective web resource based on the received data. detects 304 that it provides functionality for In some examples, the chat user interface is a chat widget. Live assistance can be provided by human representatives at certain third party content providers. A chat user interface can be presented on a web page that displays content items and results in response to search requests. In some examples, users access chat sessions through networked devices. A networked device can be a mobile device, a desktop device, or any of a variety of other networked devices. In some instances, networked devices do not have screens.

In some examples, detecting includes accessing a web resource; determining that a new window has opened that is separate from the window in which the web resource is being accessed; determining textual phrases indicative of providing functionality for live assistance by a third party content provider through a chat user interface on the web resource.

In some examples, detecting includes accessing the web resource; identifying a widget on the web resource; and in code for the widget on the web resource, the web resource and identifying tags that indicate providing functionality for live assistance by third-party content providers through the interface.

Process 300 continues with, for each of the plurality of web resources, the communication server storing 306 an entry in a database indicating that the respective web resource has the same functionality. For example, gateway 110 can store entries in a database indicating that a particular web page has messaging functionality.

The process 300 continues with a communication server receiving (308) a request from a user to access a particular web resource hosted by a particular third party content provider. For example, a user can select a search results link that directs the user to a web resource associated with a particular content provider. In some examples, requests are presented in response to search requests and served in response to selection of content items that link to particular web resources. In some examples, a request to access a particular web resource comprises voice input.

Step 300 continues with the communication server determining whether the particular web resource is live by the particular third party content provider through the particular chat user interface on the particular web resource based on the stored entries in the database representing the particular web resource. Determine 310 to provide functionality for assistance.

Process 300 continues with the communication server initiating a chat session between the user and the third party content provider (312). For example, gateway 110 can initiate a chat session between the user and the content provider. In some examples, the chat session includes a first session between the communication server and the user and a second session between the communication server and the third party content provider. In some examples, initiating includes receiving from a third party content provider a first unique session identifier for a first session of the chat session; and providing a first unique session identifier to facilitate a session of.

In some examples, step 300 includes receiving input to the first session through the chat user interface and providing the third-party content provider with data indicative of the user input to the second session. include. Step 300 calculates, for each of a plurality of chat sessions initiated for a particular web resource, a content item metric value for the chat session based on the unique identifier of the content item that directed the user to the particular web resource. using the content item metric values to generate a presentation of the content item metric values; and providing the presentation to a third party content provider for display. For example, content item metric values can include click-through rates associated with chat functionality.

In some examples, process 300 includes detecting no activity for a predetermined period of time and that at least one of the first session or the second session has ended. Step 300 includes determining that the user has not completed the chat session based on chat session contextual data, and storing data indicative of the entire first session in a database. Step 300 continues by initiating a third session between the communication server and the third party content provider as part of the chat session in response to detecting that the second session has ended, and by the communication system: The third party content provider can be provided with data indicative of at least a portion of the first session so that the user can resume the chat session with the third party content provider.

In some examples, process 300 further includes receiving a second audio input in the first session from the user. Step 300 continues by providing the third party content provider with data indicative of the textual representation of the second voice input in the second session. Step 300 continues with receiving, by the communication system, text input from the third party content provider in a second session between the communication system and the third party content provider. Process 300 may continue by providing the user with data indicative of a phonetic representation of the text input from the third party content provider in the first session.

FIG. 4 is a block diagram of an example computer system 400 that can be used to perform the operations described above. System 400 includes processor 410 , memory 420 , storage device 430 and input/output device 440 . Each of the components 410, 420, 430, 440 are interconnectable using a system bus 450, for example. Processor 410 is capable of processing instructions for execution within system 400 . In one implementation, processor 410 is a single-threaded processor. In another implementation, processor 410 is a multithreaded processor. Processor 410 can process instructions stored in memory 420 or in storage device 430 .

Memory 420 stores information within system 400 . In one implementation, memory 420 is a computer-readable medium. In one implementation, memory 420 is a volatile memory unit. In another implementation, memory 420 is a non-volatile memory unit.

Storage device 430 may provide mass storage for system 400 . In one implementation, storage device 430 is a computer-readable medium. In various different implementations, the storage device 430 may be, for example, a hard disk device, an optical disk device, a storage device shared over a network by multiple computing devices (eg, a cloud storage device), or some other mass storage device. can include

Input/output devices provide input/output operations for system 400 . In one implementation, the input/output device includes one or more network interface devices such as Ethernet cards, serial communication devices such as RS-232 ports, and/or wireless interface devices such as 802.11 cards. can contain. In another implementation, the input/output devices may include driver devices configured to receive input data and send output data to other input/output devices such as keyboards, printers and display devices 460 . However, other implementations may also be used, such as mobile computing devices, mobile communications devices, set-top box television client devices, and the like.

Although an example processing system has been described in FIG. 4, example implementations of the subject matter and functional operations described herein may be implemented in other types of digital electronic networks or with the structures and components disclosed herein. It can be implemented in computer software, firmware or hardware, including structural equivalents, or in any combination of one or more thereof.

Electronic documents (to be simply referred to as documents for brevity) do not necessarily correspond to files. A document may be stored in part of a file that holds other documents, in a single file dedicated to that document, or in multiple linked files.

Embodiments of the subject matter and operations described herein may be implemented in digital electronic circuitry or in computer software, firmware or hardware, including the structures disclosed herein and their structural equivalents. can be implemented with one or more combinations of Embodiments of the subject matter described herein may be encoded in one or more computer programs, i.e., one or more computer storage media, for execution by a data processing apparatus or for controlling the operation thereof. can be implemented as one or more modules of coded computer program instructions. Alternatively, or in addition, the program instructions may be transferred to man-made propagated signals, e.g., machine-generated electricity, generated to encode information for transmission to appropriate receiver devices for execution by a data processing device. It can be encoded onto an optical or electromagnetic signal. A computer storage medium can be or be included in a computer readable storage device, a computer readable storage substrate, a random or serial access memory array or device, or a combination of one or more thereof. Moreover, while a computer storage medium is not a propagated signal, a computer storage medium can be the source or destination of computer program instructions encoded in an artificially generated propagated signal. A computer storage medium may also be or be included in one or more separate physical components or media (eg, multiple CDs, disks, or other storage devices).

The operations described herein can be implemented as operations performed by a data processing apparatus on data stored in one or more computer-readable storage devices or received from other sources.

The term "data processor" encompasses all kinds of apparatus, devices and machines for processing data including, by way of example, programmable processors, computers, systems-on-chips, or any plurality or combination of the foregoing. The device may include dedicated logic circuitry, such as FPGAs (Field Programmable Gate Arrays) or ASICs (Application Specific Integrated Circuits). The apparatus includes hardware plus code that creates an execution environment for the computer program, e.g., processor firmware, protocol stacks, database management systems, operating systems, cross-platform runtime environments, virtual machines, or one of these. Alternatively, it can also include code that constitutes a plurality of combinations. Devices and execution environments can implement a variety of different computing model infrastructures such as web services, distributed computing and grid computing infrastructures.

A computer program (also known as a program, software, software application, script or code) can be written in any form of programming language, including compiled or interpreted languages, declarative or procedural languages, and It can be deployed in any form, including as a stand-alone program, or as modules, components, subroutines, objects, or other units suitable for use in a computing environment. A computer program may or may not correspond to a file in a file system. A program may be part of a file holding other programs or data (e.g., one or more scripts stored in a markup language document), a single file dedicated to the program, or multiple linked files. (eg, a file that stores one or more modules, subprograms, or portions of code). A computer program can be deployed and executed on one computer or on multiple computers located at one site or distributed across multiple sites and interconnected by a communication network.

The steps and logic flows described herein can be performed by one or more programmable computers that operate by executing one or more computer programs to manipulate input data and generate output. . The steps and logic flow can also be performed by dedicated logic circuitry, such as FPGAs (Field Programmable Gate Arrays) or ASICs (Application Specific Integrated Circuits), and devices can be implemented as such.

Processors suitable for the execution of computer programs include, by way of example, both general and special purpose microprocessors. Generally, a processor will receive instructions and data from read-only memory or random-access memory or both. The essential elements of a computer are a processor for acting in accordance with instructions, and one or more memory devices for storing instructions and data. Generally, a computer also includes, or is operatively coupled to, one or more mass storage devices for storing data, such as magnetic, magneto-optical or optical disks, to receive data from or transmit data to. Transfer or do both. However, a computer need not have such devices. Moreover, the computer may be used by another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device, to name a few. (eg, a universal serial bus (USB) flash drive). Devices suitable for storing computer program instructions and data include, by way of example, semiconductor memory devices such as EPROM, EEPROM and flash memory devices; magnetic disks such as internal hard disks or removable disks; magneto-optical disks; and CD ROMs. and all forms of non-volatile memory media and memory devices, including DVD-ROM discs. The processor and memory can be supplemented by or embedded in dedicated logic circuitry.

To provide interaction with a user, embodiments of the subject matter described herein include a display device, such as a CRT (cathode ray tube) or LCD (liquid crystal display) monitor, for displaying information to a user, and It can be implemented in a computer having a keyboard and pointing device, such as a mouse or trackball, that allows a user to provide input to the computer. Other types of devices can also be used to provide interaction with the user, for example the feedback provided to the user can be any form of sensory feedback, such as visual, auditory or tactile feedback. and input from the user can be received in any form, including acoustic, speech or tactile input. In addition, a computer can send a document to and receive a document from a device used by a user, for example, to render a web page to a web browser in response to a request received from the web browser on the user's client device. You can interact with the user by sending.

Embodiments of the subject matter described herein include back-end components, e.g., as data servers, or include middleware components, e.g., application servers, or front-end components, e.g. implemented on a computing system comprising a client computer having a graphical user interface or web browser capable of interacting with an implementation of the subject matter described therein, or any combination of one or more such back-end, middleware or front-end components is. The components of the system can be interconnected by any form or medium of digital data communication, eg, a communication network. Examples of communication networks include local area networks (“LAN”) and wide area networks (“WAN”), internetworks (eg, the Internet) and peer-to-peer networks (eg, ad-hoc peer-to-peer networks).

The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. In some embodiments, the server transmits data (eg, HTML pages) to the client device (eg, for the purpose of displaying data to and receiving user input from the user interacting with the client device). Data generated at the client device (eg, results of user interactions) can be received from the client device at the server.

While this specification contains many specific implementation details, these are not intended as limitations on the scope of any invention or what may be claimed, but rather specific to particular embodiments of particular inventions. It should be interpreted as a description of the features. Certain features that are described in this specification in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination. Moreover, although features are described above and initially claimed as working in a combination, one or more features from the claimed combination may, in some cases, act in the same combination. and a claimed combination may be a subcombination or a variant of a subcombination.

Similarly, while acts may be drawn in the figures in a particular order, this indicates that such acts are performed in the specific order or sequence in which they are illustrated, or that all steps are performed in order to achieve a desired result. should not be understood to require that the illustrated operations of are performed. Multitasking and parallel processing may be advantageous in some situations. Moreover, the separation of various system components in the above-described embodiments should not be understood to require such separation in all embodiments, and that the program components and systems described are generally a single piece of software. It should be understood that the products may be integrated together or implemented in multiple software products.

Thus, specific embodiments of the subject matter have been described. Other embodiments are within the following claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve desirable results. Additionally, the steps depicted in the accompanying figures do not necessarily require the particular order or order depicted to achieve desirable results. In some implementations, multitasking and parallel processing may be advantageous.

100 system 102 mobile device,
104 client device 106 screenless assistant device 110 gateway 120 web page 122 button 130 content provider system 200 user interface 202 search query 204 search results page 210 search results web page 220 search results web page 230 search results web page 240 search results web page 212 User Interface Element 222 User Interface Element 232 User Interface Element 242 User Interface Element 400 Computer System 402 Processor 404 Memory 406 Storage Device

Claims (17)

receiving, by a communication server, verbal input from a user presented through a microphone of a personal digital assistant;
obtaining, by the communication server, search results using the verbal input;
the third-party content provider corresponding to one of the search results, based on an analysis of web resources provided by third-party content providers by the communication server; determining to provide live interactive assistance with a chat feature through the chat user interface by detecting the inclusion of a user interface element that initiates a connection to the live chat system;
an option to initiate a chat session using the chat functionality provided by the third-party content provider when the search results are delivered to the user without requiring the user to make an initial request to the web resource; , providing to the user through the personal digital assistant;
receiving, through the personal digital assistant, an acknowledgment that the user has requested to initiate the chat session;
initiating, by the communication server, a chat session between the user and an agent of the content provider without redirecting the user to the web resource provided by the third party content provider;
Method. providing an option to initiate a chat session, through the personal digital assistant, the user desires to connect or chat with an agent who can provide the user with more information from the content provider; providing a voice query asking whether
2. The method of claim 1, wherein receiving an acknowledgment that the user has requested initiation of the chat session comprises receiving, via the personal digital assistant, a voice response to the voice query. wherein the personal digital assistant is implemented across two or more different devices, including a first device that does not include a display and a second device that includes a display;
Providing an option to initiate a chat session indicates that, through the second device, the user wishes to connect or chat with an agent who can provide the user with more information from the content provider. providing a voice query asking whether to
3. The method of claim 2, wherein receiving an acknowledgment that the user has requested initiation of the chat session comprises receiving, through the first device, a voice response to the voice query. 2. The method of claim 1, wherein initiating the chat session comprises initiating an internet protocol voice call with the agent. maintaining state of the chat session, including logging communications between the user and the agent during the chat session;
determining that the chat session has ended prior to completion of interaction between the agent and the user;
initiating subsequent chat sessions with subsequent agents of the content provider;
and providing the subsequent agent with the state of the chat session, including at least some of the logged communications between the user and the agent. determining that the chat session has ended prior to completion of interaction between the agent and the user includes determining no activity through the chat feature for at least a predetermined period of time; 6. The method of claim 5 . a data store storing interaction data corresponding to input to a client-side chat session;
A communication server in communication with a client device, said communication server enabling a chat session between said client device and a content provider, wherein:
receiving verbal input from a user of the client device presented through a microphone of a personal digital assistant;
obtaining search results using the verbal input;
Based on analysis of web resources provided by third-party content providers, the third-party content provider corresponding to one of the search results provides a live chat system where the web resources were provided by the third-party content provider. determining to provide live interactive assistance with chat functionality through the chat user interface by detecting the inclusion of a user interface element that initiates a connection;
an option to initiate a chat session using the chat functionality provided by the third-party content provider when the search results are delivered to the user without requiring the user to make an initial request for the web resource; providing to the user through the portable information terminal;
receiving, through the personal digital assistant, an acknowledgment that the user has requested to initiate the chat session;
initiating, by the communication server, a chat session between the user and an agent of the content provider without redirecting the user to the web resource provided by the third-party content provider. implement,
system. The step of providing an option to initiate a chat session determines whether the user, through the personal digital assistant, desires to connect or chat with an agent who can provide the user with more information from the content provider. providing a voice query asking whether
8. The system of claim 7 , wherein receiving an acknowledgment that the user has requested initiation of the chat session comprises receiving a voice response to the voice query through the personal digital assistant. wherein the personal digital assistant is implemented across two or more different devices, including a first device that does not include a display and a second device that includes a display;
providing an option to initiate a chat session through the second device, the user wishes to connect or chat with an agent who can provide the user with more information from the content provider; providing a voice query asking whether
9. The system of claim 8 , wherein receiving an acknowledgment that the user has requested initiation of the chat session comprises receiving, through the first device, a voice response to the voice query. 8. The system of claim 7 , wherein initiating the chat session comprises initiating an internet protocol voice call with the agent. maintaining state of the chat session, wherein the actions include logging communications between the user and the agent during the chat session;
determining that the chat session has ended prior to completion of interaction between the agent and the user;
initiating subsequent chat sessions with subsequent agents of said content provider;
and providing the subsequent agent with the state of the chat session including at least a portion of a logged call between the user and the agent. Determining that the chat session has ended prior to completion of interaction between the agent and the user includes determining no activity through the chat feature for at least a predetermined period of time. 12. The system of claim 11 . A non-transitory computer-readable medium storing instructions that, when executed by one or more computing devices, cause the one or more computing devices to perform an action, the action comprising:
receiving verbal input from a user presented through a microphone of a personal digital assistant;
obtaining search results using the verbal input;
Based on analysis of web resources provided by third-party content providers, the third-party content provider corresponding to one of the search results provides a live chat system where the web resources were provided by the third-party content provider. determining to provide live interactive assistance with chat functionality through the chat user interface by detecting the inclusion of a user interface element that initiates a connection;
an option to initiate a chat session using the chat functionality provided by the third-party content provider when the search results are delivered to the user without requiring the user to make an initial request to the web resource; , providing to the user through the portable information terminal;
receiving, through the personal digital assistant, an acknowledgment that the user has requested to initiate the chat session;
initiating a chat session between the user and an agent of the content provider without redirecting the user to the web resource provided by the third party content provider;
Non-transitory computer-readable medium. providing an option to initiate a chat session, through the personal digital assistant, the user desires to connect or chat with an agent who can provide the user with more information from the content provider; providing a voice query asking whether
14. The non-transitory computer-readable medium of claim 13 , wherein receiving an acknowledgment that the user has requested initiation of the chat session comprises receiving, via the personal digital assistant, a voice response to the voice query. . wherein the personal digital assistant is implemented across two or more different devices, including a first device that does not include a display and a second device that includes a display;
Providing an option to initiate a chat session indicates that, through the second device, the user wishes to connect or chat with an agent who can provide the user with more information from the content provider. providing a voice query asking whether to
15. The non-transitory computer readable of claim 14 , wherein receiving an acknowledgment that the user has requested initiation of the chat session comprises receiving, via the first device, a voice response to the voice query. medium. 14. The non-transitory computer-readable medium of claim 13 , wherein initiating the chat session comprises initiating an internet protocol voice call with the agent. maintaining state of the chat session including logging communications between the user and the agent during the chat session;
determining that the chat session has ended prior to completion of interaction between the agent and the user;
initiating subsequent chat sessions with subsequent agents of said content provider;
and providing the subsequent agent with the status of the chat session including at least some of the logged communications between the user and the agent.

Images