JP2021099862A - Improvement of dialog with electronic chat interface - Google Patents

Abstract

To provide a method of improving dialog with an electronic chat interface, and a device and a communication server connected to a network.SOLUTION: A method includes: acquiring, by a communication server, a search result by receiving verbal input through a portable information terminal from a user; detecting that a web resource corresponding to one search result includes a user interface element that starts connecting to a live chat system based on web resource analysis provided by a third party content provider; thereby determining to provide live interactive assistance through a chat user interface; providing the user with an option to start a chat session when the search result is transmitted to the user, without requiring the user to make a first request to the web resource; receiving affirmation of starting a chat session; and starting the chat session between the user and an agent of the content provider.SELECTED DRAWING: Figure 1

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 be inconsistent across content providers and may be implemented and presented in different ways. Moreover, some or all of the functionality may be lost when a traditional chat interface is presented on a mobile device. In addition, when a chat session is disconnected, there is little to rely on.

In general, one innovative aspect of the subject matter described herein is the step of receiving a content search request from a user by a communication server and multiple display on a web page by the communication server in response to the search request. Steps to obtain search results in the form of selectable content items in, each selectable content item embodied in a way that includes steps, including links to the respective web resources associated with the search request. It can be converted. This method provides live assistance by a particular third-party content provider through a particular chat user interface on a particular web resource by a communication server based on information obtained from a database of the characteristics of multiple web resources. A step that determines that the functionality is provided for the above, and a step that automatically provides a chat interface on the display web page for the specific web resource described above, wherein each of the chat interfaces is on the display web page. Includes steps that are drawn and / or controlled by the communication server for display adjacent to selectable content items. In response to a user interaction with a chat interface from a displayed web page, the communication server initiates a chat session between the user and a particular third-party content provider associated with a particular web resource.

Each of these and other embodiments may optionally include one or more of the following features: In some implementations, the method includes populating a database that has database entries for multiple web resources. The steps for setting data in the database are a step of receiving data indicating the characteristics of each web resource on the communication server for each of the above-mentioned plurality of web pages, and a step of receiving data by the communication server, respectively. The steps to detect that a web resource provides functionality for live assistance by a third-party content provider through a chat user interface on each web resource, and the communication server provides the database with the same functionality for each web resource. Includes a step of storing an entry indicating that it has. Steps to populate the database are performed on a regular basis to acquire data for web pages that are not yet contained 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 detects by the communication system that there is no activity in the chat session for a given period of time, and the communication system terminates at least one of the first or second sessions. The step of detecting that the user has completed the chat session, the step of determining that the user has not completed the chat session based on the context data of the chat session by the communication system, and the data indicating the entire first session are stored in the database. A step and a communication system that initiates a third session between the communication server and a third-party content provider as part of a chat session in response to detection by the communication system that the second session has ended. This may include providing the third party content provider with data indicating 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 involves receiving input from the user to the first session through the chat user interface on the communication server, and the communication server to a third-party content provider to the second session. Includes a step of providing data indicating user input of. In some implementations, the request to access a particular web resource involves voice input. In some implementations, the method involves receiving a second voice input from the user in a first session and a second voice input in a second session to a third-party content provider by means of a communication system. A step of providing data indicating a textual representation of the text input from a third-party content provider and a step of receiving text input from the third-party content provider in a second session between the communication system and the third-party content provider by the communication system. And the communication system includes a step of providing the user with data indicating a voice representation of the text input from the third party content provider in the first session.

In some implementations, the chat user interface is a chat widget. In some implementations, the step of 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 that particular web resource is determined by the communication system. The step of accessing the web resource, the step of identifying the widget on the web resource by the communication system, and the code for the widget on the web resource by the communication system, the web resource is third through the chat user interface on the web resource. Includes steps to identify tags that indicate that it provides functionality for live assistance by the party content provider.

In some implementations, live assistance is provided by a person representing a particular third-party content provider.

In some implementations, the method is for each of multiple chat sessions initiated for a particular web resource, a unique identifier for the content item that led the user to the particular web resource by the communication system. Includes a step to determine the content item metric value for a chat session based on. The method comprises the steps of generating a presentation of the content item metric value using the content item metric value by the communication system and providing the third party content provider with the presentation for display by the communication system. Including.

In some implementations, the step of 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 that particular web resource is determined by the communication system. In the step of accessing the web resource, the step of determining that the communication system has opened a new window different from the window in which the web resource is accessed, and in the new window, the web resource is a chat user interface on the web resource. Includes steps to determine text terms that indicate that it provides functionality for live assistance by a third-party content provider through.

In some implementations, the user accesses the chat session through a networked device. The networked device can be a mobile device. The networked device can be a desktop device. In some implementations, networked devices do not have a screen.

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

Another innovative aspect of the subject matter described herein implements a device communicably connected to a network, a third-party content provider server communicably connected to the network, and methods as described above. It can be embodied in a system that includes a communication server that performs operations to do so.

Yet another innovative aspect of the subject matter described herein is an executable instruction that, when executed by at least one processor, causes at least one processor to perform an operation to implement the method as described above. Can be embodied in at least one computer-readable storage medium encoded by.

Another innovative aspect of the subject matter described herein is that for each of the plurality of web resources, the communication server receives data demonstrating the characteristics of each web resource, and by the communication server. Based on the data received, the steps to detect that each web resource provides functionality for live assistance by a third-party content provider through the chat user interface on each web resource, and the communication server to the database, respectively. It can be embodied in a way that includes a step of storing an entry indicating that the web resource of the server has the same functionality. In this method, the communication server receives a request from a user to access a specific web resource hosted by a specific third-party content provider, and the communication server stores a stored entry in the database that represents the specific web resource. Based on the steps that determine that a particular web resource provides functionality for live assistance by a particular third-party content provider through a particular chat user interface on a particular web resource, and by a communication server, users and third parties. Includes steps to initiate 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. In this method, the communication server receives the input to the first session from the user through the chat user interface, and the communication server provides the third-party content provider with data indicating the user input to the second session. Includes steps to provide and maintain state information for chat sessions between users and third-party content providers. The method comprises a step of detecting by the communication system that there is no activity for a predetermined period of time, a step of detecting by the communication system that at least one of the first or second sessions has ended, and by the communication system. , A step of determining that the user has not completed the chat session based on the context data of the chat session, a step of storing data indicating the entire first session in the database, and a second step by the communication system. In response to the detection that the session has ended, a step of initiating a third session between the communication server and the third-party content provider as part of the chat session and the communication system allow the user to the third-party content provider. It can include a step of providing data indicating 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, requests to access a particular web resource include voice input. The method provides data indicating a step of receiving a second voice input from the user in the first session and a text representation of the second voice input to the third party content provider in the second session by the communication system. The step of providing and the step of receiving text input from the third party content provider from the third party content provider by the communication system and the text input from the third party content provider in the second session between the communication system and the third party content provider by the communication system and the user by the communication system. Includes, in the first session, a step of providing data indicating a voice representation of text input from a third party content provider.

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

In some implementations, the request is presented in response to a search request and provided in response to a selection of content items that link to a particular web resource. The chat interface can be presented on a web page displaying the results in response to a search request and the content item.

In some implementations, the chat user interface is a chat widget. In some implementations, the step of detecting that each web resource provides functionality for live assistance by a third-party content provider through a chat user interface on that web resource is accessed by the communication system. And by the communication system, the steps to identify the widget on the web resource, and by the communication system, in the code for the widget on the web resource, the web resource is sent by a third-party content provider through the chat user interface on the web resource. Includes steps to identify tags that indicate that it provides functionality for live assistance.

In some implementations, live assistance is provided by a person representing a particular third-party content provider. In some implementations, the method is for each of multiple chat sessions initiated for a particular web resource, a unique identifier for the content item that led the user to the particular web resource by the communication system. To determine the content item metric value for a chat session based on, and to generate a presentation of the content item metric value by using the content item metric value by the communication system, and to a third-party content provider by the communication system. Includes steps to provide the same presentation for display.

In some implementations, the step of detecting that each web resource provides functionality for live assistance by a third-party content provider through a chat user interface on that web resource is accessed by the communication system. And the step that the communication system determines that a new window has opened that is different from the window the web resource is accessing, and in the new window, the web resource has third-party content through the chat user interface on the web resource. Includes a step to determine a textual phrase indicating that it provides functionality for live assistance by the provider.

In some implementations, the user accesses the chat session through a networked device. The networked device can be a mobile device. The networked device can be a desktop device. In some implementations, networked devices do not have a screen.

Yet another innovative aspect of the subject matter described herein is a device communicably connected to a network, a third-party content provider server communicatively connected to the network, and a communication server operating. It can be embodied in a system that includes. The behavior is to receive data indicating the characteristics of each web resource for each of the multiple web resources, and based on the received data, each web resource has a chat user interface on each web resource. Includes detecting that it provides functionality for live assistance by a third-party content provider through, and storing in the database an entry indicating that each web resource has the same functionality. The behavior is based on receiving a request from a user to access a particular web resource hosted by a particular third-party content provider and a stored entry in a database that represents the particular web resource. Determines that provides functionality for live assistance by a particular third-party content provider through a particular chat user interface on a particular web resource, and a communication server chats between the user and the third-party content provider. Includes starting a session.

Another innovative aspect of the subject matter described herein is at least one computer-readable memory in which, when executed by at least one processor, an executable instruction that causes at least one processor to perform an operation is encoded. It can be embodied in a medium. The behavior is to receive data indicating the characteristics of each web resource for each of the multiple web resources, and based on the received data, each web resource has a chat user interface on each web resource. Includes detecting that it provides functionality for live assistance by a third-party content provider through, and storing in the database an entry indicating that each web resource has the same functionality. The behavior is based on receiving a request from a user to access a particular web resource hosted by a particular third-party content provider and a stored entry in a database that represents the particular web resource. Determines that provides functionality for live assistance by a particular third-party content provider through a particular chat user interface on a particular web resource, and a communication server chats between the user and the third-party content provider. Includes starting a session.

The subject matter described herein can be implemented in a particular embodiment to achieve one or more of the following advantages: The proposed system for initiating and maintaining a messaging session provides an efficient and optimized technique for identifying and interacting with the resources that provide the functionality of the chat interface. The proposed technology, in one aspect, is seamless and reliable on the chat interface functionality provided by the user interface terminal or resource or content provider, regardless of the browser function, service provider or operating system being used by the user. Implement a chat interface that includes chat sessions drawn and managed by a control or communication server / gateway to enable a capable and scalable chat interface. 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 the user and the gateway and between the content provider and the gateway to reestablish a disconnected chat session and storing session data. To. In addition, the gateway can keep sessions open in case of temporary connection loss, thus improving the reliability of chat connections. Even if a chat session cannot be kept open and must be reestablished, the user has to enter redundant data already provided through a previously established chat session without interruption. , You can continue the re-established chat session. In addition, by providing a chat interface without redirecting the user to the content provider's page, the system reduces network traffic associated with the user looking for chat functionality. The system allows users to connect and communicate with content providers without experiencing frustration when looking for messaging functionality within each content provider's page or when disconnected from the content provider. , Computer related technology, improve the function of chat interface.

In addition, gateway systems improve the capabilities of computer-related technologies by providing multiple content providers with the ability to scale chat functionality without the need for tight integration. The system allows content providers to maintain a certain degree of individuality and control over their chat interfaces. The ability of this system to have chat conversations without using the 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 scheduled to meet at 5 pm", the system will automatically detect that there is a calendar event and add a calendar entry to the existing conflict. You can ask the user about and perform various other related tasks. The effects that result from chat conversations can be logged and / or provided for analysis, and the results can be used to influence future chat interface presentations. Gateway systems reduce user latency because users with slow network connections are no longer required to visit content provider web pages and request the pages to be rendered. Instead, only communication is carried, reducing network traffic and latency.

It is a block diagram of an environment example in which a user can contact a content provider through various devices. It is an example of a user interface illustrated to provide a chat interface to a user. It is a flowchart of a process example for starting and maintaining a chat session between a user and a third party content provider. It is a block diagram of an example of a computing system.

Similar reference numbers and symbols in various drawings indicate similar elements.

This document describes methods, systems and devices that improve the connection strength and quality of communication sessions by providing a gateway between the user and the content provider with which the user is communicating. The gateway relays the content (eg, message) received on one of the user's communication interfaces to the other communication interface of the content provider, and one session directly between the user and the content provider without maintaining session data. As a result, the disconnection on the part of either the user or the content provider stores relevant data about the conversation between the user and the content provider, rather than ending the session without the ability to reestablish the chat session. Maintain session information by doing so.

In some situations, conversations between client devices can be interrupted or disconnected, causing frustration for users seeking help and content providers 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 try to call back, but if connected with a different person, the customer will have to explain the situation again, resulting in an overall inefficient and annoying experience for the customer. Here, the gateway displays specific data about the conversation between the user and the content provider in order to reduce the amount of information the user and content provider provided prior to disconnection and the amount of time spent trying to recover the progress achieved. Can be detected and stored. This is a computer-related technology by preventing the loss of data already communicated using the chat interface in the event of a chat interface failure (eg, loss of connection or other blockage of communication links). Electronic chat application / functionality will also be improved.

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 result 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 the user.

As used throughout this document, the term "digital component" refers to a unit of digital content or digital information (eg, a unit of video clip, audio clip, multimedia clip, image, text or other content). Digital components can be stored electronically on a physical memory device as a single file or as a set of files, and digital components take the form of video files, audio files, multimedia files, image files or text files. , And can contain advertising information, so that the advertisement is a kind of digital component. In general, a digital component is defined (or provided by) by a single provider or source (eg, 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 (eg, a group of different different digital components), and parts of different digital components from different sources can be found in search results (or other). It can be combined into a single digital component of the information extracted from the content part).

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

In some examples, the user can contact the content provider through the user interface provided on the web page of the particular content provider. The user interface can be, for example, a chat interface that allows the user to communicate with a person in charge of a particular content provider. Many web pages have different formats, including different arrangements of interface elements that guide the user to the chat interface. For example, a web page can include a button that guides the user to a chat interface.

Chat interfaces typically include a text box that allows the user to provide input that will be transmitted to the other party communicating with him. In addition, other user interface elements for submitting and editing user input may generally be included in the chat interface; such user interface elements are small elements that must be accessed by navigating the user interface menu. Can be. For example, commonly used interface elements include small buttons for sending messages or switching keyboards, or menus for selecting content to send, such as pictures or video data.

Some web pages may require users to navigate the website tree to reach the chat interface. For example, a user interface element that directs the user to a chat interface that allows the user to contact the content provider may appear on a page other than the main page of the content provider's website. The user interface element may be placed in an obscure position or sized so that the user has trouble selecting the user interface element to access the chat interface.

Chat interfaces can be difficult to use on mobile devices, as the screen area on mobile devices is generally smaller than the screen area on desktop client devices. For example, the screen area on a smartphone is generally smaller than the screen area on a desktop computer with a monitor. Small user interface elements 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. When viewed on a mobile device with a small screen, it can be difficult to interact with the chat interface. The user may have little ability to interact with the chat interface to interact with it, causing frustration for the user and reducing the value of providing the chat interface for many content providers.

When a chat session is initiated between the user and the content provider representative, the chat session disconnection generally reaches the same point in the conversation between the user and the content provider representative when the disconnection occurs. This means that the user must provide any information that he or she has already provided to the content provider. For example, a user looking for support for a particular type of ham radio through a chat interface for a chat session can ask the person in charge of the ham radio manufacturer they are using, their registration number, their wishes. Can provide a description of your broadcast frequency and your problem. If a user's chat session with a manufacturer's representative is disconnected, the user generally goes to the manufacturer's web page, finds a user interface element that guides them to the manufacturer's chat interface, and once a new chat session. Once established, re-provide all of the information you have already presented to another person in the manufacturer (ie your registration number, your desired broadcast frequency and a description of your problem). There must be.

This document describes methods, systems and devices that reduce the amount of computer resources used to perform and restore chat sessions between users and content providers. In some situations, the content provider's website contains a user interface element that guides the user to the chat interface and initiates a chat session between the user and the content provider representative. For example, a tractor company website can include a button to connect a user to a tractor company live rep. Buttons appear as navigation menu items, notably as a key feature on tractor company website support or contact pages, or based on user behavior while visiting the tractor company website. It can be displayed in various ways, including as a suggestion.

The 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 a chat interface. Once a website is identified as providing chat session functionality, such as a live chat session or an automated chat session where a library of answers is built using a messaging machine learning model, the system allows the web page to chat. It can be shown to provide sex. For example, the system can indicate in the search results that the website appears that the website provides the functionality of a chat session.

The messaging machine learning model may be a model that receives response data from the user and from the content provider as input. Messaging machine learning models include technologies such as decision trees, linear regression models, logistic regression models, neural networks, classifiers, support vector machines, inductive logic programming, and sets of models (eg, bagging, boosting, random forest, etc.) You can use any of a variety of models such as), genetic algorithms, Bayesian networks, etc., and various types such as deep learning, perceptrons, binding rules, inductive logic, clustering, maximum entropy classification, learning classification, etc. It is possible to train 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 a user interface element that allows a user to initiate a chat session with a content provider. Once the user chooses the user interface element to initiate a chat session with the content provider, the system identifies the characteristics of the chat session to use when initiating and facilitating the chat session. For example, the system may have a device identifier for the client device that the user provides input to the chat interface, a session identifier for a particular session between the client device and a particular contact for the content provider, and a particular contact for the content provider. Can store device identifiers 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 chat session with the content provider, and uses data indicating the inputs provided in the first and second chat sessions. 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, a personal digital assistant receives audio input (eg, verbal query or command) from a user through the personal digital assistant's microphone, and uses the audio output by the personal digital assistant's speaker to search the user for search results. 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 to a display or another device that presents information on the display (eg, wirelessly or by wire), the personal digital assistant will search results. Visual information, such as one or more of the other information associated with the and / or audio input, can also be presented. A personal digital assistant (PDA) can be implemented across multiple different physical devices (eg, mobile phones, tablets, audio / video streaming devices, tabletop PDA units and / or other devices), and the input is one of the devices. Note that it can be received by one (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 provided in response to a query or command may be output by one of the devices (eg, audio information output by a tabletop PDA unit), while different parts of the information (eg, eg). , Visual information) can be presented by a different device (eg, a display including a mobile phone or audio / video streaming device).

As part of the audio output and / or visual information, the PDA can offer the option for the user to initiate a chat session. For example, a PDA may ask the user if he or she wants to connect to or chat with an agent that can provide more information to the user, and the user affirms his or her desire to connect to the agent. Can respond by voice (for example, by speaking the word "yes" or the word "connect with an agent"). In response to the user affirming his or her desire to connect to the 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). It is configured to make a voice call over the phone, eg, using a mobile device and / or a tabletop PDA unit). When a user is connected to an agent, the techniques discussed throughout this document can be used to maintain the state of the chat session (eg, text or voice), thereby even if the chat session is interrupted. Allows chat sessions to continue seamlessly. For voice chat sessions, voice recognition techniques can be used to convert voice dialogues into text, and as a result the techniques discussed herein can also be used in those situations.

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

The mobile device 102, the client device 104, and the screenless assistant device 106 are electronic devices that can request and receive resources through the network, respectively. Examples of mobile devices 102 include mobile phones, smartphones, tablets, and other portable mobile devices that allow users to connect to content providers over a network. Client device example 104 includes personal computers, mobile workstations and laptop computers. Devices 102, 104 and 106 typically include user applications such as web browsers to facilitate the transmission and reception of data over the network, while native applications executed by client device 104 also transmit and receive data over the network. Can be promoted.

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

Search results are data generated by a search system that identifies electronic documents that are responding to (eg, related to) a particular search query, and the network specified to the client device in response to user interaction with the search results. Includes an active link (eg, a hypertext link) that requests data from a location (eg, a URL). Examples of search results can include a web page title, a snippet or part of an image of text extracted from the web page, and a URL of the web page. Other search result examples include the title of the downloadable application, a text snippet describing the downloadable application, an image depicting the user interface of the downloadable application, and / or the application downloaded to device 102, 104 or 106. It can include a URL to a possible location.

In some situations, the search system is an application store (or application store) where the application is downloadable for installation on the client device in order to provide information about the downloadable application associated with the submitted search query. Can be part of an online portal) or can interact with it. Like other electronic documents, a search results page is one or more digital components that can be presented with digital components (eg, video clips, audio clips, images, or other digital components that can be formatted as advertisements). Can include slots.

Gateway 110 facilitates chat sessions and includes backends and frontends. The gateway 110 backend provides the infrastructure for chat sessions and communicates separately with content providers and users. For example, the backend uses the data entered by the user through the client device to have a chat session with the content provider, as well as the data entered by the content provider representative to have a chat session with the user. It can be carried out. The backend interface can be a common format or package that the user or content provider agrees on, such as a particular script application programming interface (API), a particular android application package (.apk) or various other suitable packages. ..

The front end of gateway 110 can be an interface on which one of the user and the content provider can provide the input to be transmitted and presented to the other. For example, the front end can be a chat interface that is presented separately to the user and content provider. The front end can be customized for the user and for the content provider, and can have default profile settings or can be adjusted by the user or content provider. For example, the front end for the user can include a larger text box and bold font, while the front end for the content provider can include additional features such as remote access and control of the user's device.

The gateway 110 identifies each web page that provides messaging functionality and stores data indicating that the web page provides that functionality. Identification of a web page that provides messaging functionality is generally done before the web page is presented as search results, rather than when the search request is executed.

Web pages that provide messaging functionality typically include user interface elements that allow the user to initiate a messaging session, such as a button to initiate a chat session. For example, the web page 120 is illustrated to include a button 122 that allows the user to choose to initiate a chat session with the content provider. Web page 120 can also include various other indications that messaging functionality is provided or supported, such as key text terms. For example, web page 120 contains text that reads "chat with someone now."

Gateway 110 also provides messaging or chat functionality by detecting certain script features of web page 120, such as code snippets that open a new window when the user selects a particular user interface element. Then it can be identified. Another feature of the web page 120 that may be used to determine if the web page 120 provides chat functionality is that the web page 120 is displayed on the web page 120, which links to a different website or provider. Whether to include a widget. For example, web page 120 probably provides chat functionality if it provides a widget that communicates with a known chat service provider. The widget can include an identifier for a particular session in addition to other communication information, such as an identifier for a particular client device, a particular case, etc.

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

When the gateway 110 receives the initial search request, the gateway 110 accesses the 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 the search results web page. Generates a user interface element that will be presented with the search results.

The content provider system 130 can be a network destination that is associated with a particular content provider and provides resources in response to search queries. For example, the 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 the person in charge of the content provider to interact with the user. In some examples, the user interface is a chat interface through which personnel can communicate with the user in real time.

Gateway 110 reduces the number of computing resources used to initiate and maintain chat sessions between users and content providers. In addition, by reducing the user's need to navigate to the content provider's web page, the gateway 110 states that the user must look for chat functionality and transmit data about 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 can 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 a communication gateway such as gateway 110.

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

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

When the user selects one of the user interface elements 212, 222, 232 or 242, the gateway 110 establishes a chat session between the user and the content provider providing the corresponding search result web pages 210, 220, 230 or 240. Start. In the example illustrated in FIG. 2, the user selects the user interface element 212 associated with the search result web page 210. Chat sessions are drawn this way and are therefore managed by the gateway. This is a seamless chat session regardless of the particular browser, operating system and any other user device or system that the gateway or server associated with the gateway is currently using by the user and / or content provider. Allows you to implement control and any required protocols and data structures to ensure the scalability, security, reliability and storage associated with.

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

In order to maintain a session between the user and the content provider when the gateway 110 manages many different conversations between many different users and the content provider, the gateway 110 provides content from one session with the user. Guide the response to another session with the provider. The gateway 110 uses stored data indicating a session identifier in order to properly transfer a message between the user and the content provider.

The gateway 110 can receive input in various formats, format the input, and provide the input for a chat session between the user and the content provider. 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 a content provider, and receiving a text message at a particular phone number can trigger the start of a chat session with the content provider. For example, receiving a text message at a particular phone number can be invoked to communicate the system with gateway 110 and provide user input as input to a chat session. When the user receives the response from the content provider, the gateway 110 can provide the user with the response 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.

The gateway 110 can process input from users or content providers in various formats. For example, a chat session with a content provider can be initiated if the user uses the mobile device 102 to interact with the gateway 110 and chooses user interface element 212 to initiate an email conversation with the content provider. , And user input and responses can be presented within the email client interface.

In some implementations, with traditional conversation, gateway 110 can provide a particular identifier, such as a telephone number, to which the user can provide input. For example, if the user is already connected to the content provider and the user input is provided to a different application such as a text message application or an email client, the gateway 110 can detect the user input depending on the content provider. The user's input can then be translated into the input that will be provided for 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 the data transferred to establish the chat session. For example, the chat interface can be presented on search result page 204. As mentioned above, the chat interface can include user interface elements from which the user can enter data. For example, the chat interface can include a text box where the user can enter a response or question that will be provided to the content provider, and a button where the user can submit input. Additional interface elements may be provided within the chat interface, such as file attachments, screen sharing, etc.

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

Once the session is established, certain metrics such as click-through rate, conversion rate, average traffic, access time, etc. can be calculated for the chat interface method of communicating with the content provider. For example, the click-through rate associated with a chat functionality user interface element can be calculated. In some implementation examples, content providers have access to reports generated using calculated metrics. For example, content providers may consider adjusting the campaign budget for chat interfaces based on reports on the performance of chat interface methods and 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 the fixed client device 104 to interact with the user and the content provider. Can facilitate conversations between. However, since the screenless assistant device 106 does not include a screen, the method of receiving and outputting data involves additional steps. The screenless assistant device 106 can receive various types of suitable inputs, such as voice or touch inputs. 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 textual data representing voice input can be extracted. In some implementations, the screenless assistant device 106 processes the voice input, while in other implementations the gateway 110 or the remote system processes the voice input.

Gateway 110 can then use the text data as input to a session with the content provider. 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, when the screenless assistant device 106 receives the voice input, the screenless assistant device 106 can receive the output data including the voice data.

In an exemplary use of system 100, the user can provide voice input to the mobile device 102 by saying "I want to talk to ABC customer service." The mobile device 102 can then display search results that may include a web page identified as providing messaging functionality along with a user interface element that allows the user to initiate a messaging session.

The user can continue the conversation with the content provider on different devices. For example, if the user initiates a messaging session with the content provider on the mobile device 102, the user can continue the conversation with the content provider on the screenless assistant device 106. The gateway 110 can detect the device the user is providing input to or accessing the messaging session and can select the appropriate output method such as text, voice, picture, etc.

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 the information already provided by the user or the content provider. Reduce the amount of computing resources. For example, a user can continue a chat session without interruption and without having to enter redundant data that has already been entered through an already established chat session. In addition, the gateway 110 improves the robustness of the chat session by keeping the sessions between the user and the content provider separate, so that the chat session is not terminated by the temporary disconnection of any session.

In some examples, the gateway 110 stores the conversation by storing data from the conversation as the conversation between the user and the content provider takes place. If the user and content provider are disconnected, the gateway 110 will reestablish at least some of the stored data for the conversation up to where the user and content provider were disconnected in order to reestablish the conversation between the user and the content provider. use.

When the chat session is reestablished, the gateway 110 engages in a conversation with the content provider (or to the content provider) without further input from the user in order to catch up with the content provider to the point of the conversation that has already taken place with the user. Can provide a previous chat session). For example, the gateway 110 allows the next person in charge of the content provider to which the user is connected to be notified of the user's status so that the user can continue his or her conversation with the person without repeating the information already provided. As such, stored data indicating the user's device information and problem description can be automatically provided. The gateway 110 can autonomously determine the answer to the content provider's response using a machine learning model trained using the answer already provided by the user. The machine learning model can take the response of the content provider as input and output various 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 continue the conversation from a particular location, such as when the user leaves the conversation. By doing so, server-side integration is performed. For example, once the gateway 110 establishes a new messaging session, the gateway 110 can provide stored data to different content provider personnel.

In some implementations, gateway 110 is unable to update new personnel up to the point of the previous conversation. For example, the new contact's response to certain information may differ from the previous contact's response, and the gateway 110 will provide the gateway 110 with all the information that the user could have previously provided to the contact. You may not be able to proceed in the direction you can provide. When the gateway 110 is unable to provide all of the information already provided by the user, the gateway 110 can provide the user with context for conversations that take place without the user.

The gateway 110 can also perform client-side integration by storing session data or user input. The gateway 110 can provide the user with stored data when the conversation is caught up or the gateway 110 is updated as much as possible, so that the user has a context for understanding the situation of the content provider personnel.

The gateway 110 can detect when the user is inactive or free. For example, if the user leaves his device without going to a meeting or notifying a content provider representative, the gateway 110 can mark the case as inactive. The gateway 110 can determine if the user is inactive based on various characteristics of the current conversation. Such characteristics include the threshold period elapsed between the content provider's last response and the user's last response, some words entered by the user, some words entered by the content provider, or the gateway 110. Contains various event data associated with the accessing user. For example, if the meeting is scheduled during the user's conversation, the gateway 110 can determine that the user is in a meeting if the user does not respond within the threshold time amount.

If the conversation is marked as inactive, the gateway 110 can notify the content provider that the user is absent. For example, if the user is detected to be inactive, the gateway 110 provides the content provider contact on behalf of the user with a response asking the content provider contact to wait a few minutes and stay connected. it can.

In some examples, gateway 110 can mark the case as resolved instead of inactive. For example, the content provider has solved the user's problem, for example, the user does not respond for the threshold amount of time, but the user responds "great, this is enough, thank you" in the response provided by the user. For example, the gateway 110 can mark the conversation as resolved. The gateway 110 or the device 102, 104 or 106 with which the user is communicating with the content provider may also require input from the user or content provider to clarify whether the problem has been resolved. For example, the screenless assistant device 106 can provide the user with audio output asking if the problem has been resolved, apart from the conversation between the user and the content provider. If the user provides an acknowledgment, the screenless assistant device 106 can provide the response to gateway 110, which can mark the conversation as resolved and does not prompt or otherwise elicit further response from the user. ..

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

FIG. 3 is a flowchart of Step Example 300 for starting and maintaining a chat session between a user and a third party content provider. In some implementation examples, step 300 can be implemented by a messaging system such as system 100. For example, step 300 can be implemented by the gateway 110 of FIG. In some implementations, step 300 can be implemented as an instruction stored on a non-temporary computer-readable medium, and when the instruction is executed by one or more servers, the instruction is one or more. The server can be made to perform the operation of step 300.

When step 300 starts, for each of the plurality of web resources, the communication server receives data indicating the characteristics of each web resource (302). For example, the gateway 110 can receive data that characterizes a particular web page, including whether the web page contains a particular phrase, widget, code snippet, and so on.

Step 300 is followed by for each of the plurality of web resources, based on the data received by the communication server, each web resource provides live assistance by a third party content provider through a chat user interface on each web resource. 304 to detect that it provides functionality for. In some examples, the chat user interface is a chat widget. Live assistance can be provided by a human representative of a particular third party content provider. The chat user interface can be presented on a web page displaying the results in response to a search request and the content item. In some examples, the user accesses the chat session through a networked device. The networked device can be either a mobile device, a desktop device, or various other networked devices. In some examples, networked devices do not have a screen.

In some examples, detecting is 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, and in the new window the web resource is Includes determining text terms that indicate that it provides functionality for live assistance by a third-party content provider through a chat user interface on a web resource.

In some examples, detecting is accessing a web resource, identifying a widget on the web resource, and in the code for the widget on the web resource, the web resource is a chat user on the web resource. Includes identifying tags that indicate that it provides functionality for live assistance by third-party content providers through the interface.

Step 300 subsequently stores, for each of the plurality of web resources, an entry in the database indicating that each web resource has the same functionality (306). For example, the gateway 110 can store in the database an entry indicating that a particular web page has messaging functionality.

Step 300 subsequently receives a request from the user to access a particular web resource hosted by a particular third party content provider (308). For example, a user can select a search result link that directs the user to a web resource associated with a particular content provider. In some examples, the request is presented in response to a search request and is provided in response to a selection of content items that link to a particular web resource. In some examples, requests to access a particular web resource include voice input.

Step 300 is followed by a communication server performing live by a particular third-party content provider through a particular chat user interface on a particular web resource, based on a stored entry in a database representing the particular web resource. Determined to provide functionality for assistance (310).

Step 300 then initiates a chat session between the user and the third party content provider by the communication server (312). For example, the 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 is to receive a first unique session identifier for the first session of the chat session from the third party content provider and to the third party content provider by the communication server. Includes providing a first unique session identifier to facilitate a session of.

In some examples, step 300 receives input to the first session through the chat user interface and provides the third party content provider with data indicating user input to the second session. Including. Step 300 is a content item metric value for a chat session based on the unique identifier of the content item that led the user to the particular web resource for each of the plurality of chat sessions initiated for the particular web resource. Further includes determining, using the content item metric value to generate a presentation of the content item metric value, and providing the third party content provider with the same presentation for display. For example, the content item metric value can include a click-through rate associated with chat functionality.

In some examples, step 300 includes detecting that there is no activity for a predetermined period of time and that at least one of the first or second sessions has ended. Step 300 includes determining that the user has not completed the chat session based on the context data of the chat session, and storing data indicating the entire first session in the database. Step 300 then initiates a third session between the communication server and the third party content provider as part of the chat session in response to the detection that the second session has ended, and by the communication system. The third party content provider can be provided with data indicating 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, step 300 further comprises receiving a second voice input from the user in the first session. Step 300 subsequently provides the third party content provider with data indicating a textual representation of the second voice input in the second session. Step 300 subsequently receives text input from the third-party content provider through the communication system in a second session between the communication system and the third-party content provider. Step 300 can subsequently provide the user with data indicating a voice representation of the text input from the third party content provider in the first session.

FIG. 4 is a block diagram of a computer system example 400 that can be used to perform the above operations. The system 400 includes a processor 410, a memory 420, a storage device 430 and an input / output device 440. Each of the components 410, 420, 430, 440 can be interconnected using, for example, the system bus 450. 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 is capable of processing instructions stored in memory 420 or in storage device 430.

The memory 420 stores information in the system 400. In one implementation example, the memory 420 is a computer-readable medium. In one implementation example, the memory 420 is a volatile memory unit. In another implementation, the memory 420 is a non-volatile memory unit.

The storage device 430 can provide a large amount of storage for the system 400. In one implementation, the storage device 430 is a computer-readable medium. In a variety of different implementations, the storage device 430 may include, 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 be included.

The input / output device provides input / output operations for system 400. In one implementation, the I / O device may be 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 include. In another example implementation, the input / output device may include a driver device that is configured to receive the input data and send the output data to other input / output devices such as a keyboard, printer and display device 460. However, other implementation examples such as mobile computing devices, mobile communication devices, set-top box TV client devices, etc. can also be used.

Examples of processing systems are shown in FIG. 4, but implementation examples of the subject matter and functional operations described herein are in other types of digital electronic networks, or the structures and theirs disclosed herein. It can be implemented in computer software, firmware or hardware, including structural equivalents, or in one or more combinations thereof.

Electronic documents (for short, simply referred to as documents) do not necessarily correspond to files. A document may be stored in a portion of a file holding another document, in a single file dedicated to the document, or in multiple linked files.

Embodiments of the subject matter and operations described herein are in digital electronic networks, or in computer software, firmware or hardware, including the structures and their structural equivalents disclosed herein, or them. It can be implemented in one or a combination of two or more. Embodiments of the subject matter described herein are encoded in one or more computer programs, i.e., one or more computer storage media for execution by a data processor or to control its operation. It can be implemented as one or more modules of computer program instructions. Alternatively, or in addition, a program instruction is an artificially generated propagating signal, eg, machine-generated electricity, generated to encode information to be transmitted to a suitable receiver device for execution by a data processing device. It can be encoded on an optical or electromagnetic signal. The computer storage medium can be, or can be included in, a computer readable storage device, a computer readable storage board, a random or serial access memory array or device, or a combination thereof. Moreover, the computer storage medium can be the source or destination of the computer program instructions encoded in the artificially generated propagation signal, whereas the computer storage medium is not the propagation signal. The computer storage medium can also be, or can be included in, one or more separate physical components or media (eg, multiple CDs, discs or other storage devices).

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

The term "data processor" includes all types of devices, devices and machines for processing data, including, for example, programmable processors, computers, system-on-chips or a plurality or combinations thereof. The device can include a dedicated logic network, such as an FPGA (Field Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit). The device, in addition to the hardware, is the code that creates the execution environment for the computer program, such as processor firmware, protocol stack, database management system, operating system, cross-platform runtime environment, virtual machine or one of them. Alternatively, the code that constitutes a plurality of combinations can also be included. Equipment and execution environments can implement a variety of different computing model infrastructures such as web services, distributed computing and grid computing infrastructures.

Computer programs (also known as programs, software, software applications, scripts or code) can be written in any form of programming language, including compiler or interpreted languages, declarative or procedural languages, and It can be deployed in any format, including as a stand-alone program or as a module, component, subroutine, object or other unit suitable for use in a computing environment. Computer programs may or may not correspond to files in the file system. A program may be part of a file that holds another program or data (eg, one or more scripts stored in a markup language document), a single file dedicated to that program, or multiple linked files. It can be stored in (for example, a file that stores one or more modules, subprograms, or parts of code). Computer programs can be deployed and run on one computer, or on multiple computers that are located at one site or distributed across multiple sites and interconnected by communication networks.

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

Processors suitable for running computer programs include, for example, both general purpose and dedicated microprocessors. In general, the processor will receive instructions and data from read-only memory and / or random access memory. Essential elements of a computer are a processor for acting according to instructions and one or more memory devices for storing instructions and data. In general, a computer also includes or is operatively coupled with one or more mass storage devices for storing data, such as magnetic, magneto-optical disks or optical disks, from which it receives or receives data. You will either transfer or both. However, the computer does not need to have such a device. Moreover, computers are other devices, such as mobile phones, personal digital assistants (PDAs), mobile audio or video players, game consoles, Global Positioning System (GPS) receivers, or portable storage devices, to name a few. It can be embedded in (for example, a universal serial bus (USB) flash drive). Suitable devices for storing computer program instructions and data include, for 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 includes all forms of non-volatile memory media and memory devices, including DVD-ROM disks. Processors and memory can be supplemented or embedded in a dedicated logic network.

To provide interaction with the user, embodiments of the subject matter described herein include display devices for displaying information to the user, such as a CRT (cathode tube) or LCD (liquid crystal display) monitor, as well. It can be implemented on a computer with a keyboard and pointing device that allows the user to provide input to the computer, such as a mouse or trackball. Other types of devices can also be used to provide user interaction, for example, the feedback provided to the user may be any form of sensory feedback, such as visual feedback, auditory feedback or tactile feedback. Yes, and input from the user can be received in any form, including acoustic, voice or tactile input. In addition, the computer sends a document to the device used by the user and then receives the document, for example, sending a web page to the 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 a back-end component, eg, as a data server, or a middleware component, eg, an application server, or a front-end component, eg, a user described herein. Can be implemented on a computing system, including a client computer with a graphical user interface or web browser capable of interacting with an example implementation of the subject, or any combination of one or more such backends, middleware or frontend components. Is. The components of the system can be interconnected by any form or medium of digital data communication, such as 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. Clients and servers are generally separated from each other and typically interact through communication networks. The client-server relationship runs on each computer and is caused by computer programs that have a client-server relationship with each other. In some embodiments, the server transmits data (eg, HTML pages) to the client device (eg, for the purpose of displaying the data to the user interacting with the client device and receiving user input from the user). The data generated on the client device (eg, the result of the user dialogue) can be received from the client device on the server.

Whereas this specification contains many specific implementation details, they are not limited to the scope of any invention or claims, but rather are specific to a particular embodiment of a particular invention. It should be interpreted as a description of the features. Certain features described herein in the context of different embodiments can be combined and implemented in a single embodiment. Conversely, the various features described in the context of a single embodiment can be implemented separately in multiple embodiments or in any suitable subcombination. Moreover, it is mentioned above that the features work in a combination, and so first claimed, but one or more features from the claimed combination, in some cases, the same combination. The combination that can be removed from and claimed can be a subcombination or a variant of the subcombination.

Similarly, while the actions are drawn in the drawing in a particular order, this is all done so that such actions are performed in the particular order or sequence shown, or to achieve the desired result. It should not be understood that the illustrated behavior of is required to be performed. In some situations, multitasking and parallelism can be advantageous. Moreover, the separation of various system components in the above embodiments should not be understood as requiring such separation in all embodiments, and the program components and systems described are generally single software. It should be understood that both can be integrated into a product or implemented in multiple software products.

Thus, specific embodiments of the subject have been described. Other embodiments are within the scope of the following claims. In some cases, the actions listed in the claims may be performed in a different order and still achieve the desired result. In addition, the steps depicted in the accompanying figures do not necessarily require the particular order or order shown to achieve the desired result. In some implementations, multitasking and parallelism can be advantageous.

100 systems 102 mobile devices,
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 result page 210 Search result web page 220 Search result web page 230 Search result web page 240 Search result 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 (39)

The step of receiving a content search request from the user by the communication server,
A step of obtaining search results in the form of a plurality of selectable content items on a display web page by the communication server in response to the search request, and each selectable content item is associated with the search request. Steps and steps, including links to their respective web resources
For live assistance by a particular third-party content provider through a particular chat user interface on the particular web resource by said communication server based on information obtained from a database of the characteristics of multiple web resources. Steps to determine that it provides functionality and
A step of automatically providing a chat interface on the display web page for the particular web resource, wherein the chat interface is adjacent to each of the selectable content items on the display web page. Including steps that are drawn and / or controlled by the communication server for display.
In response to a user interaction with the chat interface from the display web page, the communication server provides a chat session between the user and the particular third-party content provider associated with the particular web resource. Start,
Method. A step to populate a database with database entries for multiple web resources.
For each of the plurality of web pages
In the communication server, a step of receiving data indicating the characteristics of each web resource, and
A step of detecting by the communication server that, based on the received data, each of the web resources provides functionality for live assistance by a third-party content provider through a chat user interface on each of the web resources.
The communication server further comprises setting data in the database, including storing an entry indicating that each of the web resources has said functionality.
The method of claim 1, wherein the steps for populating the database are performed periodically to acquire data for a web page that is not yet included in the database. The first aspect of claim 1, wherein the chat session comprises i) a first session between the communication server and the user, and ii) a second session between the communication server and the third party content provider. the method of. A step of detecting that the chat session is inactive for a predetermined period of time by the communication system.
A step of detecting that at least one of the first session or the second session has been completed by the communication system.
A step of determining that the user has not completed the chat session based on the context data of the chat session by the communication system.
A step of storing data indicating the entire first session in the database, and
A step of initiating a third session between the communication server and the third-party content provider as part of the chat session in response to detection by the communication system that the second session has ended.
The communication system comprises providing the third party content provider with the data indicating at least a portion of the first session so that the user can resume the chat session with the third party content provider.
The method according to claim 3. A step of receiving an input to the first session from the user through the chat user interface in the communication server.
The communication server comprises providing the third party content provider with data indicating the user input to the second session.
The method according to claim 3. The method of claim 3, wherein the request to access the particular web resource comprises voice input. A step of receiving a second voice input from the user in the first session by the communication system.
A step of providing the third party content provider with data indicating a textual representation of the second voice input in the second session.
A step of receiving text input from the third-party content provider from the third-party content provider by the communication system in the second session between the communication system and the third-party content provider.
The communication system comprises providing the user with data indicating a voice representation of the text input from the third party content provider in the first session.
The method according to claim 6. The method according to claim 1, wherein the chat user interface is a chat widget. The determination step is
The step of accessing the web resource by the communication system and
A step of identifying a widget on the web resource by the communication system,
A tag indicating that the web resource provides functionality for live assistance by a third party content provider through a chat user interface on the web resource in the code for the widget on the web resource by the communication system. 8. The method of claim 8, comprising: The method of claim 1, wherein the live assistance is provided by a person representing the particular third party content provider. For each of the plurality of chat sessions initiated for the particular web resource, the chat session is based on the unique identifier of the content item that led the user to the particular web resource by the communication system. Steps to determine the content item metric value for
A step of generating a presentation of the content item metric value by using the content item metric value by the communication system.
A step of providing the presentation for display to the third party content provider by the communication system.
The method according to claim 1. The determination step is
The step of accessing the web resource by the communication system and
A step of determining that the communication system has opened a new window different from the window in which the web resource is being accessed.
1. The new window comprises the step of determining a textual phrase indicating that the web resource provides functionality for live assistance by a third party content provider through a chat user interface on the web resource. The method described in. The method of claim 1, wherein the user accesses the chat session through a networked device. 13. The method of claim 13, wherein the networked device is a mobile device. 13. The method of claim 13, wherein the networked device is a desktop device. 13. The method of claim 13, wherein the networked device does not have a screen. The step to start is
A step of receiving a first unique session identifier for the first session of the chat session from the third party content provider by the communication server.
The method of claim 1, comprising the step of providing the third party content provider with the first unique session identifier to facilitate the second session by means of the communication server. Devices that are communicatively connected to the network and
A third-party content provider server that is communicably connected to the network
A communication server that performs an operation for implementing the method according to any one of claims 1 to 17 is provided.
system. At least one encoded executable instruction that, when executed by at least one processor, causes the at least one processor to perform an operation to implement the method according to any one of claims 1 to 17. Computer-readable storage medium. For each of multiple web resources
In the communication server, the step of receiving data showing the characteristics of each web resource,
A step of detecting by the communication server that, based on the received data, each of the web resources provides functionality for live assistance by a third-party content provider through a chat user interface on each of the web resources.
A step of storing an entry in the database by the communication server indicating that each of the web resources has the functionality.
The step of receiving a request from a user to access a specific web resource hosted by a specific third-party content provider by the communication server.
Based on the stored entries in the database representing the particular web resource by the communication server, the particular web resource is live by the particular third party content provider through a particular chat user interface on the particular web resource. Steps to determine that it provides functionality for assistance, and
The communication server includes a step of initiating a chat session between the user and the third party content provider.
Method. 20. The chat session comprises i) a first session between the communication server and the user, and ii) a second session between the communication server and the third party content provider. the method of. A step of receiving an input to the first session from the user through the chat user interface in the communication server.
A step of providing the third party content provider with data indicating the user input to the second session by the communication server.
A step of maintaining state information of the chat session between the user and the third party content provider.
21. The method of claim 21. A step in which the communication system detects that there is no activity for a given period of time,
A step of detecting that at least one of the first session or the second session has been completed by the communication system.
A step of determining that the user has not completed the chat session based on the context data of the chat session by the communication system.
A step of storing data indicating the entire first session in the database, and
A step of initiating a third session between the communication server and the third-party content provider as part of the chat session in response to detection by the communication system that the second session has ended.
The communication system comprises providing the third party content provider with the data indicating at least a portion of the first session so that the user can resume the chat session with the third party content provider.
21. The method of claim 21. 21. The method of claim 21, wherein the request to access the particular web resource comprises voice input. A step of receiving a second voice input from the user in the first session by the communication system.
A step of providing the third party content provider with data indicating a textual representation of the second voice input in the second session.
A step of receiving text input from the third-party content provider from the third-party content provider by the communication system in the second session between the communication system and the third-party content provider.
The communication system comprises providing the user with data indicating a voice representation of the text input from the third party content provider in the first session.
24. The method of claim 24. The step to start is
A step of receiving a first unique session identifier for the first session of the chat session from the third party content provider by the communication server.
21. The method of claim 21, comprising the step of providing the third party content provider with the first unique session identifier to facilitate the second session by means of the communication server. 20. The method of claim 20, wherein the request is provided in response to i) a search request and ii) a selection of content items that link to the particular web resource. 27. The method of claim 27, wherein the chat user interface is presented on a web page that i) responds to the search request and ii) displays the content item. The method of claim 20, wherein the chat user interface is a chat widget. The step to detect is
The step of accessing the web resource by the communication system and
A step of identifying a widget on the web resource by the communication system,
A tag indicating that the web resource provides functionality for live assistance by a third party content provider through a chat user interface on the web resource in the code for the widget on the web resource by the communication system. 29. The method of claim 29, comprising: 20. The method of claim 20, wherein the live assistance is provided by a person representing the particular third party content provider. For each of the plurality of chat sessions initiated for the particular web resource, the chat session is based on the unique identifier of the content item that led the user to the particular web resource by the communication system. Steps to determine the content item metric value and
A step of generating a presentation of the content item metric value by using the content item metric value by the communication system.
A step of providing the presentation for display to the third party content provider by the communication system.
The method of claim 20. The step to detect is
The step of accessing the web resource by the communication system and
A step of determining that the communication system has opened a new window different from the window in which the web resource is being accessed.
20. The new window comprises the step of determining a textual phrase indicating that the web resource provides functionality for live assistance by a third party content provider through a chat user interface on the web resource. The method described in. 20. The method of claim 20, wherein the user accesses the chat session through a networked device. 34. The method of claim 34, wherein the networked device is a mobile device. 34. The method of claim 34, wherein the networked device is a desktop device. 34. The method of claim 34, wherein the networked device does not have a screen. Devices that are communicatively connected to the network and
A third-party content provider server that is communicably connected to the network
It ’s a communication server,
For each of multiple web resources
Receiving data showing the characteristics of each web resource
Detecting that each of the web resources provides functionality for live assistance by a third-party content provider through the chat user interface on each of the web resources, based on the data received.
To store an entry in the database indicating that each of the web resources has the functionality.
Receiving requests from users to access certain web resources hosted by certain third-party content providers,
A feature for live assistance by the particular third-party content provider through a particular chat user interface on the particular web resource, based on a stored entry in the database representing the particular web resource. Determining to provide sex and
The communication server comprises a communication server that performs operations including initiating a chat session between the user and the third-party content provider.
system. When executed by at least one processor, the at least one processor
For each of multiple web resources
Receiving data showing the characteristics of each web resource on the communication server,
The communication server detects that, based on the received data, each of the web resources provides functionality for live assistance by a third-party content provider through a chat user interface on each of the web resources.
The communication server stores an entry in the database indicating that each of the web resources has the functionality.
The communication server receives a request from a user to access a particular web resource hosted by a particular third-party content provider.
Based on the stored entries in the database representing the particular web resource by the communication server, the particular web resource is live by the particular third party content provider through a particular chat user interface on the particular web resource. Determining that it provides functionality for assistance,
An executable instruction-encoded at least one computer-readable storage medium that causes the communication server to perform operations, including initiating a chat session between the user and the third-party content provider.

Images