Abstract: Provided are systems and methods for creating custom dialog system engines. The system comprises a dialog system interface installed on a first server or a user device and a platform deployed on a second server. The platform is configured to receive dialog system entities and intents associated with a developer profile and associate the dialog system entities with the dialog system intents to form a custom dialog system engine associated with the dialog system interface. The web platform receives a user request from the dialog system interface, activates the custom dialog system engine based on identification, and retrieves the dialog system entities and intents. The user request is processed by applying the dialog system entities and intents to generate a response to the user request. The response is sent to the dialog system interface.

Abstract: Invoking an agent during a dialog between a user and an automated assistant. Some implementations are directed to receiving, during a human-to-automated assistant dialog, natural language input of the user that indicates a desire to engage an agent, but that fails to indicate a particular agent to be engaged. Those implementations are further directed to selecting a particular agent from a plurality of available agents, and transmitting an invocation request to the selected particular agent. In some implementations an agent selection model can be utilized in selecting the particular agent, such as a machine learning model. The machine learning model can be trained to enable generation of output that indicates, for each of a plurality of available agents (and optionally intent(s) for those agents), a probability that the available agent (and optionally intent) will generate appropriate responsive content.

Abstract: Invoking an agent during a dialog between a user and an automated assistant. Some implementations are directed to receiving, during a human-to-automated assistant dialog, natural language input of the user that indicates a desire to engage an agent, but that fails to indicate a particular agent to be engaged. Those implementations are further directed to selecting a particular agent from a plurality of available agents, and transmitting an invocation request to the selected particular agent. In some implementations an agent selection model can be utilized in selecting the particular agent, such as a machine learning model. The machine learning model can be trained to enable generation of output that indicates, for each of a plurality of available agents (and optionally intent(s) for those agents), a probability that the available agent (and optionally intent) will generate appropriate responsive content.

Abstract: Invoking an agent during a dialog between a user and an automated assistant. Some implementations are directed to receiving, during a human-to-automated assistant dialog, natural language input of the user that indicates a desire to engage an agent, but that fails to indicate a particular agent to be engaged. Those implementations are further directed to selecting a particular agent from a plurality of available agents, and transmitting an invocation request to the selected particular agent. In some implementations an agent selection model can be utilized in selecting the particular agent, such as a machine learning model. The machine learning model can be trained to enable generation of output that indicates, for each of a plurality of available agents (and optionally intent(s) for those agents), a probability that the available agent (and optionally intent) will generate appropriate responsive content.

Abstract: Invoking an agent during a dialog between a user and an automated assistant. Some implementations are directed to receiving, during a human-to-automated assistant dialog, natural language input of the user that indicates a desire to engage an agent, but that fails to indicate a particular agent to be engaged. Those implementations are further directed to selecting a particular agent from a plurality of available agents, and transmitting an invocation request to the selected particular agent. In some implementations an agent selection model can be utilized in selecting the particular agent, such as a machine learning model. The machine learning model can be trained to enable generation of output that indicates, for each of a plurality of available agents (and optionally intent(s) for those agents), a probability that the available agent (and optionally intent) will generate appropriate responsive content.

Abstract: Provided are systems and methods for creating custom dialog system engines. The system comprises a dialog system interface installed on a first server or a user device and a platform deployed on a second server. The platform is configured to receive dialog system entities and intents associated with a developer profile and associate the dialog system entities with the dialog system intents to form a custom dialog system engine associated with the dialog system interface. The web platform receives a user request from the dialog system interface, activates the custom dialog system engine based on identification, and retrieves the dialog system entities and intents. The user request is processed by applying the dialog system entities and intents to generate a response to the user request. The response is sent to the dialog system interface.

Abstract: A method for push interaction with a mobile device using a chat interface includes establishing a chat protocol connection between a server and the mobile device, wherein the chat protocol format is used as a part of the push protocol; generating an event on the server; sending a push protocol command relating to the event from the server to the mobile device using the chat protocol connection; in the background, processing the chat protocol request that was packaged within the push protocol command; receiving the response from the mobile device through the chat protocol connection using the pull protocol mode; sending media contents from the server to the client using pull protocol mode; and displaying the media contents on the mobile device.

Abstract: Disclosed is a technology for providing information to users of a chat information system. The chat information system may receive an information request from a user. The information request may be processed to determine its subject area and forwarded to information sources or external communication services, such as social networks, forums, and the like. Answers received from the information sources and external communication services may be validated and selected based on user feedbacks and ratings. The selected answers may be then delivered to the users of the chat information system. After receiving the answers, the user may evaluate them to be further stored for future use by the chat information system.

Abstract: A method and graphical user interface intended to simplify interaction between a user and a chat information system running on a portable electronic device that includes a touch screen. User interfaces and methods include user input controls (i.e., a virtual keyboard or voice recognition devices). The system also includes output trays, means for viewing chat history, means for displaying the Internet content and means for displaying graphical elements and avatars.

Abstract: Disclosed is a technology for providing information to users of a chat information system. The chat information system may receive an information request from a user. The information request may be processed to determine its subject area and forwarded to information sources or external communication services, such as social networks, forums, and the like. Answers received from the information sources and external communication services may be validated and selected based on user feedbacks and ratings. The selected answers may be then delivered to the users of the chat information system. After receiving the answers, the user may evaluate them to be further stored for future use by the chat information system.