Google Inc.

Theai, Inc.

Speaktoit, Inc.

Ilya Gennadyevich Gelfenbeyn

Artem Goncharuk

Pavel Aleksandrovich Sirotin

Kylan Gibbs

Mikhail Ermolenko

Ilya Andreevich Platonov

Olga Aleksandrovna Gelfenbeyn

Evgenii Shingarev

Kirill Ryzhov

Nathan Yu

Aleksey Tikhonov

Roman Gusarov

Ilya Platonov

Khaled Jedoui

Nastassia Smolskaya

Alex Huang

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.

Automated assistant invocation of appropriate agent

Systems and methods for dynamically controlling a knowledge scope of artificial intelligence (AI) characters are provided. An example method includes associating a knowledge store with an AI character generated by an AI character model, where the AI character is a virtual character in a virtual world; determining context parameters for the AI character; defining, based on the context parameters, a scope of knowledge available to the AI character from a knowledge store; constricting access of the AI character to the knowledge store based on the defined scope of knowledge; monitoring changes in the context parameters; and dynamically adjusting the scope of knowledge based on the changes in the context parameters.

Dynamic control of knowledge scope of artificial intelligence characters

Systems and methods for providing interactions of an Artificial Intelligence (AI) character model with users are provided. An example method includes receiving a message from a user of a client-side computing device; retrieving, from a graph, information concerning relationships between the AI character model and the user; generating, based on the message and the information concerning relationships, an action associated with AI character model; and causing the AI character model to perform the action in a virtual environment provided to the user via the client-side computing device. The client-side computing device may be in communication with a computing platform. The graph may include a first node associated with the AI character model, a second node associated with the user, and an edge between the first node and the second node. The edge may be associated with the information concerning relationships between the AI character model and the user.

Relationship graphs for artificial intelligence character models

A method for enhancing dialog systems is disclosed herein. The method may include maintaining an online marketplace that may have a plurality of dialog system extension elements. The plurality of dialog system extension elements may include at least one of a dialog system plugin, a dialog system add-on, a dialog system update, and a dialog system upgrade. The method may further include receiving a selection of one of the plurality of dialog system extension elements from an end user. The end user may be associated with a dialog system. The method may continue with associating the one of the plurality of dialog system extension elements with the dialog system of the end user.

Enhancing functionalities of virtual assistants and dialog systems via plugin marketplace

Systems and methods for training an Artificial Intelligence (AI) character model are provided. An example method includes receiving, from a client-side computing device being in communication with a computing platform, input data to the AI character model; generating an action to be performed by the AI character model in response to the input data; transmitting the action to the client-side computing device, where the client-side computing device presents the action to a user; receiving, from the client-side computing device, a message including an indication that the action is incorrect; and, based on the message, modifying parameters of the AI character model such that the AI character model executes a corrected action in response to the input data.

Agent-based training of artificial intelligence character models

Disclosed is the technology for computer-based 'Daily Brief' service, which includes methods and corresponding systems for proactively providing push notifications for users of chat information systems. The push notifications are dynamically generated and presented to the user based on identification of one or more triggering events, which may include predetermined time/date, current geographical location, activity of peers and friends in social media associated with the user, scheduled events, appointments, meetings, emails, instant messages, and many more. The described technology improves the interaction interface between the user and chat information system.

Proactive environment-based chat information system

Systems and methods for controlling safety settings for behavior characteristics of an Artificial Intelligence (AI) character model are provided. An example method includes receiving context associated with the AI character model; determining, based on the context, a level of safety of a content generated by the AI character model; and adjusting, based on the level of safety, the safety settings associated with the content generated by the AI character model. The determination of the level of safety may include determining specific characteristics of an audience interacting with the AI character model in a virtual environment and selecting, based on the specific characteristics, the level of safety from a set of levels of safety.

Controlling safety settings for behavior characteristics of artificial intelligence characters

Embodiments of the disclosure generally relate to a dialog system allowing for automatically reactivating a speech acquiring mode after the dialog system delivers a response to a user request. The reactivation parameters, such as a delay, depend on a number of predetermined factors and conversation scenarios. The embodiments further provide for a method of operating of the dialog system. An exemplary method comprises the steps of: activating a speech acquiring mode, receiving a first input of a user, deactivating the speech acquiring mode, obtaining a first response associated with the first input, delivering the first response to the user, determining that a conversation mode is activated, and, based on the determination, automatically re-activating the speech acquiring mode within a first predetermined time period after delivery of the first response to the user.

Dialog system with automatic reactivation of speech acquiring mode

Systems and methods for archetype-based generation of Artificial Intelligence (AI) characters are provided. An example method includes receiving at least one keyword describing an AI character, where the AI character is generated by an AI character model in a virtual environment; selecting, based on the at least one keyword, an archetype from a plurality of archetypes; acquiring at least one parameter of the AI character model, where the at least one parameter corresponds to at least one feature of the AI character; determining, based on the archetype, at least one value for the at least one parameter; and assigning the at least one value to the at least one parameter.

Archetype-based generation of artificial intelligence characters

Systems and methods for providing contextually oriented behavior of artificial intelligence (AI) characters are provided. An example method includes receiving a description of a plurality of scenes associated with an AI environment, where the description includes a list of AI objects and a list of AI character models present in a scene of the plurality of scenes; generating, based on the description, a plurality of AI scene models corresponding to the plurality of scenes, where the plurality of AI scene models include an AI scene model corresponding to the scene; and adjusting, based on parameters of the scene, behavioral characteristics of an AI character model of the list of AI character models.

Contextually oriented behavior of artificial intelligence characters

Systems and methods for providing a network for generating, sharing, and viewing artificial intelligence (AI) characters are provided. An example method includes providing a web-based interface enabling a user to generate and modify a template associated with an AI character generated by an AI character model, where the template includes parameters of the AI character model; receiving at least one value for at least one parameter of the AI character model; receiving a first request to store the template in a data store; storing the template in the data store and attributing the template to an account associated with the user; receiving, from the user, a second request to allow access to the template by at least one further user; and providing the access to the template to the at least one further user to enable the at least one further user to view and interact with the AI character.

Providing a network for sharing and viewing artificial intelligence characters

Systems and methods for conducting communications between a user and an Artificial Intelligence (AI) character model are provided. An example method includes determining a context of a dialog between the AI character model and the user, the context being determined based on a data stream received from a client-side computing device associated with the user; receiving a message of the user in the dialog; and generating, based on the context and the message, an input to a language model configured to predict a response to the message; providing the input to the language model to obtain the response; and transmitting the response to the client-side computing device, where the client-side computing device presents the response to the user. The input to the language model includes the message expanded by a keyword associated with the context. The context includes an intent of the user and an emotional state of the user.

Controlling generative language models for artificial intelligence characters

Systems and methods for text description-based generation of avatars for Artificial Intelligence (AI) characters are provided. An example method includes receiving a description of a face of an AI character, where the description is in a free-text format and where the face of the AI character is rendered by an AI character model in a virtual environment; acquiring at least one parameter of the AI character model, where the at least one parameter corresponds to at least one facial feature of the face of the AI character; analyzing the description to generate at least one value for the at least one parameter; and assigning the at least one value to the at least one parameter.

Text-description based generation of avatars for artificial intelligence characters

Systems and methods for dynamic control of behavioral characteristics of artificial intelligence (AI) characters are provided. The method includes ascertaining an occurrence of an event in a virtual environment associated with an AI character model; receiving a plurality of narratives associated with the AI character model; selecting, based on the event, a narrative from the plurality of narratives; determining, based on the selected narrative, behavioral settings; and applying the behavioral settings to the AI character model, thereby causing the AI character model to follow the narrative in interactions with a user in the virtual environment.

Dynamic control of behavioral characteristics of artificial intelligence characters

Systems and methods for recognition of intent of a character are provided. The character is an Artificial Intelligence (AI) character generated by an AI character model for interacting with users in the virtual environment or is controlled by a human user. An example method includes monitoring interactions between a plurality of characters in a virtual environment; recognizing, based on environmental parameters associated with the interactions, an intent of a character selected from the plurality of characters: selecting a plurality of possible behaviors for the character based on the intent; and triggering a behavior selected from the plurality of possible behaviors based on predetermined criteria.

Growing community of inventors

Sunnyvale, CA, United States of America

Ilya Gennadyevich Gelfenbeyn