Microsoft Technology Licensing, LLC

Other

Keizo Fujiwara

Xianchao Wu

Zhan Chen

Momo Klyen

Sridhar Srinivasan

Wei Wu

Katsuya Iida

Thomas Anand Jeyaseelan

Daigo Hamura

Suresh Parameshwar

Jianfeng Yan

Kyohei Tomita

Kazushige Ito

Zhou Xiang

Sayuri Miyakawa

Jyunnya Saiki

Mina Miyoshi

Akihiro Okuzawa

Described herein is a system and method for providing a conversation session with an artificial intelligence entity that is associated with a business entity. In some aspects, input is provided to an artificial intelligence entity advertisement system. The input is analyzed to determine the subject matter of the input. An artificial intelligence entity associated with the subject matter is then selected and provided to the user. The artificial intelligence entity recommends products or services that are provided by the business entity to the user.

Using various artificial intelligence entities as advertising media

The present disclosure provides a method for providing voice-based knowledge through intelligent automated chatting. An input is received. A knowledge message is selected from a set of knowledge messages in response to the input, wherein a length of a voice corresponding to each of the set of knowledge messages is no more than a predefined length. The voice corresponding to the knowledge message is output in a conversation of the intelligent automated chatting.

Voice-based knowledge sharing application for chatbots

A method provides information to a user as a function of derived user intent. The method includes receiving input from a user, generating an intent vector by processing the received input though an artificial intelligence model that has been trained with data representative of the user's intention, wherein the intent vector comprises a probability for each intent in a known set of possible intents, executing a trigger control model to determine whether to respond to the user as a function of the input from the user and the intent vector, utilizing the trigger control model, received input, and intent vector input to generate a response via a trained chatbot, and providing the response via an output device.

Chatbot integrating derived user intent

The present disclosure is directed to systems, methods and devices for providing artificial intelligence (AI) entity-specific feedback. Official content related to an entity or entity figure may be extracted and analyzed. The extracted content may be classified in an entity corpus based on a determined language style of the content. An input into a conversational AI system may be received. A plurality of potential responses related to the input may be determined from one or more entity corpus. Each of the plurality of potential responses may be ranked according to a rank match value calculated for each of the plurality of determined responses, and at least one of potential responses may be provided as feedback.

Entity-specific conversational artificial intelligence

The present disclosure provides a method for recommending media content through intelligent automated chatting. A message is received from a user in a conversation with the user. A new topic is identified based on the message and context of the conversation. A media content is identified from a set of media contents based on the new topic. A recommendation of the media content is provided in the conversation.

Media content recommendation through chatbots

The present disclosure is directed to systems, methods and devices for providing product and service recommendations to users via conversational AI dialog. A natural language user input may be inspected. One or more product-related keywords from the inspected natural language user input may be extracted. A user profile for a user may be analyzed and a determination regarding one or more categories from the user profile that are related to the extracted product-related keywords may be made. One or more match values connecting the natural language user input to one or more candidate product recommendations may be calculated. The one or more candidate product recommendations may be ranked and a product recommendation based on the ranking may be provided.

Recommendation through conversational AI

Described is a pipeline for handling notification messages sent to a mobile messaging message (e.g., SMS or SMTP) recipient, and handling a reply to that notification message, including correlating the notification message with the reply. An engine receives a notification message, and for a notification message to which a reply is possible, maintains state data for use in correlating a received reply with the notification message. The state data includes metadata that indicates that text or code data is expected in any reply. For a reply providing code data, the engine calls a selected URL corresponding to the code. To facilitate message delivery, the engine may format the notification message, including shortening a URL of the message, and/or splitting a longer notification message into shorter notification messages.

Growing community of inventors

Kanagawa, Japan

Keizo Fujiwara