Microsoft Technology Licensing, LLC

Avichai Cohen

Benny Schlesinger

Yuval Pinchas Borsutsky

William Ramsey

Hen Fitoussi

Keren Damari

Eldar Cohen

Delia Koren

Shira Weinberg

Nir Levy

A computer system can conduct corresponding natural language dialogs with multiple computer-readable profiles using a computer proxy messaging bot. For example, a first set of natural language instructions can be received via a computer messaging proxy bot from a first computer-readable profile. The first set of natural language instructions can be analyzed via the proxy bot. Also, first and second natural language dialog scripts can be generated via the proxy bot using results of the analyzing of the first set of natural language instructions, with the second natural language dialog script including natural language data derived from the first set of natural language instructions. The first natural language dialog script can be sent to the first profile via the proxy bot and the second natural language dialog script can be sent to a second computer-readable profile via the proxy bot, both in response to the first set of instructions.

Computer proxy messaging bot

A computer-implemented technique is described for enabling a user to create a conversational bookmark in the course of the user's interaction with a BOT. The bookmark designates a particular juncture in the user's interaction with the BOT. When the user later invokes the bookmark, the computer-implemented technique resumes the user's interaction with the BOT, starting at the particular juncture. The technique can accomplish the above functions in a BOT-independent manner (which does not involve changes to the BOT) or a BOT-dependent manner (which involves changes to the BOT). The technique can also be extended to a task of creating and activating bookmarks in the course of a conversation among two or more humans.

Conversational bookmarks

A user profile and messaging bots can be joined to participate in a group chat session. A first natural language requirement set can be received from the profile and sent to the bots. A first solution set from a first bot can be processed, with the set including a first natural language script describing a first solution to the requirement set. A second solution set from a second bot can be processed, with the set including a second natural language script that describes a second solution to the requirement set. The first and second scripts can be sent to the profile, and at least part of each solution set can be sent to the other bot. A selection of the first bot for providing a solution to the requirement set can be received from the profile, and an indication of the selection can be transmitted to the first bot.

Messaging bot selection in multi-bot chat sessions

Creation data can be received from a computer-readable developer profile, with the creation data including instructions to create a messaging bot. A messaging bot definition can be generated using the instructions, and a messaging bot may be executed using the definition. The instructions may include natural language instructions defining one or more messaging bot characteristics. The natural language instructions can be matched with one or more commands to include one or more characteristics in the messaging bot, and instructions for those characteristic(s) can be included in the messaging bot definition. The instructions can be instructions that are not in a computer programming language, and they can be instructions to create one or more general messaging bot characteristics configured to be implemented with a specific dialog structure that defines one or more specific natural language dialog scripts.

Computer messaging bot creation

In various implementations, routing factors are identified based on a routing request associated with a user, where the routing factors include route preferences of the user. Routes are generated based on the routing request. Preference weights are determined for the route preferences, where the preference weights correspond to machine learning models based on sensor data provided by one or more sensors in association with the user. Route scores are determined for the routes based on the preference weights. A suggested route is provided to a user device associated with the user, where the suggested route corresponds to a selected route of the routes and is provided based on the route score of the selected route.

Enhanced user efficiency in route planning using route preferences

Command instruction data can be generated via a computerized control system, with the instruction data being formatted to prompt a plurality of tile units to change their output. The instruction data can be sent from the control system to the tile units, with each of the tile units including a tile controller connected to one or more tiles embedded in one or more sidewalk floors, and with each of the tiles including a user interface output device. At least part of the instruction data from the control system can be received via a tile controller of a tile unit. At least part of the instruction data can be processed via the tile controller. In response, the user interface output device of the tile can be signaled via the tile controller to change the output of the output device.

Growing community of inventors

Giv′at-Shmuel, Israel

Avichai Cohen