Microsoft Technology Licensing, LLC

Microsoft Corporation

Microsoflt Corporation

William Ramsey

Sanjeev Katariya

Benny Schlesinger

Yuval Pinchas Borsutsky

Eldar Cohen

Hen Fitoussi

Ronnie Chaiken

Peter Bailey

Avichai Cohen

Delia Koren

Jianfeng Gao

Li Jiang

Sandy Wong

Paul Reinholdtsen

Qi Yao

Jonas Barklund

Patricia M Schmid

Jun Liu

Steven Wayne Ickman

Benoit F Dumoulin

Christopher Clayton McConnell

Thomas Matthew Laird-McConnell

David Neal Weise

Gaurav Sareen

Nicholas Eric Craswell

Kevin Roland Powell

Nitin Agrawal

Nikhil Dandekar

Girish Kumar

David Dawson

Keren Damari

Douglas W Potter

Pär Jonas Barklund

Pratibha Permandla

Nick Craswell

Aidan C Crook

Zhanliang Chen

Sebastian De La Chica

Antonio Gulli

Rohit Wad

Hisakazu Igarashi

Junhua Wang

Daniel Robert Schwartz

Edward C Hart, Jr

Simant Dube

Binit Kumar Jha

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

Systems and methods are provided for performing tasks and related tasks. While a user is performing a task, a group of related tasks is presented. When a new task is selected, a new group of related tasks is provided. This allows a user to perform a series of tasks without having to separately search for each task. As the user moves between tasks, task information items are passed between the tasks so that previously provided information can be preserved.

Related tasks and tasklets for search

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

A user is allowed to communicate with a chatbot. A menu is provided to the user that includes a list of actions that can be performed by the user. Whenever natural language input asking a question is received from the user, this input is forwarded to the chatbot, a response to this input is received from the chatbot, this response is provided to the user, and the menu is again provided to the user. Whenever natural language input is received from the user requesting an action that is not one of the actions in the menu, this input is forwarded to the chatbot, a response to this input is received from the chatbot, where this response includes another menu that includes a list of subsequent actions that are related to the requested action and can be performed by the user, and this other menu is provided to the user.

Combined menu-based and natural-language-based communication with chatbots

The insertion and processing of programming language code (e.g., C#) in SQL statements, and the dynamic compiling of the code to detect errors prior to statement execution. The SQL statement with arbitrary programming language code can then be executed concurrently as a query on a computer cluster. External libraries can be imported and the associated functionality leveraged from within a SQL statement. The programming language compiler performs checking at build time, rather than retuning an error during the statement execution against the cluster, a potentially costly proposition in both computing time and human resources.

Programming language extensions in structured queries

Systems, methods, and computer-readable storage media are provided for reconciling query results associated with multiple indices. A search query having a first spelling is received. A plurality of query results is determined, each query result being derived from one of a plurality of indices. At least a first index is associated with a lexicon that is specific to a user computing device and at least a second index is associated with a lexicon that is specific to web-based content. Each query result may be a query result determined based upon the first spelling for the search query, a suggested alternate spelling for the received search query, a query result determined based upon the suggested alternate spelling for the received search query, or a null result. One or more of the query results then is selected as responsive to the received search query.

Reconciling query results associated with multiple indices

Various embodiments of the disclosed subject matter include computer-implemented methods, computer-readable media, and computer systems configured to respond to a search query from a computer user. In response to receiving a search query from the computer user, search results are obtained. A plurality of user intents are identified according to the obtained search results. The obtained search results are then grouped according to the subject matter of the search results, where each group corresponds to one of the plurality of user intents. A first user intent (with the corresponding group of search results) is selected. A search results page is generated from the search results of the group the search results corresponding to the selected first user intent and the generated search results page is returned to the computer user in response to the search query.

Intent-based presentation of search results

Embodiment described herein are directed to an enhanced search engine with multiple feedback loops for providing optimal search results that are responsive a user's search query. The user's search query is parsed, and based on the underlying terms, different linguistic models and refinement techniques generate alternative candidate search queries that may yield better results. Searches are performed for the original search query and the candidate search queries, and different scores are used to select the best search results to present to the user. Results making it onto the list, as well as the underlying candidate search query, linguistic model, or refinement technique for generating that search query, will have their corresponding scores updated to reflect their success of generating a search result. Scores are stored and used by future searches to come up with better results.

Self-tuning alterations framework

Methods are provided for re-ranking documents based on user-specific features. Search results are received from a non-contextual ranking system such that the search results are not specific toward a particular user, such as the user who submitted the search query. Contextual signals are received and provide user-specific features that are used to re-rank documents so that the most important and relevant documents are listed at the top of the list of search results. Each of the user-specific features are evaluated and compared to determine a new position of each document. A set of contextual search results is then generated based on the new positions.

Ranking contextual signals for search personalization

Systems and methods for presenting search results ordered, at least in part, based upon indicated user preferences are provided. User preferences for one potential search result over another that are free of position bias are obtained utilizing random relative order interchange of juxtaposed, ranked search results. Upon receipt of a search query, a determination is made to present at least a portion of search results satisfying the received query ordered based on user preferences, whether or not the order coincides with that determined using a ranking algorithm. In this way, presented search results are ordered, at least in part, according to user preferences, thus improving the relevance of the output relative to standard ranking algorithms alone.

Presenting search results ordered using user preferences

Core commands and aggregations of such commands are provided to programmers to enable them to generate programs that can be parallel-processed without requiring the programmer to be aware of parallel-processing techniques. The core commands and aggregations abstract mechanisms that can be executed in parallel, enabling the programmer to focus on higher-level concepts. The core commands provided include commands for applying a function in parallel and distributing and joining data in parallel. The output of each core command can implement an interface that can enable underlying mechanisms to stitch together multiple core commands in a cohesive manner to perform more complex actions.

Disco: a simplified distributed computing library

Growing community of inventors

Redmond, WA, United States of America

William Ramsey