Microsoft Technology Licensing, LLC

Manjot Singh Pal

Bernd Ingo Plontsch

Shahil Soni

Thomas Coolidge Stanton

Antonio José Consuegra Berruezo

Iurii Kondratiuk

Tae Hun Kim

Timothy Alexander Yates

Selina Wang

A system for assisting users in making progress towards the completion of a task by recommending actions is provided. The techniques disclosed herein enable a system to receive user input signals, such as a voice input, a text input or any other type of input comprising phrases indicating a task. The system can then automatically generate recommendations for directing the user to complete the task. The techniques disclosed herein can also identify a contextually-relevant application that is most suitable for completing the identified task. For instance, a user may have several messaging applications. Based on a context of the user's input, and other historical data utilized by one or more machine learning engines, a system can recommend an appropriate application, or provide a ranking of the applications, suitable for completing an identified task. The techniques disclosed herein also employ machine learning engines to improve accuracy of the recommendations over time.

Contextually-aware recommendations for assisting users with task completion

In non-limiting examples of the present disclosure, systems, methods and devices for assisting with task completion are provided. A plurality of items may be added to an electronic shopping list, wherein the plurality of items is arranged in a first order in the electronic shopping list. A store that each of the plurality of items is available for purchase at may be identified. An indication that a computing device associated with the electronic shopping list is within a threshold distance of an entrance of the store may be received. A location of each of the plurality of items in the store may be identified. The plurality of items may be arranged in a second order in the electronic shopping list based on the location of each of the plurality of items in the store relative to the entrance of the store.

Efficient task completion via intelligent aggregation and analysis of data

In non-limiting examples of the present disclosure, systems, methods and devices for assisting with task completion are provided. A natural language input may be received. A natural language processing engine may be applied to the natural language input. A primary task associated with the natural language input may be identified. A plurality of subtasks for completing the primary task may be identified from the natural language input. A determination may be made from the natural language input that the primary task or one of the plurality of subtasks is more important than other tasks. The primary task and the plurality of subtasks may be added to a list of tasks in a task completion application. An indication of importance may be associated in the task completion application in association with the task or subtask that is determined to be more important.

Natural language processing and machine learning for personalized tasks experience

Automatic generation of electronic messaging templates is provided. After a first email/message is generated and used, a second or a plurality of subsequent messages may be compared against the first or other similar emails/messages. Common elements among the similar emails/messages and elements not in common in the compared emails/messages are identified. An email/message template is automatically generated having textual content comprising all elements (e.g., text) common to each compared email/message and having highlighting components, such as an 'XXX' or other acceptable highlighting notation at a location in the textual content corresponding to each uncommon element. Upon subsequent use, when a sender opens the template and enters any information particular to the intended recipient, that information may be used to query a database or other data source for information that may be used to automatically fill-in (autofill) each highlighted uncommon element in the template.

Smart electronic mail and messaging templates

Enriched polling user experiences are provided. In some examples, a local and/or remote search may be performed based on a top choice in an ongoing poll. The search may be performed when a threshold such as predefined duration, a predefined number of votes, and/or a percentage of received votes over a polled population. Search results may be used to enrich the user experience displaying the poll with static or interactive items such as images, graphics, textual data, links to resources, etc. If the top choice changes at some point during the poll, new search may be performed and the enriching elements revised based on the new top choice. Types and numbers of the enriching elements to be displayed may be selected based on a type of the poll or a vote distribution in the poll.

Growing community of inventors

Seattle, WA, United States of America

Manjot Singh Pal