摘要:
An adaptive shared infrastructure that can be easily utilized to enable natural interaction between user(s) and machine system(s) is provided. Additionally, the novel innovation can provide interactive techniques that produce accurate intent-to-action mapping based upon a user input. Further, the innovation can provide novel mechanism by which assets (e.g., documents, actions) can be authored. The authoring mechanisms can enable the generation of learning models such that the system can infer a user intent based at least in part upon an analysis of a user input. In response thereto, the system can discover an asset, or group of assets based upon the inference. Moreover, the innovation can provide a natural language interface that learns and/or adapts based upon one or more user input(s), action(s), and/or state(s).
摘要:
A task system and method are provided. The system provides an automated approach for task creation, maintenance and/or execution. The system includes a browser that receives search results and at least one task associated with a query from a search engine. The system further includes a browser helper object that binds to the browser at runtime. The browser helper object provides information associated with a user's action with respect to the search results and/or at least one task. The information can be employed as feedback to update model(s) (e.g., query classification model(s) and/or slot-filling model(s)) of a semantic reasoning component that retrieves task based, at least in part, upon user query(ies).
摘要:
A task system and method are provided. The system provides an automated approach for task creation, maintenance and/or execution. The system includes a browser that receives search results and at least one task associated with a query from a search engine. The system further includes a browser helper object that binds to the browser at runtime. The browser helper object provides information associated with a user's action with respect to the search results and/or at least one task. The information can be employed as feedback to update model(s) (e.g., query classification model(s) and/or slot-filling model(s)) of a semantic reasoning component that retrieves task based, at least in part, upon user query(ies).
摘要:
Systems and methods are provided that perform automatic URL analysis and correction in a computing system. The systems and methods automatically detect misentered or incorrect URLs, analyzing the invalid URLs with respect intelligent rules and valid URLs, and where a high likelihood exists for alternative URLs being intended, the alternative URLs are presented to the user as suggestions. The URLs used for comparison to the URL input may be collected through multiple channels or from multiple sources, which may be dynamically updated sources, including URLs commonly or newly found on the Web, users' favorite URLs and the like, as well as URLs from a standard URL list or database, all of which may be from one or more multi-lingual domain. In various embodiments, the alternative URL(s) are automatically presented when there is a very high confidence that the alternatives are desirable. Optionally, a mini search or a full blown search on the URL input may be performed and presented to the user to supplement the alternative URL suggestions. The systems allow a user to seek help or technical information about the URL navigation or search attempt and also allow a user to easily retry the query, ignoring the suggestions.
摘要:
A development system is provided. The system includes a workspace component to visually display one or more model components. A separation component automatically segments the model components into two or more project components. A synchronization component can be provided to automatically update at least one of the project components in view of changes made to at least one other project component.
摘要:
A classifier is used to predict relevant results with arbitrary filtering conditions specified by the user. The classifier model is stored as a database table and joined with a metadata properties table instead of calculating the query result probability using the full classifier model. A user-specified query based filter is applied to the joined tables to obtain the list of documents satisfying the filter. The probability is then computed using the sub-model.
摘要:
A system and methods are provided for runtime spelling analysis and correction in a computing system. Misspelled entries or input text is automatically corrected turning the misspelled entries or input text into valid entries or text. The words used for spell checking and correction may be collected through multiple channels or from multiple sources, including words commonly found on the Web, and in users' entries or input text, as well as words from a standard language lexicon, all of which may be in one or more languages. The word(s) are automatically corrected only when there is a very high confidence that the correction is desirable. In various embodiments, the system implements a plurality of mechanisms with which the user can override the correction if invoked.