Visual and multi-dimensional search
First Claim
1. A multi-dimension search system, comprising:
- a computer memory having stored thereon the following components executable by a processor;
an input analyzer, comprised of an image analyzer, that extracts features from an input, the input comprises visual data and at least one of text, or audio data, wherein the visual data is from an image file,the image analyzer includes a pattern recognition component that extracts features of the image file, the features comprising physical attributes that are visually identifiable in the image file;
a search engine that formulates a search query based at least in part upon a subset of the extracted features, the search engine employs pattern recognition systems to extract visual information from searchable items, the search engine comprises;
a multi-dimension index generator that includes a set of content analyzer components, the multi-dimension index generator builds an index based upon features associated with the input, automatically and dynamically extracts features from searchable items, makes the features available for search based upon a particular query or set of queries, and maps extrinsic dimensional data including at least one of temporal data, audio data, visual data, context data, mood data or event data to the query or set of queries to generate results that include a combination of text, visual or audible data; and
an index item locator component that conducts a search across one or more of the plurality of dimensions based at least in part upon the subset of extracted features; and
a machine learning and reasoning component that learns, based on context information, historical data, or user feedback, what results are desired in view of a determined and inferred query, as well as how the results should be rendered.
3 Assignments
0 Petitions
Accused Products
Abstract
A system that can analyze a multi-dimensional input thereafter establishing a search query based upon extracted features from the input. In a particular example, an image can be used as an input to a search mechanism. Pattern recognition and image analysis can be applied to the image thereafter establishing a search query that corresponds to features extracted from the image input. The system can also facilitate indexing multi-dimensional searchable items thereby making them available to be retrieved as results to a search query. More particularly, the system can employ text analysis, pattern and/or speech recognition mechanisms to extract features from searchable items. These extracted features can be employed to index the searchable items.
98 Citations
19 Claims
-
1. A multi-dimension search system, comprising:
-
a computer memory having stored thereon the following components executable by a processor; an input analyzer, comprised of an image analyzer, that extracts features from an input, the input comprises visual data and at least one of text, or audio data, wherein the visual data is from an image file, the image analyzer includes a pattern recognition component that extracts features of the image file, the features comprising physical attributes that are visually identifiable in the image file; a search engine that formulates a search query based at least in part upon a subset of the extracted features, the search engine employs pattern recognition systems to extract visual information from searchable items, the search engine comprises; a multi-dimension index generator that includes a set of content analyzer components, the multi-dimension index generator builds an index based upon features associated with the input, automatically and dynamically extracts features from searchable items, makes the features available for search based upon a particular query or set of queries, and maps extrinsic dimensional data including at least one of temporal data, audio data, visual data, context data, mood data or event data to the query or set of queries to generate results that include a combination of text, visual or audible data; and an index item locator component that conducts a search across one or more of the plurality of dimensions based at least in part upon the subset of extracted features; and a machine learning and reasoning component that learns, based on context information, historical data, or user feedback, what results are desired in view of a determined and inferred query, as well as how the results should be rendered. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A computer-implemented method of performing a multi-dimensional search, comprising:
-
employing a processor to execute computer executable instructions stored on a computer readable storage medium to perform the following acts; receiving an input, the input comprises visual data and at least one of text or audio data, wherein the visual data is from an image file; extracting a plurality of features from the input comprising; utilizing a pattern recognition component to extract a plurality of features from the image file, wherein the features comprise physical attributes that are visually identifiable in the image file; establishing a plurality of search terms based at least in part upon a subset of the extracted features; retrieving a plurality of results based at least in part upon a subset of the search terms; collecting and indexing search-related information across a plurality of dimensions, and building an index based upon features associated with the input; automatically and dynamically extracting features from searchable items and making the features available for search based upon a particular query or set of queries; learning, based on context information, historical data, or feedback, what results are desired in view of a determined and inferred query, as well as how the results should be rendered, and generating a statistical model with the results; and filtering a subset of the plurality of results in accordance with at least one of a user context, a user preference, a relevancy factor with respect to the input, or a device context. - View Dependent Claims (10, 11, 12, 14, 15, 16, 17)
-
-
13. A system comprising:
-
a computer memory having stored thereon the following components executable by a processor; means for receiving an input, the input comprises visual data and at least one of text or audio data, wherein the visual data is from an image file; means for extracting a plurality of features from the input; means for utilizing a language parser, a speech recognition component or a pattern recognition component to extract the plurality of features, the pattern recognition component extracting the features of the image file, the features comprising physical attributes that are visually identifiable in the image file; means for generating a search query based at least in part upon a subset of the plurality of features; means for collecting and indexing search-related information across a plurality of dimensions, and building an index based upon features associated with the input; means for automatically and dynamically extracting features from searchable items and making the features available for search based upon a particular query or set of queries; means for learning, based on context information, historical data, or user feedback, what results are desired in view of a determined and inferred query, as well as how the results should be rendered; and means for generating results that include a combination of text, visual or audible data. - View Dependent Claims (18, 19)
-
Specification