Back to results
US 12,361,204 B1Granted
Extracting relevant information from a document
AssigneeTiny Fish Inc.
InventorsShuhao Zhang, Wenjie Hu, Mingyang Li
Life of this patent
Estimating the term…
Abstract
A document associated with a query is preprocessed including by deconstructing the query into individual components and understanding a relationship between the individual components. A query response is received. An annotated version of the document is outputted.
Claims28
A method, comprising:
- preprocessing a document associated with a query including by deconstructing the query into individual components and understanding a relationship between the individual components, wherein preprocessing the document associated with the query includes scanning the document to locate sections of the document that include elements associated with the query;
- providing the located sections of the document that include the elements associated with the query and the query to a cloud service;
- receiving a query response;
- and
- outputting an annotated version of the document.
2 more elements
A method, comprising:
- preprocessing a document associated with a query including by deconstructing the query into individual components and understanding a relationship between the individual components, wherein preprocessing the document associated with the query includes realigning a table included in the document;
- receiving a query response;
- and
- outputting an annotated version of the document.
1 more element
A method, comprising:
- preprocessing a document associated with a query including by deconstructing the query into individual components and understanding a relationship between the individual components, wherein preprocessing the document associated with the query includes adjusting a resolution associated with the document;
- receiving a query response;
- and
- outputting an annotated version of the document.
1 more element
A method, comprising:
- preprocessing a document associated with a query including by deconstructing the query into individual components and understanding a relationship between the individual components, wherein preprocessing the document associated with the query includes converting handwritten characters into text characters;
- receiving a query response;
- and
- outputting an annotated version of the document.
1 more element
A method, comprising:
- preprocessing a document associated with a query including by deconstructing the query into individual components and understanding a relationship between the individual components, wherein preprocessing the document associated with the query includes providing structure to floating words;
- receiving a query response;
- and
- outputting an annotated version of the document.
1 more element
A method, comprising:
- preprocessing a document associated with a query including by deconstructing the query into individual components and understanding a relationship between the individual components, wherein preprocessing the document associated with the query includes scanning the document to locate sections of the document that include elements associated with the query, wherein scanning the document to locate sections of the document that include elements associated with the query includes utilizing semantic understanding and visual cues;
- receiving a query response;
- and
- outputting an annotated version of the document.
1 more element
A system, comprising:
- a processor configured to:
- preprocess a document associated with a query including by deconstructing the query into individual components and understanding a relationship between the individual components, wherein preprocessing the document associated with the query includes scanning the document to locate sections of the document that include elements associated with the query;
- provide the located sections of the document that include the elements associated with the query and the query to a cloud service;
- receive a query response;
- and
- output an annotated version of the document;
- and
- a memory coupled to the processor and configured to provide the processor with instructions.
5 more elements
A computer program product embodied in a non-transitory computer readable medium and comprising computer instructions for:
- preprocessing a document associated with a query including by deconstructing the query into individual components and understanding a relationship between the individual components, wherein preprocessing the document associated with the query includes scanning the document to locate sections of the document that include elements associated with the query;
- providing the located sections of the document that include the elements associated with the query and the query to a cloud service;
- receiving a query response;
- and
- outputting an annotated version of the document.
2 more elements
A system, comprising:
- a processor configured to:
- preprocess a document associated with a query including by deconstructing the query into individual components and understanding a relationship between the individual components, wherein preprocessing the document associated with the query includes realigning a table included in the document;
- receive a query response;
- and
- output an annotated version of the document.
2 more elements
A computer program product embodied in a non-transitory computer readable medium and comprising computer instructions for:
- preprocessing a document associated with a query including by deconstructing the query into individual components and understanding a relationship between the individual components, wherein preprocessing the document associated with the query includes realigning a table included in the document;
- receiving a query response;
- and
- outputting an annotated version of the document.
1 more element
A system, comprising:
- a processor configured to:
- preprocess a document associated with a query including by deconstructing the query into individual components and understanding a relationship between the individual components, wherein preprocessing the document associated with the query includes adjusting a resolution associated with the document;
- receive a query response;
- and
- output an annotated version of the document.
2 more elements
A computer program product embodied in a non-transitory computer readable medium and comprising computer instructions for:
- preprocessing a document associated with a query including by deconstructing the query into individual components and understanding a relationship between the individual components, wherein preprocessing the document associated with the query includes adjusting a resolution associated with the document;
- receiving a query response;
- and
- outputting an annotated version of the document.
1 more element
A system, comprising:
- a processor configured to:
- preprocess a document associated with a query including by deconstructing the query into individual components and understanding a relationship between the individual components, wherein preprocessing the document associated with the query includes converting handwritten characters into text characters;
- receive a query response;
- and
- output an annotated version of the document.
2 more elements
A computer program product embodied in a non-transitory computer readable medium and comprising computer instructions for:
- preprocessing a document associated with a query including by deconstructing the query into individual components and understanding a relationship between the individual components, wherein preprocessing the document associated with the query includes converting handwritten characters into text characters;
- receiving a query response;
- and
- outputting an annotated version of the document.
1 more element
A system, comprising:
- a processor configured to:
- preprocess a document associated with a query including by deconstructing the query into individual components and understanding a relationship between the individual components, wherein preprocessing the document associated with the query includes providing structure to floating words;
- receive a query response;
- and
- output an annotated version of the document.
2 more elements
A computer program product embodied in a non-transitory computer readable medium and comprising computer instructions for:
- preprocessing a document associated with a query including by deconstructing the query into individual components and understanding a relationship between the individual components, wherein preprocessing the document associated with the query includes providing structure to floating words;
- receiving a query response;
- and
- outputting an annotated version of the document.
1 more element
A system, comprising:
- a processor configured to:
- preprocess a document associated with a query including by deconstructing the query into individual components and understanding a relationship between the individual components, wherein preprocessing the document associated with the query includes scanning the document to locate sections of the document that include elements associated with the query, wherein scanning the document to locate sections of the document that include elements associated with the query includes utilizing semantic understanding and visual cues;
- receive a query response;
- and
- output an annotated version of the document.
2 more elements
A computer program product embodied in a non-transitory computer readable medium and comprising computer instructions for:
- preprocessing a document associated with a query including by deconstructing the query into individual components and understanding a relationship between the individual components, wherein preprocessing the document associated with the query includes scanning the document to locate sections of the document that include elements associated with the query, wherein scanning the document to locate sections of the document that include elements associated with the query includes utilizing semantic understanding and visual cues;
- receiving a query response;
- and
- outputting an annotated version of the document.
1 more element
Dependencies are inferred from the claim text.