System and method for facilitating associating semantic labels with content
First Claim
Patent Images
1. A system configured to facilitate associating semantic labels with content, the system comprising:
- one or more processors configured by machine readable instructions to;
obtain matched sets of documents, wherein individual matched sets of documents include a structured document and an unstructured document having related content;
identify numeric instances present in the documents obtained by the document module such that, responsive to obtaining a first matched set of documents including a first structured document and a first unstructured document, the fact module identifies a first set of numeric instances present in the first structured document and a second set of numeric instances present in the first unstructured document, wherein the individual numeric instances represent numbers;
correlate numeric instances in different documents in a common matched set of documents that express matching numbers such that, responsive to the first set of numeric instances including a first numeric instance expressing a first number and the second set of numeric instances including a second numeric instance expressing the first number, the first numeric instance and the second numeric instance are correlated based on the common expression of the first number;
determine, responsive to identification of the first set of numeric instances in the first structured document and to correlation of the first numeric instance with the second numeric instance, structured contextual information for the first numeric instance, such structured contextual information labeling the first numeric instance and/or content associated with the first numeric instance in the first structured document, such structured contextual information including one or more of a semantic label, a dimension, or an attribute of the first numeric instance and/or the content associated with the first numeric instance;
analyze associated structured contextual information for the first numeric instance and content appearing with the second numeric instance to determine one or more trends in the associated contextual information;
determine unstructured contextual information for correlated numeric instances such that, responsive to correlation of the first numeric instance with the second numeric instance, unstructured contextual information for the second numeric instance is determined, the unstructured contextual information including the content appearing with the second numeric instance in the first unstructured document;
facilitate user entry of content into a second unstructured document being authored by a user through a graphical user interface presented to the user subsequent to correlation of the numeric instances in the first structured document and the first unstructured document; and
determine and present to the user, through the graphical user interface concurrent with user entry of content, suggested semantic labels for content being entered to the second unstructured document by the user based on the trends in the associated contextual information, such presentation being performed during the user entry of the content into the second unstructured document through the graphical user interface.
1 Assignment
0 Petitions
Accused Products
Abstract
The association of semantic labels with content may be facilitated. In particular, the content in the sentences, labels, headers, text, and/or other context that surround a fact may provide information descriptive for a semantic label that has been applied to the sentence and/or fact. By analyzing some of these implicit semantic associations between semantic labels and facts (numeric or otherwise), suggestions for semantic labels may be made for previously labeled or unlabeled facts. The labels that are suggested may include suggestions for concepts, members, and other structured constructs.
52 Citations
10 Claims
-
1. A system configured to facilitate associating semantic labels with content, the system comprising:
-
one or more processors configured by machine readable instructions to; obtain matched sets of documents, wherein individual matched sets of documents include a structured document and an unstructured document having related content; identify numeric instances present in the documents obtained by the document module such that, responsive to obtaining a first matched set of documents including a first structured document and a first unstructured document, the fact module identifies a first set of numeric instances present in the first structured document and a second set of numeric instances present in the first unstructured document, wherein the individual numeric instances represent numbers; correlate numeric instances in different documents in a common matched set of documents that express matching numbers such that, responsive to the first set of numeric instances including a first numeric instance expressing a first number and the second set of numeric instances including a second numeric instance expressing the first number, the first numeric instance and the second numeric instance are correlated based on the common expression of the first number; determine, responsive to identification of the first set of numeric instances in the first structured document and to correlation of the first numeric instance with the second numeric instance, structured contextual information for the first numeric instance, such structured contextual information labeling the first numeric instance and/or content associated with the first numeric instance in the first structured document, such structured contextual information including one or more of a semantic label, a dimension, or an attribute of the first numeric instance and/or the content associated with the first numeric instance; analyze associated structured contextual information for the first numeric instance and content appearing with the second numeric instance to determine one or more trends in the associated contextual information; determine unstructured contextual information for correlated numeric instances such that, responsive to correlation of the first numeric instance with the second numeric instance, unstructured contextual information for the second numeric instance is determined, the unstructured contextual information including the content appearing with the second numeric instance in the first unstructured document; facilitate user entry of content into a second unstructured document being authored by a user through a graphical user interface presented to the user subsequent to correlation of the numeric instances in the first structured document and the first unstructured document; and determine and present to the user, through the graphical user interface concurrent with user entry of content, suggested semantic labels for content being entered to the second unstructured document by the user based on the trends in the associated contextual information, such presentation being performed during the user entry of the content into the second unstructured document through the graphical user interface. - View Dependent Claims (2, 3, 4, 5)
-
-
6. A computer-implemented method of facilitating the association of semantic labels with content, the method being implemented in a computer system comprising one or more processors configured to execute computer modules, the method comprising:
-
obtaining a matched set of documents, wherein the matched set of documents includes a structured document and a unstructured document having related content; identifying numeric instances present in the structured document and the unstructured document such that a first set of numeric instances present in the structured document are identified and a second set of numeric instances present in the unstructured document are identified, wherein the individual numeric instances represent numbers; correlating numeric instances in the first set of numeric instances and the second set of numeric instances that express matching numbers such that, responsive to the first set of numeric instances including a first numeric instance expressing the first number and the second set of numeric instances including a second numeric instance expressing the first number, the first numeric instance and the second numeric instance are correlated based on the common expression of the first number; determining structured contextual information for the first numeric instance responsive to correlation of the first numeric instance with the second numeric instance, such structured contextual information labeling the first numeric instance and/or content associated with the first numeric instance in the first structured document, such structured contextual information including one or more of a semantic label, a dimension, or an attribute of the first numeric instance and/or the content associated with the first numeric instance; determining unstructured contextual information for the second numeric instance responsive to correlation of the first numeric instance with the second numeric instance, the unstructured contextual information including the content appearing with the second numeric instance in the first unstructured document; analyzing associated structured contextual information for the first numeric instance and content appearing with the second numeric instance to determine one or more trends in the associated contextual information; facilitating user entry of content into a second unstructured document being authored by a user through a graphical user interface presented to the user subsequent to correlation of the numeric instances in the first structured document and the first unstructured document; and determining and presenting to the user, through the graphical user interface concurrent with user entry of content, suggested semantic labels for content being entered to the second unstructured document by the user based on the trends in the associated contextual information, such presentation being performed during the user entry of the content into the second unstructured document through the graphical user interface. - View Dependent Claims (7, 8, 9, 10)
-
Specification