Abstract: A Metric Information Network (MIN) with a plurality of Ground Control Points (GCPs) that are selected in an automated fashion. The GCP selection includes clustering algorithms as compared to prior art pair-wise matching algorithms. Further, the image processing that takes place in identifying interest points, clustering, and selecting tie points to be GCPs is all performed before the MIN is updated. By arranging for the processing to happen in this manner, the processing that is embarrassingly parallel (identifying interest points, clustering, and selecting tie points) can be performed in a distributed fashion across many computers and then the MIN can be updated.

Abstract: A Metric Information Network (MIN) with a plurality of Ground Control Points (GCPs) that are selected in an automated fashion. The GCP selection includes clustering algorithms as compared to prior art pair-wise matching algorithms. Further, the image processing that takes place in identifying interest points, clustering, and selecting tie points to be GCPs is all performed before the MIN is updated. By arranging for the processing to happen in this manner, the processing that is embarrassingly parallel (identifying interest points, clustering, and selecting tie points) can be performed in a distributed fashion across many computers and then the MIN can be updated.

Abstract: A Metric Information Network (MIN) with a plurality of Ground Control Points (GCPs) that are selected in an automated fashion. The GCP selection includes clustering algorithms as compared to prior art pair-wise matching algorithms. Further, the image processing that takes place in identifying interest points, clustering, and selecting tie points to be GCPs is all performed before the MIN is updated. By arranging for the processing to happen in this manner, the processing that is embarrassingly parallel (identifying interest points, clustering, and selecting tie points) can be performed in a distributed fashion across many computers and then the MIN can be updated.

Abstract: A separate panel may be used to display business icons near images of business entries, if the GIS does not include a business's front door geolocation. Users may place icons that represent business entities near the entrances to the entity. Also, a concise but extensive display of business listing data (e.g., reviews, summaries, services, hours, etc.) in the display near the geolocation and the presentation of further information upon user actions such as a mouse-overs, may avoid browsing away from the viewing application in order to learn more about the business.

Abstract: Texts may be classified by mapping the texts to concept space, and by dividing the concept space based on substantive classes. A concept space containing a diverse set of concepts is defined. One example of a concept space is the set of on-line encyclopedia articles, each of which is an example of a concept. A text is scored for relevance against each concept, and a vector is created containing each of the scores. The vector represents the text's position in concept space. For any given substantive class of texts, the concept space may be divided into regions containing texts that are members/non-members of the class. The dividing boundary may be determined by training a classifier on a set of labeled examples of texts that fall inside and outside the class.

Abstract: A Metric Information Network (MIN) with a plurality of Ground Control Points (GCPs) that are selected in an automated fashion. The GCP selection includes clustering algorithms as compared to prior art pair-wise matching algorithms. Further, the image processing that takes place in identifying interest points, clustering, and selecting tie points to be GCPs is all performed before the MIN is updated. By arranging for the processing to happen in this manner, the processing that is embarrassingly parallel (identifying interest points, clustering, and selecting tie points) can be performed in a distributed fashion across many computers and then the MIN can be updated.

Abstract: The present invention is directed to predicting whether two character strings refer to a same subject. An exemplary embodiment includes using a set of character-string pairs, which have been identified as either matches or nonmatches, to learn a function. The function can then be applied to the two character strings to quantify a likelihood that they refer to the same subject matter. For example, a kernel-based classifier analyzes the set of character-string pairs using a kernel function. Based on the analysis the classifier can generate parameters. The parameters are usable to define a prediction algorithm that when applied to the two character strings generates a prediction value, which suggests whether the two characters are matches, i.e., refer to the same subject matter.

Abstract: Texts may be classified by mapping the texts to concept space, and by dividing the concept space based on substantive classes. A concept space containing a diverse set of concepts is defined. One example of a concept space is the set of on-line encyclopedia articles, each of which is an example of a concept. A text is scored for relevance against each concept, and a vector is created containing each of the scores. The vector represents the text's position in concept space. For any given substantive class of texts, the concept space may be divided into regions containing texts that are members/non-members of the class. The dividing boundary may be determined by training a classifier on a set of labeled examples of texts that fall inside and outside the class.

Abstract: The present invention is directed to predicting whether two character strings refer to a same subject. An exemplary embodiment includes using a set of character-string pairs, which have been identified as either matches or nonmatches, to learn a function. The function can then be applied to the two character strings to quantify a likelihood that they refer to the same subject matter. For example, a kernel-based classifier analyzes the set of character-string pairs using a kernel function. Based on the analysis the classifier can generate parameters. The parameters are usable to define a prediction algorithm that when applied to the two character strings generates a prediction value, which suggests whether the two characters are matches, i.e., refer to the same subject matter.

Abstract: A separate panel may be used to display business icons near images of business entries, if the GIS does not include a business's front door geolocation. Users may place icons that represent business entities near the entrances to the entity. Also, a concise but extensive display of business listing data (e.g., reviews, summaries, services, hours, etc.) in the display near the geolocation and the presentation of further information upon user actions such as a mouse-overs, may avoid browsing away from the viewing application in order to learn more about the business.