Abstract: A method for ranking genealogical records includes using a machine learning model to rank multiple searched records based on relevancy. The relevancy may be determined by identifying features included in a record and scaling each feature by a corresponding weight factor. In addition, a method for training a machine learning model and increasing the convergence speed of the training is described. To train the model, a machine learning process is used to optimize a ranking performance metric. A set of weights corresponding to multiple features are used to rank multiple past search records in a training set. An initial set of the weights are set by the expectation values of the weights. The weights are incrementally changed to optimize the ranking performance metric. The step size of the increment is determined based on the sensitivity of the ranking performance metric relative to the step size.

Abstract: Techniques for training a machine-learning (ML) model for captioning images are disclosed. A plurality of feature vectors and a plurality of visual attention maps are generated by a visual model of the ML model based on an input image. Each of the plurality of feature vectors correspond to different regions of the input image. A plurality of caption attention maps are generated by an attention model of the ML model based on the plurality of feature vectors. An attention penalty is calculcated based on a comparison between the caption attention maps and the visual attention maps. A loss function is calculcated based on the attention penalty. One or both of the visual model and the attention model are trained using the loss function.

Abstract: Systems and methods for registering documents. A two-dimensional document image and one or more form images may be obtained. The document image may be projected onto a horizontal axis and a vertical axis to create a horizontal document projection and a vertical document projection. The form images may be projected onto the horizontal axis and the vertical axis to create a horizontal form projection and a vertical form projection. The horizontal document projection may be correlated with the horizontal form projection of the form images and the vertical document projection may be correlated with the vertical form projection of the form images. Correlation scores may be calculated based on the correlations.

Abstract: Embodiments described herein relate generally to a methodology of efficient object classification within a visual medium. The methodology utilizes a first neural network to perform an attention based object localization within a visual medium to generate a visual mask. The visual mask is applied to the visual medium to generate a masked visual medium. The masked visual medium may be then fed into a second neural network to detect and classify objects within the visual medium.

Abstract: Systems and methods for retrieving a set of ordered items from a distributed database. A plurality of ordered items may be stored at a cache. The plurality of ordered items may have a length of N+B at a first instant in time. A first instruction to delete a first item of the plurality of ordered items may be received. A second instruction to add a second item to the plurality of ordered items may be received. The first instruction and the second instruction may be stored in a change log. A request for the first N items of the plurality of ordered items may be received. The first instruction may be executed by deleting the first item from the plurality of ordered items. The second instruction may be executed by adding the second item to the plurality of ordered items. The first N items of the plurality of ordered items may be sent in response to the request.

Abstract: Systems and methods for training a machine learning (ML) ranking model to rank genealogy hints are described herein. One method includes retrieving a plurality of genealogy hints for a target person, where each of the plurality of genealogy hints corresponds to a genealogy item and has a hint type of a plurality of hint types. The method includes generating, for each of the plurality of genealogy hints, a feature vector having a plurality of feature values, the feature vector being included in a plurality of feature vectors. The method includes extending each of the plurality of feature vectors by at least one additional feature value based on the number of features of one or more other hint types of the plurality of hint types. The method includes training the ML ranking model using the extended plurality of feature vectors and user-provided labels.

Abstract: Systems and methods for classifying historical images. A feature extractor may create feature vectors corresponding to a plurality of images. A first classification of the plurality of images may be performed based on the plurality of feature vectors, which may include assigning a label to each of the plurality of images and assigning a probability for each of the assigned labels. The assigned probability for each of the assigned labels may be related to a statistical confidence that a particular assigned label is correctly assigned to a particular image. A subset of the plurality of images may be displayed to a display device. An input corresponding to replacement of an incorrect label with a corrected label for a certain image may be received from a user. A second classification of the plurality of images based on the input from the user may be performed.

Abstract: Systems and methods for classifying historical images. A feature extractor may create feature vectors corresponding to a plurality of images. A first classification of the plurality of images may be performed based on the plurality of feature vectors, which may include assigning a label to each of the plurality of images and assigning a probability for each of the assigned labels. The assigned probability for each of the assigned labels may be related to a statistical confidence that a particular assigned label is correctly assigned to a particular image. A subset of the plurality of images may be displayed to a display device. An input corresponding to replacement of an incorrect label with a corrected label for a certain image may be received from a user. A second classification of the plurality of images based on the input from the user may be performed.

Abstract: A data record management system develops person match scores for data records that may relate to the same person or subject. In a genealogical system where the data records are represented as nodes in a family tree, and where multiple data records may relate the same person in question, the data record management system evaluates not only two data records to determine if they relate to the same person, but also individually evaluate various data records pertaining to people that are related to the person in question. Person match scores are calculated by combining sub-scores based on the comparison of corresponding nodes. Sub-scores for nodes pertaining to related people may be adjusted higher even if those notes do not match, to reflect circumstances such as remarriage.

Abstract: A data record management system develops person match scores for data records that may relate to the same person or subject. In a genealogical system where the data records are represented as nodes in a family tree, and where multiple data records may relate the same person in question, the data record management system evaluates not only two data records to determine if they relate to the same person, but also individually evaluate various data records pertaining to people that are related to the person in question. Person match scores are calculated by combining sub-scores based on the comparison of corresponding nodes. Sub-scores for nodes pertaining to related people may be adjusted higher even if those notes do not match, to reflect circumstances such as remarriage.

Abstract: Systems and methods for retrieving a set of ordered items from a distributed database. A plurality of ordered items may be stored at a cache. The plurality of ordered items may have a length of N+B at a first instant in time. A first instruction to delete a first item of the plurality of ordered items may be received. A second instruction to add a second item to the plurality of ordered items may be received. The first instruction and the second instruction may be stored in a change log. A request for the first N items of the plurality of ordered items may be received. The first instruction may be executed by deleting the first item from the plurality of ordered items. The second instruction may be executed by adding the second item to the plurality of ordered items. The first N items of the plurality of ordered items may be sent in response to the request.

Abstract: Methods and systems for creating a cluster view person for genealogical studies. Methods may include obtaining a plurality of genealogical trees. Each of the genealogical trees may include a plurality of interconnected nodes representing individuals that are related to each other. Methods may also include identifying one or more of the genealogical trees that contain a similar individual. Whether two individuals are grouped may depend on similarity and/or quality thresholds. Methods may include creating an aggregate individual including each of the similar individuals in each of the identified genealogical trees. The aggregate individual may combine information from each of the similar individuals.

Abstract: Systems and methods for classifying historical images. A feature extractor may create feature vectors corresponding to a plurality of images. A first classification of the plurality of images may be performed based on the plurality of feature vectors, which may include assigning a label to each of the plurality of images and assigning a probability for each of the assigned labels. The assigned probability for each of the assigned labels may be related to a statistical confidence that a particular assigned label is correctly assigned to a particular image. A subset of the plurality of images may be displayed to a display device. An input corresponding to replacement of an incorrect label with a corrected label for a certain image may be received from a user. A second classification of the plurality of images based on the input from the user may be performed.

Abstract: Systems and methods for registering documents. A two-dimensional document image and one or more form images may be obtained. The document image may be projected onto a horizontal axis and a vertical axis to create a horizontal document projection and a vertical document projection. The form images may be projected onto the horizontal axis and the vertical axis to create a horizontal form projection and a vertical form projection. The horizontal document projection may be correlated with the horizontal form projection of the form images and the vertical document projection may be correlated with the vertical form projection of the form images. Correlation scores may be calculated based on the correlations.

Abstract: A tree building system that accesses data from a social networking site and, in some embodiments, other data sites having information that may pertain to the relationships between users of the social networking site. A rules engine within the system implements logic for analyzing the data from the social networking site. The system provides a candidate list of possible relatives for selection by a user and solicits information from the user through the use of guided questions.

Abstract: A handwriting recognition system converts word images on documents, such as document images of historical records, into computer searchable text. Word images (snippets) on the document are located, and have multiple word features identified. For each word image, a word feature vector is created representing multiple word features. Based on the similarity of word features (e.g., the distance between feature vectors), similar words are grouped together in clusters, and a centroid that has features most representative of words in the cluster is selected. A digitized text word is selected for each cluster based on review of a centroid in the cluster, and is assigned to all words in that cluster and is used as computer searchable text for those word images where they appear in documents. An analyst may review clusters to permit refinement of the parameters used for grouping words in clusters, including the adjustment of weights and other factors used for determining the distance between feature vectors.

Abstract: A handwriting recognition system converts word images on documents, such as document images of historical records, into computer searchable text. Word images (snippets) on the document are located, and have multiple word features identified. For each word image, a word feature vector is created representing multiple word features. Based on the similarity of word features (e.g., the distance between feature vectors), similar words are grouped together in clusters, and a centroid that has features most representative of words in the cluster is selected. A digitized text word is selected for each cluster based on review of a centroid in the cluster, and is assigned to all words in that cluster and is used as computer searchable text for those word images where they appear in documents. An analyst may review clusters to permit refinement of the parameters used for grouping words in clusters, including the adjustment of weights and other factors used for determining the distance between feature vectors.

Abstract: A graph database system is used to determine relationships between persons. The graph database system manages relationship data records having a compact data structure stored at a relationship database and accessed to find links or common relationships. For determining relationships between two people, the relationship records in the relationship paths for those two people are alternatively accessed and compared it to each other. Relationship records may include an identifier for a person having a relationship to a given individual, a relationship type, and a weight reflecting the confidence level or quality of the relationship.

Abstract: A handwriting recognition system converts word images on documents, such as document images of historical records, into computer searchable text. Word images (snippets) on the document are located, and have multiple word features identified. For each word image, a word feature vector is created representing multiple word features. Based on the similarity of word features (e.g., the distance between feature vectors), similar words are grouped together in clusters, and a centroid that has features most representative of words in the cluster is selected. A digitized text word is selected for each cluster based on review of a centroid in the cluster, and is assigned to all words in that cluster and is used as computer searchable text for those word images where they appear in documents. An analyst may review clusters to permit refinement of the parameters used for grouping words in clusters, including the adjustment of weights and other factors used for determining the distance between feature vectors.

Abstract: A handwriting recognition system converts word images on documents, such as document images of historical records, into computer searchable text. Word images (snippets) on the document are located, and have multiple word features identified. For each word image, a word feature vector is created representing multiple word features. Based on the similarity of word features (e.g., the distance between feature vectors), similar words are grouped together in clusters, and a centroid that has features most representative of words in the cluster is selected. A digitized text word is selected for each cluster based on review of a centroid in the cluster, and is assigned to all words in that cluster and is used as computer searchable text for those word images where they appear in documents. An analyst may review clusters to permit refinement of the parameters used for grouping words in clusters, including the adjustment of weights and other factors used for determining the distance between feature vectors.