Ancestry.com Operations Inc.

The present disclosure relates to methods, systems, and non-transitory computer-readable media for a unique approach to processing genealogical records. For instance, the disclosed systems can receive a genealogical record in a digital format and transcribe text from the genealogical record to generate machine-readable text. The disclosed systems can process the machine-readable text using a sliding window for in-page entity and relationship extraction. The disclosed systems can also segment each page of the genealogical record to identify and categorize text blocks therefrom. Additionally, the disclosed systems can perform cross-page entity and relation extraction and reconcile entities and relationships extracted from in-page and cross-page extraction. Further, the disclosed systems can generate, from the extracted entities and relationships, family tree data instances representing family relationships between the entities, and associating biographical data with each entity. In some embodiments, the disclosed systems store the generated family tree data instances in a database.

The present disclosure is directed toward systems, methods, and non-transitory computer-readable media for generating bounding boxes for an image in accordance with one or more embodiments. The disclosed systems can generate a set of hidden states for an image of a document. The disclosed systems can generate a set of bounding boxes and a set of tokens from the hidden states utilizing a first head component and a second head component of a record generation model. The disclosed systems can aggregate a plurality of bounding boxes into a bounding box group. Additionally, the disclosed systems can provide the image depicting the bounding box group for display within a graphical user interface of a client device. Additionally or alternatively, the disclosed systems can train the record generation model, in part, by determining that a loss associated with masking one or more training bounding boxes satisfies a threshold loss.

The present disclosure is directed toward systems, methods, and non-transitory computer-readable media for a retrieval augmented thought approach to generating responses using neural networks. For example, the disclosed systems can receive a prompt instruction a large language model to generate a response. The disclosed systems can identify a retrieval-augmented-thought (RAT) store item corresponding to the prompt from among RAT-store items stored in a repository accessible by the large language model. In some cases, the disclosed systems can retrieve the RAT-store item and can generate a response using the large language model to execute processes defined by the RAT-store item. Further, in some cases, the disclosed systems utilize a dynamic graph-based agentic framework that incorporates one or more functional adapters and a RAT replanner to execute a sequence of processes indicated by a RAT-store item in a sequential manner.

Systems and methods for transforming and navigating historical map images are presented. The systems and methods embodiments facilitate providing, searching for, retrieving, transforming, and/or navigating a historical map image vis-à-vis a modern location and/or map. A map interface facilitates automatedly overlaying, annotating, and aligning a historical map image(s) with a modern map, allowing a user to search for a location and see the same in the historical map image, and change a visibility of the overlaid and aligned map images relative to each other. The map interface provides user interactions that facilitate retrieving, viewing, and manipulating records, historical districts, and other pertinent data through interacting with a particular location and/or searched-for individual, such as an ancestor or other person of interest.

The present disclosure is directed toward systems, methods, and non-transitory computer-readable media for determining links between source genealogical records and candidate genealogical records. The disclosed systems can apply a first machine learning model to generate embeddings of a set of genealogical records. Further, the disclosed systems can compare the embeddings within a latent space of the first machine learning model to identify embeddings that are within a threshold distance of a source genealogical embedding that corresponds to a source genealogical record. The disclosed systems can further apply a second machine learning model to extract field data from the embeddings, and a third machine learning model to extract contextual data from the embeddings. The disclosed systems can use the field data and contextual data to determine a link between the source genealogical record and a candidate genealogical record.

The present disclosure is directed toward systems, methods, and non-transitory computer-readable media for utilizing an improved search algorithm which prioritizes content items that include data fields (or other information) missing from a search query. For example, in response to a search query, the disclosed systems can prioritize or rank candidate content items to focus on candidate content items which include new information. Indeed, the disclosed systems can prioritize content items that include new information by ranking according to which content items include data fields missing from the search query. In some cases, the disclosed systems can prioritize content items with new information by determining which content items include data fields not already stored within a database associated with a user account (e.g., the user account performing the search) and/or for a particular entity or record within a genealogical database.

Disclosed herein relates to a method that analyzes the sentiment of user feedback for a genealogical system and identifies key phrases that may relate to novel themes in the user feedback. Sentiment analysis and novel theme prediction systems, methods, and computer-program products are described. Sentiment analysis of user feedback may include dividing user-generated unstructured text files into sections. The method classifies each section to an aspect of the genealogical system from a predetermined list of aspects monitored by the genealogical system. The method inputs the text belonging to the classified section to a supervised machine learning model and determines a sentiment associated with the classified section. In other embodiments, a method generates embedding vectors representing survey responses from users of a genealogical system. The method extracts a subset of survey responses having embedding vectors grouped into one cluster. The method extracts key phrases that may indicate a novel theme.

Image identification, retrieval, transformation and arrangement systems, methods, and computer-program products are configured to access a family tree of a user in a family tree database, identify one or more additional persons of interest in the family tree, determine whether the one or more persons of interest is associated with an image, retrieve the image, and transform the image of the one or more additional persons of interest with an image of the user or other person such as in an image arrangement template. Whether an image pertains to a person is determined using a machine learning classifier. A plurality of candidate lineages from a root or self node may be evaluated based on the number and/or quality of images associated therewith and/or based on filtering the one or more characteristics of the nodes in the candidate lineages.

Methods, systems, and computer-program products for image enhancement include receiving an image and optionally a user request, classify the image, crop image components of the image, restore cropped image components of the image, colorized restored image components, and reconstruct the image from the colorized, restored image components and other components. The other components may include text components that are restored in a separate treatment pipeline.

A computing server may receive genealogical records that include historical records of deceased individuals. The computing server may normalize the genealogical records into normalized genealogical records. Normalizing the genealogical records may include converting a text string of a genealogical record into a standardized format. The computing server may stitch the normalized genealogical records into a plurality of clusters. Each cluster corresponds to an individual and includes one or more genealogical records associated with the individual. The computing server may identify a life-event record that is commonly associated with a subset of clusters, the life-event record indicating that a plurality of deceased individuals are connected through a non-familial relationship in a life event documented by the life-event record. The computing server may cause a graphical user interface to display a representation of a historical network among the plurality of deceased individuals that are connected through the non-familial relationship.