Abstract: Embodiments as disclosed include document analysis systems that may obtain email data collected or obtained from email servers from one or more source systems and build a graph of the emails, where the nodes of the email graph represent data about an email and the edges in the graph between the nodes of the graph are determined based on metadata associated with the emails or the text content of the emails. These email graphs may be quickly and efficiently updated as new email data is obtained such that the document analysis systems may organize emails into conversations for utilization by users in reviewing these emails in context.

Abstract: Systems and methods for data modeling in multi-tenant systems are disclosed. Embodiments allow the customization of data models for data types (e.g., such as documents or the like) through the addition of fields to data models for data types for particular tenants without modification to components of the system by allowing the definition of a data type and its associated fields for each tenant and externalizing the definition of those data types. This metamodel can thus enable the fields of a data type for a particular tenant to be independently modified or updated for that tenant and data type. The data type for an individual tenant at any given point in time can thus be defined by the set of fields (e.g., and field versions) associated with that data type as defined for that tenant in the metamodel at that point in time.

Abstract: Systems and methods for providing consistent and time aligned data from arbitrary sets of data in a data analytics platform are disclosed. Embodiments of such systems and methods may format datasets comprising data received from various data sources to facilitate the provisioning of time aligned data from these datasets based on a time specified in a query for one or more of those datasets.

Abstract: Embodiments as disclosed include document analysis systems that may obtain email data collected or obtained from email servers from one or more source systems and build a graph of the emails, where the nodes of the email graph represent data about an email and the edges in the graph between the nodes of the graph are determined based on metadata associated with the emails or the text content of the emails. These email graphs may be quickly and efficiently updated as new email data is obtained such that the document analysis systems may organize emails into conversations for utilization by users in reviewing these emails in context.

Abstract: Systems and methods for data modeling in multi-tenant systems are disclosed. Embodiments allow the customization of data models for data types (e.g., such as documents or the like) through the addition of fields to data models for data types for particular tenants without modification to components of the system by allowing the definition of a data type and its associated fields for each tenant and externalizing the definition of those data types. This metamodel can thus enable the fields of a data type for a particular tenant to be independently modified or updated for that tenant and data type. The data type for an individual tenant at any given point in time can thus be defined by the set of fields (e.g., and field versions) associated with that data type as defined for that tenant in the metamodel at that point in time.

Abstract: Embodiments of systems and methods for a search system that is adapted to utilize a family search operator are disclosed. Such a family search operator may return all documents that match the inner expression encompassed by the family search operator or having a family member that matched the inner expression of the family search operator.

Abstract: Artificial intelligence based document analysis systems and methods are disclosed. Embodiments of document analysis systems may allow the manipulation of datasets and associated codes by determining representations for these codes or datasets based on a machine learning model. The codes or datasets can then be manipulated using the associated representations.

Abstract: Embodiments as disclosed may generate an organizational hierarchy based on embeddings of portions of documents. Embeddings resulting from the embedding of the portions of the documents can be clustered using a hierarchical clustering mechanism to segment the portion space into a set of hierarchical clusters. Documents can be assigned to these clusters based on the presence of a portion of a document within a cluster. In this manner, the documents may themselves be clustered based on the clusters created from portions across the documents of the corpus. The clusters to which a document is assigned may also be ranked with respect to that document. Similarly, documents assigned to cluster can be ranked within the cluster to which they are assigned. Additionally, in certain embodiments, names or snippets for the clusters of the hierarchy may be derived from the portions comprising that cluster.

Abstract: Artificial intelligence based document analysis systems and methods are disclosed. Embodiments of document analysis systems may allow the reuse of coded datasets defined in association with a particular code by allowing these datasets to be bundled to define a dataset for another code, where that code may be associated with a target corpus of documents. A model can then be trained based on that dataset and used to provide predictive scores for the documents of the target corpora with respect to the code. Furthermore, this code can be applied not just to the target corpus of documents, but additionally can be applied against any other corpora.

Abstract: A machine learning system continuously receives tag signals indicating membership relations between data objects from a data corpus and tag targets. The machine learning system is asynchronously and iteratively trained with the received tag signals to identify further data objects from the data corpus predicted to have a membership relation with the single tag target. The machine learning system constantly improves its predictive accuracy in short time by the continuous training of a backend machine learning model based on implicit and explicit tag signals gathered from a non-intrusive monitoring of user interactions during a review process of the data corpus.

Abstract: Embodiments as disclosed may generate an organizational hierarchy based on embeddings of portions of documents. Embeddings resulting from the embedding of the portions of the documents can be clustered using a hierarchical clustering mechanism to segment the portion space into a set of hierarchical clusters. Documents can be assigned to these clusters based on the presence of a portion of a document within a cluster. In this manner, the documents may themselves be clustered based on the clusters created from portions across the documents of the corpus. The clusters to which a document is assigned may also be ranked with respect to that document. Similarly, documents assigned to cluster can be ranked within the cluster to which they are assigned. Additionally, in certain embodiments, names or snippets for the clusters of the hierarchy may be derived from the portions comprising that cluster.

Abstract: A non-transitory medium includes code representing processor-executable instructions; the code causes a processor to produce, via a machine learning model, a predicted value of a membership relationship between a data object and a target tag. The code causes the processor to display, via a user interface, the data object and the target tag and indicate a non-empty set of identified sections of one or more attributes of data object supporting the membership relationship between the data object and the target tag. The code also causes the processor to receive a tag signal, via the user interface, indicating one of an acceptance tag signal, a dismissal tag signal, or a corrective tag signal, and re-train the machine learning model based at least in part on the tag signal.

Abstract: A non-transitory medium includes code representing processor-executable instructions; the code causes a processor to produce, via a machine learning model, a predicted value of a membership relationship between a data object and a target tag. The code causes the processor to display, via a user interface, the data object and the target tag and indicate a non-empty set of identified sections of one or more attributes of data object supporting the membership relationship between the data object and the target tag. The code also causes the processor to receive a tag signal, via the user interface, indicating one of an acceptance tag signal, a dismissal tag signal, or a corrective tag signal, and re-train the machine learning model based at least in part on the tag signal.

Abstract: A machine learning system continuously receives tag signals indicating membership relations between data objects from a data corpus and tag targets. The machine learning system is asynchronously and iteratively trained with the received tag signals to identify further data objects from the data corpus predicted to have a membership relation with the single tag target. The machine learning system constantly improves its predictive accuracy in short time by the continuous training of a backend machine learning model based on implicit and explicit tag signals gathered from a non-intrusive monitoring of user interactions during a review process of the data corpus.