Abstract: Systems and methods for generating output data based on a data graph are provided. An output request for the output data based on the data graph is received. The output request comprises one of a natural language request from a target user or an application request from an application of the target user. The data graph has nodes and edges between the nodes. The nodes represent entities associated with an enterprise organization and the edges represent relationships among the entities. A graph data query is generated with a large language model (LLM) using the output request as a first input to the LLM. The graph data query is performed against the data graph to obtain a graph data output that represents a sub-portion of the data graph. The output data is generated with the LLM using the graph data output as a second input to the LLM.

Abstract: Techniques for extracting and ranking multiple topic descriptions based on source contexts and subsequently selecting individual topic descriptions to surface based on recipient contexts. More specifically, a mining platform may extract, from a set of source documents making up a corpus, topic descriptions for various topics that are relevant to an enterprise. The mining platform may further rank the extracted topic descriptions based on a source context of those documents from which individual topic descriptions are extracted. Subsequently, when users access enterprise documents including term-usage instances of topics for which one or more topic descriptions have been extracted and ranked, a description serving module may select a topic description that is contextually appropriate for a recipient view the enterprise documents.

Abstract: A computerized personal assistant includes a natural language user interface, a natural language processing machine, an identity machine, and a knowledge-base updating machine. The knowledge-base updating machine is configured to update a user-centric artificial intelligence knowledge base associated with the particular user to include a new or updated user-centric fact based on the computer-readable representation of the user input, wherein the knowledge-base updating machine updates the user-centric artificial intelligence knowledge base via an update protocol useable by a plurality of different computer services.

Abstract: A method of generating a unified graph is described. First graph data is received from a first data source, nodes within the first graph data including first, second, and third fields. Second graph data is received from a second data source, nodes within the second graph data including first, second, and fourth fields. The unified graph is generated from the first and second graph data using aggregated fields of the first field and the third field as a unique identifier of a unified schema for nodes within the unified graph having a first type and aggregated fields of the first field and the fourth field as a unique identifier of the unified schema for nodes within the unified graph having a second type, wherein nodes of the unified graph represent entities and edges of the unified graph represent relationships among the entities.

Abstract: A computing system obtain a keyword and an identifier for a user of a content authoring application. Based upon the keyword and identifier for the user, the computing system walks a user graph comprising nodes connected by edges. The walk comprises identifying seed nodes in the user graph representing at least one topic that corresponds to the keyword and identifying second level nodes in the user graph that are connected to the seed nodes. The second level nodes represent first content that is associated with the user. The computing system transmits contextual data that is based upon the first content to the content authoring application. The contextual data is processed and formatted and is included in second content presentable by the content authoring application. The contextual data may be used to autogenerate the second content without user input. The second content may be modified by the user as desired.

Abstract: A computerized personal assistant includes a natural language user interface, a natural language processing machine, an identity machine, and a knowledge-base updating machine. The knowledge-base updating machine is configured to update a user-centric artificial intelligence knowledge base associated with the particular user to include a new or updated user-centric fact based on the computer-readable representation of the user input, wherein the knowledge-base updating machine updates the user-centric artificial intelligence knowledge base via an update protocol useable by a plurality of different computer services.

Abstract: A computing system identifies a user graph for a user, where the user graph comprises nodes and edges connecting the nodes. The nodes comprise topic nodes and entity nodes representing documents of the user. The computing system identifies a cluster of the topic nodes corresponding to a productivity area of the user. The computing system performs a walk of the user graph based upon the cluster to identify activities performed by the user with respect to the productivity area within a period of time. The computing system computes a score for the productivity area based upon types of each of the activities and a number of times each of the activities were performed and causes graphical data to be presented on a display based upon the score. The graphical data may include the score and a suggestion to the user as to how to improve productivity.

Abstract: A computing system obtain a keyword and an identifier for a user of a content authoring application. Based upon the keyword and identifier for the user, the computing system walks a user graph comprising nodes connected by edges. The walk comprises identifying seed nodes in the user graph representing at least one topic that corresponds to the keyword and identifying second level nodes in the user graph that are connected to the seed nodes. The second level nodes represent first content that is associated with the user. The computing system transmits contextual data that is based upon the first content to the content authoring application. The contextual data is processed and formatted and is included in second content presentable by the content authoring application. The contextual data may be used to autogenerate the second content without user input. The second content may be modified by the user as desired.

Abstract: A computing system identifies a heterogenous multi-entity graph user graph for a user based upon an identifier for the user. The user graph includes nodes and edges connecting the nodes. The nodes include topic nodes representing topics and entity nodes. The entity nodes represent people associated with the user, documents of the user, or derived information that is derived from the documents. The computing system identifies a cluster of the topic nodes corresponding to a productivity area of the user and performs a walk of the user graph based upon the subset of the topic nodes to identify a subset of the people, the documents, and the derived information. The computing system causes a graphical user interface (GUI) to be presented on a display, where the GUI includes identifiers for the subset of the people, the documents, and the derived information.

Abstract: Systems and methods for contextual memory capture and recall are provided. The contextual memory capture and recall systems and methods help a user create, store, and recall memory information associated with an identified activity. The contextual memory capture and recall systems and methods are capable of identifying user activities where a memory inquiry may be desirable, creating a memory inquiry with a recommended memory action based on the activity, providing the memory inquiry to the user, and automatically linking an accepted memory action, along with any received memory information for the memory action, with the identified activity.

Abstract: An entity interlinkage platform may receive a corpus of enterprise documents and user profile data that corresponds to an individual user. The entity interlinkage platform utilizes topic extraction models to extract entities from the corpus and further utilizes the user profile data to generate a knowledge graph that includes interlinkages between the extracted entities. The entity interlinkage platform may identify a multitude of topic descriptions and corresponding topic terms from source documents that an access control list permits an individual user to access. Then, based on the user profile data, the entity interlinkage platform may generate a knowledge graph that is tailored for the individual user's specific purposes within the enterprise. For example, the knowledge graph may be generated based on knowledge graph preferences (which may be defined by the individual user) indicating preferred topic description types and/or levels of detail in association with specific topics and/or categories of topics.

Abstract: Aspects of the present disclosure relate to identifying relationships between entities in a user graph relative to a specific user. The identified relationships may provide user specific insights on related entities from across the enterprise environment. The insights may be provided to the user in a graphical user interface which may organize the insights into categories of information with selectable features to permit user interaction with the insights. Thus, the insights provided from the user graph or user sub-graph according to aspects described herein, may improve productivity and the potential for collaboration across the enterprise environment while reducing user workload.

Abstract: A method of generating a unified graph is described. First graph data is received from a first data source, nodes within the first graph data including first, second, and third fields. Second graph data is received from a second data source, nodes within the second graph data including first, second, and fourth fields. The unified graph is generated from the first and second graph data using aggregated fields of the first field and the third field as a unique identifier of a unified schema for nodes within the unified graph having a first type and aggregated fields of the first field and the fourth field as a unique identifier of the unified schema for nodes within the unified graph having a second type, wherein nodes of the unified graph represent entities and edges of the unified graph represent relationships among the entities.

Abstract: A method for providing graph data is described. A request for graph data based on a data graph is received, the data graph having i) nodes representing entities associated with an enterprise organization, and ii) edges between nodes representing relationships among the entities. A search embedding corresponding to the request is generated. Embeddings from a set of embeddings that are adjacent to the search embedding are identified, wherein the set of embeddings represent the data graph. Graph data corresponding to the identified embeddings is provided in response to the request.

Abstract: A graph data structure for an artificial intelligence knowledge base includes a plurality of user-centric facts associated with a user. Each user-centric fact has an application-agnostic data format and includes a subject graph node, an object graph node, and an edge connecting the subject graph node to the object graph node. The graph data structure is designed to accommodate facts from different application-specific data providers using the same application-agnostic data format even when the different application-specific data providers use different native data formats.

Abstract: A computing system identifies a first subgraph and a second subgraph of a user graph of a user. The first subgraph represents first activities performed by the user in a plurality of applications during a first time period and the second subgraph represents second activities performed by the user in the plurality of applications during a second time period. The computing system identifies a topic of interest to the user based upon the first subgraph and the second subgraph. The computing system predicts an amount of time that the user will spend on working on the topic during a future time period based upon the first subgraph and the second subgraph, where the future time period occurs after the first time period and the second time period. The computing system causes an identifier for the topic and an indication of the amount of time to be displayed to the user.

Abstract: An intelligent task assistant program can identify tasks associated with a user over a reporting period based on an analysis of, and inferences drawn from, data associated with one or more personal information programs, such as an electronic calendar application, an electronic reminder application, an electronic collaborative application, and/or an electronic communication application. The task assistant may also prioritize the identified tasks based on content associated with the tasks. Some or all of the prioritized tasks can be provided to an output device for perception by the user.

Abstract: A computerized personal assistant includes a natural language user interface, a natural language processing machine, an identity machine, and a knowledge-base updating machine. The knowledge-base updating machine is configured to update a user-centric artificial intelligence knowledge base associated with the particular user to include a new or updated user-centric fact based on the computer-readable representation of the user input, wherein the knowledge-base updating machine updates the user-centric artificial intelligence knowledge base via an update protocol useable by a plurality of different computer services.

Abstract: This disclosure provides a system and method for providing intelligently-selected collections of user-centric content in a web browser. When implemented as a method, the method includes maintaining a user-centric graph with a plurality of user-centric facts derived from user interaction with different computer services. The method further includes recognizing different contexts of interest to the user. For each context, a collection of user-centric facts pertaining to the context are recognized in the user-centric graph, such recognition being based on a relationship between user-centric facts in the user-centric graph. The method further includes, for each context, displaying intelligently-selected content based on the collection of user-centric facts.

Abstract: An intelligent task assistant program can identify tasks associated with a user over a reporting period based on an analysis of, and inferences drawn from, data associated with one or more personal information programs, such as an electronic calendar application, an electronic reminder application, an electronic collaborative application, and/or an electronic communication application. The task assistant may also prioritize the identified tasks based on content associated with the tasks. Some or all of the prioritized tasks can be provided to an output device for perception by the user.