Abstract: Generating profiles that consolidate tenant data with interaction and transaction records from heterogeneous data sources in real time. Executing AI agents including an orchestration agent that orchestrates other agents. Providing a model interface layer that securely connects to an external machine learning model of a third-party agent while enforcing data governance rules, wherein the machine learning model can securely access customer data from the profiles of the multi-tenant platform under context-aware policies. Providing secure access to data from the profiles to the model through the model interface layer without exporting the data into a separate repository, such that the model processes live enterprise data in place. Receiving a predictive output derived from the exported data. Updating a profile by writing the predictive output as a new attribute of that profile, thereby enriching the profile with machine-generated insights in real time to create an enriched profile.

Abstract: Profiling, by a data profiler agent, an external dataset intended for integration into a multi-tenant platform. Determining data quality metrics for the dataset. Identifying data quality issues in the dataset that are predicted to adversely impact entity resolution operations of the multi-tenant platform. Identifying at least a portion of the dataset that is predicted not to adversely impact entity resolution operations of the multi-tenant platform. Generating recommended data improvement actions, wherein the data improvement actions include corrections or enrichments for the dataset. Generating and storing data profiling results. Ingesting the portion of the dataset that is predicted not to adversely impact the entity resolution operations of the multi-tenant platform into the multi-tenant platform. Executing a first data improvement action on the portion of the dataset associated with the first data improvement action, thereby generating a first improved portion of the dataset.

Abstract: Automatically classifying data fields given a set of their sample values (e.g., schema mapping) is disclosed. These models aim to infer attribute and entity structure defined by a platform and/or automated classification system. These models may rely upon both public machine learning models as well as proprietary model weights owned by the platform and/or automated classification system (and/or associated organizations or enterprises).

Abstract: Obtaining a data model associated with one or more tenants of a multi-tenant platform. Ingesting data from one or more data sources, wherein the data includes a plurality of columns. Generating a first natural language summary, by a first large language model, underlying data of each of the columns of the data. Generating a second natural language summary, by a second large language model, the data model, wherein the data model includes a plurality of different fields. Comparing the first natural language summary and the second natural language summary. Automatically classifying, based on the comparison of the first natural language summary and the second natural language summary, a first portion of the data as corresponding to a first field of the data model and a second portion of the data as corresponding to a second field of the data model. Obtaining a query from a user. Resolving the query, based on the automatic classification, to generate an answer for the query. Providing the answer to the user.

Abstract: Ingesting data from one or more data sources, wherein the data is associated with a tenant of a multi-tenant platform. Generating a machine learning model input based on the ingested data. Providing the generated machine learning model input to a machine learning model. Inferring, using the machine learning model, an inferred dynamic data structure, wherein the inferred dynamic data structure includes a subset of entity attributes inferred by the machine learning model from a set of the entity attributes, wherein at least a portion of the entity attributes include conditional entity attributes, wherein the conditional entity attributes depend on the values of one or more of the other entity attributes of the set of the entity attributes. Presenting, via a graphical user interface (GUI), a visual representation of the inferred dynamic data structure. Tracking user interactions received through the GUI associated with the visual representation of the inferred dynamic data structure.

Abstract: Receiving, by a multi-tenant platform, a segment query, wherein the segment query includes static attributes and dynamic attributes, wherein the dynamic attributes include interaction data. Executing, by the multi-tenant platform, the segment query. Receiving, by the multi-tenant platform in response to the execution of the segment query, a segment result set, wherein the segment result set comprises a segment of a population of a tenant of the multi-tenant platform. Automatically synchronizing, by the multi-tenant platform in response to receiving the segment result set, the segment result set with one or more third-party systems. Triggering, in response to the automatic synchronization, the one or more third-party systems to perform one or more campaign actions of a campaign using the segment included in the segment result set. Storing the segment query. Receiving updated data for the static attributes and the dynamic attributes.

Abstract: Instantiating a first microservice-based platform instance in a first geographic region, wherein a first microservice of the first microservice-based platform instance performs index searching, a second microservice of the first microservice-based platform instance performs audit tracking, a third microservice of the first microservice-based platform instance performs object history tracking, and a fourth microservice of the first microservice-based platform instance performs entity matching. Instantiating a second microservice-based platform instance in a second geographic region, wherein the second microservice-based platform instance is a duplicate of the first microservice-based platform instance. Continuously synchronizing the first microservice-based platform instance and the second microservice-based platform instance. Receiving a query. Detecting a failure of the first microservice-based platform instance. Redirecting the query to the second microservice-based platform instance.

Abstract: Instantiating a first microservice-based platform instance in a first geographic region, wherein a first microservice of the first microservice-based platform instance performs index searching, a second microservice of the first microservice-based platform instance performs audit tracking, a third microservice of the first microservice-based platform instance performs object history tracking, and a fourth microservice of the first microservice-based platform instance performs entity matching. Instantiating a second microservice-based platform instance in a second geographic region, wherein the second microservice-based platform instance is a duplicate of the first microservice-based platform instance. Continuously synchronizing the first microservice-based platform instance and the second microservice-based platform instance. Pre-calculating, via the microservices, the index searching, the audit tracking, the object history tracking, and the entity matching.

Abstract: Ingesting data from a plurality of data sources. Converting the data into a plurality of vectors, wherein each vector represents a respective object of the data. Comparing the plurality of vectors with each other. Determining a distance between the plurality of vectors based on the comparison. Receiving a query. Automatically determining a set of candidate matches based on the query and the determined distances between the plurality of vectors based on the comparison. Resolving the query based on matching one or more portions of the query with the set of candidate matches.

Abstract: Among other techniques, techniques for machine learning-based entity resolution are described.

Abstract: Among other techniques, techniques for machine learning-based entity resolution are described.

Abstract: Among other techniques, techniques for real-time cross-domain data management are described.

Abstract: Deploying a multi-tenant computing platform, wherein the multi-tenant computing platform comprises a plurality of different underlying data structures, applications, functions, and back-end services. Defining a unified data model for the multi-tenant computing platform, wherein the unified data model normalizes the plurality of different underlying data structures, applications, functions, and back-end services of the multi-tenant computing platform, and wherein the unified data model defines relationships and dependencies between data types, and wherein at least a portion of the data types are indicated as private by the unified data model. Receiving data management operation metadata from a local area computing environment remote from the multi-tenant computing platform, wherein the data management operation metadata anonymously indicates one or more local data operations of the local area computing environment, the one or more local data operations associated with one or more private data types.

Abstract: Among other techniques, techniques for parallelized rules-based and machine learning-based grouping are described.

Abstract: Among other techniques, techniques for parallelized rules-based and machine learning-based matching are described.