A table organized into a set of batch units is accessed. A set of N-grams are generated for a data value in the source table. The set of N-grams include a first N-gram of a first length and a second N-gram of a second length where the first N-gram corresponds to a prefix of the second N-gram. A set of fingerprints are generated for the data value based on the set of N-grams. The set of fingerprints include a first fingerprint generated based on the first N-gram and a second fingerprint generated based on the second N-gram and the first fingerprint. A pruning index that indexes distinct values in each column of the source table is generated based on the set of fingerprints and stored in a database with an association with the source table.

A processor-implemented method securely responds to a query for information from a data graph. One or more processors create an embedding for encrypted sensitive information in vertices in a data graph; and bucketize embedded encrypted sensitive information on an embedding graph, where bucketizing the embedded encrypted sensitive information clusters vertices from the graph database that have shared data graph features. The processor(s) receive a query of the data graph from a requester, where the query is for information related to the shared data graph features. The processor(s) retrieve a bucket from the embedding graph that contains the information related to the shared data graph features; and extract encrypted sensitive information from the retrieved bucket.

A processor-implemented method securely responds to a query for information from a data graph. One or more processors create an embedding for encrypted sensitive information in vertices in a data graph; and bucketize embedded encrypted sensitive information on an embedding graph, where bucketizing the embedded encrypted sensitive information clusters vertices from the graph database that have shared data graph features. The processor(s) receive a query of the data graph from a requester, where the query is for information related to the shared data graph features. The processor(s) retrieve a bucket from the embedding graph that contains the information related to the shared data graph features; and extract encrypted sensitive information from the retrieved bucket.

A method of providing artificial intelligence (AI) functionality to target legacy customer outreach platforms of a plurality of tenant enterprises includes storing a plurality of AI templates, each of which is associated with one or more AI routines, generating a campaign object associating one or more of the AI templates with a tenant enterprise from among the plurality of tenant enterprises, transforming a communication on a switching network associated with the tenant enterprise according to the one or more AI templates associated with the campaign object, and providing the transformed communication to a target legacy customer outreach platform of the tenant enterprise.

A method of providing artificial intelligence (AI) functionality to target legacy customer outreach platforms of a plurality of tenant enterprises includes storing a plurality of AI templates, each of which is associated with one or more AI routines, generating a campaign object associating one or more of the AI templates with a tenant enterprise from among the plurality of tenant enterprises, transforming a communication on a switching network associated with the tenant enterprise according to the one or more AI templates associated with the campaign object, and providing the transformed communication to a target legacy customer outreach platform of the tenant enterprise.

Techniques and systems are described that leverage computer vision as part of search to expand functionality of a computing device available to a user and increase operational computational efficiency as well as efficiency in user interaction. In a first example, user interaction with items of digital content is monitored. Computer vision techniques are used to identify digital images in the digital content, objects within the digital images, and characteristics of those objects. This information is used to assign a user to a user segment of a user population which is then used to control output of subsequent digital content to the user, e.g., recommendations, digital marketing content, and so forth.

A method of auto-provisioning AI-based dialog services for a plurality of target applications includes storing a plurality of dialog templates, generating a deployment object associating one or more of the dialog templates with a target application from among the plurality of target applications, extracting textual data from the target application, assembling the extracted textual data into inquiries or inquiry responses according to the one or more dialog templates associated with the deployment object, and deploying an AI-based dialog service to the target application based on the assembled inquiries or inquiry responses. Each of the dialog templates may include one or more sets of common inquiries or common inquiry responses.

A method of auto-provisioning AI-based dialog services for a plurality of target applications includes storing a plurality of dialog templates, generating a deployment object associating one or more of the dialog templates with a target application from among the plurality of target applications, extracting textual data from the target application, assembling the extracted textual data into inquiries or inquiry responses according to the one or more dialog templates associated with the deployment object, and deploying an AI-based dialog service to the target application based on the assembled inquiries or inquiry responses. Each of the dialog templates may include one or more sets of common inquiries or common inquiry responses.

Systems and methods are described for recommending a content item. A search query for a content item is received. The availability of the content item from more than one source is determined. In response to determining that the content item is available from more than one source, the quality of each of the available content items from respective sources is determined. A recommendation factor is determined. The recommendation factor is based on at least one of the bandwidth available to a user device, the resolution capability of the user device, and the quality of experience of each of the sources from which the content item is available. A list of search results for the available content items is generated. The list is ordered based on the quality of each of the available content items from respective sources and the recommendation factor.

An online concierge system generates an item graph connecting item nodes with attribute nodes of the items. Example attributes include a brand, a category, a department, or any other suitable information about the item. When the online concierge system receives a search query to identify one or more items from a customer, the online concierge system parses the search query into combinations of terms and identifies item nodes and attribute nodes related to the search query. The online concierge system identifies item nodes and attribute nodes that are likely to result in a conversion. Information about the identified nodes is presented to the customer. The customer may select an item node to purchase the item, or an attribute node to execute a new search query based on terms associated with the attribute node.