Systems and methods are disclosed for providing content by generating a bookmark data structure for a topic based on determining retrieval of a first content item related to the topic, of a first content type. In response to determining retrieval of the first content item, the system may add the first content item to the bookmark data structure for the topic. The system may then determine retrieval of a second content item related to the topic, of a second content type and, in response to determining retrieval of the second content item, the system may add the second content item to the bookmark data structure for the topic. The system may generate, for display in a user interface (UI), a menu based on the data structure, with interactive UI elements that provide preview and/or access to the content item when interaction with the UI element is detected.

Various examples are provided related to identification of protected information elements associated with unique entities in data files present in data file collections associated with enterprise IT networks. The unique entities can be associated with one or more entity identifications in one or more data files. Computer-generated identification of entity identifications and protected information elements can be conducted, in part, by at least some human review. Information generated accordingly to the disclosed methodology can be used to generate plans for a time and number of human reviewers needed to review data files. Information generated from the processes herein can be configured as user notifications, reports, dashboards, machine learning for subsequent data file analyses, and notifications of unique entities having protected information elements present in one or more data files.

Various examples are provided related to identification of protected information elements associated with unique entities in data files present in data file collections associated with enterprise IT networks. The unique entities can be associated with one or more entity identifications in one or more data files. Computer-generated identification of entity identifications and protected information elements can be conducted, in part, by at least some human review. Information generated accordingly to the disclosed methodology can be used to generate plans for a time and number of human reviewers needed to review data files. Information generated from the processes herein can be configured as user notifications, reports, dashboards, machine learning for subsequent data file analyses, and notifications of unique entities having protected information elements present in one or more data files.

A POI popularity derivation device (10) includes: a dictionary generation unit (11) that assigns a feature word used as a co-occurrence word of a POI name to each popularity-assigned POI name serving as a popularity assignment target to generate a popularity-assigned POI dictionary in which a popularity-assigned POI name and a feature word are associated with each other; an extraction unit (12) that extracts posted data serving as a search target from posted data on the basis of predetermined criteria; and a popularity derivation unit (18) that searches for the posted data on the basis of a predetermined rule regarding feature words while referring to the popularity-assigned POI dictionary, to extract posted data linked to the popularity-assigned POI name, and derives the popularity of each popularity-assigned POI name on the basis of the number of pieces of extracted posted data for each popularity-assigned POI name.

The disclosure proposes a search method and system based on forbidden node awareness, comprising: Get a social network consisting of multiple nodes and their interactions. Assign weights to nodes and the interaction between nodes in the social network according to the method of calculating the authority value of web pages. With the preset forbidden node sensitivity threshold, the nodes whose weights are less than the threshold are removed from the social network. The remaining nodes are arranged in descending order according to their weights. Starting from an empty community, nodes are added into the community one by one in descending order of their weights, and the corresponding weighted conductance is calculated every time the node is added. The community corresponding to the moment with the least weighted conductance is the final result of community search, which can help people find more accurate community results when there are forbidden nodes.

The disclosure proposes a search method and system based on forbidden node awareness, comprising: Get a social network consisting of multiple nodes and their interactions. Assign weights to nodes and the interaction between nodes in the social network according to the method of calculating the authority value of web pages. With the preset forbidden node sensitivity threshold, the nodes whose weights are less than the threshold are removed from the social network. The remaining nodes are arranged in descending order according to their weights. Starting from an empty community, nodes are added into the community one by one in descending order of their weights, and the corresponding weighted conductance is calculated every time the node is added. The community corresponding to the moment with the least weighted conductance is the final result of community search, which can help people find more accurate community results when there are forbidden nodes.

The technology disclosed relates to deduplicating metadata about places. A feature generator module is configured to generate features for metadata profiles. The metadata profiles represent a plurality of places. The features are based on geohash strings and word embeddings generated for the metadata profiles. A diff generator module is configured to generate diff vectors that pair-wise encode results of comparison between features of paired metadata profiles. A classification module is configured to generate similarity scores for the paired metadata profiles based on the diff vectors. A particular similarity score indicates whether metadata profiles in a particular pair of metadata profiles represent a same place.

The technology disclosed relates to deduplicating metadata about places. A feature generator module is configured to generate features for metadata profiles. The metadata profiles represent a plurality of places. The features are based on geohash strings and word embeddings generated for the metadata profiles. A diff generator module is configured to generate diff vectors that pair-wise encode results of comparison between features of paired metadata profiles. A classification module is configured to generate similarity scores for the paired metadata profiles based on the diff vectors. A particular similarity score indicates whether metadata profiles in a particular pair of metadata profiles represent a same place.

Embodiments of the present disclosure describe selective discovery, management, and deletion of personal data. The method accesses a set of data on a networked resource. The data is formed of a plurality of data elements which are arranged in at least one data table. The method identifies one or more sensitive data elements within the set of data related to one or more individuals. The method determines a sensitivity level of the one or more sensitive data elements and generates a catalogue including at least one new data element representative of the one or more sensitive data elements and based on the sensitivity level of the one or more sensitive data elements. The method tags the one or more sensitive data elements within the catalogue based on the sensitivity level of the one or more sensitive data elements corresponding to the new data element.

Embodiments of the present disclosure describe selective discovery, management, and deletion of personal data. The method accesses a set of data on a networked resource. The data is formed of a plurality of data elements which are arranged in at least one data table. The method identifies one or more sensitive data elements within the set of data related to one or more individuals. The method determines a sensitivity level of the one or more sensitive data elements and generates a catalogue including at least one new data element representative of the one or more sensitive data elements and based on the sensitivity level of the one or more sensitive data elements. The method tags the one or more sensitive data elements within the catalogue based on the sensitivity level of the one or more sensitive data elements corresponding to the new data element.