Developing event-specific provisional knowledge graphs
Techniques and a framework are described herein for constructing and/or updating, e.g., on top of a general-purpose knowledge graph, an “event-specific provisional knowledge graph.” In various implementations, live data stream(s) may be analyzed to identify entity(s) associated with a developing event. The entity(s) may form part of a general-purpose knowledge graph that includes entity nodes and edges between the entity nodes. Based on the identified one or more entities, an event-specific provisional knowledge graph may be constructed or updated in association with the developing event. In some implementations, the event-specific provisional knowledge graph may be queried for new information about the developing event. Computing devices may be caused to render, as output, the new information.
1. A method implemented using one or more processors, comprising:
analyzing two or more live data streams;
based on the analyzing, newly detecting a developing event and identifying one or more entities associated with the newly-detected developing event;
in response to newly detecting the developing event, and based on the identified one or more entities, constructing an event-specific provisional knowledge graph associated with the newly-detected developing event;
querying the event-specific provisional knowledge graph for first information about the newly-detected developing event;
causing one or more computing devices to render, as first output, the first information about the newly-detected developing event;
subsequent to the constructing, monitoring one or more of the live data streams to corroborate or verify one or more elements of the event-specific provisional knowledge graph; and
subsequent to the causing, and in response to corroboration or verification of the one or more elements of the event-specific provisional knowledge graph, merging one or more of the elements of the event-specific provisional knowledge graph with a general-purpose knowledge graph, whereby the general-purpose knowledge graph is subsequently searchable for information related to the developing event.
2. The method of claim 1 , wherein the first output comprises an annotation that indicates the first information is uncorroborated.
3. The method of claim 2 , further comprising:
subsequent to the merging, querying the general-purpose knowledge graph for second information about the newly-detected developing event; and
causing one or more of the computing devices to render, as second output, the second information about the newly-detected developing event.
4. The method of claim 3 , wherein the second output comprises an annotation that indicates the second information is corroborated.
5. The method of claim 1 , wherein one or more of the entities associated with the newly-detected developing event forms part of the general-purpose knowledge graph, wherein the general-purpose knowledge graph includes a plurality of entity nodes and a plurality of edges between the plurality of entity nodes, wherein the plurality of entity nodes represent entities and the plurality of edges represent relationships between the entities.
6. The method of claim 5 , wherein the event-specific provisional knowledge graph shares one or more entity nodes with the general-purpose knowledge graph.
7. A system comprising one or more processors and memory storing instructions that, in response to execution by the one or more processors, cause the one or more processors to:
analyze two or more live data streams;
based on the analysis, newly detect a developing event and identify one or more entities associated with the newly-detected developing event;
in response to the developing event being newly detected, and based on the identified one or more entities, construct an event-specific provisional knowledge graph associated with the newly-detected developing event;
query the event-specific provisional knowledge graph for first information about the newly-detected developing event;
cause one or more computing devices to render, as first output, the first information about the newly-detected developing event;
subsequent to the event-specific provisional knowledge graph being constructed, monitor one or more of the live data streams to corroborate or verify one or more elements of the event- specific provisional knowledge graph; and
subsequent to the first output being rendered, and in response to corroboration or verification of the one or more elements of the event-specific provisional knowledge graph, merge one or more of the elements of the event-specific provisional knowledge graph with a general-purpose knowledge graph, whereby the general-purpose knowledge graph is subsequently searchable for information related to the developing event.
8. The system of claim 7 , wherein the first output comprises an annotation that indicates the first information is uncorroborated.
9. The system of claim 8 , further comprising instructions to:
query the general-purpose knowledge graph for second information about the newly-detected developing event; and
transmit second data to one or more computing devices, wherein the second data is configured to be rendered as second output that includes the second information about the newly-detected developing event.
10. The system of claim 9 , wherein the second output comprises an annotation that indicates the second information is corroborated.
11. The system of claim 7 , wherein one or more of the entities associated with the newly-detected developing event forms part of the general-purpose knowledge graph, wherein the general-purpose knowledge graph includes a plurality of entity nodes and a plurality of edges between the plurality of entity nodes, wherein the plurality of entity nodes represent entities and the plurality of edges represent relationships between the entities.
12. The system of claim 11 , wherein the event-specific provisional knowledge graph shares one or more entity nodes with the general-purpose knowledge graph.
13. At least one non-transitory computer-readable medium comprising instructions that, in response to execution by one or more processors, cause the one or more processors to:
analyze two or more live data streams;
based on the analysis, newly detect a developing event and identify one or more entities associated with the newly-detected developing event;
in response to the developing event being newly detected, and based on the identified one or more entities, construct an event-specific provisional knowledge graph associated with the newly-detected developing event;
query the event-specific provisional knowledge graph for first information about the newly-detected developing event;
cause one or more computing devices to render, as first output, the first information about the newly-detected developing event;
subsequent to the event-specific provisional knowledge graph being constructed, monitor one or more of the live data streams to corroborate or verify one or more elements of the event- specific provisional knowledge graph; and
subsequent to the first output being rendered, and in response to corroboration or verification of the one or more elements of the event-specific provisional knowledge graph, merge one or more of the elements of the event-specific provisional knowledge graph with a general-purpose knowledge graph, whereby the general-purpose knowledge graph is subsequently searchable for information related to the developing event.
14. The at least one non-transitory computer-readable medium of claim 13 , wherein the first output comprises an annotation that indicates the first information is uncorroborated.
15. The at least one non-transitory computer-readable medium of claim 14 , further comprising instructions to:
query the general-purpose knowledge graph for second information about the newly-detected developing event; and
transmit second data to one or more computing devices, wherein the second data is configured to be rendered as second output that includes the second information about the newly-detected developing event.
16. The at least one non-transitory computer-readable medium of claim 15 , wherein the second output comprises an annotation that indicates the second information is corroborated.
17. The at least one non-transitory computer-readable medium of claim 13 , wherein one or more of the entities associated with the newly-detected developing event forms part of the general-purpose knowledge graph, wherein the general-purpose knowledge graph includes a plurality of entity nodes and a plurality of edges between the plurality of entity nodes, wherein the plurality of entity nodes represent entities and the plurality of edges represent relationships between the entities.