Auto-organizing objects based on document analysis
The present technology provides a solution that can bring organization to the accumulated data and can surface insights derived from an analysis of stored objects. More specifically, the present technology is directed to an object analysis and classification service which is a configurable platform for identifying objects relevant to a topic and providing analysis of the objects relevant to that topic. The object analysis and classification service can include one or more technologies for identifying objects relevant to a topic. The topic can be configured by a user account or can be a predefined topic selected by the user account. The topic can include parameters that can be used by the one or more technologies for identifying objects relevant to a topic and to provide insights defined by the topic.
1 . A method of automatically organizing objects into topics based on an analysis of a collection of objects, the method comprising:
receiving, via user input to a topic summary user interface at a client device, one or more parameters for identifying objects in the collection of objects relevant to a first topic;
analyzing, by at least one processor, the objects in the collection of objects for relevance to the first topic by an object analysis and classification service, the collection of objects being a general collection of objects associated with a user account, the objects being of diverse object types and from diverse sources, wherein the object types include directories, images, videos, documents, and code;
identifying a first object of a first object type based on the one or more parameters and a second object of a second object type, wherein the first object and the second object are part of the collection of objects and the first object type and the second object type are different;
tagging first objects in the collection of objects for relevance to the first topic as a result of the analyzing;
automatically surfacing, in the topic summary user interface, a user interface widget associated with the first topic and comprising information descriptive of the first objects and a link to the first objects;
receiving, in the topic summary user interface, an indication that the link to the first objects was activated; and
providing for display in the topic summary user interface the first objects.
2 . The method of claim 1 , wherein the topic summary user interface displays a plurality of widgets including a first widget and a second widget, wherein the first widget is associated with the first topic and displays the information descriptive of the first objects, and the second widget is associated with a second topic and displays information descriptive of second objects.
3 . The method of claim 1 , wherein the object analysis and classification service is a platform that is configured to receive the one or more parameters for objects associated with the first topic and to identify the first objects based on the one or more parameters and to analyze the first objects.
4 . The method of claim 1 , wherein the object analysis and classification service includes a clustering service, the clustering service is configured to cluster similar types of objects in the collection of objects associated with the user account into topic clusters.
5 . The method of claim 4 , further comprising:
identifying at least a portion of the first objects as objects located in a first topic cluster matching a topic identified in the first topic.
6 . The method of claim 1 , wherein the object analysis and classification service includes a classification service, the classification service includes at least one machine learning algorithm configured to identify objects in the collection of objects that correspond with objects in a training set of objects.
7 . The method of claim 1 , wherein the object analysis and classification service includes an LLM (large language model) prompt service, and the LLM prompt service is configured to prompt an LLM with at least one prompt included as part of the first topic.
8 . The method of claim 1 , wherein the first topic defines metadata for objects relevant to the first topic, the object analysis and classification service is configured to search for or filter the collection of objects associated with the user account to identify the first objects.
9 . The method of claim 1 , wherein the object analysis and classification service includes a patterns service, the patterns service is configured to recognize a pattern in data in at least one object in the collection of objects associated with the user account based on a pattern defined by the first topic.
10 . A computing system comprising:
at least one processor; and
a memory storing instructions that, when executed by the at least one processor, configure the system to:
receive, via user input to a topic summary user interface at a client device, one or more parameters for identifying objects in a collection of objects relevant to a first topic;
analyze, by the at least one processor, the objects in the collection of objects for relevance to the first topic by an object analysis and classification service, the collection of objects being a general collection of objects associated with a user account the objects being of diverse object types and from diverse sources, wherein the object types include directories, images, videos, documents, and code;
identify a first object of a first object type based on the one or more parameters and a second object of a second object type, wherein the first object and the second object are part of the collection of objects and the first object type and the second object type are different;
select first objects in the collection of objects for relevance to the first topic as a result of the analyzing;
automatically surface, in the topic summary user interface, a user interface widget associated with the first topic and comprising information descriptive of the first objects and a link to the first objects;
receive, in the topic summary user interface, an indication that the link to the first objects was activated; and
provide for display in the topic summary user interface the first objects.
11 . The computing system of claim 10 , wherein the topic summary user interface displays a plurality of widgets include a first widget and a second widget, wherein the first widget is associated with the first topic and displays the information descriptive of the first objects, and the second widget is associated with a second topic and displays information descriptive of second objects.
12 . The computing system of claim 10 , wherein the object analysis and classification service is a platform that is configured to receive the one or more parameters for objects associated with the first topic and to identify the first objects based on the one or more parameters and to analyze the first objects.
13 . The computing system of claim 10 , wherein the instructions further configure the system to:
identify at least a portion of the first objects as objects located in a first topic cluster matching a topic identified in the first topic.
14 . The computing system of claim 10 , wherein the object analysis and classification service includes an LLM (large language model) prompt service, and the LLM prompt service is configured to prompt an LLM with at least one prompt included as part of the first topic.
15 . A non-transitory computer-readable storage medium, the computer-readable storage medium including instructions that when executed by at least one processor, cause the at least one processor to:
receive, via user input to a topic summary user interface at a client device, one or more parameters for identifying objects in a collection of objects relevant to a first topic;
analyze, by the at least one processor, the objects in the collection of objects for relevance to the first topic by an object analysis and classification service, the collection of objects being a general collection of objects associated with a user account, the objects being of diverse object types and from diverse sources, wherein the object types include directories, images, videos, documents, and code;
identifying a first object of a first object type based on the one or more parameters and a second object of a second object type, wherein the first object and the second object are part of the collection of objects and the first object type and the second object type are different;
select first objects in the collection of objects for relevance to the first topic as a result of the analyzing;
automatically surface, in the topic summary user interface, a user interface widget associated with the first topic and comprising information descriptive of the first objects and a link to the first objects;
receive, in the topic summary user interface, an indication that the link to the first objects was activated; and
provide for display in the topic summary user interface the first objects.
16 . The computer-readable storage medium of claim 15 , wherein the topic summary user interface displays a plurality of widgets include a first widget and a second widget, wherein the first widget is associated with the first topic and displays the information descriptive of the first objects, and the second widget is associated with a second topic and displays information descriptive of second objects.
17 . The computer-readable storage medium of claim 15 , wherein the object analysis and classification service is a platform that is configured to receive the one or more parameters for objects associated with the first topic and to identify the first objects based on the one or more parameters and to analyze the first objects.
18 . The computer-readable storage medium of claim 15 , wherein the object analysis and classification service includes a clustering service, the clustering service is configured to cluster similar types of objects in the collection of objects associated with the user account into topic clusters.
19 . The computer-readable storage medium of claim 18 , wherein the instructions further configure the at least one processor to:
identify at least a portion of the first objects as objects located in a first topic cluster matching a topic identified in the first topic.
20 . The computer-readable storage medium of claim 15 , wherein the object analysis and classification service includes an LLM (large language model) prompt service, and the LLM prompt service is configured to prompt an LLM with at least one prompt included as part of the first topic.