Assistant for providing information on unknown topics

1 . A system comprising:

a processing device; and

memory storing instructions that, when executed, perform operations comprising:

identifying, by a digital assistant, a topic in activity data, wherein the digital assistant is configured to monitor a conversation between users and detect topics used by the users in real-time;

determining information for the topic, wherein a type of the information is based on a type of the topic;

determining, by analyzing the activity data, a user having knowledge of the topic;

determining a candidate definition for the topic as known by the user based on an evaluation of the activity data, wherein the candidate definition at least one of defines a meaning of the topic or includes an acronym expansion of the topic;

determining, for the user, a confidence score for the candidate definition for the topic, wherein the confidence score indicates a confidence or a probability that the user knows the topic is associated with the candidate definition;

storing the topic, the information for the topic, the candidate definition for the topic, and the confidence score in a global list; and

evaluating the candidate definition during a subsequent conversation to determine whether the topic is known to the user.

2 . The system of claim 1 , wherein the topic represents an acronym, a codename, or an abbreviation.

3 . The system of claim 1 , wherein the topic represents a tool, a team, or an organizational unit.

4 . The system of claim 1 , wherein the activity data is associated with multiple users in an enterprise, the user being a member of the enterprise.

5 . The system of claim 1 , wherein the activity data includes at least one of: an electronic communication, a document, a meeting, a task, or a project.

6 . The system of claim 1 , wherein the activity data includes at least one of: internet browser activity or a search history.

7 . The system of claim 1 , wherein the information includes a definition of the topic, a description of the topic, or people associated with the topic.

8 . The system of claim 1 , wherein determining the user having knowledge of the topic comprises:

determining whether the user has used the topic previously in the activity data; and

when the user has used the topic previously in the activity data, determining the user has knowledge of the topic.

9 . The system of claim 1 , wherein determining the user having knowledge of the topic comprises:

determining whether the user has searched for or accessed information on the topic previously in the activity data; and

when the user has searched for or accessed the information on the topic previously in the activity data, determining the user has knowledge of the topic.

10 . The system of claim 1 , wherein the confidence score indicates a probability that the user knows the topic is associated with the candidate definition.

11 . The system of claim 1 , wherein the confidence score is based on at least one of:

interactions the user has with the topic;

a frequency of the interactions; or

a usage or referral of the topic by other users associated with the user.

12 . The system of claim 1 , wherein the global list comprises a plurality of topics and a plurality of candidate definitions that are associated with a plurality of users.

13 . The system of claim 1 , wherein the candidate definition is a definition as known by the user.

14 . The system of claim 1 , wherein the global list further stores one or more topics that are related to the topic based on the one or more topics being semantically or topically related to the topic.

15 . A method comprising:

identifying, by a digital assistant, a topic in activity data, wherein the digital assistant is configured to monitor a conversation between users and detect topics used by the users in real-time;

determining information for the topic as known;

determining, by analyzing the activity data, a first user and a second user having knowledge of the topic;

determining, for the first user, a first confidence score for a first candidate definition for the topic as known by the first user, wherein the first confidence score indicates a confidence or a probability that the first user knows the topic is associated with the first candidate definition;

determining, for the second user, a second confidence score for a second candidate definition for the topic as known by the second user;

storing in a global list:

the topic;

the information for the topic;

the first candidate definition;

the second candidate definition;

the first confidence score; and

the second confidence score; and

evaluating the candidate definition during a subsequent conversation to determine whether the topic is known to the user.

16 . The method of claim 15 , wherein the activity data includes documents or communications of users belonging to an enterprise.

17 . The method of claim 16 , wherein analyzing the activity data comprises:

searching the documents or the communications of the users for uses of the topic and references to the topic; and

determining the first user and the second user have knowledge of the topic based on at least one of their respective uses of the topic or their respective references to the topic.

18 . The method of claim 15 , the method further comprising:

determining, for the first user, a third confidence score for the second candidate definition for the topic as known by the first user; and

further storing in the global list the third confidence score.

19 . The method of claim 18 , the method further comprising:

determining, for the second user, a fourth confidence score for the first candidate definition for the topic as known by the second user; and

further storing in the global list the fourth confidence score.

20 . A device comprising:

a processing device; and

memory storing instructions that, when executed, perform operations comprising:

identifying, by a digital assistant, a topic in conversation data, wherein the digital assistant is configured to monitor a conversation between users and detect topics used by the users in real-time;

determining information for the topic;

determining, based on the conversation data, a user having knowledge of the topic;

determining a candidate definition for the topic as known by the user based on an evaluation of activity data associated with the user, wherein the candidate definition at least one of defines a meaning of the topic or includes an acronym expansion of the topic;

determining, based on the conversation data, a candidate definition for the topic as known by the user;

determining, for the user, a confidence score for the candidate definition;

storing the topic, the information for the topic, the candidate definition for the topic, and the confidence score in a global list; and

evaluating the candidate definition during a subsequent conversation to determine whether the topic is known to the user.