Intelligent system and method of optimizing cross-team information flow

A method for optimizing cross-team information flow in a communication network comprising:

• receiving, from a communication application, via a network, a plurality of candidate post items for display to a first user of an organization, each candidate post item being a post item published by another user of the organization and being a post that is accessible to the first user;
• generating, in real-time, via a knowledge network generating engine, a temporal communication knowledge network graph which represents communication events that have occurred between users of the organization, each communication event being represented by a first node that represents a sender of the communication event, a second node that represents a receiver of the communication event and an edge that represents the communication event from the sender to the receiver, a departure time, and an arrival time, the graph being continuously updated as new communication events occur, wherein the candidate post items are messages that are shared with and are available for viewing to a group of two or more users of the organization that are a subset of the users of the organization;
• for each one of the plurality of candidate post items, estimating a value of a total information metric for the temporal communication knowledge network if one of the plurality of candidate post items is viewed by the first user, wherein the total information metric accounts for degradation of information along long paths and amount of communication by applying an exponential decay function to model the degradation;
• ranking the plurality of candidate post items based on the estimated total information metric for each of the plurality of candidate post items;
• and
• transmitting recommendation data to the communication application, via the network, for recommending the plurality of candidate post items to the user based on the ranking, the recommendation data usable by the communication application to sort the candidate post items according to ranking based on a weighted combination of at least an information latency metric and the total information metric, wherein the temporal communication knowledge network and the recommendation are updated in real-time as new candidate post items are received.

A non-transitory computer readable medium on which are stored instructions that, when executed, cause a programmable device to perform functions of:

• receiving, from a communication application, via a network, a plurality of candidate post items for display to a first user of an organization, each candidate post item being a post item published by another user of the organization and being a post that is accessible to the first user, the organization having a plurality of teams and the first user belonging to a first team of the plurality of teams and the other user belonging to a second team of the plurality of teams;
• generating, in real-time, via a knowledge network generating engine, a temporal communication knowledge network graph which represents communication events that have occurred between the plurality of the teams, each communication event being represented by a first node that represents a sending team of the communication event, a second node that represents a receiving team of the communication event and an edge that represents the communication event from the sending team to the receiving team, a departure time, and an arrival time, the graph being continuously updated as new communication events occur, wherein the candidate post items are messages that are shared with and are available for viewing to a group of two or more users of the organization that are a subset of the users of the organization;
• for each one of the plurality of candidate post items, estimating a value for a total information metric for the communication knowledge network if one of the plurality of candidate post items is viewed by the first user, wherein the total information metric accounts for degradation of information along long paths and amount of communication by applying an exponential decay function to model the degradation;
• ranking the plurality of candidate post items based on the estimated total information metric for each of the plurality of candidate post items to optimize cross-team information flow in the organization;
• and
• transmitting recommendation data to the communication application, via the network, for recommending the plurality of candidate post items to the user based on the ranking, the recommendation data usable by the communication application to sort the candidate post items according to ranking based on a weighted combination of at least an information latency metric and the total information metric, wherein the temporal communication knowledge network and the recommendation are updated in real-time as new candidate post items are received.