System and method for quantifying meeting effectiveness using natural language processing

A system comprising:

• a processor;
• and
• a non-transitory computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising:
• using a machine learning process to perform natural language processing on an audio input of a meeting between a plurality of individuals in which a speaker participates to obtain a plurality of segments and a set of contexts associated with the plurality of segments;
• generating a meeting score based on a user profile and the set of contexts by comparing the user profile to the set of contexts or a set of tags derived from the set of contexts;
• updating weights of the machine learning process to reduce a computational cost of obtaining the plurality of segments based on the meeting score and common patterns within the plurality of segments;
• and
• storing the weights of the updated machine learning process in a memory.

A non-transitory computer-readable storage medium having instructions stored which, when executed by a processor, cause the processor to perform operations comprising:

• receiving a meeting score, wherein the meeting score is generated by:
• performing natural language processing on audio input from a meeting, resulting in a transcript of the audio input;
• using a machine learning process based on the transcript of the audio input to determine a set of segments and a set of contexts for each respective segment of the set of segments;
• comparing a user profile of a user to the set of segments and the set of contexts to determine a comparison;
• and
• generating the meeting score of the meeting based on the comparison;
• updating weights of the machine learning process to reduce a computational cost of obtaining the set of segments based on the meeting score and common patterns within the set of segments;
• and
• storing the weights of the updated machine learning process in a memory.