Enhanced scheduling operations utilizing large language models and methods of use thereof
Disclosed are systems and methods for receiving a meeting request via an electronic account of a user; determining a conflict between the meeting request and a pre-existing meeting, extracting and comparing information associated with each meeting based on an analysis of each meeting; determining a priority associated with each meeting based on the analysis of the information of each meeting; and utilizing a machine learning model to generate an output associated with the priority of each meeting to the electronic account of the user.
1 . A method comprising:
receiving, by a processor, a meeting request via an electronic account of a user;
determining, by the processor, a conflict between the meeting request and a pre-existing meeting;
building, by the processor, a prompt, the prompt including representations of the meeting request, the pre-existing meeting, and at least one user preference;
inputting, by the processor, the prompt into a machine learning model, an output of the machine learning model comprising a proposed modification of an item selected from the group consisting of the meeting request and the pre-existing meeting;
generating, by the processor, a recommendation based on the output of the machine learning model and presenting the recommendation to the user;
generating, by the processor, a response to the meeting request using the output of the machine learning model;
receiving user feedback responsive to the recommendation;
generating a second prompt that includes the prompt and the user feedback; and
inputting the second prompt into the machine learning model to obtain a revised recommendation.
2 . The method of claim 1 , wherein the machine learning model comprises a large language model.
3 . The method of claim 1 , wherein building the prompt comprises inputting the representations of the meeting request and the pre-existing meeting into a prompt template.
4 . The method of claim 1 , wherein the at least one user preference comprises a preference selected from the group consisting of an explicit user preference and an inferred user preference.
5 . The method of claim 1 , wherein a representation of a given meeting includes one or more of a type, a duration, a location, a number of participants, content to be discussed, and identification of a host.
6 . The method of claim 1 , wherein an output of the machine learning model comprises a serialized format and the method further comprises executing an action based on the serialized format.
7 . A non-transitory computer readable storage medium for tangibly storing computer program instructions capable of being executed by a computer processor, the computer program instructions defining the steps of:
receiving, by a processor, a meeting request via an electronic account of a user;
determining, by the processor, a conflict between the meeting request and a pre-existing meeting;
building, by the processor, a prompt, the prompt including representations of the meeting request, the pre-existing meeting, and at least one user preference;
inputting, by the processor, the prompt into a machine learning model, an output of the machine learning model comprising a proposed modification an item selected from the group consisting of the meeting request and the pre-existing meeting;
generating, by the processor, a recommendation based on the output of the machine learning model and presenting the recommendation to the user;
generating, by the processor, a response to the meeting request using the output of the machine learning model;
receiving, by the processor, user feedback responsive to the recommendation;
generating, by the processor, a second prompt that includes the prompt and the user feedback; and
inputting, by the processor, the second prompt into the machine learning model to obtain a revised recommendation.
8 . The non-transitory computer readable storage medium of claim 7 , wherein the machine learning model comprises a large language model.
9 . The non-transitory computer readable storage medium of claim 7 , wherein building the prompt comprises inputting the representations of the meeting request and the pre-existing meeting into a prompt template.
10 . The non-transitory computer readable storage medium of claim 7 , wherein the at least one user preference comprises a preference selected from the group consisting of an explicit user preference and an inferred user preference.
11 . The non-transitory computer readable storage medium of claim 7 , wherein a representation of a given meeting includes one or more of a type, a duration, a location, a number of participants, content to be discussed, and identification of a host.
12 . The non-transitory computer readable storage medium of claim 7 , wherein an output of the machine learning model comprises a serialized format and the steps further comprise executing an action based on the serialized format.
13 . A device comprising:
a processor configured to:
receive a meeting request via an electronic account of a user;
determine a conflict between the meeting request and a pre-existing meeting;
build a prompt, the prompt including representations of the meeting request, the pre-existing meeting, and at least one user preference;
input the prompt into a machine learning model, an output of the machine learning model comprising a proposed modification of an item selected from the group consisting of the meeting request and the pre-existing meeting;
generate a recommendation based on the output of the machine learning model and presenting the recommendation to the user;
generate a response to the meeting request using the output of the machine learning model;
receive user feedback responsive to the recommendation;
generate a second prompt that includes the prompt and the user feedback; and
input the second prompt into the machine learning model to obtain a revised recommendation.
14 . The device of claim 13 , wherein the machine learning model comprises a large language model.
15 . The device of claim 13 , wherein building the prompt comprises inputting the representations of the meeting request and the pre-existing meeting into a prompt template.
16 . The device of claim 13 , wherein the at least one user preference comprises a preference selected from the group consisting of an explicit user preference and an inferred user preference.
17 . The device of claim 13 , wherein a representation of a given meeting includes one or more of a type, a duration, a location, a number of participants, content to be discussed, and identification of a host.
18 . The device of claim 13 , wherein an output of the machine learning model comprises a serialized format and the processor further configured for executing an action based on the serialized format.