Meeting Space Recommendation via Visit Profiles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face difficulties in selecting suitable meeting rooms due to lack of knowledge about building layouts and attendee location preferences, leading to inefficient computer-implemented scheduling systems that require extensive input and resource consumption.
Innovation Solution
A computer-implemented technique that recommends candidate meeting spaces based on selected visit profiles for attendees, using movement-related data from mobile devices and crowdsourced geographical position information to reduce the number of operations and resource consumption in setting up meetings.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If the organizer performs a computer-implemented search to find information regarding meeting rooms, then the organizer can obtain meeting room information, but the process requires extensive time and computing resources
Solution Approach 1:
The system pre-generates visit profiles for attendees based on their historical visit data stored in the database before the meeting scheduling occurs. This preliminary preparation eliminates the need for real-time search operations when organizing meetings, as the recommendation engine can directly query pre-processed profile data.
Solution Approach 2:
The system automatically captures and processes visit data from mobile devices to create and update visit profiles without requiring organizer intervention. The recommendation engine then autonomously matches attendees with suitable meeting rooms based on their profiles, eliminating the need for extended dialogues between organizers and attendees to discover preferences.
2Loss of information
If the organizer engages in an extended dialogue with attendees to discover their preferences, then the organizer can understand attendee location preferences, but the process increases time expenditure and operational complexity
Solution Approach 1:
Attendees' location preferences are automatically captured through their mobile device data and processed by the system to generate visit profiles. The recommendation engine then uses these profiles to autonomously identify suitable meeting rooms, completely eliminating the need for extended dialogues between organizers and attendees.
Solution Approach 2:
The visit profile acts as an intermediary data structure that bridges the gap between raw mobile device data and meeting room recommendations. This profile contains processed information about attendee visit patterns and preferences, allowing the recommendation engine to make informed decisions without direct organizer-attendee communication.
3Productivity
If the system uses prior scheduling sessions to suggest meeting rooms, then the organizer can get quick suggestions, but this does not help when current needs differ from prior sessions
Solution Approach 1:
The system dynamically selects which visit profile to use based on the current meeting context and attendee characteristics. Rather than relying on a fixed set of historical data from prior scheduling sessions, the recommendation engine adapts by querying the most relevant visit profile that matches the current situation, ensuring both speed and adaptability.
Data Source
AI summary
A computer-implemented technique is described herein for scheduling events. The technique involves recommending one or more candidate spaces (e.g., candidate meeting rooms) based on a selected visit profile for each attendee to the event. More specifically, the technique selects a visit profile for each attendee from a group including a live visit profile, a short-term visit profile, and a long-term visit profile. Each such visit profile describes one or more visits made by the attendee within a prescribed timespan. The technique captures visit data for each such visit based on movement-related signals provided by one or more movement-determining mechanisms. A mobile computing device provides at least one movement-determining mechanism. In a preliminary phase, the technique can identify the geographical position of each candidate meeting space using a crowdsourcing operation.