Determining building occupancy rates from multiple datasets

Patent metadata

Field	Value
Publication number	US-2016110652-A1
Application number	US-201414518268-A
Country	US
Kind code	A1
Filing date	Oct 20, 2014
Priority date	Oct 20, 2014
Publication date	Apr 21, 2016
Grant date	—

Abstract

A mechanism is provided for determining occupancy of a building at a time segment. Data points for potential occupants are obtained, which each have a collection data source, a probability of occupancy, an identity to a given potential occupant, and a timestamp. An individual probability is determined by: gathering the data points in time segment requested for the given potential occupant such that the data points gathered only identify the given potential occupant, and averaging each of the probability of occupancy for the data points to obtain the individual probability the given potential occupant was in building during time segment. The individual probabilities are added for the potential occupants during the time segment to obtain a total of the individual probabilities, and divided by an amount N, which is a number of occupants that should be in the building, to obtain a building probability of occupancy for the building.

First claim

What is claimed is:

1 . A method for determining occupancy of a building, the method comprising:
receiving a request to determine the occupancy of the building at a time segment in the past; obtaining data points for potential occupants of the building, the data points each having a collection data source, a probability of occupancy in the building, an identity that corresponds to a given potential occupant, and a timestamp; determining an individual probability that the given potential occupant of the potential occupants is in the building during the time segment by:
gathering the data points within the time segment requested for the given potential occupant of the potential occupants such that the data points gathered only identify the given potential occupant;
averaging each of the probability of occupancy for the data points of the given potential occupant to obtain the individual probability that the given potential occupant was in the building during the time segment;
determining individual probabilities for each of the potential occupants during the time segment; in response to determining the individual probabilities for each of the potential occupants during the time segment, adding together the individual probabilities for each of the potential occupants during the time segment to obtain a total of the individual probabilities; and dividing the total of the individual probabilities by an amount N, which is a number of occupants that should be in the building during the time segment, to obtain a building probability of occupancy for the building.

2 . The method of claim 1 , further comprising associating the probability of occupancy for each data point based on the collection data source and a type of collected data;
wherein the data points having collection data sources at the building have a higher probability of occupancy than the data points having the collection data sources located a predetermined distance away from the building.

3 . The method of claim 2 , wherein the individual probability for the given potential occupant requires more than one data point during the time segment requested;
wherein when only the one data point is in the time segment requested, the time segment is automatically enlarged to include an additional data point before or after the time segment requested; and wherein the individual probability determined for the given potential occupant is a likelihood that the given potential occupant was present in the building during the time segment requested.

4 . The method of claim 1 , wherein the data points specific to each of the potential occupants are respectively stored in an individual file for the potential occupants, such that the data points for the given potential occupant are identifiable.

5 . The method of claim 1 , wherein different time segments for each of the potential occupants are created in advance in anticipation for the time segment requested.

6 . The method of claim 5 , wherein each of the different time segments has a time segment probability of occupancy.

7 . The method of claim 5 , wherein each of the different time segments has a corresponding beginning time and ending time;
wherein the time segment probability, for the different time segments, is generated from the data points within the corresponding beginning time and ending time.

8 . The method of claim 7 , wherein a minimum block of time is required for each of the different time segments.

9 . An apparatus for determining occupancy of a building, the apparatus comprising:
a processor; and memory comprising computer-executable instructions that, when executed by the processor, cause the processor to perform operations, the operations comprising: receiving a request to determine the occupancy of the building at a time segment in the past; obtaining data points for potential occupants of the building, the data points each having a collection data source, a probability of occupancy in the building, an identity that corresponds to a given potential occupant, and a timestamp; determining an individual probability that the given potential occupant of the potential occupants is in the building during the time segment by:
gathering the data points within the time segment requested for the given potential occupant of the potential occupants such that the data points gathered only identify the given potential occupant;
averaging each of the probability of occupancy for the data points of the given potential occupant to obtain the individual probability that the given potential occupant was in the building during the time segment;
determining individual probabilities for each of the potential occupants during the time segment; in response to determining the individual probabilities for each of the potential occupants during the time segment, adding together the individual probabilities for each of the potential occupants during the time segment to obtain a total of the individual probabilities; and dividing the total of the individual probabilities by an amount N, which is a number of occupants that should be in the building during the time segment, to obtain a building probability of occupancy for the building.

10 . The apparatus of claim 9 , further comprising associating the probability of occupancy for each data point based on the collection data source and a type of collected data;
wherein the data points having collection data sources at the building have a higher probability of occupancy than the data points having the collection data sources located a predetermined distance away from the building.

11 . The apparatus of claim 10 , wherein the individual probability for the given potential occupant requires more than one data point during the time segment requested;
wherein when only the one data point is in the time segment requested, the time segment is automatically enlarged to include an additional data point before or after the time segment requested; and wherein the individual probability determined for the given potential occupant is a likelihood that the given potential occupant was present in the building during the time segment requested.

12 . The apparatus of claim 9 , wherein the data points specific to each of the potential occupants are respectively stored in an individual file for the potential occupants, such that the data points for the given potential occupant are identifiable.

13 . The apparatus of claim 9 , wherein different time segments for each of the potential occupants are created in advance in anticipation for the time segment requested.

14 . The apparatus of claim 13 , wherein each of the different time segments has a time segment probability of occupancy.

15 . The apparatus of claim 13 , wherein each of the different time segments has a corresponding beginning time and ending time;
wherein the time segment probability, for the different time segments, is generated from the data points within the corresponding beginning time and ending time.

16 . The apparatus of claim 14 , wherein a minimum block of time is required for each of the different time segments.

17 . A computer program product, tangibly embodied on a computer readable medium, for determining occupancy of a building, the computer program product including instructions that, when executed by a processor, cause the processor to perform operations comprising:
receiving a request to determine the occupancy of the building at a time segment in the past; obtaining data points for potential occupants of the building, the da

Assignees

• At & T Mobility Ii Llc

Inventors

• Meredith Sheldon K
• Austin Mark
• Fix Jeremy

Classifications

• G06N7/01 Primary

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06N7/005 Primary

  Physics · mapped topic