Building risk analysis system with geographic risk scoring

1. A building risk analysis system comprising one or more memory devices storing instructions thereon, that, when executed by one or more processors, cause the one or more processors to:

receive a plurality of threats, each of the plurality of threats comprising a location, wherein each of the plurality of threats are threats of a particular threat category;

determine a number of threats for each of a plurality of geographic areas based on the location of each of the plurality of threats;

determine, based on the plurality of threats for the plurality of geographic areas, a correlation indicator for the particular threat category indicating a level of linearity between the plurality of threats and a population level for the plurality of geographic areas for the particular threat category;

determine, based on the level of linearity indicated by the correlation indicator, whether a linear relationship or a non-linear relationship exists between the plurality of threats and the population level for the plurality of geographic areas;

generate a risk model to generate a risk score for each of the plurality of geographic areas, the risk model generated to apply a linear mapping responsive to a determination that the linear relationship exists between the plurality of threats and the population level, the risk model generated to apply a non-linear mapping responsive to a determination that the non-linear relationship exists between the plurality of threats and the population level; and

execute the risk model for a geographic region to generate the risk score, causing building equipment to control an environment of a building.

2. The building risk analysis system of claim 1 , wherein the instructions cause the one or more processors to determine a per capita number of the plurality of threats for each of the plurality of geographic areas based on the population level of each of the plurality of geographic areas; and

wherein the instructions cause the one or more processors to determine the risk score for each of the plurality of geographic areas based on one or more characteristics of a distribution and the per capita number of the plurality of threats for each of the plurality of geographic areas.

3. The building risk analysis system of claim 1 , wherein the instructions cause the one or more processors to:

store the risk score for each of the plurality of geographic areas in a database;

receive a query from an external system for a particular risk score of a particular geographic area of the plurality of geographic areas, the query comprising an identifier of the particular geographic area;

retrieving the particular risk score from the database;

generate a query response comprising the particular risk score; and

communicate the query response to the external system.

4. The building risk analysis system of claim 1 , wherein the instructions cause the one or more processors to:

determine, based on a distribution, one or more of the plurality of threats that are anomalies; and

filter out the one or more of the plurality of threats.

5. The building risk analysis system of claim 1 , wherein the instructions cause the one or more processors to:

receive a plurality of weather threats, each of the plurality of weather threats comprising a second location, wherein each of the plurality of weather threats are threats of one weather threat category of a plurality of weather threat categories;

determine a particular number of weather threats for each of the plurality of geographic areas and each of the plurality of weather threat categories based on the location of each of the plurality of threats;

generate a weather threat distribution based on the number of threats for each of the plurality of geographic areas and each of the plurality of weather threat categories; and

determine a particular risk score for each of the plurality of geographic areas and each of the plurality of weather threat categories based on the weather threat distribution.

6. The building risk analysis system of claim 1 , wherein the instructions cause the one or more processors to receive the population level for each of the plurality of geographic areas;

wherein the instructions cause the one or more processors to generate a distribution based on the population level for each of the plurality of geographic areas.

7. The building risk analysis system of claim 1 , wherein the instructions cause the one or more processors to:

determine, based on the plurality of threats, a Pearson correlation score for the particular threat category; and

determine that the linear relationship exists between the particular threat category and a population number based on the Pearson correlation score;

wherein the instructions cause the one or more processors to determine the risk score for each of the plurality of geographic areas by applying a linear normalization to the number of threats or a non-linear normalization to the number of threats based on whether the linear relationship exists.

8. The building risk analysis system of claim 1 , wherein the instructions cause the one or more processors to:

receive a second plurality of threats, each of the second plurality of threats comprising a second location, wherein each of the second plurality of threats are threats of a threat category of a plurality of threat categories;

determine a second number of threats for each of the plurality of geographic areas based on the location of each of the second plurality of threats;

generate a distribution based on the number of threats for each of the plurality of geographic areas and each of the plurality of threat categories; and

determine a second risk score for each of the plurality of geographic areas and each of the plurality of threat categories based on one or more characteristics of the distribution of each of the plurality of geographic areas and each of the plurality of threat categories and the number of threats for each of the plurality of geographic areas.

9. The building risk analysis system of claim 8 , wherein the plurality of threat categories are each a crime threat category, wherein the plurality of threat categories comprise at least one of a violent crime or a property related crime.

10. The building risk analysis system of claim 1 , wherein the instructions cause the one or more processors to determine the risk score for each of the plurality of geographic areas based on one or more characteristics of a distribution and the number of threats for each of the plurality of geographic areas by:

determining the one or more characteristics of the distribution, wherein the one or more characteristics define a skew of the distribution;

select a normalization algorithm from a plurality of normalization algorithms based on the skew of the distribution; and

determine the risk score for each of the plurality of geographic areas by normalizing the number of threats for each of the plurality of geographic areas with the normalization algorithm.

11. The building risk analysis system of claim 10 , wherein the skew of the distribution is one of a positive skew, a negative skew, or a normal distribution, wherein the positive skew, the negative skew, and the normal distribution are each linked to one of the plurality of normalization algorithms.

12. The building risk analysis system of claim 10 , wherein the one or more characteristics of the distribution comprise a median and a mean;

wherein the instructions further comprise determining the skew of the distribution by comparing the median and the mean.

13. A method of risk analysis comprising:

receiving, by one or more processing circuits, a plurality of threats, each of the plurality of threats comprising a location, wherein each of the plurality of threats are threats of a particular threat category;

determining, by the one or more processing circuits, a number of threats for each of a plurality of geographic areas based on the location of each of the plurality of threats;

determining, by the one or more processing circuits, a correlation indicator for the particular threat category indicating a level of linearity between the plurality of threats and a population level for the plurality of geographic areas for the particular threat category, based on the plurality of threats for the plurality of geographic areas;

determining, based on the level of linearity indicated by the correlation indicator by the one or more processing circuits, whether a linear relationship or a non-linear relationship exists between the plurality of threats and the population level for the plurality of geographic areas;

generating, by the one or more processing circuits, a risk model to generate a risk score for each of the plurality of geographic areas, the risk model generated to apply a linear mapping responsive to a determination that the linear relationship exists between the plurality of threats and the population level, the risk model generated to apply a non-linear mapping responsive to a determination that the non-linear relationship exists between the plurality of threats and the population level; and

executing, by the one or more processing circuits, the risk model for a geographic region to generate the risk score, causing building equipment to control an environment of a building.

14. The method of claim 13 , further comprising:

receiving, by the one or more processing circuits, a plurality of weather threats, each of the plurality of weather threats comprising a second location, wherein each of the plurality of weather threats are threats of one weather threat category of a plurality of weather threat categories;

determining, by the one or more processing circuits, a particular number of weather threats for each of the plurality of geographic areas and each of the plurality of weather threat categories based on the location of each of the plurality of threats;

generating, by the one or more processing circuits, a weather threat distribution based on the number of threats for each of the plurality of geographic areas and each of the plurality of weather threat categories; and

determining, by the one or more processing circuits, a particular risk score for each of the plurality of geographic areas and each of the plurality of weather threat categories based on the weather threat distribution.

15. The method of claim 13 , further comprising:

receiving, by the one or more processing circuits, the population level for each of the plurality of geographic areas; and

generating, by the one or more processing circuits, a distribution based on the population level for each of the plurality of geographic areas.

16. The method of claim 13 , further comprising:

receiving, by the one or more processing circuits, a second plurality of threats, each of the second plurality of threats comprising a second location, wherein each of the second plurality of threats are threats of a threat category of a plurality of threat categories;

determining, by the one or more processing circuits, a second number of threats for each of the plurality of geographic areas based on the location of each of the second plurality of threats;

generating, by the one or more processing circuits, a distribution based on the number of threats for each of the plurality of geographic areas and each of the plurality of threat categories; and

determining, by the one or more processing circuits, a second risk score for each of the plurality of geographic areas and each of the plurality of threat categories based on one or more characteristics of the distribution of each of the plurality of geographic areas and each of the plurality of threat categories and the number of threats for each of the plurality of geographic areas.

17. The method of claim 16 , wherein the plurality of threat categories are each a crime threat category, wherein the plurality of threat categories comprise at least one of a violent crime or a property related crime.

18. The method of claim 13 , comprising:

determining, by the one or more processing circuits, the risk score for each of the plurality of geographic areas based on one or more characteristics of a distribution and the number of threats for each of the plurality of geographic areas by:

determining the one or more characteristics of the distribution, wherein the one or more characteristics define a skew of the distribution;

selecting a normalization algorithm from a plurality of normalization algorithms based on the skew of the distribution; and

determining the risk score for each of the plurality of geographic areas by normalizing the number of threats for each of the plurality of geographic areas with the normalization algorithm.

19. The method of claim 18 , wherein the skew of the distribution is one of a positive skew, a negative skew, or a normal distribution, wherein the positive skew, the negative skew, and the normal distribution are each linked to one of the plurality of normalization algorithms.

20. A risk analysis system comprising:

one or more memory devices storing instructions thereon; and

one or more processors, wherein the one or more processors execute the instructions causing the one or more processors to:

receive a plurality of threats, each of the plurality of threats comprising a location, wherein each of the plurality of threats are threats of a particular threat category;

determine a number of threats for each of a plurality of geographic areas based on the location of each of the plurality of threats;

determine, based on the plurality of threats for the plurality of geographic areas, a correlation indicator for the particular threat category indicating a level of linearity between the plurality of threats and a population level for the plurality of geographic areas for the particular threat category;

determine, based on the level of linearity indicated by the correlation indicator, whether a linear relationship or a non-linear relationship exists between the plurality of threats and the population level for the plurality of geographic areas;

generate a risk model to generate a risk score for each of the plurality of geographic areas, the risk model generated to apply a linear mapping responsive to a determination that the linear relationship exists between the plurality of threats and the population level, the risk model generated to apply a non-linear mapping responsive to a determination that the non-linear relationship exists between the plurality of threats and the population level; and

execute the risk model for a geographic region to generate the risk score, causing building equipment to control an environment of a building.