Syntax translation from first syntax to second syntax based on string analysis
A computerized method of assigning a building automation system point type to a plurality of unclassified data points is provided. The method includes receiving unclassified data points and attributes for each data point. The method includes receiving classifications for a first subset of the unclassified data points. Each classification associates a data point with a building automation system point type. The method includes generating a term set containing substrings that appear in the attributes. The method includes generating a first matrix describing a frequency that the substrings appear in the attributes. The method includes calculating an indicator of a probability that the presence of the selected substring results in the data point belonging to the selected point type. The method includes assigning a point type to a second subset by finding the substring and potential point type pair having the greatest indication of probability.
1 . A building system of a building comprising one or more storage devices having instructions stored thereon that, when executed by one or more processors, cause the one or more processors to:
receive a plurality of strings representing a plurality of points, spaces, or pieces of equipment of the building;
receive a list of a plurality of semantic type descriptions for the plurality of points, spaces, or pieces of equipment computable by a plurality of software applications;
label the plurality of points, spaces, or pieces of equipment with the plurality of semantic type descriptions by analyzing the plurality of strings with a translation technique;
determine a plurality of relationships between a plurality of labels selected for the plurality of points, spaces, or pieces of equipment; and
generate a file computable by the plurality of software applications, the file comprising the plurality of labels and the plurality of relationships between the plurality of labels.
2 . The building system of claim 1 , wherein:
the plurality of strings are defined in a first syntax;
the plurality of labels assigned for the plurality of points, spaces, or pieces of equipment are defined in a second syntax; and
the translation technique is trained to translate between the first syntax and the second syntax.
3 . The building system of claim 1 , wherein the plurality of strings are in a first syntax;
wherein the instructions cause the one or more processors to:
generate a user interface comprising indications of the plurality of points, spaces, or pieces of equipment of the building in a second syntax comprising the plurality of semantic type descriptions;
cause a user device to display the user interface; and
receive, via the user device, an indication of one or more of the plurality of relationships from the user device based on one or more user interactions with the user interface.
4 . The building system of claim 1 , wherein the instructions cause the one or more processors to:
assign at least one type of the plurality of semantic type descriptions to each of the plurality of strings.
5 . The building system of claim 1 , wherein the building system further comprises a plurality of pieces of building equipment of the building, wherein the plurality of pieces of building equipment are configured to monitor and control one or more building spaces of the building using the plurality of labels.
6 . The building system of claim 1 , wherein the plurality of strings form text descriptions of attributes of the plurality of points, spaces, or pieces of equipment of the building.
7 . The building system of claim 1 , wherein the instructions cause the one or more processors to:
generate a set of probability values for a string of the plurality of strings, each probability value of the set of probability values corresponding to a different label of the plurality of semantic type descriptions and indicating a probability that the string belongs to a corresponding label based on one or more characters of the string;
wherein the one or more characters of the string are an input to the translation technique and the set of probability values are an output of the translation technique.
8 . The building system of claim 1 , wherein the translation technique is at least one of a Bayes technique or a latent semantic indexing technique.
9 . A method, comprising:
receiving, by one or more processing circuits, a plurality of strings representing a plurality of points, spaces, or pieces of equipment of a building;
receiving, by the one or more processing circuits, a list of a plurality of semantic type descriptions for the plurality of points, spaces, or pieces of equipment computable by a plurality of software applications;
labeling, by the one or more processing circuits, the plurality of points, spaces, or pieces of equipment with the plurality of semantic type descriptions by analyzing the plurality of strings with a translation technique;
determining, by the one or more processing circuits, a plurality of relationships between a plurality of labels selected for the plurality of points, spaces, or pieces of equipment; and
generating, by the one or more processing circuits, a file computable by the plurality of software applications, the file comprising the plurality of labels and the plurality of relationships between the plurality of labels.
10 . The method of claim 9 , wherein:
the plurality of strings are defined in a first syntax;
the plurality of labels assigned for the plurality of points, spaces, or pieces of equipment are defined in a second syntax; and
the translation technique is trained to translate between the first syntax and the second syntax.
11 . The method of claim 9 , wherein the plurality of strings are in a first syntax;
wherein the method comprises:
generating, by the one or more processing circuits, a user interface comprising indications of the plurality of points, spaces, or pieces of equipment of the building in a second syntax comprising the plurality of semantic type descriptions;
causing, by the one or more processing circuits, a user device to display the user interface; and
receiving, by the one or more processing circuits an indication of one or more of the plurality of relationships from the user device based on one or more user interactions with the user interface.
12 . The method of claim 9 , comprising:
assigning, by the one or more processing circuits, at least one type of the plurality of semantic type descriptions to each of the plurality of strings.
13 . The method of claim 9 , comprising:
monitoring or controlling, by the one or more processing circuits, one or more building spaces of the building using the plurality of labels.
14 . The method of claim 9 , wherein the plurality of strings form text descriptions of attributes of the plurality of points, spaces, or pieces of equipment of the building.
15 . The method of claim 9 , comprising:
generating, by the one or more processing circuits, a set of probability values for a string of the plurality of strings, each probability value of the set of probability values corresponding to a different label of the plurality of semantic type descriptions and indicating a probability that the string belongs to a corresponding label based on one or more characters of the string;
wherein the one or more characters of the string are an input to the translation technique and the set of probability values are an output of the translation technique.
16 . The method of claim 9 , wherein the translation technique is at least one of a Bayes technique or a latent semantic indexing technique.
17 . One or more non-transitory storage media having instructions stored thereon that, when executed by one or more processors, cause the one or more processors to:
receive a plurality of strings representing a plurality of points, spaces, or pieces of equipment of a building;
receive a list of a plurality of semantic type descriptions for the plurality of points, spaces, or pieces of equipment computable by a plurality of software applications;
label the plurality of points, spaces, or pieces of equipment with the plurality of semantic type descriptions by analyzing the plurality of strings with a translation technique;
determine a plurality of relationships between a plurality of labels selected for the plurality of points, spaces, or pieces of equipment; and
generate a file computable by the plurality of software applications, the file comprising the plurality of labels and the plurality of relationships between the plurality of labels.
18 . The one or more non-transitory storage media of claim 17 , wherein:
the plurality of strings are defined in a first syntax;
the plurality of labels assigned for the plurality of points, spaces, or pieces of equipment are defined in a second syntax; and
the translation technique is trained to translate between the first syntax and the second syntax.
19 . The one or more non-transitory storage media of claim 17 , wherein the plurality of strings are in a first syntax;
wherein the instructions cause the one or more processors to:
generate a user interface comprising indications of the plurality of points, spaces, or pieces of equipment of the building in a second syntax comprising the plurality of semantic type descriptions;
cause a user device to display the user interface; and
receive, via the user device, an indication of one or more of the plurality of relationships from the user device based on one or more user interactions with the user interface.
20 . The one or more non-transitory storage media of claim 17 , wherein the instructions cause the one or more processors to:
assign at least one type of the plurality of semantic type descriptions to each of the plurality of strings.