Virtual zoning review

A system comprising:

• at least one hardware processor;
• and
• one or more software modules that are configured to, when executed by the at least one hardware processor:
• employ partial encoding using fuzzy logic to transform and generate textual provisions and guidelines of land development codes and regulations into a computable digital representation of the land development codes and regulations by translating a semantic structure of each code and regulation into object rules or parametric models using a formal language, classifying and encoding objective data specified in the land development codes and regulations using feature extraction in the object rules or parametric models, and classifying and encoding subjective data specified in the object rules using fuzzy logic and neural Natural Language Processing (NLP) in the object rules or parametric models;
• acquire, from a land development design document in a building information model (BIM) digital format, a plurality of objects and a plurality of attributes describing the plurality of objects, wherein the plurality of attributes include at least a spatial relationship of a land development design and one or more details on zoning, landscaping, drainage, sanitation, and wetland controls with respect to the land development design;
• and
• perform real time code checking and/or compliance of individual building elements of the land development design document in the BIM digital format as the land development design document is being developed by:
• graphically displaying a graphical user interface of a site design model platform, wherein the graphical user interface is embedded with a plurality of graphic buttons for initiating a plurality of actions of code conformance checking of the land development design document;
• upon receiving a selection of a first one of the plurality of graphic buttons, performing design model validation, wherein the design model validation comprises approving a format of the land development design document;
• performing, via with an artificial neural network, code checking, wherein exchange model code conformance checking of the land development design document comprises using the computable digital representation of the land development codes and regulations, wherein code conformance checking comprises checking land use details of the land development design document for conformance with at least zoning codes and regulations, landscaping codes and regulations, drainage codes and regulations, sanitation codes and regulations, and wetland control codes and regulations, as defined by the computable digital representation of the land development codes and regulations;
• upon receiving a selection of a second one of the plurality of graphic buttons embedded in the graphical user interface of the site design model platform, performing compliance reporting based on input provided from the software modules, wherein the compliance reporting includes a prediction confidence data for the code conformance checking performed by the software modules;
• receiving inaccurate prediction of code conformance data;
• and
• retraining the software modules and the artificial neural network using the inaccurate prediction of code conformance data to improve prediction accuracy.

A non-transitory computer-readable medium having instructions stored therein, wherein the instructions, when executed by a processor, cause the processor to:

• employ partial encoding using fuzzy logic to transform and generate textual provisions and guidelines of land development codes and regulations into a computable digital representation of the land development codes and regulations by translating a semantic structure of each code and regulation into object rules or parametric models using a formal language, classifying and encoding objective data specified in the land development codes and regulations is encoded using feature extraction in the object rules or parametric models, and classifying and encoding subjective data specified in the object rules using fuzzy logic and neural Natural Language Processing (NLP) in the object rules or parametric models;
• acquire from a land development design document in a building information model (BIM) digital format, a plurality of objects and a plurality of attributes describing the plurality of objects, wherein the plurality of attributes include at least a spatial relationship of a land development design and one or more details on zoning, landscaping, drainage, sanitation, and wetland controls with respect to the land development design;
• and
• perform real time code checking and/or compliance of individual building elements of the land development design document in the BIM digital format as the land development design document is being developed by:
• graphically displaying a graphical user interface of a site design model platform, wherein the graphical user interface is embedded with a plurality of graphic buttons for initiating a plurality of actions of code conformance checking of the land development design document;
• upon receiving a selection of a first one of the plurality of graphic buttons, performing design model validation, wherein the design model validation comprises approving a format of the land development design document;
• performing, via one or more design checking modules and an artificial neural network, code conformance checking of the land development design document using the computable digital representation of the land development codes and regulations, wherein code conformance checking comprises checking land use details of the land development design document for conformance with at least zoning codes and regulations, landscaping codes and regulations, drainage codes and regulations, sanitation codes and regulations, and wetland control codes and regulations, as defined by the computable digital representation of the land development codes and regulations;
• upon receiving a selection of a second one of the plurality of graphic buttons embedded in the graphical user interface of the site design model platform, performing compliance reporting based on input provided from the design checking modules, wherein the compliance reporting includes a prediction confidence data for the code conformance checking performed by the one or more design checking modules;
• receiving inaccurate prediction of code conformance data;
• and
• retraining the one or more design checking modules and the artificial neural network using the inaccurate prediction of code conformance data to improve prediction accuracy.