USING ARTIFICIAL INTELLIGENCE FOR BUILDING DESIGN SPECIFICATION GENERATION

1 . A computer-implemented method comprising:

obtaining, as building design artificial intelligence model training data, building design data for a plurality of buildings;

enhancing the building design artificial intelligence model training data to include building performance specification data corresponding to obtained building design data;

training an artificial intelligence model using the building design artificial intelligence model training data to generate building design specifications based on building performance specifications and to translate building performance specifications into corresponding viable building performance specifications;

receiving building performance specifications for a building project, wherein each requested building performance specification corresponds to a respective performance specification parameter;

translating, using the artificial intelligence model and the building design artificial intelligence model training data, at least a first building performance specification into a first viable building performance specification parameter value;

providing the building performance specifications, including the first viable building performance specification parameter value, to the artificial intelligence model that is trained to generate building design specifications based on building performance specifications;

generating, by the artificial intelligence model, building designs for the building project that satisfy the building performance specifications; and

providing the building designs for the building project for evaluation and construction of the building project.

2 . The computer-implemented method of claim 1 , wherein obtaining building design data comprising obtaining building design data for existing buildings.

3 . The computer-implemented method of claim 1 , wherein obtaining building design data comprises generating synthetic data for synthetically-designed buildings.

4 . The computer-implemented method of claim 3 , wherein generating synthetic data comprises generating the synthetic data based on a set of rules that includes rules for how buildings can be composed.

5 . The computer-implemented method of claim 1 , wherein enhancing the building design artificial intelligence model training data comprises determining the building performance specifications for obtained building design data and associating determined performance specifications, in the building design artificial intelligence model training data, with corresponding building design information.

6 . The computer-implemented method of claim 1 , wherein the artificial intelligence model is trained to generate different kinds of building designs, including structural, architectural, and fixtures-related designs.

7 . The computer-implemented method of claim 1 , wherein the artificial intelligence model is trained to generate one kind of building design information selected from at least structural, architectural, and fixtures-related designs.

8 . The computer-implemented method of claim 7 , wherein the artificial intelligence model is included with other artificial intelligence models in a model cascade in which outputs of some artificial intelligence models are provided as inputs to other artificial intelligence models.

9 . The computer-implemented method of claim 1 , wherein received performance specifications include multi-modal information comprising at least textual and image inputs.

10 . The computer-implemented method of claim 1 , wherein at least some of the building design specifications include vector representations.

11 . The computer-implemented method of claim 10 , further comprising providing the vector representations to a performance evaluation system that evaluates performance of the building design specifications.

12 . A system comprising one or more computers and one or more storage devices on which are stored instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:

obtaining, as building design artificial intelligence model training data, building design data for a plurality of buildings;

enhancing the building design artificial intelligence model training data to include building performance specification data corresponding to obtained building design data;

training an artificial intelligence model using the building design artificial intelligence model training data to generate building design specifications based on building performance specifications and to translate building performance specifications into corresponding viable building performance specifications;

receiving building performance specifications for a building project, wherein each requested building performance specification corresponds to a respective performance specification parameter;

translating, using the artificial intelligence model and the building design artificial intelligence model training data, at least a first building performance specification into a first viable building performance specification parameter value;

providing the building performance specifications, including the first viable building performance specification parameter value, to the artificial intelligence model that is trained to generate building design specifications based on building performance specifications;

generating, by the artificial intelligence model, building designs for the building project that satisfy the building performance specifications; and

providing the building designs for the building project for evaluation and construction of the building project.

13 . The system of claim 12 , wherein obtaining building design data comprising obtaining building design data for existing buildings.

14 . The system of claim 12 , wherein obtaining building design data comprises generating synthetic data for synthetically-designed buildings.

15 . The system of claim 14 , wherein generating synthetic data comprises generating the synthetic data based on a set of rules that includes rules for how buildings can be composed.

16 . One or more computer-readable storage media encoded with instructions that, when executed by one or more computers, cause the one or more computers to perform operations comprising:

obtaining, as building design artificial intelligence model training data, building design data for a plurality of buildings;

enhancing the building design artificial intelligence model training data to include building performance specification data corresponding to obtained building design data;

training an artificial intelligence model using the building design artificial intelligence model training data to generate building design specifications based on building performance specifications and to translate building performance specifications into corresponding viable building performance specifications;

receiving building performance specifications for a building project, wherein each requested building performance specification corresponds to a respective performance specification parameter;

translating, using the artificial intelligence model and the building design artificial intelligence model training data, at least a first building performance specification into a corresponding first viable building performance specification parameter value;

providing the building performance specifications, including the corresponding first viable building performance specification parameter value, to the artificial intelligence model that is trained to generate building design specifications based on building performance specifications;

generating, by the artificial intelligence model, building designs for the building project that satisfy the building performance specifications; and

providing the building designs for the building project for evaluation and construction of the building project.

17 . The computer-readable storage media of claim 16 , wherein obtaining building design data comprising obtaining building design data for existing buildings.

18 . The computer-readable storage media of claim 16 , wherein obtaining building design data comprises generating synthetic data for synthetically-designed buildings.

19 . The computer-readable storage media of claim 18 , wherein generating synthetic data comprises generating the synthetic data based on a set of rules that includes rules for how buildings can be composed.

20 . The computer-readable storage media of claim 16 , wherein enhancing the building design artificial intelligence model training data comprises determining the building performance specifications for obtained building design data and associating determined performance specifications, in the building design artificial intelligence model training data, with corresponding building design information.

21 . The computer-implemented method of claim 1 , wherein the building performance specifications include at least a first building performance specification that requests a maximum or minimum value for a first performance specification parameter.

22 . The computer-implemented method of claim 21 , further comprising:

determining, by the artificial intelligence model, possible bounds for each respective performance specification parameter; and

determining, by the artificial intelligence model, a viable performance specification parameter value for each performance specification parameter based on corresponding possible bounds for the performance specification parameter.

23 . The computer-implemented method of claim 22 , wherein determining the possible bounds for the first performance specification parameter comprises determining an upper or lower possible bound for the first performance specification parameter.

24 . The computer-implemented method of claim 23 , wherein determining the viable performance specification parameter value for the first performance specification parameter comprises automatically determining the upper or lower possible bound of the first performance specification parameter as the viable performance specification parameter value for the first performance specification parameter.

25 . The computer-implemented method of claim 24 , wherein determining the upper or lower possible bound of the first performance specification parameter as the viable performance specification parameter value for the first performance specification parameter comprises:

providing, in response to receiving the building performance specifications, the upper or lower possible bound as a suggested parameter value for the first performance specification parameter;

receiving a confirmation of using the upper or lower possible bound as a parameter value for the first performance specification parameter; and

determining the upper possible or lower possible bound as the viable performance specification parameter value for the first performance specification parameter in response to the confirmation.

26 . The computer-implemented method of claim 23 , wherein determining the viable performance specification parameter value for the first performance specification parameter comprises:

providing, in response to receiving the building performance specifications, the upper or lower possible bound as a suggested parameter value for the first performance specification parameter;

receiving, as a modified parameter value, a modification of the suggested parameter value;

determining that the modified parameter value is within the possible bounds of the first performance specification parameter; and

determining the modified parameter value as the viable performance specification parameter value for the first performance specification parameter.

27 . The computer-implemented method of claim 22 , wherein the building performance specifications include at least a second building performance specification that requests an explicit value for a second performance specification parameter.

28 . The computer-implemented method of claim 27 , wherein determining the viable performance specification parameter value for the second performance specification parameter comprises:

determining that the explicit value is within the possible bounds of the second performance specification parameter; and

automatically selecting the explicit value as the viable performance specification parameter value for the second performance specification parameter in response to determining that the explicit value is within the possible bounds of the second performance specification parameter.

29 . The computer-implemented method of claim 27 , wherein determining the viable performance specification parameter value for the second performance specification parameter comprises:

determining that the explicit value is not within the possible bounds of the second performance specification parameter;

providing possible bounds information for the second performance specification parameter in response to receiving the building performance specifications;

receiving a new explicit value for the second performance specification parameter;

determining that the new explicit value is within the possible bounds of the second performance specification parameter; and

selecting the new explicit value as the viable performance specification parameter value for the second performance specification parameter in response to determining that the new explicit value is within the possible bounds of the second performance specification parameter.

30 . The computer-implemented method of claim 1 , wherein translating comprises determining, by the artificial intelligence model and using multiple iterations, different respective building specification parameter values for multiple different respective building specification parameters.

31 . The computer-implemented method of claim 1 , wherein the building performance specifications include different relative priorities of different building performance specification parameters.

32 . The computer-implemented method of claim 31 , wherein determining viable building performance specification parameter values for the different building performance specification parameters comprises determining viable performance specification parameter values for building performance specification parameters with higher relative priorities before determining viable building performance specification parameter values for building performance specification parameters with lower relative priorities.

33 . The computer-implemented method of claim 32 , wherein determining a viable building performance specification parameter value for a first building performance specification parameter comprises determining the viable building performance specification parameter value for the first building performance specification parameter based on training data for the first building performance specification parameter.

34 . The computer-implemented method of claim 33 , wherein determining the viable building performance specification parameter value for a second building performance specification parameter that has a lower importance value than the first building performance specification parameter comprises determining the viable building performance specification parameter value for the second building performance specification parameter based both on training data for the second building performance specification parameter and the viable building performance specification parameter value previously determined by the artificial intelligence model for the first building performance specification parameter.

35 . The computer-implemented method of claim 33 , wherein determining the viable building performance specification parameter value for the first building performance specification parameter comprises:

identifying constraints of the building project;

generating filtered training data by filtering the building design artificial intelligence model training data based on the constraints of the building project and the first building performance specification parameter; and

determining the viable building performance specification parameter value for the first building performance specification parameter based on a distribution of values for the first building performance specification parameter in the filtered training data.

36 . The computer-implemented method of claim 35 , further comprising:

determining, by the artificial intelligence model, possible bounds for the first building performance specification parameter based on the distribution of values for the first building performance specification parameter in the filtered training data; and

selecting, by the artificial intelligence model, the viable building performance specification parameter value for the first building performance specification parameter based on the possible bounds for the first building performance specification parameter.