Systems and methods for building an architecture knowledge graph

1 . A method for building and querying an architecture knowledge graph, comprising:

identifying, by a computer program, a plurality of evaluated architectures for an evaluated organization;

identifying, by the computer program, attributes for each of the plurality of evaluated architectures;

generating, by the computer program, an architectural knowledge graph comprising each of the plurality of evaluated architectures represented as architectural nodes, each of the attributes represented as attribute nodes, and connections between the architectural nodes and attribute nodes represented as edges;

determining, by the computer program and using an intent processing engine, an intended state for each of the plurality of evaluated architectures from documents in a document processing repository, wherein the intended state represents a designed functioning of the evaluated architecture;

representing, by the computer program, the intended state for each of the plurality of evaluated architectures as an intended state node having an intended state dimension in the architectural knowledge graph;

identifying, by the computer program, a functional state of each of the plurality of evaluated architectures that represents a functionality the evaluated architecture as actually functioning;

representing, by the computer program, the functional state as a functional node having a functional state dimension;

receiving, by the computer program, a natural language query for architecture information;

formatting, by the computer program, the natural language query into a query graph based on a shape of the architectural knowledge graph;

retrieving, by the computer program, a plurality of graph properties from the architectural knowledge graph based on the query graph;

formatting, by the computer program, the plurality of graph properties into a response; and

displaying the response with a confidence score through an interface.

2 . The method of claim 1 , wherein the response is displayed in a natural language format.

3 . The method of claim 1 , wherein the step of retrieving a plurality of graph properties from the architectural knowledge graph based on the query graph comprises:

matching a pattern of the query graph to a plurality of graph properties in the architecture knowledge graph, wherein the plurality of graph properties in the architecture knowledge graph have a pattern similar to the pattern of the query graph.

4 . The method of claim 3 , wherein results of the querying include the plurality of graph properties in the architecture knowledge graph that have a pattern similar to the pattern of the query graph.

5 . The method of claim 1 , further comprising:

receiving positive feedback from a submitter of the natural language query with respect to an accuracy of the response.

6 . The method of claim 5 , comprising:

raising the confidence score based on the positive feedback.

7 . The method of claim 6 , comprising:

training a machine learning model with the response.

8 . The method of claim 7 , wherein the machine learning model is a variant of a graph neural network model.

9 . A system comprising:

at least one server including a processor and a memory, wherein the at least one server is in operative communication with a technology infrastructure network of an evaluating organization, and wherein the at least one server is configured to:

identify a plurality of evaluated architectures for the evaluated organization;

identify attributes for each of the plurality of evaluated architectures;

generate an architectural knowledge graph comprising each of the plurality of evaluated architectures represented as architectural nodes, each of the attributes represented as attribute nodes, and connections between the architectural nodes and attribute nodes represented as edges;

determine, using an intent processing engine, an intended state for each of the plurality of evaluated architectures from documents in a document processing repository, wherein the intended state represents a designed functioning of the evaluated architecture;

represent the intended state for each of the plurality of evaluated architectures as an intended state node having an intended state dimension in the architectural knowledge graph;

identify a functionality of each of the plurality of evaluated architectures that represents the functionality the evaluated architecture as actually functioning;

represent the functionality as a functional node having a functional state dimension;

receive a natural language query for architecture information;

format the natural language query into a query graph based on a shape of the architectural knowledge graph;

retrieve, a plurality of graph properties from the architectural knowledge graph based on the query graph;

format the plurality of graph properties into a response; and

display the response with a confidence score through an interface.

10 . The system of claim 9 , wherein the response is displayed in a natural language format.

11 . The system of claim 9 , wherein the at least one server is configured to retrieve the plurality of graph properties from the architectural knowledge graph based on the query graph by:

matching a pattern of the query graph to a plurality of graph properties in the architecture knowledge graph, wherein the plurality of graph properties in the architecture knowledge graph have a pattern similar to the pattern of the query graph.

12 . The system of claim 11 , wherein results of the querying include the plurality of graph properties in the architecture knowledge graph that have a pattern similar to the pattern of the query graph.

13 . The system of claim 9 , wherein the at least one server is configured to:

receive positive feedback from a submitter of the natural language query with respect to an accuracy of the response.

14 . The system of claim 13 , wherein the at least one server is configured to:

raise the confidence score based on the positive feedback.

15 . The system of claim 14 , wherein the at least one server is configured to:

train a machine learning model with the response.

16 . A non-transitory computer readable storage medium, including instructions stored thereon for building and querying of an architecture knowledge graph, which when read and executed by one or more computers cause the one or more computers to perform steps comprising:

identifying a plurality of evaluated architectures for an evaluated organization;

identifying attributes for each of the plurality of evaluated architectures;

generating an architectural knowledge graph comprising each of the plurality of evaluated architectures represented as architectural nodes, each of the attributes represented as attribute nodes, and connections between the architectural nodes and attribute nodes represented as edges;

determining, using an intent processing engine, an intended state for each of the plurality of evaluated architectures from documents in a document processing repository, wherein the intended state represents a designed functioning of the evaluated architecture;

representing the intended state for each of the plurality of evaluated architectures as an intended state node having an intended state dimension in the architectural knowledge graph;

identifying a functional state of each of the plurality of evaluated architectures that represents a functionality the evaluated architecture as actually functioning;

representing the functional state as a functional node having a functional state dimension;

receiving a natural language query for architecture information;

formatting the natural language query into a query graph based on a shape of the architectural knowledge graph;

retrieving, a plurality of graph properties from the architectural knowledge graph based on the query graph;

formatting the plurality of graph properties into a response; and

displaying the response with a confidence score through an interface.