Decision support system for data retrieval
Systems for use in data retrieval. A natural language processing module is used in conjunction with a classifier module to analyze and decompose a user query into its elements, and to determine a type of query. These modules are also used to determine the parameters for the query. The type of query and the parameters are then used to find a suitable function that creates a structured database query with the fields in the database query being populated using the parameters and query elements found by the NLP module. The completed structured database query is then used to retrieve relevant data records in response to the query. The retrieved records are then further processed and formatted as necessary to result in a suitable response to the query.
1. A system for retrieving data, the system comprising:
a non-transitory storage medium storing computer-readable instructions thereon; and
at least one processor operatively connected to the non-transitory storage medium, the at least one processor, upon executing the computer-readable instructions, being configured for:
receiving a natural language query from a user;
decomposing said natural language query into query elements using at least one natural language processing (NLP) model;
determining, using at least one classifier, query types and respective query parameters for said query based on said query elements and relationships between query elements for said query;
selecting at least one suitable function for said query from a set of functions based on said query types, said respective query parameters and the relationships between the query elements to formulate at least one database query;
retrieving data from at least one knowledge graph database operatively connected to the system, using said at least one database query;
processing said data retrieved from the at least one knowledge graph database based on the relationships between the query elements to thereby determine a response to said query; and
formatting said response into a formatted response to said natural language query from said user.
2. The system according to claim 1 , wherein said at least one NLP model comprises a NLP machine learning model.
3. The system according to claim 1 , wherein said at least one classifier comprises at least one trained classification machine learning model.
4. The system according to claim 1 , wherein said query types comprises at least two of: an identification query, an amount query, a strategy query, a counting query, a listing query, a grouping query, a time query, and a calculation query.
5. The system according to claim 4 , wherein each query type corresponds to at least one function.
6. The system according to claim 1 , wherein said at least one classifier is configured to classify said query based on said query types.
7. The system according to claim 1 , wherein the at least one classifier comprises a trained classification machine learning model.
8. The system according to claim 7 , wherein said at least one classifier is configured to determine at least one of: entities within the query, relationships between the entities and intent between the entities to be used as candidates by the suitable function to retrieve data from the at least one knowledge graph database.
9. A system for retrieving data, the system comprising:
a non-transitory storage medium storing computer-readable instructions thereon; and
at least one processor operatively connected to the non-transitory storage medium, the at least one processor, upon executing the computer-readable instructions, being configured for:
decomposing, using at least one natural language processing (NLP) model, a user query into query elements;
determining, using at least one classifier, parameters for said query based on said query elements and relationships between query elements for said query;
selecting at least one suitable function from a set of functions for said query based on said parameters for said query and the relationships between the query elements to formulate at least one database query;
retrieving data from at least one knowledge graph database operatively connected to the system using said at least one database query; and
processing retrieved data based on the relationships between the query elements to thereby determine a response to said query.
10. The system according to claim 9 , further comprising, prior to said retrieving the data from the at least one knowledge graph database: generating, using the at least one suitable function a structured database query based on said parameters.
11. The system according to claim 9 , further comprising:
determining, using the at least one classifier, respective query types based on said query elements; and wherein
said generating the structured database query is based on the query types.
12. The system according to claim 9 , wherein the at least one suitable function comprises a plurality of suitable functions each of a respective query type.
13. The system according to claim 9 , wherein said processing comprises at least one of: ordering said data, performing a logical operation on said data, performing a mathematical operation on said data.
14. The system according to claim 9 , wherein formatting said response into a formatted response to said natural language query from said user comprises at least one of: generating a graph based on the response, generating a list based on the response, and generating a table based on the response.
15. The system according to claim 9 , wherein the at least one classifier comprises a trained classification machine learning model.
16. The system according to claim 15 , wherein said at least one classifier is configured to determine at least one of: entities within the query, relationships between the entities and intent between the entities to be used as candidates by the suitable function to retrieve data from the at least one knowledge graph database.
17. A method for retrieving data, the method being executed by at least one processor, the method comprising:
receiving a natural language query from a user;
decomposing said natural language query into query elements using at least one natural language processing (NLP) model;
determining, using at least one classifier, query types and respective query parameters for said query based on said query elements and relationships between query elements for said query;
selecting at least one suitable function for said query from a set of functions based on said query types, said respective query parameters and the relationships between the query elements to formulate at least one database query;
retrieving data from at least one knowledge graph database operatively connected to the at least one processor, using said at least one database query;
processing said data retrieved from the at least one knowledge graph database based on the relationships between the query elements to thereby determine a response to said query; and
formatting said response into a formatted response to said natural language query from said user.
18. The method according to claim 17 , wherein the at least one NLP comprises a trained NLP machine learning model and the at least one classifier comprises a trained classification machine learning model.
19. The method according to claim 18 , wherein said query types comprises at least two of: an identification query, an amount query, a strategy query, a counting query, a listing query, a grouping query, a time query, and a calculation query.