Semantic processing of customer communications
An electronic computing device includes a processing unit and system memory. The system memory includes instructions which, when executed by the processing unit, cause the electronic computing device to receive data associated with one or more customers of an institution. The data is received from one or more other electronic computing devices. The received data is analyzed to identify grammatical elements in the data. Relationships are derived between a plurality of the grammatical elements. At least one derived relationship is used to update a profile for a customer. At least one derived relationship is used to identify a customer for which a remedial action is warranted.
1. A system comprising:
a text translator;
a server;
a processing unit; and
system memory, the system memory including instructions which, when executed by the processing unit, cause the system to:
receive, at the text translator, a voice communication associated with a customer of an institution, the voice communication including voice data received from one or more electronic computing devices;
transcribe, using the text translator, the voice data into text data;
parse, using a natural language processor of the server, the text data into a Resource Description Framework (RDF) file;
convert, using the natural language processor, the RDF file into a Web Ontology Language (OWL) file;
derive, by the server, relationships from the OWL file;
identify, by the server and based on at least one of the relationships, the customer as an individual;
identify, by the server and based on at least one of the relationships and the OWL file, another individual associated with the customer;
capture, with a machine configured to crawl the web included on the server, semantically tagged information based on the OWL file, the semantically tagged information being related to the another individual, to provide contextual information for the communication, the contextual information not being available from the communication;
infer, by a predictive analysis engine included on the server and based on the contextual information, how an expense associated with a consumer household that includes the customer and the another individual is paid for; and
generate and display, by the server and using the OWL file, a visual representation of the relationships and the contextual information, the visual representation also including the consumer household.
2. The system of claim 1 , wherein the visual representation includes representations of an account balance and a time frame.
3. The system of claim 1 , wherein the instructions, when executed by the processing unit, cause the processing unit to use at least one of the relationships to predict future behavior of the customer.
4. The system of claim 1 , wherein the instructions, when executed by the processing unit, cause the processing unit to provide a link for viewing the visual representation.
5. The system of claim 1 , wherein the visual representation includes a two-dimensional graph.
6. The system of claim 1 , wherein the instructions, when executed by the processing unit, cause the processing unit to generate a recommendation for the customer.
7. A computer-implemented method, comprising:
receiving, by a text translator, a voice communication associated with a customer of an institution, the voice communication including voice data received from one or more electronic computing devices;
transcribing, using the text translator, the voice data into text data;
parsing, using a natural language processor of the server, the text data into a Resource Description Framework (RDF) file;
converting, using the natural language processor, the RDF file into a Web Ontology Language (OWL) file;
deriving, by a server, relationships from the OWL file;
identifying, by the server and based on at least one of the relationships, the customer as an individual;
identifying, by the server and based on at least one of the relationships and the OWL file, another individual associated with the customer;
capturing, with a machine configured to crawl the web included on the server, semantically tagged information based on the OWL file, the semantically tagged information being related to the another individual, to provide contextual information for the communication, the contextual information not being available from the communication;
inferring, by a predictive analysis engine included on the server and based on the contextual information, how an expense associated with a consumer household that includes the customer and the another individual is paid for; and
generating and displaying, by the server and using the OWL file, a visual representation of the relationships and the contextual information, the visual representation also including the consumer household.
8. The method of claim 7 , wherein the visual representation includes representations of an account balance and a time frame.
9. The method of claim 7 , further comprising:
using at least one of the relationships to predict future behavior of the customer.
10. The method of claim 7 , further comprising:
providing a link for viewing the visual representation.
11. The method of claim 7 , wherein the visual representation includes a two-dimensional graph.
12. The method of claim 7 , further comprising:
generating a recommendation for the customer.