Method and system for hybrid entity recognition

1. A computer-implemented process, comprising:

receiving an input sentence;

preprocessing the input sentence to generate a cleaned input sentence;

tagging parts of speech of the cleaned input sentence;

identifying first level entities in the cleaned input sentence;

converting and translating the cleaned input sentence into numeric vectors based on identifying the first level entities, wherein one of the numeric vectors includes at least a number of occurrences of a part of speech in the cleaned input sentence;

creating a first training set comprising the numeric vectors and the tagged parts of speech;

training a first machine learning model using the first training set to identify basic entities;

creating a second training set based on the tagged parts of speech and the basic entities;

training a second machine learning model using the second training set; and

extracting composite entities from the cleaned input sentence based on the second machine learning model and using the numeric vectors, wherein one of the composite entities includes at least a first level entity with a linguistic pattern.

2. The computer-implemented process of claim 1 , wherein the first level entities include one or more of Company, Name, Currency, City, Social Security Number, State, E-Mail Address, Product, Contact, and Postal Index Number (Pin) Code.

3. The computer-implemented process of claim 1 , wherein the composite entities include one or more of To Date, From Date, Promo Amount, and Payment Account.

4. The computer-implemented process of claim 3 , wherein the composite entities are extracted from the cleaned input sentence using a memory based linguistic pattern recognizer.

5. The computer-implemented process of claim 1 , wherein extracting the composite entities from the cleaned input sentence uses one or more of machine learning, memory based learning, computational linguistics and custom rules.

6. The computer-implemented process of claim 1 , wherein the operations further comprise identifying indirect entities addressed by pronouns based on context of the cleaned input sentence.

7. The computer-implemented process of claim 1 , wherein the operations further comprise learning linguistic patterns and storing one or more of the linguistic patterns, information of the first level entities, keywords, and relative proximity information of one of the keywords to one of the basic entities.

8. A system, comprising:

a preprocessor that receives an input sentence and processes the input sentence to generate a cleaned input sentence;

a POS tagger that tags parts of speech of the cleaned input sentence;

a rule based entity recognizer that identifies first level entities in the cleaned input sentence;

a vectorizer that converts and translates the cleaned input sentence into numeric vectors based on identifying the first level entities, wherein one of the numeric vectors includes at least a number of occurrences of a part of speech in the cleaned input sentence;

a machine learning based entity recognizer that creates a first training set comprising the numeric vectors and the tagged parts of speech and trains a first machine learning model using the first training set to identify basic entities; and

a memory based entity recognizer that creates a second training set based on the tagged parts of speech and the basic entities, trains a second machine learning model using the second training set, and extracts composite entities from the cleaned input sentence based on the second machine learning model and using the numeric vectors, wherein one of the composite entities includes at least a first level entity with a linguistic pattern.

9. The system of claim 8 , wherein the first level entities include one or more of Company, Name, Currency, City, Social Security Number, State, E-Mail Address, Product, Contact, and Postal Index Number (Pin) Code.

10. The system of claim 8 , wherein the composite entities include one or more of To Date, From Date, Credit Amount, Debit Amount, Promo Amount, Payment Account, From address, To address, Sender's Address, and Receiver's Address.

11. The system of claim 10 , wherein the composite entities are extracted from the cleaned input sentence using a memory based linguistic pattern recognizer.

12. The system of claim 8 , wherein extracting the composite entities from the cleaned input sentence uses one or more of machine learning, memory based learning, computational linguistics and custom rules.

13. The system of claim 12 , further comprising a context engine that identifies indirect entities addressed by pronouns based on context of the cleaned input sentence.

14. The system of claim 8 , wherein the memory based entity recognizer learns linguistic patterns and stores one or more of the linguistic patterns, information of the first level entities, keywords, and relative proximity information of one of the keywords to one of the first level entities.

15. The system of claim 8 , wherein identifying the basic entities is also based on reconverting a vector into text representing identification of the basic entities.

16. The system of claim 8 , further comprising a regular expression based entity recognizer that communicates with the rule based entity recognizer to identify the first level entities based on word structures and linguistic rules.

17. The system of claim 8 , further comprising an artificial intelligence system.

18. The system of claim 8 , further comprising data sources including one or more of corpus data, application data, customer relationship management (CRM) data, or peer-to-peer (P2P) systems data.

19. The system of claim 8 , further comprising a security layer that provides secure sockets layer (SSL) security.

20. The system of claim 8 , further comprising a business layer that provides domain specific knowledge used for identifying the basic entities and composite entities.