Document content search index
A system, method, and computer program product are configured to extract key value pair (KVP) data from one or more documents; obtain a content index for the one or more documents; and enhance the content index with the KVP data to provide a KVP content index.
1. A computer-implemented method, comprising
extracting, by a processor set, key value pair (KVP) data from one or more documents by utilizing a machine learning model that is trained by identifying whether words within the one or more documents are a key or a value by performing key normalization by analyzing the words of the one or more documents to determine that the key is one of a mail to, an email, an email address, send email to, contact, and a company email and determine that the value is in a predetermined vicinity of the key;
matching the key and the key value to form the KVP data;
obtaining, by the processor set, a content index for the one or more documents; and
enhancing, by the processor set, the content index with the KVP data to provide a KVP content index.
2. The computer-implemented method of claim 1 , further comprises:
determining a document type for the one or more documents.
3. The computer-implemented method of claim 2 , wherein the document type comprises one or more document type selected from the group consisting of identification card, a driving license, invoice, contract, business card, mailing label, letter, and purchase order, and the enhancing the context index with the KVP data comprises adding an enhancement to each file node of the context index to provide the KVP context index.
4. The computer-implemented method of claim 2 , wherein the determining is accomplished by the machine learning model which is further trained by analyzing the one or more documents, the layout of the one or more documents, and the text content of the one or more documents, and the enhancement comprises a phrase in supplement of a word.
5. The computer-implemented method of claim 1 , wherein the extracting involves object detection or key normalization.
6. The computer-implemented method of claim 1 , wherein the KVP data comprises one or more data selected from the group consisting of invoice number, date, address, amount, terms, and telephone number.
7. The computer-implemented method of claim 1 , wherein the obtaining comprises retrieving the content index from a database.
8. The computer-implemented method of claim 1 , wherein the obtaining comprises analyzing the one or more documents and generating the content index.
9. The computer-implemented method of claim 1 , wherein the enhancing comprises adding a phase and tags to a word of the content index.
10. The computer-implemented method of claim 9 , wherein the tags comprise a role of the word or phrase, a type of data of the word or phrase, and a reference of the word or phrase.
11. The computer-implemented method of claim 10 , wherein the role indicates whether the word or phrase is the key or the value.
12. The computer-implemented method of claim 10 , wherein the type of data indicates whether the word or phrase comprises one or more word or phrase selected from the group consisting of a string, an integer, a date, a time, a currency, and an address.
13. The computer-implemented method of claim 10 , wherein the reference indicates the value associated with the phrase or word or the key associated with the word or phrase.
14. A computer program product comprising one or more computer readable storage media having program instructions collectively stored on the one or more computer readable storage media, the program instructions executable to:
extract key value pair (KVP) data from one or more documents by utilizing a machine learning model that is trained by identifying whether words within the one or more documents are a key or a value by performing key normalization by analyzing the words of the one or more documents to determine that the key is one of a mail to, an email, an email address, send email to, contact, and a company email and determine that the value is in a predetermined vicinity of the key;
match the key and the value to form the KVP data;
obtain a content index for the one or more documents; and
enhance the content index with the KVP data to provide a KVP content index.
15. The computer program product of claim 14 , wherein the program instructions further executable to:
determine a document type for the one or more documents.
16. The computer program product of claim 15 , wherein the determining is performed by the machine learning model, and the enhancing the context index with the KVP data comprises adding an enhancement to each file node of the context index to provide the KVP context index.
17. The computer program product of claim 14 , wherein the KVP data comprises one or more data selected from the group consisting of invoice number, date, address, amount, terms, and telephone number, and the enhancement comprises a phrase in supplement of a word.
18. A system comprising a processor set, one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions executable to:
extract key value pair (KVP) data from one or more documents by utilizing a machine learning model that is trained by identifying whether words within the one or more documents are a key or a value by performing key normalization by analyzing the words of the one or more documents to determine that the key is one of a mail to, an email, an email address, send email to, contact, and a company email and determine that the value is in a predetermined vicinity of the key;
match the key and the value to form the KVP data;
obtain a content index for the one or more documents; and
enhance the content index with the KVP data to provide a KVP content index.
19. The system of claim 18 , wherein the program instructions are further executable to:
determine a document type for the one or more documents
wherein the enhancing the context index with the KVP data comprises adding an enhancement to each file node of the context index to provide the KVP context index.
20. The system of claim 19 , wherein the enhancement comprises a phrase in supplement of a word.