Natural language processing integrated with database and data storage management
The disclosed technology can receive a voice query or text query in a natural language and translate it from natural language to a native database management language to respond to the query. For example, a human can ask his or her computer to “show large emails from December 2016”, and a data agent on computer can receive the voice request, convert audio associated with the voice to words in natural language, convert natural language into a SQL query, and convert the SQL query into a database management query. The data agent is trained with a corpus of technical documents and rules to determine the intent or keywords for answering the query. In some implementations, the disclosed technology can also include a chatbot and/or administrative assistant to enable a human to interface with a database management software using voice or text.
1. A computer-implemented method to communicate with an information management system, wherein the information management system comprises a translator database, an action database, and a storage manager, the method comprising:
receiving an audio command from a user, wherein the audio command is associated with a storage operation in the information management system;
translating the audio command to natural language text by the storage manager, wherein translation of the audio command to natural language text is at least partially executed with a natural language tool kit, and
wherein the natural language tool kit has a modified vocabulary based at least partially on a technical document for storage operations in the information management system;
translating the natural language text to a domain language command by the storage manager;
translating the domain language command to a database software command using the translator database;
accessing by the storage manager the action database to obtain actions and parameters to execute the storage operation in the information management system; and
transmitting an audio response to the user confirming execution of the storage operation.
2. The computer-implemented method of claim 1 , wherein translating the natural language text to the domain language command includes determining an intent of the user's audio command at least partially based on the action database.
3. The computer-implemented method of claim 1 , wherein translating the audio command into natural language text is at least partially based on a corpus for the information management system, and wherein the user's audio command relates to a past or current data storage operation for one or more of: archiving, backing up, and restoring data in the information management system.
4. The computer-implemented method of claim 1 , wherein the domain language command is Structured Query Language (SQL).
5. The computer-implemented method of claim 1 , wherein the database software command comprises one of: DB2, MySQL, Oracle, PostgreSQL or SQLite command.
6. The computer-implemented method of claim 1 , wherein the modified vocabulary is modified using machine learning algorithms trained on historical data regarding tasks performed in the information management system.
7. The computer-implemented method of claim 1 further comprising automatically connecting the user to a help desk technician upon the user's request to be connected to a help desk.
8. A non-transitory computer-readable medium storing instructions that, when executed by a computing system, cause the computing system to communicate with an information management system, wherein the information management system comprises a translator database, an action database, and a storage manager, and wherein the communication comprises:
establishing a connection with a voice-recognition device based on a user's audio command;
transmitting instructions by the storage manager to the voice-recognition device to install a voice data agent, wherein the voice data agent causes the voice-recognition device to install a modified vocabulary for storage operations in the information management system;
receiving an audio query wherein the audio query is a query associated with a storage operation in the information management system;
determining an intent of the audio query based on executing a query operation with a representational state transfer (REST) application-specific interface (API) of the voice-recognition device; and
translating the audio query to natural language text by the storage manager, wherein translation of the audio query to natural language text is at least partially executed with a natural language tool kit, and
wherein the natural language tool kit has the modified vocabulary based at least partially on a technical document for storage operations in the information management system;
translating the natural language text to a domain language command by the storage manager;
translating the domain language command to a database software query using the translator database;
transmitting a response to the user's audio command.
9. The non-transitory computer-readable medium of claim 8 , wherein the voice-recognition device is a mobile device.
10. The non-transitory computer-readable medium of claim 8 , wherein the modified vocabulary is modified using machine learning algorithms trained on historical data regarding tasks performed in the information management system.
11. The non-transitory computer-readable medium of claim 8 , wherein the modified vocabulary is at least partially provided by the user.
12. The non-transitory computer-readable medium of claim 8 , the operations further comprising automatically connecting the user to a help desk technician upon the user's request to be connected to a help desk.
13. The non-transitory computer-readable medium of claim 12 , wherein the help desk technician is connected to the user via one or more of: a graphical user interface, a telephone, and video conference.
14. The non-transitory computer-readable storage medium of claim 8 , further comprising requesting the user to provide additional parameters missing from the audio query after the step of receiving an audio query from the user.