Mining data for services

• US 9,497,314 B2
• Filed: 04/10/2006
• Issued: 11/15/2016
• Est. Priority Date: 04/10/2006
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Milstein, David, Wang, Kuansan, Criddle, Linda, Chu, Lon-Chan, Malueg, Michael D., Forbes, Scott C.
• Primary Examiner(s): KASSIM, KHALED M
• Application Number:
  US11/401,022
• Publication Number:
  US 20070237149A1
• Time in Patent Office: 3,872 Days
• Field of Search: 370351-356, 370/392, 707/1, 707/101, 707/3, 707/5, 704/235, 704/246, 379/265.02
• US Class Current: 1/1
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04L 63/306 intercepting packet switched data communications, e.g. Web, Internet or IMS communications
• CPC Class Codes: H04M 3/2281 Call monitoring, e.g. for law enforcement purposes; Call tracing; Detection or prevention of malicious calls
• CPC Class Codes: H04M 7/006 Networks other than PSTN/ISDN providing telephone service, e.g. Voice over Internet Protocol (VoIP) , including next generation networks with a packet-switched transport layer H04L65/00 takes precedence; aspects not specific to the type of network H04M3/00; special services in those networks H04M3/42

Abstract

Generally described, the present invention provides the ability to process digital voice conversations to identify data packets containing content of interest and to further process the identified data packets. More specifically, mining profiles may be developed identifying particular types of content that is to be mined and further identifying what is to be done when data packets containing such content is located. A system may search a digital voice conversation for the data packets containing the content and perform processing on the data packets once identified.

Claims

1. A method for mining data packets from a digital voice conversation comprising:

receiving, at a first client, a request from a second client to establish a digital voice conversation over a communication channel that is used to transmit and receive data packets comprising contextual data packets and conversational data packets;

wherein the conversational data packets are for conversation data and the contextual data packets are for data other than the conversation data;

selecting, by the first client, a mining profile for use in mining at least one of contextual data packets and conversational data packets of the digital voice conversation, wherein the mining profile identifies at least one type of content that is to be mined and processing to be performed on the mined content;

determining that a mining profile rule exists relating to the conversation;

modifying the selected mining profile according to the mining profile rule;

receiving, by the first client, a structured hierarchy defining an organization of the contextual data packets;

receiving, by the first client over the communication channel, one or more contextual data packets organized in a structure defined by the structured hierarchy and one or more conversational data packets;

during the digital voice conversation, determining, based in part on the at least one type of content identified in the mining profile, whether at least one of the received contextual data packets and conversational data packets are to be mined;

mining, by the first client, the determined data packets based on the selected mining profile and the structured hierarchy; and

processing the mined data packets based on the selected mining profile.

2. The method of claim 1, further comprising:

in response to a determination that the data packet includes content identified in to the mining profile, indicating that the data packet is a mined data packet.

3. The method of claim 1, wherein processing further comprises:

processing the data packet to obtain additional information relating to content of the data packet.

4. The method of claim 1, further comprising:

storing the data packet with the mining profile for post-processing.

5. The method of claim 4, further comprising:

identifying post-processing rules; and

storing the post-processing rules with the mining profile and the data packet for post-processing.

6. The method of claim 1, wherein the mining profile further defines how to process the content once it is mined.

7. The method of claim 1, wherein the mining profile specifies a type of processing to be performed on the data packet.

8. The method of claim 1, wherein selecting a mining profile includes selecting a plurality of mining profiles.

9. A computer-readable memory having computer executable components for processing mined data, comprising:

a mining profile component selecting a mining profile for use in mining at least one of contextual data packets and conversational data packets of a digital voice conversation, determining that a mining profile rule exists relating to the conversation, and modifying the selected mining profile according to the mining profile rule, wherein the mining profile identifies at least one type of content that is to be mined, processing to be performed on the mined content, and alteration information;

a structured hierarchy component selecting a structured hierarchy defining an organization of the contextual data packets;

a mined data packet management component determining, during the digital voice conversation and based in part on the at least one type of content identified in the mining profile, one or more contextual data packets and conversational data packets to be mined;

a mined data packet alteration component altering content of mined data packets based on alteration information included in the mining profile; and

a mined data packet processing component performing processing of mined data packets as identified in the mining profile.

10. The computer-readable memory of claim 9, wherein the mined data packet alteration component alters content of data packets based on rules applied to a mining profile.

11. The computer-readable memory of claim 10, wherein the rules are applied by a service provider.

12. The computer-readable memory of claim 9, wherein content may be altered by removing the data packet from a digital voice conversation, storing the data packet, replacing the content, or forwarding the data packet.

13. The computer-readable memory of claim 9, wherein the mined data packet processing component provides real-time information to an individual related to a content of the mined data packet.

14. The computer-readable memory of claim 9, wherein the processing of the mined data packet is done real-time.

15. The computer-readable memory of claim 9, further comprising:

a post-processing component for storing mined data packets with post-processing rules.

16. A system including:

at least one processor; and

a memory operatively coupled to the at least one processor and including instructions that, when executed by the at least one processor, cause the at least one processor to perform a method, the method comprising;

receiving, at a first client, a request from a second client to establish a digital voice conversation over a communication channel that is used to transmit and receive data packets comprising contextual data packets and conversational data packets;

wherein the conversational data packets are for conversation data and the contextual data packets are for data other than the conversation data;

selecting, by the first client, a mining profile for use in mining at least one of contextual data packets and conversational data packets of the digital voice conversation, wherein the mining profile identifies at least one type of content that is to be mined and processing to be performed on the mined content;

determining that a mining profile rule exists relating to the conversation;

modifying the selected mining profile according to the mining profile rule;

receiving, by the first client, a structured hierarchy defining an organization of the contextual data packets;

receiving, by the first client over the communication channel, one or more contextual data packets organized in a structure defined by the structured hierarchy and one or more conversational data packets;

during the digital voice conversation, determining, based in part on the at least one type of content identified in the mining profile, whether at least one of the received contextual data packets and conversational data packets are to be mined;

mining, by the first client, the determined data packets based on the selected mining profile; and

processing the mined data packets based on the selected mining profile.

17. The system of claim 16, wherein a third party performs processing of the mined data packets.

18. The system of claim 17, wherein the third party is requested to mine digital voice conversations for particular items of content.

19. The system of claim 16, wherein received data packets are identified for processing based on a header of the data packet.