Phone assisted ‘photographic memory’

• US 8,775,454 B2
• Filed: 07/29/2008
• Issued: 07/08/2014
• Est. Priority Date: 07/29/2008
• Status: Expired due to Fees

• Current Assignee: Mimzi, LLC
• Original Assignee: James L. Geer
• Inventors: Geer, James L.
• Primary Examiner(s): KUDDUS, DANIEL A
• Application Number:
  US12/181,956
• Publication Number:
  US 20100030738A1
• Time in Patent Office: 2,170 Days
• US Class Current: 707/758
• CPC Class Codes: G06F 16/24 Querying
• CPC Class Codes: G06F 16/433 using audio data
• CPC Class Codes: G06F 16/487 using geographical or spatial information, e.g. location
• CPC Class Codes: G06F 16/489 using time information
• CPC Class Codes: G06F 16/634 Query by example, e.g. query by humming
• CPC Class Codes: G06F 16/685 using automatically derived transcript of audio data, e.g. lyrics speech recognition G10L15/00
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04M 1/72457 according to geographic location

Abstract

A system and method for collecting data may include a data collection device to obtain the data from a user, an apparatus for obtaining metadata for each word of the data from the user, an apparatus for obtaining a searchable transcript of the data and a device to store the searchable transcript. The metadata may be date data, time data, name data or location data and the data collection device may include a speech recognition engine to translate speech into searchable words. The speech recognition engine may provide a confidence level corresponding to the translation of the speech into searchable words.

Claims

1. A mobile telephone communication system, comprising:

an input port configured to obtain voice data from at least one user, wherein the input port is configured to further communicate the voice data as part of a conversation through a mobile telephone communication network;

at least one memory configured to store the voice data, a plurality of searchable transcripts of voice data obtained during a respective plurality of communications, each searchable transcript comprising a plurality of words, data indicating a time offset of the plurality of words with respect to the obtained voice data, and a synopsis of the conversation, wherein the searchable transcript is derived from at least a portion of the voice data obtained by the input port which is not communicated as part of a telephone conversation through the mobile telephone communication system, a respective word of a respective searchable transcript being synchronized with the voice data corresponding to the respective word; and

a processor configured to;

associate searchable metadata with the voice data for each of the plurality of communications, the searchable metadata comprising at least a physical location of the user during the respective communication,

store the associated searchable metadata with the respective searchable transcript and synopsis of the conversation for each of the respective plurality of communications, in a manner searchable based on a content of the searchable transcript, a content of the synopsis, and the physical location of the user during a respective communication, and

associate targeted advertising for presentation to a user in dependence on both the physical location and the searchable transcript.

2. The system as in claim 1, wherein the metadata further comprises date data representing a date of a respective communication.

3. The system as in claim 1, wherein the metadata further comprises time data representing a time of a portion of the searchable transcript of a respective communication.

4. The system as in claim 1, wherein the metadata further comprises name data representing a name of a telephone communication counterparty of a respective communication.

5. The system as in claim 1, further comprising a speech recognition engine configured to translate speech into searchable words.

6. The system as in claim 5, wherein the speech recognition engine provides a confidence level corresponding to the translation of the speech into searchable words.

7. The system as in claim 5, wherein the speech recognition engine is configured to distinguish between a first user and a second user in order to provide a first searchable transcript for the first user and a second searchable transcript for the second user.

8. A method for collecting data, comprising the steps of:

obtaining voice data from a user communicating from a physical location using a mobile phone through a mobile telephone communication network as part of a telephone conversation during a communication, wherein the obtained voice data exceeds an amount communicated through the mobile telephone communication network as part of a telephone conversation;

storing the voice data, a searchable transcript of the voice data comprising at least a portion of the voice data which exceeds the amount communicated through the mobile telephone communication network, during each of a plurality of respective communications in a memory, each searchable transcript comprising a plurality of words, data indicating a time offset of the plurality of words with res s ect to the voice data and a synopsis of the telephone conversation, wherein a respective word of a respective searchable transcript is synchronized with the voice data corresponding to the respective word;

obtaining metadata for the voice data, the metadata comprising at least the physical location of the user during the communication;

associating the metadata and the synopsis of the conversation with a respective searchable transcript of the voice data;

searching the searchable transcript, using an automated database, wherein a search result is responsive to at least the metadata, the searchable transcript, and a content of the synopsis; and

associating targeted advertising to the user in dependence on both the physical location and the searchable transcript.

9. The method for collecting data as in claim 8, wherein the metadata further comprises date data representing a date of a respective communication.

10. The method for collecting data as in claim 8, wherein the metadata further comprises time data representing a time of a portion of the searchable transcript of a respective communication.

11. The method for collecting data as in claim 8, wherein the metadata further comprises name data representing a name of a telephone communication counterparty of a respective communication.

12. The method for collecting data as in claim 8, further comprising translating speech in the voice data into searchable words using a speech recognition engine.

13. The method for collecting data as in claim 12, wherein the speech recognition engine provides a confidence level corresponding to the translation of the speech into searchable words.

14. The method for collecting data as in claim 12, wherein the speech recognition engine distinguishes between the user at the physical location and a second user remote from the physical location, as parties to a conversation, in order to provide a first searchable transcript for the first user and a second searchable transcript for the second user.

15. A method, comprising the steps of:

providing a searchable database, containing a plurality of information records, acquired with at least a mobile phone device, representing a user input or image, and associating metadata describing at least a physical location of the mobile phone device at a time of acquisition of the respective information records and a synopsis of the information records, wherein the searchable database comprises at least voice data received by the mobile phone device as part of a telephone conversation which is not communicated as part of the telephone conversation and a time offset of a plurality of words in a searchable transcript of the telephone conversation, a respective word of the searchable transcript being synchronized with the voice data corresponding to the respective word;

analyzing the information using an automated processor to render the information searchable based on a user query based on content of the information records, the synopsis of the information records, and the metadata;

searching the database for information with respect to the query relating to a physical location;

generating an output responsive to the query representing at least one information record selected by the automated processor in dependence on at least the respective content of the information record and the respective metadata information of the information record comprising the physical location;

automatically associating a targeted advertisement with both the searchable information and the physical location.

16. The method according to claim 15, wherein the user input comprises speech, and said analyzing comprises performing a speech to text conversion to generate a searchable transcript, wherein said generating is performed based on at least a relationship between the query and the searchable transcript.