Information sequence extraction and building apparatus e.g. for producing personalised music title sequences

• US 7,203,702 B2
• Filed: 12/14/2001
• Issued: 04/10/2007
• Est. Priority Date: 12/15/2000
• Status: Expired due to Term

• Current Assignee: Sony Europe (Amsterdam) BV (Sony Group Corp.)
• Original Assignee: Sony France SA (Sony Group Corp.)
• Inventors: Pachet, Franc
• Primary Examiner(s): LEROUX, ETIENNE PIERRE
• Application Number:
  US10/020,015
• Publication Number:
  US 20020078029A1
• Time in Patent Office: 1,943 Days
• Field of Search: 707/3, 707/10, 707/104.1, 707/1, 707/2, 707/9, 725/32, 725/86, 725/87, 386/95, 386/125, 386/126, 345/473, 345/719
• US Class Current: 1/1
• CPC Class Codes: G06F 16/40 of multimedia data, e.g. slideshows comprising image and additional audio data retrieval of still image data G06F16/50; retrieval of audio data G06F16/60; retrieval of video data G06F16/70
• CPC Class Codes: G06F 16/637 Administration of user profiles, e.g. generation, initialization, adaptation or distribution
• CPC Class Codes: G06F 16/639 using playlists
• CPC Class Codes: G06F 16/64 Browsing; Visualisation therefor generation of a list or set of audio data G06F16/638
• CPC Class Codes: G06F 16/68 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: H04H 20/28 Arrangements for simultaneous broadcast of plural pieces of information
• CPC Class Codes: H04H 60/06 Arrangements for scheduling broadcast services or broadcast-related services
• CPC Class Codes: H04H 60/27 Arrangements for recording or accumulating broadcast information or broadcast-related information
• CPC Class Codes: H04H 60/47 for recognising genres
• CPC Class Codes: H04H 60/65 for using the result on users' side
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing
• CPC Class Codes: Y10S 707/99948 Application of database or data structure, e.g. distributed, multimedia, or image

Abstract

This invention serves to provide an apparatus for storing at least one sequence of information formed from a succession of information items in which an artistic or rational link is considered to exist between at least some pairs of adjacent items in the succession. The apparatus comprises an input for receiving the sequence of information, and a storage unit for storing the information.

Further, a segmentation device is provided for segmenting the sequence of information into individually accessible segments, each corresponding to a respective information item, in response to segmentation data indicating end limits of the information items. The storage unit outputs the segments in a sequence corresponding to the succession of information items.

Claims

1. An apparatus for establishing and outputting a succession of music titles in which an artistic or rational link is reflected in said succession, comprising:

first input means for receiving a sequence comprising an audio data stream of music titles in which an initial artistic or rational link is considered to exist between at least some pairs of adjacent items;

segmentation means for extracting segmentation data indicating end limits of said music titles from a website associated to a source of said audio data stream, for receiving said segmentation data through second input means separate from the audio data stream, and for recovering music titles from said audio data stream in response to said segmentation data; and

means for storing said recovered music titles.

2. The apparatus according to claim 1, wherein said segmentation means being responsive to time information in said segmentation data indicating times of occurrence of said end limits of said music titles for cutting up said audio data stream automatically to extract said segments therefrom.

3. The apparatus according to claim 1, wherein said input means includes means for receiving said audio data from a radio station and sending a sequence of music titles in accordance with a music program.

4. The apparatus according to claim 1, further comprising:

identification means connectable to a source of identification data identifying information items in said sequence of information, said identification means extracting at least some of said identification data to form an identifier, and

combining means for combining with a given segment an identifier corresponding thereto,

said storage means further being arranged to store said identifier corresponding to said segment.

5. The apparatus according to claim 4, wherein said identifier includes data indicative of an attribute under which respective groups of said segments can be generically identified and classified.

6. The apparatus according to claim 5, wherein said attribute corresponds to at least one type of music under which a music title can be classified.

7. The apparatus according to claim 6, wherein said identifier includes artist data indicative of an artist associated with the corresponding music title, and said apparatus further comprises deriving means for deriving at least one said type of music based on said artist data.

8. The apparatus according to claim 1, further comprising similarity analyzing means for automatically analyzing similarity relations between stored segments in terms of their closeness in said sequence of stored segments.

9. The apparatus according to claim 1, wherein said producing means produces said similarity relations by producing, for each segment corresponding to an information item considered in a given stored sequence, a similarity relation representation expressing a distance between that information item and other stored information items.

10. The apparatus according to claim 9, wherein said similarity relation representation contains, for each said other information item, a closeness value determined between pairs formed by said information item considered and said other information item.

11. The apparatus according to claim 10, wherein said producing means is arranged to calculate said closeness value for said information item considered by attributing a first closeness value each time said other information item appears just before or just after in said sequence,

said first closeness value being cumulated over said sequence to yield a cumulated value indicating a closeness of said pairs of information items.

12. The apparatus according to claim 11, wherein said producing means is further arranged to attribute a second closeness value, smaller than said first closeness value, each time said other information item is separated from said information considered by m separating information items, where m is an upper bounded number,

said first and second closeness values being cumulated over said sequence to yield a cumulated value indicating the closeness of said pairs of information items.

13. The apparatus according to claim 12, wherein said number m of separating information items is equal to one.

14. The apparatus according to claim 1, wherein said apparatus further comprises a music program generating means for building a sequence of information items from said stored segments.

15. The apparatus according to claim 14, wherein said program generating means is capable of building said sequence of information items in response to user preferences expressed through user inputs.

16. The apparatus according to claim 14, wherein said program generating means is capable of building said sequence of information items in response to similarity relations between stored segments in terms of their closeness values in said sequence of stored segments, in which information items are concatenated by taking their closeness values into account.

17. The apparatus according to claim 15, wherein said program generating means is responsive to a user input expressing a like or dislike, associated to at least some information items in said succession of information items, to create a sequence of information items in which said disliked information items are removed and liked information items are emphasized.

18. The apparatus according to claims 16, wherein said program generating means is further responsive to said similarity relations to create a sequence of information items in which information items close to disliked information items are deemphasized and/or in which information items close to liked information items are emphasized.

19. The apparatus according to claim 14, wherein said program generating means is responsive to a selected attribute of said information items said selected attribute being entered through a corresponding user input, to create a sequence of information items containing at least a preponderance of information items falling under said selected attribute.

20. The apparatus according to claim 19, wherein said program generating means is arranged to create a sequence of information items by taking into account said selected attributes associated to said information items, and

wherein said program generating means is further responsive to a discovery parameter entered through a user input, said discovery parameter indicating a degree of closeness of said sequence to said selected attribute.

21. The apparatus according to claim 20, wherein said program generating means is further responsive to said similarity relations between the stored segments in terms of their closeness in said sequence of stored segments, such that said information items do not fall under said selected attribute and are entered in said created sequence when said information items have a predetermined degree of closeness, as determined by said similarity relations, with an adjacent information item of said sequence.

22. The apparatus according to claim 14, wherein said program generating means comprises means for labeling and storing said created sequences as objects which can be selectively exported outside said apparatus.

23. The apparatus according to claim 22, further comprising importing means for importing said created sequences.

24. The apparatus according to claim 22, wherein said apparatus is connected to a playback means for receiving said segments of a selected created sequence.

25. The apparatus according to claim 1, wherein said apparatus produces at least one preference, said preference being a user preference comprised of the succession of information items produced by taking into account feedback from said user, or a generic preference comprised of a sequence.

26. A method for establishing and outputting a succession of music titles in which an artistic or rational link is reflected in said succession, said method comprising the steps of:

receiving a sequence comprising an audio data stream of music titles in which an initial artistic or rational link is considered to exist between at least some pairs of adjacent items;

receiving from a website associated to a source of said audio data stream, segmentation data separate from the audio data stream, said segmentation data indicating end limits of said music titles;

recovering said music titles from said audio data stream in response to said segmentation data; and

storing said recovered music titles.

27. The method according to claim 26, wherein the received sequence of information is in a data stream form, said segmentation being performed in response to time information in said segmentation data indicating times of occurrence of said end limits of said information items for automatically dividing the stream in order to extract said segments.

28. The method according to claim 26, wherein said audio data is received from a radio station sending a sequence of music titles in accordance with a music program.

29. The method according to claim 26, further comprising the steps of:

identifying from a source of identification data, information items in said sequence of information, said identifying step extracting at least some of said identification data to form an identifier, and

combining with a given segment an identifier corresponding thereto,

said identifier being stored in accordance with said segment.

30. The method according to claim 29, wherein said identifier includes data indicative of an attribute under which respective groups of said segments can be generically identified and classified.

31. The method according to claim 30, wherein said attribute corresponds to at least one type of music under which a music title can be classified.

32. The method according to claim 31, wherein said identifier includes artist data indicative of an artist associated with the corresponding music title, and said method further comprises a deriving step for deriving at least one said type of music based on said artist data.

33. The method according to claim 26, further comprising the step of automatically analyzing similarity relations between stored segments in terms of their closeness in said sequence of stored segments.

34. The method according to claim 26, wherein said producing step produces said similarity relations by producing, for each segment corresponding to an information item considered in a given stored sequence, a similarity relation representation expressing a distance between that information item and other stored information items.

35. The method according to claim 34, wherein said similarity relation representation contains, for each said other information item, a closeness value determined between pairs formed by said information item considered and said other information item.

36. The method according to claim 34, wherein said producing step involves calculating said closeness value for said information item considered by attributing a first closeness value each time said other information item appears just before or just after in said sequence,

said first closeness value being cumulated over said sequence to yield a cumulated value indicating a closeness of said pairs of information items.

37. The method according to claim 36, wherein said producing step is further carried out to attribute a second closeness value, smaller than said first closeness value, each time said other information item is separated from said information considered by m separating information items, where m is an upper bounded number,

said first and second closeness values being cumulated over said sequence to yield a cumulated value indicating the closeness of said pairs of information items.

38. The method according to claim 26, further comprising the step of generating a music program by building a sequence of information items from said stored segments.

39. The method according to claim 38, wherein said program generating step involves building said sequence of information items in response to user preferences expressed through user inputs.

40. The method according to claim 38, wherein said program generating step involves building said sequence of information items in response to said similarity relations between stored segments in terms of their closeness values in said sequence of stored segments, in which information items are concatenated by taking their closeness values into account.

41. The method according to claim 39, wherein said program generating step is carried out by taking into account a user input expressing a like or dislike, associated to at least some information items in said succession of information items, to create a sequence of information items in which said disliked information items are removed and liked information items are emphasized.

42. The method according to claim 40, wherein said program generating step is further carried out by taking into account said similarity relations to create a sequence of information items in which information items close to disliked information items are de-emphasized and/or in which information items close to liked information items are emphasized.

43. The method according to claim 39, wherein said program generating step is carried out by taking into account a selected attribute of said information items, said selected attribute being entered through a corresponding user input, to create a sequence of information items containing at least a preponderance of information items falling under said selected attribute.

44. The method according to claim 43, wherein said program generating step is carried out by creating a sequence of information items and taking into account said selected attributes associated to said information items, and wherein said program generating step is further carried out by taking into account a discovery parameter entered through a user input, said discovery parameter indicating a degree of closeness of said sequence to said selected attribute.

45. The method according to claim 44, wherein said program generating step is further carried out by taking into account said similarity relations between the stored segments in terms of their closeness in said sequence of stored segments, such that said information items do not fall under said selected attribute and are entered in said created sequence when said information items have a predetermined degree of closeness, as determined by said similarity relations, with an adjacent information item of said sequence.

46. The method according to claim 39, wherein said program generating step involves labeling and storing said created sequences as objects which can be selectively exported.

47. The method according to claim 46, further comprising the step of importing said created sequences.