DEVICE AND METHOD FOR AUTOMATIC FILTER ADJUSTMENT

• US 20150169585A1
• Filed: 07/05/2013
• Published: 06/18/2015
• Est. Priority Date: 07/06/2012
• Status: Active Grant

• Current Assignee: Funke TV Guide GmbH
• Original Assignee: Funke Digital Tv Guide GmbH (Axel Springer SE)
• Inventors: Korst, Jan, Pronk, Serverius Petrus Paulus, Barbieri, Mauro
• Granted Patent: US 9,959,316 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: H04N 21/4662 characterized by learning algorithms
• CPC Class Codes: H04N 21/4668 for recommending content, e.g. movies
• CPC Class Codes: H04N 21/4826 using recommendation lists, e.g. of programs or channels sorted out according to their score

Abstract

A method and a device for adjusting filter parameters comprises a display, a physical user interface, a memory and a processing unit. The memory comprises a sorted list of items in an ordered manner, the order determined by their rank, and each item has at least one feature-value pair that represents a value of a feature of the item. The processing unit generates a graphical representation of the items in the list in an ordered manner on the display. The processing unit responds to the user interface so as to allow a user to re-order (rearrange) and/or drop items in the graphical representation of the list of items; it modifies the rank of the items in the list, and it determines a like-degree for at least some of the feature-value pairs.

Claims

1. A device for adjusting filter parameters, the device comprises or can be connected to

a display, a physical user interface and a memory,

the device further comprises a processing unit that is or can be operatively connected to the display, the physical user interface and the memory,

wherein the memory comprises

a sorted list of items comprising a plurality of items in an ordered manner wherein the order of the items is determined by their rank, and

wherein the processing unit is configured to generate a graphical representation of the items in the list in an ordered manner on the display,

wherein the processing unit is further configured to respond to the physical user interface so as to allow a user to rearrange and/or drop items in the graphical representation of the list of items to thus generate a re-ordered list,

wherein the processing unit is further configured to modify the rank of the items in the list according to the graphical representation after rearrangement in response to the physical user interface, and

wherein the processing unit is further configured to modify a relative rating history based on the re-ordered list and to generate from the modified relative rating history a modified set of filter parameters.

2. The device according to claim 1, wherein the processing unit is further configured to respond to the physical user interface so as to allow a user to qualify each item as belonging to one of a predetermined number of like-degree related clusters.

3. The device according to claim 1, wherein each item is characterized by at least one feature-value pair that represents a value of a feature of the item and wherein the processing unit is further configured to determine a like-degree indicating factor for at least some of the feature-value pairs characterizing the items in the re-ordered list so that a product of feature-value pair like-degree indicating factors for a particular item matches the rank of the item in the re-ordered list when compared to a product of feature-value pair like-degree indicating factors of other items in the reordered list.

4. The device according to claim 3, wherein the like-degree indicating factor is a skewing factor for a particular feature-value pair and wherein the product of the skewing factors of the feature-value pairs characterizing a specific item is the skewing factor of said item.

5. The device according to claim 4, wherein the processing unit is adapted to solve a set of linear inequalities Σ

<sub>i∈

F(x—

j)</sub>ρ

_i>

Σ

<sub>i∈

F(x—

(j+1))</sub>ρ

_i wherein ρ

_i is the logarithm log (r_i) of a skewing factor r_i of an item i and wherein the notation x_j is used to indicate x_j.

6. The device according to claim 1, wherein the memory comprises a plurality of ordered lists of items and wherein the processing unit is adapted to successively generate graphical representations of the items in each list in an ordered manner on the display, and

wherein the processing unit is further configured to respond to the physical user interface so as to allow a user to rearrange and/or drop items in the graphical representation of the lists of items and to modify the rank of the items in the lists according to the graphical representation after rearrangement in response to the physical user interface.

7. The device according to claim 3, wherein a plurality of items have at least a subset of feature-value pairs in common and wherein like-degree indicating factors are assigned to each item and to each feature-value pair such that a like-degree indicating factor of an item is defined by a product of the like-degree indicating factors of the feature-value pairs characterizing said item.

8. The device according to claim 7, wherein the processing unit is configured to calculate the like-degree indicating factors of the feature-value pairs from the rank of the items after rearrangement of the ordered list of items in response to inputs via the physical user interface.

9. The device according to claim 1, wherein the device is configured to apply a seed item and the processing unit is configured to generate the sorted list of items based on a degree of similarity between the seed item and further items stored in that memory.

10. The device according to claim 1, wherein the memory is configured as a database.

11. The device according to claim 1, wherein the device is configured to allow entering a separator in the sorted list between any pair of successive items, before the first, or after the last item and wherein the processing unit is configured to set a decision threshold t in response to the positioning of a separator between any pair of successive items, before the first, or after the last item,

12. A method for adjusting filter parameters, the method comprising the steps of:

providing a sorted list of items comprising a plurality of items in an ordered manner wherein the order of the items is determined by their rank,

generating a graphical representation of the items in the list in an ordered manner on the display,

responding to the physical user interface so as to allow a user to re-order (rearrange) and/or drop items in the graphical representation of the list of items,

modifying the rank of the items in the list according to the graphical representation after rearrangement in response to the physical user interface,

modifying a relative rating history based on the re-ordered list, and

generating from the modified relative rating history a modified set of filter parameters.

13. The method according to claim 12, wherein the method further comprises the step of determining a like-degree indicating factor for at least some of the feature-value pairs characterizing the items in the re-ordered list so that a product of feature-value pair like-degree indicating factors for a particular item matches the rank of the items in the re-ordered list when compared to a product of feature-value pair like-degree indicating factors of other items in the reordered list.

14. The method according to claim 12, wherein the method further comprises the steps of:

applying a seed item and

generating the sorted list of items based on a degree of similarity between the seed item and further items stored in that memory.

15. The method according to claim 12, wherein the method further comprises the step of:

generating a new sorted list of items based on the modified filter parameters.

16. The method according to claim 13, wherein the method further comprises the step of:

generating a new sorted list of items based on the determined like-degree indicating factors of the feature-value pairs characterizing the items.

17. The method according to claim 15, wherein the method further comprises the steps of:

generating a graphical representation of the items in the new sorted list of items in an ordered manner on the display,

responding to the physical user interface so as to allow a user to re-order and/or drop items in the graphical representation of the new sorted list of items,

modifying the rank of the items in the new sorted list according graphical representation after rearrangement in response to the physical user interface, and

modifying a relative rating history based on the re-ordered list and generating from the modified relative rating history a modified set of filter parameters and/or

determining a like-degree indicating factor for at least some of the feature-value pairs characterizing the items in the re-ordered new list so that a product of feature-value pair like-degree indicating factors for a particular item matches the rank of the items in the re-ordered list when compared to a product of feature-value pair like-degree indicating factors of other items in the reordered list.