Method and apparatus for predicting value of caching content items

• US 9,178,959 B2
• Filed: 07/02/2008
• Issued: 11/03/2015
• Est. Priority Date: 07/02/2008
• Status: Expired due to Fees

• Current Assignee: Alcatel-Lucent SA (Nokia Corporation)
• Original Assignee: Alcatel-Lucent SA (Nokia Corporation)
• Inventors: Segel, Jonathan
• Primary Examiner(s): Stevens, Robert
• Application Number:
  US12/167,225
• Publication Number:
  US 20100005046A1
• Time in Patent Office: 2,680 Days
• Field of Search: 707/694, 707/46, 706/46
• US Class Current: 1/1
• CPC Class Codes: H04L 67/56 Provisioning of proxy services store-and-forward switching systems in data switching networks H04L12/54
• CPC Class Codes: H04L 67/5681 Pre-fetching or pre-delivering data based on network characteristics

Abstract

The invention includes a method and apparatus for predicting value of caching content items. In one embodiment, a method for selecting ones of a plurality of content items to be cached includes, for each of the content items, determining a probability of use of the content item comprising a probability that the content item will be used if cached, determining a value of caching the content item, and computing a caching value estimate associated with the content item using the probability of use of the content item and the value of caching the content item. The content items to be cached may then be selected using the respective caching value estimates of the content items.

Claims

1. A method for selecting, from a set of content items, one or more content items to be cached, the method comprising:

determining, for each content item in the set of content items, a respective probability of use value for the content item that is indicative of a probability that the content item will be used if the content item is cached, wherein, for at least one of the content items in the set of content items, determining the probability of use value for the content item comprises;

determining predicted signaled factor information comprising information indicative of a probability that a set of signaled factors will be received;

determining joint probability information comprising a joint probability of a combination of receiving the set of signaled factors and the content item being used by a user; and

determining the probability of use value for the content item based on the predicted signaled factor information and the joint probability information;

determining, for each content item in the set of content items, a respective value of caching the content item;

computing, for each content item in the set of content items, a respective caching value estimate associated with the content item wherein the caching value estimate associated with the content item is computed based on the respective probability of use value for the content item and the respective value of caching the content item; and

selecting, from the set of content items based on the respective caching value estimates of the content items, one or more content items to be cached.

2. The method of claim 1, wherein the respective probability of use value for the content item comprises a posterior probability of use estimate that is determined using a Bayesian updating process or a directly observable probability of use estimate that is determined given a set of user signaled information.

3. The method of claim 1, wherein the respective probability of use value for the content item comprises a posterior probability of use estimate for the content item that is determined using a Bayesian updating process, wherein the posterior probability of use estimate for the content item is determined based on prior probability of use information comprising a prior probability of the content item being used in the absence of user signaled information, wherein the joint probability of the combination of receiving the set of signaled factors and the content item being used by the user comprises a joint probability of the set of signaled factors being received when the content item is being used by the user.

4. The method of claim 3, wherein the prior probability of the content item being used in the absence of user signaled information is determined based on at least one of a past content viewing history of the user, content preference information associated with the user, or information indicative of popularity of the content item with at least one other user.

5. The method of claim 1, wherein the respective probability of use value for the content item is a directly observable probability of use estimate for the content item that is determined given a set of user signaled information, wherein the joint probability of the combination of receiving the set of signaled factors and the content item being used by the user comprises a joint probability of the content item being used by the user when the set of signaled factors is received.

6. The method of claim 1, wherein the predicted signaled factor information comprises a predicted signaled factor probability for a predicted signaled factor, wherein the predicted signaled factor probability for the predicted signaled factor is determined by:

receiving previous signaled factors associated with the user, wherein the previous signaled factors comprise at least one user signaled factor entered by the user via at least one user device in the past; and

determining the predicted signaled factor probability for the predicted signaled factor based on the at least one user signaled factor.

7. The method of claim 6, wherein the predicted signaled factor comprises at least one of an audience factor indicative of one or more individuals expected to consume the content item, a genre factor, an available-time factor indicative of an available time to consume the content item, a factor indicative of a preferred content item length, a preferred content item mood factor, a popularity factor, a critical rating factor, a factor indicative of audience age, a factor for signaling potentially offensive content, or a factor indicative of a preferred tempo of the content item.

8. The method of claim 6, wherein the predicted signaled factor probability for the predicted signaled factor is determined as a function of at least one external factor.

9. The method of claim 8, wherein the at least one external factor comprises at least one of a time of day, a day of week, a day of year, or a specified holiday.

10. The method of claim 1, wherein the respective probability of use value for the content item is determined as a sum, over a plurality of combinations of values of signaled factors in the set of signaled factors, of a probability of use of the content item within that combination of values of signaled factors in the set of signaled factors multiplied by a probability of occurrence of that combination of values of signaled factors in the set of signaled factors.

11. The method of claim 1, wherein, for at least one content item in the set of content items, the respective caching value estimate associated with the content item is calculated as a time-weighted sum at multiple points in the future.

12. The method of claim 1, wherein, for at least one content item in the set of content items, determining the respective value of caching the content item comprises:

determining a benefit of caching the content item;

determining a cost of caching the content item; and

determining the respective value of caching the content item based on the benefit of caching the content item and the cost of caching the content item.

13. The method of claim 12, wherein the benefit of caching the content item is:

lowered based on a determination that the content item is already cached;

or

increased based on a determination that caching of the content item is likely to reduce network load during a peak usage period.

14. The method of claim 12, wherein the cost of caching the content item is dependent on at least one of a size of the content item, available space in a cache, or network resources that are consumed to retrieve the content item.

15. The method of claim 1, wherein, for at least one content item in the set of content items, the respective caching value estimate associated with the content item is computed based on a weighting factor.

16. The method of claim 15, wherein the weighting factor is dependent on at least one of a network loading factor, a network overloading cost factor, or a size of the content item.

17. The method of claim 1, wherein, for the at least one of the content items in the set of content items, the respective caching value estimate associated with the content item is computed as:

18. The method of claim 17, wherein prob(I_k,t) comprises a cumulative posterior probability determined using a Bayesian updating approach or a cumulative probability determined using a directly-observable approach;

wherein, when the prob(I_k,t) comprises the cumulative posterior probability determined using a Bayesian updating approach, the probability of use value prob(I_k,t) is computed as;

19. The method of claim 1, further comprising:

propagating the selected one or more content items toward a content cache adapted to cache the selected one or more content items.

20. The method of claim 19, wherein the cache is located at least one of:

on a user device of a user;

or

on a network device configured to serve the user and at least one additional user.

21. The method of claim 1, further comprising:

propagating the respective caching value estimates associated with the content items in the set of content items toward an element configured to select the one or more content items to be cached based on the respective caching value estimates associated with the content items in the set of content items.

22. An apparatus for selecting, from a set of content items, one or more content items to be cached, the apparatus comprising:

a processor and a memory communicatively connected to the processor, the processor configured to;

determine, for each content item in the set of content items, a respective probability of use value for the content item that is indicative of a probability that the content item will be used if the content item is cached, wherein, for at least one of the content items in the set of content items, to determine the probability of use value for the content item, the processor is configured to;

determine predicted signaled factor information comprising information indicative of a probability that a set of signaled factors will be received;

determine joint probability information comprising a joint probability of a combination of receiving the set of signaled factors and the content item being used by a user; and

determine the probability of use value for the content item based on the predicted signaled factor information and the joint probability information;

determine, for each content item in the set of content items, a respective value of caching the content item;

compute, for each content item in the set of content items, a respective caching value estimate associated with the content item wherein the caching value estimate associated with the content item is computed based on the respective probability of use value for the content item and the respective value of caching the content item; and

select, from the set of content items based on the respective caching value estimates of the content items, one or more content items to be cached.

23. A non-transitory computer-readable storage medium storing a software program which, when executed by a computer, causes the computer to perform a method for selecting, from a set of content items, one or more content items to be cached, the method comprising:

determining, for each content item in the set of content items, a respective probability of use value for the content item that is indicative of a probability that the content item will be used if the content item is cached, wherein, for at least one of the content items in the set of content items, determining the probability of use value for the content item comprises;

determining predicted signaled factor information comprising information indicative of a probability that a set of signaled factors will be received;

determining joint probability information comprising a joint probability of a combination of receiving the set of signaled factors and the content item being used by a user; and

determining the probability of use value for the content item based on the predicted signaled factor information and the joint probability information;

determining, for each content item in the set of content items, a respective value of caching the content item;

computing, for each content item in the set of content items, a respective caching value estimate associated with the content item wherein the caching value estimate associated with the content item is computed based on the respective probability of use value for the content item and the respective value of caching the content item; and

selecting, from the set of content items based on the respective caching value estimates of the content items, one or more content items to be cached.