Description:AS FILED PDF DOCUMENTS , Claims:AS FILED PDF DOCUMENTS

I\WE CLAIM:
1. A method for managing recaching of pages, the method comprising:
extracting (304), by a processor (114), a set of attributes associated with a page;
5 generating (306), by the processor (114), a set of first scores and a second score, wherein
each of the set of first scores is generated based on an associated subset of the set of attributes and
the second score is generated based on a set of network parameters; and
determining (308), by the processor (114) using a Machine Learning (ML) model (118), a
recaching action for the page, based on the set of first scores and the second score.
10
2. The method as claimed in claim 1, further comprising detecting (302) occurrence of a trigger
event, wherein the set of attributes are extracted in response to the detection of occurrence of the
trigger event, and wherein the trigger event comprises a modification in the page, and wherein the
modification comprises content alteration in the page, structure modification in the page, or
15 updating of metadata associated with the page.
3. The method as claimed in claim 1, wherein the set of attributes comprises at least one of:
a periodically recorded frequency of modification for the page over a time period;
a volume of traffic associated with the page over a plurality of time periods;
20 a plurality of traffic sources associated with the page;
a plurality of access patterns associated with the page; and
data associated with users and devices accessing the page.
4. The method as claimed in claim 1, wherein the set of first scores comprises a page volatility
25 score generated based on a first subset selected of the set of attributes, and wherein the page
volatility score is representative of frequency of modifications associated with the page over a time
period, and wherein the set of first scores comprises a page priority score generated based on a
second subset of the set of attributes, and wherein the page priority score is representative of
weighted average of attributes in the second subset.
5. The method as claimed in claim 1, further comprising determining a time required to recache
the page, based on a plurality of pre-recorded values of the set of network parameters, wherein the
second score comprises a recaching execution score representative of the time required to recache
5 the page.
6. The method as claimed in claim 1, further comprising training the ML model (118), wherein the
training comprises:
selecting (402) a training dataset of pages, wherein a first reaching pattern for each of the
10 training data set of pages is predetermined by a user based on the associated set of first scores and
the second score;
determining (404), by the ML model (118), a second recaching pattern for each of the
training dataset of pages, based on the associated set of first scores and the second score;
comparing (406), for each of the training dataset of pages, the second recaching pattern
15 with the first recaching pattern;
determining (408) a degree of accuracy of the ML model (118) based on the comparing;
and
performing (410) reinforcement learning on the ML model (118), based on the degree of
accuracy determined for the ML model (118).
20
7. The method of claim 1, wherein determining (308) the recaching action comprises determining
(310), by the ML model (118), a cumulative score for the page, and wherein the recaching action
comprises one of:
recaching the page when the cumulative score is above a first predefined threshold;
25 scheduling recaching of the page at a predetermined time, when the cumulative score is
less than equal to the first predefined threshold and above a second predefined threshold; and
invalidating of an existing cache page when the cumulative score is less than equal to the
second predefined threshold.
8. The method of claim 7, wherein the ML model determines (702) a cumulative score for each of
a plurality of pages, wherein the plurality of pages comprises the page.
5 9. The method of claim 8, further comprising:
determining (704) a sequence of transmitting the recaching action determined for each of
the plurality of pages, based on the cumulative score associated with each of the plurality of pages;
and
transmitting (706) the recaching action determined for each of the plurality of pages in
10 accordance with the determined sequence.
10. A system for managing recaching of pages, the system (100) comprising:
a processer (114); and
a memory (116) communicatively coupled to the processer (114), wherein the memory
15 (116) stores processor-executable instructions, which, on execution, causes the processer (114) to:
extract (304) a set of attributes associated with a page;
generate (306) a set of first scores and a second score, wherein each of the set of
first scores is generated based on an associated subset of the set of attributes and the second
score is generated based on a set of network parameters; and
20 determine (308) a recaching action for the page, based on the set of first scores and
the second score using a Machine Learning (ML) model.