Method for selecting valid variants in search and recommendation systems (variants)
Selecting and ranking valid variants in search and recommendation systems selects and ranks variants with accuracy and speed. Criteria for evaluating the relevance of a variant to the search request are generated. A set of procedures for the selection and ranking of variants and a sequence for performing said procedures for the selection of variants evaluated as the most valid are established. An evaluation of each variant is based on relevance to search request criteria. The variants are then ranked by assigning a rank to each variant based on the condition of correspondence to the greatest number of criteria in decreasing order. Then the variants are selected and ranked in at least two stages using the superposition method, and the variants are selected, ranked and excluded until all of the established selection procedures have been used and the selected group of variants is evaluated as being the most valid.
1. A computer-implemented method for reducing computational complexity of selecting and ranking options in a search query of a search engine on the Internet and for enhancing accuracy of results presented to an end user in a user-readable format, the method comprising:
ranking relevance values of the options according to selected evaluation criteria;
selecting a desired number of remaining options in the search query based on a duration of a time slot allocated for executing the search query;
selecting (i) ranking rules including at least one threshold rule and the Borda rule or the Pareto set rule, and (ii) sequences of applying the ranking rules to the options;
reducing computational complexity by applying in sequential stages the ranking rules to the search query and at each of the stages eliminating the options having lowest of the relevance values until the desired number of the remaining options is achieved, wherein this step can be performed on a server and/or on a computer of the end user; and
presenting the results of eliminating the options to the end user of the search engine in the user-readable format, wherein the results can be stored in a RAM of the computer or on a computer-readable media; wherein:
the ranking rules having a linear computational complexity O(n) are applied in a first portion of the stages; and
the ranking rules having not less than quadratic O(n 2 ) computational complexity are applied after completion of the first portion of the stages.
2. The method of claim 1 , wherein applying the first portion of the stages includes re-ranking of the relevance values.
3. The method of claim 1 , wherein applying the second portion of the stages includes re-ranking of the relevance values.
4. The method of claim 1 , further comprising:
selecting the desired number of the remaining options based on computational resources of the search engine.
5. A computer-implemented method for reducing computational complexity of selecting and ranking options in a search query of a search engine on the Internet and for enhancing accuracy of results presented to an end user in a user-readable format, the method comprising:
forming evaluation criteria of relevance of the options to the search query;
selecting (i) ranking rules including at least one threshold rule, and (ii) sequences of applying the ranking rules to the options;
selecting a desired number of remaining options in the search query based on computational resources of the search engine;
ranking relevance values of the options according to the evaluation criteria;
reducing computational complexity by applying in sequential stages the ranking rules to the search query and at each of the stages eliminating the options having lowest of the relevance values until the desired number of the remaining options is achieved, wherein this step can be performed on a server and/or on a computer of the end user; and
presenting the results of eliminating the options to the end user of the search engine in the user-readable format, wherein the results can be stored in a RAM of the computer or on a computer-readable media; wherein
the ranking rules having a linear computational complexity O(n) are applied in a first portion of the stages; and
the ranking rules having not less than quadratic O(n 2 ) computational complexity are applied after completion of the first portion of the stages.
6. The method of claim 5 , wherein applying the first portion of the stages includes re-ranking of the relevance values.
7. The method of claim 5 , wherein applying the second portion of the stages includes re-ranking of the relevance values.
8. The method of claim 5 , further comprising:
selecting the desired number of the remaining options based on a duration of a time slot allocated for executing the search query.
9. The method of claim 5 , wherein the ranking rules include the plurality rule, the Borda rule, or the Pareto set rule.