FIELD: computer engineering.
SUBSTANCE: result is achieved due to the fact that during the training phase of the ranking system, a plurality of data sets on previous user interactions with interfaces are obtained; for each data set, the last viewed content element in the interface is determined; determining a score for content items with which the user interacted; determining a loss score for content items with a lower rank than the last viewed content item; then, in the phase of using the ranking system, a set of content items is received; for each content element from the set of content elements, predicted relevance scores are determined; ranking positions of each content element from the set of content elements are determined based on predicted relevance scores.
EFFECT: high accuracy of identifying relevant content elements.
17 cl, 6 dwg
Title | Year | Author | Number |
---|---|---|---|
METHOD AND SYSTEM FOR DETERMINATION OF RANKED POSITIONS OF ELEMENTS BY RANKING SYSTEM | 2020 |
|
RU2781621C2 |
METHOD AND SYSTEM OF RANKING OF A VARIETY OF DOCUMENTS ON THE PAGE OF SEARCH RESULTS | 2017 |
|
RU2677380C2 |
METHOD AND SYSTEM FOR RANKING DIGITAL OBJECTS BASED ON TARGET CHARACTERISTIC RELATED TO THEM | 2019 |
|
RU2757174C2 |
METHOD AND SERVER FOR RANKING DIGITAL DOCUMENTS IN RESPONSE TO REQUEST | 2020 |
|
RU2818279C2 |
METHOD AND SERVER FOR TRAINING MACHINE LEARNING ALGORITHM IN OBJECT RANKING | 2020 |
|
RU2782502C1 |
METHOD AND SYSTEM FOR DETERMINING RANK POSITIONS OF NON-NATIVE ELEMENTS USING RANKING SYSTEM | 2017 |
|
RU2689812C2 |
METHOD AND SYSTEM OF SEARCH QUERY PROCESSING | 2015 |
|
RU2640639C2 |
METHOD AND SERVER FOR PRESENTING RECOMMENDED CONTENT ITEM TO USER | 2017 |
|
RU2699574C2 |
METHOD AND SERVER FOR GENERATING META-ATTRIBUTE FOR RANGING DOCUMENTS | 2018 |
|
RU2721159C1 |
METHOD AND SYSTEM OF SELECTION FOR RANKING SEARCH RESULTS USING MACHINE LEARNING ALGORITHM | 2018 |
|
RU2731658C2 |
Authors
Dates
2024-12-05—Published
2021-04-09—Filed