FIELD: computer technology.
SUBSTANCE: set of digital objects is selected based on a request from a pool of digital objects, which is relevant to the request taking into account a target characteristic of digital objects and can be ranked according to their target characteristics; a filtering request is received from an electronic device for a rearranged set of digital objects from the set of digital objects, while the filtering request is based on an additional characteristic other than the target characteristic; digital objects to be included in the rearranged set of digital objects are selected by determining for a digital object from the set of digital objects the corresponding object parameter indicating the probability that the inclusion of this digital object in the rearranged set of digital objects will increase a quality metric of the rearranged set of digital objects, taking into account the target characteristic of digital objects; digital objects are selected based on corresponding object parameters; and the rearranged set of digital objects is ranked based on corresponding values of the additional characteristic to form a rearranged set of digital objects containing selected digital objects ranked according to the additional characteristic.
EFFECT: technical result is an increase in the accuracy of ranking digital objects based on the target characteristic related to them.
20 cl, 8 dwg
Title | Year | Author | Number |
---|---|---|---|
METHOD AND SERVER FOR TRAINING MACHINE LEARNING ALGORITHM IN OBJECT RANKING | 2020 |
|
RU2782502C1 |
METHOD AND SERVER FOR RANKING DIGITAL DOCUMENTS IN RESPONSE TO REQUEST | 2020 |
|
RU2818279C2 |
SEARCH INDEX CONSTRUCTION METHOD AND SYSTEM USING MACHINE LEARNING ALGORITHM | 2018 |
|
RU2720954C1 |
METHOD AND SERVER FOR GENERATING META-ATTRIBUTE FOR RANGING DOCUMENTS | 2018 |
|
RU2721159C1 |
METHOD AND SYSTEM OF RANKING OF A VARIETY OF DOCUMENTS ON THE PAGE OF SEARCH RESULTS | 2017 |
|
RU2677380C2 |
TRAINING METHOD OF RATING MODULE USING THE TRAINING SELECTION WITH THE INTERFERENCE LABELS | 2016 |
|
RU2632143C1 |
METHOD AND SYSTEM FOR GENERATING FEATURE FOR RANGING DOCUMENT | 2018 |
|
RU2733481C2 |
METHODS AND SERVERS FOR DETERMINING METRIC-DEPENDENT THRESHOLDS USED WITH MULTIPLE NESTED METRICS FOR BINARY CLASSIFICATION OF A DIGITAL OBJECT | 2020 |
|
RU2795202C2 |
METHOD AND SYSTEM FOR DETERMINATION OF RANKED POSITIONS OF ELEMENTS BY RANKING SYSTEM | 2020 |
|
RU2781621C2 |
SYSTEM AND METHOD FOR FORMATION OF TRAINING SET FOR MACHINE LEARNING ALGORITHM | 2020 |
|
RU2790033C2 |
Authors
Dates
2021-10-11—Published
2019-09-05—Filed