FIELD: computer technology.
SUBSTANCE: server receives an indication of the user request, uses the first model to generate a first candidate string and a second candidate string that represent the corresponding candidates for the extended query, uses the second model to determine that the first string is candidate and the second candidate string are a pair of similar candidate strings, and causes only one of the pair of similar candidate strings to be displayed on the electronic device as an extended query. The second model is trained in a pairwise configuration based on the training set. The training set contains the first and second training lines and a label. The label indicates the similarity of the first training string and the second training string. The label is determined based on a comparison of the training document or several documents relevant to the first and second training string.
EFFECT: increase of accuracy of information retrieval due to the ability to provide the user with predictable extended search queries.
26 cl, 6 dwg
Title | Year | Author | Number |
---|---|---|---|
METHOD AND SYSTEM OF SEARCH QUERY PROCESSING | 2015 |
|
RU2640639C2 |
METHOD AND SERVER FOR TRAINING MACHINE LEARNING ALGORITHM IN OBJECT RANKING | 2020 |
|
RU2782502C1 |
METHOD AND SYSTEM OF RANKING OF A VARIETY OF DOCUMENTS ON THE PAGE OF SEARCH RESULTS | 2017 |
|
RU2677380C2 |
SYSTEM AND METHOD FOR FORMATION OF TRAINING SET FOR MACHINE LEARNING ALGORITHM | 2020 |
|
RU2790033C2 |
SEARCH OFFER METHOD AND PROCESSING SERVER | 2015 |
|
RU2609079C2 |
METHOD AND SERVER FOR GENERATING META-ATTRIBUTE FOR RANGING DOCUMENTS | 2018 |
|
RU2721159C1 |
METHOD AND SYSTEM FOR GENERATING FEATURE FOR RANGING DOCUMENT | 2018 |
|
RU2733481C2 |
METHOD AND SERVER FOR TEACHING A NEURAL NETWORK TO FORM A TEXT OUTPUT SEQUENCE | 2020 |
|
RU2798362C2 |
METHOD (OPTIONS) AND SERVER OF SEARCH RESULTS RANKING BASED ON UTILITY PARAMETER | 2015 |
|
RU2632138C2 |
METHOD AND SYSTEM FOR EXPANDING SEARCH QUERIES IN ORDER TO RANK SEARCH RESULTS | 2018 |
|
RU2720905C2 |
Authors
Dates
2024-02-13—Published
2021-09-14—Filed