|
Korolev is the algorithm of the Yandex search engine, on which the new version of the search is based. It was launched in August 2017. It is a logical continuation of the Palekh algorithm. A neural network trained on search statistics and user behavior compares the meaning and essence of a query and web pages, which makes it possible to better respond to complex queries.
The principle of operation The Korolev search algorithm, unlike the previously created Palekh, analyzes not only the page title, but the entire page. The definition of meaning takes place simultaneously with indexing, which significantly increases the speed and number of pages processed. In order for the user to receive a response, several stages are used. At each of them, the documents are sorted, the best ones go to the next stage.
As the level increases, more and more heavy algorithms are used. To speed up the final stage and increase the volume of analyzed documents, an additional index was introduced containing the approximate relevance calculated at the indexing stage for popular words and their pairs from user queries. This made it possible to significantly increase the depth – up to 200 thousand documents analyzed per request. In addition to comparing the question asked with the meaning of the page, the algorithm takes into account which other queries users viewed a particular document for, which allows you to establish additional semantic links. The algorithm uses a neural network that is trained on impersonal statistics. Simple users are involved in neural network training. If previously only Yandex employees and assessors, were engaged in this, now anyone can take part in training the Matrixnet, a machine learning method that builds the ranking formula. Users can register at Yandex.Toloka and proceed with assessing tasks.
Korolev algorithm touches on verbose queries with clarification of meaning, and these are, as a rule, informational, low- and micro-frequency queries, often set by voice search. As a response, there may be pages where some of the words used in the query are missing altogether.
Immediately after the launch, for many clarifying queries, to the right of the search results in Yandex, users were asked to evaluate the quality of the answer to the question and specify the site that was more successful in answering their query.
Impact on SEO
Korolev search algorithm has the greatest impact on information queries with complex, verbose, and often unique wording. However, it has been noticed that sites with occurrences of some words from the query are still often assigned higher positions. Korolev algorithm has practically no effect on the issuance of standard commercial requests so far. However, the increasing appeal of Yandex towards understanding the meaning of search queries naturally suggests that it is a matter of time. Therefore: it is necessary to pay more attention to the informative content, its value and usefulness to the user, exclude empty descriptions and include the principles of LSI copywriting with subject-specific words & synonyms.
It is also important to maintain high rates of behavioral factors (visit duration, viewing depth, revisits).
The "cosmic" premiere of Yandex is not only a change in the index structure, but also a kind of another reminder that you need to make content for people, and not just for attempts to manipulate the output.
|
