After the new Yandex algorithm “Korolev” was presented on August 22, many SEO specialists had concerns about a possible drop in site traffic. On the other hand, if search traffic for some sites drops, then others will see an increase.
But let's figure it out together whether everything is so scary.
By the way, based on Yandex Metrica data, we see that many users enter the query “How to enable Yandex Korolev?” and visit our article. In fact no need to turn on anything, this new ranking system already works automatically for everyone.
What is the Yandex Korolev algorithm?
In essence, “Korolyov” is a pumped-up version Palekh, whose work is based on recognizing meaning using a neural network. If Palekh could only recognize headings and processed up to 150 documents, then Korolev evaluates all the text on the page and can process over 200 thousand pages.
The official blog also states that the changes concern not only the application neural networks for search not in words, but in meaning, but also in the very architecture of the search results index.
How the Korolev algorithm works
According to the creators of the algorithm, it will allow us to move to a completely different level of understanding the meaning of user requests. Now the entire site page will be evaluated with semantic vector search queries.
When a user enters a query, the search engine needs to understand which page and which title matches it the most. To do this, the request and title are converted into a multiplication of vectors, and the larger the result, the greater the relevance of the page to the request. At the moment of generating a response to a request, the text of headers and requests is instantly converted into vectors and compared. This makes it possible to identify possible connections in meaning, but at the same time requires enormous computing power. This is how Palekh works.
What has been done to improve its performance? The Korolev algorithm performs a preliminary calculation of vectors, which allows you not to load the server during the request itself, but to take a ready-made result. In addition, as mentioned above, Korolev converts not only the page title, but also its entire content into a semantic vector.
But you should understand that “Korolev” is not a revolutionary website ranking algorithm that will turn Yandex search results upside down. This is a complex of already implemented solutions, improved with the help of neural networks and user experience.
What awaits the industry after the release of “Korolev”?
At the moment, there are no global changes in search results and they are unlikely to occur in the near future. For example, in the search there are still many pages that answer the synonymous queries “kitchen interior” and “kitchen design”, using different pages where there is a direct occurrence of the key.
Real changes will come when there is no need to collect a database for one “big” request low frequency queries, write text under them of 10,000 characters.
1. Users
From the point of view of users, it can be strange that queries that are identical in meaning, but differ in spelling, produce different results. Many users submit queries to a search engine as if they were asking a friend. The new algorithm will make it easier to answer these requests.
2. Webmasters
In an ideal world, webmasters would make good products, create quality content, and not think about specifically promoting their site in search engines. In reality, they often have to adjust texts and the site itself for search engines.
3. SEO specialists
Some of the methods that helped promote websites before (for example, SEO copywriting) will no longer give such an effect. Of course, there will be attempts to outwit the new algorithm, but part of the effort will be aimed at creating high-quality content.
It’s too early to judge the quality of the new algorithm, but the more answers it gives, the better it will become. Therefore, in the long term, users should feel the difference.
What kind of machine is this?
With the introduction and growth of the IQ level of neural networks in search engines, the quality and relevance of the content returned will increase exponentially. The machine can analyze visual content and understand the meaning of words and expressions.
An attempt to weave into pages any popular news items that do not have a direct semantic relationship to the topic of the resource’s niche will lead to exclusion from the search results.
Advantages
The key advantage of a neural network is not that it can analyze, but that it can learn and remember. That is, resources that, at the choice of users, do not meet the expectations of the search results will also gradually drop out of the search results.
That is, the machine records that for request A, the relevant number of users always click on resource B and never click on resource D. Resource D will be excluded from the niche of matching request A.
Let's wait a few weeks and we'll see
On the one hand, the name is not as fucking as “Palekh”. And that's already good. On the other hand, everyone has not yet had time to perfectly adapt to “Palekh”, when here comes a new, more twisted algorithm that focuses more and more on content.
Content is a king – confirmed after each update
Of the advantages, it is obvious that this provides an increasing opportunity for progressive, savvy and new sites to compete in saturated niches with long-established search results leaders, as well as sending everything into the more distant astral plane of thoughtless SEO copywriters who made a garbage dump on sites by listing anchors in texts.
The algorithm provides the opportunity for new professional growth for copywriters with a head, they can do something more useful than write posts for social networks.
But, from a skeptical point of view, it is unlikely that Yandex will miss the moment to promote its commercial capabilities and their necessity, in particular the context.
I always perceive such news very positively. Because in addition to SEO optimization, you have a large area for content strategic actions, and this takes SEO to a new level. They stop treating him as something strange and incomprehensible. In the form people are familiar with, SEO is fucked up, it used to be like that, but time passes, and the outdated perception remains.
The logic is this: Previously, there were many web studios on the market that did SEO, and some simply pretended to do it, but took a budget for it. The latter predominated in number. This is why there is an opinion that SEO is a scam. Time passes, each update of the algorithm displaces those who “pretended”, and the outdated perception of people still remains.
The new Queen algorithm logically continues the changes in Yandex search in recent years. Greater emphasis on neural networks, analysis of the entire content of the page, and not just the headings.
A very important point is the analysis of other search queries that bring users to the current page, which allows you to more accurately determine the relevance of the content and the relationship between search queries.
To summarize: search quality will improve. And that's great.
Goodbye SEO texts
It will be interesting to see how the new algorithm will perform in real life. It takes time to evaluate both the adequacy of semantic output and ranking priorities.
Definitely, search will now have to do a better job of handling non-standard and rare queries if the network really sees more meaning behind keywords. I really hope so, because this is another step towards “Goodbye, SEO texts.” However, the network will need to be trained. This doesn't seem to be a joke.
I just tried the search for "Movie Boy with a Scar on His Forehead" and got a lot of references to the movie "Scarface" in the search results. That is, keywords still triumph over meaning.
And only if I find the Harry Potter pages I need in the search results and spend a significant amount of time on them, the machine will understand what meaning I put into the request and will clarify the search results for the next time. At least that's how it should be. The learning process will not be quick, but in any case it is a good step into the future.
A little closer to business...
Today, in response to the request “Buy a cabinet with a sliding door,” I persistently receive ovens and a bunch of unnecessary things (louvered, hinged, and so on).
The essence of the algorithm is to determine additional properties of the document at the URL indexing stage, expressing in numerical form the correspondence of the page text to previously known and frequently used phrases. It is stated that the innovation will affect low-frequency queries, which make up about a third of the search results.
Due to the lack of statistics on such “rare” queries, the quality of search for them suffers. In fact, this algorithm will pull out of oblivion documents that do not directly contain a long query, but are close in meaning to the user’s query.
It is important for marketers and SEO specialists that their optimized sites compete not only with each other, but also with with sites that have not been touched by the optimizer at all.
Of course, this only applies to low-frequency requests, and estimating the share of requests as 1/3 of the flow is an upper estimate. But in the near future, some sites may experience an outflow of low-frequency traffic. At the same time, it is pointless to make any numerical forecasts.
In my opinion, the very idea of building various indices made up of labeled n-grams (and this is what Yandex claims) lies on the surface. For example, one of the main features of the statoperator crawler is the construction of an n-gram index.
N-grams are more informative than individual words, they are amenable to classification and allow you to significantly expand the number of factors for constructing a search by meaning. I am glad that Yandex is moving in the right direction and is implementing current methods at a high level to increase the speed and quality of search.
Opinion of Dmitry Sevalnev, head of the SEO and advertising department at “
Yandex has launched a new ranking algorithm - “Korolev”. Now the search engine matches the meaning of the search query and the page. This is very convenient for users. However, what does the new algorithm mean for optimizers and website owners, how will promotion change and whether we should expect changes in traffic.
More than ever, the entire SEO world was waiting for the launch of a new ranking algorithm, announced on August 22, 2017. Of course, such announcements are a completely atypical thing for Yandex; usually they prefer not to talk about their plans, and announce the next release of the ranking algorithm after the fact.
On August 22, 2017, Yandex launched a new version of search. It is based on the Korolev search algorithm (since 2008, new ranking algorithms in Yandex are named after cities). Using a neural network, the algorithm compares the meaning of queries and web pages - this allows Yandex to more accurately respond to complex queries. Search statistics and ratings from millions of people are used to train the new version of search. Thus, not only developers, but also all Yandex users contribute to the development of search.
The scope of application of the new algorithm practically does not affect traditional SEO areas of interest, primarily which include commercial search results. “Korolev” turned out to be a logical continuation of the “Palekh” algorithm and is designed to serve the long tail of micro-frequency requests, usually asked in natural language. The peculiarity of such queries is that the documents relevant to them may not contain many of the words included in the query. This confounds traditional ranking algorithms based on textual relevance.
A solution was found in the form of using neural networks, which are trained, among other things, on user behavior. Therefore, the new Yandex algorithm works based on a neural network. It learns from examples of user queries and selects answers based on the meaning of the text on the page. This means, in particular, that it will be much more effective at working with non-standard queries when users themselves are not sure what the name of what they want to find is called. A lot comes down to computing power here.
In general, such an approach to solving the problem of ranking the long microfrequency tail of queries is not new. Back in 2015, it became known about the technology used by the Google search engine to find answers to multi-word queries asked in natural language - RankBrain. This technology, also based on machine learning, allows you to recognize the most significant words in queries and analyze the context in which the search is carried out. This allows you to find relevant documents that do not contain all the query words.
In addition, the algorithm also works with pictures. It analyzes the content of the image and selects the necessary option based on it, and not just from the description in the tags or the text surrounding it.
However, the long tail of micro-frequency multi-word queries in natural language may well be of interest to “burners” of information semantics - the creators of so-called information sites “for all occasions”. In general, they are already trying to organize an exact entry into their texts for as many queries as they know, which they manage to obtain using various methods of collecting semantics. In the same place where there will be no exact occurrences, i.e. for queries that were not sucked up by the “semantic vacuum cleaner” of the creators of information sites or for which they were unable to provide exact occurrences in the content, the domain of “Korolev” begins, which is designed to look for correspondence between queries and answers in the case when there are few intersections between them on key words. In such cases, Korolev will undoubtedly increase the requirements for the quality of content, and really interesting readable articles will benefit even more from collections of occurrences of key phrases diluted with water, because It is precisely such articles that may contain signals useful for the new algorithm. Well, all other SEOs can really relax - the next spanking is postponed. There are no casualties or destruction.
By launching Palekh, Yandex taught a neural network to convert search queries and web page titles into groups of numbers - semantic vectors.
An important property of such vectors is that they can be compared with each other: the stronger the similarity, the closer the query and header are to each other in meaning.
How is it different from Palekh?
The main difference of the new algorithm, in addition to improving the technical implementation, is the ability to recognize similar “meanings” throughout the document, and not just by the title (Title), which appears in the browser window.
How the Korolev algorithm works
Search algorithm "Korolev" compares semantic vectors search engines queries and entire web pages- and not just their headlines. This allows us to reach a new level of understanding of meaning.
As in the case of Palekh, the texts of web pages are converted into semantic vectors by a neural network. This operation requires a lot of computing resources. Therefore, Korolev calculates page vectors not in real time, but in advance, at the indexing stage.
When a person asks a query, the algorithm compares the query vector with the page vectors already known to it.
The "Queen" effect
The ability to understand meaning is especially useful when processing rare and unusual queries - when people try to describe the properties of an object in their own words and expect that the search will prompt its name.
This scheme allows you to start selecting web pages that match your search query in the early stages of ranking. In "Palekh" semantic analysis- one of the final stages: only 150 documents go through it. At Korolev it is produced for 200,000 documents.
In addition, the new algorithm not only compares the text of a web page with the search query, but also pays attention to other queries that bring people to that page.
This way you can establish additional semantic connections.
People teach machines
The use of machine learning, and especially neural networks, will sooner or later make it possible to teach search to operate with meaning at the human level. In order for a machine to understand how to solve a particular problem, it is necessary to show it a huge number of examples: positive and negative. Such examples are given by Yandex users.
The neural network used by the Korolev algorithm is trained on anonymized search statistics. Statistics collection systems take into account which pages users go to for certain queries and how much time they spend there.
If a person opens a web page and hangs there for a long time, he probably found what he was looking for - that is, the page answers his request well. This is a positive example.
It is much easier to find negative examples: just take a request and any random web page. The statistics that are used to train the algorithm are anonymized
Matrixnet, which is building a ranking formula, also needs people’s help.
Cleanup
For search to grow, people must continually evaluate its performance. Once upon a time, only Yandex employees, the so-called assessors. But the more ratings, the better - so Yandex attracted everyone to this and launched the Yandex.Toloka service. Now more than a million users are registered there: they analyze the quality of search and participate in improving other Yandex services. Toloka tasks are paid - the amount that can be earned is indicated next to the task. Over the two-plus years of the service’s existence, talkers have given about two billion ratings.
Modern search is based on complex algorithms. Algorithms are invented by developers, and taught by millions of Yandex users. Any request is an anonymous signal that helps the machine understand people better. A new search is a search that we do together.
Yesterday evening, in the presence of several thousand webmasters and two astronauts, Yandex announced the launch of a new algorithm called “Korolev”. Never before has the company announced a change in the algorithm on such a large scale: an Apple-style presentation, direct communication with space, a huge hall of the Moscow Planetarium, online broadcast, and post-releases in major Runet publications. It is not surprising that such powerful PR caused a strong reaction from the SEO community and another outburst of emotions towards “bloodthirsty Yandex, which passionately wants to drive everyone into Direct.”
Let's figure out what really happened and what we can expect from the next innovations.
What can we expect from Korolev in the near future?
The main difference between Korolev and previous algorithms is that a ranked document can be considered relevant to a query even if the query itself is never contained in the body of the document (a logical continuation of Palekh, who did the same thing, only for Title).
The neural network identifies semantic relationships between different words and phrases and stores them in a separate database. The algorithm relies on these relationships when generating a response to a specific request. As a result, TOP pages can give a clear answer to the user’s question, but at the same time not contain a word from the request itself.
This fact raises many questions and speculations on the part of webmasters. How to optimize texts now? How to distribute requests across pages? Should we expect a drop in positions and traffic in the near future?
It’s too early to draw conclusions, but I’m inclined to believe that in the near future, most experts will not see any difference, because:
1) For commercial topics, little will change
From the examples given in the presentation and press releases, it is clear that the algorithm works primarily with informational NPs that reflect the meaning of names and terms that have flown out of your head:
- a picture where the sky swirls(Van Gogh)
– lazy cat from Mongolia(Pallas cat)
- a film about a man who grew potatoes on another planet("Martian")
It is difficult to imagine that a user would search for some product using such a query, for example “smartphone with the bitten apple logo” or "a vehicle in the form of a plank with two wheels on the sides".
2) The changes primarily affect multi-word queries
Judging by the presentation, the main task of the algorithm is to better understand the meaning of clarifying queries. As a rule, these are queries consisting of 5 or more words. Do we need to use neural networks to understand the meaning of queries like " rent an apartment in Moscow», « roller blinds for the bedroom" or " taxi to the airport"? I think the question is rhetorical.
How can I determine if Korolev has impacted my sites?
Judging by the number of tasks for checking positions in SEOlib, today all webmasters rushed to check how the new algorithm affected the ranking of their sites.
According to the presentation, the algorithm was launched earlier and has been working in mainstream search for some time. Therefore, the dynamics need to be assessed not over the last 24 hours, but over the last few weeks.
Moreover, it is incorrect to diagnose the impact of the new algorithm only by positions. If over the past few months your positions in the mid/low range have been dropping or jumping, I am 99% sure that the problem is not in the “Queen” (if you need help finding the reasons, send us a request - we will try to help).
How to check? See if your traffic from Yandex along the low-frequency tail has changed (see the report “Keywords” - “Others” in Y.Metrika). If it has fallen or increased significantly, then you are the happy owner of the “Queen” consequences.
How to optimize texts for Korolev?
For information specialists collecting traffic based on low-frequency requests, this question is more relevant than ever. But very little time has passed to draw up specific instructions or give targeted recommendations on texts.
For now I can only give one piece of advice. If you have already planned the work of copywriters for months in advance, take a timeout for 2-4 weeks and start revising the technical specifications. Can't stop the conveyor? Then write texts rich in semantics to increase the likelihood of getting happiness:
“Another important feature of Korolev is that in addition to comparing the meaning of the query and the page, it also takes into account the meaning of other queries to which the page is relevant.” Pruflink
I think that in the very near future services will appear to automate the process, and the era of clusterers will be replaced by the era of LSI analyzers.
There is reason to believe that over time, Yandex will expand the influence of “Queen” on commercial and short queries. Perhaps this is something to be happy about. After all, then there will be no need to balance between the need to optimize the text with occurrences and the risk of getting Baden-Baden. Whatever happens, everything is for the better.
If your site is down in Yandex or Google, and you cannot determine the reason, contact us, we will try to help.
Hello, dear readers of the blog site. I apologize that some posts are published over a long period of time, but I launched several more projects that suddenly rose to the TOP in 1.5 months, using my knowledge in the field of blogging (if anyone needs advice, write in a personal message). I have to be torn between projects and building a house for my family.
Today we will touch on the new Korolev algorithm from Yandex and try to compare it with its predecessors. Personally, it didn’t have much impact on my blog, except that useful and voluminous articles became even higher in the TOP. Well, let's take a closer look at everything in the article and draw the necessary conclusions after observing this algorithm.
Korolev Yandex algorithm - what it is and how it works
At the end of August 2017, a new Yandex Queen algorithm was released. The news about the update in the search engine immediately attracted interest from SEO specialists and the media.
The main feature of Korolev is to increase the speed of information processing and improve the quality of semantic analysis of the text.
The speed of data processing has increased several thousand times. Palekh used 150 documents to form the TOP. Now more than 200,000 articles are compared with each other. This result was achieved by optimizing the ranking protocol.
To understand the new algorithm, we need to go back a step to Palekh. His presentation was held on November 2, 2016. Statistics showed that the largest portion of search phrases were low-frequency phrases tailored to the only correct answer. This part falls on the bird's long tail.
To give the desired answer, the client must have associative thinking and self-learning skills, like a person. Neural networks are best suited for such tasks, which is why they became the basis of the new algorithm.
The main goal of "Korolev"
If a person wants to find a specific object, he begins to describe its properties; these are features of associative thinking. If we have forgotten the name of the video, then we begin to say what was contained inside: “a film about girls during the war” or “a film about a creature with a tail and wings.” In the first case, Yandex provides “And the dawns here are quiet”, in the second option we get “chimera”.
Yandex improves the quality of comparison of multi-word phrases. The program analyzes the connection between each word in a sentence and builds a unique association with multiple answer options. Just like the human brain does.
What's new?
Innovations:
- semantic vector for all content, not just the title;
- comparison of more than 200,000 articles when creating search results;
- user behavior on the page is taken into account;
- people help train the system.
Korolev analyzes not only the title, but the entire content (including photos, videos, tables, etc.) and composes a semantic vector based on it.
The main innovation was the multiple acceleration of search methods. In the past, the semantic vector was built at the moment the phrase was entered into the search bar. This method heavily loaded the servers and delayed the speed of response.
When you send a search phrase, its semantic vector is compared with the array already recorded in the database. Palekh compared about 150 options, but the new version analyzes more than 200,000 articles at a time. This increases the chance of finding the desired answer.
Yandex neural network: operating principle of the Korolev neural network + examples
The main feature of a neural network is the ability to self-learn. Work is carried out not only according to deliberate formulas, but also on the basis of previous experience and mistakes.
The human brain is a huge neural network with associative thinking, and computers try to emulate human behavior by recreating the architecture of neural networks.
Features of the neural network structure
A neural network is a set of single neurons, each of which stores or processes information. Each of the neurons is capable of receiving, processing and transmitting signals. The input data stream is gradually processed from one neuron to another and in the end the desired result is obtained.
Artificial neural networks transmit conditional weights—numbers from 0 to 1—to each other to determine how well one or another version of the incoming information corresponds to the desired information. After the analysis is completed, the neuron with the highest weight is considered the most suitable to answer the question.
The diagram depicts a neural network. The first two layers do the processing. Each of the neurons contains a specific function that receives input data and, after processing, produces the necessary response. This is how semantic vectors are compared.
Semantic vectors
Computers cannot operate with words or pictures, so they use arrays of numbers to compare information with each other. Search engines must independently determine the main topic and idea of the text in order to give the user what he needs.
The similar the vector of the question asked and the text, the higher the article is in the search priority. Korolev uses analysis of all content:
- tables;
- text;
- photo;
- video;
- headers;
- quotes;
- lists;
- emphasis (italics, bold, etc.).
The quality of vector construction increases several times due to the conversion of more information.
To create vectors, a neural network is used, the text is passed through a sequence of neurons, and as a result, an output three-hundred-dimensional array of numbers is obtained. Subsequently, it is entered into a single database and used for comparison.
Education
The main feature of neural networks is learning ability. Unlike standard algorithms, neurons are able to remember their previous experience and self-learn from it. The computer is getting better and better at distinguishing information each time.
In the past, training was carried out by company employees, their task was to navigate through millions of requests and change issuance priorities at their discretion. Then the developers created the Yandex.Toloka application, it is a list of simple tasks. You need to go through queries and evaluate the quality of search results. For each task they pay about 0.1-1$
What content does the new search algorithm think is good?
The most suitable article for the TOP search results will be the one containing the maximum useful information for the user and corresponding to the request. Therefore, it should cover all sorts of client questions section by section.
In Korolev, user behavior on the page is taken into account as a priority. Therefore, the task of administrators is to try to retain the user and interest him. To do this, use structured headings, tables, lists, highlights, photos and videos.
New search priorities
SEO specialists, after the release, conducted a study to evaluate changes in ranking priorities. No significant changes were observed; priorities remain:
- text structure;
- completeness of the topic;
- content reading prostate;
- correspondence of headings to the semantic content of the text;
- correct formation of the semantic core.
The main thing is to write for living people; this priority remains the most important.
Why Yandex launched a new search algorithm and how it threatens sites
Any company strives to make its products the best in the service market. In this case, Yandex's biggest rival is Google. Innovations were created for the following purposes:
- improving the quality of search on non-standard issues;
- attracting new investors;
- increase in ranking productivity (more than 200,000 articles when generating results).
The main goal was to improve the quality of delivery. In addition, it was necessary to show investors that the company’s work was in full swing and their money was being used for its intended purpose. The innovations were subsequently used to create the Alice voice assistant.
Line of previous algorithms
To better understand new technologies, we need to go back to the past. In this case, we will consider the line of previous algorithms that were used by the search engine for ranking.
At first, the Internet contained only a couple of thousand sites; to find the desired article on them, it was enough to compare the keywords of the search phrase. Subsequently, the global network grew exponentially; now on one topic you can find more than hundreds of thousands of similar sites with a million articles.
Therefore, it was necessary to complicate the ranking systems and began to take into account the following additional parameters:
- number of referring materials;
- uniqueness of content;
- client behavior on the page.
Matrixnet
In 2009, Yandex faced a problem that articles increasingly did not answer user questions. To fix this error, it was necessary to teach the server to make decisions independently and learn on its own.
A complex mathematical formula with many parameters was invented to determine whether text matches a search phrase.
But the following problems remained:
- search depends on words;
- auxiliary materials (photos, videos, quotes, etc.) are not taken into account.
The main problem was that it was not always possible to fully describe the meaning of the article in one title. Quite often, the article does not contain specific keywords, but at the same time it fully reveals the topic and gives a detailed answer to the user’s question.
Palekh algorithm
In 2016, a neural network computer model was used in the ranking system. The main feature of this approach is that the computer is now able to remember its mistakes and learn from its own experience.
In the same year, semantic vectors were introduced. The title of the article was passed through a neural network and decomposed into many vectors. Now computers compared not words from the search, but multidimensional arrays of numbers and vectors. We managed to move away from direct dependence on the number of certain words in a phrase, and give priority to the semantic content.
One of the shortcomings remains the problem of low speed. To create the search results, only 200 of the most relevant articles were compared. Therefore, it was difficult for the system to find multi-word semantic phrases like “a film about a girl, a spy who runs away and goes to school.”
Yandex Korolev algorithm
In the latest innovation, we primarily optimized the neural network and improved the productivity of text processing. Now the vectors are compared in advance in offline mode, thanks to this it has been possible to increase the effectiveness of the search.
Yandex independently collects statistics on user interest and uses them to create pre-prepared search results.
Thanks to optimization, a semantic vector is compiled not only for headings, but for the entire content. It is possible to find a maximum of semantic connections between words.
Threats to websites
In general, no dangers have been created for the sites and the conversion statistics do not change much. First of all, the innovations will affect information blogs, forums and sites with films.
Websites that do not meet the interests of the user may fall from their leading positions. For example, the title is “homemade apple juice,” but the article discusses methods of growing trees, pancakes with jam, and a completely different text.
Don't forget to repost and subscribe to the blog newsletter. All the best.
All the best, Galiuin Ruslan.
