When someone searches at Bing, as they are entering their query into a search box, Bing shows a drop-down set of query suggestions. Imagine Bing showing off query suggestions that go beyond auto-complete search results, which could show off competitors. That may be in the works according to a recently granted Microsoft patent.
Ideally query suggestions that are shown should reflect in some manner the intent of a person doing a search.
To a degree, the query suggestions that might be shown are generated by Bing may be based solely upon search queries submitted in the past. A newly granted Microsoft patent describes other ways that might capture query terms that might more closely capture the intent behind a search. These could be generated based upon:
- Query-log-based query suggestions
- Semantic-pattern-based query suggestions that are derived from semantic query patterns
- at least one of one or more entities or information associated with the one or more entities in a user’s query
The patent is:
Interactive semantic query suggestion for content search
Invented by Bo-June Hsu, Kuansan Wang, Yu-Ting Kuo, Chao-Chia Liu, Heung-Yeung Shum, Cornelia Carapcea, Yusuf Furkan Fidan, Lawrence William Colagiovanni, Arun Sacheti
Assigned to Microsoft
US Patent 8,983,995
Granted March 17, 2015
Filed: June 23, 2011
“Systems, methods and computer-storage media are provided for identifying query formulation suggestions in response to receiving a search query. A portion of a search query is received. Query formulation suggestions are identified by semantically analyzing the search query. The query formulation suggestions are used to further formulate the received search query. The query formulation suggestions include semantic-pattern-based query suggestions that are derived from semantic query patterns, one or more entities, and information associated with these entities. The query formulation suggestions are transmitted for presentation.”
Historically, the queries suggested by the search engine have been taken from query logs for queries submitted in the past that start with the alpha-numeric characters that the user began their query with (in effect, an autocompletion of the searcher’s query.)
The goal of the process described in this patent is aimed at better understanding or disambiguating the searcher’s actual intent, and matching it with useful information. (The burden of finding a good query as a query suggestion has shifted from the searcher to the search engine.)
The patent tells us that it may accomplish this task by “semantically analyzing at least a portion of a search query that is entered by a user to provide the user with query formulation suggestions based on identified entities.”
Entities are particular items (products, locations, companies, persons, organizations, etc.) that have known associated information, which can include categories, attributes, and attribute values.
These entities and their respective associated information may be stored in an entity store which might be referred to in the creation of query suggestions. The patent tells us that its advantages may be “scaled to tail and never-seen queries and can provide better user-intent signals to the system.” This means that the results based upon query suggestions will likely be more relevant and more likely to match a searcher’s intent behind a search.
The sources of information( The “semantic knowledge of a search system”) comes from “query logs, facets, relationships of entities from structured and unstructured data, contextual signals, and the like”.
The process described in the patent provides query formulation suggestions in response to a search query. It includes receiving at least a part of the query and identifying one or more query suggestions by semantically analyzing that portion of the search query. The query formulation suggestions comprise semantic-pattern-based query suggestions that are derived from semantic query patterns and at least one of one or more entities or information associated with the one or more entities. The method further includes transmitting the one or more query formulation suggestions to be presented to searchers.
Information associated entities in an original query can be comprised of one or more attributes and one or more attribute values. These are used to provide a list of query suggestions to a searcher.
Generating query formulation suggestions using a semantic pattern can involve receiving a number of search queries from a query log, each of the many search queries being associated with a respective set of matching entities, and identifying at least one semantic query pattern from the plurality of search queries. The method further includes identifying, as the patent tells us:
- “A weight for each identified semantic query pattern
- A plurality of semantic categories from an entity database, each of the plurality of semantic categories being associated with a respective set of entities
- At least one term or phrase (e.g, an n-gram) commonly associated with at least one of the semantic categories
- A plurality of semantic attributes as they pertain to the plurality of semantic categories
- At least one semantic attribute pattern from the plurality of semantic attributes
- A Weight for each identified semantic attribute pattern
- Generating a text-parser from the at least one semantic query pattern and respective weights, the at least one semantic category term or phrase and respective weights, and the at least one semantic attribute patterns and respective weights”
An Entity Store
The entity store may be configured to store various types of information used by the semantic suggestion generator to identify query formulation suggestions based on a semantic analysis of at least the portion of the search query entered by the user. The type of information stored in the entity store can include, for example:
- Attribute values
- Entities or items (e.g., products available for commerce, locations, people, companies, organizations, and the like)
- Categories to which such entities may correspond
- Attributes associated with the entities, and
- Attribute values associated with the entities as they pertain to particular attributes thereof
The patent also tells us that it might keep information about “common queries that previously have been issued or submitted to the search engine, in addition to popular or frequently selected interpretations.” These might be from a query log, so the idea of moving away from a query log for search suggestions hasn’t been abandoned completely.
query formulation suggestions
Query formulation suggestions may include various types of suggestions for formulating queries including, by way of example query-log-based query suggestions, semantic-pattern-based query suggestions (e.g., template-based query suggestions), categories associated with a search query, attributes associated with one or more identified entities, and attribute values associated with one or more identified entities.
Query-log-based query suggestions vs.Semantic-pattern-based query suggestions
“Query-log-based query suggestions” are suggestions that attempt to aid the user in formulation of a search query by providing the user with the most popular previously-submitted search queries identified from a query log that correspond to the character sequence entered into the search box at a particular instance. “Semantic-pattern-based query suggestions,” on the other hand, refer to query formulation suggestions that are generated from semantic query patterns (e.g., templates).
When a search query, or portion thereof, is submitted to the search system, a database of semantic query patterns (such as ” camera,” is accessed and an attempt is made to identify one or more semantic query patterns that correspond in some way to the input search query. In generating semantic-pattern-based query suggestions, a database or entity store may be used. By accessing entities and their respective associated information from the entity store, it can be ensured that only those semantic-pattern-based query suggestions that match known entities are returned. As such, before being presented to a user, semantic-pattern-based query suggestions are compared to entities stored in the entity store.
The patent also tells us that if a particular semantic-pattern-based query suggestion is not found in the entity store, it will not be returned to the user as a query suggestion, since it may not exist (e.g., such as a particular product that does not exist), or at least it does not match with the known information in the entity store. But if it is found, it may be returned to the user. Semantic-pattern-based query suggestions may be presented to the user in much the same way as query-log-based query suggestions.
Someone types the sequence “role” into the search query input area. “Rolex” may be identified as a potential query formulation suggestion by either identifying it as a query-log-based query suggestion or as a semantic-pattern-based query suggestion. It may be identified as a brand of watches, or a popular query, and may also correspond to one or more entities found in the entity index. The entity “rolex” may be associated with the category “watches,” and such category may be returned to the user as a suggested category that may then be utilized to further formulate the user’s search.
Similarly, a searcher may enter the characters “facebo” into the search query box, which may lead to the identification of the query formulation suggestion “facebook,” which may be an entity in the entity store. Further, it may include an associated categories, such as “Web,” such that an entered search query for “facebo” may return “Web” as a suggested category. This provides the searcher with an indication as to how the portion of the entered search query has been interpreted.
Someone may enter “Digital Camera”as a query which may lead to the identification of an entity with a category “digital cameras.” This display of a category may help the searcher better understand the intent of the query suggestion
The patent provides more details as to how this process is supposed to work, but the general idea seems to be to move away from query suggestions that are primarily based upon previously performed queries that are mostly auto-completed results.
By the query suggestion showing off a category related to the term being suggested, the patent is telling us that this approach helps better meet the intent of a searcher.
To a degree, this patent matches well with a recent observation by Dan Shure at Evolving SEO when he wrote recently about Google Showing Related Searches In Autocomplete