CN110020148B

CN110020148B - Information recommendation method and device and information recommendation device

Info

Publication number: CN110020148B
Application number: CN201711227095.0A
Authority: CN
Inventors: 林建素; 王俊豪
Original assignee: Beijing Sogou Technology Development Co Ltd
Current assignee: Beijing Sogou Technology Development Co Ltd
Priority date: 2017-11-29
Filing date: 2017-11-29
Publication date: 2022-04-26
Anticipated expiration: 2037-11-29
Also published as: CN110020148A

Abstract

The embodiment of the invention provides an information recommendation method, an information recommendation device and a device for information recommendation, wherein the method specifically comprises the following steps: aiming at a search word input by a user, acquiring a corresponding scene characteristic and/or a corresponding associated search word; the related search words are obtained according to historical search data generated by at least one user; determining a recommended search word corresponding to the search word according to the scene features and/or the associated search word; and displaying the recommended search terms. The embodiment of the invention can display the recommended search words which accord with the personalized characteristics of the user to the user, so that the recommended search words accord with the search intention of the user better.

Description

Information recommendation method and device and information recommendation device

Technical Field

The invention relates to the technical field of internet, in particular to an information recommendation method and device and an information recommendation device.

Background

Currently, a user can input a search word in a search box of a search engine to search so as to obtain a search result matched with the search word; and the search engine displays the search results matched with the search terms in a search result page for the user to select and view.

In addition, the search engine also obtains recommended search words related to the search words and displays the recommended search words at positions such as below or right side of the search results, so that when the search results do not accord with the search intention of the user, the user can select the required recommended search words from the displayed recommended search words to continue searching.

However, the recommended search terms provided by the search engine are usually only related to the literal meaning of the search terms, for example, the search term is "weekend weather", and the search engine may provide the following recommended search terms: "Beijing weekend weather", "Shanghai weekend weather", "Wuhan weekend weather", etc., but these recommended search terms may not meet the user's search intent.

Disclosure of Invention

The embodiment of the invention provides an information recommendation method and device and an information recommendation device, and aims to solve the problem that a recommended search word does not accord with a user search intention in the prior art.

In order to solve the above problem, an embodiment of the present invention discloses an information recommendation method, including:

aiming at a search word input by a user, acquiring a corresponding scene characteristic and/or a corresponding associated search word; the related search words are obtained according to historical search data generated by at least one user;

determining a recommended search word corresponding to the search word according to the scene features and/or the associated search word;

and displaying the recommended search terms.

Optionally, the historical search data includes historical search terms, and determining, according to the associated search terms, recommended search terms corresponding to the search terms includes:

obtaining associated search words corresponding to the search words according to the mapping relation between the historical search words and the associated search words;

and determining a recommended search word corresponding to the search word according to the search word and the associated search word.

Optionally, the determining, according to the search term and the associated search term, a recommended search term corresponding to the search term includes:

and combining at least one associated search word and the search word, and taking a new search word obtained by combination as a recommended search word corresponding to the search word.

Optionally, the mapping relationship between the historical search terms and the associated search terms is established by:

determining related search words corresponding to the historical search words in the historical search data;

and establishing a mapping relation between the historical search words and the associated search words.

Optionally, the determining the associated search terms corresponding to the historical search terms includes:

screening a historical search word set with an incidence relation from the historical search words;

and determining the associated search words corresponding to the historical search words according to the historical search word set.

Optionally, the historical search data further comprises: the determining the associated search terms corresponding to the historical search terms in the historical search data according to the historical search results corresponding to the historical search terms includes:

and extracting the associated search words corresponding to the historical search words from the historical search results according to the selection operation of the user on the historical search results.

Optionally, the method further comprises:

and updating the mapping relation between the historical search words and the associated search words according to the selection operation of the user aiming at the recommended search words.

Optionally, the obtaining, for a search term input by a user, a scene feature corresponding to the search term includes: obtaining the position of the user from the search terms input by the user;

determining a recommended search term corresponding to the search term according to the scene characteristics, including:

determining a recommended search word corresponding to the search word according to the position attribute of the search word and the position of the user; and/or the presence of a gas in the gas,

determining a recommended search word corresponding to the search word according to the historical search word corresponding to the search word within a preset time range and the position of the user; and/or the presence of a gas in the gas,

and determining a recommended search word corresponding to the search word according to the category characteristics of the search word and the position of the user.

Optionally, the obtaining, for a search term input by a user, a scene feature corresponding to the search term includes: acquiring input time of the search terms from the search terms input by the user;

obtaining candidate search terms having an incidence relation with the input time according to historical search data of a user;

and determining a recommended search word corresponding to the search word according to the candidate search word and/or the hot word corresponding to the input time.

On the other hand, the embodiment of the invention discloses an information recommendation device, which comprises:

the acquisition module is used for acquiring corresponding scene characteristics and/or corresponding associated search terms aiming at the search terms input by the user; the related search words are obtained according to historical search data generated by at least one user;

the determining module is used for determining a recommended search word corresponding to the search word according to the scene features and/or the associated search word;

and the display module is used for displaying the recommended search terms.

Optionally, the historical search data includes historical search terms, and the determining module includes:

the related search word determining submodule is used for obtaining related search words corresponding to the search words according to the mapping relation between the historical search words and the related search words;

and the recommendation determining submodule is used for determining a recommended search word corresponding to the search word according to the search word and the associated search word.

Optionally, the recommendation determining sub-module includes:

and the recommendation determining unit is used for combining at least one associated search word and the search word and taking a new search word obtained by combination as a recommended search word corresponding to the search word.

Optionally, the apparatus further comprises: the establishing module is used for establishing a mapping relation between the historical search words and the associated search words; the establishing module may specifically include:

the related search word acquisition sub-module is used for determining related search words corresponding to the historical search words in the historical search data;

and the mapping relation establishing submodule is used for establishing the mapping relation between the historical search words and the associated search words.

Optionally, the related search term obtaining sub-module includes:

the screening unit is used for screening a historical search word set with an incidence relation from the historical search words;

and the first determining unit is used for determining the associated search words corresponding to the historical search words according to the historical search word set.

Optionally, the historical search data further comprises: historical search results corresponding to the historical search terms; the related search word obtaining sub-module comprises:

and the second determining unit is used for extracting and obtaining the associated search words corresponding to the historical search words from the historical search results according to the selection operation of the user on the historical search results.

Optionally, the apparatus further comprises:

and the updating module is used for updating the mapping relation between the historical search words and the associated search words according to the selection operation of the user aiming at the recommended search words.

Optionally, the obtaining module includes: the first obtaining sub-module is used for obtaining the position of the user from the search words input by the user;

the determining module includes:

the first determining submodule is used for determining a recommended search word corresponding to the search word according to the position attribute of the search word and the position of the user; and/or the presence of a gas in the gas,

the second determining submodule is used for determining a recommended search word corresponding to the search word according to the historical search word corresponding to the search word within the preset time range and the position of the user; and/or the presence of a gas in the gas,

and the third determining submodule is used for determining the recommended search word corresponding to the search word according to the category characteristics of the search word and the position of the user.

Optionally, the obtaining module includes: the second obtaining sub-module is used for obtaining the input time of the search terms from the search terms input by the user;

said determining means comprises:

the candidate search word acquisition sub-module is used for acquiring candidate search words which have an incidence relation with the input time according to historical search data of the user;

and the fourth determining submodule is used for determining the recommended search word corresponding to the search word according to the candidate search word and/or the hot word corresponding to the input time.

In yet another aspect, an embodiment of the present invention discloses an apparatus for information recommendation, including a memory, and one or more programs, where the one or more programs are stored in the memory and configured to be executed by the one or more processors include instructions for:

and displaying the recommended search terms.

In yet another aspect, an embodiment of the present invention discloses a machine-readable medium having stored thereon instructions, which, when executed by one or more processors, cause an apparatus to perform an information recommendation method according to one or more of the preceding.

The embodiment of the invention has the following advantages:

according to the embodiment of the invention, the corresponding scene features and/or the corresponding associated search words are obtained aiming at the search words input by the user; the scene features can be used for reflecting differences of search environments, users may have different search intentions in different search environments, the associated search words can be used for reflecting differences of search habits, different users generally have different search habits, and different search habits may correspond to different search intentions. Therefore, according to the scene characteristics and/or the associated search words corresponding to the search words, the recommended search words which accord with the search environment where the user is located and/or accord with the search habits of the user can be obtained, namely, the recommended search words which accord with the personalized characteristics of the user can be displayed to the user, so that the recommended search words accord with the search intentions of the user better.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.

FIG. 1 is a flow chart of the steps of an embodiment of a method for information recommendation of the present invention;

FIG. 2 is a block diagram of an embodiment of an information recommendation device according to the present invention;

FIG. 3 is a block diagram of an apparatus 800 for information recommendation of the present invention; and

fig. 4 is a schematic structural diagram of a server according to the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Method embodiment

Referring to fig. 1, a flowchart illustrating steps of an embodiment of an information recommendation method according to the present invention is shown, which may specifically include:

step 101, acquiring scene features corresponding to search terms input by a user and/or associated search terms corresponding to the search terms; wherein the associated search terms may be obtained from historical search data generated by at least one user;

step 102, determining a recommended search word corresponding to the search word according to the scene features and/or the associated search word;

and 103, displaying the recommended search terms.

The information recommendation method provided by the embodiment of the present invention may be applied to various APPs (Application programs) or websites with a search function, such as a search engine, and the information recommendation method provided by the embodiment of the present invention may be applied to an Application environment corresponding to a client and a server, where the client and the server may be located in a wired or wireless network, and the client and the server perform data interaction through the wired or wireless network.

Specifically, the client may run on a terminal, and the terminal may specifically include but is not limited to: smart phones, tablet computers, electronic book readers, MP3 (Moving Picture Experts Group Audio Layer III) players, MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop portable computers, car-mounted computers, desktop computers, set-top boxes, smart televisions, wearable devices, and the like.

In practical applications, the client may obtain the search term input by the user through a preset interface, for example, obtain the search term input by the user through a search box in a search engine.

In order to solve the problem that the recommended search words provided by a search engine in the existing scheme are only related to the literal meanings of the search words and further do not accord with the search intentions of the user, the embodiment of the invention aims at the search words input by the user to obtain the corresponding scene features and/or the corresponding associated search words, determine the recommended search words corresponding to the search words according to the scene features and/or the associated search words, and display the recommended search words to the user so that the recommended search words accord with the current search scenes of the user and further accord with the search intentions of the user.

Optionally, the embodiment of the present invention may further display a link corresponding to the recommended search term to the user, where the link may point to a result page where the search is performed with the recommended search term. The user can enter the result page searched by the recommended search word by clicking the link corresponding to the recommended search word, and the operation of manually inputting the search word and triggering the search can be saved, so that the user operation can be simplified, and the search efficiency of the user can be improved.

The scene features can be used for reflecting the difference of search environments, and users may have different search intentions in different search environments. For example, a user may search at different geographic locations, or at different times, and may have different search intents. The associated search terms can be used for reflecting differences of search habits, different users usually have different search habits, and different search habits may correspond to different search intents. Therefore, according to the scene characteristics and/or the associated search words corresponding to the search words, the recommended search words which accord with the search environment where the user is located and/or accord with the search habits of the user can be obtained, namely, the recommended search words which accord with the personalized characteristics of the user can be displayed for the user, so that the recommended search words accord with the search intentions of the user better.

In the embodiment of the present invention, the associated search word may be obtained according to historical search data generated by at least one user, and the associated search word has an association relationship with the search word. The associated search terms can be used for reflecting differences of search habits, different users usually have different search habits, and different search habits may correspond to different search intents. Therefore, according to the associated search terms corresponding to the search terms, the embodiment of the invention can obtain the recommended search terms according with the search habits of the user.

The embodiment of the invention can acquire at least one historical search data generated by a user, wherein the historical search data can specifically comprise historical search words, further can determine associated search words corresponding to the historical search words, and establishes the mapping relation between the historical search words and the associated search words. In the searching process of the user, the associated search words corresponding to the historical search words matched with the search words input by the user can be obtained through inquiry according to the search words input by the user and the mapping relation, and then the recommended search words displayed to the user can be determined according to the associated search words. The at least one user may be any user in the internet, such as a user who currently inputs a search term, and the embodiment of the present invention does not limit a specific user.

In an alternative embodiment of the present invention, the mapping relationship between the historical search terms and the associated search terms may be established by:

step S11, determining the related search words corresponding to the historical search words in the historical search data;

and step S12, establishing a mapping relation between the historical search words and the associated search words.

According to the embodiment of the invention, the associated search words which accord with the personalized characteristics of the user can be mined according to the historical search data of the user, and the associated search words can reflect the personalized differences of the user, such as different search habits, search interests, search modes and the like of the user, so that the recommended search words determined according to the associated search words are more accord with the search intention of the user.

Specifically, the associated search term may be a historical search term appearing in the historical search data, and in an optional embodiment of the present invention, the determining the associated search term corresponding to the historical search term may specifically include:

The association relationship may specifically refer to literal association or meaning association, and it is understood that the embodiment of the present invention does not limit the specific relationship of the association relationship. In an application example of the present invention, it is assumed that screening out a historical search term set having an association relationship from historical search data of a user includes: { "Chengdu delicious food", "Chengdu on the tip of tongue", "Chengdu snack" }. Since all three historical search terms in the set are related to the Chengdu food, which indicates that the user wants to know the related information of the Chengdu food or the Chengdu snack while searching for the Chengdu food, the three historical search terms in the set can be related search terms. That is, it may be determined that the associated search word corresponding to the history search word "achievement cate" includes "achievement capital" and "achievement snack", that the associated search word corresponding to the history search word "achievement capital" includes "achievement cate" and "achievement snack", and that the associated search word corresponding to the history search word "achievement snack" includes "achievement cate" and "achievement capital".

In another optional embodiment of the present invention, the historical search data may include: the determining, by the history search result corresponding to the history search word, the associated search word corresponding to the history search word in the history search data may specifically include: and extracting the associated search words corresponding to the historical search words from the historical search results according to the selection operation of the user on the historical search results.

In this embodiment of the present invention, the associated search term may include, in addition to the historical search term appearing in the historical search data, the following: and the related search words are obtained by analyzing the historical search data and do not appear in the historical search data.

In an optional embodiment of the present invention, the extracting, according to a selection operation of a user for the historical search result, an associated search term corresponding to the historical search term from the historical search result may specifically include:

determining a target historical search result selected by the user from the historical search results;

extracting key words in the target historical search results;

and taking the keywords as associated search words corresponding to the historical search words.

In an application example of the present invention, it is assumed that the history search word of the obtained user includes "lie", and a history search result obtained by the user through the history search word "lie" search includes a plurality of URLs (Uniform Resource locators) related to "lie", such as a lie official website, a lie person introduction, and the like. According to the historical search data of the user, the target historical search result selected and clicked by the user further in the historical search results is a Lining official website, and the commodity information related to the sports shoes is selected and clicked in the Lining official website, which indicates that when the user inputs the search word "Lining", the search intention is to search the commodity information of the Lining sports shoes, so that the keyword is "sports shoes" can be extracted from the target historical search result, although the historical search word "sports shoes" is not input by the user, the user can be known to have search preference on the Lining sports shoes according to the selection operation of the user on the historical search result corresponding to the historical search word "Lining", therefore, the keyword "sports shoes" can be extracted from the historical search result of the user as the associated search word corresponding to the historical search word "Lining", and a mapping relation between the historical search word 'Lining' and the associated search word 'sports shoes' is established.

For example, when the history search word is a movie name, the movie theater showing information is usually included in the target search result selected by the user, and therefore, the "showing information", ticket purchasing information ", and the like can be extracted from the target history search result of the user as the related search word corresponding to the movie search word. For example, a mapping relationship between the historical search word "wrestle dad" and the associated search word "show information" and the associated search word "ticket buying information" can be established.

For another example, a user often searches using the place name search term as a starting place or a destination to obtain traffic information related to the place name search term, such as flight information or high-speed rail information. Therefore, the "departure place", "destination", "flight information", "high-speed rail information", and the like can be extracted as the related search words corresponding to the place name search words. For example, a mapping relationship between the historical search term "beijing" and the associated search term "flight information" may be established, and so on.

It can be understood that, in the embodiment of the present invention, the storage location of the mapping relationship is not limited, and may be stored locally in the terminal, or may also be stored in the server.

In practical application, a user may search for information of interest for multiple times or click for multiple times to view, so that the embodiment of the present invention may further count the number of clicks of the user for the historical search results, and determine the associated search term according to the historical search result whose number of clicks exceeds a first preset value, so that the determined associated search term better conforms to the search preference of the user. It can be understood that the specific value of the first preset value is not limited in the embodiment of the present invention.

In practical application, one search word may correspond to a large number of associated search words in different field ranges, the associated search word user who does not match the field of the search word may not be interested in, and in order to make the obtained recommended search word more conform to the search intention of the user, the embodiment of the invention may further filter the associated search word according to the field corresponding to the search word, so that the finally obtained field corresponding to the associated search word matches with the field corresponding to the search word.

In embodiments of the invention, a field may refer to a specific area, and all matters related to that area may be cited therein. Examples of fields may include: home appliances, entertainment, automobiles, sports, science and technology, environmental protection and the like. The term "domain" refers to a term that occurs frequently in certain specific domains and rarely in other unrelated domains. For example, the 'first-steam public' is a word in the field of automobiles, the 'low-carbon' is a word in the field of environmental protection, and the 'Haier refrigerator' is a word in the fields of science and technology and household appliances. In practical applications, the domain range to which a word belongs can be determined by domain classification, and the embodiment of the present invention does not limit the specific domain classification process.

In an application example of the present invention, for a search term "air ticket", an associated search term having an association relationship with the search term may include: "air ticket inquiry", "air ticket booking", "special air ticket", "beijing to shanghai air ticket", "train ticket booking", "eastern airline company", "white cloud airport", and the like. Therefore, the embodiment of the present invention may filter the related search terms to obtain related search terms in a range corresponding to the field of the search term "air ticket", which may include, for example: the method comprises the steps of 'air ticket inquiry', 'air ticket reservation', 'special price air ticket', 'Beijing to Shanghai air ticket', and establishing a mapping relation between search words and associated search words.

The embodiment of the invention can acquire the associated search words in the field range corresponding to the search words, so that the recommended search words obtained according to the associated search words also conform to the field range of the search words, the range of the recommended search words is more accurate, and the recommended search words conform to the search intention of the user.

In an optional embodiment of the present invention, the historical search data may include historical search terms, and the determining, according to the associated search terms, a recommended search term corresponding to the search term may specifically include:

step S21, obtaining related search words corresponding to the search words according to the mapping relation between the history search words and the related search words;

and step S22, determining a recommended search word corresponding to the search word according to the search word and the associated search word.

After the historical search data of the user is obtained and the mapping relation between the historical search words and the associated search words is established according to the historical search data, the associated search words corresponding to the search words input by the user can be obtained through inquiry according to the search words input by the user and the mapping relation in the user search process, the recommended search words corresponding to the search words are determined according to the search words and the associated search words, and then the recommended search words can be displayed to the user.

Specifically, the associated search term may be directly presented to the user as a recommended search term, for example, assuming that the search term input by the user is "name of people", by querying the stored mapping relationship, the associated search term corresponding to "name of people" may be obtained by: the "introduction of a scenario", "introduction of an actor", etc., the associated search terms "introduction of a scenario", "introduction of an actor" may be directly presented to the user as recommended search terms.

Or, a new search word may be generated according to the search word and the associated search word, and the new search word may be presented to the user as a recommended search word. In an optional embodiment of the present invention, the determining, according to the search term and the associated search term, a recommended search term corresponding to the search term may specifically include: and combining at least one associated search word and the search word, and taking a new search word obtained by combination as a recommended search word corresponding to the search word.

In an application example of the present invention, assuming that a search term input by a user is "lianing", by querying a stored mapping relationship, obtaining an associated search term corresponding to "lianing" includes: "sports shoes", "sports wear", "running shoes", the search term "runing" and its corresponding at least one associated search term may be combined to obtain the following new search terms: "lie sports shoes", "lie sports wear", "lie running shoes", and the above-mentioned new search word is presented to the user as a recommended search word.

It can be understood that, in practical applications, in the process of combining at least one of the associated search terms and the search term, the embodiment of the present invention does not limit the specific number of the associated search terms, for example, the number of times that the user clicks the associated search term may be counted, and the associated search term with the number of clicks exceeding a second preset value is selected to be combined. For example, in the above-mentioned associated search words, the number of clicks of "sports shoes" and "running shoes" is higher than the second preset value, and the number of clicks of "sports wear" is lower than the second preset value, only "lie" may be combined with "sports shoes" and "running shoes", respectively, to obtain new search words "lie sports shoes" and "lie running shoes", and "lie sports shoes" and "lie running shoes" may be presented to the user as recommended search words. It can be understood that the specific value of the second preset value is not limited in the embodiment of the present invention.

In addition, the order between the search term and the associated search term in the above combining process is not limited in the embodiment of the present invention, for example, in the above example, the following new search terms may also be obtained by combining: "sports shoes lie", "running shoes lie" and so on.

In an optional embodiment of the present invention, the method of the embodiment of the present invention may further include: and updating the mapping relation between the search words and the associated search words according to the selection operation of the user aiming at the recommended search words.

According to the embodiment of the invention, the mapping relation between the search words and the associated search words can be updated according to the selection operation of the user aiming at the recommended search words, so that the associated search words in the mapping relation are more in line with the search preference of the user. For example, if the user selects and clicks the presented recommended search word "li ning sports shoes", which indicates that the recommended search word meets the search intention of the user, the number of clicks corresponding to the associated search word "sports shoes" is increased. If the user does not select the recommended search word "Lining gym suit", which indicates that the user is not interested in the Lining gym suit, the mapping relationship between the search word "Lining" and the associated search word "gym suit" may be deleted.

Optionally, the embodiment of the present invention may further count the number of clicks of the user for the recommended search term in a first preset time period, for example, if the first preset time period is 10 days, the number of clicks of the user for the recommended search term in the last 10 days is recorded, and if the number of clicks of the recommended search term in the last 10 days does not exceed a third preset value, the mapping relationship corresponding to the associated search term corresponding to the recommended search term may be deleted. It can be understood that the specific values of the first preset time period and the third preset value are not limited in the embodiment of the present invention.

Aiming at the search word input by the user, the embodiment of the invention can also obtain the corresponding scene characteristic, so as to determine the recommended search word corresponding to the search word according to the scene characteristic. The scene characteristics may specifically include: the location of the user and/or the time of entry of the search term. For the above scene features, the embodiment of the present invention may provide the following scheme for determining the recommended search term corresponding to the search term:

scheme one

In a first scheme, the scene features may specifically include: the location of the user.

In an optional embodiment of the present invention, the obtaining, for a search term input by a user, a scene feature corresponding to the search term may specifically include: obtaining the position of the user from the search terms input by the user; determining the recommended search term corresponding to the search term according to the scene characteristics may specifically include: and determining a recommended search word corresponding to the search word according to the position attribute of the search word and the position of the user.

The location attribute may refer to that the search word has a characteristic related to a geographic location, for example, for a search word of a place name class, the search word generally has a location attribute, such as "beijing", "chengdu", "france", and the like, when a user inputs the search word "beijing", location information of the user may be obtained, and if the location of the user is "west ampere", it indicates that the user may want to go to beijing from west ampere, and according to the location attribute "beijing" corresponding to the search word and the location "west ampere" of the user, the following recommended search word "flight information from west ampere to beijing", "high-speed information from west ampere to beijing", and the like may be determined.

In an optional embodiment of the present invention, the determining, according to the scene characteristic, a recommended search term corresponding to the search term may specifically include:

and determining a recommended search word corresponding to the search word according to the historical search word corresponding to the search word within a preset time range and the position of the user.

In practical application, search terms input by a user within a certain time range usually have an association relationship, and therefore, the embodiment of the present invention may further obtain a historical search term within a preset time range corresponding to the search term, for example, in the above example, if the search term input by the user is "beijing", the historical search term within the preset time range corresponding to the search term is obtained, and assuming that the historical search term within 5 minutes before the input of the search term is obtained, the method specifically includes: the historical search terms related to travel, such as "travel", "five day trip", and the like, can determine that the user currently wants to acquire information related to travel, and then according to the historical search terms "travel", "five day trip", the search term "beijing", which is currently input by the user, and the current position "xi 'an", recommended search terms related to travel, such as "xi' an to beijing five day trip", and the like, can be provided to the user, so that the recommended search terms more conform to the current search intention of the user.

It may be understood that the location attribute may also be an implicit characteristic of the search term that is related to a geographic location, and in an optional embodiment of the present invention, the determining, according to the scene characteristic, a recommended search term corresponding to the search term may specifically include:

In an application example of the present invention, for the search term "wrestling bar dad", since the search term is the name of a movie recently popular, the user may want to know the related information of the movie, such as the user may want to view the related introduction of the movie or the user wants to watch the movie, and thus, the following recommended search terms may be provided to the user: "introduction of wrestling bar father film", "wrestling bar father online ticket purchase". In addition, since the category feature of the search word is a movie, the user may also want to go to a movie to watch the movie, and may also acquire the position information of the user and present the movie information near the user position to the user as a recommended search word, for example, the recommended search word "wrestling bar dad middle guan maja online shopping ticket" or the like may be presented to the user.

Scheme two

In a second aspect, the scene characteristics may specifically include: an input time of the search term.

In practical applications, the search intention of the user may be different at different times. For example, the user's search intent may be more inclined to search for information such as restaurants or snack bars nearby during a time period corresponding to lunch or dinner. On the weekend, the user may prefer to search information such as road condition information or weather conditions, so that the recommended search terms corresponding to the search terms can be determined according to the input time of the search terms, so that the recommended search terms are more in line with the current search intention of the user, and more accurate recommended search terms can be provided for the user.

In an optional embodiment of the present invention, the obtaining, for a search term input by a user, a scene feature corresponding to the search term may specifically include: acquiring input time information of the search terms from the search terms input by the user; determining the recommended search term corresponding to the search term according to the scene characteristics may specifically include:

step S21, obtaining candidate search words having an incidence relation with the input time according to historical search data of a user;

and step S22, determining a recommended search word corresponding to the search word according to the candidate search word and/or the hot word corresponding to the input time.

The candidate search term may be a historical search term appearing in the historical search data, or may also be a search term related to the historical search term obtained by analyzing according to the historical search data. And the historical search time corresponding to the candidate search word has an incidence relation with the input time of the search word. It is to be understood that the association relationship may specifically be a time point when the historical search time is the same as the input time, for example, the historical search time and the input time are both 9 am 10 min, or the historical search time is within a second preset time period before and after the input time, for example, the second preset time period is 30 min, and the input time is 9 am 10 min, and then the historical search time is in a range from 8 am 40 to 9 am 40, and it may be considered that the historical search time and the input time have an association relationship. It can be understood that, in the embodiment of the present invention, specific values of the second preset time period are not limited.

In practical applications, some users may always search for the same or similar information at a certain fixed time, for example, every morning after work, the user needs to open the internet easy business mailbox, but the user does not remember the web address of the internet access enterprise mailbox, always inputs a search word 'mailbox' in a search engine to search for the web address of the internet access enterprise mailbox, according to the historical search data of the user, it can be known that the user often opens the home page of the internet easy business mailbox through the search word "mailbox" in the time period of 9 o 'clock to 9 o' clock 30 minutes in the morning, therefore, if the search word obtained to the user is 'mailbox', and the input time of the search word is 9 am, 10 am, then "internet easy business mailbox" may be used as a candidate search word having an association relationship with the input time 9 am, 10 am according to the historical search data of the user.

In a specific application, the number of candidate search terms having an association relationship with the input time may be multiple, for example, in the above example, acquiring the search term input by the user as "mailbox", and the input time is 9 am, 10 am, and according to the historical search data of the user, acquiring the candidate search terms having an association relationship with the input time may further include: "air ticket", "weather", etc.

After obtaining the candidate search term having an association relationship with the input time, determining a recommended search term corresponding to the search term according to the candidate search term. Specifically, the candidate search term may be directly used as a recommended search term corresponding to the search term. Optionally, the candidate search term with the click times exceeding a fourth preset value is used as the recommended search term corresponding to the search term. It can be understood that the specific value of the fourth preset value is not limited in the embodiment of the present invention.

Optionally, the embodiment of the present invention may further obtain a hotword corresponding to the input time, for example, if the search word input by the user is "mushroom," the recommended search word such as "mushroom practice," "nutritional value of mushroom," and the like may be provided to the user. In addition, the fact that the blue thin lentinus edodes is a popular hot word in the near term can be known through the obtained hot word corresponding to the input time, and the hot word is in a literal correlation with the search word of the mushroom, so that the hot word of the blue thin lentinus edodes can be used as a recommended search word corresponding to the search word of the mushroom and displayed to a user, and more choices can be provided for the user.

It is to be understood that, in practical applications, the scene features may be used alone or in combination, and the embodiment of the present invention is not limited thereto. In addition, the embodiment of the present invention also does not limit the specific content of the scene features, for example, the scene features may further include: current network conditions, occupational characteristics of the user, etc.

In an application example of the present invention, it is assumed that a search word input by a user is "jongxi god", and it is detected that a current network signal of the user is poor, a search intention of the user may be to search for text information, such as a character introduction or a novel, related to jongxi god, that requires a low network condition, and it is not necessary to search for resources, such as pictures and videos, that require a high network condition, and therefore, recommended search words, such as "jongxi god character introduction", "jongxi god novel", and the like, may be presented to the user.

In the embodiment of the invention, the recommended search words can be determined according to the professional characteristics of the user. For example, by obtaining historical search data of a user, it can be known that the user frequently searches technical data related to programming, and if the professional characteristics of the user are judged to be programmers, recommended search words related to the professional characteristics can be displayed to the user.

It can be understood that, in practical applications, the scene features corresponding to the search terms and/or the associated search terms corresponding to the search terms obtained in the embodiment of the present invention may be obtained according to the user data of the current user, or may be obtained according to the user data of other users.

In an application example of the present invention, assuming that the search word input by the user a is "wrestling bar dad", by querying the user data stored in the server, it can be known that the user data of the user B includes a mapping relationship between the search word "wrestling bar dad" and the associated search word "wrestling bar dad film introduction", "wrestling bar dad online ticket purchase", and then a recommended search word corresponding to the search word "wrestling bar dad" can be determined according to the associated search word of the user B, and the obtained recommended search word is displayed to the user a. Therefore, when the user A inputs a certain search word for the first time, the user A can be provided with a proper recommended search word according to the user data of other users, so that the recommendation accuracy is improved.

In summary, the information recommendation method of the embodiment of the present invention obtains the corresponding scene features and/or the corresponding associated search terms for the search terms input by the user; the scene features can be used for reflecting differences of search environments, and users may have different search intentions in different search environments; the associated search terms can be used for reflecting differences of search habits, different users usually have different search habits, and different search habits may correspond to different search intents. Therefore, according to the scene characteristics and/or the associated search words corresponding to the search words, the recommended search words which accord with the search environment where the user is located and/or accord with the search habits of the user can be obtained, namely, the recommended search words which accord with the personalized characteristics of the user can be displayed for the user, so that the recommended search words accord with the search intentions of the user better.

Device embodiment

Referring to fig. 2, a block diagram of an embodiment of an information recommendation apparatus according to the present invention is shown, which may specifically include:

an obtaining module 201, configured to obtain, for a search term input by a user, a scene feature corresponding to the search term and/or an associated search term corresponding to the search term; the related search words are obtained according to historical search data generated by at least one user;

a determining module 202, configured to determine, according to the scene feature and/or the associated search term, a recommended search term corresponding to the search term;

and the display module 203 is used for displaying the recommended search terms.

Optionally, the historical search data includes historical search terms, and the determining module 202 may specifically include:

Optionally, the recommendation determining sub-module may specifically include:

Optionally, the apparatus may further include: the establishing module is used for establishing a mapping relation between the historical search words and the associated search words; the establishing module may specifically include:

Optionally, the related search term obtaining sub-module may specifically include:

Optionally, the historical search data may further include: historical search results corresponding to the historical search terms; the related search term obtaining sub-module may specifically include:

Optionally, the apparatus may further include:

Optionally, the obtaining module 201 may specifically include: the first obtaining sub-module is used for obtaining the position of the user from the search words input by the user;

the determining module 202 may specifically include:

Optionally, the obtaining module 201 may specifically include: the second obtaining sub-module is used for obtaining the input time of the search terms from the search terms input by the user;

the determining module 202 may specifically include:

For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.

The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.

With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

The embodiment of the invention discloses a device for information recommendation, which comprises a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs are configured to be executed by one or more processors and comprise instructions for: aiming at a search word input by a user, acquiring a corresponding scene characteristic and/or a corresponding associated search word; the related search words are obtained according to historical search data generated by at least one user; determining a recommended search word corresponding to the search word according to the scene features and/or the associated search word; and displaying the recommended search terms.

Optionally, the device is also configured to execute the one or more programs by the one or more processors including instructions for:

Fig. 3 is a block diagram illustrating an apparatus 800 for information recommendation, according to an example embodiment. For example, the apparatus 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, and the like.

Referring to fig. 3, the apparatus 800 may include one or more of the following components: processing component 802, memory 804, power component 806, multimedia component 808, audio component 810, input/output (I/O) interface 812, sensor component 814, and communication component 816.

The processing component 802 generally controls overall operation of the device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing elements 802 may include one or more processors 820 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interaction between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

The memory 804 is configured to store various types of data to support operation at the device 800. Examples of such data include instructions for any application or method operating on device 800, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 804 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

Power components 806 provide power to the various components of device 800. The power components 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the apparatus 800.

The multimedia component 808 includes a screen that provides an output interface between the device 800 and a user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front facing camera and/or a rear facing camera. The front-facing camera and/or the rear-facing camera may receive external multimedia data when the device 800 is in an operating mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the apparatus 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

The sensor assembly 814 includes one or more sensors for providing various aspects of state assessment for the device 800. For example, the sensor assembly 814 may detect the open/closed state of the device 800, the relative positioning of the components, such as a display and keypad of the apparatus 800, the sensor assembly 814 may also detect a change in position of the apparatus 800 or a component of the apparatus 800, the presence or absence of user contact with the apparatus 800, orientation or acceleration/deceleration of the apparatus 800, and a change in temperature of the apparatus 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 816 is configured to facilitate communications between the apparatus 800 and other devices in a wired or wireless manner. The device 800 may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the apparatus 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.

In an exemplary embodiment, a non-transitory computer-readable storage medium comprising instructions, such as the memory 804 comprising instructions, executable by the processor 820 of the device 800 to perform the above-described method is also provided. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

Fig. 4 is a schematic structural diagram of a server in an embodiment of the present invention. The server 1900 may vary widely by configuration or performance and may include one or more Central Processing Units (CPUs) 1922 (e.g., one or more processors) and memory 1932, one or more storage media 1930 (e.g., one or more mass storage devices) storing applications 1942 or data 1944. Memory 1932 and storage medium 1930 can be, among other things, transient or persistent storage. The program stored in the storage medium 1930 may include one or more modules (not shown), each of which may include a series of instructions operating on a server. Still further, a central processor 1922 may be provided in communication with the storage medium 1930 to execute a series of instruction operations in the storage medium 1930 on the server 1900.

The server 1900 may also include one or more power supplies 1926, one or more wired or wireless network interfaces 1950, one or more input-output interfaces 1958, one or more keyboards 1956, and/or one or more operating systems 1941, such as WindowsServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

A non-transitory computer-readable storage medium in which instructions, when executed by a processor of an apparatus (terminal or server), enable the apparatus to perform an information recommendation method, the method comprising: aiming at a search word input by a user, acquiring a corresponding scene characteristic and/or a corresponding associated search word; the related search words are obtained according to historical search data of the user; determining a recommended search word corresponding to the search word according to the scene features and/or the associated search word; and displaying the recommended search terms.

Optionally, the determining, according to the associated search term, a recommended search term corresponding to the search term includes:

acquiring historical search data of a user; the historical search data includes: historical search terms;

determining related search words corresponding to the historical search words;

acquiring a historical search result corresponding to the historical search word;

Optionally, the processor is also configured to execute the one or more programs by one or more processors including instructions for:

Optionally, the scene features include: the location of the user;

determining a recommended search word corresponding to the search word according to the scene characteristics, including:

if the search word has the position attribute, determining a recommended search word corresponding to the search word according to the position of the search word and the position of the user; and/or the presence of a gas in the gas,

Optionally, the scene features include: an input time of the search term;

Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.

It will be understood that the invention is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the invention is limited only by the appended claims.

The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

The information recommendation method, the information recommendation device and the device for information recommendation provided by the invention are described in detail, specific examples are applied in the text to explain the principle and the implementation of the invention, and the description of the above embodiments is only used to help understanding the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.

Claims

1. An information recommendation method, characterized in that the method comprises:

displaying the recommended search word;

wherein the determining of the recommended search term corresponding to the search term includes: step A, or step A and step B, or step A and step C, or step A, step B and step C;

the step A comprises the following steps: the historical search data comprises historical search words, and associated search words corresponding to the search words are obtained according to the mapping relation between the historical search words and the associated search words; combining at least one associated search word and the search word, and taking a new search word obtained by combination as a recommended search word corresponding to the search word;

the step B comprises the following steps: determining a recommended search word corresponding to the search word according to the position attribute of the search word and the position of the user;

the step C comprises the following steps: determining a recommended search word corresponding to the search word according to the category characteristics of the search word and the position of the user;

the mapping relation between the historical search words and the associated search words is established through the following steps:

2. The method of claim 1, wherein the determining the associated search term to which the historical search term corresponds comprises:

3. The method of claim 1, wherein the historical search data further comprises: the determining the associated search terms corresponding to the historical search terms in the historical search data according to the historical search results corresponding to the historical search terms includes:

4. The method of claim 1, further comprising:

5. The method according to claim 1, wherein the obtaining of the scene features corresponding to the search terms input by the user comprises: acquiring input time of the search terms from the search terms input by the user;

determining a recommended search term corresponding to the search term according to the scene characteristics, further comprising:

6. An information recommendation apparatus, comprising:

the display module is used for displaying the recommended search terms;

wherein the determining module comprises: the first determining submodule or the first determining submodule and the second determining submodule or the first determining submodule and the third determining submodule or the first determining submodule, the second determining submodule and the third determining submodule;

the first determining sub-module is configured to, when the historical search data includes historical search words, obtain associated search words corresponding to the search words according to a mapping relationship between the historical search words and the associated search words, combine at least one of the associated search words and the search words, and use a new search word obtained by the combination as a recommended search word corresponding to the search word;

the second determining submodule is used for determining a recommended search word corresponding to the search word according to the position attribute of the search word and the position of the user;

the third determining submodule is used for determining a recommended search word corresponding to the search word according to the category characteristics of the search word and the position of the user;

wherein the apparatus further comprises: the establishing module is used for establishing a mapping relation between the historical search words and the associated search words; the establishing module comprises:

7. The apparatus of claim 6, wherein the related search term obtaining sub-module comprises:

8. The apparatus of claim 6, wherein the historical search data further comprises: the historical search result corresponding to the historical search word and the associated search word acquisition submodule comprise:

9. The apparatus of claim 6, further comprising:

10. The apparatus of claim 6, wherein the obtaining module comprises: the second obtaining sub-module is used for obtaining the input time of the search terms from the search terms input by the user;

the determining module includes:

11. An apparatus for information recommendation, comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory, and wherein execution of the one or more programs by one or more processors comprises instructions for:

displaying the recommended search word;

wherein the determining of the recommended search term corresponding to the search term includes: operation a, or operation a and operation B, or operation a and operation C, or operation a, operation B and operation C;

the operation A comprises the following steps: the historical search data comprises historical search words, and associated search words corresponding to the search words are obtained according to the mapping relation between the historical search words and the associated search words; combining at least one associated search word and the search word, and taking a new search word obtained by combination as a recommended search word corresponding to the search word;

the operation B comprises the following steps: determining a recommended search word corresponding to the search word according to the position attribute of the search word and the position of the user;

the operation C comprises the following steps: determining a recommended search word corresponding to the search word according to the category characteristics of the search word and the position of the user;

12. The apparatus of claim 11, wherein the determining the associated search term to which the historical search term corresponds comprises:

13. The apparatus of claim 11, wherein the historical search data further comprises: the determining the associated search terms corresponding to the historical search terms in the historical search data according to the historical search results corresponding to the historical search terms includes:

14. The apparatus of claim 11, wherein the apparatus is also configured to execute the one or more programs by one or more processors includes instructions for:

15. The apparatus according to claim 11, wherein the obtaining of the scene features corresponding to the search terms input by the user comprises: acquiring input time of the search terms from the search terms input by the user;

16. A machine-readable medium having stored thereon instructions, which when executed by one or more processors, cause an apparatus to perform the information recommendation method of one or more of claims 1-5.