CN105404680A - Searching recommendation method and apparatus - Google Patents
Searching recommendation method and apparatus Download PDFInfo
- Publication number
- CN105404680A CN105404680A CN201510828522.5A CN201510828522A CN105404680A CN 105404680 A CN105404680 A CN 105404680A CN 201510828522 A CN201510828522 A CN 201510828522A CN 105404680 A CN105404680 A CN 105404680A
- Authority
- CN
- China
- Prior art keywords
- search
- recommendation information
- query word
- user
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Embodiments of the present invention provide a searching recommendation method and apparatus. According to one aspect, the method provided by the embodiment of the present invention comprises: determining at least two searching intentions of a user according to an obtained query word; obtaining a set of recommendation information associated with each searching intention, and generating a corresponding description label for each set of recommendation information; and furthermore, in a searching result page that matches the query word, correspondingly displaying at least two of the description labels and at least two sets of the recommendation information. Therefore, the technical scheme provided by the embodiments of the present invention improves the efficiency of obtaining the recommendation information from the searching result page.
Description
[technical field]
The present invention relates to the Internet search technology field, particularly relate to a kind of search recommend method and device.
[background technology]
At present, user is after input inquiry word (Query), and search engine is searched for according to this query word, and exports some search results pages matched with this query word to user.In prior art, in each search results pages of display, the below of last Search Results, can show the some recommendation informations recommending user.User is sometimes after navigate search results, when think input query word improper cause current search result not meet self search need time, or, after meeting search need, when user needs to carry out searching for obtain more information further, the recommendation information of display often can be recommended for user carry out search, completes search mission as early as possible to enable user, reduce searching cost, improve search efficiency.
But, the recommendation information of current output, carries out mixed display by the recommendation information of different dimensions often, needs user manually to check one by one in recommendation information, then filter out required information, the efficiency comparison therefore obtaining recommendation information in prior art from search results pages is low.
[summary of the invention]
In view of this, embodiments provide a kind of search recommend method and device, improve the efficiency obtaining recommendation information from search results pages.
The one side of the embodiment of the present invention, provides a kind of search recommend method, comprising:
According to the query word obtained, determine at least two search intentions of user;
Obtain the one group recommendation information relevant to each described search intention;
Corresponding description label is generated for often organizing described recommendation information;
In the search results pages matched with described query word, recommendation information described at least two described description labels and at least two groups is carried out correspondence display.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, the described query word according to obtaining, and determines at least two search intentions of user, comprising:
Obtain at least one in the co-occurrence information of the attribute information relevant to described query word, the search behavior information of being correlated with described query word and described query word;
According in the co-occurrence information of the attribute information relevant to described query word, the search behavior information of being correlated with described query word and described query word at least one, carry out cluster computing, at least two search intentions described in acquisition.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, and at least two search intentions described in acquisition, comprising:
According to user search feature, at least two the candidate's intentions obtained after cluster computing are screened, at least two search intentions described in obtaining from described at least two candidates intention.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, obtains the one group recommendation information relevant to each described search intention, comprising:
According to user search historical record, obtain the search behavior information relevant to each described search intention;
According to described search behavior information, obtain the Candidate Recommendation information relevant to each described search intention;
Described Candidate Recommendation information is screened, to obtain the one group recommendation information relevant to each described search intention.
Aspect as above and arbitrary possible implementation, there is provided a kind of implementation further, the description label often organizing described recommendation information corresponding comprises: often organize description text corresponding to described recommendation information and often organize at least one in description picture corresponding to described recommendation information.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, in the search results pages matched with described query word, recommendation information described at least two described description labels and at least two groups carried out correspondence display, comprising:
In the search results pages matched with described query word, utilize recommendation information described at least two cards display at least two described description labels and at least two groups, in each described card, show recommendation information described in a group of describing label and correspondence;
According to user's operating gesture for the card of current display in described search results pages, the card of current display is switched to other cards, to show description label in other cards and one group of corresponding recommendation information.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, in the search results pages matched with described query word, recommendation information described at least two described description labels and at least two groups carried out correspondence display, comprising:
According to the degree of correlation often organizing described recommendation information and described query word, sort to often organizing described recommendation information, to obtain ranking results;
According to described ranking results, in each search results pages of at least two search results pages matched with described query word, show the description label of recommendation information and correspondence described in a group.
The one side of the embodiment of the present invention, provides a kind of search recommendation apparatus, comprising:
Determination module, for according to the query word obtained, determines at least two search intentions of user;
Acquisition module, for obtaining the one group recommendation information relevant to each described search intention;
Generation module, for generating corresponding description label for often organizing described recommendation information;
Display module, in the search results pages matched with described query word, carries out correspondence display by recommendation information described at least two described description labels and at least two groups.
Aspect as above and arbitrary possible implementation, provide a kind of implementation, described determination module further, specifically for:
Obtain at least one in the co-occurrence information of the attribute information relevant to described query word, the search behavior information of being correlated with described query word and described query word;
According in the co-occurrence information of the attribute information relevant to described query word, the search behavior information of being correlated with described query word and described query word at least one, carry out cluster computing, at least two search intentions described in acquisition.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, described determination module for described in obtaining during at least two search intentions, specifically for:
According to user search feature, at least two the candidate's intentions obtained after cluster computing are screened, at least two search intentions described in obtaining from described at least two candidates intention.
Aspect as above and arbitrary possible implementation, provide a kind of implementation, described acquisition module further, specifically for:
According to user search historical record, obtain the search behavior information relevant to each described search intention;
According to described search behavior information, obtain the Candidate Recommendation information relevant to each described search intention;
Described Candidate Recommendation information is screened, to obtain the one group recommendation information relevant to each described search intention.
Aspect as above and arbitrary possible implementation, there is provided a kind of implementation further, the description label often organizing described recommendation information corresponding comprises: often organize description text corresponding to described recommendation information and often organize at least one in description picture corresponding to described recommendation information.
Aspect as above and arbitrary possible implementation, provide a kind of implementation, described display module further, specifically for:
In the search results pages matched with described query word, utilize recommendation information described at least two cards display at least two described description labels and at least two groups, in each described card, show recommendation information described in a group of describing label and correspondence;
According to user's operating gesture for the card of current display in described search results pages, the card of current display is switched to other cards, to show description label in other cards and one group of corresponding recommendation information.
Aspect as above and arbitrary possible implementation, provide a kind of implementation, described display module further, specifically for:
According to the degree of correlation often organizing described recommendation information and described query word, sort to often organizing described recommendation information, to obtain ranking results;
According to described ranking results, in each search results pages of at least two search results pages matched with described query word, show the description label of recommendation information and correspondence described in a group.
As can be seen from the above technical solutions, the embodiment of the present invention has following beneficial effect:
The technical scheme that the embodiment of the present invention provides can provide many group recommendation informations and recommendation information carries out grouping shows to user in result of page searching, and be often organize recommendation information to add description label, so that user is according to the grouping describing label and recommendation information, required recommendation information can be obtained in time, with need in prior art manually to check one by one, then required information is filtered out and the changeless scheme of recommendation information is compared, the technical scheme that the embodiment of the present invention provides, improve the diversity of recommendation information in search results pages and from search results pages, obtain the efficiency of recommendation information.
[accompanying drawing explanation]
In order to be illustrated more clearly in the technical scheme of the embodiment of the present invention, be briefly described to the accompanying drawing used required in embodiment below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is the schematic flow sheet of the search recommend method that the embodiment of the present invention provides;
Fig. 2 is the exemplary plot of the acquisition search intention that the embodiment of the present invention provides;
Fig. 3 is the first exemplary plot showing recommendation information in prior art in search results pages;
Fig. 4 (a) ~ Fig. 4 (c) is the first exemplary plot showing recommendation information in search results pages that the embodiment of the present invention provides;
Fig. 5 (a) ~ Fig. 5 (c) is the second exemplary plot showing recommendation information in search results pages that the embodiment of the present invention provides;
Fig. 6 is the second exemplary plot showing recommendation information in prior art in search results pages;
Fig. 7 (a) ~ Fig. 7 (c) be the embodiment of the present invention be provided in search results pages the 3rd exemplary plot showing recommendation information;
Fig. 8 is the functional block diagram of the search recommendation apparatus that the embodiment of the present invention provides.
[embodiment]
Technical scheme for a better understanding of the present invention, is described in detail the embodiment of the present invention below in conjunction with accompanying drawing.
Should be clear and definite, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making other embodiments all obtained under creative work prerequisite, belong to the scope of protection of the invention.
The term used in embodiments of the present invention is only for the object describing specific embodiment, and not intended to be limiting the present invention." one ", " described " and " being somebody's turn to do " of the singulative used in the embodiment of the present invention and appended claims is also intended to comprise most form, unless context clearly represents other implications.
Should be appreciated that term "and/or" used herein is only a kind of incidence relation describing affiliated partner, can there are three kinds of relations in expression, and such as, A and/or B, can represent: individualism A, exists A and B simultaneously, these three kinds of situations of individualism B.In addition, character "/" herein, general expression forward-backward correlation is to the relation liking a kind of "or".
Depend on linguistic context, word as used in this " if " can be construed as into " ... time " or " when ... time " or " in response to determining " or " in response to detection ".Similarly, depend on linguistic context, phrase " if determination " or " if detecting (the conditioned disjunction event of statement) " can be construed as " when determining " or " in response to determining " or " when detecting (the conditioned disjunction event of statement) " or " in response to detection (the conditioned disjunction event of statement) ".
Embodiment one
The embodiment of the present invention provides a kind of search recommend method, and please refer to Fig. 1, the schematic flow sheet of its search recommend method provided for the embodiment of the present invention, as shown in the figure, the method comprises the following steps:
S101, according to the query word obtained, determines at least two search intentions of user.
Concrete, in the embodiment of the present invention, the query word of user's input can be received, then search for according to this query word, to obtain the some Search Results matched with query word, represent some Search Results finally by search results pages to user.Generating in the process of search results pages according to Search Results, needing display in search results pages to be supplied to the recommendation information of user, in the embodiment of the present invention, in order to obtain recommendation information, needing at least two search intentions first determining user.
Illustrate, in the embodiment of the present invention, according to the query word obtained, determine that the method for at least two search intentions of user can include but not limited to:
Please refer to Fig. 2, the exemplary plot of its acquisition search intention provided for the embodiment of the present invention, as shown in the figure, first, at least one in the co-occurrence information of the attribute information relevant to described query word, the search behavior information of being correlated with described query word and described query word is obtained.Then, according in the co-occurrence information of the attribute information relevant to described query word, the search behavior information of being correlated with described query word and described query word at least one, carry out cluster computing, at least two search intentions described in acquisition.
In a concrete implementation procedure, if described query word is comprise entity in entity or described query word, then can obtain this entity attributes information from knowledge mapping, using as the attribute information relevant to described query word.
In a concrete implementation procedure, user search historical record can be obtained, then from user search historical record, the search behavior information relevant to this query word is obtained according to query word, if user is after this query word of search, search for again which query word, or, and for example, user, after this query word of search, clicks the Search Results which and this query word match.
In a concrete implementation procedure, according to web page contents, the co-occurrence information of described query word can be obtained, as other entities with this query word co-occurrence.Such as, word can be cut to a large amount of web page contents comprising this query word, and extract entity wherein, then add up the co-occurrence number of times of each entity and this query word, using the co-occurrence information of some entities the highest for co-occurrence number of times as described query word.
In the embodiment of the present invention, clustering algorithm can be utilized, in the search behavior information that the attribute information relevant to query word and query word are correlated with and the co-occurrence information of query word at least one, carry out cluster computing, at least two search intentions described in acquisition, realize, according to the query word of user's input, analyzing the search intention of user, like this, just recommendation information can be provided according to search intention to user.
Illustrate, in the embodiment of the present invention, according to cluster operation result, the method for at least two search intentions described in acquisition can include but not limited to:
As shown in Figure 2, after cluster computing, can be obtained up to few two candidates intention, then, according to user search feature, at least two the candidate's intentions obtained after cluster computing are screened, at least two search intentions described in obtaining from described at least two candidates intention.
Such as, can according to user search historical record, add up searching times or the number of clicks of each candidate intention, then according to searching times or number of clicks order from high to low, at least two candidate's intentions are sorted, obtain ranking results, finally extract at least two candidate's intentions the most forward in ranking results, as at least two search intentions of above-mentioned user.
S102, obtains the one group recommendation information relevant to each search intention.
Concrete, in the embodiment of the present invention, after at least two search intentions obtaining user, need to obtain the one group recommendation information relevant to each search intention, thus obtaining at least two group recommendation informations, this at least two groups recommendation information is used for being presented in search results pages.
Illustrate, in the embodiment of the present invention, the method obtaining the one group recommendation information relevant to each search intention can include but not limited to:
First, according to user search historical record, obtain the search behavior information relevant to each described search intention.Then, according to described search behavior information, obtain the Candidate Recommendation information relevant to each described search intention.Finally, described Candidate Recommendation information is screened, to obtain the one group recommendation information relevant to each search intention.
Which such as, according to each search intention, user can be searched in search behavior information under this search intention, searches for or click query word or entity, using these query words or entity as the Candidate Recommendation information relevant to this search intention.Then, can according to search or number of clicks order from high to low, these query words and entity are sorted, using the highest some query words that wherein sort with entity as relevant to this search intention one group of recommendation information.
Be understandable that, at least two recommendation informations can being comprised in one group of recommendation information relevant to each search intention, such as, 8 ~ 20 recommendation informations can be comprised for often organizing recommendation information, each recommendation information can be the query word that user inputs, or also can be entity.
S103, generates corresponding description label for often organizing described recommendation information.
Concrete, in the embodiment of the present invention, after obtaining the one group recommendation information relevant to each search intention, need to generate corresponding description label for often organizing recommendation information.
In the embodiment of the present invention, often organize description label corresponding to described recommendation information and can comprise at least one in following two kinds of description labels: often organize description text corresponding to described recommendation information and often organize description picture corresponding to described recommendation information.Be equivalent to, can obtain simultaneously and show and often organize description text corresponding to recommendation information and describe picture, or, also can obtain and show and often organize description text corresponding to recommendation information, or, also can obtain and show and often organize description picture corresponding to recommendation information.
In addition, it should be noted that, the classification of the description label that the different recommendation information organized is corresponding can be identical, also can be different, and the embodiment of the present invention is not particularly limited this.
In a concrete implementation procedure, according to the common trait often organizing recommendation information, and the description template preset can being utilized, generating corresponding description text for often organizing described recommendation information.Such as, description template can be " relevant search > common trait ", after acquisition one group of recommendation information, can extract the common trait of this group recommendation information, then can generate description text according to this common trait.
Being understandable that, often organizing description label corresponding to recommendation information for describing the common trait of this group recommendation information, also can embody the search intention of user and this organizes incidence relation between recommendation information.
Such as, the query word of user search is " Ha Shiqi ", describe label and can comprise " relevant search > general knowledge ", " relevant search > buys ", " relevant search > trains ", visible description label may be used for embodying the search intention of user and this organizes incidence relation between recommendation information, and " general knowledge ", " purchase " and " training " described in label embodies the common trait of corresponding recommendation information respectively.
In the embodiment of the present invention, in order to the recommendation information under different search intention can be provided to user more intuitively, when showing recommendation information, exemplary plot can be shown as description label.Such as, can in the below of the description text as one of description label, the left side of recommendation information, display can represent the picture of the common trait of recommendation information, and this picture can help user can obtain interested recommendation information intuitively, fast and accurately.And what increase that visual picture can strengthen recommendation information under this search intention and describe between label is explanatory, user can be made to be more prone to and to understand the recommendation information of display intuitively.
S104, in the search results pages matched with described query word, carries out correspondence display by recommendation information described at least two described description labels and at least two groups.
Concrete, after obtaining at least two group recommendation informations and often organizing description label corresponding to recommendation information, need in the search results pages matched with described query word, recommendation information described at least two described description labels and at least two groups is carried out correspondence display, realize exporting recommendation information and description label corresponding to recommendation information to user.
Illustrate, in the embodiment of the present invention, in the search results pages matched with described query word, the method for recommendation information described at least two described description labels and at least two groups being carried out corresponding display can include but not limited to following two kinds:
The first: in the search results pages matched with described query word, utilize recommendation information described at least two card display at least two described description labels and at least two groups, show one in each described card and describe recommendation information described in label and corresponding a group; Then, according to user's operating gesture for the card of current display in described search results pages, the card of current display can be switched to other cards, to show description label in other cards and one group of corresponding recommendation information.
Such as, in the search results pages matched with query word, describe between label and the card of recommendation information for display is different, user can utilize and slide left or switching that the gesture of sliding to the right realizes between different card, to make the card of current display can be switched to next card or a upper card, thus the description label that can show in next card or a upper card and recommendation information.Each slip gesture can carry out the refreshing of a recommendation information, to show the description label of new one group of recommendation information and correspondence.
In the embodiment of the present invention, different recommendation informations is shown by utilizing different card, the recommendation information that various dimensions are provided to user can be realized, and owing to only showing the some recommendation informations under a search intention in a card, therefore under each dimension, the quantity of recommendation information is more, realize providing more careful and the more high-quality content recommendation of number to user, not only meet user and multifarious demand is recommended to search, solve in prior art due to the limited recommendation information number that causes of display control and the less problem of kind, description label can also be utilized to help user to obtain interested recommendation information fast, improve search efficiency, reduce the cost obtaining recommendation information.
The second: first, according to the degree of correlation often organizing recommendation information and described query word, can sort to often organizing described recommendation information, to obtain ranking results.Then, can according to described ranking results, in each search results pages of at least two search results pages matched with described query word, show the description label of recommendation information and correspondence described in a group.Wherein, the recommendation information that the degree of correlation is higher is presented in the search results pages of preferential display.
In a concrete implementation procedure, according to the degree of correlation order from high to low often organizing recommendation information and query word, can sort to often organizing recommendation information, to obtain ranking results.
Utilize in many search results pages when showing different recommendation informations, can according to the matching degree of some the Search Results shown in different search page from front to back and search intention, and the degree of correlation of recommendation information and query word, for user provides matching degree by height on earth in different search results pages, the degree of correlation different recommendation informations from high to low, help user at the vertical whole navigation process of search results pages, obtain the recommendation information of different dimensions, recommendation information is combined with the page turning behavior of user, allow user in page turning process, when seeing different Search Results, also different recommendation informations can be obtained.
Such as, the query word of user's input is " Liu Dehua is picture by motorcycle ", one group of recommendation information in first search results pages is all relevant to the main demand " the handsome picture of Liu De China " of user, therefore determines that the search intention of user can be the recommendation information of " the young beautiful photograph of China " and relevant search thereof; One group of recommendation information in second search results pages is the recommendation information that demand secondary to user " the handsome photo of other stars " is relevant, therefore determines that the search intention of user can be the recommendation information of " star by bike " and relevant search thereof.
Embodiment two
Please refer to Fig. 3, it for showing the first exemplary plot of recommendation information in search results pages in prior art, as shown in Figure 3, in prior art, in the first search results pages matched with query word " Ha Shiqi ", article 10, the below of Search Results shows 8 relevant recommendation informations, as " Ha Shiqi IQ ", " Ha Shiqi how much ", " Ha Shiqi supports well " etc., the negligible amounts of recommendation information, and recommendation information static state is constant in different search results pages, mix between the recommendation information of different dimensions, user's pair all search needs relevant to " Ha Shiqi " can not be met.
Please refer to Fig. 4 (a) ~ Fig. 4 (c), its the first exemplary plot showing recommendation information in search results pages provided for the embodiment of the present invention, as shown in Fig. 4 (a) ~ Fig. 4 (c), as user input query word " Ha Shiqi ", determine that the search intention of user can be other general knowledge obtaining " Ha Shiqi ", slightly more weak search intention may comprise successively " purchase of Ha Shiqi ", " training of Ha Shiqi " etc.
In the embodiment of the present invention, to each search intention in these search intentions relevant to the query word that user inputs " Ha Shiqi ", obtain one group of recommendation information respectively, and according to the degree of correlation order from high to low of recommendation information and query word, in different search results pages, show one group of recommendation information respectively.
As shown in Fig. 4 (a), recommendation information under first search results pages provides from " relevant search > general knowledge " dimension to user and corresponding description label, as recommendation information comprises: " Ha Shiqi IQ ", " breathing out scholar's singularity lattice " and " the picture wolf why Ha Shiqi grows " etc.
Secondly, as shown in Fig. 4 (b), in order to meet the search needs of the more weak level of user, recommendation information under second search results pages provides from " relevant search > buys " dimension to user and corresponding description label, as recommendation information comprises: " Ha Shiqi brand shop ", " Ha Shiqi how much ", " Ha Shiqi chooses skill " etc.
Finally, as shown in Fig. 4 (c), in order to meet the search needs of the most weak level of user, recommendation information under the 3rd search results pages provides from " relevant search > trains " dimension to user and description label, as recommendation information comprises: " training Ha Shiqi feigns death ", " four months Ha Shiqi training methods ", " the good handling of Ha Shiqi " etc.
As shown in Fig. 4 (a) ~ Fig. 4 (c), also recommendation information and corresponding descriptor can be shown by card mode in the below of Search Results, the gesture horizontally slipped can be utilized between card to switch, recommend with interested search more under providing different dimensions to user, user's quick obtaining information needed from " general knowledge ", " purchase ", " training " these three dimensions can also be helped, improve search efficiency.
Please refer to Fig. 5 (a) ~ Fig. 5 (c), its the second exemplary plot showing recommendation information in search results pages provided for the embodiment of the present invention, as shown in Fig. 5 (a) ~ Fig. 5 (c), can also in the below describing text, show to recommendation information and describe the relevant picture of text, utilize the form of exemplary plot, make user more quick, get interested demand dimension accurately, enhance " relevant search > general knowledge ", " relevant search > buys ", " relevant search > trains " recommendation information and to describe between label explanatory under three demand dimensions.
Embodiment two
Please refer to Fig. 6, it for showing the second exemplary plot of recommendation information in search results pages in prior art, as shown in Figure 6, in prior art, in the first search results pages matched with query word " Liu Dehua by motorcycle ", article 10, the below of Search Results shows 8 relevant recommendation informations, as " Liu Dehua plays the part of civilian worker and rides motor photo ", " Liu De Hua Shuaizhao ", " Guo Fucheng by motorcycle " etc., the negligible amounts of recommendation information, and recommendation information static state is constant in different search results pages, mix between the recommendation information of different dimensions, user's pair all search needs relevant to " Liu Dehua by motorcycle " can not be met.
Please refer to Fig. 7 (a) ~ Fig. 7 (c), be provided in by the embodiment of the present invention in search results pages the 3rd exemplary plot showing recommendation information for it, as shown in Fig. 7 (a) ~ Fig. 7 (c), when user input query word " Liu Dehua by motorcycle ", determine that the search intention of user can be obtain Liu De China other handsome pictures, other stars picture, Liu Dehua the personal production etc. by motorcycle by motorcycle.
In the embodiment of the present invention, to each search intention in these search intentions relevant to the query word that user inputs " Liu Dehua by motorcycle ", obtain one group of recommendation information respectively, and according to the degree of correlation order from high to low of recommendation information and query word, in different search results pages, show one group of recommendation information respectively.
As shown in Fig. 7 (a), recommendation information under first search results pages provides from " the young beautiful shadow of relevant search > China " dimension to user and corresponding description label, as recommendation information comprises: " Liu De China Chariots Of Fire picture ", " Liu De China head portrait " and " locomotive picture that Liu Dehua rides through " etc.
Secondly, as shown in Fig. 7 (b), in order to meet the search needs of the more weak level of user, recommendation information under second search results pages provides from " relevant search > star by bike " dimension to user and corresponding description label, as recommendation information comprises: " Zhu Liqian is beautiful photograph by motorcycle ", " Zhou Jielun bike riding general shone ", " Ha Lin rides Halley's picture " etc.
Finally, as shown in Fig. 7 (c), in order to meet the search needs of the most weak level of user, recommendation information under the 3rd search results pages provides from " the young locomotive works of relevant search > China " dimension to user and description label, as recommendation information comprises: " Liu Dehua is film by motorcycle ", " Liu De China racing car film ", " Liu Dehua sings Chinese by motorcycle " etc.
As shown in Fig. 7 (a) ~ Fig. 7 (c), recommendation information and corresponding descriptor can be shown by card mode in the below of Search Results, the gesture horizontally slipped can be utilized between card to switch, recommend with interested search more under providing different dimensions to user, user's quick obtaining information needed from " the young beautiful shadow of China ", " star by bike ", " magnificent young locomotive works " these three dimensions can also be helped, improve search efficiency.
The embodiment of the present invention provides the device embodiment realizing each step and method in said method embodiment further.
Please refer to Fig. 8, the functional block diagram of its search recommendation apparatus provided for the embodiment of the present invention.As shown in the figure, this device comprises:
Determination module 81, for according to the query word obtained, determines at least two search intentions of user;
Acquisition module 82, for obtaining the one group recommendation information relevant to each described search intention;
Generation module 83, for generating corresponding description label for often organizing described recommendation information;
Display module 84, in the search results pages matched with described query word, carries out correspondence display by recommendation information described at least two described description labels and at least two groups.
In a concrete implementation procedure, described determination module 81, specifically for:
Obtain at least one in the co-occurrence information of the attribute information relevant to described query word, the search behavior information of being correlated with described query word and described query word;
According in the co-occurrence information of the attribute information relevant to described query word, the search behavior information of being correlated with described query word and described query word at least one, carry out cluster computing, at least two search intentions described in acquisition.
In a concrete implementation procedure, described determination module 81 for described in obtaining during at least two search intentions, specifically for:
According to user search feature, at least two the candidate's intentions obtained after cluster computing are screened, at least two search intentions described in obtaining from described at least two candidates intention.
In a concrete implementation procedure, described acquisition module 82, specifically for:
According to user search historical record, obtain the search behavior information relevant to each described search intention;
According to described search behavior information, obtain the Candidate Recommendation information relevant to each described search intention;
Described Candidate Recommendation information is screened, to obtain the one group recommendation information relevant to each described search intention.
In a concrete implementation procedure, the description label often organizing described recommendation information corresponding comprises: often organize description text corresponding to described recommendation information and often organize at least one in description picture corresponding to described recommendation information.
In a concrete implementation procedure, described display module 84, specifically for:
In the search results pages matched with described query word, utilize recommendation information described at least two cards display at least two described description labels and at least two groups, in each described card, show recommendation information described in a group of describing label and correspondence;
According to user's operating gesture for the card of current display in described search results pages, the card of current display is switched to other cards, to show description label in other cards and one group of corresponding recommendation information.
Or, described display module 84, specifically for:
According to the degree of correlation often organizing described recommendation information and described query word, sort to often organizing described recommendation information, to obtain ranking results;
According to described ranking results, in each search results pages of at least two search results pages matched with described query word, show the description label of recommendation information and correspondence described in a group.
Because each unit in the present embodiment can perform the method shown in Fig. 1, the part that the present embodiment is not described in detail, can with reference to the related description to Fig. 1.
The technical scheme of the embodiment of the present invention has following beneficial effect:
In the embodiment of the present invention, by according to the query word obtained, determine at least two search intentions of user; Thus, obtain the one group recommendation information relevant to each described search intention, and, generate corresponding description label for often organizing described recommendation information; And then, in the search results pages matched with described query word, recommendation information described at least two described description labels and at least two groups is carried out correspondence display.
The technical scheme that the embodiment of the present invention provides can provide many group recommendation informations and recommendation information carries out grouping shows to user in result of page searching, and be often organize recommendation information to add description label, so that user is according to the grouping describing label and recommendation information, required recommendation information can be obtained in time, with need in prior art manually to check one by one, then required information is filtered out and the changeless scheme of recommendation information is compared, the technical scheme that the embodiment of the present invention provides, improve the diversity of recommendation information in search results pages and from search results pages, obtain the efficiency of recommendation information.
In addition, in the embodiment of the present invention, different recommendation informations can be shown in different search results pages, solve in prior art because the restriction of display space shows a limited number of problems of the recommendation information caused, the recommendation information of various dimensions, most amount can be exported, meet the search need of user.
Those skilled in the art can be well understood to, and for convenience and simplicity of description, the system of foregoing description, the specific works process of device and unit, with reference to the corresponding process in preceding method embodiment, can not repeat them here.
In several embodiment provided by the present invention, should be understood that, disclosed system, apparatus and method, can realize by another way.Such as, device embodiment described above is only schematic, such as, the division of described unit, is only a kind of logic function and divides, and actual can have other dividing mode when realizing, such as, multiple unit or assembly can in conjunction with or another system can be integrated into, or some features can be ignored, or do not perform.Another point, shown or discussed coupling each other or direct-coupling or communication connection can be by some interfaces, and the indirect coupling of device or unit or communication connection can be electrical, machinery or other form.
The described unit illustrated as separating component or can may not be and physically separates, and the parts as unit display can be or may not be physical location, namely can be positioned at a place, or also can be distributed in multiple network element.Some or all of unit wherein can be selected according to the actual needs to realize the object of the present embodiment scheme.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, also can be that the independent physics of unit exists, also can two or more unit in a unit integrated.Above-mentioned integrated unit both can adopt the form of hardware to realize, and the form that hardware also can be adopted to add SFU software functional unit realizes.
The above-mentioned integrated unit realized with the form of SFU software functional unit, can be stored in a computer read/write memory medium.Above-mentioned SFU software functional unit is stored in a storage medium, comprising some instructions in order to make a computer installation (can be personal computer, server, or network equipment etc.) or processor (Processor) perform the part steps of method described in each embodiment of the present invention.And aforesaid storage medium comprises: USB flash disk, portable hard drive, ROM (read-only memory) (Read-OnlyMemory, ROM), random access memory (RandomAccessMemory, RAM), magnetic disc or CD etc. various can be program code stored medium.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, within the spirit and principles in the present invention all, any amendment made, equivalent replacement, improvement etc., all should be included within the scope of protection of the invention.
Claims (14)
1. search for a recommend method, it is characterized in that, described method comprises:
According to the query word obtained, determine at least two search intentions of user;
Obtain the one group recommendation information relevant to each described search intention;
Corresponding description label is generated for often organizing described recommendation information;
In the search results pages matched with described query word, recommendation information described at least two described description labels and at least two groups is carried out correspondence display.
2. method according to claim 1, is characterized in that, the described query word according to obtaining, and determines at least two search intentions of user, comprising:
Obtain at least one in the co-occurrence information of the attribute information relevant to described query word, the search behavior information of being correlated with described query word and described query word;
According in the co-occurrence information of the attribute information relevant to described query word, the search behavior information of being correlated with described query word and described query word at least one, carry out cluster computing, at least two search intentions described in acquisition.
3. method according to claim 2, is characterized in that, at least two search intentions described in acquisition, comprising:
According to user search feature, at least two the candidate's intentions obtained after cluster computing are screened, at least two search intentions described in obtaining from described at least two candidates intention.
4. according to the method in any one of claims 1 to 3, it is characterized in that, obtain the one group recommendation information relevant to each described search intention, comprising:
According to user search historical record, obtain the search behavior information relevant to each described search intention;
According to described search behavior information, obtain the Candidate Recommendation information relevant to each described search intention;
Described Candidate Recommendation information is screened, to obtain the one group recommendation information relevant to each described search intention.
5. method according to claim 1, is characterized in that, the description label often organizing described recommendation information corresponding comprises: often organize description text corresponding to described recommendation information and often organize at least one in description picture corresponding to described recommendation information.
6. method according to claim 1 or 5, is characterized in that, in the search results pages matched with described query word, recommendation information described at least two described description labels and at least two groups is carried out correspondence display, comprising:
In the search results pages matched with described query word, utilize recommendation information described at least two cards display at least two described description labels and at least two groups, in each described card, show recommendation information described in a group of describing label and correspondence;
According to user's operating gesture for the card of current display in described search results pages, the card of current display is switched to other cards, to show description label in other cards and one group of corresponding recommendation information.
7. method according to claim 1 or 5, is characterized in that, in the search results pages matched with described query word, recommendation information described at least two described description labels and at least two groups is carried out correspondence display, comprising:
According to the degree of correlation often organizing described recommendation information and described query word, sort to often organizing described recommendation information, to obtain ranking results;
According to described ranking results, in each search results pages of at least two search results pages matched with described query word, show the description label of recommendation information and correspondence described in a group.
8. search for a recommendation apparatus, it is characterized in that, described device comprises:
Determination module, for according to the query word obtained, determines at least two search intentions of user;
Acquisition module, for obtaining the one group recommendation information relevant to each described search intention;
Generation module, for generating corresponding description label for often organizing described recommendation information;
Display module, in the search results pages matched with described query word, carries out correspondence display by recommendation information described at least two described description labels and at least two groups.
9. device according to claim 8, is characterized in that, described determination module, specifically for:
Obtain at least one in the co-occurrence information of the attribute information relevant to described query word, the search behavior information of being correlated with described query word and described query word;
According in the co-occurrence information of the attribute information relevant to described query word, the search behavior information of being correlated with described query word and described query word at least one, carry out cluster computing, at least two search intentions described in acquisition.
10. device according to claim 9, is characterized in that, described determination module for described in obtaining during at least two search intentions, specifically for:
According to user search feature, at least two the candidate's intentions obtained after cluster computing are screened, at least two search intentions described in obtaining from described at least two candidates intention.
Device according to any one of 11. according to Claim 8 to 10, is characterized in that, described acquisition module, specifically for:
According to user search historical record, obtain the search behavior information relevant to each described search intention;
According to described search behavior information, obtain the Candidate Recommendation information relevant to each described search intention;
Described Candidate Recommendation information is screened, to obtain the one group recommendation information relevant to each described search intention.
12. devices according to claim 8, is characterized in that, the description label often organizing described recommendation information corresponding comprises: often organize description text corresponding to described recommendation information and often organize at least one in description picture corresponding to described recommendation information.
Device described in 13. according to Claim 8 or 12, is characterized in that, described display module, specifically for:
In the search results pages matched with described query word, utilize recommendation information described at least two cards display at least two described description labels and at least two groups, in each described card, show recommendation information described in a group of describing label and correspondence;
According to user's operating gesture for the card of current display in described search results pages, the card of current display is switched to other cards, to show description label in other cards and one group of corresponding recommendation information.
Device described in 14. according to Claim 8 or 12, is characterized in that, described display module, specifically for:
According to the degree of correlation often organizing described recommendation information and described query word, sort to often organizing described recommendation information, to obtain ranking results;
According to described ranking results, in each search results pages of at least two search results pages matched with described query word, show the description label of recommendation information and correspondence described in a group.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510828522.5A CN105404680A (en) | 2015-11-25 | 2015-11-25 | Searching recommendation method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510828522.5A CN105404680A (en) | 2015-11-25 | 2015-11-25 | Searching recommendation method and apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105404680A true CN105404680A (en) | 2016-03-16 |
Family
ID=55470169
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510828522.5A Pending CN105404680A (en) | 2015-11-25 | 2015-11-25 | Searching recommendation method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105404680A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106294618A (en) * | 2016-08-01 | 2017-01-04 | 北京百度网讯科技有限公司 | Searching method and device |
| CN106656741A (en) * | 2016-09-30 | 2017-05-10 | 北京奇虎科技有限公司 | Information push method and system |
| CN106844609A (en) * | 2017-01-17 | 2017-06-13 | 百度在线网络技术（北京）有限公司 | A kind of searching method and device |
| CN106933947A (en) * | 2017-01-20 | 2017-07-07 | 北京三快在线科技有限公司 | A kind of searching method and device, electronic equipment |
| CN107730313A (en) * | 2017-09-30 | 2018-02-23 | 口碑(上海)信息技术有限公司 | Recommend method and device in shop based on rationale for the recommendation |
| CN107807957A (en) * | 2017-09-30 | 2018-03-16 | 北京奇虎科技有限公司 | entity library generating method and device |
| CN108304432A (en) * | 2017-08-01 | 2018-07-20 | 腾讯科技（深圳）有限公司 | Information push processing method, information push processing unit and storage medium |
| CN108491540A (en) * | 2018-03-30 | 2018-09-04 | 北京百度网讯科技有限公司 | Text message method for pushing, device and intelligent terminal |
| CN109255542A (en) * | 2018-09-26 | 2019-01-22 | 中国联合网络通信集团有限公司 | A kind of data processing method and system |
| CN110196947A (en) * | 2019-05-31 | 2019-09-03 | 三角兽（北京）科技有限公司 | Method, apparatus, electronic equipment and the storage medium that recommendation information determines |
| CN110941766A (en) * | 2019-12-10 | 2020-03-31 | 北京字节跳动网络技术有限公司 | Information pushing method and device, computer equipment and storage medium |
| CN111540466A (en) * | 2020-04-19 | 2020-08-14 | 周玉娟 | Big data based intelligent medical information pushing method and big data medical cloud platform |
| CN111930954A (en) * | 2020-09-21 | 2020-11-13 | 北京三快在线科技有限公司 | Intention recognition method and device, storage medium and electronic equipment |
| CN113407828A (en) * | 2021-06-11 | 2021-09-17 | 北京搜狗科技发展有限公司 | Searching method, searching device and searching device |
| WO2022033321A1 (en) * | 2020-08-10 | 2022-02-17 | 北京字节跳动网络技术有限公司 | Search method and apparatus, and electronic device and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090019033A1 (en) * | 2007-07-11 | 2009-01-15 | Sungkyunkwan University Foundation For Corporate Collaboration | User-customized content providing device, method and recorded medium |
| CN102567408A (en) * | 2010-12-31 | 2012-07-11 | 阿里巴巴集团控股有限公司 | Method and device for recommending search keyword |
| CN103309886A (en) * | 2012-03-13 | 2013-09-18 | 阿里巴巴集团控股有限公司 | Trading-platform-based structural information searching method and device |
| CN104462325A (en) * | 2014-12-02 | 2015-03-25 | 百度在线网络技术（北京）有限公司 | Search recommendation method and device |
| CN105022840A (en) * | 2015-08-18 | 2015-11-04 | 新华网股份有限公司 | News information processing method, news recommendation method and related devices |
-
2015
- 2015-11-25 CN CN201510828522.5A patent/CN105404680A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090019033A1 (en) * | 2007-07-11 | 2009-01-15 | Sungkyunkwan University Foundation For Corporate Collaboration | User-customized content providing device, method and recorded medium |
| CN102567408A (en) * | 2010-12-31 | 2012-07-11 | 阿里巴巴集团控股有限公司 | Method and device for recommending search keyword |
| CN103309886A (en) * | 2012-03-13 | 2013-09-18 | 阿里巴巴集团控股有限公司 | Trading-platform-based structural information searching method and device |
| CN104462325A (en) * | 2014-12-02 | 2015-03-25 | 百度在线网络技术（北京）有限公司 | Search recommendation method and device |
| CN105022840A (en) * | 2015-08-18 | 2015-11-04 | 新华网股份有限公司 | News information processing method, news recommendation method and related devices |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106294618A (en) * | 2016-08-01 | 2017-01-04 | 北京百度网讯科技有限公司 | Searching method and device |
| CN106656741A (en) * | 2016-09-30 | 2017-05-10 | 北京奇虎科技有限公司 | Information push method and system |
| CN106844609A (en) * | 2017-01-17 | 2017-06-13 | 百度在线网络技术（北京）有限公司 | A kind of searching method and device |
| CN106933947A (en) * | 2017-01-20 | 2017-07-07 | 北京三快在线科技有限公司 | A kind of searching method and device, electronic equipment |
| CN108304432B (en) * | 2017-08-01 | 2021-09-07 | 腾讯科技（深圳）有限公司 | Information push processing method, information push processing device and storage medium |
| CN108304432A (en) * | 2017-08-01 | 2018-07-20 | 腾讯科技（深圳）有限公司 | Information push processing method, information push processing unit and storage medium |
| CN107730313A (en) * | 2017-09-30 | 2018-02-23 | 口碑(上海)信息技术有限公司 | Recommend method and device in shop based on rationale for the recommendation |
| CN107807957A (en) * | 2017-09-30 | 2018-03-16 | 北京奇虎科技有限公司 | entity library generating method and device |
| CN108491540A (en) * | 2018-03-30 | 2018-09-04 | 北京百度网讯科技有限公司 | Text message method for pushing, device and intelligent terminal |
| CN108491540B (en) * | 2018-03-30 | 2022-02-22 | 北京百度网讯科技有限公司 | Text information pushing method and device and intelligent terminal |
| CN109255542A (en) * | 2018-09-26 | 2019-01-22 | 中国联合网络通信集团有限公司 | A kind of data processing method and system |
| CN110196947A (en) * | 2019-05-31 | 2019-09-03 | 三角兽（北京）科技有限公司 | Method, apparatus, electronic equipment and the storage medium that recommendation information determines |
| CN110941766A (en) * | 2019-12-10 | 2020-03-31 | 北京字节跳动网络技术有限公司 | Information pushing method and device, computer equipment and storage medium |
| CN110941766B (en) * | 2019-12-10 | 2023-10-20 | 北京字节跳动网络技术有限公司 | Information pushing method, device, computer equipment and storage medium |
| CN111540466A (en) * | 2020-04-19 | 2020-08-14 | 周玉娟 | Big data based intelligent medical information pushing method and big data medical cloud platform |
| WO2022033321A1 (en) * | 2020-08-10 | 2022-02-17 | 北京字节跳动网络技术有限公司 | Search method and apparatus, and electronic device and storage medium |
| US11868389B2 (en) | 2020-08-10 | 2024-01-09 | Beijing Bytedance Network Technology Co., Ltd. | Search method and apparatus, and electronic device and storage medium |
| CN111930954B (en) * | 2020-09-21 | 2021-01-29 | 北京三快在线科技有限公司 | Intention recognition method and device, storage medium and electronic equipment |
| CN111930954A (en) * | 2020-09-21 | 2020-11-13 | 北京三快在线科技有限公司 | Intention recognition method and device, storage medium and electronic equipment |
| CN113407828A (en) * | 2021-06-11 | 2021-09-17 | 北京搜狗科技发展有限公司 | Searching method, searching device and searching device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105404680A (en) | Searching recommendation method and apparatus | |
| US11741173B2 (en) | Related notes and multi-layer search in personal and shared content | |
| CN107122400B (en) | Method, computing system and storage medium for refining query results using visual cues | |
| AU2009337678B2 (en) | Visualizing site structure and enabling site navigation for a search result or linked page | |
| US10140368B2 (en) | Method and apparatus for generating a recommendation page | |
| US10198506B2 (en) | System and method of sentiment data generation | |
| US20180121456A1 (en) | Aggregating personalized suggestions from multiple sources | |
| US8700621B1 (en) | Generating query suggestions from user generated content | |
| US20080077569A1 (en) | Integrated Search Service System and Method | |
| US20160217142A1 (en) | Method and system of acquiring semantic information, keyword expansion and keyword search thereof | |
| CN106294500B (en) | Content item pushing method, device and system | |
| CN104216942A (en) | Query suggestion templates | |
| CN106156157B (en) | Electronic book navigation system and method | |
| EP2546764A1 (en) | System and method of sentiment data use | |
| CN104699841A (en) | Method and device for providing list summary information of search results | |
| EP2889788A1 (en) | Accessing information content in a database platform using metadata | |
| CN112084405A (en) | Searching method, searching device and computer storage medium | |
| CN102930038A (en) | Combined method of search result similar items and system of the same | |
| CN105488159A (en) | Page display method and page display apparatus | |
| CN105512178A (en) | Entity recommendation method and device | |
| JP2015517711A (en) | Completing the application interface using search query keywords | |
| CN104142990A (en) | Search method and device | |
| US7743046B2 (en) | Cybernetic search with knowledge maps | |
| US20120046937A1 (en) | Semantic classification of variable data campaign information | |
| CN106971004B (en) | Search result providing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160316 |