CN105512178A - Entity recommendation method and device - Google Patents
Entity recommendation method and device Download PDFInfo
- Publication number
- CN105512178A CN105512178A CN201510828555.XA CN201510828555A CN105512178A CN 105512178 A CN105512178 A CN 105512178A CN 201510828555 A CN201510828555 A CN 201510828555A CN 105512178 A CN105512178 A CN 105512178A
- Authority
- CN
- China
- Prior art keywords
- entity
- descriptor
- recommended
- sets
- query word
- 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.)
- Granted
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
-
- 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
-
- 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
- G06F16/951—Indexing; Web crawling techniques
Abstract
The embodiment of the invention provides an entity recommendation method and device. Through obtained search words, at least two entity sets are obtained. Therefore, description information corresponding to all the entity sets is generated based on common characteristics of all entity sets and search words. Furthermore, description information corresponding to all the entity sets is displayed on a search result page matching search words. In addition, all recommendation entities contained by entity sets corresponding to clicked description information are displayed according to description information clicked by a user. Hence, the technical scheme provided by the embodiment can provide description information of all entity sets on the search result page and further display all recommendation entities included by the entity sets so that diversity of recommendation entities on the search result page and efficiency of obtaining recommendation entities on the search result page are increased.
Description
[technical field]
The present invention relates to the Internet search technology field, particularly relate to a kind of entity 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, one can be inserted recommend card in the search results pages of display, for recommending relevant to query word and that classification is single some recommended entity, user can click an entity in recommendation card, jumps to the search results pages matched with the entity of this click from current search result page.
But, the recommended entity related entities that classification is single often of current output, and correlationship between recommended entity and query word is indefinite, therefore user is needed in recommended entity, to carry out artificial screening and search required entity, cause the classification of recommended entity in prior art single, and the efficiency comparison obtaining recommended entity from search results pages is low.
[summary of the invention]
In view of this, embodiments provide a kind of entity recommend method and device, improve the diversity of recommended entity in search results pages, and improve the efficiency obtaining recommended entity from search results pages.
The one side of the embodiment of the present invention, provides a kind of entity recommend method, comprising:
According to the query word obtained, obtain at least two entity setses;
According to the common trait of each entity sets and described query word, be that each entity sets generates corresponding descriptor;
With show descriptor corresponding to each entity sets in the search results pages that described query word matches, and, according to the descriptor that user clicks, show each recommended entity that entity sets corresponding to the descriptor clicked comprises.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, and the described query word according to obtaining, obtains at least two entity setses, comprising:
According to the searching entities comprised in described query word, in the entity relevant to described searching entities, obtain at least two the highest entities of temperature; And, cluster is carried out to described at least two entities, with at least two entity setses described in obtaining; Or,
According to the searching entities comprised in described query word and search need information, obtain at least two candidate collection with described searching entities and described search need information match, according to the degree of correlation of each candidate collection and described search need information, at least two entity setses described in obtaining from least two candidate collection.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, with show descriptor corresponding to each entity sets in the search results pages that described query word matches, comprising:
Obtain the Target Photo matched with each entity sets;
In the search results pages matched with described query word, carry out descriptor corresponding to each entity sets and show with the corresponding of described Target Photo.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, obtains the Target Photo matched with each entity sets, comprising:
For each described entity sets, obtain the Target Photo matched with described entity sets; Or,
For each described entity sets, obtain at least two the candidate's pictures matched with described entity sets, picture mosaic is carried out to described at least two candidate's pictures, to generate the Target Photo matched with described entity sets.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, according to the descriptor that user clicks, shows each recommended entity that entity sets corresponding to the descriptor clicked comprises, comprising:
Each recommended entity that entity sets corresponding to the descriptor utilizing user to click comprises carries out page rendering, to represent the new page comprising each recommended entity.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, utilizes the layout of a page without columns to show each recommended entity in described new page; Described method also comprises:
The recommended entity clicked in each recommended entity shown in the described layout of a page without columns according to user, the Search Results that display matches with the recommended entity clicked below the layout of a page without columns described in described new page.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, described method also comprises:
The navigation information between clicked recommended entity and described query word is shown in the described layout of a page without columns;
Wherein, the described navigation information recommended entity that comprises descriptor corresponding to described query word, described recommended entity place entity sets and click.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, according to the descriptor that user clicks, shows each recommended entity that entity sets corresponding to the descriptor clicked comprises, comprising:
According to the descriptor that user clicks, combobox is shown below descriptor described in the search results pages matched with described query word, and, each recommended entity utilizing described combobox to show entity sets corresponding to the descriptor clicked of user to comprise.
The one side of the embodiment of the present invention, provides a kind of entity recommendation apparatus, comprising:
Entity acquisition module, for according to the query word obtained, obtains at least two entity setses;
Data obtaining module, for the common trait according to each entity sets and described query word, for each entity sets generates corresponding descriptor;
Recommend display module, for with show descriptor corresponding to each entity sets in the search results pages that described query word matches, and, according to the descriptor that user clicks, show each recommended entity that entity sets corresponding to the descriptor clicked comprises.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, described entity acquisition module, specifically for:
According to the searching entities comprised in described query word, in the entity relevant to described searching entities, obtain at least two the highest entities of temperature; And, cluster is carried out to described at least two entities, with at least two entity setses described in obtaining; Or,
According to the searching entities comprised in described query word and search need information, obtain at least two candidate collection with described searching entities and described search need information match, according to the degree of correlation of each candidate collection and described search need information, at least two entity setses described in obtaining from least two candidate collection.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, described device also comprises: image generating module, for obtaining the Target Photo matched with each entity sets;
Described recommendation display module, specifically for: in the search results pages matched with described query word, carry out descriptor corresponding to each entity sets and show with the corresponding of described Target Photo.
Aspect as above and arbitrary possible implementation, provide a kind of implementation, described image generating module further, specifically for:
For each described entity sets, obtain the Target Photo matched with described entity sets; Or,
For each described entity sets, obtain at least two the candidate's pictures matched with described entity sets, picture mosaic is carried out to described at least two candidate's pictures, to generate the Target Photo matched with described entity sets.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, described recommendation display module, specifically for:
Each recommended entity that entity sets corresponding to the descriptor utilizing user to click comprises carries out page rendering, to represent the new page comprising each recommended entity.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, utilizes the layout of a page without columns to show each recommended entity in described new page; Described recommendation display module, also for:
The recommended entity clicked in each recommended entity shown in the described layout of a page without columns according to user, the Search Results that display matches with the recommended entity clicked below the layout of a page without columns described in described new page.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, described recommendation display module, also for: in the described layout of a page without columns, show the navigation information between clicked recommended entity and described query word;
Wherein, the described navigation information recommended entity that comprises descriptor corresponding to described query word, described recommended entity place entity sets and click.
Aspect as above and arbitrary possible implementation, provide a kind of implementation further, described recommendation display module, specifically for:
According to the descriptor that user clicks, combobox is shown below descriptor described in the search results pages matched with described query word, and, each recommended entity utilizing described combobox to show entity sets corresponding to the descriptor clicked of user to comprise.
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 the descriptor of multiple entity sets in search results pages, and can each recommended entity of comprising of display entity set further, compared with the technical scheme of recommended entity that classification is single can only be provided in prior art, the technical scheme that the embodiment of the present invention provides can export multi-class, that quantity is many recommended entity, thus improves the diversity of recommended entity in search results pages.And, with in prior art between recommended entity with query word compared with the indefinite technical scheme of recommendation relation, by exporting descriptor corresponding to entity sets in the embodiment of the present invention, the recommendation relation between query word and recommended entity can be exported, help user to obtain required entity fast, improve the efficiency obtaining recommended entity from search results pages.
[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 entity recommend method that the embodiment of the present invention provides;
Fig. 2 (a) ~ Fig. 2 (h) is at least two candidate's pictures that the embodiment of the present invention provides array mode exemplary plot when generating Target Photo;
Fig. 3 is the first exemplary plot of recommended entity in search results pages in prior art;
Fig. 4 (a) ~ Fig. 4 (c) is the first exemplary plot of recommended entity in search results pages that the embodiment of the present invention provides;
Fig. 5 (a) ~ Fig. 5 (b) is the second exemplary plot of recommended entity in search results pages that the embodiment of the present invention provides;
Fig. 6 is the second exemplary plot of recommended entity in search results pages in prior art;
Fig. 7 (a) ~ Fig. 7 (c) is the 3rd exemplary plot of recommended entity in search results pages that the embodiment of the present invention provides;
Fig. 8 (a) ~ Fig. 8 (b) is the 4th exemplary plot of recommended entity in search results pages that the embodiment of the present invention provides;
Fig. 9 is the functional block diagram of the entity 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 entity recommend method, please refer to Fig. 1, the schematic flow sheet of its entity recommend method provided for the embodiment of the present invention, and as shown in the figure, the method comprises the following steps:
S101, according to the query word obtained, obtains at least two entity setses.
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.In the search results pages generated, need to provide various dimensions, multi-class recommended entity to user simultaneously.In order to realize providing various dimensions, multi-class recommended entity to user, in the embodiment of the present invention, need, first according to the query word obtained, to obtain at least two entity setses.
Illustrate, in the embodiment of the present invention, according to the query word obtained, the method obtaining at least two entity setses can include but not limited to following two kinds:
The first: according to the searching entities comprised in described query word, in the entity relevant to described searching entities, obtain at least two the highest entities of temperature; And, cluster is carried out to described at least two entities, with at least two entity setses described in obtaining.
Be understandable that, if only comprise searching entities in query word, or query word is searching entities, the search need information cannot determining user according to query word is described, therefore the search need of user is indefinite, then from all entities relevant to described searching entities, at least two entities that temperature is the highest can be obtained.
Further, at least two entities that clustering algorithm can be utilized the highest to temperature carry out cluster computing, and described at least two entities are divided at least two entity setses, thus realize, according to the query word obtained, obtaining at least two entity setses.
The second: according to the searching entities comprised in described query word and search need information, obtain at least two candidate collection with described searching entities and described search need information match, according to the degree of correlation of each candidate collection and described search need information, at least two entity setses described in obtaining from least two candidate collection.
Be understandable that, if comprise searching entities and search need information in query word, the search need information can determining user according to query word is described, therefore the search need of user is clear and definite, then according to searching entities and search need information, at least two candidate collection the highest with search need information correlation can be obtained.
In a concrete implementation procedure, can according to the degree of correlation of each candidate collection and search need information, and according to the descending order of the degree of correlation, each candidate collection is sorted, to obtain ranking results, last from ranking results, obtain at least two the highest candidate collection of sequence, using as described at least two entity setses.
Such as, when the query word of user's input is " Ha Shiqi ", the search need of user is indefinite, in order to excite the potential search need of user, can obtain and " Ha Shiqi " some entity setses that the degree of correlation is the highest, temperature is the highest, as " IQ the same as Ha Shiqi allows people catch anxious dog dog ", " dog of looking like wolf the same as Ha Shiqi ", " nothing of personality docility the same as Ha Shiqi attacks medium-sized dog ".
Again such as, when the query word of user's input is " Ha Shiqi supports well ", the search need of user is very clear and definite, namely interested in the feeding manner of Ha Shiqi and other relevant pets, the some entity setses the highest with the search need information correlation of user can be obtained, as " the medium-sized dog of more difficult raising the same as Ha Shiqi ", " being applicable to domestic small-sized pet dog on the contrary with Ha Shiqi ", " pet of the obedient good training of loyalty the same as Ha Shiqi ".
In this method, the different search needs of query word user inputted divide, by match with search need, the interested entity of user divides into groups in order according to classification, form different entity setses, finally these entity setses are recommended user, for meeting the different search need of user, wherein, for the degree of correlation of search need between the query word that the sequence of each entity sets can input according to entity sets and user, the entity sets the highest with the search need degree of correlation of user, comes the most forward position.
S102, according to the common trait of each entity sets and described query word, is that each entity sets generates corresponding descriptor.
Concrete, in the embodiment of the present invention, after acquisition at least two entity setses, can extract the common trait of each entity sets and query word, then according to the common trait of each entity sets with query word, be the descriptor of each entity sets generation correspondence.
It should be noted that, when generating descriptor, need to build in descriptor and the relation embodying and exist between query word or search intention information.Such as, query word is " Beethovan ", recommended entity is comprised in entity sets, as " Huo Jin " and " Vincent van gogh " etc., the common trait of this entity sets and query word is " broken in body but firm in spirit famous person ", then the descriptor that this entity sets is corresponding can be " with the famous person that Beethovan is equally broken in body but firm in spirit ".
In addition, the descriptor that entity sets is corresponding not only can embody the common trait between entity sets and search word, also embody the reason of recommending this entity sets to user, each recommended entity user being understood better comprise in entity sets, and the relation understood better between the entity sets of recommendation and the query word of user search, or the relation between entity sets and the search intention of user, thus enable user select interested or required entity fast, and then improve the efficiency that user obtains required recommended entity.
S103, with show descriptor corresponding to each entity sets in the search results pages that described query word matches.
Concrete, in the embodiment of the present invention, after generating corresponding descriptor for each entity sets, can show and in the search results pages that described query word matches, show descriptor corresponding to each entity sets.Such as, can in the search results pages matched with described query word, the centre position of any two Search Results, shows the descriptor that each entity sets is corresponding.
In a concrete implementation procedure, also can obtain the Target Photo matched with each entity sets; Then, in the search results pages matched with described query word, carry out descriptor corresponding to each entity sets and show with the corresponding of described Target Photo.
Such as, in the search results pages matched with query word, level shows descriptor corresponding to each entity sets, and the lower position of each descriptor in display, the Target Photo that the display entity sets corresponding with this descriptor matches.The descriptor corresponding by each entity sets shows with the corresponding of described Target Photo, descriptor corresponding for each entity sets can be associated with corresponding Target Photo, makes user directly can perceive the entity sets of recommendation by Target Photo.
Illustrate, in the embodiment of the present invention, the method obtaining the Target Photo matched with each entity sets can include but not limited to following two kinds:
The first: for each described entity sets, obtain the Target Photo matched with described entity sets.
The second: for each described entity sets, obtains at least two the candidate's pictures matched with described entity sets, carries out picture mosaic, to generate the Target Photo matched with described entity sets to described at least two candidate's pictures.
In a concrete implementation procedure, can be polymerized with many figure that entity sets matches, as being the polymerization of three candidate's pictures, four candidate's pictures or five candidate's pictures, it can be even the polymerization of the picture of more how representative single entity.Utilize many pictures to be polymerized and obtain Target Photo, the picture of more recommended entity in this entity sets can be transmitted, the recommendation perception of user to entity sets can also be strengthened.
Such as, when scheming the Target Photo of polymerization pattern for entity sets generation, can select in this entity sets, the picture in several recommended entity front corresponding to each recommended entity more, then arrangement polymerization be carried out to these pictures.Or, again such as, also can select the picture that can reflect the search need representated by this entity sets in entity sets, and in the feature such as vision, style, color of picture, similar picture is polymerized, generate Target Photo.
Please refer to Fig. 2 (a) ~ Fig. 2 (h), array mode exemplary plot during at least two candidate's pictures generation Target Photos that it provides for the embodiment of the present invention, as shown in Fig. 2 (a) ~ Fig. 2 (f), at least two candidate's pictures can be multiple candidate's picture combination producing Target Photos.As shown in Fig. 2 (g), also at least two candidate's pictures can be carried out shade superposition and generate Target Photo.As shown in Fig. 2 (h), also at least two candidate's pictures can be carried out 3D combination producing Target Photo.It should be noted that, the mode of above-mentioned utilization at least two candidate's pictures generation Target Photos is only and illustrates, the embodiment of the present invention is not particularly limited this generating mode.
S104, according to the descriptor that user clicks, shows each recommended entity that entity sets corresponding to the descriptor clicked comprises.
Concrete, in the embodiment of the present invention, owing to showing and showing descriptor corresponding to each entity sets in the search results pages that described query word matches, therefore, if there is the required entity sets understood of user in each entity sets, then user in the descriptor that each entity sets is corresponding, can utilize gesture to slide left or the entity sets that slides to the right, thus can browse to the descriptor of each entity sets.When user is interested in certain entity sets, user clicks the descriptor of this entity sets, like this, the descriptor can clicked according to user, each recommended entity that entity sets corresponding to the descriptor clicked of further display comprises, like this, each recommended entity that this entity sets comprises is supplied to user.
Illustrate, in the embodiment of the present invention, according to the descriptor that user clicks, the method showing each recommended entity that entity sets corresponding to the descriptor clicked comprises can include but not limited to following two kinds:
The first: each recommended entity that entity sets corresponding to the descriptor utilizing user to click comprises carries out page rendering, to represent the new page comprising each recommended entity.
In a concrete implementation procedure, can in described new page, the layout of a page without columns be utilized to show each recommended entity; Then, the recommended entity clicked in each recommended entity that can show in the described layout of a page without columns according to user, the Search Results that display matches with the recommended entity clicked below the layout of a page without columns described in described new page.
Be understandable that, after user selects a descriptor in the descriptor that each entity sets is corresponding, entity sets that can be corresponding according to clicked descriptor, carry out once new search, and show a layout of a page without columns at the tip position of new page, this layout of a page without columns can be fixed on the top of search results pages, like this, and all recommended entity that user can comprise in entity sets corresponding to fast browsing is clicked in the layout of a page without columns descriptor.
User can click required recommended entity further, according to the recommended entity that user clicks, Asynchronous loading technology can be passed through, automatically the Search Results matched with clicked recommended entity is rendered below the layout of a page without columns in new page, wherein, click recommended entity, rendering the Search Results matched with clicked recommended entity is all carry out in described new page, do not need to jump to other pages, therefore without the need to the switching back and forth between the page, thus required recommended entity can be clicked easily, and obtain the Search Results matched with the recommended entity clicked fast, substantially increase the efficiency obtaining multiple recommended entity, reduce search time.
Optionally, the navigation information between clicked recommended entity and described query word can also be shown in the described layout of a page without columns; Wherein, the described navigation information recommended entity that comprises descriptor corresponding to described query word, described recommended entity place entity sets and click.
Be understandable that, the described layout of a page without columns can be made up of two parts: navigation information and each recommended entity.Navigation information may be displayed on above each recommended entity in the layout of a page without columns, be convenient to user understand fast by query word to click recommended entity recommendation logic, be convenient to the recommended entity that user's quick position is clicked.
Such as, described in described navigation information, query word is positioned at the left side, and the descriptor that described recommended entity place entity sets is corresponding is positioned at centre, and the recommended entity clicked is positioned at the right.Such as, navigation information can be " Beethovan > broken in body but firm in spirit famous person > Vincent van gogh the same as Beethovan ", wherein, " Beethovan " is the query word that user inputs, " broken in body but firm in spirit famous person the same as Beethovan " is the descriptor that entity sets that user clicks in each entity sets is corresponding, the recommendation information clicked further in " Vincent van gogh " each recommendation information that to be user comprise at this entity sets.
In addition, also information abstraction can be carried out to the descriptor of entity sets, using the information of simplifying after refinement as the descriptor in navigation information, if navigation information also can be " the broken in body but firm in spirit famous person > Vincent van gogh that Beethovan > is similar ", thus decrease information redundancy, improve the efficiency of obtaining information.
In this method, when showing each recommended entity in the layout of a page without columns, horizontal direction can show the title of each recommended entity and picture corresponding to each recommended entity.Wherein, can according to the degree of correlation of each recommended entity and search need information, sort to each recommended entity, the recommended entity that the degree of correlation is higher more comes forward position, and user can slide left or slide to the right and browse each recommended entity in the layout of a page without columns.In addition, also can return by the above-mentioned new page comprising each recommended entity the search results pages matched with query word, and select other entity sets further.
The second: the descriptor clicked according to user, combobox is shown below descriptor described in the search results pages matched with described query word, and, each recommended entity utilizing described combobox to show entity sets corresponding to the descriptor clicked of user to comprise.
In a concrete implementation procedure, when selecting interested entity sets in the descriptor that user is corresponding according to each entity sets, slip gesture left or slip gesture to the right can be utilized to move each entity sets, then each entity sets is browsed to, when user clicks descriptor corresponding to certain entity sets interested, combobox can be shown below the descriptor corresponding with each entity sets in the search results pages that query word matches, and then in combobox, show each recommended entity comprised in entity sets corresponding to descriptor that user clicks, such as, 12 ~ 20 recommended entity can be comprised in this entity sets, can sort to each recommended entity according to the degree of correlation of recommended entity and search need, the recommended entity that the degree of correlation is higher more comes forward position.
Further, in combobox, user also can utilize slip gesture left or slip gesture to the right to move each recommended entity, to browse in this entity sets all recommended entity comprised, make user can browse to the entity sets of each dimension in search results pages, and multiple recommended entity in entity sets, improve the efficiency obtaining recommended entity.
Embodiment two
(the comprehensive expression of person of classicism music style as user input query word " Beethovan ", impoverished, broken in body but firm in spirit music artist), when main search demand is met, user may also comprise by other search needs interested: broken in body but firm in spirit famous person the same as Beethovan impoverished artist the same as Beethovan and Beethovan have the musician etc. of the same creation style.
Please refer to Fig. 3, it is the first exemplary plot of recommended entity in search results pages in prior art, as shown in the figure, in conventional solution, recommended entity recommends " Mozart " around Beethovan, " Chopin ", " Shu Baite ", some entities such as " Bach ", these are all musicians well-known in the world, explanatory weak to recommended entity of single and " related person " this descriptor of the dimension of recommended entity, for user " impoverished artist the same as Beethovan ", " broken in body but firm in spirit famous person the same as Beethovan " these two search needs can not meet.
Please refer to Fig. 4 (a) ~ Fig. 4 (c), its first exemplary plot of recommended entity in search results pages provided for the embodiment of the present invention.As shown in Fig. 4 (a), by " Hayden ", " Mozart ", " Chopin ", entities such as " Bach " is summarized in an entity sets, extract common trait and generate descriptor and " have the musician of the same creation style with Beethovan ", compared with conventional solution, add " van gogh, Huo Jin, Shi Tiesheng, Ah bright " etc. composition entity sets, and be this entity sets increase descriptor " broken in body but firm in spirit famous person the same as Beethovan ", and add " Andersen, Xu Beihong, Michelangelo, Shu Baite " etc. composition entity sets, and be this entity sets increase descriptor " impoverished artist the same as Beethovan ", and, for these three entity setses mix the picture after many figure polymerizations respectively, as shown in Fig. 4 (a), combine there being most the picture of three of representative entities in each entity sets, compared with conventional solution, the technical scheme that the embodiment of the present invention provides has accomplished the upgrading recommending to entity sets recommendation from entity.
As shown in Fig. 4 (b), when user to other to have with Beethovan the musician of the same creation style interested time, the descriptor clicking entity sets " has the musician of the same creation style with Beethovan ", then new page can be shown, and the layout of a page without columns is shown in new page, the all recommended entity comprised are shown in this entity sets, as Hayden, Mozart, Chopin, Bach etc. in the layout of a page without columns.User by selecting clicks interested recommended entity, and current page is by the Search Results of this recommended entity of display.
When user wants can return former search results pages when continuing to browse other entity setses, a beans-and bullets shooter of going forward side by side hits descriptor " broken in body but firm in spirit famous person the same as Beethovan " or " impoverished artist the same as Beethovan ", as shown in Fig. 4 (c), the new page of the recommended entity comprised in entity sets corresponding to display " broken in body but firm in spirit famous person the same as Beethovan " can be jumped to again by former search results pages.
Please refer to Fig. 5 (a) ~ Fig. 5 (b), its second exemplary plot of recommended entity in search results pages provided for the embodiment of the present invention.As shown in Fig. 5 (a), if when user is interested in " having the musician of the same creation style with Beethovan ", click this descriptor, combobox is shown below each solid model shown in the search results pages relevant to query word, the each recommended entity in entity sets corresponding to this descriptor is shown, as the recommended entity such as " Mozart ", " Chopin ", " Hayden " and " Bach " in combobox.In addition, as shown in Fig. 5 (a), user can utilize slip gesture left or slip gesture to the right to browse to all recommended entity in each recommended entity.As shown in Fig. 5 (b), if when user is interested in " broken in body but firm in spirit famous person the same as Beethovan ", click this descriptor, combobox is shown below each solid model shown in the search results pages relevant to query word, the each recommended entity in entity sets corresponding to this descriptor is shown, as the recommended entity such as " van gogh ", " Huo Jin ", " Shi Tiesheng " and " Ah bright " in combobox.
Embodiment three
(the film of pursuing a goal with determination that Tom's hanks is acted the leading role when user input query word " Ah sweet's main story ", nineteen ninety-five obtains Oscar 6 Grand Prixs), when main search demand is met, user may also comprise by other search needs interested: other obtain other works of the cinematographic work of Oscar, classical film of pursuing a goal with determination, the protagonist of Tom's hanks.
Please refer to Fig. 6, it is the second exemplary plot of recommended entity in search results pages in prior art, as shown in the figure, in conventional solution, recommended entity recommends some entities such as " The Shawshank Redemption ", " Rudy ", " succeeding people " around Ah sweet's formal dress, these are all obtain the famous movies of Oscar, and explanatory weak to recommended entity of single and " associated recommendation " this descriptor of the dimension of recommended entity, other search needs for user can not meet.
Please refer to Fig. 7 (a) ~ Fig. 7 (c), its 3rd exemplary plot of recommended entity in search results pages provided for the embodiment of the present invention.As shown in Fig. 7 (a), the entity such as " bird people ", " leaping madhouse ", " Legends of the Fall ", " the magical drift of juvenile group " is summarized in an entity sets, extracts common trait and generate descriptor " the Oscar award-winning work at high box office the same as Ah sweet's main story ".By the entity sets that " The Shawshank Redemption ", " when happiness is knocked at the door ", " never giving up ", " Les Choristes " etc. form, and it is this entity sets increase descriptor " film of pursuing a goal with determination that classics the same as Ah sweet's main story must be seen ".In addition, the entity sets of the composition such as " mermaid ", " Philips captain ", " The Philadelphia Story " and " Cast Away " can also be increased, and " be all the popular film that Tom's hanks is acted the leading role " for this entity sets increases descriptor.
As shown in Fig. 7 (a), for these three entity setses mix the picture after many figure polymerizations respectively, combine there being most the picture of five of representative entities in each entity sets, compared with conventional solution, the technical scheme that the embodiment of the present invention provides has accomplished the upgrading recommending to entity sets recommendation from entity.
As shown in Fig. 7 (b), when user to other classics pursue a goal with determination film interested time, click the descriptor " film of pursuing a goal with determination that classics the same as Ah sweet's main story must be seen " of entity sets, then new page can be shown, and the layout of a page without columns is shown in new page, the all recommended entity comprised are shown in this entity sets, as " The Shawshank Redemption ", " when happiness is knocked at the door ", " never giving up ", " Les Choristes " etc. in the layout of a page without columns.User by selecting clicks interested recommended entity, and current page is by the Search Results of this recommended entity of display.
When user wants can return former search results pages when continuing to browse other entity setses, a beans-and bullets shooter of going forward side by side hits descriptor " the Oscar award-winning work at high box office the same as Ah sweet's main story ", as shown in Fig. 7 (c), the new page of the recommended entity comprised in entity sets corresponding to display " the Oscar award-winning work at high box office the same as Ah sweet's main story " can be jumped to again by former search results pages.
Please refer to Fig. 8 (a) ~ Fig. 8 (b), its 4th exemplary plot of recommended entity in search results pages provided for the embodiment of the present invention.As shown in Fig. 8 (a), if when user is interested in " film of pursuing a goal with determination that classics the same as Ah sweet's main story must be seen ", click this descriptor, combobox is shown below each solid model shown in the search results pages relevant to query word, the each recommended entity in entity sets corresponding to this descriptor is shown, as the recommended entity such as " never compromising ", " Like Mike ", " having qualified successors " and " weakness " in combobox.As shown in Fig. 8 (b), if when user is interested in " the Oscar award-winning work at high box office the same as Ah sweet's main story ", click this descriptor, combobox is shown below each solid model shown in the search results pages relevant to query word, the each recommended entity in entity sets corresponding to this descriptor is shown, as the recommended entity such as " bird people ", " stealing dream space ", " the magical drift of juvenile group ", " imitating game " in combobox.
The embodiment of the present invention provides the device embodiment realizing each step and method in said method embodiment further.
Please refer to Fig. 9, the functional block diagram of its entity recommendation apparatus provided for the embodiment of the present invention.As shown in the figure, this device comprises:
Entity acquisition module 91, for according to the query word obtained, obtains at least two entity setses;
Data obtaining module 92, for the common trait according to each entity sets and described query word, for each entity sets generates corresponding descriptor;
Recommend display module 93, for with show descriptor corresponding to each entity sets in the search results pages that described query word matches, and, according to the descriptor that user clicks, show each recommended entity that entity sets corresponding to the descriptor clicked comprises.
In a concrete implementation procedure, described entity acquisition module 91, specifically for:
According to the searching entities comprised in described query word, in the entity relevant to described searching entities, obtain at least two the highest entities of temperature; And, cluster is carried out to described at least two entities, with at least two entity setses described in obtaining; Or,
According to the searching entities comprised in described query word and search need information, obtain at least two candidate collection with described searching entities and described search need information match, according to the degree of correlation of each candidate collection and described search need information, at least two entity setses described in obtaining from least two candidate collection.
In a concrete implementation procedure, described device can also comprise: image generating module 94, for obtaining the Target Photo matched with each entity sets;
Described recommendation display module 93, specifically for: in the search results pages matched with described query word, carry out descriptor corresponding to each entity sets and show with the corresponding of described Target Photo.
In a concrete implementation procedure, described image generating module 94, specifically for:
For each described entity sets, obtain the Target Photo matched with described entity sets; Or,
For each described entity sets, obtain at least two the candidate's pictures matched with described entity sets, picture mosaic is carried out to described at least two candidate's pictures, to generate the Target Photo matched with described entity sets.
In a concrete implementation procedure, described recommendation display module 93, specifically for:
Each recommended entity that entity sets corresponding to the descriptor utilizing user to click comprises carries out page rendering, to represent the new page comprising each recommended entity.
In a concrete implementation procedure, the layout of a page without columns in described new page, is utilized to show each recommended entity; Described recommendation display module 93, also for:
The recommended entity clicked in each recommended entity shown in the described layout of a page without columns according to user, the Search Results that display matches with the recommended entity clicked below the layout of a page without columns described in described new page.
In a concrete implementation procedure, described recommendation display module 93, also for: in the described layout of a page without columns, show the navigation information between clicked recommended entity and described query word;
Wherein, the described navigation information recommended entity that comprises descriptor corresponding to described query word, described recommended entity place entity sets and click.
Or, in a concrete implementation procedure, described recommendation display module 93, specifically for:
According to the descriptor that user clicks, combobox is shown below descriptor described in the search results pages matched with described query word, and, each recommended entity utilizing described combobox to show entity sets corresponding to the descriptor clicked of user to comprise.
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, obtain at least two entity setses; Thus, according to the common trait of each entity sets and described query word, be that each entity sets generates corresponding descriptor; And then, with show descriptor corresponding to each entity sets in the search results pages that described query word matches, and, according to the descriptor that user clicks, show each recommended entity that entity sets corresponding to the descriptor clicked comprises.
The technical scheme that the embodiment of the present invention provides can provide the descriptor of multiple entity sets in search results pages, and can each recommended entity of comprising of display entity set further, compared with the technical scheme of recommended entity that classification is single can only be provided in prior art, the technical scheme that the embodiment of the present invention provides can export multi-class, that quantity is many recommended entity, thus improves the diversity of recommended entity in search results pages.And, with in prior art between recommended entity with query word compared with the indefinite technical scheme of recommendation relation, by exporting descriptor corresponding to entity sets in the embodiment of the present invention, the recommendation relation between query word and recommended entity can be exported, help user to obtain required entity fast, improve the efficiency obtaining recommended entity from search results pages.
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 (16)
1. an entity recommend method, is characterized in that, described method comprises:
According to the query word obtained, obtain at least two entity setses;
According to the common trait of each entity sets and described query word, be that each entity sets generates corresponding descriptor;
With show descriptor corresponding to each entity sets in the search results pages that described query word matches, and, according to the descriptor that user clicks, show each recommended entity that entity sets corresponding to the descriptor clicked comprises.
2. method according to claim 1, is characterized in that, the described query word according to obtaining, obtains at least two entity setses, comprising:
According to the searching entities comprised in described query word, in the entity relevant to described searching entities, obtain at least two the highest entities of temperature; And, cluster is carried out to described at least two entities, with at least two entity setses described in obtaining; Or,
According to the searching entities comprised in described query word and search need information, obtain at least two candidate collection with described searching entities and described search need information match, according to the degree of correlation of each candidate collection and described search need information, at least two entity setses described in obtaining from least two candidate collection.
3. method according to claim 1, is characterized in that, with show descriptor corresponding to each entity sets in the search results pages that described query word matches, comprising:
Obtain the Target Photo matched with each entity sets;
In the search results pages matched with described query word, carry out descriptor corresponding to each entity sets and show with the corresponding of described Target Photo.
4. method according to claim 3, is characterized in that, obtains the Target Photo matched with each entity sets, comprising:
For each described entity sets, obtain the Target Photo matched with described entity sets; Or,
For each described entity sets, obtain at least two the candidate's pictures matched with described entity sets, picture mosaic is carried out to described at least two candidate's pictures, to generate the Target Photo matched with described entity sets.
5. method according to claim 1, is characterized in that, according to the descriptor that user clicks, shows each recommended entity that entity sets corresponding to the descriptor clicked comprises, comprising:
Each recommended entity that entity sets corresponding to the descriptor utilizing user to click comprises carries out page rendering, to represent the new page comprising each recommended entity.
6. method according to claim 5, is characterized in that, utilizes the layout of a page without columns to show each recommended entity in described new page; Described method also comprises:
The recommended entity clicked in each recommended entity shown in the described layout of a page without columns according to user, the Search Results that display matches with the recommended entity clicked below the layout of a page without columns described in described new page.
7. method according to claim 6, is characterized in that, described method also comprises:
The navigation information between clicked recommended entity and described query word is shown in the described layout of a page without columns;
Wherein, the described navigation information recommended entity that comprises descriptor corresponding to described query word, described recommended entity place entity sets and click.
8. method according to claim 1, is characterized in that, according to the descriptor that user clicks, shows each recommended entity that entity sets corresponding to the descriptor clicked comprises, comprising:
According to the descriptor that user clicks, combobox is shown below descriptor described in the search results pages matched with described query word, and, each recommended entity utilizing described combobox to show entity sets corresponding to the descriptor clicked of user to comprise.
9. an entity recommendation apparatus, is characterized in that, described device comprises:
Entity acquisition module, for according to the query word obtained, obtains at least two entity setses;
Data obtaining module, for the common trait according to each entity sets and described query word, for each entity sets generates corresponding descriptor;
Recommend display module, for with show descriptor corresponding to each entity sets in the search results pages that described query word matches, and, according to the descriptor that user clicks, show each recommended entity that entity sets corresponding to the descriptor clicked comprises.
10. device according to claim 9, is characterized in that, described entity acquisition module, specifically for:
According to the searching entities comprised in described query word, in the entity relevant to described searching entities, obtain at least two the highest entities of temperature; And, cluster is carried out to described at least two entities, with at least two entity setses described in obtaining; Or,
According to the searching entities comprised in described query word and search need information, obtain at least two candidate collection with described searching entities and described search need information match, according to the degree of correlation of each candidate collection and described search need information, at least two entity setses described in obtaining from least two candidate collection.
11. devices according to claim 9, is characterized in that,
Described device also comprises: image generating module, for obtaining the Target Photo matched with each entity sets;
Described recommendation display module, specifically for: in the search results pages matched with described query word, carry out descriptor corresponding to each entity sets and show with the corresponding of described Target Photo.
12. devices according to claim 11, is characterized in that, described image generating module, specifically for:
For each described entity sets, obtain the Target Photo matched with described entity sets; Or,
For each described entity sets, obtain at least two the candidate's pictures matched with described entity sets, picture mosaic is carried out to described at least two candidate's pictures, to generate the Target Photo matched with described entity sets.
13. devices according to claim 9, is characterized in that, described recommendation display module, specifically for:
Each recommended entity that entity sets corresponding to the descriptor utilizing user to click comprises carries out page rendering, to represent the new page comprising each recommended entity.
14. devices according to claim 13, is characterized in that, utilize the layout of a page without columns to show each recommended entity in described new page; Described recommendation display module, also for:
The recommended entity clicked in each recommended entity shown in the described layout of a page without columns according to user, the Search Results that display matches with the recommended entity clicked below the layout of a page without columns described in described new page.
15. devices according to claim 14, is characterized in that, described recommendation display module, also for: in the described layout of a page without columns, show the navigation information between clicked recommended entity and described query word;
Wherein, the described navigation information recommended entity that comprises descriptor corresponding to described query word, described recommended entity place entity sets and click.
16. devices according to claim 9, is characterized in that, described recommendation display module, specifically for:
According to the descriptor that user clicks, combobox is shown below descriptor described in the search results pages matched with described query word, and, each recommended entity utilizing described combobox to show entity sets corresponding to the descriptor clicked of user to comprise.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510828555.XA CN105512178B (en) | 2015-11-25 | 2015-11-25 | A kind of entity recommended method and device |
| PCT/CN2016/089649 WO2017088497A1 (en) | 2015-11-25 | 2016-07-11 | Entity recommendation method, device, apparatus, and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510828555.XA CN105512178B (en) | 2015-11-25 | 2015-11-25 | A kind of entity recommended method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105512178A true CN105512178A (en) | 2016-04-20 |
| CN105512178B CN105512178B (en) | 2019-02-05 |
Family
ID=55720160
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510828555.XA Active CN105512178B (en) | 2015-11-25 | 2015-11-25 | A kind of entity recommended method and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN105512178B (en) |
| WO (1) | WO2017088497A1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017088497A1 (en) * | 2015-11-25 | 2017-06-01 | 百度在线网络技术（北京）有限公司 | Entity recommendation method, device, apparatus, and computer storage medium |
| 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 |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110929139B (en) * | 2018-09-04 | 2023-12-29 | 阿里巴巴集团控股有限公司 | Search recommendation method and device |
| CN111680230B (en) * | 2020-05-25 | 2023-04-18 | 北京百度网讯科技有限公司 | Display method and device of search result page, electronic equipment and storage medium |
| CN111797257B (en) * | 2020-06-29 | 2024-02-23 | 京东方科技集团股份有限公司 | Picture recommendation method and related equipment based on word vector |
| CN114064930A (en) * | 2021-11-29 | 2022-02-18 | 北京字节跳动网络技术有限公司 | Data display method and device, computer equipment and storage medium |
| CN114722823B (en) * | 2022-03-24 | 2023-04-14 | 华中科技大学 | Method and device for constructing aviation knowledge graph and computer readable medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102279869A (en) * | 2010-06-09 | 2011-12-14 | 微软公司 | Navigating relationships among entities |
| CN104281699A (en) * | 2014-10-15 | 2015-01-14 | 百度在线网络技术（北京）有限公司 | Search recommending method and device |
| CN104778255A (en) * | 2015-04-20 | 2015-07-15 | 百度在线网络技术（北京）有限公司 | Method and device for recommending searching results |
| US20150234814A1 (en) * | 2000-02-17 | 2015-08-20 | Audible Magic Corporation | Method and apparatus for identifying media content |
| CN104969212A (en) * | 2013-01-30 | 2015-10-07 | 奎克西公司 | Performing application search based on entities |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101364239B (en) * | 2008-10-13 | 2011-06-29 | 中国科学院计算技术研究所 | Method for auto constructing classified catalogue and relevant system |
| CN102609433B (en) * | 2011-12-16 | 2013-11-20 | 北京大学 | Method and system for recommending query based on user log |
| US20150234813A1 (en) * | 2013-11-04 | 2015-08-20 | Michael R. Knapp | Systems and Methods for Categorizing and Accessing Information Databases and for Displaying Query Results |
| CN105512178B (en) * | 2015-11-25 | 2019-02-05 | 百度在线网络技术（北京）有限公司 | A kind of entity recommended method and device |
-
2015
- 2015-11-25 CN CN201510828555.XA patent/CN105512178B/en active Active
-
2016
- 2016-07-11 WO PCT/CN2016/089649 patent/WO2017088497A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150234814A1 (en) * | 2000-02-17 | 2015-08-20 | Audible Magic Corporation | Method and apparatus for identifying media content |
| CN102279869A (en) * | 2010-06-09 | 2011-12-14 | 微软公司 | Navigating relationships among entities |
| CN104969212A (en) * | 2013-01-30 | 2015-10-07 | 奎克西公司 | Performing application search based on entities |
| CN104281699A (en) * | 2014-10-15 | 2015-01-14 | 百度在线网络技术（北京）有限公司 | Search recommending method and device |
| CN104778255A (en) * | 2015-04-20 | 2015-07-15 | 百度在线网络技术（北京）有限公司 | Method and device for recommending searching results |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017088497A1 (en) * | 2015-11-25 | 2017-06-01 | 百度在线网络技术（北京）有限公司 | Entity recommendation method, device, apparatus, and computer storage medium |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105512178B (en) | 2019-02-05 |
| WO2017088497A1 (en) | 2017-06-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105512178A (en) | Entity recommendation method and device | |
| US11720633B2 (en) | Aggregating personalized suggestions from multiple sources | |
| KR101778679B1 (en) | Method and system for classifying data consisting of multiple attribues represented by sequences of text words or symbols using deep learning | |
| US10175860B2 (en) | Search intent preview, disambiguation, and refinement | |
| CN107103016B (en) | Method for matching image and content based on keyword representation | |
| US20140075393A1 (en) | Gesture-Based Search Queries | |
| CN101884042B (en) | Using reputation measures to improve search relevance | |
| US20080077569A1 (en) | Integrated Search Service System and Method | |
| CN105095440A (en) | Search recommendation method and device | |
| CN105404680A (en) | Searching recommendation method and apparatus | |
| CN107391561B (en) | Advertisement processing method in content source page, server and computer readable medium | |
| CN112446727B (en) | Advertisement triggering method, device, equipment and computer readable storage medium | |
| CN112052397B (en) | User characteristic generation method and device, electronic equipment and storage medium | |
| CN110968789A (en) | Electronic book pushing method, electronic equipment and computer storage medium | |
| CN105550217B (en) | Scene music searching method and scene music searching device | |
| US8914398B2 (en) | Methods and apparatus for automated keyword refinement | |
| CN113516491A (en) | Promotion information display method and device, electronic equipment and storage medium | |
| TW201428515A (en) | Content and object metadata based search in e-reader environment | |
| US11341141B2 (en) | Search system using multiple search streams | |
| KR102315068B1 (en) | Method and system for determining document consistence to improve document search quality | |
| CN112883218A (en) | Image-text combined representation searching method, system, server and storage medium | |
| CN104376034B (en) | Information processing equipment, information processing method and program | |
| CN104123378A (en) | Information processing method and electronic device | |
| CN111831938A (en) | Information display method, information display device, electronic equipment and medium | |
| CN115516448A (en) | Evaluating similarity between items using embedding generated by a distributed training framework |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |