CN110020148A - A kind of information recommendation method, device and the device for information recommendation - Google Patents

A kind of information recommendation method, device and the device for information recommendation Download PDF

Info

Publication number
CN110020148A
CN110020148A CN201711227095.0A CN201711227095A CN110020148A CN 110020148 A CN110020148 A CN 110020148A CN 201711227095 A CN201711227095 A CN 201711227095A CN 110020148 A CN110020148 A CN 110020148A
Authority
CN
China
Prior art keywords
search
search word
word
user
historical
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
Application number
CN201711227095.0A
Other languages
Chinese (zh)
Other versions
CN110020148B (en
Inventor
林建素
王俊豪
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Sogou Technology Development Co Ltd
Original Assignee
Beijing Sogou Technology Development Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Sogou Technology Development Co Ltd filed Critical Beijing Sogou Technology Development Co Ltd
Priority to CN201711227095.0A priority Critical patent/CN110020148B/en
Publication of CN110020148A publication Critical patent/CN110020148A/en
Application granted granted Critical
Publication of CN110020148B publication Critical patent/CN110020148B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9535Search 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

The embodiment of the invention provides a kind of information recommendation method, device and for the device of information recommendation, method therein is specifically included: for the search term of user's input, obtaining its corresponding scene characteristic, and/or its corresponding association search word;Wherein, the historical search data that at least one user generates according to the association search word obtains;According to the scene characteristic and/or the association search word, the corresponding recommendation search term of described search word is determined;Show the recommendation search term.The embodiment of the present invention can show the recommendation search term for meeting the individualized feature of user to user, so that recommendation search term is more in line with the search intention of user.

Description

A kind of information recommendation method, device and the device for information recommendation
Technical field
The present invention relates to Internet technical field more particularly to a kind of information recommendation method, device and it is used for information recommendation Device.
Background technique
It is scanned for currently, user can input search term in the search box of search engine, to obtain and search term phase Matched search result;And search engine shows the search result to match with search term in result of page searching, for Family selection is checked.
In addition, search engine can also obtain recommendation search term relevant to search term, and show under search result The positions such as side or right side, when search intention not meet user in search result, user can search in the recommendation of displaying Required recommendation search term is selected to continue to search in rope word.
However, the recommendation search term that search engine provides at present is mostly just related to the literal meaning of search term, for example, Search term is " weekend weather ", then search engine may provide following search term of recommending: " Beijing weekend weather ", " Shanghai week Last weather ", " Wuhan weekend weather " etc., still, these recommendation search terms may and not meet the search intention of user.
Summary of the invention
The embodiment of the present invention provides a kind of information recommendation method, device and the device for information recommendation, existing to solve The problem of recommending search term not meet user search intent in technology.
To solve the above-mentioned problems, the embodiment of the invention discloses a kind of information recommendation methods, comprising:
For the search term of user's input, its corresponding scene characteristic, and/or its corresponding association search word are obtained;Its In, the historical search data that at least one user generates according to the association search word obtains;
According to the scene characteristic and/or the association search word, the corresponding recommendation search term of described search word is determined;
Show the recommendation search term.
Optionally, the historical search data includes historical search word, described according to the association search word, determine described in The corresponding recommendation search term of search term, comprising:
According to the mapping relations between historical search word and association search word, the corresponding association search of described search word is obtained Word;
According to described search word and the association search word, the corresponding recommendation search term of described search word is determined.
Optionally, described according to described search word and the association search word, determine the corresponding recommendation of described search word Search term, comprising:
At least one described association search word and described search word are combined, the new search word that combination is obtained As the corresponding recommendation search term of described search word.
Optionally, the mapping relations between the historical search word and association search word are established as follows:
Determine the corresponding association search word of historical search word in the historical search data;
Establish the mapping relations between the historical search word and the association search word.
Optionally, the corresponding association search word of the determination historical search word, comprising:
The historical search set of words with incidence relation is filtered out from the historical search word;
According to the historical search set of words, the corresponding association search word of the historical search word is determined.
Optionally, the historical search data further include: the corresponding historical search of the historical search word as a result, it is described really The corresponding association search word of historical search word in the fixed historical search data, comprising:
It is directed to the selection operation of the historical search result according to user, is extracted from the historical search result and obtains institute State the corresponding association search word of historical search word.
Optionally, the method also includes:
According to user for the selection operation for recommending search term, update the historical search word and association search word it Between mapping relations.
Optionally, the search term for user's input, it includes: defeated from the user for obtaining its corresponding scene characteristic In the search term entered, the position of user is acquired;
It is then described according to the scene characteristic, determine the corresponding recommendation search term of described search word, comprising:
According to the position attribution of described search word and the position of the user, determine that the corresponding recommendation of described search word is searched Rope word;And/or
According to the position of historical search word and the user in the corresponding preset time range of described search word, really Determine the corresponding recommendation search term of described search word;And/or
According to the category feature of described search word and the position of the user, the corresponding recommendation of described search word is determined Search term.
Optionally, the search term for user's input, it includes: defeated from the user for obtaining its corresponding scene characteristic In the search term entered, the input time of described search word is acquired;
It is then described according to the scene characteristic, determine the corresponding recommendation search term of described search word, comprising:
According to the historical search data of user, the candidate search word that there is incidence relation with the input time is obtained;
According to the candidate search word, and/or the input time corresponding hot word, determine that described search word is corresponding Recommend search term.
On the other hand, the embodiment of the invention discloses a kind of information recommending apparatus, comprising:
Module is obtained, for the search term for user's input, its corresponding scene characteristic is obtained, and/or its is corresponding Association search word;Wherein, the historical search data that at least one user generates according to the association search word obtains;
Determining module, for determining that described search word is corresponding according to the scene characteristic and/or the association search word Recommend search term;
Display module, for showing the recommendation search term.
Optionally, the historical search data includes historical search word, the determining module, comprising:
Association search word determines submodule, for obtaining according to the mapping relations between historical search word and association search word To the corresponding association search word of described search word;
Recommend to determine submodule, for determining described search word pair according to described search word and the association search word The recommendation search term answered.
Optionally, the recommendation determines submodule, comprising:
Recommendation determining units, for being combined at least one described association search word and described search word, by group Obtained new search word is closed as the corresponding recommendation search term of described search word.
Optionally, described device further include: module is established, for establishing between the historical search word and association search word Mapping relations;It is described to establish module, it can specifically include:
Association search word acquisition submodule, for determining, the corresponding association of historical search word is searched in the historical search data Rope word;
Mapping relations setting up submodule, the mapping for establishing between the historical search word and the association search word are closed System.
Optionally, the association search word acquisition submodule, comprising:
Screening unit, for filtering out the historical search set of words with incidence relation from the historical search word;
First determination unit, for determining the corresponding association of the historical search word according to the historical search set of words Search term.
Optionally, the historical search data further include: the corresponding historical search result of the historical search word;The pass Join search term acquisition submodule, comprising:
Second determination unit is searched for being directed to the selection operation of the historical search result according to user from the history It is extracted in hitch fruit and obtains the corresponding association search word of the historical search word.
Optionally, described device further include:
Update module, for, for the selection operation for recommending search term, updating the historical search word according to user With the mapping relations between association search word.
Optionally, the acquisition module, comprising: the first acquisition submodule, for from the search term that the user inputs, Acquire the position of user;
The then determining module, comprising:
First determines submodule, for determining institute according to the position attribution of described search word and the position of the user State the corresponding recommendation search term of search term;And/or
Second determine submodule, for according in the corresponding preset time range of described search word historical search word, with And the position of the user, determine the corresponding recommendation search term of described search word;And/or
Third determines submodule, for determining institute according to the category feature of described search word and the position of the user State the corresponding recommendation search term of search term.
Optionally, the acquisition module, comprising: the second acquisition submodule, for from the search term that the user inputs, Acquire the input time of described search word;
The then determining module, comprising:
Candidate search word acquisition submodule obtains and has with the input time for the historical search data according to user Relevant candidate search word;
4th determines submodule, is used for according to the candidate search word, and/or the input time corresponding hot word, really Determine the corresponding recommendation search term of described search word.
In another aspect, including memory, Yi Jiyi the embodiment of the invention discloses a kind of device for information recommendation A perhaps more than one program one of them or more than one program is stored in memory, and is configured to by one Or it includes the instruction for performing the following operation that more than one processor, which executes the one or more programs:
For the search term of user's input, its corresponding scene characteristic, and/or its corresponding association search word are obtained;Its In, the historical search data that at least one user generates according to the association search word obtains;
According to the scene characteristic and/or the association search word, the corresponding recommendation search term of described search word is determined;
Show the recommendation search term.
Another aspect, the embodiment of the invention discloses a kind of machine readable medias, are stored thereon with instruction, when by one or When multiple processors execute, so that device executes the information recommendation method as described in aforementioned one or more.
The embodiment of the present invention includes following advantages:
The embodiment of the present invention is directed to the search term of user's input, obtains its corresponding scene characteristic and/or its corresponding pass Join search term;The scene characteristic can be used for embodying the otherness of search environment, and user, may tool under different search environments There is different search intentions, the association search word can be used for embodying the otherness of search habit, and different user usually has not Same search habit, different search habits may correspond to different search intentions.Therefore, the embodiment of the present invention is according to search term Corresponding scene characteristic and/or association search word, it is available obtain meeting search environment locating for user and/or meet user search The recommendation search term of rope habit, that is, the embodiment of the present invention can show the recommendation for meeting the individualized feature of user to user Search term, so that recommendation search term is more in line with the search intention of user.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by institute in the description to the embodiment of the present invention Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention Example, for those of ordinary skill in the art, without any creative labor, can also be according to these attached drawings Obtain other attached drawings.
Fig. 1 is a kind of step flow chart of information recommendation method embodiment of the invention;
Fig. 2 is a kind of structural block diagram of information recommending apparatus embodiment of the invention;
Fig. 3 is a kind of block diagram of device 800 for information recommendation of the invention;And
Fig. 4 is a kind of structural schematic diagram of server of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts Example, shall fall within the protection scope of the present invention.
Embodiment of the method
Referring to Fig.1, a kind of step flow chart of information recommendation method embodiment of the invention is shown, specifically can wrap It includes:
Step 101, the search term inputted for user, obtain its corresponding scene characteristic, and/or its corresponding association Search term;Wherein, the association search word historical search data of at least one user generation can obtain according to;
Step 102, according to the scene characteristic and/or the association search word, determine the corresponding recommendation of described search word Search term;
Step 103 shows the recommendation search term.
The various APP that information recommendation method provided in an embodiment of the present invention can be applied to have function of search are (using journey Sequence, Application) or website in, in search engine, and information recommendation method provided in an embodiment of the present invention can be applied In client application environment corresponding with server, wherein client and server can be located in wired or wireless network, By the wired or wireless network, client and server carry out data interaction.
Specifically, client may operate in terminal, and the terminal can specifically include but be not limited to: smart phone, Tablet computer, E-book reader, MP3 (dynamic image expert's compression standard audio level 3, Moving Picture Experts Group Audio Layer III) player, MP4 (dynamic image expert's compression standard audio level 4, Moving Picture Experts Group Audio Layer IV) player, pocket computer on knee, vehicle-mounted computer, desk-top meter Calculation machine, set-top box, intelligent TV set, wearable device etc..
In practical applications, the search term that client can be inputted by preset interface captures user, such as pass through search Search box in engine obtains the search term of user's input.
For solve in existing scheme the recommendation search term that provides of search engine mostly just with the literal meaning phase of search term The problem of closing and then not meeting user search intent, the embodiment of the present invention are directed to the search term of user's input, it is corresponding to obtain its Scene characteristic, and/or its corresponding association search word, according to the scene characteristic and/or the association search word, determination is searched The corresponding recommendation search term of rope word, and the recommendation search term is shown to user, so that the recommendation search term meets user Current search scene, and then more meet the search intention of user.
Optionally, the embodiment of the present invention can also will recommend the corresponding link of search term to show user, which can be with It is directed toward the results page scanned for the recommendation search term.User recommends the corresponding link of search term, Ji Kejin by clicking Enter the results page scanned for the recommendation search term, since the behaviour for being manually entered search term and triggering search can be saved Make, therefore can simplify user's operation, improves the search efficiency of user.
Wherein, the scene characteristic can be used for embodying the otherness of search environment, and user, can under different search environments There can be different search intentions.For example, user scans in different geographical locations or different time, it may tool There is different search intentions.The association search word can be used for embodying the otherness of search habit, and different user usually has not Same search habit, different search habits may correspond to different search intentions.Therefore, the embodiment of the present invention is according to search term Corresponding scene characteristic and/or association search word, it is available to meet search environment locating for user and/or meet user's search habit Used recommendation search term, that is, the embodiment of the present invention can show the recommendation search for meeting the individualized feature of user to user Word, so that recommendation search term is more in line with the search intention of user.
In embodiments of the present invention, the association search word can according at least one user generate historical search number According to obtaining, and the association search word and described search word have incidence relation.The association search word can be used for embodying search The otherness of habit, different user usually have different search habits, and different search habits may correspond to different search It is intended to.Therefore, the embodiment of the present invention is available to obtain meeting user's search habit according to the corresponding association search word of search term Recommendation search term.
The historical search data that available at least one user of the embodiment of the present invention generates, in the historical search data It can specifically include historical search word, and then can determine the corresponding association search word of historical search word, and establish history and search Mapping relations between rope word and association search word.In the search process of user, can according to user input search term, with And the mapping relations, it inquires and obtains association search word corresponding with the historical search word that the search term that user inputs matches, And then the recommendation search term that can be shown according to the true directional user of the association search word.Wherein, at least one above-mentioned user can Think any user in internet, such as the user of current input search term, the embodiment of the present invention for specific user not It limits.
In an alternative embodiment of the invention, the historical search word can be established as follows to be searched with being associated with Mapping relations between rope word:
Step S11, the corresponding association search word of historical search word in the historical search data is determined;
Step S12, the mapping relations between the historical search word and the association search word are established.
The embodiment of the present invention can excavate the association for meeting user individual feature according to the historical search data of user Search term, the association search word can embody the personalized difference of user, for example, the different search habit of user, search for it is emerging Therefore interest, way of search etc. according to the recommendation search term that the association search word determines, are more in line with the search intention of user.
Specifically, the association search word can be the historical search word occurred in the historical search data, at this In a kind of alternative embodiment of invention, the corresponding association search word of the determining historical search word be can specifically include:
The historical search set of words with incidence relation is filtered out from the historical search word;
According to the historical search set of words, the corresponding association search word of the historical search word is determined.
Wherein, the incidence relation can specifically refer to that literal correlation or meaning are related, it will be understood that the present invention is implemented Example is without restriction for the physical relationship of the incidence relation.In a kind of application example of the invention, it is assumed that from user's Filtered out in historical search data the historical search set of words with incidence relation include: " Chengdu cuisines ", " on the tip of the tongue at All ", " Chengdu snack " }.Since three historical search words in the set are all related to Chengdu cuisines, illustrate that the user is searching for " Chengdu cuisines " simultaneously, and want to understand the relevant information in " Chengdu on the tip of the tongue " or " Chengdu snack ", therefore, above-mentioned set In three historical search words can association search word each other.That is, can determine that historical search word " Chengdu cuisines " is corresponding Association search word includes " Chengdu on the tip of the tongue " and " Chengdu snack ", determines the corresponding pass of historical search word " Chengdu on the tip of the tongue " Joining search term includes " Chengdu cuisines " and " Chengdu snack " and determining historical search word " Chengdu snack " corresponding association search Word includes " Chengdu cuisines " and " Chengdu on the tip of the tongue ".
In another alternative embodiment of the invention, the historical search data may include: the historical search word Corresponding historical search is as a result, the corresponding association search word of historical search word in the determination historical search data, specifically It may include: the selection operation for being directed to the historical search result according to user, extract and obtain from the historical search result The corresponding association search word of the historical search word.
In embodiments of the present invention, the association search word is in addition to including the history occurred in the historical search data Search term, can also include: by it is that the historical search data is analyzed, be not present in the historical search Association search word in data.
In an alternative embodiment of the invention, described to be grasped according to user for the selection of the historical search result Make, extracted from the historical search result and obtain the corresponding association search word of the historical search word, can specifically include:
Determine the target histories search result that the user selects from the historical search result;
Extract the keyword in the target histories search result;
Using the keyword as the corresponding association search word of the historical search word.
In a kind of application example of the invention, it is assumed that the historical search word for obtaining user includes " Li Ning ", and the user Include and " Li Ning " relevant multiple URL (Uniform by the historical search result that historical search word " Li Ning " search obtains Resource Locator, uniform resource locator), such as Li Ning official website, Li Ning personage introduction etc..According to the user's Historical search data it is found that user's target histories search result for further selecting and click in above-mentioned historical search result for Li Ning official website, and the merchandise news in relation to sport footwear is selected and clicked in Li Ning official website, illustrate the user When inputting search term " Li Ning ", search intention is the merchandise news in order to search Li Ning sport footwear, therefore, can be from the mesh Marking and extracting keyword in historical search result is " sport footwear ", although the user did not input " sport footwear " this historical search Word, but the selection operation carried out according to the user for historical search word " Li Ning " corresponding historical search result, can obtain Know that the user there are searching preferences therefore can extract keyword from the historical search result of the user Li Ning sport footwear " sport footwear " is used as historical search word " Li Ning " corresponding association search word, and establishes historical search word " Li Ning " and search with being associated with Mapping relations between rope word " sport footwear ".
For another example, it when historical search word is movie name, is generally included on movie theatre in the target search result of user's selection Information is reflected, therefore, " showing information ", " Ticketing information " etc. can be extracted from the target histories search result of the user as electricity The corresponding association search word of shadow class search term.For example, can establish historical search word " wrestling father " and association search word " on Reflect information " and association search word " Ticketing information " between mapping relations.
For another example, user often scans for using place name class search term as departure place or destination, with acquisition and place name The relevant traffic information of class search term, such as Flight Information or high-speed rail information.Therefore, " departure place ", " purpose can be extracted Ground ", " Flight Information ", " high-speed rail information " etc. are as the corresponding association search word of place name class search term.For example, can establish history Mapping relations etc. between search term " Beijing " and association search word " Flight Information ".
It is appreciated that the embodiment of the present invention is without restriction for the storage location of the mapping relations, such as can deposit Storage is in terminal local, alternatively, can also store in the server.
In practical applications, multiple search may be will do it for interested information user, or repeatedly clicks and checks, Therefore, the embodiment of the present invention can be directed to the number of clicks of the historical search result with counting user, and secondary according to clicking Number determines association search word more than the historical search result of the first preset value, so that the association search word determined is more in line with user Searching preferences.It is appreciated that the embodiment of the present invention is without restriction for the specific value of first preset value.
In practical applications, a search term may correspond to a large amount of, different field range association search word, with search The unmatched association search word user in the field of word may and lose interest in, in order to enable the recommendation search term obtained is more in line with The search intention of user, the embodiment of the present invention can also be filtered association search word according to the corresponding field of search term, make The corresponding field of finally obtained association search word field corresponding with described search word is obtained to match.
In the embodiment of the present invention, field can refer to a certain professional range, be related to all items in the range Reference.The example in field may include: household electrical appliances, amusement, automobile, sport, science and technology, environmental protection etc..Domain term, which refers to, to be frequently appeared in Certain specific areas, and the term word seldom occurred in other uncorrelated fields.It is " low if " FAW-Volkswagen " is automotive field word Carbon " is environment protection field word, and " Haier's refrigerator " is science and technology, field of household appliances word.It in practical applications, can be by domain classification, really Territory belonging to a fixed vocabulary, the embodiment of the present invention are without restriction for specific domain classification process.
In a kind of application example of the invention, for search term " air ticket ", there is the pass of incidence relation with the search term Joining search term may include: " air ticket inquiry ", " reservation ", " budget fare ", " air ticket in Beijing to Shanghai ", " train ticket It is predetermined ", " Eastern Air Lines Inc. ", " White Cloud Airport " etc..Wherein comprising with the not related association search word in " air ticket " field, because This, the embodiment of the present invention can be filtered above-mentioned association search word, to obtain in search term " air ticket " corresponding territory Association search word, such as may include: " air ticket inquiry ", " reservation ", " budget fare ", " machine in Beijing to Shanghai Ticket ", and establish the mapping relations between search term and association search word.
The available search term of the embodiment of the present invention corresponds to the association search word in territory, so that according to association The recommendation search term that search term obtains also complies with the territory of search term, so that recommending the range of search term more accurate, more Add the search intention for meeting user.
In an alternative embodiment of the invention, the historical search data may include historical search word, and described According to the association search word, determines the corresponding recommendation search term of described search word, can specifically include:
Step S21, according to the mapping relations between historical search word and association search word, it is corresponding to obtain described search word Association search word;
Step S22, according to described search word and the association search word, the corresponding recommendation search of described search word is determined Word.
The embodiment of the present invention in the historical search data for obtaining user, and according to the historical search data, go through by foundation After mapping relations between history search term and association search word, in user's search process, it can be searched according to what user inputted Rope word and the mapping relations, inquiry obtains the corresponding association search word of search term of user's input, and is searched according to described Rope word and the association search word determine the corresponding recommendation search term of described search word, and then can show and recommend to user Search term.
It specifically, can be by the association search word directly as recommending search term to show user, for example, it is assumed that user The search term of input is " names of the people ", and by inquiring stored mapping relations, available " names of the people " are corresponding Association search word include: " story introduction ", " performer's introduction " etc., then can by association search word " story introduction ", " performer is situated between Continue " user is showed directly as recommendation search term.
Alternatively, new search word can also be generated according to search term and association search word, searched new search word as recommendation Rope word shows user.In an alternative embodiment of the invention, described according to described search word and the association search Word determines the corresponding recommendation search term of described search word, can specifically include: at least one described association search word and Described search word is combined, and the new search word that combination is obtained is as the corresponding recommendation search term of described search word.
In a kind of application example of the invention, it is assumed that the search term of user's input is " Li Ning ", has been stored by inquiry Mapping relations, available " Li Ning " corresponding association search word includes: " sport footwear ", " gym suit ", " running shoes ", then can be with Search term " Li Ning " and its at least one corresponding association search word are combined, following new search word: " Li Ning is obtained Sport footwear ", " Li Ning gym suit ", " Li Ning running shoes ", and user is showed using above-mentioned new search word as recommendation search term.
It is appreciated that in practical applications, carrying out group at least one described association search word and described search word During conjunction, the embodiment of the present invention is without restriction for the specific number of association search word, such as can be with counting user point The number of association search word is hit, selecting number of clicks is more than that the association search word of the second preset value is combined.For example, above-mentioned In association search word, the number of clicks of " sport footwear " and " running shoes " is higher, and more than the second preset value, and the click of " gym suit " is secondary Number is lower, is less than the second preset value, then can only be combined, obtain with " sport footwear " and " running shoes " respectively to " Li Ning " New search word " Li Ning sport footwear " and " Li Ning running shoes ", and by " Li Ning sport footwear " and " Li Ning running shoes " as recommendation search term Show user.It is appreciated that the embodiment of the present invention is without restriction for the specific value of second preset value.
In addition, the embodiment of the present invention is not subject to the sequence between search term during said combination and association search word Limitation, for example, in the examples described above, can also combine to obtain following new search word: " sport footwear Li Ning ", " running shoes Li Ning " etc..
In an alternative embodiment of the invention, the method for the embodiment of the present invention can also include: and is directed to according to user The selection operation for recommending search term, updates the mapping relations between described search word and association search word.
The embodiment of the present invention can also update described search word according to user for the selection operation for recommending search term With the mapping relations between association search word so that the search that the association search word in the mapping relations is more in line with user is inclined It is good.For example, illustrating that the recommendation search term meets if user selects and click the recommendation search term " Li Ning sport footwear " of displaying The search intention of user then increases the corresponding number of clicks of association search word " sport footwear ".If user does not select to recommend to search Rope word " Li Ning gym suit ", illustrates that user loses interest in Li Ning gym suit, then can be searched with Delete Search word " Li Ning " with being associated with Mapping relations between rope word " gym suit ".
Optionally, the embodiment of the present invention can be directed to the point for recommending search term with counting user in the first preset time period Number is hit, for example, it is assumed that first preset time period is 10 days, then records user in nearest 10 days for recommendation search term Number of clicks can delete this if number of clicks of the search term in nearest 10 days is recommended to be no more than third preset value and push away It recommends search term and corresponds to the corresponding mapping relations of association search word.It is appreciated that when the embodiment of the present invention is default for described first Between section and the specific value of third preset value it is without restriction.
For the search term of user's input, the embodiment of the present invention can also obtain its corresponding scene characteristic, according to institute Scene characteristic is stated, determines the corresponding recommendation search term of described search word.The scene characteristic can specifically include: the position of user And/or the input time of search term.For above-mentioned scene characteristic, the embodiment of the present invention can provide that determining search term is corresponding to be pushed away Recommend the following scheme of search term:
Scheme one
In scheme one, the scene characteristic be can specifically include: the position of user.
In an alternative embodiment of the invention, the search term for user's input, obtains its corresponding scene Feature can specifically include: from the search term that the user inputs, acquire the position of user;It is then described according to Scene characteristic determines the corresponding recommendation search term of described search word, can specifically include: according to the position attribution of described search word And the position of the user, determine the corresponding recommendation search term of described search word.
Wherein, the position attribution can refer to that described search word has characteristic relevant to geographical location, for example, for ground The search term of name class, usually has position attribution, such as " Beijing ", " Chengdu ", " France ", when user inputs search term " north When capital ", the location information of available user, it is assumed that the position of user is " Xi'an ", then illustrates that user may wish to from Xi'an Beijing is left for, then can be determined according to the corresponding position attribution of search term " Beijing " and the position " Xi'an " of the user It is following to recommend search term " Xi'an to Pekinese's Flight Information ", " Xi'an to Pekinese's high-speed rail information " etc..
In an alternative embodiment of the invention, described according to the scene characteristic, determine that described search word is corresponding Recommend search term, can specifically include:
According to the position of historical search word and the user in the corresponding preset time range of described search word, really Determine the corresponding recommendation search term of described search word.
In practical applications, the search term that user inputs in a certain section of time range usually has incidence relation, therefore, The embodiment of the present invention can also obtain the historical search word in the corresponding preset time range of described search word, for example, above-mentioned In example, the search term of user's input is " Beijing ", then obtains the historical search in the corresponding preset time range of the search term Word, it is assumed that obtain historical search word within 5 minutes before search term input, specifically include: " tourism ", " five day tours " etc. with It travels relevant historical search word, can determine that the user currently wants to obtain relevant information of travelling, then it can be according to above-mentioned Historical search word " tourism ", " five day tours, user's search term currently entered " Beijing " and the current position " Xi'an " of user, The recommendation search term relevant to tourism such as " five day tour of Xi'an to Beijing " is provided a user, so as to which search term is recommended to be more in line with use The current search intention in family.
It is appreciated that the position attribution can also for described search word imply have spy relevant to geographical location Property, it is in an alternative embodiment of the invention, described according to the scene characteristic, determine that the corresponding recommendation of described search word is searched Rope word, can specifically include:
According to the category feature of described search word and the position of the user, the corresponding recommendation of described search word is determined Search term.
In a kind of application example of the invention, for search term " wrestling father ", since the search term is hot in the recent period The title of the film reflected, therefore, user may wish to understand the relevant information of the film, for example user may wish to check The related introduction of the film or user want to watch the film, therefore, can provide a user following recommendation search term: " fall Fall father's film introduction ", " the wrestling online booking of father ".Further, since the category feature of the search term is film, therefore User watches the film it is also possible to wanting to go to the cinema, and can also obtain the location information of user, and user location is attached Close movie theatre information is as recommending search term to show user, for example, can show " wrestling father Zhong Guan-cun Mei Jia to user Search term is recommended in online booking " etc..
Scheme two
In scheme two, the scene characteristic be can specifically include: the input time of described search word.
In practical applications, in different time, the search intention of user is also possible to not identical.For example, in lunch or In the dinner corresponding period, the search intention of user may be more likely to search for the information such as neighbouring restaurant or snack bar.And At weekend, user may be more likely to the search information such as traffic information or weather conditions, and therefore, the embodiment of the present invention can root According to the input time of search term, the corresponding recommendation search term of search term is determined, so that it is current to recommend search term to be more in line with user Search intention, and then more accurate recommendation search term can be provided a user.
In an alternative embodiment of the invention, the search term for user's input, obtains its corresponding scene Feature can specifically include: from the search term that the user inputs, acquire the input time information of described search word; It is then described according to the scene characteristic, it determines the corresponding recommendation search term of described search word, can specifically include:
Step S21, according to the historical search data of user, obtaining with the input time there is the candidate of incidence relation to search Rope word;
Step S22, according to the candidate search word, and/or the input time corresponding hot word, described search is determined The corresponding recommendation search term of word.
Wherein, the candidate search word can be the historical search word occurred in the historical search data, alternatively, also It historical search data can be analyzed according to, obtained search term relevant to historical search word.Also, the candidate searches Rope word corresponding historical search time and the input time of described search word have incidence relation.It is appreciated that described have pass Connection relationship, being specifically as follows the historical search time and the input time is identical time point, such as when historical search Between and the input time be all 10 minutes 9 points of mornings, alternatively, the historical search time is second default before and after the input time In period, such as the second preset time period is 30 minutes, and the input time is 10 minutes 9 points of mornings, then the historical search time In the morning in 8: 40 to morning, 9: 40 range, it is believed that historical search time and the input time have incidence relation. It is appreciated that the embodiment of the present invention is without restriction for the specific value of second preset time period.
In practical applications, some users may always search for same or similar information, example in a certain set time Such as, after user goes to work every morning, need to open enterprise, Netease mailbox, but the user does not remember the net of enterprise, Netease mailbox Location, always input search term " mailbox " is scanned for obtain the network address of enterprise, Netease mailbox in a search engine, according to the use The historical search data at family can learn that the user often in the morning in 9 points to 9 points 30 minutes periods, passes through search term " postal Case " opens the homepage of enterprise, Netease mailbox, therefore, if getting the search term of the user as " mailbox ", and the search term Input time be 10 minutes 9 points of mornings, then according to the historical search data of the user, can by " enterprise, Netease mailbox " as with Morning input time 9 points of 10 minutes candidate search words with incidence relation.
In a particular application, the number of the candidate search word with the input time with incidence relation can be multiple, For example, in the examples described above, the search term for obtaining user's input is " mailbox ", and input time is 10 minutes 9 points of mornings, according to this The historical search data of user, the candidate search word that can also obtain has incidence relation with the input time includes: " machine Ticket ", " weather " etc..
It, can be according to the candidate search after obtaining the candidate search word that there is incidence relation with the input time Word determines the corresponding recommendation search term of described search word.It specifically, can be by the candidate search word directly as described search The corresponding recommendation search term of word.Optionally, it also will click on the candidate search word that number is more than the 4th preset value, as described search The corresponding recommendation search term of word.It is appreciated that the embodiment of the present invention does not limit the specific value of the 4th preset value System.
Optionally, the embodiment of the present invention can also obtain the input time corresponding hot word, for example, it is assumed that user inputs Search term be " mushroom ", then can provide a user " way of mushroom ", " nutritive value of mushroom " etc. recommend search term.This Outside, by the input time corresponding hot word got, it can learn that " blue thin mushroom " is hot word more popular in the recent period, And above there is incidence relation literal with search term " mushroom ", and hence it is also possible to by searching described in hot word " blue thin mushroom " conduct The corresponding recommendation search term of rope word " mushroom ", shows user, to provide a user more selections.
It is appreciated that in practical applications, above-mentioned scene characteristic may be used alone, can also be used in combination, the present invention Embodiment is without restriction to this.In addition, the embodiment of the present invention is also without restriction for the particular content of the scene characteristic, For example, the scene characteristic can also include: current network conditions, job characteristics of user etc..
In a kind of application example of the invention, it is assumed that the search term of user's input is " the big Supreme Being of Kangxu ", and detects use The current network signal in family is poor, then the search intention of the user may for search for relevant to the big Supreme Being of Kangxu personage introduction or Person's novel etc. is to the lower text information of Network status demand, without searching for the higher picture of Network status demand, video Etc. resources, therefore, can be shown to user " the big Supreme Being's personage introduction of Kangxu ", " the big Supreme Being's novel of Kangxu " etc. recommend search term.
In embodiments of the present invention, it can also determine according to user job characteristics and recommend search term.For example, by obtaining The historical search data at family is taken, can learn that the user often searches for technical data related to programming, it can be determined that the use The job characteristics at family are programmer, then can show recommendation search term relevant to its job characteristics to user.
It is appreciated that in practical applications, the corresponding scene characteristic of search term, and/or search that the embodiment of the present invention obtains The corresponding association search word of rope word, can obtain according to the user data of active user, can also be according to the user of other users Data obtain, and the embodiment of the present invention is without restriction for the specific source of the scene characteristic and/or association search word.
In a kind of application example of the invention, it is assumed that the search term of user A input is " wrestling father ", passes through inquiry The user data stored in server can learn in the user data of user B to include search term " wrestling father " and be associated with Mapping relations between search term " wrestling father's film introduction ", " the wrestling online booking of father ", then can be according to user B Association search word determine the corresponding recommendation search term of search term " wrestling father ", and obtained recommendation search term is shown Give user A.It, can be according to the user data of other users, to user A as a result, when user A inputs some search term for the first time Suitable recommendation search term is provided, to improve the accuracy recommended.
To sum up, the information recommendation method of the embodiment of the present invention obtains its corresponding scene for the search term of user's input Feature and/or its corresponding association search word;The scene characteristic can be used for embodying the otherness of search environment, and user is in difference Search environment under, may have different search intentions;The association search word can be used for embodying the otherness of search habit, Different user usually has different search habits, and different search habits may correspond to different search intentions.Therefore, this hair Bright embodiment is available to meet search environment locating for user according to the corresponding scene characteristic of search term and/or association search word And/or meet the recommendation search term that user searches for habit, that is, the embodiment of the present invention can show for meeting user to user Property feature recommendation search term, so as to which search term is recommended to be more in line with the search intention of user.
Installation practice
Referring to Fig. 2, a kind of structural block diagram of information recommending apparatus embodiment of the invention is shown, can specifically include:
Module 201 is obtained, for the search term for user's input, its corresponding scene characteristic is obtained, and/or its is right The association search word answered;Wherein, the historical search data that at least one user generates according to the association search word obtains;
Determining module 202, for determining described search word pair according to the scene characteristic and/or the association search word The recommendation search term answered;
Display module 203, for showing the recommendation search term.
Optionally, the historical search data includes historical search word, and the determining module 202 can specifically include:
Association search word determines submodule, for obtaining according to the mapping relations between historical search word and association search word To the corresponding association search word of described search word;
Recommend to determine submodule, for determining described search word pair according to described search word and the association search word The recommendation search term answered.
Optionally, the recommendation determines submodule, can specifically include:
Recommendation determining units, for being combined at least one described association search word and described search word, by group Obtained new search word is closed as the corresponding recommendation search term of described search word.
Optionally, described device can also include: to establish module, for establishing the historical search word and association search word Between mapping relations;It is described to establish module, it can specifically include:
Association search word acquisition submodule, for determining, the corresponding association of historical search word is searched in the historical search data Rope word;
Mapping relations setting up submodule, the mapping for establishing between the historical search word and the association search word are closed System.
Optionally, the association search word acquisition submodule, can specifically include:
Screening unit, for filtering out the historical search set of words with incidence relation from the historical search word;
First determination unit, for determining the corresponding association of the historical search word according to the historical search set of words Search term.
Optionally, the historical search data can also include: the corresponding historical search result of the historical search word;Institute Association search word acquisition submodule is stated, can specifically include:
Second determination unit is searched for being directed to the selection operation of the historical search result according to user from the history It is extracted in hitch fruit and obtains the corresponding association search word of the historical search word.
Optionally, described device can also include:
Update module, for, for the selection operation for recommending search term, updating the historical search word according to user With the mapping relations between association search word.
Optionally, the acquisition module 201, can specifically include: the first acquisition submodule, for inputting from the user Search term in, acquire the position of user;
The then determining module 202, can specifically include:
First determines submodule, for determining institute according to the position attribution of described search word and the position of the user State the corresponding recommendation search term of search term;And/or
Second determine submodule, for according in the corresponding preset time range of described search word historical search word, with And the position of the user, determine the corresponding recommendation search term of described search word;And/or
Third determines submodule, for determining institute according to the category feature of described search word and the position of the user State the corresponding recommendation search term of search term.
Optionally, the acquisition module 201, can specifically include: the second acquisition submodule, for inputting from the user Search term in, acquire the input time of described search word;
The then determining module 202, can specifically include:
Candidate search word acquisition submodule obtains and has with the input time for the historical search data according to user Relevant candidate search word;
4th determines submodule, is used for according to the candidate search word, and/or the input time corresponding hot word, really Determine the corresponding recommendation search term of described search word.
For device embodiment, since it is basically similar to the method embodiment, related so being described relatively simple Place illustrates referring to the part of embodiment of the method.
All the embodiments in this specification are described in a progressive manner, the highlights of each of the examples are with The difference of other embodiments, the same or similar parts between the embodiments can be referred to each other.
About the device in above-described embodiment, wherein modules execute the concrete mode of operation in related this method Embodiment in be described in detail, no detailed explanation will be given here.
The embodiment of the invention discloses a kind of devices for information recommendation, include memory and one or one A above program, perhaps more than one program is stored in memory and is configured to by one or one for one of them It includes the instruction for performing the following operation that the above processor, which executes the one or more programs: being inputted for user Search term, obtain its corresponding scene characteristic, and/or its corresponding association search word;Wherein, the association search word is It is obtained according to the historical search data that at least one user generates;According to the scene characteristic and/or the association search word, really Determine the corresponding recommendation search term of described search word;Show the recommendation search term.
Optionally, the historical search data includes historical search word, described according to the association search word, determine described in The corresponding recommendation search term of search term, comprising:
According to the mapping relations between historical search word and association search word, the corresponding association search of described search word is obtained Word;
According to described search word and the association search word, the corresponding recommendation search term of described search word is determined.
Optionally, described according to described search word and the association search word, determine the corresponding recommendation of described search word Search term, comprising:
At least one described association search word and described search word are combined, the new search word that combination is obtained As the corresponding recommendation search term of described search word.
Optionally, the mapping relations between the historical search word and association search word are established as follows:
Determine the corresponding association search word of historical search word in the historical search data;
Establish the mapping relations between the historical search word and the association search word.
Optionally, the corresponding association search word of the determination historical search word, comprising:
The historical search set of words with incidence relation is filtered out from the historical search word;
According to the historical search set of words, the corresponding association search word of the historical search word is determined.
Optionally, the historical search data further include: the corresponding historical search of the historical search word as a result, it is described really The corresponding association search word of historical search word in the fixed historical search data, comprising:
It is directed to the selection operation of the historical search result according to user, is extracted from the historical search result and obtains institute State the corresponding association search word of historical search word.
Optionally, described device is also configured to execute one or one by one or more than one processor Procedure above includes the instruction for performing the following operation:
According to user for the selection operation for recommending search term, update the historical search word and association search word it Between mapping relations.
Optionally, the search term for user's input, it includes: defeated from the user for obtaining its corresponding scene characteristic In the search term entered, the position of user is acquired;
It is then described according to the scene characteristic, determine the corresponding recommendation search term of described search word, comprising:
According to the position attribution of described search word and the position of the user, determine that the corresponding recommendation of described search word is searched Rope word;And/or
According to the position of historical search word and the user in the corresponding preset time range of described search word, really Determine the corresponding recommendation search term of described search word;And/or
According to the category feature of described search word and the position of the user, the corresponding recommendation of described search word is determined Search term.
Optionally, the search term for user's input, it includes: defeated from the user for obtaining its corresponding scene characteristic In the search term entered, the input time of described search word is acquired;
It is then described according to the scene characteristic, determine the corresponding recommendation search term of described search word, comprising:
According to the historical search data of user, the candidate search word that there is incidence relation with the input time is obtained;
According to the candidate search word, and/or the input time corresponding hot word, determine that described search word is corresponding Recommend search term.
Fig. 3 is a kind of block diagram of device 800 for information recommendation shown according to an exemplary embodiment.For example, dress Setting 800 can be mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical treatment Equipment, body-building equipment, personal digital assistant etc..
Referring to Fig. 3, device 800 may include following one or more components: processing component 802, memory 804, power supply Component 806, multimedia component 808, audio component 810, the interface 812 of input/output (I/O), sensor module 814, and Communication component 816.
The integrated operation of the usual control device 800 of processing component 802, such as with display, telephone call, data communication, phase Machine operation and record operate associated operation.Processing element 802 may include that one or more processors 820 refer to execute It enables, to perform all or part of the steps of the methods described above.In addition, processing component 802 may include one or more modules, just Interaction between processing component 802 and other assemblies.For example, processing component 802 may include multi-media module, it is more to facilitate Interaction between media component 808 and processing component 802.
Memory 804 is configured as storing various types of data to support the operation in equipment 800.These data are shown Example includes the instruction of any application or method for operating on device 800, contact data, and telephone book data disappears Breath, picture, video etc..Memory 804 can be by any kind of volatibility or non-volatile memory device or their group It closes and realizes, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM) is erasable to compile Journey read-only memory (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, flash Device, disk or CD.
Power supply module 806 provides electric power for the various assemblies of device 800.Power supply module 806 may include power management system System, one or more power supplys and other with for device 800 generate, manage, and distribute the associated component of electric power.
Multimedia component 808 includes the screen of one output interface of offer between described device 800 and user.One In a little embodiments, screen may include liquid crystal display (LCD) and touch panel (TP).If screen includes touch panel, screen Curtain may be implemented as touch screen, to receive input signal from the user.Touch panel includes one or more touch sensings Device is to sense the gesture on touch, slide, and touch panel.The touch sensor can not only sense touch or sliding action Boundary, but also detect duration and pressure associated with the touch or slide operation.In some embodiments, more matchmakers Body component 808 includes a front camera and/or rear camera.When equipment 800 is in operation mode, such as screening-mode or When video mode, front camera and/or rear camera can receive external multi-medium data.Each front camera and Rear camera can be a fixed optical lens system or have focusing and optical zoom capabilities.
Audio component 810 is configured as output and/or input audio signal.For example, audio component 810 includes a Mike Wind (MIC), when device 800 is in operation mode, when such as call mode, recording mode, and voice recognition mode, microphone is matched It is set to reception external audio signal.The received audio signal can be further stored in memory 804 or via communication set Part 816 is sent.In some embodiments, audio component 810 further includes a loudspeaker, is used for output audio signal.
I/O interface 812 provides interface between processing component 802 and peripheral interface module, and above-mentioned peripheral interface module can To be keyboard, click wheel, button etc..These buttons may include, but are not limited to: home button, volume button, start button and lock Determine button.
Sensor module 814 includes one or more sensors, and the state for providing various aspects for device 800 is commented Estimate.For example, sensor module 814 can detecte the state that opens/closes of equipment 800, and the relative positioning of component, for example, it is described Component is the display and keypad of device 800, and sensor module 814 can be with 800 1 components of detection device 800 or device Position change, the existence or non-existence that user contacts with device 800,800 orientation of device or acceleration/deceleration and device 800 Temperature change.Sensor module 814 may include proximity sensor, be configured to detect without any physical contact Presence of nearby objects.Sensor module 814 can also include optical sensor, such as CMOS or ccd image sensor, at As being used in application.In some embodiments, which can also include acceleration transducer, gyro sensors Device, Magnetic Sensor, pressure sensor or temperature sensor.
Communication component 816 is configured to facilitate the communication of wired or wireless way between device 800 and other equipment.Device 800 can access the wireless network based on communication standard, such as WiFi, 2G or 3G or their combination.In an exemplary implementation In example, communication component 816 receives broadcast singal or broadcast related information from external broadcasting management system via broadcast channel. In one exemplary embodiment, the communication component 816 further includes near-field communication (NFC) module, to promote short range communication.Example Such as, NFC module can be based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra wide band (UWB) technology, Bluetooth (BT) technology and other technologies are realized.
In the exemplary embodiment, device 800 can be believed by one or more application specific integrated circuit (ASIC), number Number processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), controller, microcontroller, microprocessor or other electronic components are realized, for executing the above method.
In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instruction, example are additionally provided It such as include the memory 804 of instruction, above-metioned instruction can be executed by the processor 820 of device 800 to complete the above method.For example, The non-transitorycomputer readable storage medium can be ROM, random access memory (RAM), CD-ROM, tape, floppy disk With optical data storage devices etc..
Fig. 4 is the structural schematic diagram of server in the embodiment of the present invention.The server 1900 can be different because of configuration or performance And generate bigger difference, may include one or more central processing units (central processing units, CPU) 1922 (for example, one or more processors) and memory 1932, one or more storage application programs 1942 or data 1944 storage medium 1930 (such as one or more mass memory units).Wherein, memory 1932 It can be of short duration storage or persistent storage with storage medium 1930.Be stored in storage medium 1930 program may include one or More than one module (diagram does not mark), each module may include to the series of instructions operation in server.Further Ground, central processing unit 1922 can be set to communicate with storage medium 1930, and storage medium 1930 is executed on server 1900 In series of instructions operation.
Server 1900 can also include one or more power supplys 1926, one or more wired or wireless nets Network interface 1950, one or more input/output interfaces 1958, one or more keyboards 1956, and/or, one or More than one operating system 1941, such as WindowsServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM Etc..
A kind of non-transitorycomputer readable storage medium, when the instruction in the storage medium is by device (terminal or clothes Be engaged in device) processor execute when, enable a device to execute a kind of information recommendation method, which comprises for user it is defeated The search term entered obtains its corresponding scene characteristic, and/or its corresponding association search word;Wherein, the association search word To be obtained according to the historical search data of user;According to the scene characteristic and/or the association search word, described search is determined The corresponding recommendation search term of word;Show the recommendation search term.
Optionally, described according to the association search word, determine the corresponding recommendation search term of described search word, comprising:
According to the mapping relations between historical search word and association search word, the corresponding association search of described search word is obtained Word;
According to described search word and the association search word, the corresponding recommendation search term of described search word is determined.
Optionally, described according to described search word and the association search word, determine the corresponding recommendation of described search word Search term, comprising:
At least one described association search word and described search word are combined, the new search word that combination is obtained As the corresponding recommendation search term of described search word.
Optionally, the mapping relations between the historical search word and association search word are established as follows:
Obtain the historical search data of user;The historical search data includes: historical search word;
Determine the corresponding association search word of the historical search word;
Establish the mapping relations between the historical search word and the association search word.
Optionally, the corresponding association search word of the determination historical search word, comprising:
The historical search set of words with incidence relation is filtered out from the historical search word;
According to the historical search set of words, the corresponding association search word of the historical search word is determined.
Optionally, the corresponding association search word of the determination historical search word, comprising:
Obtain the corresponding historical search result of the historical search word;
It is directed to the selection operation of the historical search result according to user, is extracted from the historical search result and obtains institute State the corresponding association search word of historical search word.
Optionally, the processor is also configured to execute one or one by one or more than one processor A procedure above includes the instruction for performing the following operation:
According to user for the selection operation for recommending search term, update the historical search word and association search word it Between mapping relations.
Optionally, the scene characteristic includes: the position of user;
It is described according to the scene characteristic, determine the corresponding recommendation search term of described search word, comprising:
If described search word has position attribution, according to the position of described search word and the position of the user, really Determine the corresponding recommendation search term of described search word;And/or
According to the position of historical search word and the user in the corresponding preset time range of described search word, really Determine the corresponding recommendation search term of described search word;And/or
According to the category feature of described search word and the position of the user, the corresponding recommendation of described search word is determined Search term.
Optionally, the scene characteristic includes: the input time of described search word;
It is described according to the scene characteristic, determine the corresponding recommendation search term of described search word, comprising:
According to the historical search data of user, the candidate search word that there is incidence relation with the input time is obtained;
According to the candidate search word, and/or the input time corresponding hot word, determine that described search word is corresponding Recommend search term.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to of the invention its Its embodiment.The present invention is directed to cover any variations, uses, or adaptations of the invention, these modifications, purposes or Person's adaptive change follows general principle of the invention and including the undocumented common knowledge in the art of the disclosure Or conventional techniques.The description and examples are only to be considered as illustrative, and true scope and spirit of the invention are by following Claim is pointed out.
It should be understood that the present invention is not limited to the precise structure already described above and shown in the accompanying drawings, and And various modifications and changes may be made without departing from the scope thereof.The scope of the present invention is limited only by the attached claims.
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention and Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
A kind of information recommendation method provided by the present invention, a kind of information recommending apparatus and one kind are pushed away for information above The device recommended, is described in detail, and specific case used herein explains the principle of the present invention and embodiment It states, the above description of the embodiment is only used to help understand the method for the present invention and its core ideas;Meanwhile for this field Those skilled in the art, according to the thought of the present invention, there will be changes in the specific implementation manner and application range, to sum up institute It states, the contents of this specification are not to be construed as limiting the invention.

Claims (12)

1. a kind of information recommendation method, which is characterized in that the described method includes:
For the search term of user's input, its corresponding scene characteristic, and/or its corresponding association search word are obtained;Wherein, The historical search data that at least one user generates according to the association search word obtains;
According to the scene characteristic and/or the association search word, the corresponding recommendation search term of described search word is determined;
Show the recommendation search term.
2. described the method according to claim 1, wherein the historical search data includes historical search word According to the association search word, the corresponding recommendation search term of described search word is determined, comprising:
According to the mapping relations between historical search word and association search word, the corresponding association search word of described search word is obtained;
According to described search word and the association search word, the corresponding recommendation search term of described search word is determined.
3. according to the method described in claim 2, it is characterized in that, described according to described search word and the association search Word determines the corresponding recommendation search term of described search word, comprising:
At least one described association search word and described search word are combined, using the obtained new search word of combination as The corresponding recommendation search term of described search word.
4. according to the method described in claim 2, it is characterized in that, establish as follows the historical search word be associated with Mapping relations between search term:
Determine the corresponding association search word of historical search word in the historical search data;
Establish the mapping relations between the historical search word and the association search word.
5. according to the method described in claim 4, it is characterized in that, the corresponding association search of the determination historical search word Word, comprising:
The historical search set of words with incidence relation is filtered out from the historical search word;
According to the historical search set of words, the corresponding association search word of the historical search word is determined.
6. according to the method described in claim 4, it is characterized in that, the historical search data further include: the historical search The corresponding historical search of word is as a result, the corresponding association search word of historical search word in the determination historical search data, packet It includes:
It is directed to the selection operation of the historical search result according to user, is extracted from the historical search result and obtains described go through The corresponding association search word of history search term.
7. according to the method described in claim 2, it is characterized in that, the method also includes:
According to user for the selection operation for recommending search term, update between the historical search word and association search word Mapping relations.
8. the method according to claim 1, wherein the search term for user's input, obtains its correspondence Scene characteristic include: from the user input search term in, acquire the position of user;
It is then described according to the scene characteristic, determine the corresponding recommendation search term of described search word, comprising:
According to the position attribution of described search word and the position of the user, the corresponding recommendation search of described search word is determined Word;And/or
According to the position of historical search word and the user in the corresponding preset time range of described search word, institute is determined State the corresponding recommendation search term of search term;And/or
According to the category feature of described search word and the position of the user, the corresponding recommendation search of described search word is determined Word.
9. the method according to claim 1, wherein the search term for user's input, obtains its correspondence Scene characteristic include: from the user input search term in, acquire the input time of described search word;
It is then described according to the scene characteristic, determine the corresponding recommendation search term of described search word, comprising:
According to the historical search data of user, the candidate search word that there is incidence relation with the input time is obtained;
According to the candidate search word, and/or the input time corresponding hot word, the corresponding recommendation of described search word is determined Search term.
10. a kind of information recommending apparatus characterized by comprising
Module is obtained, for the search term for user's input, obtains its corresponding scene characteristic, and/or its corresponding association Search term;Wherein, the historical search data that at least one user generates according to the association search word obtains;
Determining module, for determining the corresponding recommendation of described search word according to the scene characteristic and/or the association search word Search term;
Display module, for showing the recommendation search term.
11. a kind of device for information recommendation, which is characterized in that include memory and one or more than one Program, perhaps more than one program is stored in memory and is configured to by one or more than one processing for one of them It includes the instruction for performing the following operation that device, which executes the one or more programs:
For the search term of user's input, its corresponding scene characteristic, and/or its corresponding association search word are obtained;Wherein, The historical search data that at least one user generates according to the association search word obtains;
According to the scene characteristic and/or the association search word, the corresponding recommendation search term of described search word is determined;
Show the recommendation search term.
12. a kind of machine readable media is stored thereon with instruction, when executed by one or more processors, so that device is held Information recommendation method of the row as described in one or more in claim 1 to 9.
CN201711227095.0A 2017-11-29 2017-11-29 Information recommendation method and device and information recommendation device Active CN110020148B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711227095.0A CN110020148B (en) 2017-11-29 2017-11-29 Information recommendation method and device and information recommendation device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711227095.0A CN110020148B (en) 2017-11-29 2017-11-29 Information recommendation method and device and information recommendation device

Publications (2)

Publication Number Publication Date
CN110020148A true CN110020148A (en) 2019-07-16
CN110020148B CN110020148B (en) 2022-04-26

Family

ID=67185975

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711227095.0A Active CN110020148B (en) 2017-11-29 2017-11-29 Information recommendation method and device and information recommendation device

Country Status (1)

Country Link
CN (1) CN110020148B (en)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110388933A (en) * 2019-07-22 2019-10-29 上海图聚智能科技股份有限公司 Interest point search method, device, server and storage medium
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
CN110968789A (en) * 2019-12-04 2020-04-07 掌阅科技股份有限公司 Electronic book pushing method, electronic equipment and computer storage medium
CN111080339A (en) * 2019-11-18 2020-04-28 口口相传(北京)网络技术有限公司 Method and device for generating category preference data based on scene
CN111368025A (en) * 2020-02-24 2020-07-03 百度在线网络技术(北京)有限公司 Hot word recommendation method and device for intelligent voice device and storage medium
CN111737574A (en) * 2020-06-19 2020-10-02 口口相传(北京)网络技术有限公司 Search information acquisition method and device, computer equipment and readable storage medium
CN111931046A (en) * 2020-07-30 2020-11-13 大众问问(北京)信息科技有限公司 Intelligent information recommendation method and device and computer equipment
CN112989177A (en) * 2019-12-12 2021-06-18 阿里巴巴集团控股有限公司 Information processing method, information processing device, electronic equipment and computer storage medium
CN113126779A (en) * 2019-12-30 2021-07-16 阿里巴巴集团控股有限公司 Man-machine interaction method, device, equipment and system
CN113792136A (en) * 2021-08-25 2021-12-14 北京库睿科技有限公司 Text data diversified recommendation type searching method and system
CN117271869A (en) * 2023-11-22 2023-12-22 深圳市灵智数字科技有限公司 User search word recommendation method and device and electronic equipment

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102368262A (en) * 2011-10-14 2012-03-07 北京百度网讯科技有限公司 Method and equipment for providing searching suggestions corresponding to query sequence
CN102375885A (en) * 2011-10-21 2012-03-14 北京百度网讯科技有限公司 Method and device for providing search suggestions corresponding to query sequence
CN103678358A (en) * 2012-09-13 2014-03-26 腾讯科技(深圳)有限公司 Information search method and system
CN104166700A (en) * 2014-08-01 2014-11-26 百度在线网络技术(北京)有限公司 Search term recommendation method and device
CN104462364A (en) * 2014-12-08 2015-03-25 百度在线网络技术(北京)有限公司 Search recommendation method and device
CN105653588A (en) * 2015-12-21 2016-06-08 北京奇虎科技有限公司 Search history record generation method and device
CN105868390A (en) * 2016-04-15 2016-08-17 乐视控股(北京)有限公司 Method and device for recommending personalized information

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102368262A (en) * 2011-10-14 2012-03-07 北京百度网讯科技有限公司 Method and equipment for providing searching suggestions corresponding to query sequence
CN102375885A (en) * 2011-10-21 2012-03-14 北京百度网讯科技有限公司 Method and device for providing search suggestions corresponding to query sequence
CN103678358A (en) * 2012-09-13 2014-03-26 腾讯科技(深圳)有限公司 Information search method and system
CN104166700A (en) * 2014-08-01 2014-11-26 百度在线网络技术(北京)有限公司 Search term recommendation method and device
CN104462364A (en) * 2014-12-08 2015-03-25 百度在线网络技术(北京)有限公司 Search recommendation method and device
CN105653588A (en) * 2015-12-21 2016-06-08 北京奇虎科技有限公司 Search history record generation method and device
CN105868390A (en) * 2016-04-15 2016-08-17 乐视控股(北京)有限公司 Method and device for recommending personalized information

Cited By (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110388933A (en) * 2019-07-22 2019-10-29 上海图聚智能科技股份有限公司 Interest point search method, device, server and storage medium
CN111080339A (en) * 2019-11-18 2020-04-28 口口相传(北京)网络技术有限公司 Method and device for generating category preference data based on scene
CN111080339B (en) * 2019-11-18 2024-01-30 口口相传(北京)网络技术有限公司 Scene-based category preference data generation method and device
CN110968789B (en) * 2019-12-04 2023-05-23 掌阅科技股份有限公司 Electronic book pushing method, electronic equipment and computer storage medium
CN110968789A (en) * 2019-12-04 2020-04-07 掌阅科技股份有限公司 Electronic book pushing method, electronic equipment and computer storage medium
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
CN112989177A (en) * 2019-12-12 2021-06-18 阿里巴巴集团控股有限公司 Information processing method, information processing device, electronic equipment and computer storage medium
CN113126779A (en) * 2019-12-30 2021-07-16 阿里巴巴集团控股有限公司 Man-machine interaction method, device, equipment and system
CN111368025A (en) * 2020-02-24 2020-07-03 百度在线网络技术(北京)有限公司 Hot word recommendation method and device for intelligent voice device and storage medium
CN111368025B (en) * 2020-02-24 2023-12-22 百度在线网络技术(北京)有限公司 Hot word recommendation method and equipment for intelligent voice equipment and storage medium
CN111737574B (en) * 2020-06-19 2024-01-26 口口相传(北京)网络技术有限公司 Search information acquisition method, apparatus, computer device and readable storage medium
CN111737574A (en) * 2020-06-19 2020-10-02 口口相传(北京)网络技术有限公司 Search information acquisition method and device, computer equipment and readable storage medium
CN111931046A (en) * 2020-07-30 2020-11-13 大众问问(北京)信息科技有限公司 Intelligent information recommendation method and device and computer equipment
CN113792136A (en) * 2021-08-25 2021-12-14 北京库睿科技有限公司 Text data diversified recommendation type searching method and system
CN117271869A (en) * 2023-11-22 2023-12-22 深圳市灵智数字科技有限公司 User search word recommendation method and device and electronic equipment
CN117271869B (en) * 2023-11-22 2024-03-29 深圳市灵智数字科技有限公司 User search word recommendation method and device and electronic equipment

Also Published As

Publication number Publication date
CN110020148B (en) 2022-04-26

Similar Documents

Publication Publication Date Title
CN110020148A (en) A kind of information recommendation method, device and the device for information recommendation
CN106708282B (en) A kind of recommended method and device, a kind of device for recommendation
CN107656938B (en) Recommendation method and device and recommendation device
US9600584B2 (en) Scalable visual search system simplifying access to network and device functionality
CN105812830B (en) The recommendation method and system of hotel service content
CN105488154A (en) Theme application recommendation method and device
CN107436893A (en) A kind of webpage recommending method and device
RU2635045C2 (en) Method and device for application execution
CN107341162B (en) Webpage processing method and device and webpage processing device
CN105574182A (en) News recommendation method and device as well as device for news recommendation
CN106874308A (en) It is a kind of to recommend method and apparatus, a kind of device for recommending
CN108227950A (en) A kind of input method and device
CN108874827B (en) Searching method and related device
CN110688576B (en) Content recommendation method and device, electronic equipment and storage medium
CN110019645A (en) Index base construction method, searching method and device
CN107622074A (en) A kind of data processing method, device and computing device
CN106506868A (en) A kind of music recommends method and terminal
CN110222256A (en) A kind of information recommendation method, device and the device for information recommendation
CN104683496B (en) address filtering method and device
CN103218440A (en) Media file recommendation method and device based on identity recognition
CN110110204A (en) A kind of information recommendation method, device and the device for information recommendation
CN110472158A (en) A kind of sort method and device of search entry
CN108572979A (en) A kind of position service method and device, a kind of device for location-based service
CN109521888A (en) A kind of input method, device and medium
CN107045541A (en) data display method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant