CN104166700A - Search term recommendation method and device - Google Patents
Search term recommendation method and device Download PDFInfo
- Publication number
- CN104166700A CN104166700A CN201410378537.1A CN201410378537A CN104166700A CN 104166700 A CN104166700 A CN 104166700A CN 201410378537 A CN201410378537 A CN 201410378537A CN 104166700 A CN104166700 A CN 104166700A
- Authority
- CN
- China
- Prior art keywords
- described user
- user
- search word
- interest
- current
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a search term recommendation method and device. The search term recommendation method comprises the steps that search terms recommended to a user are determined according to at least one parameter of the condition of the network currently used by the user, the current position of the user, the interest of the user, the condition of the user, the current time and the hot spot information; the search term used for search is determined from the search terms recommended to the user. By means of the technical scheme, the efficiency of determining the search term for search is improved.
Description
[technical field]
The present invention relates to Internet technical field, relate in particular to a kind of search word recommend method and device.
[background technology]
When user searches for, in the input frame that need to provide at search engine, input the search word (query) relevant to user search intent.There is a kind of method of the user's of raising inputted search word efficiency in prior art, during one or several character in user's inputted search word, system is mated as prefix the character of user's input in historical search word, and the search word that comprises this prefix matching is offered to user with the form of drop-down list, for user, directly from drop-down list, select the search word that will input.
But, because user's search need is diversified, search word in the drop-down list that said method provides does not generally meet user's query demand, user still needs inputted search word, or user need to input more character so that the search word in drop-down list meets user's query demand greatly.As can be seen here, said method is not clearly in the effect aspect the definite search word efficiency of raising.
[summary of the invention]
Many aspects of the present invention provide a kind of search word recommend method and device, determine the efficiency of search word in order to further raising.
An aspect of of the present present invention, provides a kind of search word recommend method, comprising:
According to the network condition of the current use of user, the current residing position of described user, described user's interest, at least one parameter in described user's state, current time and hot information, determine the search word of recommending to described user;
From the search word of recommending to described user, determine and search for the search word using.
Another aspect of the present invention, provides a kind of search word recommendation apparatus, comprising:
The first determination module, for according to the network condition of the current use of user, the current residing position of described user, described user's interest, at least one parameter of described user's state, current time and hot information, determine the search word of recommending to described user;
The second determination module, for the search word from recommending to described user, determines and searches for the search word using.
Technical solution of the present invention adopts other parameters that are different from historical search word, be the current residing position of network condition, user, user's interest, at least one parameter in user's state, current time and hot information of the current use of user, to user, recommend search word, and then the search word based on recommending to user is determined the search word that search is used.Because the present invention is for recommending the parameter of search word more can characterize this search intention of user to user, therefore, based at least one in these parameters, to user, recommend search word, can improve the probability hitting, so be conducive to as a whole improve the efficiency of determining search word.
[accompanying drawing explanation]
In order to be illustrated more clearly in the technical scheme in the embodiment of the present invention, to the accompanying drawing of required use in embodiment or description of the Prior Art be briefly described below, apparently, accompanying drawing in the following describes is some embodiments of the present invention, for those of ordinary skills, do not paying under the prerequisite of creative work, can also obtain according to these accompanying drawings other accompanying drawing.
The schematic flow sheet of the search word recommend method that Fig. 1 provides for one embodiment of the invention;
The structural representation of the search word recommendation apparatus that Fig. 2 provides for one embodiment of the invention.
[embodiment]
For making object, technical scheme and the advantage of the embodiment of the present invention clearer, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is the present invention's part embodiment, rather than whole embodiment.Embodiment based in the present invention, those of ordinary skills, not making the every other embodiment obtaining under creative work prerequisite, belong to the scope of protection of the invention.
The schematic flow sheet of the search word recommend method that Fig. 1 provides for one embodiment of the invention.As shown in Figure 1, the method comprises:
101, according to the network condition of the current use of user, the current residing position of user, user's interest, at least one parameter in user's state, current time and hot information, the search word that really directional user recommends.
102,, from the search word of recommending to user, determine and search for the search word using.
The executive agent of the present embodiment can be the various search service ends that search service is provided, and search service end can be search server, such as being Baidu's search server, Google's search server etc.User can send request to search server by the search client on its terminal device, and then the function of search of using search server to provide.User's terminal device can be smart mobile phone, ipad etc.
Wherein, user may use different networks to search in different scenes.For example, user is in or generally can uses WIFI accessing Internet during company, and user on the way or generally can use 2G, 3G or 4G technology accessing Internet while going out.The network condition that user uses can affect user's search intention.For example, in the situation that network condition is good, user is more prone to adopt behavior that some traffic consumes are large to meet oneself demand, such as download, watch online video, and tend to inquire about class demand the poor situation of network condition is next, such as encyclopaedia, know mhkc, or web page browsing.Because user's search intention is different, so the search word using also can be different.That is to say, the search word that the network condition of the current use of user can be used user affects to some extent.
For the standard of different accessing Internets, its operator generally can dispose separately gateway, that is to say, the gateway that different access standards are used is generally different.Therefore, the type of the gateway that search server can access by terminal device is determined the current mode for accessing Internet of terminal device, and then the network condition of the current use of definite user.
Wherein, when the residing geographical environment of user is different, generally also have different query demands.For example, when user is positioned at location, commercial circle, likely wish that understanding some purchases by group information of discount; When user is during in tourist district, may need to consider the information such as layout of sight spot of tourist district.Because user's search intention is different, so the search word using also can be different.That is to say, the search word that the current residing position of user also can be used user affects to some extent.
User's terminal device generally has positioning function, can determine user's Position Approximate.For example, terminal device generally all has GPS, position that can the current place of consumer positioning by GPS.Again for example, terminal device can carry out alternately, obtaining current position information from base station with base station.Wherein, the position at terminal device place can be determined according to the signal intensity of terminal device in base station.For terminal device, the positional information at user or the current place of terminal device can be offered to search server.
Wherein, the hobby of different user generally can be different.For example, certain user may like seeing certain this novel, so wish to understand some information about this novel; Another user may be a stock mania, so wish to understand relevant stock market information; Another user may be a football fan, so wish to understand whether have in the recent period ball match etc.Different user is because interest is different, so wish that the information of understanding is also just different.Therefore, user's interest also can affect the search word that user uses.
For user's interest, can be arranged in advance in terminal device, by terminal device, offer search server, or by search server to terminal device request.Or search server can, according to this user's search daily record, be determined user's interest.The search log recording here has user's historical search information, such as user's historical search word, the webpage that user accessed etc.For example, search server finds that according to user's search daily record this user often accesses novel server, or often downloads novel, can determine that user likes seeing novel, further can also determine that user likes seeing certain class novel.Again for example, the search daily record of search server by user finds that user often watches football match, can determine user's match of liking watching the football game, and is an individual football fan.
Wherein, generally also can be different without the residing state of user.For example, a user may, in conceived state, need to understand some pregnancy period general knowledge; Another user may be in participating in college entrance examination state, needs to understand information that some college entrance examinations are relevant etc.The information that need to understand due to the user in different conditions is different, so the search word using also can be different.That is to say the search word that user's state is used in the time of also can affecting user search.
For user's state, user can be arranged in terminal device in advance, by terminal device, offers search server, or by search server to terminal device request.Or search server can, according to this user's search daily record, be determined user's state.The search log recording here has user's historical search information, such as user's historical search word, the webpage that user accessed etc.For example, search server can also find that user often searches for pregnancy period data by user's search daily record, can determine that user may be in conceived state.Again for example, search server can also be found this user often search or download college entrance examination data by user's search daily record, can determine that user may be in participating in college entrance examination state.
What deserves to be explained is, it is a kind of preferred implementation that user's interest and user's combinations of states is used, and can further characterize like this user's search intention.For example, search server determines that user may be in participating in college entrance examination state and the match of liking watching the football game, but in this period, this user may more pay close attention to college entrance examination data and not need to pay close attention to football match, so can no longer recommend the search word of relevant football match to user.
Wherein, at different time, user's search need also can be different.For example, at noon the period, user may be more prone to the information such as near the restaurant of search or snack bar.Again for example, go out the period in the morning, user may be more prone to search for traffic information or weather conditions etc.That is to say, the time (current) when user intends to search for also can affect the search word that user search is used.
Conventionally, user, before searching for by terminal device, generally can start the search client on terminal device, at this, starts in the process of search client, and search client can send request the request of using search service to search server.Time when search service end can determine that user searches for according to the time that receives this request, i.e. current time.Or, user is after opening search client, the input frame input character that generally can provide at search client, search client can be real-time transmitted to search server by the character of user's input, so time when search server also can determine that user searches for according to the time that receives character.
General user knows about the demand of up-to-date hot information.And search word corresponding to different hot informations is generally different.Therefore,, according to the difference of hot information, the search word that user uses also can be different.About hot information, search server is generally understood real-time update and is stored hot information, also can store corresponding search word simultaneously.
To sum up analyze knownly, the network condition of the current use of user, the current residing position of user, user's interest, the parameters such as user's state, current time and hot information all can affect the search word that user search is used.And, compare with user's historical search word, these parameters may more can characterize user's search intention, therefore, the present embodiment adopts the network condition of the current use of user, the current residing position of user, user's interest, user's state, at least one in the parameter such as current time and hot information, to user, recommend search word, the search word of recommending meets user's search intention more, therefore the probability being hit has just improved, once be hit, just can directly use the search word being hit to search for, be conducive to improve the efficiency of determining search word, further be conducive to improve the efficiency that obtains Search Results.
In an optional embodiment, above-mentioned steps 102 can comprise: show the search word of recommending to user, for user, therefrom determine and search for the search word using.
In this embodiment, adopt the network condition of the current use of user, the current residing position of user, user's interest, user's state, at least one in the parameter such as current time and hot information, to user, recommend search word, the search word of recommending meets user's search intention more, by recommended search word is shown to user, user can directly therefrom determine and search for the search word using, can manually input or reduce user's manual input, be conducive to improve the efficiency of determining search word, further be conducive to improve the efficiency that obtains Search Results.
In an optional embodiment, above-mentioned steps 102 can comprise: server, from the search word of recommending to user, is determined and searched for the search word using.
Afterwards, server is used determined search word to search for, and pushes Search Results to user.
In this embodiment, server is directly determined and is searched for the search word using, do not need user to participate in, so user do not need to carry out any input from the search word of recommending to user, be conducive to improve the efficiency of determining search word, be further conducive to improve the efficiency that obtains Search Results.
In an optional embodiment, search server can adopt the current residing position of network condition, the user of the current use of user, user's interest, user's state, current time and hot information simultaneously, the search word that really directional user recommends, the probability that the search word recommended is like this hit can be higher, is more conducive to improve the efficiency of inputted search word.
In an optional embodiment, search server can adopt the network condition of the current use of user, the current residing position of described user, described user's interest, two or more parameters in user's state, current time and hot information, the search word that really directional user recommends.In this case, the true directional user of search server recommends the embodiment of search word to include but not limited to following mode:
Search server, using at least one in two or more used parameters as Prediction Parameters, is user in predicting candidate search word;
Further, search server, according to being different from the parameter of Prediction Parameters in two or more used parameters, filters out the search word of recommending to user from candidate search word.
Illustrate below, suppose that search server adopts the network condition of the current use of user simultaneously, the current residing position of user, user's interest, user's state, current time and hot information, the search word that really directional user recommends, search server can user's interest and/or user's state as Prediction Parameters, be used for as user in predicting candidate search word, and according to the network condition of the current use of user, the current residing position of user, current time and hot information, candidate search word is done to further screening, thereby the keyword that really directional user recommends.For example, suppose that search server is using user's interest and/or user's state as Prediction Parameters, the search word using from other identical users of the interest with this user and/or user's state, determine candidate search word; Afterwards, the candidate word that selector closes current network conditions, current present position, current time and hot information then from candidate search word is as the candidate word of recommending to user.
What deserves to be explained is, when Prediction Parameters has two or more, present embodiment does not limit the mode that Prediction Parameters is used in combination.The mode being used in combination between Prediction Parameters includes but not limited to following two kinds: a kind of is the union of getting the candidate search word of each Prediction Parameters prediction, as final candidate search word; Another kind is the common factor of getting the candidate search word of each Prediction Parameters prediction, as final candidate search word.
In an optional embodiment, search server can also be according to the network condition of the current use of user, the current residing position of user, user's interest, at least one parameter in user's state, current time and hot information and user's historical search word, the search word that really directional user recommends.; search server is except adopting the current residing position of network condition, user, user's interest of current use, at least one parameter in user's state, current time and hot information; can also be by user's historical search word;,, combining, at least one parameter in user's state, current time and hot information is used for recommending search word to user with the current residing position of network condition, user, user's the interest of current use.
Further, search server can, using the network condition of the current use of user, the current residing position of user, user's interest, at least one at least one parameter in user's state, current time and hot information and user's historical search word as Prediction Parameters, be user in predicting candidate search word; Again according to the network condition of the current use of user, the current residing position of user, user's interest, be different from the parameter of Prediction Parameters at least one parameter in user's state, current time and hot information and user's historical search word, from candidate search word, filter out the search word of recommending to user.
Illustrate, search server can adopt the network condition of the current use of user and the current residing position of user as Prediction Parameters, for user in predicting candidate search parameter, according to user's interest, user's state, current time, hot information and user's historical search word, candidate search word is screened again the final search word that really directional user recommends.Again for example, search server can adopt user's interest and/or user's state as Prediction Parameters, for user in predicting candidate search parameter, then according to current time and user's historical search word, candidate search word is screened the final search word that really directional user recommends.Again for example, search server can adopt user's interest and/or user's state as Prediction Parameters, is user in predicting candidate search parameter, then according to user's historical search word, candidate search word is screened, the final search word that really directional user recommends.The array mode of above-mentioned parameter can have multiple, and present embodiment illustrates no longer one by one.
In this explanation, if above-mentioned Prediction Parameters comprises user's interest and/or user's state, using user's interest and/or user's state as Prediction Parameters, for user in predicting candidate search word, comprise: the search word using from other identical users of the interest with this user and/or user's state, determine candidate search word.The search word that for example, can directly other identical users of the interest with this user and/or user's state be used is as candidate search word.
If above-mentioned Prediction Parameters comprises user's historical search word, using user's historical search word as Prediction Parameters, for user in predicting candidate search word, comprise: the historical search word to user is analyzed, to judge whether user's historical search word exists other search words with context continuous relationship, determine that existing other search words that have context continuous relationship with historical search word user are as candidate search word.
What deserves to be explained is, if above-mentioned Prediction Parameters comprises user's interest, user's state simultaneously, and user's historical search word, the union that can get the definite candidate search word of three is as being the candidate search word of user in predicting, or the common factor that can get the definite candidate search word of three is as being the candidate search word of user in predicting.
In another optional embodiment, in order further to improve the efficiency of inputted search word, search server can be before user inputs in input frame, according to the network condition of the current use of user, the current residing position of user, user's interest, at least one parameter in user's state, current time and hot information, the search word that really directional user recommends.In this embodiment, search server can determine whether user inputs in input frame.Conventionally, when user uses search client, start search client, now search client can send the request of using function of search to search server, and search server can determine that according to this request user is about to search for.If user is input character in input frame, search client can be by the character real-time Transmission of input to search server, so search server can, according to whether receiving the character that search client sends, determine whether user inputs in input frame.
For example, search server is when receiving the request of the use search service that search client sends, just start according to the network condition of the current use of user, the current residing position of user, user's interest, at least one parameter in user's state, current time and hot information, the search word that really directional user recommends, just carries out the matching treatment of search word no longer will receive the character of search client transmission user input as prior art after.In this embodiment, search server can be before user inputs, according to above-mentioned parameter, to user, recommend search word and show that the search word of recommending is to user, user can carry out input operation like this, can directly from the search word of recommending, determine the search word using, be conducive to further improve the efficiency of inputted search word.
In another optional embodiment, search server can also, before the search word that really directional user recommends, obtain the character that user inputs in input frame.Afterwards, search server is again according to the character of the network condition of the current use of user, the current residing position of user, user's interest, at least one parameter in user's state, current time and hot information and user's input, the search word that really directional user recommends.For example, can be first according to the network condition of the current use of user, the current residing position of user, user's interest, at least one parameter in user's state, current time and hot information, for user in predicting candidate search word, afterwards again according to the character of user's input, candidate search word is screened to the search word that really directional user recommends.
Illustrate, can be according to the character of the network condition of the current use of user, the current residing position of user and user's input, the search word that really directional user recommends.Or, can be according to the character of the network condition of the current use of user, user's interest, user's state and user's input, the search word that really directional user recommends.Or, can be according to the character of hot information and user's input, the search word that really directional user recommends.In this embodiment, except according to the network condition of the current use of user, the current residing position of user, user's interest, the parameters such as user's state, current time and hot information, can also be in conjunction with the character of user's input, although user needs importation character, but after the character in conjunction with user's input, the search word that can make to recommend user meets user's search intention more, further the probability being hit can be improved, the efficiency of inputted search word can be further improved as a whole.
It should be noted that, for aforesaid each embodiment of the method, for simple description, therefore it is all expressed as to a series of combination of actions, but those skilled in the art should know, the present invention is not subject to the restriction of described sequence of movement, because according to the present invention, some step can adopt other orders or carry out simultaneously.Secondly, those skilled in the art also should know, the embodiment described in instructions all belongs to preferred embodiment, and related action and module might not be that the present invention is necessary.
In the above-described embodiments, the description of each embodiment is all emphasized particularly on different fields, in certain embodiment, there is no the part of detailed description, can be referring to the associated description of other embodiment.
The structural representation of the search word recommendation apparatus that Fig. 2 provides for one embodiment of the invention.As shown in Figure 2, this device comprises: the first determination module 21 and the second determination module 22.
The first determination module 21, for according to the network condition of the current use of user, the current residing position of user, user's interest, at least one parameter of user's state, current time and hot information, the search word that really directional user recommends.
The second determination module 22, is connected with the first determination module 21, for the search word of recommending from the first determination module 21 to user, determines and searches for the search word using.
In an optional embodiment, the second determination module 22 specifically can be used for showing the search word of recommending to the first determination module 21 users, for user, therefrom determines and searches for the search word using.
In an optional embodiment, the first determination module 21 specifically can be used for according to the network condition of the current use of user, the current residing position of user, user's interest, at least one parameter in user's state, current time and hot information and user's historical search word, the search word that really directional user recommends.
Further, the first determination module 21 specifically can be used for using the network condition of the current use of user, the current residing position of user, user's interest, at least one at least one parameter in user's state, current time and hot information and user's historical search word as Prediction Parameters, is user in predicting candidate search word; According to the network condition of the current use of user, the current residing position of user, user's interest,, be different from the parameter of Prediction Parameters at least one parameter in user's state, current time and hot information and user's historical search word, from candidate search word, filter out the search word of recommending to user.
In an optional embodiment, the first determination module 21 also can be used for the search daily record according to user, determines user's interest and/or user's state.Further, when the first determination module 21 is specifically used in Prediction Parameters and comprises user's interest and/or user's state, the search word using from other identical users of the interest with user and/or user's state, determine candidate search word, and when Prediction Parameters comprises user's historical search word, historical search word to user is analyzed, to judge whether historical search word exists other search words with context continuous relationship, determine that existing other search words that have context continuous relationship with historical search word are as candidate search word.
In an optional embodiment, the first determination module 21 specifically can be used for the current residing position of network condition, user, user's interest, two or more parameters in user's state, current time and hot information when the current use of user, during search word that really directional user recommends, using at least one in two or more used parameters as Prediction Parameters, it is user in predicting candidate search word; According to being different from the parameter of Prediction Parameters in two or more used parameters, from candidate search word, filter out the search word of recommending to user.
In an optional embodiment, the first determination module 21 is specifically used in before user inputs in input frame, according to the network condition of the current use of user, the current residing position of user, user's interest, at least one parameter in user's state, current time and hot information, the search word that really directional user recommends.
In an optional embodiment, the device of the present embodiment can also comprise: acquisition module, the character of inputting at input frame for obtaining user.Based on this, the first determination module 21 specifically can be used for according to the character of the network condition of the current use of user, the current residing position of user, user's interest, at least one parameter in user's state, current time and hot information and user's input, the search word that really directional user recommends.
The search word recommendation apparatus that the present embodiment provides can be any search service end that function of search can be provided, for example, can be specifically search server, but be not limited to this.
The search word recommendation apparatus that the present embodiment provides, employing is different from other parameters of historical search word, be the current residing position of network condition, user, user's interest, at least one parameter in user's state, current time and hot information of the current use of user, to user, recommend search word, and then from the search word of recommending to user, determine and search for the search word using.The search word recommendation apparatus providing due to the present embodiment recommends parameter that search word is used more can characterize this search intention of user to user, therefore, based at least one in these parameters, to user, recommend search word, can improve the probability hitting, so be conducive to as a whole improve the efficiency of determining search word, further can improve the efficiency that obtains Search Results.
Those skilled in the art can be well understood to, for convenience and simplicity of description, the system of foregoing description, the specific works process of device and unit, can, with reference to the corresponding process in preceding method embodiment, not repeat them here.
In several embodiment provided by the present invention, should be understood that, disclosed system, apparatus and method, can realize by another way.For example, device embodiment described above is only schematic, for example, the division of described unit, be only that a kind of logic function is divided, during actual realization, can have other dividing mode, for example a plurality of unit or assembly can in conjunction with or can be integrated into another system, or some features can ignore, or do not carry out.Another point, shown or discussed coupling each other or direct-coupling or communication connection can be by some interfaces, indirect coupling or the communication connection of device or unit can be electrically, machinery or other form.
The described unit as separating component explanation can or can not be also physically to separate, and the parts that show as unit can be or can not be also physical locations, can be positioned at a place, or also can be distributed in a plurality of network element.Can select according to the actual needs some or all of unit wherein to realize the object of the present embodiment scheme.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, can be also that the independent physics of unit exists, and also can be integrated in a unit two or more unit.Above-mentioned integrated unit both can adopt the form of hardware to realize, and the form that also can adopt hardware to add SFU software functional unit realizes.
The integrated unit that the above-mentioned form with SFU software functional unit realizes, can be stored in a computer read/write memory medium.Above-mentioned SFU software functional unit is stored in a storage medium, comprise that some instructions are with so that a computer equipment (can be personal computer, server, or the network equipment etc.) or processor (processor) carry out the part steps of method described in each embodiment of the present invention.And aforesaid storage medium comprises: USB flash disk, portable hard drive, ROM (read-only memory) (Read-Only Memory, ROM), the various media that can be program code stored such as random access memory (Random Access Memory, RAM), magnetic disc or CD.
Finally it should be noted that: above embodiment only, in order to technical scheme of the present invention to be described, is not intended to limit; Although the present invention is had been described in detail with reference to previous embodiment, those of ordinary skill in the art is to be understood that: its technical scheme that still can record aforementioned each embodiment is modified, or part technical characterictic is wherein equal to replacement; And these modifications or replacement do not make the essence of appropriate technical solution depart from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (16)
1. a search word recommend method, is characterized in that, comprising:
According to the network condition of the current use of user, the current residing position of described user, described user's interest, at least one parameter in described user's state, current time and hot information, determine the search word of recommending to described user;
From the search word of recommending to described user, determine and search for the search word using.
2. method according to claim 1, is characterized in that, described from the search word of recommending to described user, determines and searches for the search word using, and comprising:
The search word that demonstration is recommended to described user, therefrom determines and searches for the search word using for described user.
3. method according to claim 1, it is characterized in that, described according to the network condition of the current use of user, the current residing position of described user, described user's interest, at least one parameter in described user's state, current time and hot information, determine the search word of recommending to described user, comprising:
According to the network condition of the current use of described user, the current residing position of described user, described user's interest, at least one parameter in described user's state, described current time and described hot information and described user's historical search word, determine the search word of recommending to described user.
4. method according to claim 3, it is characterized in that, described according to the network condition of the current use of described user, the current residing position of described user, described user's interest, at least one parameter in described user's state, described current time and described hot information and described user's historical search word, determine the search word of recommending to described user, comprising:
Using the network condition of the current use of described user, the current residing position of described user, described user's interest, at least one at least one parameter in described user's state, described current time and described hot information and described user's historical search word as described Prediction Parameters, it is described user in predicting candidate search word;
According to being different from the parameter of described Prediction Parameters in the network condition of the current use of described user, the current residing position of described user, described user's interest and/or at least one parameter in state, described current time and described hot information and described user's historical search word, from described candidate search word, filter out the search word of recommending to described user.
5. method according to claim 4, is characterized in that, also comprises:
According to described user's search daily record, determine described user's interest and/or described user's state;
If described Prediction Parameters comprises described user's interest and/or described user's state, described using described user's interest and/or described user's state as described Prediction Parameters, be described user in predicting candidate search word, comprising:
The search word using from other identical users of the interest with described user and/or described user's state, determine described candidate search word;
If described Prediction Parameters comprises described user's historical search word, using described user's historical search word as described Prediction Parameters, be described user in predicting candidate search word, comprising:
Historical search word to described user is analyzed, to judge whether described historical search word exists other search words with context continuous relationship, determine that other search words that existing and described historical search word has context continuous relationship are as described candidate search word.
6. method according to claim 1, it is characterized in that, described according to the network condition of the current use of user, the current residing position of described user, described user's interest, at least one parameter in described user's state, current time and hot information, determine the search word of recommending to described user, comprising:
When using the current residing position of network condition, described user, described user's interest, two or more parameters in described user's state, described current time and described hot information of the current use of described user, while determining the search word of recommending to described user, using at least one in two or more used parameters as Prediction Parameters, it is described user in predicting candidate search word;
According to being different from the parameter of described Prediction Parameters in two or more used parameters, from described candidate search word, filter out the search word of recommending to described user.
7. according to the method described in claim 1-6 any one, it is characterized in that, described according to the network condition of the current use of user, the current residing position of described user, described user's interest, at least one parameter in described user's state, current time and hot information, determine the search word of recommending to described user, comprising:
Before described user inputs in input frame, according to the network condition of the current use of described user, the current residing position of described user, described user's interest, at least one parameter in described user's state, described current time and described hot information, determine the search word of recommending to described user.
8. according to the method described in claim 1-6 any one, it is characterized in that, described according to the network condition of the current use of user, the current residing position of described user, described user's interest, at least one in described user's state, current time and hot information, before determining the search word of recommending to described user, comprising:
Obtain the character that described user inputs in input frame;
Described according to the network condition of the current use of user, the current residing position of described user, described user's interest, at least one in described user's state, current time and hot information, determine the search word of recommending to described user, comprising:
According to the character of the network condition of the current use of described user, the current residing position of described user, described user's interest, at least one parameter in described user's state, described current time and described hot information and described user input, determine the search word of recommending to described user.
9. a search word recommendation apparatus, is characterized in that, comprising:
The first determination module, for according to the network condition of the current use of user, the current residing position of described user, described user's interest, at least one parameter of described user's state, current time and hot information, determine the search word of recommending to described user;
The second determination module, for the search word from recommending to described user, determines and searches for the search word using.
10. device according to claim 9, is characterized in that, described the second determination module, specifically for showing the search word of recommending to described user, is therefrom determined and searched for the search word using for described user.
11. devices according to claim 9, it is characterized in that, described the first determination module, specifically for according to the network condition of the current use of described user, the current residing position of described user, described user's interest, at least one parameter in described user's state, described current time and described hot information and described user's historical search word, is determined the search word of recommending to described user.
12. devices according to claim 11, it is characterized in that, described the first determination module, specifically for using the network condition of the current use of described user, the current residing position of described user, described user's interest, at least one at least one parameter in described user's state, described current time and described hot information and described user's historical search word as described Prediction Parameters, is described user in predicting candidate search word; According to the network condition of the current use of described user, the current residing position of described user, described user's interest,, be different from the parameter of described Prediction Parameters at least one parameter in described user's state, described current time and described hot information and described user's historical search word, from described candidate search word, filter out the search word of recommending to described user.
13. devices according to claim 12, is characterized in that, described the first determination module also, for according to described user's search daily record, is determined described user's interest and/or described user's state;
Described the first determination module is when comprising described user's interest and/or described user's state in described Prediction Parameters, the search word using from other identical users of the interest with described user and/or described user's state, determine described candidate search word, and when described Prediction Parameters comprises described user's historical search word, historical search word to described user is analyzed, to judge whether described historical search word exists other search words with context continuous relationship, determine that other search words that existing and described historical search word has context continuous relationship are as described candidate search word.
14. devices according to claim 9, it is characterized in that, described the first determination module is specifically for the current residing position of network condition, described user, described user's interest, two or more parameters in described user's state, described current time and described hot information when the current use of the described user of use, while determining the search word of recommending to described user, using at least one in two or more used parameters as Prediction Parameters, it is described user in predicting candidate search word; According to being different from the parameter of described Prediction Parameters in two or more used parameters, from described candidate search word, filter out the search word of recommending to described user.
15. according to the device described in claim 9-14 any one, it is characterized in that, described the first determination module is specifically for before inputting in input frame described user, according to the network condition of the current use of described user, the current residing position of described user, described user's interest, at least one parameter in described user's state, described current time and described hot information, determine the search word of recommending to described user.
16. according to the device described in claim 9-14 any one, it is characterized in that, also comprises:
Acquisition module, the character of inputting at input frame for obtaining described user;
Described the first determination module, specifically for according to the character of the network condition of the current use of described user, the current residing position of described user, described user's interest, at least one parameter in described user's state, described current time and described hot information and described user input, is determined the search word of recommending to described user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410378537.1A CN104166700A (en) | 2014-08-01 | 2014-08-01 | Search term recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410378537.1A CN104166700A (en) | 2014-08-01 | 2014-08-01 | Search term recommendation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104166700A true CN104166700A (en) | 2014-11-26 |
Family
ID=51910513
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410378537.1A Pending CN104166700A (en) | 2014-08-01 | 2014-08-01 | Search term recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104166700A (en) |
Cited By (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104598607A (en) * | 2015-01-29 | 2015-05-06 | 百度在线网络技术（北京）有限公司 | Method and system for recommending search phrase |
| CN105045883A (en) * | 2015-07-21 | 2015-11-11 | 惠州Tcl移动通信有限公司 | Mobile terminal and search method thereof |
| CN105159930A (en) * | 2015-08-05 | 2015-12-16 | 百度在线网络技术（北京）有限公司 | Search keyword pushing method and apparatus |
| CN105302916A (en) * | 2015-11-16 | 2016-02-03 | 北京百度网讯科技有限公司 | Information recommendation method and device |
| CN105426385A (en) * | 2015-10-20 | 2016-03-23 | 百度在线网络技术（北京）有限公司 | Method and apparatus for random search by users |
| CN105574176A (en) * | 2015-12-21 | 2016-05-11 | 北京奇虎科技有限公司 | Hot word recommending method and device with combination of multiple data sources |
| CN105740343A (en) * | 2016-01-25 | 2016-07-06 | 百度在线网络技术（北京）有限公司 | Searching method and device |
| CN105786492A (en) * | 2016-02-23 | 2016-07-20 | 浪潮软件集团有限公司 | Method for realizing code prediction prompt by using big data method |
| CN105786949A (en) * | 2015-01-08 | 2016-07-20 | 纳宝株式会社 | Method and system for providing retargeting search service |
| CN105956149A (en) * | 2016-05-12 | 2016-09-21 | 北京奇艺世纪科技有限公司 | Default search word recommendation method and apparatus |
| WO2016202214A3 (en) * | 2015-06-19 | 2017-02-09 | 阿里巴巴集团控股有限公司 | Method and device for displaying keyword |
| CN106484859A (en) * | 2016-09-30 | 2017-03-08 | 维沃移动通信有限公司 | A kind of conjunctive word exhibiting method and device |
| CN106503233A (en) * | 2016-11-03 | 2017-03-15 | 北京挖玖电子商务有限公司 | Top search term commending system |
| CN106909582A (en) * | 2015-12-23 | 2017-06-30 | 北京奇虎科技有限公司 | Recommend method and device with reference to the hot word of multi-data source |
| CN107169116A (en) * | 2017-05-24 | 2017-09-15 | 北京奇艺世纪科技有限公司 | The generation method and device of default search word |
| WO2017177630A1 (en) * | 2016-04-15 | 2017-10-19 | 乐视控股（北京）有限公司 | Method and device for recommending personalized information |
| CN107291713A (en) * | 2016-03-30 | 2017-10-24 | 高德软件有限公司 | Reminding method, terminal and the server of point of interest search keyword |
| CN107341165A (en) * | 2016-04-29 | 2017-11-10 | 上海京东到家元信信息技术有限公司 | The method and apparatus for prompting display are carried out at search box |
| CN107368553A (en) * | 2017-06-30 | 2017-11-21 | 北京奇虎科技有限公司 | The method and device of search suggestion word is provided based on active state |
| CN107665220A (en) * | 2016-07-29 | 2018-02-06 | 苏宁云商集团股份有限公司 | A kind of processing method and system for searching service |
| CN107784092A (en) * | 2017-10-11 | 2018-03-09 | 深圳市金立通信设备有限公司 | A kind of method, server and computer-readable medium for recommending hot word |
| CN107798066A (en) * | 2017-09-25 | 2018-03-13 | 北京小度信息科技有限公司 | A kind of search term method for pushing, device and terminal |
| CN108280108A (en) * | 2017-03-16 | 2018-07-13 | 广州市动景计算机科技有限公司 | Search for candidate item display methods, device and data terminal |
| CN108319376A (en) * | 2017-12-29 | 2018-07-24 | 北京奇虎科技有限公司 | A kind of input association recommendation method and device that optimization business word is promoted |
| CN109582878A (en) * | 2018-11-05 | 2019-04-05 | 咪咕文化科技有限公司 | Method and device for realizing search prompt and computer readable storage medium |
| CN110020148A (en) * | 2017-11-29 | 2019-07-16 | 北京搜狗科技发展有限公司 | A kind of information recommendation method, device and the device for information recommendation |
| CN110244860A (en) * | 2018-03-08 | 2019-09-17 | 北京搜狗科技发展有限公司 | A kind of input method, device and electronic equipment |
| CN110347926A (en) * | 2019-07-15 | 2019-10-18 | 北京百度网讯科技有限公司 | Method and apparatus for pushed information |
| CN110532351A (en) * | 2019-07-19 | 2019-12-03 | 口口相传(北京)网络技术有限公司 | Recommend word methods of exhibiting, device, equipment and computer readable storage medium |
| CN111083229A (en) * | 2019-12-24 | 2020-04-28 | 珠海大横琴科技发展有限公司 | Application information pushing method and device, electronic equipment and storage medium |
| CN113765954A (en) * | 2020-06-03 | 2021-12-07 | 本田技研工业(中国)投资有限公司 | Information pushing method, information pushing system and server |
| CN116089729A (en) * | 2023-03-31 | 2023-05-09 | 浙江口碑网络技术有限公司 | Search recommendation method, device and storage medium |
| CN116303983A (en) * | 2021-12-21 | 2023-06-23 | 中国移动通信有限公司研究院 | A keyword recommendation method, device and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102930022A (en) * | 2012-10-31 | 2013-02-13 | 中国运载火箭技术研究院 | User-oriented information search engine system and method |
| CN102930012A (en) * | 2012-10-31 | 2013-02-13 | 北京奇虎科技有限公司 | Client and search pilot method |
| CN102937975A (en) * | 2012-10-17 | 2013-02-20 | 北京奇虎科技有限公司 | Device and method for webpage search |
| CN103324720A (en) * | 2013-06-25 | 2013-09-25 | 百度在线网络技术（北京）有限公司 | Personalized recommendation method and system according to user state |
| CN103914536A (en) * | 2014-03-31 | 2014-07-09 | 北京百度网讯科技有限公司 | Interest point recommending method and system for electronic maps |
-
2014
- 2014-08-01 CN CN201410378537.1A patent/CN104166700A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102937975A (en) * | 2012-10-17 | 2013-02-20 | 北京奇虎科技有限公司 | Device and method for webpage search |
| CN102930022A (en) * | 2012-10-31 | 2013-02-13 | 中国运载火箭技术研究院 | User-oriented information search engine system and method |
| CN102930012A (en) * | 2012-10-31 | 2013-02-13 | 北京奇虎科技有限公司 | Client and search pilot method |
| CN103324720A (en) * | 2013-06-25 | 2013-09-25 | 百度在线网络技术（北京）有限公司 | Personalized recommendation method and system according to user state |
| CN103914536A (en) * | 2014-03-31 | 2014-07-09 | 北京百度网讯科技有限公司 | Interest point recommending method and system for electronic maps |
Cited By (47)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105786949A (en) * | 2015-01-08 | 2016-07-20 | 纳宝株式会社 | Method and system for providing retargeting search service |
| CN105786949B (en) * | 2015-01-08 | 2019-10-08 | 纳宝株式会社 | The method and system for redirecting retrieval service are provided |
| US10482140B2 (en) | 2015-01-08 | 2019-11-19 | Naver Corporation | Method and system for providing retargeting search service |
| CN104598607B (en) * | 2015-01-29 | 2018-10-30 | 百度在线网络技术（北京）有限公司 | Recommend the method and system of search phrase |
| CN104598607A (en) * | 2015-01-29 | 2015-05-06 | 百度在线网络技术（北京）有限公司 | Method and system for recommending search phrase |
| US11403357B2 (en) | 2015-06-19 | 2022-08-02 | Advanced New Technologies Co., Ltd. | Enhancing accuracy of presented search keywords |
| US11727075B2 (en) | 2015-06-19 | 2023-08-15 | Advanced New Technologies Co., Ltd. | Enhancing accuracy of presented search keywords |
| WO2016202214A3 (en) * | 2015-06-19 | 2017-02-09 | 阿里巴巴集团控股有限公司 | Method and device for displaying keyword |
| CN105045883B (en) * | 2015-07-21 | 2020-12-25 | 惠州Tcl移动通信有限公司 | Mobile terminal and searching method thereof |
| CN105045883A (en) * | 2015-07-21 | 2015-11-11 | 惠州Tcl移动通信有限公司 | Mobile terminal and search method thereof |
| CN105159930A (en) * | 2015-08-05 | 2015-12-16 | 百度在线网络技术（北京）有限公司 | Search keyword pushing method and apparatus |
| CN105426385A (en) * | 2015-10-20 | 2016-03-23 | 百度在线网络技术（北京）有限公司 | Method and apparatus for random search by users |
| CN105426385B (en) * | 2015-10-20 | 2019-05-07 | 百度在线网络技术（北京）有限公司 | A kind of method and apparatus for carrying out the random search for user |
| CN105302916A (en) * | 2015-11-16 | 2016-02-03 | 北京百度网讯科技有限公司 | Information recommendation method and device |
| CN105574176A (en) * | 2015-12-21 | 2016-05-11 | 北京奇虎科技有限公司 | Hot word recommending method and device with combination of multiple data sources |
| CN106909582A (en) * | 2015-12-23 | 2017-06-30 | 北京奇虎科技有限公司 | Recommend method and device with reference to the hot word of multi-data source |
| CN105740343A (en) * | 2016-01-25 | 2016-07-06 | 百度在线网络技术（北京）有限公司 | Searching method and device |
| CN105786492A (en) * | 2016-02-23 | 2016-07-20 | 浪潮软件集团有限公司 | Method for realizing code prediction prompt by using big data method |
| CN107291713A (en) * | 2016-03-30 | 2017-10-24 | 高德软件有限公司 | Reminding method, terminal and the server of point of interest search keyword |
| WO2017177630A1 (en) * | 2016-04-15 | 2017-10-19 | 乐视控股（北京）有限公司 | Method and device for recommending personalized information |
| CN107341165A (en) * | 2016-04-29 | 2017-11-10 | 上海京东到家元信信息技术有限公司 | The method and apparatus for prompting display are carried out at search box |
| CN105956149B (en) * | 2016-05-12 | 2019-12-06 | 北京奇艺世纪科技有限公司 | method and device for recommending default search terms |
| CN105956149A (en) * | 2016-05-12 | 2016-09-21 | 北京奇艺世纪科技有限公司 | Default search word recommendation method and apparatus |
| CN107665220A (en) * | 2016-07-29 | 2018-02-06 | 苏宁云商集团股份有限公司 | A kind of processing method and system for searching service |
| CN106484859A (en) * | 2016-09-30 | 2017-03-08 | 维沃移动通信有限公司 | A kind of conjunctive word exhibiting method and device |
| CN106503233A (en) * | 2016-11-03 | 2017-03-15 | 北京挖玖电子商务有限公司 | Top search term commending system |
| CN108280108A (en) * | 2017-03-16 | 2018-07-13 | 广州市动景计算机科技有限公司 | Search for candidate item display methods, device and data terminal |
| CN107169116A (en) * | 2017-05-24 | 2017-09-15 | 北京奇艺世纪科技有限公司 | The generation method and device of default search word |
| CN107169116B (en) * | 2017-05-24 | 2020-11-24 | 北京奇艺世纪科技有限公司 | Method and device for generating default search words |
| CN107368553B (en) * | 2017-06-30 | 2021-02-23 | 北京奇虎科技有限公司 | Method and device for providing search suggestion words based on activity state |
| CN107368553A (en) * | 2017-06-30 | 2017-11-21 | 北京奇虎科技有限公司 | The method and device of search suggestion word is provided based on active state |
| CN107798066A (en) * | 2017-09-25 | 2018-03-13 | 北京小度信息科技有限公司 | A kind of search term method for pushing, device and terminal |
| CN107784092A (en) * | 2017-10-11 | 2018-03-09 | 深圳市金立通信设备有限公司 | A kind of method, server and computer-readable medium for recommending hot word |
| CN110020148B (en) * | 2017-11-29 | 2022-04-26 | 北京搜狗科技发展有限公司 | Information recommendation method and device and information recommendation device |
| CN110020148A (en) * | 2017-11-29 | 2019-07-16 | 北京搜狗科技发展有限公司 | A kind of information recommendation method, device and the device for information recommendation |
| CN108319376B (en) * | 2017-12-29 | 2021-11-26 | 北京奇虎科技有限公司 | Input association recommendation method and device for optimizing commercial word promotion |
| CN108319376A (en) * | 2017-12-29 | 2018-07-24 | 北京奇虎科技有限公司 | A kind of input association recommendation method and device that optimization business word is promoted |
| CN110244860B (en) * | 2018-03-08 | 2024-02-02 | 北京搜狗科技发展有限公司 | Input method and device and electronic equipment |
| CN110244860A (en) * | 2018-03-08 | 2019-09-17 | 北京搜狗科技发展有限公司 | A kind of input method, device and electronic equipment |
| CN109582878A (en) * | 2018-11-05 | 2019-04-05 | 咪咕文化科技有限公司 | Method and device for realizing search prompt and computer readable storage medium |
| CN110347926A (en) * | 2019-07-15 | 2019-10-18 | 北京百度网讯科技有限公司 | Method and apparatus for pushed information |
| CN110532351B (en) * | 2019-07-19 | 2022-04-12 | 口口相传(北京)网络技术有限公司 | Recommendation word display method, device and equipment and computer readable storage medium |
| CN110532351A (en) * | 2019-07-19 | 2019-12-03 | 口口相传(北京)网络技术有限公司 | Recommend word methods of exhibiting, device, equipment and computer readable storage medium |
| CN111083229A (en) * | 2019-12-24 | 2020-04-28 | 珠海大横琴科技发展有限公司 | Application information pushing method and device, electronic equipment and storage medium |
| CN113765954A (en) * | 2020-06-03 | 2021-12-07 | 本田技研工业(中国)投资有限公司 | Information pushing method, information pushing system and server |
| CN116303983A (en) * | 2021-12-21 | 2023-06-23 | 中国移动通信有限公司研究院 | A keyword recommendation method, device and electronic equipment |
| CN116089729A (en) * | 2023-03-31 | 2023-05-09 | 浙江口碑网络技术有限公司 | Search recommendation method, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104166700A (en) | Search term recommendation method and device | |
| US9881050B2 (en) | Method and system to recommend applications from an application market place to a new device | |
| TWI672598B (en) | Method and system for evaluating user satisfaction with respect to a user session | |
| JP6186086B2 (en) | Intelligent recommendation method, recommended device, storage medium and equipment of housing complex | |
| US8027954B2 (en) | Portable media player recommendation system | |
| US20110184873A1 (en) | Methods and systems for transmitting location based agent alerts in a real estate application | |
| US20190163714A1 (en) | Search result aggregation method and apparatus based on artificial intelligence and search engine | |
| US10031980B2 (en) | Intelligent homepage tuning in a web browser | |
| WO2019000887A1 (en) | Method and device for recommending information | |
| WO2017071251A1 (en) | Information pushing method and device | |
| JP6581357B2 (en) | Information recommendation method and apparatus | |
| JP6181867B2 (en) | Application information search method and apparatus | |
| US10057302B2 (en) | Context-based selection of instruction sets for connecting through captive portals | |
| US11430049B2 (en) | Communication via simulated user | |
| JP2010009315A (en) | Recommended store presentation system | |
| US20220358175A1 (en) | Method and system of personalized blending for content recommendation | |
| CN108959450B (en) | Popular comment determination system, method, device and readable medium | |
| US20170323326A1 (en) | Method and systems for determining programmatically expected performances | |
| US20230139539A1 (en) | Identifying viewing characteristics of an audience of a content channel | |
| CN104834721A (en) | Search processing method and device based on positions | |
| KR102601545B1 (en) | Geographic position point ranking method, ranking model training method and corresponding device | |
| US9760933B1 (en) | Interactive shopping advisor for refinancing product queries | |
| CN105119743B (en) | Acquisition method of user behavior intention and apparatus | |
| US20130332235A1 (en) | Optimizing Market Research Based on Mobile Respondent Location | |
| US20140248913A1 (en) | Optimizing Mobile User Data Storage |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20141126 |