CN102184201B - Equipment and method used for selecting recommended sequence of query sequence - Google Patents

Equipment and method used for selecting recommended sequence of query sequence Download PDF

Info

Publication number
CN102184201B
CN102184201B CN201110105486.1A CN201110105486A CN102184201B CN 102184201 B CN102184201 B CN 102184201B CN 201110105486 A CN201110105486 A CN 201110105486A CN 102184201 B CN102184201 B CN 102184201B
Authority
CN
China
Prior art keywords
sequence
recommendation
prompting
user
search
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.)
Active
Application number
CN201110105486.1A
Other languages
Chinese (zh)
Other versions
CN102184201A (en
Inventor
程恒奇
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 Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology 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 Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN201110105486.1A priority Critical patent/CN102184201B/en
Publication of CN102184201A publication Critical patent/CN102184201A/en
Application granted granted Critical
Publication of CN102184201B publication Critical patent/CN102184201B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention provides equipment and a method used for selecting a recommended sequence of a query sequence. The method comprises the following steps of: acquiring a prompting sequence corresponding to the query sequence; according to the prompting sequence, combining a matching operation of a recommended database, acquiring a recommendation degree corresponding to the prompting sequence; and according to the recommendation degree, selecting the recommended sequence corresponding to the query sequence from the prompting sequence. Compared with the prior art, the recommended sequence corresponding to the query sequence is selected according to the recommendation degree of the prompting sequence, and the search experience of a user is enhanced by subdividing the prompting sequence; therefore, the interaction between the user and a search engine is enhanced.

Description

A kind of for choosing equipment and the method for recommendation sequence of search sequence
Technical field
The present invention relates to internet hunt field, relate in particular in internet hunt the technology of the recommendation sequence for choosing search sequence.
Background technology
In the prior art, when user is in the time that search input field is keyed in a certain search sequence, tend to occur being similar to a row prompt strings (also can be described as prompting sequence) of drop-down menu, this user can select one or more as target query sequence in these prompting sequences, thereby realizes relevant search service.
But, in these prompting sequences, some prompting sequences have " Aladdin result " very clear and definite, that user's satisfaction is higher,, the corresponding Search Results of prompting sequence directly meets user's search need, and some prompting sequences have the Search Results that user's satisfaction is lower, may carry out even in addition secondary search or change prompting sequence.Once user has selected the prompting sequence that satisfaction is lower, its search experience can reduce a lot, will certainly make user's search procedure complicated.
In view of this, how designing a kind ofly for choosing the method for recommendation sequence of search sequence, to strengthen the interactivity between user and search engine, promote user's search experience, is a traffic aided technician problem urgently to be resolved hurrily.
Summary of the invention
The object of this invention is to provide a kind of for choosing equipment and the method for recommendation sequence of search sequence.
According to an aspect of the present invention, provide a kind of computer implemented for choosing the method for recommendation sequence of search sequence, wherein, the method comprising the steps of:
A obtains the recommendation sequence corresponding with described search sequence according to user's search sequence; Wherein, described steps A comprises the following steps:
A obtains the prompting sequence corresponding with described search sequence;
B, according to described prompting sequence, carries out matching operation in recommending data storehouse, to obtain the recommendation degree corresponding with described prompting sequence;
C, according to described recommendation degree, chooses described recommendation sequence from described prompting sequence.
According to another aspect of the present invention, also provide a kind of for choosing the equipment of recommendation sequence of search sequence, wherein, described equipment comprises:
Recommend retrieval device, for obtain the recommendation sequence corresponding with described search sequence according to user's search sequence;
Wherein, described recommendation retrieval device comprises:
The first acquisition device, for obtaining the prompting sequence corresponding with described search sequence;
The second acquisition device for according to described prompting sequence, carries out matching operation in recommending data storehouse, to obtain the recommendation degree corresponding with described prompting sequence;
Selecting device for according to described recommendation degree, is chosen described recommendation sequence from described prompting sequence.
According to a further aspect of the invention, also provide a kind of search engine, this search engine comprise described in one aspect of the present invention for choosing the equipment of recommendation sequence of search sequence.
Compared with prior art, the present invention is obtaining after the prompting sequence corresponding with search sequence, in recommending data storehouse, carry out matching operation to obtain corresponding recommendation degree, and from prompting sequence, choose corresponding recommendation sequence according to described recommendation degree, promote user's search experience by segmenting described prompting sequence, strengthen the interactivity between user and search engine.Apply the present invention to search engine, user can also identify easily and carry out the recommendation sequence that special type represents, and utilizes described recommendation sequence to obtain Aladdin result.
Brief description of the drawings
By reading the detailed description that non-limiting example is done of doing with reference to the following drawings, it is more obvious that other features, objects and advantages of the present invention will become:
Fig. 1 illustrate according to one aspect of the invention for choosing the equipment schematic diagram of recommendation sequence of search sequence;
Fig. 2 illustrate according to one preferred embodiment of the present invention for choosing the equipment schematic diagram of recommendation sequence of search sequence;
Fig. 3 illustrate according to a further aspect of the invention for choosing the method flow diagram of recommendation sequence of search sequence;
Fig. 4 illustrate according to one preferred embodiment of the present invention for choosing the method flow diagram of recommendation sequence of search sequence.
In accompanying drawing, same or analogous Reference numeral represents same or analogous parts.
Embodiment
Below in conjunction with accompanying drawing, the present invention is described in further detail.
Fig. 1 illustrate according to one aspect of the invention for choosing the equipment schematic diagram of recommendation sequence of search sequence.Wherein, selected equipment 1 includes but not limited to the cloud that network host, single network server, multiple webserver collection or multiple server form.At this, cloud can be made up of a large amount of computing machines based on cloud computing (Cloud Computing) or the webserver, and wherein, cloud computing is a kind of super virtual machine being made up of the loosely-coupled computing machine collection of a group of Distributed Calculation.Wherein, described selected equipment 1 comprises recommends retrieval device 11, and described recommendation retrieval device 11 comprises the first acquisition device 111, the second acquisition device 112 and selecting device 113.Those skilled in the art will be understood that above-mentioned selected equipment is only for giving an example, and other selected equipment existing or that may occur from now on, as applicable to the present invention, also should be included in protection domain of the present invention, and are contained in this with way of reference.
Recommend retrieval device 11 to obtain the recommendation sequence corresponding with described search sequence according to user's search sequence.Wherein, recommend the first acquisition device 111 in retrieval device 11 to obtain the prompting sequence corresponding with described search sequence.Particularly, the communication mode of the application programming interfaces (API) that the first acquisition device 111 for example provides by third party devices such as search engines or agreement, obtains the prompting sequence corresponding with described search sequence from this third party device; Or, the communication mode of the application programming interfaces (API) that provide by third party devices such as search engines or agreement, obtain from this third party device the search sequence that this user inputs by subscriber equipment, and by the mode such as such as front suffix match, unisonance coupling, fuzzy phoneme coupling or nearly word form coupling, obtain the prompting sequence corresponding with this search sequence; Or, by page technology, as ASP, JSP, PHP etc., obtain from subscriber equipment the search sequence that user inputs by this subscriber equipment, and by the mode such as such as front suffix match, unisonance coupling, fuzzy phoneme coupling or nearly word form coupling, obtain the prompting sequence corresponding with this search sequence.For example, in the time that user keys in search sequence " Shanghai traffic " by subscriber equipment, the first acquisition device 111 obtains this search sequence " Shanghai traffic " from described subscriber equipment, then obtains the prompting sequence " Shanghai Communications University " corresponding with described search sequence " Shanghai traffic " according to front suffix match; Or, obtain the prompting sequence " Shanghai Transit Service circuit " corresponding with described search sequence " Shanghai traffic ", " Shanghai rail transit circuit ", " Shanghai Airport information " etc. according to the result of described search sequence being carried out to semantic analysis.Those skilled in the art will be understood that the above-mentioned mode of obtaining the prompting sequence corresponding with described search sequence is only for giving an example; other existing or modes of obtaining the prompting sequence corresponding with described search sequence that may occur are from now on as applicable to the present invention; also should be included in protection domain of the present invention, and be contained in this with way of reference.
Then, the second acquisition device 112, according to described prompting sequence, carries out matching operation in recommending data storehouse, to obtain the recommendation degree corresponding with described prompting sequence.Particularly, the prompting sequence that the second acquisition device 112 obtains according to the first acquisition device 111 carries out matching operation in recommending data storehouse 14, and obtains the recommendation degree corresponding with described prompting sequence according to the result of matching inquiry.For example, the prompting sequence that the second acquisition device 112 obtains according to the first acquisition device 111 carries out matching inquiry in recommending data storehouse 14, when described prompting sequence can be searched while obtaining in described recommending data storehouse 14, the recommendation degree of described prompting sequence is the highest, if recommendation degree is 1.0; In described recommending data storehouse 14, cannot search while obtaining when described prompting sequence, the recommendation degree of described prompting sequence is minimum, if recommendation degree is 0.0.And for example, the prompting sequence that the second acquisition device 112 obtains according to the first acquisition device 111, carrying out the degree of correlation with the recommendation sequence of having demarcated in recommending data storehouse 14 mates, calculate the degree of correlation between described prompting sequence and described recommendation sequence of having demarcated, in the time that the degree of correlation between described prompting sequence and described recommendation sequence of having demarcated is higher, the recommendation degree of described prompting sequence is correspondingly also higher, and for example, described recommendation degree can be normalized to any number between 0.0 to 1.0.At this, described recommending data storehouse 14 both can be arranged in described selected equipment 1, also can be arranged in the network equipment being connected by network with described selected equipment 1, described network includes but not limited to internet, wide area network, Metropolitan Area Network (MAN), LAN (Local Area Network), VPN network, wireless self-organization network (Ad Hoc network) etc.Those skilled in the art will be understood that the above-mentioned mode of obtaining corresponding recommendation degree according to described prompting sequence is only for giving an example; other existing or modes of obtaining corresponding recommendation degree according to described prompting sequence that may occur are from now on as applicable to the present invention; also should be included in protection domain of the present invention, and be contained in this with way of reference.
Then, selecting device 113, according to described recommendation degree, is chosen the recommendation sequence corresponding with described search sequence from described prompting sequence.Particularly, the recommendation degree corresponding to described prompting sequence that selecting device 113 obtains according to the second acquisition device 112, by such as based on recommendation degree, prompting sequence being classified, described prompting sequence carried out to the modes such as examination in conjunction with recommendation degree threshold value, from described prompting sequence, choose the recommendation sequence corresponding with described search sequence.For example, the prompting sequence that the second acquisition device 112 obtains according to the first acquisition device 111, in recommending data storehouse 14, carry out matching inquiry to obtain the corresponding recommendation degree of described prompting sequence, then selecting device 113 is classified described prompting sequence according to described recommendation degree according to recommendation degree, for example, the prompting sequence that is 1.0 by all recommendation degree is divided into a class, and the prompting sequence that is 0.0 by all recommendation degree is divided into a class, and the one or more prompting sequences that are 1.0 using recommendation degree are chosen as the recommendation sequence corresponding with described search sequence.And for example, the prompting sequence that the second acquisition device 112 obtains according to the first acquisition device 111, carrying out the degree of correlation with the recommendation sequence of having demarcated in recommending data storehouse 14 mates, calculate the degree of correlation between described prompting sequence and described recommendation sequence of having demarcated, then selecting device 113 compares described recommendation degree and recommendation degree threshold value, as as described in recommendation degree threshold value be 0.7, and recommendation degree is chosen as the recommendation sequence corresponding with described search sequence higher than the prompting sequence of described recommendation degree threshold value.Those skilled in the art will be understood that the above-mentioned mode of choosing corresponding recommendation sequence according to described recommendation degree from described prompting sequence is only for giving an example; other existing or modes of choosing corresponding recommendation sequence according to described recommendation degree from described prompting sequence that may occur are from now on as applicable to the present invention; also should be included in protection domain of the present invention, and be contained in this with way of reference.
Preferably, in selected equipment 1, recommend retrieval device 11 each device between work continuously.Particularly, the first acquisition device 111 obtains the prompting sequence corresponding with described search sequence; The second acquisition device 112, according to described prompting sequence, carries out matching operation in recommending data storehouse, obtains the recommendation degree corresponding with described prompting sequence; Selecting device 113, according to described recommendation degree, is chosen the recommendation sequence corresponding with described search sequence from described prompting sequence.At this, it will be understood by those skilled in the art that " continuing " refers to that each device of recommending retrieval device 11 in selected equipment 1 requires to obtain prompting sequence, obtains the recommendation degree corresponding with described prompting sequence, chooses the recommendation sequence corresponding with described search sequence according to the mode of operation of setting or adjust in real time respectively, until recommend retrieval device 11 to stop in a long time obtaining the prompting sequence corresponding with described search sequence.
(with reference to Fig. 1) in a preferred embodiment, described recommendation retrieval device 11, according to described user's search sequence, carries out matching inquiry in negative feedback dictionary, to obtain described recommendation sequence.For example, the first acquisition device 111 in described recommendation retrieval device 11 obtains the prompting sequence corresponding with described search sequence; Then, recommend retrieval device 11 according to described prompting sequence, in described negative feedback dictionary, carry out matching inquiry, to obtain the prompting sequence after filtering, such as, can inquire about while obtaining described prompting sequence when described negative feedback dictionary, described prompting sequence is screened out; Then, described the second acquisition device 112, according to the prompting sequence after described filtration, carries out matching operation in recommending data storehouse, to obtain the recommendation degree corresponding with described prompting sequence; Finally, described selecting device 113, according to described recommendation degree, is chosen described recommendation sequence from described prompting sequence.And for example, the first acquisition device 111 in described recommendation retrieval device 11 obtains the prompting sequence corresponding with described search sequence, then, described the second acquisition device 112 is according to described prompting sequence, in recommending data storehouse and negative feedback dictionary, carry out respectively matching operation and matching inquiry, to obtain the recommendation degree corresponding and calibrated with described prompting sequence, such as, the second acquisition device 112 is according to described prompting sequence, in described recommending data storehouse, carry out matching operation and obtain the first recommendation degree 1.0 corresponding with described prompting sequence, meanwhile, the second acquisition device 112 carries out matching inquiry in described negative feedback dictionary, and to obtain the second recommendation degree corresponding with described prompting sequence be also 1.0 according to described prompting sequence, the second acquisition device 112 obtains the recommendation degree 0.0 corresponding and calibrated with described prompting sequence based on above-mentioned the first recommendation degree with the second recommendation degree, that is, although described prompting sequence is in described recommending data storehouse, the match is successful, but because described prompting sequence is also present in described negative feedback dictionary, the corresponding recommendation degree of this prompting sequence is still lower, finally, described selecting device 113, according to described calibrated recommendation degree, is chosen described recommendation sequence from described prompting sequence.For another example, the first acquisition device 111 in described recommendation retrieval device 11 obtains the prompting sequence corresponding with described search sequence; Then, described the second acquisition device 112, according to described prompting sequence, carries out matching operation in recommending data storehouse, to obtain the recommendation degree corresponding with described prompting sequence; Then, described selecting device 113, according to described recommendation degree, is chosen described recommendation sequence from described prompting sequence; Finally, described recommendation retrieval device 11 is according to the selected recommendation sequence of described selecting device 113, in described negative feedback dictionary, carry out matching inquiry, to obtain filtered described recommendation sequence, such as, described recommendation retrieval device 11 carries out matching inquiry by recommendation sequence selected described selecting device 113 in described negative feedback dictionary, and successfully recommends sequence to be screened out matching inquiry, thereby obtains still higher recommendation sequence of filtered and user's satisfaction.Preferably, described selected equipment 1 also comprises the second updating device (not shown), this second updating device, according to described recommendation sequence, in conjunction with described user's User behavior statistical study, obtains the user satisfaction feedback information corresponding with described recommendation sequence; According to described user's satisfaction feedback information, in conjunction with satisfaction threshold value, set up or upgrade described negative feedback dictionary.Particularly, the second updating device is according to the selected recommendation sequence of described recommendation retrieval device 11, the User behavior of doing for described recommendation sequence in conjunction with described user carries out statistical study, obtain the user satisfaction feedback information corresponding with described recommendation sequence, then according to described user's satisfaction feedback information, by with the comparison of satisfaction threshold value, set up or upgrade described negative feedback dictionary, for example, the active user's satisfaction reflecting when the corresponding user's satisfaction of described recommendation sequence feedback information is during lower than described satisfaction threshold value, described recommendation sequence is added into described negative feedback dictionary.At this, the corresponding user's satisfaction of described recommendation sequence feedback information is by obtaining such as the corresponding user operation records of this recommendation sequence is carried out to statistical study.At this, described negative feedback dictionary comprise be selected as recommend sequence but after the certain hour of interval active user's satisfaction of selected recommendation sequence lower than the sequence of satisfaction threshold value.For example, when user to recommend sequence corresponding Query Result carry out page turning, again when page turn over operation, because active user's satisfaction of this recommendation sequence is lower, selected equipment 1 can be added into negative feedback dictionary by described recommendation sequence.Recommendation retrieval device 11 of the present invention is by such as recommendation sequence selected selecting device 113 is carried out to matching inquiry in negative feedback dictionary, and active user's satisfaction of described recommendation sequence is assessed, to determine whether active user's satisfaction of described recommendation sequence reaches the requirement of satisfaction threshold value, thereby the selected recommendation sequence of sustainable guarantee has higher user's satisfaction, the personalized search that promotes user is experienced.Those skilled in the art will be understood that above-mentioned carry out in negative feedback dictionary according to described user's search sequence matching inquiry in the mode that obtains described recommendation sequence only as for example; other existing or may occur from now on carry out in negative feedback dictionary according to described user's search sequence matching inquiry in the mode that obtains described recommendation sequence as applicable to the present invention; also should be included in protection domain of the present invention, and be contained in this with way of reference.
Preferably, described the first acquisition device 111 obtains the described search sequence that described user inputs by subscriber equipment, and described selected equipment 1 also comprises generator (not shown), the described recommendation sequence corresponding with described search sequence offered described subscriber equipment by described generator.For example, the communication mode of the application programming interfaces (API) that described the first acquisition device 111 provides by third party devices such as search engines or agreement, obtains from this third party device the search sequence that described user inputs by subscriber equipment; Or, pass through page technology, as ASP, JSP, PHP etc., obtain from subscriber equipment the search sequence that described user inputs by this subscriber equipment, then described generator is according to the corresponding recommendation sequence of the described selecting device 113 described search sequence of inputting by subscriber equipment with user that obtain, adopt any known computing machine that the technological means of readable information is provided, such as screen display, loudspeaker broadcasting etc., offer this subscriber equipment by described recommendation sequence.Taking screen display as example, generator by described recommendation sequence in certain sequence and/or form offer this subscriber equipment.At this, user inputs the mode of described search sequence by described subscriber equipment, include but not limited to input by keyboard, mouse, telepilot, touch pad, handwriting equipment or voice-input device, and input by the input frame of browser software, application program or client software etc.More preferably, described generator is also based on the default rule that provides, the described prompting sequence corresponding with described search sequence and described recommendation sequence are had to differentiation and offer described subscriber equipment, wherein, described default provide rule comprise based on below at least any one described prompting sequence and described recommendation sequence are offered to described subscriber equipment:
The font of-described recommendation sequence;
The color of-described recommendation sequence;
The special identifier symbol of-described recommendation sequence;
Providing sequentially of-described recommendation sequence.
Taking the described default font of rule based on described recommendation sequence that provide, described prompting sequence and described recommendation sequence are offered to described subscriber equipment as example, when described prompting sequence and described recommendation sequence are offered described subscriber equipment by described generator, the font of described recommendation sequence is tuned up to show and be different from general prompting sequence, or the font-weight of described recommendation sequence is different to general prompting sequence to show, in the time that user input query sequence is inquired about, which can be distinguished is significantly to recommend sequence, and which is general prompting sequence.Taking the described default color of rule based on described recommendation sequence that provide, described prompting sequence and described recommendation sequence are offered to described subscriber equipment as example, when described prompting sequence and described recommendation sequence are offered described subscriber equipment by described generator, the color of described recommendation sequence is set to be different from general prompting sequence, such as, all recommendation sequences are with red display, general prompting sequence is with black display, or, described recommendation sequence is added to background color, to be different from general prompting sequence, in the time that user input query sequence is inquired about, which can be distinguished is significantly to recommend sequence, which is general prompting sequence.Taking the described default special identifier symbol of rule based on described recommendation sequence that provide, described prompting sequence and described recommendation sequence are offered to described subscriber equipment as example, when described prompting sequence and described recommendation sequence are offered described subscriber equipment by described generator, described recommendation sequence above or mark some special identifier symbols below, such as, *, △, ★, ◇ etc., to be different from general prompting sequence, in the time that user input query sequence is inquired about, which can be distinguished is significantly to recommend sequence, and which is general prompting sequence.Taking described default the provide order of rule based on described recommendation sequence that provide, described prompting sequence and described recommendation sequence are offered to described subscriber equipment as example, when described prompting sequence and described recommendation sequence are offered described subscriber equipment by described generator, first described prompting sequence is offered to described subscriber equipment, and then described recommendation sequence is offered to described subscriber equipment; Or, first described recommendation sequence is offered to described subscriber equipment, and then described prompting sequence is offered to described subscriber equipment, in the time that user input query sequence is inquired about, which can be distinguished is significantly to recommend sequence, which is general prompting sequence.Those skilled in the art will be understood that the above-mentioned default rule that provides is only for giving an example, and other default rules that provide existing or that may occur from now on, as applicable to the present invention, also should be included in protection domain of the present invention, and be contained in this with way of reference.
Preferably, described the first acquisition device 111, according to described search sequence, in conjunction with semantic extension processing, obtains described prompting sequence.Particularly, described the first acquisition device 111, according to described search sequence, obtains the prompting sequence corresponding with described search sequence by the Query Result such as corresponding with described search sequence and/or click behavior.For example, in the time that described search sequence is " concert ", by analyzing Query Result and/or the click behavior corresponding with " concert ", the enquiry frequency of finding " Wang Fei concert ", " concert of Liu De China " is higher, and described the first acquisition device 111 obtains the prompting sequence corresponding with described search sequence " concert " " Wang Fei concert " and " concert of Liu De China ".Those skilled in the art will be understood that the above-mentioned mode of obtaining the prompting sequence corresponding with described search sequence is only for giving an example; other existing or modes of obtaining the prompting sequence corresponding with described search sequence that may occur are from now on as applicable to the present invention; also should be included in protection domain of the present invention, and be contained in this with way of reference.
Fig. 2 illustrate according to one preferred embodiment of the present invention for choosing the equipment schematic diagram of recommendation sequence of search sequence.Wherein, selected equipment 1 ' includes but not limited to the cloud that network host, single network server, multiple webserver collection or multiple server form.At this, cloud can be made up of a large amount of computing machines based on cloud computing (Cloud Computing) or the webserver, and wherein, cloud computing is a kind of super virtual machine being made up of the loosely-coupled computing machine collection of a group of Distributed Calculation.Wherein, described selected equipment 1 ' comprises recommends retrieval device 11 ', the 3rd acquisition device 15 ' and the first updating device 16 ', wherein, described recommendation retrieval device 11 ' comprises the first acquisition device 111 ', the second acquisition device 112 ' and selecting device 113 '.
In the selected equipment 1 ' shown in Fig. 2, the first acquisition device 111 ', the second acquisition device 112 ', selecting device 113 ' are same or similar with the first acquisition device 111, the second acquisition device 112, selecting device 113 shown in Fig. 1 respectively, for describing for simplicity, so locate to repeat no more, and mode is by reference contained in this.
Described the 3rd acquisition device 15 ', based on default mining rule, according to the sequence to be excavated that obtains Query Result, obtains the high-quality sequence corresponding with described sequence to be excavated; Then, described the first updating device 16 ' is according to described high-quality sequence, sets up or upgrades described recommending data storehouse 14 '; Described the second acquisition device 112 ', according to described prompting sequence, carries out matching operation in described recommending data storehouse 14 ', to obtain the recommendation degree corresponding with described prompting sequence.At this, described high-quality sequence comprises corresponding with described sequence to be excavated and has a sequence of high user satisfaction.Particularly, the 3rd acquisition device 15 ' is based on default mining rule, according to the sequence to be excavated that obtains Query Result, the communication mode of the application programming interfaces (API) that provide by the third party device such as such as search engine or agreement, obtains the high-quality sequence corresponding with described sequence to be excavated from this third party device.Those skilled in the art will be understood that mode that sequence to be excavated that above-mentioned basis has obtained Query Result obtains corresponding high-quality sequence is only for for example; the mode that other sequences to be excavated according to obtaining Query Result existing or that may occur are from now on obtained corresponding high-quality sequence is as applicable to the present invention; also should be included in protection domain of the present invention, and be contained in this with way of reference.
Then high-quality sequence that, the first updating device 16 ' obtains based on the 3rd acquisition device 15 ' is set up or is upgraded described recommending data storehouse 14 '.Preferably, described default mining rule comprises: based on below at least any one obtain described high-quality sequence:
The first user satisfaction of first result in the-described Query Result corresponding with described sequence to be excavated;
The result degree of correlation and second user's satisfaction in-the Preset Time corresponding with described sequence to be excavated.
The first user satisfaction that comprises first result in the described Query Result corresponding with described sequence to be excavated taking described default mining rule is as example, described the 3rd acquisition device 15 ' is according to the sequence to be excavated that obtains Query Result, by such as the user query behavior of first result in the corresponding Query Result of described sequence to be excavated is carried out to statistical study, to obtain corresponding first user satisfaction, and from described sequence to be excavated, obtain described high-quality sequence according to described first user satisfaction.For example, in the time that user is inputted sequence to be excavated " Shanghai weather forecast " and is inquired about by subscriber equipment, if first result in Query Result directly shown the temperature data on the Shanghai City same day, in Query Result, first the corresponding first user satisfaction of result is higher, described the 3rd acquisition device 15 ' obtains sequence to be excavated " Shanghai weather forecast " as high-quality sequence, and then described high-quality sequence " Shanghai weather forecast " is updated to described recommending data storehouse 14 ' by described the first updating device 16 '.More preferably, the duration that described the 3rd acquisition device 15 ' also obtains first article of result in Query Result, and the described duration is combined with described first user satisfaction, from described sequence to be excavated, obtain described high-quality sequence, duration such as first the result corresponding with described sequence to be excavated is longer, and first user satisfaction is higher.Comprise that taking described default mining rule the result degree of correlation in the Preset Time corresponding with described sequence to be excavated and second user's satisfaction are as example, described the 3rd acquisition device 15 ' is according to the sequence to be excavated that obtains Query Result, by the user query behavior such as calculating the described sequence to be excavated Query Result corresponding with the accordingly correlativity between Query Result and statistical study and described sequence to be excavated, whether relevantly determine between described sequence to be excavated and Query Result, to judge whether the demand of user when a large number of users uses this sequence to be excavated to inquire about is met and then obtains described second user's satisfaction.For example, the result degree of correlation when between described sequence to be excavated and corresponding Query Result is higher, and corresponding with described sequence to be excavated second user's satisfaction is when higher, described the 3rd acquisition device 15 ' obtains described sequence to be excavated as described high-quality sequence, and described the first updating device 16 ' is set up by described high-quality sequence or upgrades described recommending data storehouse 14 '.More preferably, described the 3rd acquisition device 15 ' can also be by the result degree of correlation corresponding with described sequence to be excavated and second user's satisfaction, in conjunction with corresponding result degree of correlation threshold value and second user's satisfaction threshold value, and in the time that the described result degree of correlation is not less than described result degree of correlation threshold value and described second user's satisfaction and is not less than described second user's satisfaction threshold value, obtain described sequence to be excavated as high-quality sequence.Those skilled in the art will be understood that the above-mentioned mode of obtaining the high-quality sequence corresponding with described sequence to be excavated is only for giving an example; other existing or modes of obtaining the high-quality sequence corresponding with described sequence to be excavated that may occur are from now on as applicable to the present invention; also should be included in protection domain of the present invention, and be contained in this with way of reference.
In addition, the above-mentioned selected equipment for the recommendation sequence of choosing search sequence can combine with existing search engine, forms a kind of new search engine, and existing search engine can adopt known to search engines such as Baidu, Google, Yahoo.
Preferably, this search engine is based on the default rule that provides, and described prompting sequence and described recommendation sequence had to differentiation and offer described subscriber equipment; Wherein, describedly default provide rule to comprise: based on below at least any one described recommendation sequence is offered to described subscriber equipment:
The font of-described recommendation sequence;
The color of-described recommendation sequence;
The special identifier symbol of-described recommendation sequence;
Providing sequentially of-described recommendation sequence.
Taking the described default font of rule based on described recommendation sequence that provide, described prompting sequence and described recommendation sequence are offered to described subscriber equipment as example, when described prompting sequence and described recommendation sequence are offered described subscriber equipment by this search engine, the font of described recommendation sequence is tuned up to show and be different from general prompting sequence, or the font-weight of described recommendation sequence is different to general prompting sequence to show, in the time that user input query sequence is inquired about, which can be distinguished is significantly to recommend sequence, and which is general prompting sequence.Taking the described default color of rule based on described recommendation sequence that provide, described prompting sequence and described recommendation sequence are offered to described subscriber equipment as example, when described prompting sequence and described recommendation sequence are offered described subscriber equipment by this search engine, the color of described recommendation sequence is set to be different from general prompting sequence, such as, all recommendation sequences are with red display, general prompting sequence is with black display, or, described recommendation sequence is added to background color, to be different from general prompting sequence, in the time that user input query sequence is inquired about, which can be distinguished is significantly to recommend sequence, which is general prompting sequence.Taking the described default special identifier symbol of rule based on described recommendation sequence that provide, described prompting sequence and described recommendation sequence are offered to described subscriber equipment as example, when described prompting sequence and described recommendation sequence are offered described subscriber equipment by this search engine, described recommendation sequence above or mark some special identifier symbols below, such as, *, △, ★, ◇ etc., to be different from general prompting sequence, in the time that user input query sequence is inquired about, which can be distinguished is significantly to recommend sequence, and which is general prompting sequence.Taking described default the provide order of rule based on described recommendation sequence that provide, described prompting sequence and described recommendation sequence are offered to described subscriber equipment as example, when described prompting sequence and described recommendation sequence are offered described subscriber equipment by this search engine, first described prompting sequence is offered to described subscriber equipment, and then described recommendation sequence is offered to described subscriber equipment; Or, first described recommendation sequence is offered to described subscriber equipment, and then described prompting sequence is offered to described subscriber equipment, in the time that user input query sequence is inquired about, which can be distinguished is significantly to recommend sequence, which is general prompting sequence.Those skilled in the art will be understood that the above-mentioned default rule that provides is only for giving an example, and other default rules that provide existing or that may occur from now on, as applicable to the present invention, also should be included in protection domain of the present invention, and be contained in this with way of reference.
Fig. 3 illustrate according to a further aspect of the present invention for choosing the method flow diagram of recommendation sequence of search sequence.Wherein, the cloud that includes but not limited to that for choosing the selected equipment of recommendation sequence of search sequence network host, single network server, multiple webserver collection or multiple server form.At this, cloud can be made up of a large amount of computing machines based on cloud computing (Cloud Computing) or the webserver, and wherein, cloud computing is a kind of super virtual machine being made up of the loosely-coupled computing machine collection of a group of Distributed Calculation.Wherein, the method comprising the steps of S1, and described step S1 further comprises step S11, step S12 and step S13.
In step S1, selected equipment is obtained the recommendation sequence corresponding with described search sequence according to user's search sequence.Wherein, in step S11, selected equipment is obtained the prompting sequence corresponding with described search sequence.Particularly, the communication mode of the application programming interfaces (API) that selected equipment for example provides by third party devices such as search engines or agreement, obtains the prompting sequence corresponding with described search sequence from this third party device; Or, the communication mode of the application programming interfaces (API) that provide by third party devices such as search engines or agreement, obtain from this third party device the search sequence that this user inputs by subscriber equipment, and by the mode such as such as front suffix match, unisonance coupling, fuzzy phoneme coupling or nearly word form coupling, obtain the prompting sequence corresponding with this search sequence; Or, by page technology, as ASP, JSP, PHP etc., obtain from subscriber equipment the search sequence that user inputs by this subscriber equipment, and by the mode such as such as front suffix match, unisonance coupling, fuzzy phoneme coupling or nearly word form coupling, obtain the prompting sequence corresponding with this search sequence.For example, in the time that user keys in search sequence " Shanghai traffic " by subscriber equipment, selected equipment is obtained this search sequence " Shanghai traffic " from described subscriber equipment, then obtains the prompting sequence " Shanghai Communications University " corresponding with described search sequence " Shanghai traffic " according to front suffix match; Or, obtain the prompting sequence " Shanghai Transit Service circuit " corresponding with described search sequence " Shanghai traffic ", " Shanghai rail transit circuit ", " Shanghai Airport information " etc. according to the result of described search sequence being carried out to semantic analysis.Those skilled in the art will be understood that the above-mentioned mode of obtaining the prompting sequence corresponding with described search sequence is only for giving an example; other existing or modes of obtaining the prompting sequence corresponding with described search sequence that may occur are from now on as applicable to the present invention; also should be included in protection domain of the present invention, and be contained in this with way of reference.
Then, in step S 12, selected equipment, according to described prompting sequence, is carried out matching operation in recommending data storehouse, to obtain the recommendation degree corresponding with described prompting sequence.Particularly, selected equipment, according to the prompting sequence obtaining in described step S11, is carried out matching operation in recommending data storehouse, and obtains the recommendation degree corresponding with described prompting sequence according to the result of matching inquiry.For example, selected equipment, according to the prompting sequence obtaining in described step S11, is carried out matching inquiry in recommending data storehouse, when described prompting sequence can be searched while obtaining in described recommending data storehouse, the recommendation degree of described prompting sequence is the highest, if recommendation degree is 1.0; In described recommending data storehouse, cannot search while obtaining when described prompting sequence, the recommendation degree of described prompting sequence is minimum, if recommendation degree is 0.0.And for example, selected equipment is according to the prompting sequence obtaining in described step S11, carrying out the degree of correlation with the recommendation sequence of having demarcated in recommending data storehouse mates, calculate the degree of correlation between described prompting sequence and described recommendation sequence of having demarcated, in the time that the degree of correlation between described prompting sequence and described recommendation sequence of having demarcated is higher, the recommendation degree of described prompting sequence is correspondingly also higher, and for example, described recommendation degree can be normalized to any number between 0.0 to 1.0.At this, described recommending data storehouse both can be arranged in described selected equipment, also can be arranged in the network equipment being connected by network with described selected equipment, described network includes but not limited to internet, wide area network, Metropolitan Area Network (MAN), LAN (Local Area Network), VPN network, wireless self-organization network (Ad Hoc network) etc.Those skilled in the art will be understood that the above-mentioned mode of obtaining corresponding recommendation degree according to described prompting sequence is only for giving an example; other existing or modes of obtaining corresponding recommendation degree according to described prompting sequence that may occur are from now on as applicable to the present invention; also should be included in protection domain of the present invention, and be contained in this with way of reference.
Then,, in step S13, selected equipment, according to described recommendation degree, is chosen the recommendation sequence corresponding with described search sequence from described prompting sequence.Particularly, described selected equipment is according to the recommendation degree corresponding to described prompting sequence obtaining in described step S12, by such as based on recommendation degree, prompting sequence being classified, described prompting sequence carried out to the modes such as examination in conjunction with recommendation degree threshold value, from described prompting sequence, choose the recommendation sequence corresponding with described search sequence.For example, the prompting sequence that selected equipment is obtained according to described step S11, in recommending data storehouse, carry out matching inquiry to obtain the corresponding recommendation degree of described prompting sequence, then according to described recommendation degree, described prompting sequence is classified according to recommendation degree, for example, the prompting sequence that is 1.0 by all recommendation degree is divided into a class, and the prompting sequence that is 0.0 by all recommendation degree is divided into a class, and the one or more prompting sequences that are 1.0 using recommendation degree are chosen as the recommendation sequence corresponding with described search sequence.And for example, described selected equipment is according to the prompting sequence obtaining in described step S11, carrying out the degree of correlation with the recommendation sequence of having demarcated in recommending data storehouse mates, calculate the degree of correlation between described prompting sequence and described recommendation sequence of having demarcated, then described recommendation degree and recommendation degree threshold value are compared, as as described in recommendation degree threshold value be 0.7, and recommendation degree is chosen as the recommendation sequence corresponding with described search sequence higher than the prompting sequence of described recommendation degree threshold value.Those skilled in the art will be understood that the above-mentioned mode of choosing corresponding recommendation sequence according to described recommendation degree from described prompting sequence is only for giving an example; other existing or modes of choosing corresponding recommendation sequence according to described recommendation degree from described prompting sequence that may occur are from now on as applicable to the present invention; also should be included in protection domain of the present invention, and be contained in this with way of reference.
(with reference to Fig. 3) in a preferred embodiment, the method also comprises step S4 (not shown), and in described step S4, selected equipment is according to described user's search sequence, in negative feedback dictionary, carry out matching inquiry, to obtain described recommendation sequence.For example, in step S11, described selected equipment is obtained the prompting sequence corresponding with described search sequence; Then according to described prompting sequence, in described negative feedback dictionary, carry out matching inquiry, to obtain the prompting sequence after filtration, such as, can inquire about while obtaining described prompting sequence when described negative feedback dictionary, described prompting sequence is screened out; Then, according to the prompting sequence after described filtration, in recommending data storehouse, carry out matching operation, to obtain the recommendation degree corresponding with described prompting sequence; Finally, described selected equipment, according to described recommendation degree, is chosen described recommendation sequence from described prompting sequence.And for example, in step S11, described selected equipment is obtained the prompting sequence corresponding with described search sequence, then according to described prompting sequence, in recommending data storehouse and negative feedback dictionary, carry out respectively matching operation and matching inquiry, to obtain the recommendation degree corresponding and calibrated with described prompting sequence, such as, described selected equipment is according to described prompting sequence, in described recommending data storehouse, carry out matching operation and obtain the first recommendation degree 1.0 corresponding with described prompting sequence, meanwhile, selected equipment is carried out matching inquiry in described negative feedback dictionary, and to obtain the second recommendation degree corresponding with described prompting sequence be also 1.0 according to described prompting sequence, selected equipment obtains the recommendation degree 0.0 corresponding and calibrated with described prompting sequence based on above-mentioned the first recommendation degree with the second recommendation degree, that is, although described prompting sequence is in described recommending data storehouse, the match is successful, but because described prompting sequence is also present in described negative feedback dictionary, the corresponding recommendation degree of this prompting sequence is still lower, finally, described selected equipment, according to described calibrated recommendation degree, is chosen described recommendation sequence from described prompting sequence.For another example,, in step S11, described selected equipment is obtained the prompting sequence corresponding with described search sequence; Then according to described prompting sequence, in recommending data storehouse, carry out matching operation, to obtain the recommendation degree corresponding with described prompting sequence; Then, described selected equipment, according to described recommendation degree, is chosen described recommendation sequence from described prompting sequence; Finally, according to selected recommendation sequence, in described negative feedback dictionary, carry out matching inquiry, to obtain filtered described recommendation sequence, such as, selected equipment is carried out matching inquiry by selected recommendation sequence in described negative feedback dictionary, and successfully recommends sequence to be screened out matching inquiry, thereby obtains still higher recommendation sequence of filtered and active user's satisfaction.Preferably, the method also comprises step S7 (not shown), and in described step S7, described selected equipment is according to described recommendation sequence, in conjunction with described user's User behavior statistical study, obtain the user satisfaction feedback information corresponding with described recommendation sequence; According to described user's satisfaction feedback information, in conjunction with satisfaction threshold value, set up or upgrade described negative feedback dictionary.Particularly, in described step S7, selected equipment is according to selected recommendation sequence, the User behavior of doing for described recommendation sequence in conjunction with described user carries out statistical study, obtain the user satisfaction feedback information corresponding with described recommendation sequence, then according to described user's satisfaction feedback information, by with the comparison of satisfaction threshold value, set up or upgrade described negative feedback dictionary, for example, the active user's satisfaction reflecting when the corresponding user's satisfaction of described recommendation sequence feedback information is during lower than described satisfaction threshold value, described recommendation sequence is added into described negative feedback dictionary.At this, the corresponding user's satisfaction of described recommendation sequence feedback information is by obtaining such as the corresponding user operation records of this recommendation sequence is carried out to statistical study.At this, described negative feedback dictionary comprise be selected as recommend sequence but after the certain hour of interval active user's satisfaction of selected recommendation sequence lower than the sequence of satisfaction threshold value.For example, when user to recommend sequence corresponding Query Result carry out page turning, again when page turn over operation, because active user's satisfaction of this recommendation sequence is lower, selected equipment can be added into negative feedback dictionary by described recommendation sequence.The present invention is by such as selected recommendation sequence is carried out to matching inquiry in negative feedback dictionary, and active user's satisfaction of described recommendation sequence is assessed, to determine whether active user's satisfaction of described recommendation sequence reaches the requirement of satisfaction threshold value, thereby the selected recommendation sequence of sustainable guarantee has higher user's satisfaction, the personalized search that promotes user is experienced.Those skilled in the art will be understood that above-mentioned carry out in negative feedback dictionary according to described user's search sequence matching inquiry in the mode that obtains described recommendation sequence only as for example; other existing or may occur from now on carry out in negative feedback dictionary according to described user's search sequence matching inquiry in the mode that obtains described recommendation sequence as applicable to the present invention; also should be included in protection domain of the present invention, and be contained in this with way of reference.
Preferably, in step S11, described selected equipment is obtained the described search sequence that described user inputs by subscriber equipment, and the method also comprises step S8 (not shown), in described step S8, the described recommendation sequence corresponding with described search sequence offered described subscriber equipment by selected equipment.For example, in step S11, the communication mode of the application programming interfaces (API) that selected equipment provides by third party devices such as search engines or agreement, obtains from this third party device the search sequence that described user inputs by subscriber equipment; Or, pass through page technology, as ASP, JSP, PHP etc., obtain from subscriber equipment the search sequence that described user inputs by this subscriber equipment, then in step S8, the recommendation sequence that selected equipment is corresponding according to the obtained described search sequence of inputting by subscriber equipment with user, adopts any known computing machine that the technological means of readable information is provided, such as screen display, loudspeaker broadcasting etc., offer this subscriber equipment by described recommendation sequence.Taking screen display as example, selected equipment by described recommendation sequence in certain sequence and/or form offer this subscriber equipment.At this, user inputs the mode of described search sequence by described subscriber equipment, include but not limited to input by keyboard, mouse, telepilot, touch pad, handwriting equipment or voice-input device, and input by the input frame of browser software, application program or client software etc.More preferably, described selected equipment is also based on the default rule that provides, the described prompting sequence corresponding with described search sequence and described recommendation sequence are had to differentiation and offer described subscriber equipment, wherein, described default provide rule comprise based on below at least any one described prompting sequence and described recommendation sequence are offered to described subscriber equipment:
The font of-described recommendation sequence;
The color of-described recommendation sequence;
The special identifier symbol of-described recommendation sequence;
Providing sequentially of-described recommendation sequence.
Taking the described default font of rule based on described recommendation sequence that provide, described prompting sequence and described recommendation sequence are offered to described subscriber equipment as example, when described prompting sequence and described recommendation sequence are offered described subscriber equipment by described selected equipment, the font of described recommendation sequence is tuned up to show and be different from general prompting sequence, or the font-weight of described recommendation sequence is different to general prompting sequence to show, in the time that user input query sequence is inquired about, which can be distinguished is significantly to recommend sequence, and which is general prompting sequence.Taking the described default color of rule based on described recommendation sequence that provide, described prompting sequence and described recommendation sequence are offered to described subscriber equipment as example, when described prompting sequence and described recommendation sequence are offered described subscriber equipment by described selected equipment, the color of described recommendation sequence is set to be different from general prompting sequence, such as, all recommendation sequences are with red display, general prompting sequence is with black display, or, described recommendation sequence is added to background color, to be different from general prompting sequence, in the time that user input query sequence is inquired about, which can be distinguished is significantly to recommend sequence, which is general prompting sequence.Taking the described default special identifier symbol of rule based on described recommendation sequence that provide, described prompting sequence and described recommendation sequence are offered to described subscriber equipment as example, when described prompting sequence and described recommendation sequence are offered described subscriber equipment by described selected equipment, described recommendation sequence above or mark some special identifier symbols below, such as, *, △, ★, ◇ etc., to be different from general prompting sequence, in the time that user input query sequence is inquired about, which can be distinguished is significantly to recommend sequence, and which is general prompting sequence.Taking described default the provide order of rule based on described recommendation sequence that provide, described prompting sequence and described recommendation sequence are offered to described subscriber equipment as example, when described prompting sequence and described recommendation sequence are offered described subscriber equipment by described selected equipment, first described prompting sequence is offered to described subscriber equipment, and then described recommendation sequence is offered to described subscriber equipment; Or, first described recommendation sequence is offered to described subscriber equipment, and then described prompting sequence is offered to described subscriber equipment, in the time that user input query sequence is inquired about, which can be distinguished is significantly to recommend sequence, which is general prompting sequence.Those skilled in the art will be understood that the above-mentioned default rule that provides is only for giving an example, and other default rules that provide existing or that may occur from now on, as applicable to the present invention, also should be included in protection domain of the present invention, and be contained in this with way of reference.
Preferably, in described step S11, selected equipment, according to described search sequence, in conjunction with semantic extension processing, is obtained described prompting sequence.Particularly, described selected equipment, according to described search sequence, is obtained the prompting sequence corresponding with described search sequence by the Query Result such as corresponding with described search sequence and/or click behavior.For example, in the time that described search sequence is " concert ", by analyzing Query Result and/or the click behavior corresponding with " concert ", the enquiry frequency of finding " Wang Fei concert ", " concert of Liu De China " is higher, and described selected equipment is obtained the prompting sequence corresponding with described search sequence " concert " " Wang Fei concert " and " concert of Liu De China ".Those skilled in the art will be understood that the above-mentioned mode of obtaining the prompting sequence corresponding with described search sequence is only for giving an example; other existing or modes of obtaining the prompting sequence corresponding with described search sequence that may occur are from now on as applicable to the present invention; also should be included in protection domain of the present invention, and be contained in this with way of reference.
Fig. 4 illustrate according to one preferred embodiment of the present invention for choosing the method flow diagram of recommendation sequence of search sequence.Wherein, the cloud that includes but not limited to that for choosing the selected equipment of recommendation sequence of search sequence network host, single network server, multiple webserver collection or multiple server form.At this, cloud can be made up of a large amount of computing machines based on cloud computing (Cloud Computing) or the webserver, and wherein, cloud computing is a kind of super virtual machine being made up of the loosely-coupled computing machine collection of a group of Distributed Calculation.Wherein, the method comprising the steps of S1 ', step S5 ' and step S6 ', wherein, described step S1 ' further comprises step S11 ', step S12 ' and step S13 '.
With reference to Fig. 4, step S11 ', step S12 ', step S13 ' are same or similar with the step S11 shown in Fig. 3, step S12, step S13 respectively, and for describing for simplicity, so locate to repeat no more, and mode is by reference contained in this.
In step S5 ', described selected equipment, based on default mining rule, according to the sequence to be excavated that obtains Query Result, is obtained the high-quality sequence corresponding with described sequence to be excavated; Then, described in described step S6 ', described selected equipment is according to described high-quality sequence, sets up or upgrades described recommending data storehouse; In step S12 ', described selected equipment, according to described prompting sequence, is carried out matching operation in described recommending data storehouse, to obtain the recommendation degree corresponding with described prompting sequence.At this, described high-quality sequence comprises corresponding with described sequence to be excavated and has a sequence of high user satisfaction.Particularly, in step S5 ', described selected equipment is based on default mining rule, according to the sequence to be excavated that obtains Query Result, the communication mode of the application programming interfaces (API) that provide by the third party device such as such as search engine or agreement, obtains the high-quality sequence corresponding with described sequence to be excavated from this third party device.Those skilled in the art will be understood that mode that sequence to be excavated that above-mentioned basis has obtained Query Result obtains corresponding high-quality sequence is only for for example; the mode that other sequences to be excavated according to obtaining Query Result existing or that may occur are from now on obtained corresponding high-quality sequence is as applicable to the present invention; also should be included in protection domain of the present invention, and be contained in this with way of reference.
Then,, in described step S6 ', the high-quality sequence of selected equipment based on obtained set up or upgraded described recommending data storehouse.Preferably, described default mining rule comprises: based on below at least any one obtain described high-quality sequence:
The first user satisfaction of first result in the-described Query Result corresponding with described sequence to be excavated;
The result degree of correlation and second user's satisfaction in-the Preset Time corresponding with described sequence to be excavated.
The first user satisfaction that comprises first result in the described Query Result corresponding with described sequence to be excavated taking described default mining rule is as example, in step S5 ', selected equipment is according to the sequence to be excavated that obtains Query Result, by such as the user query behavior of first result in the corresponding Query Result of described sequence to be excavated is carried out to statistical study, to obtain corresponding first user satisfaction, and from described sequence to be excavated, obtain described high-quality sequence according to described first user satisfaction.For example, in the time that user is inputted sequence to be excavated " Shanghai weather forecast " and is inquired about by subscriber equipment, if first result in Query Result directly shown the temperature data on the Shanghai City same day, in Query Result, first the corresponding first user satisfaction of result is higher, described selected equipment is obtained sequence to be excavated " Shanghai weather forecast " as high-quality sequence, then described high-quality sequence " Shanghai weather forecast " is updated to described recommending data storehouse.More preferably, in step S5 ', described selected equipment is also obtained the duration of first result in Query Result, and the described duration is combined with described first user satisfaction, from described sequence to be excavated, obtain described high-quality sequence, duration such as first the result corresponding with described sequence to be excavated is longer, and first user satisfaction is higher.Comprise that taking described default mining rule the result degree of correlation in the Preset Time corresponding with described sequence to be excavated and second user's satisfaction are as example, in step S5 ', described selected equipment is according to the sequence to be excavated that obtains Query Result, by the user query behavior such as calculating the described sequence to be excavated Query Result corresponding with the accordingly correlativity between Query Result and statistical study and described sequence to be excavated, whether relevantly determine between described sequence to be excavated and Query Result, to judge whether the demand of user when a large number of users uses this sequence to be excavated to inquire about is met and then obtains described second user's satisfaction.For example, the result degree of correlation when between described sequence to be excavated and corresponding Query Result is higher, and corresponding with described sequence to be excavated second user's satisfaction is when higher, described selected equipment is obtained described sequence to be excavated as described high-quality sequence, and is set up or upgraded described recommending data storehouse by described high-quality sequence.More preferably, described selected equipment can also be by the result degree of correlation corresponding with described sequence to be excavated and second user's satisfaction, in conjunction with corresponding result degree of correlation threshold value and second user's satisfaction threshold value, and in the time that the described result degree of correlation is not less than described result degree of correlation threshold value and described second user's satisfaction and is not less than described second user's satisfaction threshold value, obtain described sequence to be excavated as high-quality sequence.Those skilled in the art will be understood that the above-mentioned mode of obtaining the high-quality sequence corresponding with described sequence to be excavated is only for giving an example; other existing or modes of obtaining the high-quality sequence corresponding with described sequence to be excavated that may occur are from now on as applicable to the present invention; also should be included in protection domain of the present invention, and be contained in this with way of reference.
To those skilled in the art, obviously the invention is not restricted to the details of above-mentioned example embodiment, and in the situation that not deviating from spirit of the present invention or essential characteristic, can realize the present invention with other concrete form.Therefore, no matter from which point, all should regard embodiment as exemplary, and be nonrestrictive, scope of the present invention is limited by claims instead of above-mentioned explanation, is therefore intended to all changes that drop in the implication and the scope that are equal to important document of claim to include in the present invention.Any Reference numeral in claim should be considered as limiting related claim.In addition, obviously other unit or step do not got rid of in " comprising " word, and odd number is not got rid of plural number.Multiple unit of stating in system claim or device also can be realized by software or hardware by a unit or device.The first, the second word such as grade is used for representing title, and does not represent any specific order.

Claims (16)

1. computer implemented for choosing the method for recommendation sequence for search sequence, wherein, the method comprising the steps of:
X, based on default mining rule, according to the sequence to be excavated that obtains Query Result, obtains the high-quality sequence corresponding with described sequence to be excavated;
-according to described high-quality sequence, set up or renewal recommending data storehouse;
A obtains the recommendation sequence corresponding with described search sequence according to user's search sequence; Wherein, described steps A comprises the following steps:
A obtains the prompting sequence corresponding with described search sequence;
B, according to described prompting sequence, carries out matching operation in described recommending data storehouse, to obtain the recommendation degree corresponding with described prompting sequence;
C, according to described recommendation degree, chooses described recommendation sequence from described prompting sequence;
Wherein, described default mining rule comprises: based on below at least any one obtain described high-quality sequence:
The first user satisfaction of first result in the-described Query Result corresponding with described sequence to be excavated;
The result degree of correlation and second user's satisfaction in-the Preset Time corresponding with described sequence to be excavated.
2. method according to claim 1, wherein, described default mining rule comprises: obtain described high-quality sequence based on described first user satisfaction;
Wherein, described step x also comprises:
-based on described default mining rule, according to the sequence described to be excavated that obtains Query Result, in conjunction with the duration of described first result, obtain described high-quality sequence.
3. method according to claim 1 and 2, wherein, described default mining rule comprises: obtain described high-quality sequence based on the described result degree of correlation and described second user's satisfaction;
Wherein, described step x also comprises:
-based on described default mining rule, according to the sequence described to be excavated that obtains Query Result, in conjunction with result degree of correlation threshold value and second user's satisfaction threshold value, obtain described high-quality sequence.
4. method according to claim 1, wherein, described steps A also comprises:
-according to described user's search sequence, in negative feedback dictionary, carry out matching inquiry, to obtain described recommendation sequence.
5. method according to claim 4, wherein, the method also comprises:
-according to described recommendation sequence, in conjunction with described user's User behavior statistical study, obtain the user satisfaction feedback information corresponding with described recommendation sequence;
-according to described user's satisfaction feedback information, in conjunction with satisfaction threshold value, set up or upgrade described negative feedback dictionary.
6. method according to claim 1, wherein, described step a also comprises:
-obtain the described search sequence that described user inputs by subscriber equipment;
Wherein, described method also comprises:
The described recommendation sequence corresponding with described search sequence offered described subscriber equipment by w.
7. method according to claim 6, wherein, described step w also comprises:
-based on the default rule that provides, described prompting sequence and described recommendation sequence are had to differentiation and offer described subscriber equipment;
Wherein, describedly default provide rule to comprise: based on below at least any one described prompting sequence and described recommendation sequence are offered to described subscriber equipment:
The font of-described recommendation sequence;
The color of-described recommendation sequence;
The special identifier symbol of-described recommendation sequence;
Providing sequentially of-described recommendation sequence.
8. method according to claim 1, wherein, described step a also comprises:
-according to described search sequence, in conjunction with semantic extension processing, obtain described prompting sequence.
9. for choosing the equipment of recommendation sequence for search sequence, wherein, described equipment comprises:
The 3rd acquisition device, for based on default mining rule, according to the sequence to be excavated that obtains Query Result, obtains the high-quality sequence corresponding with described sequence to be excavated;
The first updating device, for according to described high-quality sequence, sets up or renewal recommending data storehouse;
Recommend retrieval device, for obtain the recommendation sequence corresponding with described search sequence according to user's search sequence;
Wherein, described recommendation retrieval device comprises:
The first acquisition device, for obtaining the prompting sequence corresponding with described search sequence;
The second acquisition device for according to described prompting sequence, carries out matching operation in described recommending data storehouse, to obtain the recommendation degree corresponding with described prompting sequence;
Selecting device for according to described recommendation degree, is chosen described recommendation sequence from described prompting sequence;
Wherein, described default mining rule comprises: based on below at least any one obtain described high-quality sequence:
The first user satisfaction of first result in the-described Query Result corresponding with described sequence to be excavated;
The result degree of correlation and second user's satisfaction in-the Preset Time corresponding with described sequence to be excavated.
10. equipment according to claim 9, wherein, described default mining rule comprises: obtain described high-quality sequence based on described first user satisfaction;
Wherein, described the 3rd acquisition device also for:
-based on described default mining rule, according to the sequence described to be excavated that obtains Query Result, in conjunction with the duration of described first result, obtain described high-quality sequence.
11. according to the equipment described in claim 9 or 10, and wherein, described default mining rule comprises: obtain described high-quality sequence based on the described result degree of correlation and described second user's satisfaction;
Wherein, described the 3rd acquisition device also for:
-based on described default mining rule, according to the sequence described to be excavated that obtains Query Result, in conjunction with result degree of correlation threshold value and second user's satisfaction threshold value, obtain described high-quality sequence.
12. equipment according to claim 9, wherein, described recommendation retrieval device also for:
-according to described user's search sequence, in negative feedback dictionary, carry out matching inquiry, to obtain described recommendation sequence.
13. equipment according to claim 12, wherein, described equipment also comprises the second updating device, for:
-according to described recommendation sequence, in conjunction with described user's User behavior statistical study, obtain the user satisfaction feedback information corresponding with described recommendation sequence;
-according to described user's satisfaction feedback information, in conjunction with satisfaction threshold value, set up or upgrade described negative feedback dictionary.
14. equipment according to claim 9, wherein, described the first acquisition device also for:
-obtain the described search sequence that described user inputs by subscriber equipment;
Wherein, described equipment also comprises generator, for:
-the described recommendation sequence corresponding with described search sequence offered to described subscriber equipment.
15. equipment according to claim 14, wherein, described generator also for:
-based on the default rule that provides, described prompting sequence and described recommendation sequence are had to differentiation and offer described subscriber equipment;
Wherein, describedly default provide rule to comprise: based on below at least any one described prompting sequence and described recommendation sequence are offered to described subscriber equipment:
The font of-described recommendation sequence;
The color of-described recommendation sequence;
The special identifier symbol of-described recommendation sequence;
Providing sequentially of-described recommendation sequence.
16. equipment according to claim 9, wherein, described the first acquisition device also for:
-according to described search sequence, in conjunction with semantic extension processing, obtain described prompting sequence.
CN201110105486.1A 2011-04-26 2011-04-26 Equipment and method used for selecting recommended sequence of query sequence Active CN102184201B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201110105486.1A CN102184201B (en) 2011-04-26 2011-04-26 Equipment and method used for selecting recommended sequence of query sequence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201110105486.1A CN102184201B (en) 2011-04-26 2011-04-26 Equipment and method used for selecting recommended sequence of query sequence

Publications (2)

Publication Number Publication Date
CN102184201A CN102184201A (en) 2011-09-14
CN102184201B true CN102184201B (en) 2014-12-03

Family

ID=44570378

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201110105486.1A Active CN102184201B (en) 2011-04-26 2011-04-26 Equipment and method used for selecting recommended sequence of query sequence

Country Status (1)

Country Link
CN (1) CN102184201B (en)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103246654B (en) * 2012-02-03 2018-04-20 腾讯科技（深圳）有限公司 The method for displaying and processing and device of search result
CN102929957A (en) * 2012-10-09 2013-02-13 广东欧珀移动通信有限公司 Method and device for displaying sequencing result set, and mobile terminal
CN103020141B (en) * 2012-11-21 2016-06-08 北京百度网讯科技有限公司 It is a kind of for the method and apparatus of Search Results is provided
CN103885968B (en) * 2012-12-20 2019-04-12 北京百度网讯科技有限公司 It is a kind of for providing the method and apparatus of recommendation information
CN105808685B (en) * 2016-03-02 2021-09-28 腾讯科技（深圳）有限公司 Promotion information pushing method and device
CN106971004B (en) * 2017-04-26 2021-04-06 百度在线网络技术（北京）有限公司 Search result providing method and device

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101203856A (en) * 2005-06-20 2008-06-18 电子湾有限公司 System to generate related search queries
CN101321190A (en) * 2008-07-04 2008-12-10 清华大学 Recommend method and recommend system of heterogeneous network

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101251854A (en) * 2008-03-19 2008-08-27 深圳先进技术研究院 Method for creating index lexical item as well as data retrieval method and system

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101203856A (en) * 2005-06-20 2008-06-18 电子湾有限公司 System to generate related search queries
CN101321190A (en) * 2008-07-04 2008-12-10 清华大学 Recommend method and recommend system of heterogeneous network

Also Published As

Publication number Publication date
CN102184201A (en) 2011-09-14

Similar Documents

Publication Publication Date Title
CN102184201B (en) Equipment and method used for selecting recommended sequence of query sequence
US10268765B2 (en) Query construction on online social networks
CN102306171B (en) A kind of for providing network to access suggestion and the method and apparatus of web search suggestion
JP2021527260A (en) Regular expression generation based on positive pattern matching examples and negative pattern matching examples
US20110264804A1 (en) Cloud-based web content filtering
CN103631954A (en) Individualized recommendation method and device
CN103092826B (en) A kind of method and apparatus of input information architecture input entry according to user
CN102968454B (en) A kind of for obtaining the method and apparatus promoting object search results
KR101788498B1 (en) Method, Apparatus and device for providing information
CN103136253A (en) Method and device of acquiring information
CN102855261A (en) Method and device for determining video authority value
CN107809740B (en) Wi-Fi hotspot deployment optimization method, server and storage medium
CN103744575A (en) Method and equipment for providing input auxiliary areas of input applications
CA2920689A1 (en) Data sanitization and normalization and geocoding methods
US10553000B2 (en) Analytics visualization
CN102156724A (en) Method and device for matching suffix of inquiry segment
JP2014006864A (en) Method of providing preview content interlocked with retrieval word automatic completion
CN103365892A (en) Method and device for processing multiple contact objects
CN102722502A (en) Method and device for obtaining redundance-free suggested inquiry sequence
CN103514193A (en) Method and device used for determining popularization result information of popularization keyword
CN102314498B (en) Method and equipment for implementing main identification of page
US10448124B2 (en) Method and system for issuing media information
CN103064967A (en) Method and device used for establishing user binary relation bases
CN103514206A (en) Method and device for determining popularization configuration information corresponding to objective popularization object
CN103514190A (en) Method and device used for determining optimization information of target popularization information

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant