CN103514269A - Second query term determined to be related to first query term based on natural searching results - Google Patents
Second query term determined to be related to first query term based on natural searching results Download PDFInfo
- Publication number
- CN103514269A CN103514269A CN201310414817.9A CN201310414817A CN103514269A CN 103514269 A CN103514269 A CN 103514269A CN 201310414817 A CN201310414817 A CN 201310414817A CN 103514269 A CN103514269 A CN 103514269A
- Authority
- CN
- China
- Prior art keywords
- query word
- search results
- candidate
- query
- natural 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3338—Query expansion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a method and device for determining a second query term related to a first query term based on natural searching results. The method comprises the first step of obtaining the natural searching results corresponding to the first query term inputted by a user and the natural searching results corresponding to one or more candidate query terms respectively, the second step of determining the relevancy between the first query term and the one or more candidate query terms respectively according to check processing of the natural searching results corresponding to the first query term and the one or more candidate query terms, and the third step of determining the second query term related to the first query term from the one or more candidate query terms according to the relevancy. Compared with the prior art, the relevancy between the second query term and the first query term inputted by the user is guaranteed, furthermore, the relevancy between the displaying results corresponding to the second query term and the first query term is improved, and therefore the usage experience of the searching user is improved.
Description
Technical field
The present invention relates to search technique field, relate in particular to a kind of for determine the technology of the second query word being associated with the first query word based on natural Search Results.
Background technology
In user search process, except offering user's natural Search Results corresponding with the query word of its input, search engine can offer equally this user corresponding represent result, this represents result and for example according to word corresponding to this query word, triggers and represent.Yet, if this query word that represents result and this user input does not match or matching degree is lower, can greatly have influence on user's search experience.
Therefore, how to improve and represent result, or say it, this represents word corresponding to result, and the degree of correlation with the query word of user input, becomes those skilled in the art and need one of technical matters of solution badly.
The mode that prior art conventionally adopts manual evaluation and weighs by clicking rate.Yet the sample coverage rate individuality low, that be subject to appraiser of manual evaluation affects greatly; The mode of weighing by clicking rate is limited to user's clicking rate and the actual inconsistency natural between result that represents of wishing selection, causes practical operation to have larger error.
Summary of the invention
The object of this invention is to provide a kind of for determine the method and apparatus of the second query word being associated with the first query word based on natural Search Results.
According to an aspect of the present invention, provide a kind of for determine the method for the second query word being associated with the first query word based on natural Search Results, wherein, the method comprises the following steps:
A obtains respectively the corresponding natural Search Results of the first query word of user's input, and the corresponding natural Search Results of one or more candidate's query word;
B, according to the checking treatment to described the first query word and the corresponding natural Search Results of candidate's query word, determines respectively the degree of correlation of described the first query word and described one or more candidate's query words;
C, according to the described degree of correlation, determines the second query word being associated with described the first query word in described one or more candidate's query words.
According to a further aspect in the invention, also provide a kind of for determine the equipment of the second query word being associated with the first query word based on natural Search Results, wherein, this equipment comprises:
Result acquisition device, for obtaining respectively the corresponding natural Search Results of the first query word of user's input, and the corresponding natural Search Results of one or more candidate's query word;
Degree of correlation determining device, for according to the checking treatment to described the first query word and the corresponding natural Search Results of candidate's query word, determines respectively the degree of correlation of described the first query word and described one or more candidate's query words;
Query word determining device for according to the described degree of correlation, is determined the second query word being associated with described the first query word in described one or more candidate's query words.
Compared with prior art, the present invention obtains respectively the corresponding natural Search Results of the first query word of user's input, and the corresponding natural Search Results of one or more candidate's query word; According to the checking treatment to described the first query word and the corresponding natural Search Results of candidate's query word, determine respectively the degree of correlation of described the first query word and described one or more candidate's query words; According to the described degree of correlation, in described one or more candidate's query words, determine the second query word being associated with described the first query word, guaranteed the degree of correlation of the first query word of this second query word and user's input, further, improve the degree of correlation that represents result and this first query word corresponding to this second query word, promoted the experience of search subscriber.
Accompanying drawing explanation
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 determine the equipment schematic diagram of the second query word be associated with the first query word based on natural Search Results;
Fig. 2 illustrate in accordance with a preferred embodiment of the present invention for determine the equipment schematic diagram of the second query word be associated with the first query word based on natural Search Results;
Fig. 3 illustrate according to a further aspect of the present invention for determine the method flow diagram of the second query word be associated with the first query word based on natural Search Results;
Fig. 4 illustrate in accordance with a preferred embodiment of the present invention for determine the method flow diagram of the second query word be associated with the first query word based on natural Search Results.
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 determine the equipment schematic diagram of the second query word be associated with the first query word based on natural Search Results.Equipment 1 comprises result acquisition device 101, degree of correlation determining device 102 and query word determining device 103.
Wherein, result acquisition device 101 obtains respectively the corresponding natural Search Results of the first query word of user's input, and the corresponding natural Search Results of one or more candidate's query word.Particularly, result acquisition device 101 is according to the first query word of user's input, and the one or more candidate query words corresponding with this first query word, obtain respectively the natural Search Results corresponding with this first query word, and the natural Search Results corresponding with these one or more candidate's query words, for example, this result acquisition device 101 is according to this first query word and candidate's query word, in offline storage record, carry out matching inquiry, obtain respectively the corresponding natural Search Results of this first query word, and the corresponding natural Search Results of this candidate's query word.Or, mutual by with subscriber equipment of user, inputted the first query word, equipment 1 is by the application programming interfaces (API) that call this subscriber equipment and provide or the communication interface of other agreements, obtained the first query word of this user's input, then, by the mode such as mate in dictionary in inquiry, obtain the corresponding one or more candidate's query words of this first query word, subsequently, this result acquisition device 101 by carrying out matching inquiry in offline storage record, or, the process of searching for by simulating nature, obtain respectively the corresponding natural Search Results of this first query word, and the corresponding natural Search Results of this candidate's query word.
Those skilled in the art will be understood that the above-mentioned mode of obtaining nature Search Results is only for giving an example; other existing or modes of obtaining nature Search Results 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 with way of reference, be contained in this at this.
Degree of correlation determining device 102, according to the checking treatment to described the first query word and the corresponding natural Search Results of candidate's query word, is determined respectively the degree of correlation of described the first query word and described one or more candidate's query words.Particularly, the corresponding natural Search Results of the first query word that degree of correlation determining device 102 is obtained according to this result acquisition device 101, and the corresponding natural Search Results of this candidate's query word, these two natural Search Results are carried out to checking treatment, for example, the title of these two natural Search Results, summary or its splicing result are carried out to checking treatment, and then, according to the result of this checking treatment, determine respectively the degree of correlation of this first query word and these one or more candidate's query words.For example, through the checking treatment to these two natural Search Results, find that in these two natural Search Results, same or similar word is greater than predetermined quantity, judge that these two natural Search Results are relevant, according to the quantity of this same or similar word, also can quantize this degree of correlation, further to determine the degree of correlation of this first query word and this candidate's query word.
At this, checking treatment includes but not limited to splice checking treatment, cross check processing etc.For example, natural Search Results corresponding to the first query word that this degree of correlation determining device 102 is obtained respectively according to result acquisition device 101, the natural Search Results corresponding with candidate's query word, respectively these two natural Search Results title and summary separately spliced to processing, with formation long article separately originally, subsequently, these two long articles are originally carried out to checking treatment, for example, by word frequency algorithm, the latent semantic analysis algorithm of probability or document frequency algorithm etc., determine the degree of correlation between these two long articles originally, said process can be considered the splicing checking treatment to natural Search Results corresponding to this first query word natural Search Results corresponding with candidate's query word.And for example, this degree of correlation determining device 102 is carried out checking treatment by the summary of the title of natural Search Results corresponding to the first query word natural Search Results corresponding with candidate's query word respectively, or, the title of the summary of natural Search Results corresponding to this first query word natural Search Results corresponding with this candidate's query word is carried out to checking treatment, to determine the degree of correlation between the two, said process can be considered to be processed the cross check of natural Search Results corresponding to this first query word natural Search Results corresponding with candidate's query word.Preferably, the title of this nature Search Results is with summary only for giving an example, and those skilled in the art also can adopt the other guide of nature Search Results, the object such as content of pages, image content or anchor text etc. as checking treatment.Subsequently, degree of correlation determining device 102, according to the result of checking treatment, is determined the degree of correlation of this first query word and this candidate's query word, and and then determines respectively the degree of correlation of this first query word and a plurality of candidate's query words.
Preferably, first query word or the corresponding a plurality of natural Search Results of candidate's query word possibility, this degree of correlation determining device 102 can be carried out checking treatment to the plurality of natural Search Results respectively, for example, by a natural Search Results corresponding to the first query word respectively a plurality of natural Search Results corresponding with candidate's query word carry out checking treatment, vice versa, or a plurality of natural Search Results that this first query word is corresponding carries out checking treatment with the corresponding a plurality of natural Search Results of candidate's query word respectively.
Those skilled in the art will be understood that the mode of above-mentioned checking treatment is only for giving an example; the mode of other checking treatment existing or that may occur is from now on as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.Those skilled in the art also will be understood that the mode of above-mentioned definite degree of correlation is only for giving an example; the mode of other definite degrees of correlation existing or that may occur is from now on as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
Query word determining device 103, according to the described degree of correlation, is determined the second query word being associated with described the first query word in described one or more candidate's query words.Particularly, query word determining device 103 is according to the determined degree of correlation of this degree of correlation determining device 102, in these one or more candidate's query words, determine the second query word being associated with this first query word, for example, according to the height of the degree of correlation, in these one or more candidate's query words using the degree of correlation higher than candidate's query word of predetermined threshold as the second query word, or, these one or more candidate's query words are sorted from high to low according to the degree of correlation, and candidate's query word of the predetermined quantity that therefrom selection is stood out is as the second query word.
For example, the first query word of user's input is " seventh evening of the seventh moon in lunarcalendar ", and associated candidate's query word comprises " fresh flower ", " chocolate ", " rose " etc.Result acquisition device 101 obtains respectively this first query word and the corresponding natural Search Results of candidate's query word, for example, the title of the natural Search Results that this first query word " seventh evening of the seventh moon in lunarcalendar " is corresponding is " experience in knowledge-seventh evening of the seventh moon in lunarcalendar in the seventh evening of the seventh moon in lunarcalendar ", the summary of this nature Search Results be " Valentine's Day in the seventh evening of the seventh moon in lunarcalendar; send what present of TA good? following 10 sections of brands are chocolate, leisurely are all enough to transmit your great tenderness between lovers ... " And the title of the natural Search Results of candidate's query word " fresh flower " correspondence is " fresh flower-Ruili net ", summary is for " fresh flower wedding mostly is with flower: rose, tulip, lily, carnation, iris, African Chrysanthemum, magnitude all over the sky, flower language general idea is true sincere, pure, spotless white loving.These gorgeous colored materials are that wedding has increased warm atmosphere ... " The title of the natural Search Results that candidate's query word " chocolate " is corresponding is " the chocolate column of chocolate brand ranking _ brand family ", summary for " chocolate brand ranking list; which plate chocolate has? chocolate which plate is good? chocolate brand is complete works of, chocolate brand ranking ... " The title of the natural Search Results that candidate's query word " rose " is corresponding is " effect of [rose] rose and effect _ PClady encyclopaedia _ Pacific Ocean women's net ", makes a summary as " rose taste is pungent, sweet, slightly warm in nature.The Xie Yu that regulates the flow of vital energy, dampness elimination and in, promoting blood circulation to remove blood stasis.For liver-stomach disharmony, epigastric pain, the evil of vomitting uncomfortable in chest ... "Then, degree of correlation determining device 102 is according to the checking treatment to this first query word and the corresponding natural Search Results of the plurality of candidate's query word, determine respectively the degree of correlation of described the first query word and described one or more candidate's query words, for example, this candidate's query word " fresh flower " is 0.5 with the degree of correlation of this first query word " seventh evening of the seventh moon in lunarcalendar "; This candidate's query word " chocolate " is 0.7 with the degree of correlation of this first query word " seventh evening of the seventh moon in lunarcalendar "; This candidate's query word " rose " is 0.6 with the degree of correlation of this first query word " seventh evening of the seventh moon in lunarcalendar ".Subsequently, query word determining device 103, according to the degree of correlation of above-mentioned candidate's query word and this first query word, is determined " chocolate " second query word for being associated with this first query word " seventh evening of the seventh moon in lunarcalendar ".
Those skilled in the art will be understood that the above-mentioned mode of determining the second query word is only for giving an example; other existing or modes of determining the second query word 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 with way of reference, be contained in this at this.
Preferably, between each device of equipment 1, be constant work.Particularly, result acquisition device 101 obtains respectively the corresponding natural Search Results of the first query word of user's input, and the corresponding natural Search Results of one or more candidate's query word; Degree of correlation determining device 102, according to the checking treatment to described the first query word and the corresponding natural Search Results of candidate's query word, is determined respectively the degree of correlation of described the first query word and described one or more candidate's query words; Query word determining device 103, according to the described degree of correlation, is determined the second query word being associated with described the first query word in described one or more candidate's query words.At this, it will be understood by those skilled in the art that each device that " continuing " refer to equipment 1 requires to carry out the obtaining of nature Search Results, determining of the degree of correlation and determining of the second query word according to the mode of operation of setting or adjust in real time respectively.
At this, equipment 1 obtains respectively the corresponding natural Search Results of the first query word of user's input, and the corresponding natural Search Results of one or more candidate's query word; According to the checking treatment to described the first query word and the corresponding natural Search Results of candidate's query word, determine respectively the degree of correlation of described the first query word and described one or more candidate's query words; According to the described degree of correlation, in described one or more candidate's query words, determine the second query word being associated with described the first query word, guaranteed the degree of correlation of the first query word of this second query word and user's input, further, improve the degree of correlation that represents result and this first query word corresponding to this second query word, promoted the experience of search subscriber.
Preferably, described result acquisition device 101 obtains respectively the corresponding a plurality of natural Search Results of described the first query word, and the corresponding a plurality of natural Search Results of described candidate's query word; Wherein, described degree of correlation determining device 102, according to the checking treatment to described the first query word and the corresponding a plurality of natural Search Results of candidate's query word, is determined the degree of correlation of described the first query word and described candidate's query word.Particularly, result acquisition device 101 is according to this first query word and candidate's query word, in offline storage record, carry out matching inquiry, obtain respectively the corresponding a plurality of natural Search Results of this first query word, and the corresponding a plurality of natural Search Results of this candidate's query word, or, mutual by with subscriber equipment of user, inputted the first query word, equipment 1 is by the application programming interfaces (API) that call this subscriber equipment and provide or the communication interface of other agreements, obtained the first query word of this user's input, then, by the mode such as mate in dictionary in inquiry, obtain the corresponding one or more candidate's query words of this first query word, subsequently, this result acquisition device 101 by carrying out matching inquiry in offline storage record, or, the process of searching for by simulating nature, obtain respectively the corresponding a plurality of natural Search Results of this first query word, and the corresponding a plurality of natural Search Results of this candidate's query word.
Subsequently, 102 pairs of these the first query words of degree of correlation determining device and the corresponding a plurality of natural Search Results of candidate's query word carry out checking treatment, for example, this degree of correlation determining device 102 by a natural Search Results corresponding to the first query word respectively a plurality of natural Search Results corresponding with candidate's query word carry out checking treatment, vice versa, or, a plurality of natural Search Results that this first query word is corresponding carries out checking treatment with the corresponding a plurality of natural Search Results of candidate's query word respectively, to determine the degree of correlation of this first query word and candidate's query word; And then, according to the checking treatment of a plurality of natural Search Results of each candidate's query word in a plurality of natural Search Results of this first query word and this one or more candidate's query words, determine the degree of correlation of this first query word and these one or more candidate's query words.Preferably, when checking treatment, this degree of correlation determining device 102 can splice that checking treatment, cross check are processed or both combine and carry out verification.For example, degree of correlation determining device 102 is spliced checking treatment by natural Search Results corresponding to this first query word one of them natural Search Results corresponding with candidate's query word, and carries out cross check processing etc. with another natural Search Results of this candidate's query word.
At this, equipment 1 utilizes a plurality of natural Search Results to enrich the diversity of correlativity comparison, makes the measurement of the degree of correlation more accurate, has further promoted user's experience.
Preferably, described degree of correlation determining device 102 is according to the checking treatment to described the first query word and the corresponding natural Search Results of candidate's query word, utilize degree of correlation algorithm, determine respectively the degree of correlation of described the first query word and described one or more candidate's query words; Wherein, described degree of correlation algorithm comprises following at least any one:
-word frequency algorithm;
-probability semantic analysis the algorithm of diving;
-document frequency algorithm.
Particularly, the corresponding natural Search Results of the first query word that degree of correlation determining device 102 is obtained according to this result acquisition device 101, and the corresponding natural Search Results of this candidate's query word, these two natural Search Results are carried out to checking treatment, for example, title to these two natural Search Results, summary or its splicing result, utilization is such as word frequency algorithm, the probability semantic analysis algorithm of diving, the degree of correlation algorithms such as document frequency algorithm, carry out checking treatment, and then, according to the result of this checking treatment, determine respectively the degree of correlation of this first query word and these one or more candidate's query words.
At this, the number of times that word frequency algorithm utilizes given word to occur in document judges file correlation.
The latent semantic analysis algorithm of probability is the classical statistical method that the data analysing method based on double mode and co-occurrence extends, and is applied to information retrieval, filters natural language processing, the machine learning of text or other association areas.
Document frequency algorithm is the degree of correlation that the frequency of utilizing text to cut the frequency of the phrase co-occurrence in regulation collection of document after word or many phrases combination co-occurrence judges text.
Those skilled in the art will be understood that above-mentioned degree of correlation algorithm is only for giving an example, and other degree of correlation algorithms 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 with way of reference, are contained in this at this.
Fig. 2 illustrate in accordance with a preferred embodiment of the present invention for determine the equipment schematic diagram of the second query word be associated with the first query word based on natural Search Results.This equipment 1 also comprises result generator 204.Referring to Fig. 2, the preferred embodiment is described in detail: particularly, result acquisition device 201 obtains respectively the corresponding natural Search Results of the first query word of user's input, and the corresponding natural Search Results of one or more candidate's query word; Degree of correlation determining device 202, according to the checking treatment to described the first query word and the corresponding natural Search Results of candidate's query word, is determined respectively the degree of correlation of described the first query word and described one or more candidate's query words; Query word determining device 203, according to the described degree of correlation, is determined the second query word being associated with described the first query word in described one or more candidate's query words; Result generator 204, according to the second query word being associated with described the first query word, offers described user by the result that represents corresponding with described the second query word.Wherein, result acquisition device 201, degree of correlation determining device 202 and query word determining device 203 are identical with corresponding intrument shown in Fig. 1 or basic identical respectively, so locate to repeat no more, and mode is by reference contained in this.
Wherein, result generator 204, according to the second query word being associated with described the first query word, offers described user by the result that represents corresponding with described the second query word.Particularly, query word determining device 203 is after determining the second query word being associated with the first query word of this user's input, result generator 204 is according to the second query word being associated with this first query word, by modes such as matching inquiries in representing results repository, obtain the represent result corresponding with this second query word, and then, by calling dynamic page technology such as JSP, ASP or PHP, this is represented to result and offer this user.
Connect example, the first query word of user's input is " seventh evening of the seventh moon in lunarcalendar ", and associated candidate's query word comprises " fresh flower ", " chocolate ", " rose " etc.Result acquisition device 201 obtains respectively this first query word and the corresponding natural Search Results of above-mentioned candidate's query word; Then, degree of correlation determining device 202, according to the checking treatment to this first query word and the corresponding natural Search Results of candidate's query word, is determined respectively the degree of correlation of this first query word and above-mentioned a plurality of candidate's query words; Subsequently, query word determining device 203, according to this degree of correlation, determines that in above-mentioned a plurality of candidate's query words the second query word being associated with this first query word " seventh evening of the seventh moon in lunarcalendar " is " chocolate "; Then, result generator 204 is according to this second query word " chocolate ", in representing results repository, carry out matching inquiry, obtain the represent result corresponding with this second inquiry time " chocolate ", for example " No. 1 shop chocolate the whole network reserve price 100% certified products ", subsequently, by calling dynamic page technology such as JSP, ASP or PHP, this is represented to result and offer this user.
Preferably, described result generator 204 also by the natural Search Results corresponding with described the first query word and described in represent result and offer together described user.Particularly, this result generator 204 can also obtain the natural Search Results corresponding with this first query word, this nature Search Results together with representing result, this is offered to this user, for example, in zones of different or the position of result of page searching, this nature Search Results is offered to this user together with representing result, or, this nature Search Results offers user in result of page searching, and this represents result and with the page, Shipping Options Page or the suspended frame etc. that newly eject, offers this user.
In another preferred embodiment, this equipment 1 also comprises the first memory storage (not shown) and the second memory storage (not shown).This first memory storage obtains described the first query word and corresponding natural Search Results thereof in a search procedure, and deposits in offline storage record; The second memory storage obtains described candidate's query word and corresponding natural Search Results thereof in a search procedure, and deposits in described offline storage record; Wherein, described result acquisition device 201, in described offline storage record, obtains respectively the corresponding natural Search Results of the first query word of described user's input, and the corresponding natural Search Results of described one or more candidate's query word.
Particularly, mutual by with subscriber equipment of web search user, inputted the first query word, the first memory storage is by the application programming interfaces (API) that call this subscriber equipment and provide or the communication interface of other agreements, obtained the first query word of this user's input, and, mutual by with search engine or other third party devices, obtained the natural Search Results corresponding to this first query word that offers this web search user in this search procedure, the first memory storage is about to this first query word and corresponding natural Search Results deposits in offline storage record.Similarly, other web searchs user is being usingd this first query word while carrying out query search as query search word, and the first memory storage continues natural Search Results corresponding to this first query word to deposit in offline storage record.
Similar ground, usings candidate's query word while carrying out query search as query search word as web search user, and the second memory storage obtains this candidate's query word and corresponding natural Search Results thereof in this search procedure, and deposits in offline storage record.
Like this, when result acquisition device 201 need to obtain the first query word or the corresponding natural Search Results of candidate's query word, only need in this offline storage record, obtain, for example, this result acquisition device 201 is according to the first query word of user's input, and the one or more candidate query words corresponding with this first query word, directly in offline storage record, carry out matching inquiry, obtain respectively the corresponding natural Search Results of this first query word, and the corresponding natural Search Results of this candidate's query word.Or, mutual by with subscriber equipment of user, inputted the first query word, equipment 1 is by the application programming interfaces (API) that call this subscriber equipment and provide or the communication interface of other agreements, obtained the first query word of this user's input, then, by the mode such as mate in dictionary in inquiry, obtain the corresponding one or more candidate's query words of this first query word, subsequently, this result acquisition device 101 directly by carrying out matching inquiry in offline storage record, obtain respectively the corresponding natural Search Results of this first query word, and the corresponding natural Search Results of this candidate's query word.
At this, the present invention can allly represent the degree of correlation of the first query word corresponding to result and the second query word as the flux matched degree of correlation tolerance of bulk flow of current system; The degree of correlation of all the second query words that also can single the first query word trigger, as the flow matches degree of search word dimension, can be controlled in this triggering as search word dimension.
Fig. 3 illustrate according to a further aspect of the present invention for determine the method flow diagram of the second query word be associated with the first query word based on natural Search Results.
In step S301, equipment 1 obtains respectively the corresponding natural Search Results of the first query word of user's input, and the corresponding natural Search Results of one or more candidate's query word.Particularly, in step S301, equipment 1 is according to the first query word of user's input, and the one or more candidate query words corresponding with this first query word, obtain respectively the natural Search Results corresponding with this first query word, and the natural Search Results corresponding with these one or more candidate's query words, for example, in step S301, equipment 1 is according to this first query word and candidate's query word, in offline storage record, carry out matching inquiry, obtain respectively the corresponding natural Search Results of this first query word, and the corresponding natural Search Results of this candidate's query word.Or, mutual by with subscriber equipment of user, inputted the first query word, equipment 1 is by the application programming interfaces (API) that call this subscriber equipment and provide or the communication interface of other agreements, obtained the first query word of this user's input, then, by the mode such as mate in dictionary in inquiry, obtain the corresponding one or more candidate's query words of this first query word, subsequently, in step S301, equipment 1 by carrying out matching inquiry in offline storage record, or, the process of searching for by simulating nature, obtain respectively the corresponding natural Search Results of this first query word, and the corresponding natural Search Results of this candidate's query word.
Those skilled in the art will be understood that the above-mentioned mode of obtaining nature Search Results is only for giving an example; other existing or modes of obtaining nature Search Results 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 with way of reference, be contained in this at this.
In step S302, equipment 1, according to the checking treatment to described the first query word and the corresponding natural Search Results of candidate's query word, is determined respectively the degree of correlation of described the first query word and described one or more candidate's query words.Particularly, in step S302, equipment 1 is according to the corresponding natural Search Results of the first query word obtaining in step S301, and the corresponding natural Search Results of this candidate's query word, these two natural Search Results are carried out to checking treatment, for example, the title of these two natural Search Results, summary or its splicing result are carried out to checking treatment, and then, according to the result of this checking treatment, determine respectively the degree of correlation of this first query word and these one or more candidate's query words.For example, through the checking treatment to these two natural Search Results, find that in these two natural Search Results, same or similar word is greater than predetermined quantity, judge that these two natural Search Results are relevant, according to the quantity of this same or similar word, also can quantize this degree of correlation, further to determine the degree of correlation of this first query word and this candidate's query word.
At this, checking treatment includes but not limited to splice checking treatment, cross check processing etc.For example, in step S302, equipment 1 is according to natural Search Results corresponding to the first query word obtaining respectively in step S301, the natural Search Results corresponding with candidate's query word, respectively these two natural Search Results title and summary separately spliced to processing, with formation long article separately originally, subsequently, these two long articles are originally carried out to checking treatment, for example, by word frequency algorithm, the latent semantic analysis algorithm of probability or document frequency algorithm etc., determine the degree of correlation between these two long articles originally, said process can be considered the splicing checking treatment to natural Search Results corresponding to this first query word natural Search Results corresponding with candidate's query word.And for example, in step S302, equipment 1 carries out checking treatment by the summary of the title of natural Search Results corresponding to the first query word natural Search Results corresponding with candidate's query word respectively, or, the title of the summary of natural Search Results corresponding to this first query word natural Search Results corresponding with this candidate's query word is carried out to checking treatment, to determine the degree of correlation between the two, said process can be considered to be processed the cross check of natural Search Results corresponding to this first query word natural Search Results corresponding with candidate's query word.Preferably, the title of this nature Search Results is with summary only for giving an example, and those skilled in the art also can adopt the other guide of nature Search Results, the object such as content of pages, image content or anchor text etc. as checking treatment.Subsequently, in step S302, equipment 1, according to the result of checking treatment, is determined the degree of correlation of this first query word and this candidate's query word, and and then determines respectively the degree of correlation of this first query word and a plurality of candidate's query words.
Preferably, first query word or the corresponding a plurality of natural Search Results of candidate's query word possibility, in step S302, equipment 1 can carry out checking treatment to the plurality of natural Search Results respectively, for example, by a natural Search Results corresponding to the first query word respectively a plurality of natural Search Results corresponding with candidate's query word carry out checking treatment, vice versa, or a plurality of natural Search Results that this first query word is corresponding carries out checking treatment with the corresponding a plurality of natural Search Results of candidate's query word respectively.
Those skilled in the art will be understood that the mode of above-mentioned checking treatment is only for giving an example; the mode of other checking treatment existing or that may occur is from now on as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.Those skilled in the art also will be understood that the mode of above-mentioned definite degree of correlation is only for giving an example; the mode of other definite degrees of correlation existing or that may occur is from now on as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
In step S303, equipment 1, according to the described degree of correlation, is determined the second query word being associated with described the first query word in described one or more candidate's query words.Particularly, in step S303, equipment 1 is according to the determined degree of correlation in step S302, in these one or more candidate's query words, determine the second query word being associated with this first query word, for example, according to the height of the degree of correlation, in these one or more candidate's query words using the degree of correlation higher than candidate's query word of predetermined threshold as the second query word, or, these one or more candidate's query words are sorted from high to low according to the degree of correlation, and candidate's query word of the predetermined quantity that therefrom selection is stood out is as the second query word.
For example, the first query word of user's input is " seventh evening of the seventh moon in lunarcalendar ", and associated candidate's query word comprises " fresh flower ", " chocolate ", " rose " etc.In step S301, equipment 1 obtains respectively this first query word and the corresponding natural Search Results of candidate's query word, for example, the title of the natural Search Results that this first query word " seventh evening of the seventh moon in lunarcalendar " is corresponding is " experience in knowledge-seventh evening of the seventh moon in lunarcalendar in the seventh evening of the seventh moon in lunarcalendar ", the summary of this nature Search Results be " Valentine's Day in the seventh evening of the seventh moon in lunarcalendar; send what present of TA good? following 10 sections of brands are chocolate, leisurely are all enough to transmit your great tenderness between lovers ... " And the title of the natural Search Results of candidate's query word " fresh flower " correspondence is " fresh flower-Ruili net ", summary is for " fresh flower wedding mostly is with flower: rose, tulip, lily, carnation, iris, African Chrysanthemum, magnitude all over the sky, flower language general idea is true sincere, pure, spotless white loving.These gorgeous colored materials are that wedding has increased warm atmosphere ... " The title of the natural Search Results that candidate's query word " chocolate " is corresponding is " the chocolate column of chocolate brand ranking _ brand family ", summary for " chocolate brand ranking list; which plate chocolate has? chocolate which plate is good? chocolate brand is complete works of, chocolate brand ranking ... " The title of the natural Search Results that candidate's query word " rose " is corresponding is " effect of [rose] rose and effect _ PClady encyclopaedia _ Pacific Ocean women's net ", makes a summary as " rose taste is pungent, sweet, slightly warm in nature.The Xie Yu that regulates the flow of vital energy, dampness elimination and in, promoting blood circulation to remove blood stasis.For liver-stomach disharmony, epigastric pain, the evil of vomitting uncomfortable in chest ... "Then, in step S302, equipment 1 is according to the checking treatment to this first query word and the corresponding natural Search Results of the plurality of candidate's query word, determine respectively the degree of correlation of described the first query word and described one or more candidate's query words, for example, this candidate's query word " fresh flower " is 0.5 with the degree of correlation of this first query word " seventh evening of the seventh moon in lunarcalendar "; This candidate's query word " chocolate " is 0.7 with the degree of correlation of this first query word " seventh evening of the seventh moon in lunarcalendar "; This candidate's query word " rose " is 0.6 with the degree of correlation of this first query word " seventh evening of the seventh moon in lunarcalendar ".Subsequently, in step S303, equipment 1, according to the degree of correlation of above-mentioned candidate's query word and this first query word, is determined " chocolate " second query word for being associated with this first query word " seventh evening of the seventh moon in lunarcalendar ".
Those skilled in the art will be understood that the above-mentioned mode of determining the second query word is only for giving an example; other existing or modes of determining the second query word 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 with way of reference, be contained in this at this.
Preferably, between each step of equipment 1, be constant work.Particularly, in step S301, equipment 1 obtains respectively the corresponding natural Search Results of the first query word of user's input, and the corresponding natural Search Results of one or more candidate's query word; In step S302, equipment 1, according to the checking treatment to described the first query word and the corresponding natural Search Results of candidate's query word, is determined respectively the degree of correlation of described the first query word and described one or more candidate's query words; In step S303, equipment 1, according to the described degree of correlation, is determined the second query word being associated with described the first query word in described one or more candidate's query words.At this, it will be understood by those skilled in the art that each step that " continuing " refer to equipment 1 requires to carry out the obtaining of nature Search Results, determining of the degree of correlation and determining of the second query word according to the mode of operation of setting or adjust in real time respectively.
At this, equipment 1 obtains respectively the corresponding natural Search Results of the first query word of user's input, and the corresponding natural Search Results of one or more candidate's query word; According to the checking treatment to described the first query word and the corresponding natural Search Results of candidate's query word, determine respectively the degree of correlation of described the first query word and described one or more candidate's query words; According to the described degree of correlation, in described one or more candidate's query words, determine the second query word being associated with described the first query word, guaranteed the degree of correlation of the first query word of this second query word and user's input, further, improve the degree of correlation that represents result and this first query word corresponding to this second query word, promoted the experience of search subscriber.
Preferably, in step S301, equipment 1 obtains respectively the corresponding a plurality of natural Search Results of described the first query word, and the corresponding a plurality of natural Search Results of described candidate's query word; Wherein, in step S302, equipment 1, according to the checking treatment to described the first query word and the corresponding a plurality of natural Search Results of candidate's query word, is determined the degree of correlation of described the first query word and described candidate's query word.Particularly, in step S301, equipment 1, according to this first query word and candidate's query word, carries out matching inquiry in offline storage record, obtain respectively the corresponding a plurality of natural Search Results of this first query word, and the corresponding a plurality of natural Search Results of this candidate's query word, or, mutual by with subscriber equipment of user, inputted the first query word, equipment 1 is by the application programming interfaces (API) that call this subscriber equipment and provide or the communication interface of other agreements, obtained the first query word of this user's input, then, by the mode such as mate in dictionary in inquiry, obtain the corresponding one or more candidate's query words of this first query word, subsequently, in step S301, equipment 1 by carrying out matching inquiry in offline storage record, or, the process of searching for by simulating nature, obtain respectively the corresponding a plurality of natural Search Results of this first query word, and the corresponding a plurality of natural Search Results of this candidate's query word.
Subsequently, in step S302, 1 pair of this first query word of equipment and the corresponding a plurality of natural Search Results of candidate's query word carry out checking treatment, for example, in step S302, equipment 1 by a natural Search Results corresponding to the first query word respectively a plurality of natural Search Results corresponding with candidate's query word carry out checking treatment, vice versa, or, a plurality of natural Search Results that this first query word is corresponding carries out checking treatment with the corresponding a plurality of natural Search Results of candidate's query word respectively, to determine the degree of correlation of this first query word and candidate's query word, and then, according to the checking treatment of a plurality of natural Search Results of each candidate's query word in a plurality of natural Search Results of this first query word and this one or more candidate's query words, determine the degree of correlation of this first query word and these one or more candidate's query words.Preferably, when checking treatment, in step S302, equipment 1 can splice that checking treatment, cross check are processed or both combine and carry out verification.For example, in step S302, equipment 1 splices checking treatment by natural Search Results corresponding to this first query word one of them natural Search Results corresponding with candidate's query word, and carries out cross check processing etc. with another natural Search Results of this candidate's query word.
At this, equipment 1 utilizes a plurality of natural Search Results to enrich the diversity of correlativity comparison, makes the measurement of the degree of correlation more accurate, has further promoted user's experience.
Preferably, in step S302, equipment 1, according to the checking treatment to described the first query word and the corresponding natural Search Results of candidate's query word, utilizes degree of correlation algorithm, determines respectively the degree of correlation of described the first query word and described one or more candidate's query words; Wherein, described degree of correlation algorithm comprises following at least any one:
-word frequency algorithm;
-probability semantic analysis the algorithm of diving;
-document frequency algorithm.
Particularly, in step S302, equipment 1 is according to the corresponding natural Search Results of the first query word obtaining in step S301, and the corresponding natural Search Results of this candidate's query word, these two natural Search Results are carried out to checking treatment, for example, title to these two natural Search Results, summary or its splicing result, utilization is such as word frequency algorithm, the probability semantic analysis algorithm of diving, the degree of correlation algorithms such as document frequency algorithm, carry out checking treatment, and then, according to the result of this checking treatment, determine respectively the degree of correlation of this first query word and these one or more candidate's query words.
At this, the number of times that word frequency algorithm utilizes given word to occur in document judges file correlation.
The latent semantic analysis algorithm of probability is the classical statistical method that the data analysing method based on double mode and co-occurrence extends, and is applied to information retrieval, filters natural language processing, the machine learning of text or other association areas.
Document frequency algorithm is the degree of correlation that the frequency of utilizing text to cut the frequency of the phrase co-occurrence in regulation collection of document after word or many phrases combination co-occurrence judges text.
Those skilled in the art will be understood that above-mentioned degree of correlation algorithm is only for giving an example, and other degree of correlation algorithms 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 with way of reference, are contained in this at this.
Fig. 4 illustrate in accordance with a preferred embodiment of the present invention for determine the method flow diagram of the second query word be associated with the first query word based on natural Search Results.Referring to Fig. 4, the preferred embodiment is described in detail: particularly, in step S401, equipment 1 obtains respectively the corresponding natural Search Results of the first query word of user's input, and the corresponding natural Search Results of one or more candidate's query word; In step S402, equipment 1, according to the checking treatment to described the first query word and the corresponding natural Search Results of candidate's query word, is determined respectively the degree of correlation of described the first query word and described one or more candidate's query words; In step S403, equipment 1, according to the described degree of correlation, is determined the second query word being associated with described the first query word in described one or more candidate's query words; In step S404, equipment 1, according to the second query word being associated with described the first query word, offers described user by the result that represents corresponding with described the second query word.Wherein, step S401-S403 is identical or basic identical with corresponding step shown in Fig. 3 respectively, so locate to repeat no more, and mode is by reference contained in this.
Wherein, in step S404, equipment 1, according to the second query word being associated with described the first query word, offers described user by the result that represents corresponding with described the second query word.Particularly, in step S403, equipment 1 is after determining the second query word being associated with the first query word of this user's input, in step S404, equipment 1 is according to the second query word being associated with this first query word, by modes such as matching inquiries in representing results repository, obtain the represent result corresponding with this second query word, and then, by calling dynamic page technology such as JSP, ASP or PHP, this is represented to result and offer this user.
Connect example, the first query word of user's input is " seventh evening of the seventh moon in lunarcalendar ", and associated candidate's query word comprises " fresh flower ", " chocolate ", " rose " etc.In step S401, equipment 1 obtains respectively this first query word and the corresponding natural Search Results of above-mentioned candidate's query word; Then,, in step S402, equipment 1, according to the checking treatment to this first query word and the corresponding natural Search Results of candidate's query word, is determined respectively the degree of correlation of this first query word and above-mentioned a plurality of candidate's query words; Subsequently, in step S403, equipment 1, according to this degree of correlation, determines that in above-mentioned a plurality of candidate's query words the second query word being associated with this first query word " seventh evening of the seventh moon in lunarcalendar " is " chocolate "; Then, in step S404, equipment 1 is according to this second query word " chocolate ", in representing results repository, carry out matching inquiry, obtain the represent result corresponding with this second inquiry time " chocolate ", for example " No. 1 shop chocolate the whole network reserve price 100% certified products ", subsequently, by calling dynamic page technology such as JSP, ASP or PHP, this is represented to result and offer this user.
Preferably, in step S404, equipment 1 also by the natural Search Results corresponding with described the first query word and described in represent result and offer together described user.Particularly, in step S404, equipment 1 can also obtain the natural Search Results corresponding with this first query word, this nature Search Results together with representing result, this is offered to this user, for example, zones of different or position at result of page searching, this nature Search Results is offered to this user together with representing result, or, this nature Search Results offers user in result of page searching, and this represents result and with the page, Shipping Options Page or the suspended frame etc. that newly eject, offers this user.
In another preferred embodiment, the method also comprises that step S405(is not shown) and step S406(not shown).In step S405, equipment 1 obtains described the first query word and corresponding natural Search Results thereof in a search procedure, and deposits in offline storage record; In step S406, equipment 1 obtains described candidate's query word and corresponding natural Search Results thereof in a search procedure, and deposits in described offline storage record; Wherein, in step S401, equipment 1, in described offline storage record, obtains respectively the corresponding natural Search Results of the first query word of described user's input, and the corresponding natural Search Results of described one or more candidate's query word.
Particularly, mutual by with subscriber equipment of web search user, inputted the first query word, in step S405, equipment 1 is by the application programming interfaces (API) that call this subscriber equipment and provide or the communication interface of other agreements, obtained the first query word of this user's input, and, mutual by with search engine or other third party devices, obtained the natural Search Results corresponding to this first query word that offers this web search user in this search procedure, in step S405, equipment 1 is about to this first query word and corresponding natural Search Results deposits in offline storage record.Similarly, other web searchs user is usining this first query word while carrying out query search as query search word, and in step S405, equipment 1 continues natural Search Results corresponding to this first query word to deposit in offline storage record.
Similar ground, usings candidate's query word while carrying out query search as query search word as web search user, and in step S406, equipment 1 obtains this candidate's query word and corresponding natural Search Results thereof in this search procedure, and deposits in offline storage record.
Like this, when in step S401, when equipment 1 need to obtain the first query word or the corresponding natural Search Results of candidate's query word, only need in this offline storage record, obtain, for example, in step S401, equipment 1 is according to the first query word of user's input, and the one or more candidate query words corresponding with this first query word, directly in offline storage record, carry out matching inquiry, obtain respectively the corresponding natural Search Results of this first query word, and the corresponding natural Search Results of this candidate's query word.Or, mutual by with subscriber equipment of user, inputted the first query word, equipment 1 is by the application programming interfaces (API) that call this subscriber equipment and provide or the communication interface of other agreements, obtained the first query word of this user's input, then, by the mode such as mate in dictionary in inquiry, obtain the corresponding one or more candidate's query words of this first query word, subsequently, in step S401, equipment 1 directly by carrying out matching inquiry in offline storage record, obtain respectively the corresponding natural Search Results of this first query word, and the corresponding natural Search Results of this candidate's query word.
At this, the present invention can allly represent the degree of correlation of the first query word corresponding to result and the second query word as the flux matched degree of correlation tolerance of bulk flow of current system; The degree of correlation of all the second query words that also can single the first query word trigger, as the flow matches degree of search word dimension, can be controlled in this triggering as search word dimension.
It should be noted that the present invention can be implemented in the assembly of software and/or software and hardware, for example, can adopt special IC (ASIC), general object computing machine or any other similar hardware device to realize.In one embodiment, software program of the present invention can carry out to realize step mentioned above or function by processor.Similarly, software program of the present invention (comprising relevant data structure) can be stored in computer readable recording medium storing program for performing, for example, and RAM storer, magnetic or CD-ROM driver or flexible plastic disc and similar devices.In addition, steps more of the present invention or function can adopt hardware to realize, for example, thereby as coordinate the circuit of carrying out each step or function with processor.
In addition, a part of the present invention can be applied to computer program, and for example computer program instructions, when it is carried out by computing machine, by the operation of this computing machine, can call or provide the method according to this invention and/or technical scheme.And call the programmed instruction of method of the present invention, may be stored in fixing or movably in recording medium, and/or be transmitted by the data stream in broadcast or other signal bearing medias, and/or be stored in according in the working storage of the computer equipment of described programmed instruction operation.At this, comprise according to one embodiment of present invention a device, this device comprises for storing the storer of computer program instructions and for the processor of execution of program instructions, wherein, when this computer program instructions is carried out by this processor, trigger this device and move based on aforementioned according to the method for a plurality of embodiment of the present invention and/or technical scheme.
To those skilled in the art, obviously the invention is not restricted to the details of above-mentioned one exemplary 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 rather than above-mentioned explanation, is therefore intended to be included in the present invention dropping on the implication that is equal to important document of claim and all changes in scope.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.A plurality of unit that device is stated in claim or device also can You Yige unit or device by software or hardware, realize.The first, the second word such as grade is used for representing title, and does not represent any specific order.
Claims (12)
1. for determine a method for the second query word being associated with the first query word based on natural Search Results, wherein, the method comprises the following steps:
A obtains respectively the corresponding natural Search Results of the first query word of user's input, and the corresponding natural Search Results of one or more candidate's query word;
B, according to the checking treatment to described the first query word and the corresponding natural Search Results of candidate's query word, determines respectively the degree of correlation of described the first query word and described one or more candidate's query words;
C, according to the described degree of correlation, determines the second query word being associated with described the first query word in described one or more candidate's query words.
2. method according to claim 1, wherein, described checking treatment comprises following at least any one:
-splicing checking treatment;
-cross check is processed.
3. method according to claim 1 and 2, wherein, described step a comprises:
-obtain respectively the corresponding a plurality of natural Search Results of described the first query word, and the corresponding a plurality of natural Search Results of described candidate's query word;
Wherein, described step b comprises:
-according to the checking treatment to described the first query word and the corresponding a plurality of natural Search Results of candidate's query word, determine the degree of correlation of described the first query word and described candidate's query word.
4. according to the method in any one of claims 1 to 3, wherein, described step b comprises:
-according to the checking treatment to described the first query word and the corresponding natural Search Results of candidate's query word, utilize degree of correlation algorithm, determine respectively the degree of correlation of described the first query word and described one or more candidate's query words;
Wherein, described degree of correlation algorithm comprises following at least any one:
-word frequency algorithm;
-probability semantic analysis the algorithm of diving;
-document frequency algorithm.
5. according to the method described in any one in claim 1 to 4, wherein, the method also comprises:
-according to the second query word being associated with described the first query word, the represent result corresponding with described the second query word offered to described user.
6. according to the method described in any one in claim 1 to 5, wherein, the method also comprises:
-in a search procedure, obtain described the first query word and corresponding natural Search Results thereof, and deposit in offline storage record;
-in a search procedure, obtain described candidate's query word and corresponding natural Search Results thereof, and deposit in described offline storage record;
Wherein, described step a comprises:
-in described offline storage record, obtain respectively the corresponding natural Search Results of the first query word of described user's input, and the corresponding natural Search Results of described one or more candidate's query word.
7. for determine an equipment for the second query word being associated with the first query word based on natural Search Results, wherein, this equipment comprises:
Result acquisition device, for obtaining respectively the corresponding natural Search Results of the first query word of user's input, and the corresponding natural Search Results of one or more candidate's query word;
Degree of correlation determining device, for according to the checking treatment to described the first query word and the corresponding natural Search Results of candidate's query word, determines respectively the degree of correlation of described the first query word and described one or more candidate's query words;
Query word determining device for according to the described degree of correlation, is determined the second query word being associated with described the first query word in described one or more candidate's query words.
8. equipment according to claim 7, wherein, described checking treatment comprises following at least any one:
-splicing checking treatment;
-cross check is processed.
9. according to the equipment described in claim 7 or 8, wherein, described result acquisition device is used for:
-obtain respectively the corresponding a plurality of natural Search Results of described the first query word, and the corresponding a plurality of natural Search Results of described candidate's query word;
Wherein, described degree of correlation determining device is used for:
-according to the checking treatment to described the first query word and the corresponding a plurality of natural Search Results of candidate's query word, determine the degree of correlation of described the first query word and described candidate's query word.
10. according to the equipment described in any one in claim 7 to 9, wherein, described degree of correlation determining device is used for:
-according to the checking treatment to described the first query word and the corresponding natural Search Results of candidate's query word, utilize degree of correlation algorithm, determine respectively the degree of correlation of described the first query word and described one or more candidate's query words;
Wherein, described degree of correlation algorithm comprises following at least any one:
-word frequency algorithm;
-probability semantic analysis the algorithm of diving;
-document frequency algorithm.
11. according to the equipment described in any one in claim 7 to 10, and wherein, this equipment also comprises:
Result generator, for according to the second query word being associated with described the first query word, offers described user by the result that represents corresponding with described the second query word.
12. according to the equipment described in any one in claim 7 to 11, and wherein, this equipment also comprises:
The first memory storage, for obtaining described the first query word and corresponding natural Search Results thereof from a search procedure, and deposits in offline storage record;
The second memory storage, for obtaining described candidate's query word and corresponding natural Search Results thereof from a search procedure, and deposits in described offline storage record;
Wherein, described result acquisition device is used for:
-in described offline storage record, obtain respectively the corresponding natural Search Results of the first query word of described user's input, and the corresponding natural Search Results of described one or more candidate's query word.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310414817.9A CN103514269B (en) | 2013-09-12 | 2013-09-12 | Second query word associated with the first query word is determined based on natural search result |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310414817.9A CN103514269B (en) | 2013-09-12 | 2013-09-12 | Second query word associated with the first query word is determined based on natural search result |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103514269A true CN103514269A (en) | 2014-01-15 |
| CN103514269B CN103514269B (en) | 2017-08-01 |
Family
ID=49896993
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310414817.9A Active CN103514269B (en) | 2013-09-12 | 2013-09-12 | Second query word associated with the first query word is determined based on natural search result |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103514269B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104391710A (en) * | 2014-12-15 | 2015-03-04 | 北京奇虎科技有限公司 | Template generation method for tile-matching type games and tile-matching type game device |
| CN106126561A (en) * | 2016-06-16 | 2016-11-16 | 北京百度网讯科技有限公司 | The generation method and device of Search Results summary |
| CN108319614A (en) * | 2017-01-18 | 2018-07-24 | 百度在线网络技术（北京）有限公司 | Information acquisition method, device and system |
| CN109918661A (en) * | 2019-03-04 | 2019-06-21 | 腾讯科技（深圳）有限公司 | Synonym acquisition methods and device |
| CN110297930A (en) * | 2019-06-14 | 2019-10-01 | 韶关市启之信息技术有限公司 | A kind of colored language methods of exhibiting and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070220037A1 (en) * | 2006-03-20 | 2007-09-20 | Microsoft Corporation | Expansion phrase database for abbreviated terms |
| CN101241512A (en) * | 2008-03-10 | 2008-08-13 | 北京搜狗科技发展有限公司 | Search method for redefining enquiry word and device therefor |
| CN102033955A (en) * | 2010-12-24 | 2011-04-27 | 常华 | Method for expanding user search results and server |
-
2013
- 2013-09-12 CN CN201310414817.9A patent/CN103514269B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070220037A1 (en) * | 2006-03-20 | 2007-09-20 | Microsoft Corporation | Expansion phrase database for abbreviated terms |
| CN101241512A (en) * | 2008-03-10 | 2008-08-13 | 北京搜狗科技发展有限公司 | Search method for redefining enquiry word and device therefor |
| CN102033955A (en) * | 2010-12-24 | 2011-04-27 | 常华 | Method for expanding user search results and server |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104391710A (en) * | 2014-12-15 | 2015-03-04 | 北京奇虎科技有限公司 | Template generation method for tile-matching type games and tile-matching type game device |
| CN104391710B (en) * | 2014-12-15 | 2018-09-21 | 北京奇虎科技有限公司 | It eliminates the template generation method of class game and eliminates class game device |
| CN106126561A (en) * | 2016-06-16 | 2016-11-16 | 北京百度网讯科技有限公司 | The generation method and device of Search Results summary |
| CN108319614A (en) * | 2017-01-18 | 2018-07-24 | 百度在线网络技术（北京）有限公司 | Information acquisition method, device and system |
| CN109918661A (en) * | 2019-03-04 | 2019-06-21 | 腾讯科技（深圳）有限公司 | Synonym acquisition methods and device |
| CN109918661B (en) * | 2019-03-04 | 2023-05-30 | 腾讯科技（深圳）有限公司 | Synonym acquisition method and device |
| CN110297930A (en) * | 2019-06-14 | 2019-10-01 | 韶关市启之信息技术有限公司 | A kind of colored language methods of exhibiting and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103514269B (en) | 2017-08-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105144164B (en) | Scoring concept terms using a deep network | |
| CN107480158B (en) | Method and system for evaluating matching of content item and image based on similarity score | |
| CN107193792B (en) | Method and device for generating article based on artificial intelligence | |
| KR101721338B1 (en) | Search engine and implementation method thereof | |
| JP6515624B2 (en) | Method of identifying lecture video topics and non-transitory computer readable medium | |
| CN106489146B (en) | Query rewrite using session information | |
| CN106446005B (en) | Factorization model | |
| US9256649B2 (en) | Method and system of filtering and recommending documents | |
| CN108416028A (en) | A kind of method, apparatus and server of search content resource | |
| KR20160117516A (en) | Generating vector representations of documents | |
| CN106202294B (en) | Related news computing method and device based on keyword and topic model fusion | |
| CN110297897B (en) | Question-answer processing method and related product | |
| CN103514269A (en) | Second query term determined to be related to first query term based on natural searching results | |
| CN105740448B (en) | More microblogging timing abstract methods towards topic | |
| US9892110B2 (en) | Automated discovery using textual analysis | |
| US11550794B2 (en) | Automated determination of document utility for a document corpus | |
| CN103744889A (en) | Method and device for clustering problems | |
| CN112434533B (en) | Entity disambiguation method, entity disambiguation device, electronic device, and computer-readable storage medium | |
| CN111159563A (en) | Method, device and equipment for determining user interest point information and storage medium | |
| CN111241310A (en) | Deep cross-modal Hash retrieval method, equipment and medium | |
| CN112307738A (en) | Method and device for processing text | |
| CN114490926A (en) | Method and device for determining similar problems, storage medium and terminal | |
| CN112579821A (en) | Video recommendation method and device based on real-time voice input and computing equipment | |
| CN113032641A (en) | Intelligent search method and equipment | |
| CN113987156B (en) | Long text generation method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |