CN106874492A - Searching method and device - Google Patents

Searching method and device Download PDF

Info

Publication number
CN106874492A
CN106874492A CN201710099795.XA CN201710099795A CN106874492A CN 106874492 A CN106874492 A CN 106874492A CN 201710099795 A CN201710099795 A CN 201710099795A CN 106874492 A CN106874492 A CN 106874492A
Authority
CN
China
Prior art keywords
search
website
keyword
user
tuple
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201710099795.XA
Other languages
Chinese (zh)
Other versions
CN106874492B (en
Inventor
寿如阳
朱健
林睿
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 Jingdong Century Trading Co Ltd
Beijing Jingdong Shangke Information Technology Co Ltd
Original Assignee
Beijing Jingdong Century Trading Co Ltd
Beijing Jingdong Shangke Information 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 Jingdong Century Trading Co Ltd, Beijing Jingdong Shangke Information Technology Co Ltd filed Critical Beijing Jingdong Century Trading Co Ltd
Priority to CN201710099795.XA priority Critical patent/CN106874492B/en
Publication of CN106874492A publication Critical patent/CN106874492A/en
Application granted granted Critical
Publication of CN106874492B publication Critical patent/CN106874492B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/3331Query processing
    • G06F16/334Query execution
    • G06F16/3344Query execution using natural language analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/3331Query processing
    • G06F16/3332Query translation
    • G06F16/3334Selection or weighting of terms from queries, including natural language queries
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/338Presentation of query results
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9535Search customisation based on user profiles and personalisation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00Commerce
    • G06Q30/06Buying, selling or leasing transactions
    • G06Q30/0601Electronic shopping [e-shopping]
    • G06Q30/0623Item investigation
    • G06Q30/0625Directed, with specific intent or strategy
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00Commerce
    • G06Q30/06Buying, selling or leasing transactions
    • G06Q30/0601Electronic shopping [e-shopping]
    • G06Q30/0631Item recommendations

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • Development Economics (AREA)
  • Artificial Intelligence (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

This application discloses searching method and device.One specific embodiment of the method includes:The user's search keyword being input into a search engine to user carries out text dividing, and cutting word to being obtained after text dividing is combined, and obtains multiple user's search keyword tuples;Find out the search in Website keyword tuple matched with each user's search keyword tuple respectively from multiple search in Website keyword tuples;Selected from the search in Website keyword tuple for finding out and meet pre-conditioned search in Website keyword tuple, core word is selected from the search in Website keyword tuple for selecting;Search Results in the corresponding website of core word are presented to user.Realize the user's search keyword imported from such as search engine and excavate the more preferably interest of performance user and the core word being intended to, scanned in the website of such as electric business using core word, to the Search Results of the commodity of the website of user presentation user such as electric business interested.

Description

Searching method and device
Technical field
The application is related to interconnection field, and in particular to search field, more particularly to searching method and device.
Background technology
Search engine can be by the means of such as search engine marketing (SEM, Search Engine Marketing) The website of collaboration electric business brings more click and concern.Electric business buys crucial on a search engine by targetedly Word, the user on search engine is imported the website of electric business.The website of electric business can provide intermediate page and be imported as search engine The entrance of flow, excites the purchase interest of user.At present, typically directly user's search keyword that search engine is imported is existed Scanned in the commercial products retrieval system of the website of electric business, and Search Results are presented to user in intermediate page.
However, because the knowledge hierarchy of search engine and the commercial products retrieval system of the website of electric business has notable difference, searching Index holds up the application scenarios for tending to more universality, and the attribute without skewed popularity such as temperature of information is tended in search, And the commercial products retrieval system of the website of electric business is based on commodity set depth optimization, it is intended to which the target of retrieval is confined to Know in the range of commodity.So as to cause the business in the website of electric business in the user's search keyword for directly importing search engine Searched in product examine cable system, it is difficult to return to user's commodity interested, and then lead to not in intermediate page to user presentation user Commodity interested, influence Consumer's Experience and final conversion.
The content of the invention
This application provides searching method and device, for solving the technical problem that above-mentioned background section is present.
In a first aspect, this application provides searching method, the method includes:The user being input into a search engine to user Search keyword carries out text dividing, and cutting word to being obtained after text dividing is combined, and obtains multiple users and searches Rope keyword tuple;Found out respectively from multiple search in Website keyword tuples and each user's search keyword tuple The search in Website keyword tuple matched somebody with somebody, wherein, search in Website keyword tuple is based on the station being input into website to user in advance Interior search keyword carries out the cutting word that text dividing obtains and is combined and generates;From the search in Website keyword for finding out Selected in tuple and meet pre-conditioned search in Website keyword tuple, and from the search in Website keyword tuple for selecting In select core word, it is pre-conditioned including:The intensity of the search intention of at least one classification in corresponding website is more than Threshold value;Search Results in the corresponding website of core word are presented to user.
Second aspect, this application provides searcher, the device includes:Processing unit, is configured to searching user User's search keyword that index holds up middle input carries out text dividing, and cutting word to being obtained after text dividing carries out group Close, obtain multiple user's search keyword tuples;Searching unit, is configured to from multiple search in Website keyword tuples respectively The search in Website keyword tuple matched with each user's search keyword tuple is found out, wherein, search in Website keyword Tuple is based in advance carrying out the search in Website keyword that user is input into website the cutting word that text dividing obtains carrying out Combine and generate;Core word screening unit, is configured to select satisfaction from the search in Website keyword tuple for finding out Pre-conditioned search in Website keyword tuple, and select core word from the search in Website keyword tuple for selecting Language, it is pre-conditioned including:The intensity of the search intention of at least one classification in corresponding website is more than threshold value;Search in website Unit, is configured to for the Search Results in the corresponding website of core word to be presented to user.
Searching method and device that the application is provided, by the user's search keyword being input into a search engine to user Carry out text dividing, and cutting word to being obtained after text dividing is combined, and obtains multiple user's search keywords units Group;Found out respectively from multiple search in Website keyword tuples in the station matched with each user's search keyword tuple and searched Rope keyword tuple;Selected from the search in Website keyword tuple for finding out and meet pre-conditioned search in Website keyword Tuple, and select core word from the search in Website keyword tuple for selecting;By in the corresponding website of core word Search Results be presented to user.Realize the user's search keyword imported from such as search engine and excavate more preferably performance use The interest at family and the core word being intended to, are scanned for using core word in the website of such as electric business, are presented to user and used The Search Results of the commodity of the website of family such as electric business interested.
Brief description of the drawings
By the detailed description made to non-limiting example made with reference to the following drawings of reading, the application other Feature, objects and advantages will become more apparent upon:
Fig. 1 can be the exemplary system architecture figure of the searching method for being applied to the application;
Fig. 2 shows a flow chart of the searching method of the application;
Fig. 3 shows an exemplary process diagram of the searching method of the application;
Fig. 4 shows a structural representation of the searcher of the application.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that, in order to Be easy to description, be illustrate only in accompanying drawing to about the related part of invention.
It should be noted that in the case where not conflicting, the feature in embodiment and embodiment in the application can phase Mutually combination.Describe the application in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 shows the exemplary system architecture figure of the searching method that can apply to the application.
As shown in figure 1, system architecture can include search engine 101, network 102 and website 103.Network 102 is used to The medium of transmission link is provided between search engine 101 and website 103.Network 102 can include various connection types, for example, have Line, wireless transmission link or fiber optic cables etc..
Search engine 101 can import flow for website 103.For example, website 103 can be the website of electric business, search is drawn It can be that website 103 imports flow by search engine marketing means to hold up 101.Server on website 103 can draw search The user's search keyword for holding up 101 importings excavates the preferably interest of performance user and the core word being intended to, using core Word is scanned in the searching system of website 103, obtains user's Search Results interested, so that, user is interested Search Results in the search between page be presented to user.
Fig. 2 is refer to, it illustrates a flow chart of the searching method of the application.The method can be by server for example Server on website 103 in Fig. 1 is performed, and correspondingly, searcher can be arranged at the clothes on server such as website 103 In business device.The method is comprised the following steps:
Step 201, is processed the search keyword that user is input into a search engine.
Website with website as electric business, search engine can be that the website of electric business is imported as a example by the search engine of flow, be User's search keyword that search engine is imported is rewritten as the preferably interest of performance user and the core word being intended to, and Searched for using in commercial products retrieval system of the core word in the website of electric business, return to user's commodity interested, can be first Obtain user's search keyword that search engine is imported.After user's search keyword is obtained, user can be searched for first Keyword carries out text dividing, obtains multiple cutting words.It is then possible to be combined to cutting word, user's search is obtained Keyword tuple.
In certain embodiments, when text dividing is carried out to user's search keyword, it is contemplated that unregistered word The influence of (Unregistered Word) to the quality of text dividing, can pre-set comprising the word that do not log in website Default vocabulary.When text dividing is carried out, except the dictionary constituted by everyday expressions, can be according to default vocabulary, exactly It is syncopated as not logging in word in user's search keyword.
As a example by website with website as electric business, search word is usual in the website that user is input into when being searched in the website of electric business It is related to trade name, brand etc., belonging to unregistered word in website search word, but express the strong search to commodity more It is intended to.It is lifting text dividing quality, the default vocabularys, classification such as classification vocabulary, commodity vocabulary, brand vocabulary can be regularly updated Keyword, the website of expression electric business comprising the merchandise classification in the website for representing electric business in vocabulary, commodity vocabulary, brand vocabulary The keyword of the keyword of interior trade name, the Brand represented in the website of electric business.So as to search for crucial to user When word carries out text dividing, table can be accurately syncopated as according to classification vocabulary, commodity vocabulary, the brand vocabulary for regularly updating Show the words such as keyword, the keyword of expression trade name, the keyword of expression Brand of merchandise classification.So as to lifting The degree of accuracy of text dividing.
In certain embodiments, carrying out text dividing to user's search keyword, after obtaining multiple cutting words, can Cutting word is combined with using N- tuple (N-Gram) models, obtains user's search keyword tuple.
For example, including " apple " during the cutting word obtained after text dividing is carried out to user's search keyword.For " apple Really ", may refer to brand or commodity in different contexts.Group can be carried out to cutting word using N- units group model Close.When being combined to cutting word using N- units group model, each cutting word can be with the vocabulary of left and right adjacent continuous User's search keyword tuple is constituted, maximum length N is adjustable parameter.So as to so that user's search keyword tuple was both Contain phrase and also contains certain contextual information in itself, can more highlight the search intention of user.For example, user searches for " apple " and " mobile phone " is included in keyword tuple, then can determine that " apple " refers to brand, while also can more accurately reflect The search intention of user is the mobile phone productses of certain brand.
Step 202, finds out the search in Website keyword tuple matched with each user's search keyword tuple respectively.
After user's search keyword tuple is obtained by step 201, for example, carry out text in the default vocabulary of combination cutting Divide and N- units group model is processed to the user's search keyword imported from search engine, obtain user's search keyword tuple Afterwards, can respectively be found out from the multiple search in Website keyword tuples being previously obtained and each user's search keyword The search in Website keyword tuple of tuple matching, i.e., find out user from the multiple search in Website keyword tuples being previously obtained The tuple of search keyword.
In certain embodiments, can in advance obtain and be searched in the station being input into historical search of the user of magnanimity in website Search Results in rope keyword website corresponding with the search in Website keyword clicked on.It is then possible to according to comprising in website The default vocabulary for not logging in word, the search in Website keyword to getting carries out text dividing, and using N- units group model Cutting word after cutting is combined, search in Website keyword tuple is obtained.
Step 203, excavates core word from the search in Website keyword tuple for finding out.
The search in Website keyword tuple matched with each user's search keyword tuple is being found out by step 202 Afterwards, core word can be further excavated from the search in Website keyword tuple for finding out.
In certain embodiments, each the corresponding information gain of search in Website keyword tuple, base can be precalculated In the corresponding information gain of search in Website keyword tuple, core word is excavated.For any one search keyword tuple, Can be the deterministic difference of search intention in the case where the search keyword tuple is whether there is with definition information gain.With website As a example by for the website of electric business, it is assumed that the final conversion of the search behavior without keyword description is generally evenly distributed on all commodity , and now add search keyword " mobile phone ", then may infer that conversion target is only limited to cell phone type commodity now.Addition is searched The diminution of the target zone caused after rope keyword deterministic lifting in other words, can be with the information gain in information theory come amount Change description.
In certain embodiments, it may be predetermined that each corresponding historical shift classification of search in Website keyword tuple Set and the conversion number of times of each classification.For example, it is crucial that search in Website is have input in historical search of the user in website Lemma group, user clicks the search knot of a classification in the Search Results in the corresponding website of search in Website keyword tuple Really, then the classification can be searched for such purpose and tied as the corresponding historical shift classification of search in Website keyword tuple, user The number of clicks of fruit, can convert number of times as such purpose.Each search in Website keyword tuple pair is being calculated respectively After the historical shift classification set answered and the conversion number of times of each classification, further can calculate respectively in each station The corresponding information gain of search keyword tuple.Each corresponding information gain of search in Website keyword tuple can be website The entropy of interior all of classification transition probability subtracts the class in the case where search in Website keyword tuple participates in being searched in website The conditional entropy of mesh transition probability.After each corresponding information gain of search in Website keyword tuple is calculated, can be with structure Build the dictionary comprising search in Website keyword tuple and the corresponding information gain of search in Website keyword tuple.
In certain embodiments, can be corresponding comprising search in Website keyword tuple and search in Website keyword tuple In the dictionary of information gain, the search in Website keyword tuple that lookup is matched with user's search keyword tuple, i.e., in dictionary Find out the tuple of user's search keyword.
If in the absence of the search in Website keyword tuple matched with user's search keyword tuple in dictionary, i.e., in dictionary The tuple of user's search keyword is not found out, then it is considered that information gain is zero.
If there is the search in Website keyword tuple matched with user's search keyword tuple in dictionary, i.e., looked into from dictionary The tuple of user's search keyword is have found, can be crucial to finding out the search in Website matched with user's search keyword tuple The corresponding information gain of lemma group is ranked up, and the tuple of the user's search keyword that will be found out is according to information gain from height To low sequence, candidate of several user's search keyword tuples before ranking as core word is chosen.So as to so that screening Core word can preferably show the interest and intention of user.
As a example by website with website as electric business, " apple Samsung which good " user be input into a search engine, and " millet 6 is assorted When sell " etc. search word, it can be determined that in these search words whether there is " i Phone ", " Samsung mobile phone ", " millet 5 " Deng searching for useful morpheme in the website of electric business, although millet 6 is practically without selling, but can still analyze user couple The interest of the search of the commodity in the website of electric business, it is believed that user is interested in millet, the history temperature according to user in station, Millet 5 can be recommended.
In this application, the information gain that can be built by the noncommodity based on classification, it is to avoid long-tail Sales Volume of Commodity is remembered The very few evaluation for causing of record is unstable, it is also possible to adapt to the demand of follow-up intermediate page optimization.
Search Results in the corresponding website of core word are presented to user by step 204.
After core word is obtained by step 203, core word can be combined, obtain core word group Close.Can be scanned in website using core word combination, obtain user's Search Results interested, by the Search Results It is presented to user.
In certain embodiments, scanned in website using core word combination, obtain user's search interested After result, can by Search Results in the search between be presented to user in page.
Website with website as electric business, search engine be can be electric business website import flow search engine as a example by, Can be scanned for using in commercial products retrieval system of the core word combination in website, the Search Results that will be obtained are in the search Between page be presented to user.The interest and intention of user can be preferably showed due to the core combination in core word combination, because This, is that user is interested using the Search Results for scanning for obtaining in commercial products retrieval system of the core word combination in website Commodity, user's commodity interested can be presented between in the search in page so that, lifting search commercial articles displaying is accurate Rate.
Fig. 3 is refer to, an exemplary process diagram of the searching method provided it illustrates the application.
By search in Website keyword by text dividing and N- tuples mould processing, collect, obtain search in Website keyword Tuple.By user's search keyword by text dividing and N- tuples mould processing, collect, obtain user's search keyword unit Group.Each search in Website keyword tuple correspondence can be determined previously according to the corresponding click history of search in Website keyword The set of historical shift classification and each classification conversion number of times, and then it is corresponding to calculate each search in Website keyword Information gain, information gain is that the entropy of all of classification transition probability is subtracted it is determined that classification transition probability in the case of the tuple Conditional entropy, search in Website keyword tuple and corresponding informance gain constitute dictionary.
The tuple of user's search keyword can be found out from dictionary.Think that gain is zero if not existing.If in the presence of, The tuple of the user's search keyword that will can be found out sorts from high to low according to information gain, chooses lookup in the top The tuple of the user's search keyword for going out as core word candidate.Obtaining information gain multiple tuples in the top Afterwards, in fact it could happen that some tuples are the situations of the subset of other tuples, duplicate removal and removal sensitive words can be carried out, is obtained Core word, core word can preferably show the interest and intention of user.It is then possible to carry out arrangement group to core word Close, obtain rewriting target.It is thus possible to using being scanned in the searching system of the rewriting target in website, obtain user The Search Results are presented to user by Search Results interested.
Below as a example by the website with website as electric business, the advantage of the searching method of the application is illustrated:In this application, can be with Model of the reflection user to the search intention of different classifications is built using the search data of the website itself of electric business, the model can To be built according to search in Website lemma group and the corresponding information gain of site search lemma group.Search engine can be imported Search behavior is mapped on the model, using being examined in commercial products retrieval system of the revised search word tuple in website Rope, obtains user's commodity interested, in the search between page presentation user commodity interested.So as to efficiently solve straight The searching system for connecing the website of the direct incoming electric business of user's search keyword imported using search engine is scanned for, because searching Index hold up middle input search word it is irregular and search for caused by customary difference return to user content quality it is low Problem, improve search recall rate.Enable that the site search of electric business returns to user's commodity interested by rewriting, carry Rise search commercial articles displaying accuracy rate.
Fig. 4 is refer to, it illustrates a structural representation of the searcher of the application.Searcher includes:Treatment Unit 401, searching unit 402, core word screening unit 403, search unit 404 in website.Wherein, processing unit 401 is matched somebody with somebody Putting the user's search keyword for being input into a search engine to user carries out text dividing, and to being obtained after text dividing Cutting word be combined, obtain multiple user's search keyword tuples;Searching unit 402 is configured to be searched from multiple station The search in Website keyword tuple matched with each user's search keyword tuple is found out in rope keyword tuple respectively, its In, search in Website keyword tuple is based on carrying out text dividing to the search in Website keyword that user is input into website and obtaining in advance To cutting word be combined and generate;Core word screening unit 403 is configured to crucial from the search in Website for finding out Selected in lemma group and meet pre-conditioned search in Website keyword tuple, and from the search in Website critical word for selecting Select core word in group, it is pre-conditioned including:The intensity of the search intention of at least one classification in corresponding website is big In threshold value;Search unit 404 is configured to for the Search Results in the corresponding website of core word to be presented to user in website.
Present invention also provides a kind of server, the server can include the searcher described by Fig. 4.The server One or more processors can be configured with;Memory, can be with for storing one or more programs, in one or more programs Comprising the instruction for being used to perform the operation described in above-mentioned steps 201-204.At one or more programs are by one or more When reason device is performed so that one or more processors perform the operation described in above-mentioned steps 201-204.
Present invention also provides a kind of computer-readable medium, the computer-readable medium can be included in server 's;Can also be individualism, without in allocating server into.The computer-readable medium carries one or more program, When one or more program is performed by the server so that the server:The user being input into a search engine to user Search keyword carries out text dividing, and cutting word to being obtained after text dividing is combined, and obtains multiple users and searches Rope keyword tuple;Found out respectively from multiple search in Website keyword tuples and each user's search keyword tuple The search in Website keyword tuple matched somebody with somebody, wherein, search in Website keyword tuple is based on the station being input into website to user in advance Interior search keyword carries out the cutting word that text dividing obtains and is combined and generates;From the search in Website keyword for finding out Selected in tuple and meet pre-conditioned search in Website keyword tuple, and from the search in Website keyword tuple for selecting In select core word, it is pre-conditioned including:The intensity of the search intention of at least one classification in corresponding website is more than Threshold value;Search Results in the corresponding website of core word are presented to user.
It should be noted that above computer computer-readable recording medium can be computer-readable signal media or computer-readable Storage medium or the two are combined.Computer-readable recording medium for example may be-but not limited to- The system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device or device, or it is any more than combination.Computer-readable The more specifically example of storage medium can be included but is not limited to:Electrical connection, portable computing with one or more wires Machine disk, hard disk, random access storage device (RAM), read-only storage (ROM), erasable programmable read only memory (EPROM Or flash memory), optical fiber, portable compact disc read-only storage (CD-ROM), light storage device, magnetic memory device or above-mentioned Any appropriate combination.In this application, computer-readable recording medium can be it is any including or storage program it is tangible Medium, the program can be commanded execution system, device or device and use or in connection.And in this application, Computer-readable signal media can include the data-signal propagated in a base band or as a carrier wave part, wherein carrying Computer-readable program code.The data-signal of this propagation can be diversified forms, including but not limited to electromagnetic signal, Optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer-readable recording medium with Outer any computer-readable medium, the computer-readable medium can be sent, propagated or be transmitted for performing system by instruction System, device or device are used or program in connection.The program code included on computer-readable medium can be with Transmitted with any appropriate medium, including but not limited to:Wirelessly, electric wire, optical cable, RF etc., or it is above-mentioned any appropriate Combination.
Above description is only the preferred embodiment and the explanation to institute's application technology principle of the application.People in the art Member is it should be appreciated that involved invention scope in the application, however it is not limited to the technology of the particular combination of above-mentioned technical characteristic Scheme, while should also cover in the case where the inventive concept is not departed from, is carried out by above-mentioned technical characteristic or its equivalent feature Other technical schemes for being combined and being formed.Such as features described above has similar work(with (but not limited to) disclosed herein The technical scheme that the technical characteristic of energy is replaced mutually and formed.

Claims (10)

1. a kind of searching method, it is characterised in that methods described includes:
The user's search keyword being input into a search engine to user carries out text dividing, and to being obtained after text dividing Cutting word is combined, and obtains multiple user's search keyword tuples;
Found out respectively from multiple search in Website keyword tuples in the station matched with each user's search keyword tuple Search keyword tuple, wherein, the search in Website that search in Website keyword tuple is based in advance being input into user in website is closed Keyword carries out the cutting word that text dividing obtains and is combined and generates;
Selected from the search in Website keyword tuple for finding out and meet pre-conditioned search in Website keyword tuple, and Select core word from the search in Website keyword tuple for selecting, it is described it is pre-conditioned including:In corresponding website The intensity of the search intention of at least one classification is more than threshold value;
Search Results in the corresponding website of core word are presented to the user.
2. method according to claim 1, it is characterised in that the user's search being input into a search engine to user is crucial Word carries out text dividing, and cutting word to being obtained after text dividing is combined, and obtains multiple user's search keywords Tuple includes:
Based on default vocabulary, text dividing is carried out to user's search keyword, obtain cutting word, the default vocabulary bag Include:Merchandise classification keyword, trade name keyword, Brand keyword;
The cutting word is combined using N units group model, obtains user's search keyword tuple.
3. method according to claim 2, it is characterised in that methods described also includes:
Obtain the search in Website keyword that user is input into website;
Based on the default vocabulary, text dividing is carried out to search in Website keyword, obtain cutting word;
The cutting word is combined using N units group model, obtains search in Website keyword tuple.
4. method according to claim 3, it is characterised in that methods described also includes:
The corresponding information gain of search keyword tuple in computer installation, described information gain is that all of classification conversion is general in website The entropy of rate is subtracted it is determined that the conditional entropy of the classification transition probability in the case of search in Website keyword tuple;
Build the dictionary comprising search in Website keyword tuple and the corresponding information gain of search in Website keyword tuple.
5. method according to claim 4, it is characterised in that found out respectively from multiple search in Website keyword tuples The search in Website keyword tuple matched with each user's search keyword tuple includes:
The search in Website keyword tuple matched with each user's search keyword tuple is found out from the dictionary;And
Selected from the search in Website keyword tuple for finding out and meet pre-conditioned search in Website keyword tuple and include:
According to the corresponding information gain of search in Website keyword tuple found out in the dictionary, the search in Website to finding out Keyword tuple is ranked up;
Select the search in Website keyword tuple that the position after sequence is located at before preset order.
6. method according to claim 5, it is characterised in that selected from the search in Website keyword tuple for selecting Core word includes:
The word being located to the position after the sequence that selects in the search in Website keyword tuple before preset order goes Weight and removal sensitive words, obtain core word.
7. method according to claim 6, it is characterised in that the Search Results in the corresponding website of core word are presented Include to the user:
Permutation and combination is carried out to the core word, core word combination is obtained;
Scanned in website using core word combination, obtain the Search Results in website;
By the Search Results in the website in the search between be presented to the user in page.
8. a kind of searcher, it is characterised in that described device includes:
Processing unit, the user's search keyword for being configured to be input into user in a search engine carries out text dividing, and Cutting word to being obtained after text dividing is combined, and obtains multiple user's search keyword tuples;
Searching unit, is configured to be found out respectively from multiple search in Website keyword tuples and searches for crucial with each user The search in Website keyword tuple of lemma group matching, wherein, search in Website keyword tuple is based in advance to user in website The search in Website keyword of input carries out the cutting word that text dividing obtains and is combined and generates;
Core word screening unit, is configured to be selected from the search in Website keyword tuple for finding out and meets pre-conditioned Search in Website keyword tuple, and select core word from the search in Website keyword tuple for selecting, it is described pre- If condition includes:The intensity of the search intention of at least one classification in corresponding website is more than threshold value;
Search unit in website, is configured to for the Search Results in the corresponding website of core word to be presented to the user.
9. a kind of server, it is characterised in that including:
One or more processors;
Memory, for storing one or more programs,
When one or more of programs are by one or more of computing devices so that one or more of processors Realize the method as described in any in claim 1-7.
10. a kind of readable computer storage medium, it is characterised in that be stored thereon with computer program, it is characterised in that the journey Sequence is when executed by realizing the method as described in any in claim 1-7.
CN201710099795.XA 2017-02-23 2017-02-23 Searching method and device Active CN106874492B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710099795.XA CN106874492B (en) 2017-02-23 2017-02-23 Searching method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710099795.XA CN106874492B (en) 2017-02-23 2017-02-23 Searching method and device

Publications (2)

Publication Number Publication Date
CN106874492A true CN106874492A (en) 2017-06-20
CN106874492B CN106874492B (en) 2021-01-26

Family

ID=59168524

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710099795.XA Active CN106874492B (en) 2017-02-23 2017-02-23 Searching method and device

Country Status (1)

Country Link
CN (1) CN106874492B (en)

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107330023A (en) * 2017-06-21 2017-11-07 北京百度网讯科技有限公司 Content of text based on focus recommends method and apparatus
CN107609192A (en) * 2017-10-12 2018-01-19 北京京东尚科信息技术有限公司 The supplement searching method and device of a kind of search engine
CN107944166A (en) * 2017-11-30 2018-04-20 中州大学 The implementation method and device of a kind of Electronic Design
CN108228907A (en) * 2018-02-08 2018-06-29 北京三快在线科技有限公司 A kind of method, apparatus of recommendation information, electronic equipment and storage medium
CN108268617A (en) * 2018-01-05 2018-07-10 阿里巴巴集团控股有限公司 User view determines method and device
CN110209827A (en) * 2018-02-07 2019-09-06 腾讯科技(深圳)有限公司 Searching method, device, computer readable storage medium and computer equipment
CN110232581A (en) * 2018-03-06 2019-09-13 北京京东尚科信息技术有限公司 It is a kind of to provide the method and apparatus of discount coupon for user
CN110633352A (en) * 2018-06-01 2019-12-31 北京嘀嘀无限科技发展有限公司 Semantic retrieval method and device
CN110941694A (en) * 2019-10-14 2020-03-31 珠海格力电器股份有限公司 Knowledge graph searching and positioning method and system, electronic equipment and storage medium
CN111428022A (en) * 2020-03-25 2020-07-17 北京明略软件系统有限公司 Information retrieval method, device and storage medium
CN111553765A (en) * 2020-04-27 2020-08-18 广州探途网络技术有限公司 E-commerce search sorting method and device and computing equipment
WO2020168839A1 (en) * 2019-02-21 2020-08-27 北京京东尚科信息技术有限公司 Item recall method and system, electronic device and readable storage medium
CN111695022A (en) * 2019-01-18 2020-09-22 创新奇智(重庆)科技有限公司 Interest searching method based on knowledge graph visualization
CN111797205A (en) * 2020-06-30 2020-10-20 百度在线网络技术(北京)有限公司 Word list retrieval method and device, electronic equipment and storage medium
CN112769823A (en) * 2021-01-07 2021-05-07 北京码牛科技有限公司 Information management-based secure network auditing method and system
CN113360755A (en) * 2021-05-31 2021-09-07 北京乐我无限科技有限责任公司 Information pushing and displaying method and device

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102289436A (en) * 2010-06-18 2011-12-21 阿里巴巴集团控股有限公司 Method and device for determining weighted value of search term and method and device for generating search results
CN102456058A (en) * 2010-11-02 2012-05-16 阿里巴巴集团控股有限公司 Method and device for providing category information
CN104376115A (en) * 2014-12-01 2015-02-25 北京奇虎科技有限公司 Fuzzy word determining method and device based on global search

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102289436A (en) * 2010-06-18 2011-12-21 阿里巴巴集团控股有限公司 Method and device for determining weighted value of search term and method and device for generating search results
CN102456058A (en) * 2010-11-02 2012-05-16 阿里巴巴集团控股有限公司 Method and device for providing category information
CN104376115A (en) * 2014-12-01 2015-02-25 北京奇虎科技有限公司 Fuzzy word determining method and device based on global search

Cited By (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107330023B (en) * 2017-06-21 2021-02-12 北京百度网讯科技有限公司 Text content recommendation method and device based on attention points
CN107330023A (en) * 2017-06-21 2017-11-07 北京百度网讯科技有限公司 Content of text based on focus recommends method and apparatus
CN107609192A (en) * 2017-10-12 2018-01-19 北京京东尚科信息技术有限公司 The supplement searching method and device of a kind of search engine
CN107944166A (en) * 2017-11-30 2018-04-20 中州大学 The implementation method and device of a kind of Electronic Design
CN108268617A (en) * 2018-01-05 2018-07-10 阿里巴巴集团控股有限公司 User view determines method and device
CN110209827B (en) * 2018-02-07 2023-09-19 腾讯科技(深圳)有限公司 Search method, search device, computer-readable storage medium, and computer device
CN110209827A (en) * 2018-02-07 2019-09-06 腾讯科技(深圳)有限公司 Searching method, device, computer readable storage medium and computer equipment
CN108228907B (en) * 2018-02-08 2021-04-23 北京三快在线科技有限公司 Information recommending method and device, electronic equipment and storage medium
CN108228907A (en) * 2018-02-08 2018-06-29 北京三快在线科技有限公司 A kind of method, apparatus of recommendation information, electronic equipment and storage medium
CN110232581A (en) * 2018-03-06 2019-09-13 北京京东尚科信息技术有限公司 It is a kind of to provide the method and apparatus of discount coupon for user
CN110633352A (en) * 2018-06-01 2019-12-31 北京嘀嘀无限科技发展有限公司 Semantic retrieval method and device
CN111695022A (en) * 2019-01-18 2020-09-22 创新奇智(重庆)科技有限公司 Interest searching method based on knowledge graph visualization
WO2020168839A1 (en) * 2019-02-21 2020-08-27 北京京东尚科信息技术有限公司 Item recall method and system, electronic device and readable storage medium
US11907659B2 (en) 2019-02-21 2024-02-20 Beijing Jingdong Shangke Information Technology Co., Ltd. Item recall method and system, electronic device and readable storage medium
CN110941694A (en) * 2019-10-14 2020-03-31 珠海格力电器股份有限公司 Knowledge graph searching and positioning method and system, electronic equipment and storage medium
CN111428022B (en) * 2020-03-25 2023-06-02 北京明略软件系统有限公司 Information retrieval method, device and storage medium
CN111428022A (en) * 2020-03-25 2020-07-17 北京明略软件系统有限公司 Information retrieval method, device and storage medium
CN111553765A (en) * 2020-04-27 2020-08-18 广州探途网络技术有限公司 E-commerce search sorting method and device and computing equipment
CN111797205A (en) * 2020-06-30 2020-10-20 百度在线网络技术(北京)有限公司 Word list retrieval method and device, electronic equipment and storage medium
CN111797205B (en) * 2020-06-30 2024-03-12 百度在线网络技术(北京)有限公司 Vocabulary retrieval method and device, electronic equipment and storage medium
CN112769823A (en) * 2021-01-07 2021-05-07 北京码牛科技有限公司 Information management-based secure network auditing method and system
CN113360755A (en) * 2021-05-31 2021-09-07 北京乐我无限科技有限责任公司 Information pushing and displaying method and device

Also Published As

Publication number Publication date
CN106874492B (en) 2021-01-26

Similar Documents

Publication Publication Date Title
CN106874492A (en) Searching method and device
CN110162690B (en) Method and device for determining interest degree of user in item, equipment and storage medium
US10853360B2 (en) Searchable index
US11321759B2 (en) Method, computer program product and system for enabling personalized recommendations using intelligent dialog
JP2015518220A (en) Online product search method and system
JP5859606B2 (en) Ad source and keyword set adaptation in online commerce platforms
CN106610972A (en) Query rewriting method and apparatus
US8965897B2 (en) Intelligent product feedback analytics tool
CN104933100A (en) Keyword recommendation method and device
US10102246B2 (en) Natural language consumer segmentation
CN102236663A (en) Query method, query system and query device based on vertical search
CN107993134A (en) A kind of smart shopper exchange method and system based on user interest
CN109522480A (en) A kind of information recommendation method, device, electronic equipment and storage medium
US20110208715A1 (en) Automatically mining intents of a group of queries
US10963916B2 (en) Systems and methods for assessing advertisement
JP2015500525A (en) Method and apparatus for information retrieval
JP6728178B2 (en) Method and apparatus for processing search data
US20170316100A1 (en) Retrieval of Content Using Link-Based Search
US20150348061A1 (en) Crm account to company mapping
CN108197298A (en) A kind of smart shopper exchange method and system based on natural language processing
CN110232581B (en) Method and device for providing coupons for users
US7890494B2 (en) System and/or method for processing events
CN104572887A (en) Method and system for retrieving product information
US10339135B2 (en) Query handling in search systems
US10108712B2 (en) Systems and methods for generating search query rewrites

Legal Events

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