CN104143005A - Related searching system and method - Google Patents
Related searching system and method Download PDFInfo
- Publication number
- CN104143005A CN104143005A CN201410380639.7A CN201410380639A CN104143005A CN 104143005 A CN104143005 A CN 104143005A CN 201410380639 A CN201410380639 A CN 201410380639A CN 104143005 A CN104143005 A CN 104143005A
- Authority
- CN
- China
- Prior art keywords
- search word
- keyword
- module
- candidate
- mark
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—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
Abstract
The invention provides a related searching system and method. The method comprises the following steps of (a) receiving search terms, extracting key words and parameters; (b) screening candidate search terms base on the key words and parameters; (c) utilizing a neural network language model to calculate correlation between the search terms and the candidate search terms and obtaining other characteristic correlations; (d) performing weighting calculation on multiple characteristic correlations to obtain related search term results. The related searching system comprises a receiving module for receiving the search terms, a key word extracting module for extracting the key words and parameters, a search term database for storing the candidate search terms, a screening module for searching the candidate search terms under the screen conditions of the key words and parameters, a correlation calculating module for calculating the multiple characteristic correlations and a fusion module for performing the weighting calculation on multiple characteristic correlation fractions to obtain the related search term results. By means of the related searching system and method, efficient and accurate related searching can be achieved through a simple structure.
Description
Technical field
The present invention relates to search engine technique field, particularly a kind of related search system and method.
Background technology
Along with the development of internet, can provide various services for client by Internet side.Wherein one is exactly search service, namely at network side, search engine is set, when the search engine of network side receives after the searching request of client transmission, the all literal index of the keyword that this searching request of coupling of storing in retrieval Internet side candidate data storehouse is carried, offers client.In order to improve the user search Experience Degree that uses client, relevant search technology has been proposed, namely the search engine of network side is receiving after searching request, not only retrieve all literal index that mates the keyword that this searching request carries in Internet side candidate data storehouse, also retrieve the relevant or close literal index of the keyword that this searching request of coupling of storing in Internet side candidate data storehouse carries, offer client, for user's further search.
But existing relevant search utilization word frequency-inverse document frequency method is extracted keyword, but the accuracy of keyword of extracting due to the method is not high, has affected the accuracy rate of the result of relevant search.
Therefore, need a kind of related search system and method, realize efficiently relevant search accurately with simple structure.
Summary of the invention
The object of this invention is to provide a kind of related search system and method.
According to an aspect of the present invention, provide a kind of method of relevant search, it is characterized in that, comprised the steps: a) to receive search word, extracted keyword and keyword parameter; B), based on described keyword and described keyword parameter, filter out at least one candidate search word; C) utilize neural network language model to calculate the correlativity between described search word and described candidate search word, and obtain other feature correlations; D) carry out the weighted calculation to various features correlativity, obtain relevant search word result.
Preferably, in described step a, also comprise and obtain subscriber equipment context information.
Preferably, described step a also comprises and obtains subscriber identity information.
Preferably, in described step b, carry out the screening to described candidate search word by vertical search engine.
Preferably, to utilize neural network language model to calculate the method for the correlativity between current search word and candidate search word as follows for described step c: c1) extract described keyword in described search word or the described candidate search word vector in described neural network language model; C2) calculate the model vector of described search word or described candidate search word; C3) calculate the distance between the model vector of described search word or described candidate search word.
Preferably, described other feature correlations comprise at least one in following mark: keyword associated score, literal apart from mark, searching times mark, common search mark, the physical distance mark of occurring.
Preferably, steps d comprises the steps:
D1) extract the weight of various feature correlation marks;
D2) be weighted, obtain the relevance scores of described candidate search word and described search word;
D3) will calculate mark sequence;
D4) choose described in the highest one or more of mark candidate search word as described relevant search word to return results to user.
Preferably, based on described subscriber equipment context information, various feature correlation marks are configured to different weights, step c, based on described subscriber equipment context information, carries out the weighted calculation to various features relevance scores.
According to a further aspect in the invention, a kind of system of relevant search is provided, it is characterized in that, described system comprises receiver module, keyword extracting module, search word database, screening module, correlation calculations module, and Fusion Module, wherein, described receiver module is used for receiving the search word from client, and described search word is exported to described keyword extracting module; Described keyword extracting module is used for extracting keyword and keyword parameter, and exports described keyword and keyword parameter to described screening module; Described search word database is used for storing candidate search word; Described screening module, at described search word database, taking described keyword parameter as screening conditions, searches out candidate search word; Described correlation calculations module is used for utilizing neural network language model to calculate the correlativity between described search word and described candidate search word, and obtains other feature correlation marks; Described Fusion Module, for the weighted calculation to various features relevance scores, obtains relevant search word result.
Preferably, described receiver module also reads the subscriber equipment context information of client, and described subscriber equipment context information is exported to described Fusion Module.
Preferably, first described Fusion Module configures different weights based on described subscriber equipment context information to various feature correlation marks, then according to this weight, carries out the weighted calculation to various features relevance scores, obtains described relevant search word result.
According to a kind of related search system of the present invention and method, can realize with simple structure and realize efficiently relevant search accurately.
Brief description of the drawings
With reference to the accompanying drawing of enclosing, the more object of the present invention, function and advantage are illustrated the following description by embodiment of the present invention, wherein:
Fig. 1 has schematically shown the process flow diagram of a kind of related search method of the present invention.
Fig. 2 has schematically shown the block diagram of a kind of related search system of the present invention.
Embodiment
By reference to example embodiment, object of the present invention and function and will be illustrated for the method that realizes these objects and function.But the present invention is not limited to following disclosed example embodiment; Can be realized it by multi-form.The essence of instructions is only to help various equivalent modifications Integrated Understanding detail of the present invention.
Hereinafter, embodiments of the invention will be described with reference to the drawings.In the accompanying drawings, identical Reference numeral represents same or similar parts, or same or similar step.
Fig. 1 has schematically shown the process flow diagram of a kind of related search method of the present invention.As shown in Figure 1:
Step 110, receives search word, extracts keyword and keyword parameter.Wherein, the mode of extraction keyword comprises following three kinds: operated and extracted keyword by participle; Extract keyword by utilizing knowledge base; Extract keyword by participle and knowledge base.In addition, knowledge base (Knowledge Base) is structuring in knowledge engineering, easy to operate, easy utilization, comprehensive organized knowledge cluster, be for needs a certain or that some field question solves, adopt the knowledge sheet set interkniting of certain or the storage in computer memory of some knowledge representation modes, tissue, management and using.For example, search word sample is placed in a vertical search system, utilizes past high frequency historical search word and knowledge base data to carry out the extraction of keyword and keyword parameter.
Keyword parameter refers to the attribute that each keyword is corresponding, and described attribute includes but not limited to category feature, title feature, behavioural characteristic, geographic location feature etc., can be used for parameter that multiple attributes of keyword are divided and identified.
For example, the search word receiving is: " renting a house in good inscription Tongcheng ".Utilizing the keyword that knowledge base is extracted is " good inscription Tongcheng " and " renting a house ".The parameter of keyword " good inscription Tongcheng " is keyword classification (house property community), position (geographic coordinate (longitude and latitude)) etc., for example keyword classification of the parameter that keyword " is rented a house " (house property behavior).
According to another embodiment of the present invention, can also obtain subscriber equipment context information, subscriber equipment context information sends the facility information of the intelligent terminal that search word utilizes, any one in described intelligent terminal such as smart mobile phone, panel computer, portable computer, palm digital assistants, intelligent watch, desktop computer, digital glasses, electronic game machine and panorama helmet-type game machine etc. for user.The user equipment information obtaining includes but not limited to the information such as International Mobile Equipment Identity code (IMEI, International Mobile Equipment Identity) and user agent (User Agent).
According to still another embodiment of the invention, for registered users, can also obtain subscriber identity information (ID), to carry out the analysis of personalized relevant search word in subsequent step.For example: obtain user preference document from user ID, obtain user's purchasing power level, historical preference etc., thus further Optimizing Search.For example, be in the scene of renting a house at search word, user's preference is only to pay close attention to the source of houses that house type 3 occupies, and can further carry out accordingly the analysis of personalized relevant search word.
Step 120, keyword and keyword parameter based on extracting filter out at least one candidate search word.Particularly, utilize the combination of above-mentioned keyword parameter to be used as screening conditions, search out at least one candidate search word.According to one embodiment of present invention, can carry out above-mentioned screening by vertical search engine.Screening conditions are for example: " the & tag=house property behavior of & tag=house property community, local=Beijing _ & lon=116.429741 & lat=40.009287 & distance=5km rents a house ", particularly, " local: Beijing " represents that the keyword parameter of key word is geographic position: Beijing; " tag=house property community " expression parameter is label: house property community; " tag=house property behavior _ rent a house " expression parameter is label: house property behavior _ rent a house; " lon=116.429741 " and " lat=40.009287 " represent respectively parameter longitude 116.429741 and parametric latitude: 40.009287; " distance=5km " represents parameter distance scope: 5km.Utilize above-mentioned all screening conditions, can filter out geographic position is Beijing, and contains label " house property community ", " house property behavior _ rent a house ", and the search word that contains the longitude and latitude parameter within the scope of (116.429741,40.009287) 5km.
Step 130, utilizes neural network language model to calculate the correlativity between current search word and each candidate search word, and obtains other feature correlations.
Utilize the method for the correlativity between neural network language model calculating current search word and candidate search word as follows:
A) vector (be designated hereinafter simply as the model vector of keyword) of the keyword in keyword or the candidate search word of extraction current search word in neural network language model.Wherein, can participle and/or utilize knowledge base to obtain the keyword in current search word or candidate search word.In addition, can utilize any one in the instruments such as word2vec, SENNA, HLBL, RNNLM to carry out neural network training language model;
B) model vector of calculating current search word or candidate search word.Particularly, for certain search word, the model vector of wherein each keyword is weighted to summation, obtains the model vector of current search word or candidate search word.
C) distance between the model vector of calculating current search word or candidate search word.Wherein, above-mentioned distance represents correlativity, and above-mentioned distance can be cosine distance or Euclidean distance etc.
In addition, other feature correlations are other the feature correlation except the correlativity of current search word and candidate search word, comprise at least one in following mark: keyword associated score, literal apart from mark, searching times mark, common search mark, the physical distance mark of occurring.
Computing method about above-mentioned other feature correlations are specific as follows.In the computing method of keyword associated score, first participle, and obtain term vector by word2vec, then by addition of vectors, calculate cosine distance with (1) candidate search word; Literal apart from mark: to use editing distance algorithm, formula: 1-(editing distance/total number of word); Physical distance mark: use longitude and latitude distance algorithm, formula: 1 – (longitude and latitude distance (rice)/preset distance (rice)) i.e. preset distance (rice)=5km=5000m; The common search mark (2 number of times that search word was searched in same session) that occurs, draws formula: jointly occur that in searching times/candidate search word, searching times appears in maximum jointly in statistical log.
Step 140, carries out the weighted calculation to various features relevance scores, obtains relevant search word result.Specifically comprise the steps:
A) extract the weight of various feature correlation marks;
B) be weighted, obtain the relevance scores S of candidate search word and current search word, for example, S=keyword relevance scores * 0.15+ search word relevance scores * 0.1+ is literal there is searching for mark * 0.2+ physical distance mark * 0.3 jointly apart from mark * 0.1+ searching times mark * 0.15+;
C) will calculate mark sequence;
D) choose one or more candidate search words that mark is the highest as relevant search word to return results to user.
According to one embodiment of present invention, based on subscriber equipment context information, various feature correlation marks are configured to different weights, can, based on subscriber equipment context information, carry out the weighted calculation to various features relevance scores in step 140.For example, for example, if subscriber equipment context information is certain mobile intelligent terminal (panel computer), gives larger weight for the stronger feature scores of real-time, and relatively reduce the weight of less feature scores associated with real-time.For example, in house property classification, when sight is mobile device, physical distance mark can be important, secondly other features are important has: accessibility is (except distance, whether house property easily arrives), real-time (whether can relate to intermediary/owner now), convenience (whether house is supporting perfect around) etc.
Fig. 2 has schematically shown the block diagram of a kind of related search system of the present invention.As shown in Figure 2: related search system 200 of the present invention comprises receiver module 210, keyword extracting module 220, search word database 230, screening module 240, correlation calculations module 250, and Fusion Module 260.Below each module is elaborated:
Receiver module 210, for receiving the search word information from client, and exports result to keyword extracting module 220.According to one embodiment of present invention, receiver module 210 also reads the subscriber equipment context information of client, and result is exported to Fusion Module 260.
Keyword extracting module 220, for extracting keyword and keyword parameter, and exports result to screening module 240.Wherein, the mode of extraction keyword comprises following three kinds: operated and extracted keyword by participle; Extract keyword by utilizing knowledge base; Extract keyword by participle and knowledge base.
Search word database 230, for storing candidate search word.Can access search word database 230 in the time that aftermentioned screening module 240 is carried out the screening to search word.
Screening module 240, at search word database 230, the keyword parameter of inputting taking keyword extracting module 220 is screening conditions, searches out at least one candidate search word.According to one embodiment of present invention, can carry out above-mentioned screening by vertical search engine.
Correlation calculations module 250, for utilizing neural network language model to calculate the correlativity between current search word and candidate search word, and obtains other feature correlation marks.Wherein, other feature correlations are other feature correlations except the correlativity of current search word and candidate search word, comprising: keyword associated score, literal apart from mark, searching times mark, jointly there is searching times, physical distance mark.
Fusion Module 260, for the weighted calculation to various features relevance scores, obtains relevant search word result.
According to one embodiment of present invention, first Fusion Module 260 configures different weights based on subscriber equipment context information to various feature correlation marks, then according to this weight, carry out the weighted calculation to various features relevance scores, obtain relevant search word result.
According to a kind of related search system of the present invention and method, can realize with simple structure and realize efficiently relevant search accurately.
In conjunction with the explanation of the present invention and the practice that disclose here, other embodiment of the present invention are easy to expect and understand for those skilled in the art.Illustrate with embodiment and be only considered to exemplary, true scope of the present invention and purport limit by claim.
Claims (11)
1. a method for relevant search, is characterized in that, comprises the steps:
A) receive search word, extract keyword and keyword parameter;
B), based on described keyword and described keyword parameter, filter out at least one candidate search word;
C) utilize neural network language model to calculate the correlativity between described search word and described candidate search word, and obtain other feature correlations;
D) carry out the weighted calculation to various features correlativity, obtain relevant search word result.
2. method according to claim 1, is characterized in that, also comprises and obtain subscriber equipment context information in described step a.
3. method according to claim 1, is characterized in that, described step a also comprises and obtains subscriber identity information.
4. method according to claim 1, is characterized in that, in described step b, carries out the screening to described candidate search word by vertical search engine.
5. method according to claim 1, is characterized in that, described step c utilizes the method for the correlativity between neural network language model calculating current search word and candidate search word as follows:
C1) extract described keyword in described search word or the described candidate search word vector in described neural network language model;
C2) calculate the model vector of described search word or described candidate search word;
C3) calculate the distance between the model vector of described search word or described candidate search word.
6. method according to claim 1, is characterized in that, described other feature correlations comprise at least one in following mark: keyword associated score, literal apart from mark, searching times mark, common search mark, the physical distance mark of occurring.
7. method according to claim 1, is characterized in that, steps d comprises the steps:
D1) extract the weight of various feature correlation marks;
D2) be weighted, obtain the relevance scores of described candidate search word and described search word;
D3) will calculate mark sequence;
D4) choose described in the highest one or more of mark candidate search word as described relevant search word to return results to user.
8. method according to claim 1, it is characterized in that, based on described subscriber equipment context information, various feature correlation marks are configured to different weights, step c, based on described subscriber equipment context information, carries out the weighted calculation to various features relevance scores.
9. a system for relevant search, is characterized in that, described system comprises receiver module, keyword extracting module, search word database, screening module, correlation calculations module, and Fusion Module, wherein,
Described receiver module is used for receiving the search word from client, and described search word is exported to described keyword extracting module;
Described keyword extracting module is used for extracting keyword and keyword parameter, and exports described keyword and keyword parameter to described screening module;
Described search word database is used for storing candidate search word;
Described screening module, at described search word database, taking described keyword parameter as screening conditions, searches out candidate search word;
Described correlation calculations module is used for utilizing neural network language model to calculate the correlativity between described search word and described candidate search word, and obtains other feature correlation marks; And
Described Fusion Module, for the weighted calculation to various features relevance scores, obtains relevant search word result.
10. system according to claim 9, is characterized in that, described receiver module also reads the subscriber equipment context information of client, and described subscriber equipment context information is exported to described Fusion Module.
11. systems according to claim 10, it is characterized in that, first described Fusion Module configures different weights based on described subscriber equipment context information to various feature correlation marks, then according to this weight, carry out the weighted calculation to various features relevance scores, obtain described relevant search word result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410380639.7A CN104143005B (en) | 2014-08-04 | 2014-08-04 | A kind of related search system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410380639.7A CN104143005B (en) | 2014-08-04 | 2014-08-04 | A kind of related search system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104143005A true CN104143005A (en) | 2014-11-12 |
| CN104143005B CN104143005B (en) | 2017-09-12 |
Family
ID=51852179
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410380639.7A Active CN104143005B (en) | 2014-08-04 | 2014-08-04 | A kind of related search system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104143005B (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104572836A (en) * | 2014-12-10 | 2015-04-29 | 百度在线网络技术（北京）有限公司 | Method and device for confirming comprehensive relevancy of candidate inquiry sequence |
| CN106326311A (en) * | 2015-07-03 | 2017-01-11 | 北京国双科技有限公司 | Data information processing method and device |
| CN106777282A (en) * | 2016-12-29 | 2017-05-31 | 百度在线网络技术（北京）有限公司 | The sort method and device of relevant search |
| CN106776763A (en) * | 2016-11-22 | 2017-05-31 | 北京云知声信息技术有限公司 | destination searching method and device |
| CN106919702A (en) * | 2017-02-14 | 2017-07-04 | 北京时间股份有限公司 | Keyword method for pushing and device based on document |
| CN106933962A (en) * | 2017-02-06 | 2017-07-07 | 涂正富 | A kind of film micro area network insertion and vertical search precise positioning obtain mesh calibration method |
| CN107220384A (en) * | 2017-06-29 | 2017-09-29 | 北京拉勾科技有限公司 | A kind of search word treatment method, device and computing device based on correlation |
| CN107292690A (en) * | 2016-03-31 | 2017-10-24 | 杨舜凯 | A kind of thing platform implementation method easy transboundary and platform based on neutral net |
| CN107562761A (en) * | 2016-06-30 | 2018-01-09 | 阿里巴巴集团控股有限公司 | A kind of information-pushing method and device |
| CN107980130A (en) * | 2017-11-02 | 2018-05-01 | 深圳前海达闼云端智能科技有限公司 | It is automatic to answer method, apparatus, storage medium and electronic equipment |
| CN108604248A (en) * | 2015-12-28 | 2018-09-28 | 飞索科技有限公司 | Utilize the notes providing method and device of the correlation calculations based on artificial intelligence |
| CN108804443A (en) * | 2017-04-27 | 2018-11-13 | 安徽富驰信息技术有限公司 | A kind of judicial class case searching method based on multi-feature fusion |
| WO2022105171A1 (en) * | 2020-11-19 | 2022-05-27 | 平安科技（深圳）有限公司 | Stop word table generation method and apparatus, and electronic device and storage medium |
| CN116455861A (en) * | 2023-04-17 | 2023-07-18 | 江苏鑫翊翔智能化工程有限公司 | Big data-based computer network security monitoring system and method |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI811708B (en) * | 2021-06-21 | 2023-08-11 | 信義房屋股份有限公司 | Family Member Induction Device Based on Search Behavior |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7849078B2 (en) * | 2006-06-07 | 2010-12-07 | Sap Ag | Generating searchable keywords |
| CN102722498A (en) * | 2011-03-31 | 2012-10-10 | 北京百度网讯科技有限公司 | Search engine and implementation method thereof |
| CN103377232A (en) * | 2012-04-25 | 2013-10-30 | 阿里巴巴集团控股有限公司 | Headline keyword recommendation method and system |
| CN103678668A (en) * | 2013-12-24 | 2014-03-26 | 乐视网信息技术（北京）股份有限公司 | Prompting method of relevant search result, server and system |
| CN103744940A (en) * | 2013-12-31 | 2014-04-23 | 北京百度网讯科技有限公司 | Method and equipment for determining recommended keywords based on geographic position of information releaser |
-
2014
- 2014-08-04 CN CN201410380639.7A patent/CN104143005B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7849078B2 (en) * | 2006-06-07 | 2010-12-07 | Sap Ag | Generating searchable keywords |
| CN102722498A (en) * | 2011-03-31 | 2012-10-10 | 北京百度网讯科技有限公司 | Search engine and implementation method thereof |
| CN103377232A (en) * | 2012-04-25 | 2013-10-30 | 阿里巴巴集团控股有限公司 | Headline keyword recommendation method and system |
| CN103678668A (en) * | 2013-12-24 | 2014-03-26 | 乐视网信息技术（北京）股份有限公司 | Prompting method of relevant search result, server and system |
| CN103744940A (en) * | 2013-12-31 | 2014-04-23 | 北京百度网讯科技有限公司 | Method and equipment for determining recommended keywords based on geographic position of information releaser |
Non-Patent Citations (2)
| Title |
|---|
| SUN WU ET AL.: ""Approximate Keyword Search in Web Search Engines"", 《2006 1ST INTERNATIONAL CONFERENCE ON DIGITAL INFORMATION MANAGEMENT》 * |
| 李佳 等: ""百度相关搜索功能的分析语应用"", 《情报搜索》 * |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104572836A (en) * | 2014-12-10 | 2015-04-29 | 百度在线网络技术（北京）有限公司 | Method and device for confirming comprehensive relevancy of candidate inquiry sequence |
| CN106326311A (en) * | 2015-07-03 | 2017-01-11 | 北京国双科技有限公司 | Data information processing method and device |
| CN106326311B (en) * | 2015-07-03 | 2019-09-20 | 北京国双科技有限公司 | The method and apparatus of processing data information |
| CN108604248B (en) * | 2015-12-28 | 2022-05-27 | 飞索科技有限公司 | Note providing method and device using correlation calculation based on artificial intelligence |
| CN108604248A (en) * | 2015-12-28 | 2018-09-28 | 飞索科技有限公司 | Utilize the notes providing method and device of the correlation calculations based on artificial intelligence |
| CN107292690A (en) * | 2016-03-31 | 2017-10-24 | 杨舜凯 | A kind of thing platform implementation method easy transboundary and platform based on neutral net |
| CN107562761A (en) * | 2016-06-30 | 2018-01-09 | 阿里巴巴集团控股有限公司 | A kind of information-pushing method and device |
| CN106776763A (en) * | 2016-11-22 | 2017-05-31 | 北京云知声信息技术有限公司 | destination searching method and device |
| CN106776763B (en) * | 2016-11-22 | 2019-12-06 | 北京云知声信息技术有限公司 | Destination searching method and device |
| US10331685B2 (en) | 2016-12-29 | 2019-06-25 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for sorting related searches |
| CN106777282A (en) * | 2016-12-29 | 2017-05-31 | 百度在线网络技术（北京）有限公司 | The sort method and device of relevant search |
| CN106777282B (en) * | 2016-12-29 | 2018-07-13 | 百度在线网络技术（北京）有限公司 | The sort method and device of relevant search |
| CN106933962A (en) * | 2017-02-06 | 2017-07-07 | 涂正富 | A kind of film micro area network insertion and vertical search precise positioning obtain mesh calibration method |
| CN106919702B (en) * | 2017-02-14 | 2020-02-11 | 北京时间股份有限公司 | Keyword pushing method and device based on document |
| CN106919702A (en) * | 2017-02-14 | 2017-07-04 | 北京时间股份有限公司 | Keyword method for pushing and device based on document |
| CN108804443A (en) * | 2017-04-27 | 2018-11-13 | 安徽富驰信息技术有限公司 | A kind of judicial class case searching method based on multi-feature fusion |
| CN107220384B (en) * | 2017-06-29 | 2019-11-15 | 北京拉勾科技有限公司 | A kind of search word treatment method based on correlation, device and calculate equipment |
| CN107220384A (en) * | 2017-06-29 | 2017-09-29 | 北京拉勾科技有限公司 | A kind of search word treatment method, device and computing device based on correlation |
| CN107980130A (en) * | 2017-11-02 | 2018-05-01 | 深圳前海达闼云端智能科技有限公司 | It is automatic to answer method, apparatus, storage medium and electronic equipment |
| WO2022105171A1 (en) * | 2020-11-19 | 2022-05-27 | 平安科技（深圳）有限公司 | Stop word table generation method and apparatus, and electronic device and storage medium |
| CN116455861A (en) * | 2023-04-17 | 2023-07-18 | 江苏鑫翊翔智能化工程有限公司 | Big data-based computer network security monitoring system and method |
| CN116455861B (en) * | 2023-04-17 | 2023-11-24 | 福建数智闽政科技有限公司 | Big data-based computer network security monitoring system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104143005B (en) | 2017-09-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104143005A (en) | Related searching system and method | |
| US11698261B2 (en) | Method, apparatus, computer device and storage medium for determining POI alias | |
| US9794766B2 (en) | Identifying an entity associated with wireless network access point | |
| TWI703862B (en) | Content recommendation method and device | |
| CN106991576A (en) | A kind of heating power of geographic area shows method and apparatus | |
| CN105045799A (en) | Searchable index | |
| CN109564571A (en) | Utilize the inquiry recommended method and system of search context | |
| CN103761254A (en) | Method for matching and recommending service themes in various fields | |
| CN110674423A (en) | Address positioning method and device, readable storage medium and electronic equipment | |
| WO2016171860A1 (en) | Computerized system and method for performing a location-based search | |
| CN103309869A (en) | Method and system for recommending display keyword of data object | |
| CN108712712A (en) | Wireless Fidelity WiFi network related information display methods and device | |
| CN104516980B (en) | The output method and server system of search result | |
| CN102467511A (en) | Positioning search method and system | |
| CN102207942A (en) | Identification information matching-based search method and device | |
| CN113127506A (en) | Target query statement construction method and device, storage medium and electronic device | |
| CN111191133B (en) | Service search processing method, device and equipment | |
| CN103646038A (en) | Method and device for processing data of electronic search result | |
| CN103617221B (en) | Software recommendation method and software recommendation system | |
| CN104077288B (en) | Web page contents recommend method and web page contents recommendation apparatus | |
| CN102207943A (en) | Identification information matching-based search method and device | |
| KR101867421B1 (en) | Method and Apparatus for Recommending Service Provider Using Social Data | |
| KR20130064447A (en) | Method and appratus for providing search results using similarity between inclinations of users and device | |
| CN104615620A (en) | Map search type identification method and device and map search method and system | |
| CN104298786B (en) | A kind of image search method and device |
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 |