CN103226597A - Keyword advertisement matching method based on natural semantics - Google Patents

Keyword advertisement matching method based on natural semantics Download PDF

Info

Publication number
CN103226597A
CN103226597A CN2013101391633A CN201310139163A CN103226597A CN 103226597 A CN103226597 A CN 103226597A CN 2013101391633 A CN2013101391633 A CN 2013101391633A CN 201310139163 A CN201310139163 A CN 201310139163A CN 103226597 A CN103226597 A CN 103226597A
Authority
CN
China
Prior art keywords
keyword
knowledge
user
naturally
semantic
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
CN2013101391633A
Other languages
Chinese (zh)
Other versions
CN103226597B (en
Inventor
段培力
刘国清
赵杰
李春华
丁立星
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 Xiaoxiang innovation Artificial Intelligence Technology Co.,Ltd.
Original Assignee
BEIJING GEO POLYMERIZATION 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 GEO POLYMERIZATION TECHNOLOGY Co Ltd filed Critical BEIJING GEO POLYMERIZATION TECHNOLOGY Co Ltd
Priority to CN201310139163.3A priority Critical patent/CN103226597B/en
Publication of CN103226597A publication Critical patent/CN103226597A/en
Application granted granted Critical
Publication of CN103226597B publication Critical patent/CN103226597B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides a keyword advertisement matching method based on natural semantics, which comprises keywords obtaining user search and keywords analyzing the keywords based on the natural semantics to form a knowledge structure, wherein the knowledge structure is a knowledge structure signified by the combination of action and objects; the information type of the keywords of the knowledge structure is judged based on requirements of users; according to the obtained information type of the keywords of the knowledge structure through the judgment, a core keyword is extracted from the keywords of the knowledge structure and the core keyword is expanded, and then the keyword after expended is obtained; an advertisement is matched according to the priority levels of the core keyword and the keyword expanded and at least one advertisement link with an order of precedence is obtained; and then all advertisement links are displayed on return pages of a search results of users. The keyword advertisement matching method can accurately release advertisements required by users, so that releasing efficiency of the advertisements is improved.

Description

Based on semantic naturally AdWords matching process
Technical field
The invention belongs to Internet advertising and throw in technical field, be specifically related to a kind of based on semantic naturally AdWords matching process.
Background technology
AdWords (adwords) is also referred to as " keyword retrieval ", in simple terms, works as the user exactly and utilizes a certain keyword to retrieve, and the ad content relevant with this keyword can occur at the result for retrieval page.The form of AdWords is fairly simple, and normally copy wherein mainly comprises key elements such as ad title, brief introduction, network address, generally separates with natural Search Results in result of page searching, all takes this pattern as search engines such as Google, Baidu.Because AdWords is when the retrieval of particular keywords, just appears at the remarkable position of result of page searching, so its specific aim is very high, is called as cost performance than higher network promotion mode.
In the prior art, when user's keyword is carried out advertisement putting, there are the advertisement and the low problem of user's keyword matching degree of being thrown in, thereby can not throw in required advertisement more accurately, reduced the efficient of advertisement putting to the user.
Summary of the invention
At the defective that prior art exists, the invention provides and a kind ofly based on the keyword of user search, can point-devicely throw in required advertisement to the user based on the AdWords matching process of semanteme naturally, improved the efficient of advertisement putting.
The technical solution used in the present invention is as follows:
The invention provides a kind ofly, may further comprise the steps based on semantic naturally AdWords matching process:
S1 obtains the keyword of user search;
S2 resolves described keyword based on semantic naturally, forms the keyword of the structure of knowledge; Wherein, the described structure of knowledge for action and object in conjunction with the structure of knowledge of representing;
S3 based on user's request, judges the information type of the keyword of the described structure of knowledge;
S4, the information type of the keyword of the described structure of knowledge that obtains according to judgement is extracted the core keyword from the keyword of the described structure of knowledge, and the keyword after being expanded expanded in described core keyword;
S5 carries out the advertisement coupling according to the priority level of the keyword after described core keyword and the described expansion, obtains the advertisement link that at least one has priority; At user search result's back page, show each advertisement link then by described priority.
Preferably, S1 obtains in the following manner: when the user searches for, obtain the keyword of user search by internet gateway.
Preferably, among the S2, describedly be specially based on semantic naturally described keyword is resolved: by knowledge base and the object action framework set up in advance, the keyword that described search is obtained breaks and hierarchical operations, forms the keyword of the structure of knowledge.
Preferably, described information type comprises three types of navigation speech, information speech and resource speech; Described navigation speech wishes to find the vocabulary of information entry for the user, and described information speech obtains the vocabulary of appointed information answer for the user, and the vocabulary of consumed resources wished to obtain carrying out in described resource speech for the user.
Preferably, among the S4, described core keyword is expanded, the keyword after being expanded is specially:
Described core keyword is carried out synonym expansion and/or hypernym expansion and/or hyponym expansion, obtain synonym, hypernym and the hyponym corresponding respectively with described core keyword.
Beneficial effect of the present invention is as follows:
Provided by the invention based on semantic naturally AdWords matching process, by user's keyword is resolved, at user's request, extract the core keyword, then the core keyword is carried out synonym and the expansion of last hyponym, reach the advertisement that can accurately match, improve advertisement putting efficient with the user's request coupling; Can not mate fully under the situation of core keyword again, obtaining the suboptimal solution that mates with user's request, thereby realizing comprehensive purpose of recommending relevant advertisements to the user.
Description of drawings
Fig. 1 is the schematic flow sheet based on semantic naturally AdWords matching process provided by the invention.
Embodiment
The present invention is described in detail below in conjunction with accompanying drawing:
As shown in Figure 1, the invention provides a kind ofly, may further comprise the steps based on semantic naturally AdWords matching process:
S1 obtains the keyword of user search;
Concrete, when the user searches for, can obtain the keyword of user search by internet gateway.
S2 resolves described keyword based on semantic naturally, forms the keyword of the structure of knowledge; Wherein, the described structure of knowledge for action and object in conjunction with the structure of knowledge of representing;
Need to prove that action and object are meant the structure of knowledge of representing with action and relation between objects in conjunction with the structure of knowledge of expression, for example, for " having a meal " this speech, be action and object the structure of knowledge in conjunction with expression, wherein, " eating " is action, and " meal " is object.Again for example, " wearing boots " this speech, " wearing " is action, " boots " is object.
In this step, be specially based on semantic naturally keyword is resolved: by knowledge base and the object action framework set up in advance, the keyword that described search is obtained breaks and hierarchical operations, forms the keyword of the structure of knowledge.
After this step, can also comprise: the keyword to the structure of knowledge carries out digital signature, and then carries out S3, by digital signature, can guarantee information the integrality of transmission, also can protect privacy of user.
S3 based on user's request, judges the information type of the keyword of the described structure of knowledge;
This step can be carried out in cloud data center, and wherein, information type comprises three types of navigation speech, information speech and resource speech; Described navigation speech wishes to find the vocabulary of information entry for the user, and described information speech obtains the vocabulary of appointed information answer for the user, and the vocabulary of consumed resources wished to obtain carrying out in described resource speech for the user.
S4, the information type of the keyword of the described structure of knowledge that obtains according to judgement is extracted the core keyword from the keyword of the described structure of knowledge, and the keyword after being expanded expanded in described core keyword;
Wherein, described core keyword is expanded, keyword after being expanded is specially: described core keyword is carried out synonym expansion and/or hypernym expansion and/or hyponym expansion, obtain synonym, hypernym and the hyponym corresponding with described core keyword respectively.
For example, if the keyword of user search is " a white refrigerator ",, draws " refrigerator " and be core keyword, the core request of representative of consumer then by " white refrigerator " resolved; " white " is secondary keywords, the secondary request of representative of consumer.
In addition, among the present invention, the synonym implication is: have the speech of same meaning with the core keyword; The hypernym implication is: than core keyword senses vocabulary widely, for example: the hypernym of " refrigerator " is " household electrical appliance "; The hyponym implication is: than core keyword senses vocabulary more specifically, for example: the hyponym of " refrigerator " is " an individual layer refrigerator " or " double-deck refrigerator ".
S5 carries out the advertisement coupling according to the priority level of the keyword after described core keyword and the described expansion, obtains the advertisement link that at least one has priority; At user search result's back page, show each advertisement link then by described priority.This step can be carried out in the advertisement dispatching center.
Among the present invention, by user's keyword is resolved, at user's request, extract the core keyword, then the core keyword is carried out synonym and the expansion of last hyponym, reach the advertisement that can accurately match, improve advertisement putting efficient with the user's request coupling; Can not mate fully under the situation of core keyword again, obtaining the suboptimal solution that mates with user's request, thereby realizing comprehensive purpose of recommending relevant advertisements to the user.
The above only is a preferred implementation of the present invention; should be pointed out that for those skilled in the art, under the prerequisite that does not break away from the principle of the invention; can also make some improvements and modifications, these improvements and modifications also should be looked protection scope of the present invention.

Claims (5)

1. one kind based on semantic naturally AdWords matching process, it is characterized in that, may further comprise the steps:
S1 obtains the keyword of user search;
S2 resolves described keyword based on semantic naturally, forms the keyword of the structure of knowledge; Wherein, the described structure of knowledge for action and object in conjunction with the structure of knowledge of representing;
S3 based on user's request, judges the information type of the keyword of the described structure of knowledge;
S4, the information type of the keyword of the described structure of knowledge that obtains according to judgement is extracted the core keyword from the keyword of the described structure of knowledge, and the keyword after being expanded expanded in described core keyword;
S5 carries out the advertisement coupling according to the priority level of the keyword after described core keyword and the described expansion, obtains the advertisement link that at least one has priority; At user search result's back page, show each advertisement link then by described priority.
2. according to claim 1 based on semantic naturally AdWords matching process, it is characterized in that S1 obtains in the following manner: when the user searches for, obtain the keyword of user search by internet gateway.
3. according to claim 1 based on semantic naturally AdWords matching process, it is characterized in that, among the S2, describedly be specially: by knowledge base and the object action framework of setting up in advance based on semantic naturally described keyword is resolved, the keyword that described search is obtained breaks and hierarchical operations, forms the keyword of the structure of knowledge.
4. according to claim 1ly it is characterized in that described information type comprises three types of navigation speech, information speech and resource speech based on semantic naturally AdWords matching process; Described navigation speech wishes to find the vocabulary of information entry for the user, and described information speech obtains the vocabulary of appointed information answer for the user, and the vocabulary of consumed resources wished to obtain carrying out in described resource speech for the user.
5. according to claim 1 based on semantic naturally AdWords matching process, it is characterized in that among the S4, described core keyword is expanded, the keyword after being expanded is specially:
Described core keyword is carried out synonym expansion and/or hypernym expansion and/or hyponym expansion, obtain synonym, hypernym and the hyponym corresponding respectively with described core keyword.
CN201310139163.3A 2013-04-19 2013-04-19 Keyword advertisement matching method based on natural semantics Active CN103226597B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201310139163.3A CN103226597B (en) 2013-04-19 2013-04-19 Keyword advertisement matching method based on natural semantics

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201310139163.3A CN103226597B (en) 2013-04-19 2013-04-19 Keyword advertisement matching method based on natural semantics

Publications (2)

Publication Number Publication Date
CN103226597A true CN103226597A (en) 2013-07-31
CN103226597B CN103226597B (en) 2015-03-25

Family

ID=48837042

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201310139163.3A Active CN103226597B (en) 2013-04-19 2013-04-19 Keyword advertisement matching method based on natural semantics

Country Status (1)

Country Link
CN (1) CN103226597B (en)

Cited By (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104717210A (en) * 2015-02-13 2015-06-17 北京集奥聚合科技有限公司 Method and system for connecting optional media to DSP
CN105007569A (en) * 2015-06-09 2015-10-28 中山大学 Method of obtaining Internet resources by a terminal on the basis of a wireless identifier
CN105069034A (en) * 2015-07-22 2015-11-18 无锡天脉聚源传媒科技有限公司 Recommendation information generation method and apparatus
CN107092682A (en) * 2017-04-21 2017-08-25 北京恒冠网络数据处理有限公司 A kind of free database index method of user with data acquisition
CN107193962A (en) * 2017-05-24 2017-09-22 百度在线网络技术(北京)有限公司 A kind of intelligent figure method and device of internet promotion message
CN107451161A (en) * 2016-06-01 2017-12-08 阿里巴巴集团控股有限公司 Show method for pushing, device and the platform of object
CN107507046A (en) * 2017-10-13 2017-12-22 北京奇艺世纪科技有限公司 The method and system that advertisement is recalled
CN107918658A (en) * 2017-11-20 2018-04-17 金蝶软件(中国)有限公司 A kind of business opportunity generation method and system
CN107944898A (en) * 2016-10-13 2018-04-20 驰众信息技术(上海)有限公司 The automatic discovery of advertisement putting building information and sort method
CN109189892A (en) * 2018-09-17 2019-01-11 北京点网聚科技有限公司 A kind of recommended method and device based on article review
CN110020156A (en) * 2017-12-07 2019-07-16 深圳市腾讯计算机系统有限公司 Information recommendation method, front end implementation method, device, equipment and storage medium
CN110609952A (en) * 2019-08-15 2019-12-24 中国平安财产保险股份有限公司 Data acquisition method and system and computer equipment
CN110633391A (en) * 2018-06-01 2019-12-31 北京搜狗科技发展有限公司 Information searching method and device
CN113435193A (en) * 2021-06-16 2021-09-24 深圳市世强元件网络有限公司 Landing page keyword releasing method and device and computer equipment
CN114399329A (en) * 2021-12-22 2022-04-26 江苏沪磁智能科技有限公司 Digital advertisement transaction putting method

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101000608A (en) * 2006-01-11 2007-07-18 吴风勇 Key word dynamic matching generating based on search engine technology
CN101071443A (en) * 2007-06-26 2007-11-14 腾讯科技(深圳)有限公司 Content-related advertising identifying method and content-related advertising server
CN101158971A (en) * 2007-11-15 2008-04-09 深圳市迅雷网络技术有限公司 Search result ordering method and device based on search engine

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101000608A (en) * 2006-01-11 2007-07-18 吴风勇 Key word dynamic matching generating based on search engine technology
CN101071443A (en) * 2007-06-26 2007-11-14 腾讯科技(深圳)有限公司 Content-related advertising identifying method and content-related advertising server
CN101158971A (en) * 2007-11-15 2008-04-09 深圳市迅雷网络技术有限公司 Search result ordering method and device based on search engine

Cited By (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104717210A (en) * 2015-02-13 2015-06-17 北京集奥聚合科技有限公司 Method and system for connecting optional media to DSP
CN104717210B (en) * 2015-02-13 2018-06-26 北京集奥聚合科技有限公司 A kind of method and system by free media access DSP
CN105007569A (en) * 2015-06-09 2015-10-28 中山大学 Method of obtaining Internet resources by a terminal on the basis of a wireless identifier
CN105007569B (en) * 2015-06-09 2018-11-20 中山大学 A kind of method that terminal obtains Internet resources according to wireless identification
CN105069034A (en) * 2015-07-22 2015-11-18 无锡天脉聚源传媒科技有限公司 Recommendation information generation method and apparatus
CN107451161A (en) * 2016-06-01 2017-12-08 阿里巴巴集团控股有限公司 Show method for pushing, device and the platform of object
CN107944898A (en) * 2016-10-13 2018-04-20 驰众信息技术(上海)有限公司 The automatic discovery of advertisement putting building information and sort method
CN107092682A (en) * 2017-04-21 2017-08-25 北京恒冠网络数据处理有限公司 A kind of free database index method of user with data acquisition
CN107193962A (en) * 2017-05-24 2017-09-22 百度在线网络技术(北京)有限公司 A kind of intelligent figure method and device of internet promotion message
CN107507046A (en) * 2017-10-13 2017-12-22 北京奇艺世纪科技有限公司 The method and system that advertisement is recalled
CN107918658A (en) * 2017-11-20 2018-04-17 金蝶软件(中国)有限公司 A kind of business opportunity generation method and system
CN110020156A (en) * 2017-12-07 2019-07-16 深圳市腾讯计算机系统有限公司 Information recommendation method, front end implementation method, device, equipment and storage medium
CN110020156B (en) * 2017-12-07 2022-10-14 深圳市腾讯计算机系统有限公司 Information recommendation method, front-end implementation method, device, equipment and storage medium
CN110633391A (en) * 2018-06-01 2019-12-31 北京搜狗科技发展有限公司 Information searching method and device
CN110633391B (en) * 2018-06-01 2024-04-30 北京搜狗科技发展有限公司 Information searching method and device
CN109189892A (en) * 2018-09-17 2019-01-11 北京点网聚科技有限公司 A kind of recommended method and device based on article review
CN109189892B (en) * 2018-09-17 2021-04-27 北京一点网聚科技有限公司 Recommendation method and device based on article comments
CN110609952A (en) * 2019-08-15 2019-12-24 中国平安财产保险股份有限公司 Data acquisition method and system and computer equipment
CN110609952B (en) * 2019-08-15 2024-04-26 中国平安财产保险股份有限公司 Data acquisition method, system and computer equipment
CN113435193A (en) * 2021-06-16 2021-09-24 深圳市世强元件网络有限公司 Landing page keyword releasing method and device and computer equipment
CN114399329A (en) * 2021-12-22 2022-04-26 江苏沪磁智能科技有限公司 Digital advertisement transaction putting method

Also Published As

Publication number Publication date
CN103226597B (en) 2015-03-25

Similar Documents

Publication Publication Date Title
CN103226597B (en) Keyword advertisement matching method based on natural semantics
JP6105094B2 (en) Generate search results with status links to applications
US8903800B2 (en) System and method for indexing food providers and use of the index in search engines
CN103491205B (en) The method for pushing of a kind of correlated resources address based on video search and device
US20170249309A1 (en) Interpreting and Resolving Conditional Natural Language Queries
CN102419778B (en) Information searching method for discovering and clustering sub-topics of query statement
KR101040119B1 (en) Apparatus and Method for Search of Contents
CN102750375B (en) Service and tag recommendation method based on random walk
CN104111935B (en) Server and microblog pushing method and system
CN106326452A (en) Method for human-machine dialogue based on contexts
CN102622453A (en) Body-based food security event semantic retrieval system
CN103823893A (en) User comment-based product search method and system
US20130117303A1 (en) Data search device, data search method, and program
CN102722498A (en) Search engine and implementation method thereof
CN103092943A (en) Method of advertisement dispatch and advertisement dispatch server
CN102163234A (en) Equipment and method for error correction of query sequence based on degree of error correction association
AU2012335134A1 (en) Generating an advertising campaign
CN104679783A (en) Network searching method and device
WO2012151968A1 (en) Method and system for publishing internet information
US8019772B2 (en) Computer method and apparatus for tag pre-search in social software
CN105279159A (en) Contact prompting method and device
CN101599069A (en) The searching method of electronic document and system
EP2940599A1 (en) Method and apparatus for providing information and method and apparatus for providing search result
CN105095383A (en) Information issuance method, information search method and relevant device
JP6341899B2 (en) Advertisement system and advertisement delivery method

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20220421

Address after: 100000 room 116, building 3, Shuangqiao (Shuangqiao dairy factory), Chaoyang District, Beijing

Patentee after: Beijing Xiaoxiang innovation Artificial Intelligence Technology Co.,Ltd.

Address before: 901, floor 9, building 5, yard 1, Shangdi East Road, Haidian District, Beijing 100086

Patentee before: BEIJING GEO POLYMERIZATION TECHNOLOGY Co.,Ltd.