CN103514191A - Method and device for determining keyword matching mode of target popularization information - Google Patents

Method and device for determining keyword matching mode of target popularization information Download PDF

Info

Publication number
CN103514191A
CN103514191A CN201210212013.6A CN201210212013A CN103514191A CN 103514191 A CN103514191 A CN 103514191A CN 201210212013 A CN201210212013 A CN 201210212013A CN 103514191 A CN103514191 A CN 103514191A
Authority
CN
China
Prior art keywords
keyword
popularization
promotion message
information
associative key
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.)
Pending
Application number
CN201210212013.6A
Other languages
Chinese (zh)
Inventor
孙嘉
徐惠
余昌远
徐勇明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN201210212013.6A priority Critical patent/CN103514191A/en
Publication of CN103514191A publication Critical patent/CN103514191A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35—Clustering; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention provides a method and device for determining a corresponding keyword matching mode of target popularization information. The method for determining the corresponding keyword matching mode of the target popularization information specifically comprises the steps of (1) obtaining the target popularization information with the keyword matching mode to be determined, (2) carrying out clustering processing on related keywords according to keyword correlation information of the related keywords of the target popularization information, (3) determining the matching mode of a target keyword according to the keyword cluster of the target keyword of the target popularization information, and (4) determining the keyword matching mode of the target popularization information. Compared with the prior art, due to the facts that clustering is carried out on the related keywords according to the keyword correlation information of the related keywords of the target popularization information, the matching mode of the target keyword is determined according to the keyword cluster of the target keyword of the target popularization information, and then the keyword matching mode of the target popularization information is determined, the keyword matching mode corresponding to the target popularization information is effectively determined, and information popularization efficiency and information obtaining efficiency are improved.

Description

For determining the method and apparatus of the keyword match pattern of target promotion message
Technical field
The present invention relates to network promotion field, relate in particular to a kind of for determining the technology of the corresponding keyword match pattern of target promotion message.
Background technology
Current, development and the infiltration of internet, applications to user learning, work and life along with Internet technology, the network promotion, via network, promotion message is presented to the corresponding network user, because its outstanding information popularization efficiency, information acquisition efficiency and resource utilization has been subject to more and more promoting user and the network user's favor and attention.Typically, when the network user inputs certain search sequence and carries out web search, search engine not only provides conventional Search Results, the promotion message also this web search being adapted offers this network user, for example by utilizing this search sequence to carry out matching inquiry in promotion message database, obtain corresponding promotion message, should (etc.) promotion message presents to this network user.
In view of the network promotion, compare conventional information propelling movement mode and have many technical advantages, such as higher information popularization efficiency and information acquisition efficiency etc., each popularization user wishes to make full use of these technical advantages conventionally, for example, for target promotion message, determine suitable keyword match pattern and obtain better Extended Results information.Yet because reality popularization user varies, the factor that affects keyword match pattern is also very numerous, therefore, the keyword match pattern of how to confirm target promotion message, still has much challenge to improve information popularization efficiency.
Summary of the invention
The object of this invention is to provide a kind of for determining the method and apparatus of the corresponding keyword match pattern of target promotion message.
According to an aspect of the present invention, provide a kind of for determining the method for the corresponding keyword match pattern of target promotion message, the method comprises the following steps:
A obtains the target promotion message of its corresponding keyword match pattern to be determined;
B is according to the keyword correlation information corresponding with the corresponding associative key of described target promotion message, described associative key is carried out to clustering processing, to obtain one or more keyword clustering, wherein, the corresponding promotion message of described associative key is corresponding to the corresponding popularization of described target promotion message user;
C, according to the described keyword clustering under the corresponding target keyword of described target promotion message, determines the match pattern of described target keyword;
D, according to the match pattern of described target keyword, determines the corresponding keyword match pattern of described target promotion message.
According to a further aspect in the invention, also provide a kind of for determining the popularization equipment of the corresponding keyword match pattern of target promotion message, this popularization equipment comprises:
Promotion message acquisition device, for obtaining the target promotion message of its corresponding keyword match pattern to be determined;
Cluster acquisition device, for the basis keyword correlation information corresponding with the corresponding associative key of described target promotion message, described associative key is carried out to clustering processing, to obtain one or more keyword clustering, wherein, the corresponding promotion message of described associative key is corresponding to the corresponding popularization of described target promotion message user;
The first coupling determining device, for according to the described keyword clustering under the corresponding target keyword of described target promotion message, determines the match pattern of described target keyword;
The second coupling determining device, for according to the match pattern of described target keyword, determines the corresponding keyword match pattern of described target promotion message.
According to a further aspect of the invention, also provide a kind of computer equipment, comprised as the aforementioned popularization equipment for definite corresponding keyword match pattern of target promotion message according to a further aspect of the present invention.
Compared with prior art, the present invention is by the basis keyword correlation information corresponding with the corresponding associative key of target promotion message, associative key is carried out to clustering processing, according to the described keyword clustering under the corresponding target keyword of target promotion message, determine the match pattern of target keyword, according to the match pattern of target keyword, determine the corresponding keyword match pattern of target promotion message, effectively determine the corresponding keyword match pattern of target promotion message, thereby information popularization efficiency and information acquisition efficiency have been improved, and then also correspondingly improved and promoted the processing resource utilization of equipment and the source of screen utilization factor of subscriber equipment.And, the present invention can also be in conjunction with promoting the historical Extended Results information of keyword and/or the matching optimization information that matching optimization operation information is determined target keyword, determine more accurately the keyword match pattern of target promotion message, thereby improved further information popularization efficiency and information acquisition efficiency, and then also correspondingly improved and promoted the processing resource utilization of equipment and the source of screen utilization factor of subscriber equipment.Further, the present invention also can be in conjunction with the coupling preference information of promoting user, determine the corresponding keyword match pattern of target promotion message, thereby determine more accurately the corresponding keyword match pattern of target promotion message, thereby improved further information popularization efficiency and information acquisition efficiency, and then also correspondingly improved and promoted the processing resource utilization of equipment and the source of screen utilization factor of subscriber equipment.In addition, the search sequence that the present invention also can provide by obtaining search subscriber, whether detect the corresponding popularization keyword of promotion message matches with this search sequence, to determine whether that target promotion message is offered to this search subscriber, the matching degree that has improved further information popularization and user's obtaining information, has improved information popularization efficiency and information acquisition efficiency.
Accompanying drawing explanation
By reading the detailed description that non-limiting example is done of doing with reference to the following drawings, it is more obvious that other features, objects and advantages of the present invention will become:
Fig. 1 illustrates the equipment schematic diagram for definite corresponding keyword match pattern of target promotion message according to one aspect of the invention;
Fig. 2 illustrates the equipment schematic diagram for definite corresponding keyword match pattern of target promotion message in accordance with a preferred embodiment of the present invention;
Fig. 3 illustrates the method flow diagram for definite corresponding keyword match pattern of target promotion message according to a further aspect of the present invention;
Fig. 4 illustrates the method flow diagram for definite corresponding keyword match pattern of target promotion message in accordance with a preferred embodiment of the present invention.
In accompanying drawing, same or analogous Reference numeral represents same or analogous parts.
Embodiment
Below in conjunction with accompanying drawing, the present invention is described in further detail.
Fig. 1 illustrates the popularization equipment 1 for definite corresponding keyword match pattern of target promotion message according to one aspect of the invention.Wherein, popularization equipment 1 comprises promotion message acquisition device 11, cluster acquisition device 12, the first coupling determining device 13 and the second coupling determining device 14.Particularly, promotion message acquisition device 11 obtains the target promotion message of its corresponding keyword match pattern to be determined; Cluster acquisition device 12 is according to the keyword correlation information corresponding with the corresponding associative key of described target promotion message, described associative key is carried out to clustering processing, to obtain one or more keyword clustering, wherein, the corresponding promotion message of described associative key is corresponding to the corresponding popularization of described target promotion message user; The first coupling determining device 13, according to the described keyword clustering under the corresponding target keyword of described target promotion message, is determined the match pattern of described target keyword; The second coupling determining device 14, according to the match pattern of described target keyword, is determined the corresponding keyword match pattern of described target promotion message.At this, popularization equipment 1 include but not limited to the network equipment, subscriber equipment or the network equipment with subscriber equipment by the mutually integrated equipment forming of network.Wherein, the described network equipment includes but not limited to the cloud that network host, single network server, a plurality of webserver collection or a plurality of server form.At this, cloud consists of a large amount of main frames based on cloud computing (Cloud Computing) or the webserver, and wherein, cloud computing is a kind of of Distributed Calculation, the super virtual machine being comprised of the loosely-coupled computing machine collection of a group.It includes but not limited to described subscriber equipment anyly can by keyboard, telepilot, touch pad or voice-operated device, carry out with user the electronic product of man-machine interaction, such as computing machine, smart mobile phone, PDA, game machine or IPTV etc.Described network includes but not limited to internet, wide area network, Metropolitan Area Network (MAN), LAN (Local Area Network), VPN network, wireless self-organization network (Ad Hoc network) etc.Those skilled in the art will be understood that above-mentioned popularization equipment 1 is only for giving an example; other network equipments existing or that may occur from now on or subscriber equipment are as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
Particularly, the application programming interfaces (API) that promotion message acquisition device 11 provides by calling third party devices such as search engine, browser, obtain the target promotion message of its corresponding keyword match pattern to be determined; Or, by based on various communication protocol, can provide the equipment of described popularization unit to carry out alternately with other, to obtain the target promotion message of its corresponding keyword match pattern to be determined; Or by dynamic web page techniques such as JSP, obtain the search sequence that the network user inputs by subscriber equipment, search engine is according to this search sequence, in search promotion database, carry out matching inquiry, the target promotion message using the matching result inquiring as its corresponding keyword match pattern to be determined.At this, described target promotion message includes but not limited to as text link promotion message, shows class promotion message, Email promotion message etc., it comes from same popularization user, or come from a plurality of different popularization users, or come from the reference popularization user who belongs to user of the same type with popularization user.For example, user is input inquiry sequence " fresh flower " in search engine search column, search engine is according to this search sequence " fresh flower ", in search promotion database, carry out matching inquiry, the popularization keyword matching with acquisition and this search sequence " fresh flower " is as " fresh flower ", " fresh flower express delivery " etc., promotion message acquisition device 11 by with this promote the corresponding target promotion message of keyword as " fresh flower, I only choose state's fresh flower express delivery net! 100% quality guarantee ", " fresh flower is to Chinese famous-object fresh flower net " is as the target promotion message of its corresponding keyword match pattern to be determined.It will be understood by those skilled in the art that above-mentioned target promotion message is only for giving an example, other target promotion messages existing or that may occur from now on, as applicable to the present invention, also should be included in protection domain of the present invention, and with way of reference, are contained in this at this.At this, " communication protocol " comprises the transportation protocol of compunication, as TCP/IP, UDP, FTP, ICMP, NetBEUI etc., also comprise other form communications that are present in computing machine, for example the message transmission protocol between distinct program or computing machine disparate modules in the communication between the object of object based programming the inside or operating system simultaneously.
It will be understood by those skilled in the art that the above-mentioned mode of obtaining the target promotion message of its corresponding keyword match pattern to be determined is only for example; the mode of other existing or target promotion messages that obtain its corresponding keyword match pattern to be determined that may occur is from now on as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
Cluster acquisition device 12 is according to the keyword correlation information corresponding with the corresponding associative key of described target promotion message, described associative key is carried out to clustering processing, as adopt the unsupervised learning methods such as k-means, ISODATA, chain method, to obtain one or more keyword clustering, wherein, the corresponding promotion message of described associative key is corresponding to the corresponding popularization of described target promotion message user.At this, described associative key includes but not limited to following at least any one: 1) the one or more popularization keywords corresponding with described target promotion message, and wherein, this popularization keyword comes from same popularization user; 2) the whole popularization keywords corresponding with the corresponding popularization of described target promotion message user.At this, described keyword clustering includes but not limited to the popularization user's that described associative key is corresponding with it correlativity analysis category information, popularization user's as corresponding with it in associative key correlativity is high, in associative key and its corresponding popularization user's correlativity, associative key and its corresponding popularization user's correlativity is low etc.It will be understood by those skilled in the art that above-mentioned associative key or keyword clustering are only for giving an example; other associative keys existing or that may occur from now on or keyword clustering are as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
Preferably, described keyword correlation information comprises following at least any one:
The literal length information of-described associative key;
The correlation information of corresponding search sequence when-described associative key represents with it;
The popularization user's that-described associative key is corresponding with it correlation information.
For example, suppose that described keyword correlation information comprises the literal length information of described associative key, when 12 pairs of described associative keys of cluster acquisition device carry out clustering processing, suppose that the target promotion message that promotion message acquisition device 11 gets comprises from the target promotion message information1 that promotes user A:
" fresh flower, I only choose state's fresh flower express delivery net! 100% quality guarantee "
The situation of selling well fresh flower seniority among brothers and sisters birthday flower present commercial affairs fresh flower ceremony cartoon bouquet hypothesis associative key corresponding with this target promotion message comprises I to V:
I: fresh flower;
II: fresh flower express delivery;
III: gift;
IV: fresh flower express delivery;
V: flower
The literal length information of associative key I to V is respectively 2 characters, 4 characters, 2 characters, 5 characters and 1 character, cluster acquisition device 12 is according to the literal length information of associative key I to V, use k-means algorithm, to associative key, I to V carries out cluster, the one or more keyword clustering that obtain comprise as: 1.. the keyword clustering cluster1 that associative key is high with the correlativity of promoting user A, it comprises associative key II and IV; 2.. the keyword clustering cluster2 in the correlativity of associative key and popularization user A, it comprises associative key I and III; 3.. the keyword clustering cluster3 that associative key is low with the correlativity of promoting user A, it comprises associative key V.Suppose that described keyword correlation information comprises the correlation information of corresponding search sequence when described associative key represents with it, when 12 pairs of described associative keys of cluster acquisition device carry out clustering processing, when first cluster acquisition device 12 represents with it according to associative key, corresponding search sequence is carried out semantic analysis, the text matches degree of corresponding search sequence while representing with it according to associative key, determine the correlation information of corresponding search sequence when associative key represents with it, then, the correlation information of cluster acquisition device 12 corresponding search sequence during according to the representing with it of associative key I to V, use k-means algorithm, to associative key, I to V carries out cluster, to obtain one or more keyword clustering, wherein, the corresponding promotion message of described associative key is corresponding to the corresponding popularization of described target promotion message user, for example, connect example, while supposing to represent with associative key I, corresponding search sequence comprises as " fresh flower " and " gift ", while representing with associative key II and IV, corresponding search sequence comprises as " fresh flower ", " fresh flower express delivery ", " fresh flower express delivery " and " flower express delivery ", while representing with associative key III, corresponding search sequence comprises as " gift ", " red-letter day ", while representing with associative key V, corresponding search sequence comprises as " fresh flower ", when the definite associative key I to V of cluster acquisition device 12 represents with it, the correlation information of corresponding search sequence comprises: when associative key II and IV represent with it, the correlativity of corresponding search sequence is high, when associative key I and V represent with it in correlativity of corresponding search sequence, when associative key III represents with it, the correlativity of corresponding search sequence is low, the correlation information of corresponding search sequence when cluster acquisition device 12 represents with it according to this associative key I to V, use k-means algorithm, to associative key, I to V carries out cluster, to obtain one or more keyword clustering, the one or more keyword clustering that obtain comprise as: 1.. the keyword clustering cluster1 that associative key is high with the correlativity of promoting user A, it comprises associative key II and IV, 2.. the keyword clustering cluster2 in the correlativity of associative key and popularization user A, it comprises associative key I and V, 3.. the keyword clustering cluster3 that associative key is low with the correlativity of promoting user A, it comprises associative key III.Suppose that described keyword correlation information comprises the popularization user's that described associative key is corresponding with it correlation information, when 12 pairs of described associative keys of cluster acquisition device carry out clustering processing, first cluster acquisition device 12 cuts to associative key the entry set that word analysis obtains, IDF (Inverse Document Frequency according to the included one or more entries of this entry set in entry database, anti-document frequency) value, the IDF value of each entry is added or according to the predefined weight value of each entry, the IDF value of each entry is weighted to summation, obtain the IDF value of the entry set that associative key is corresponding, determine the popularization user's that described associative key is corresponding with it correlation information, then according to the described associative key of the determining popularization user's corresponding with it correlation information, use k-means algorithm, to associative key, I to V carries out cluster, to obtain one or more keyword clustering, wherein, the corresponding promotion message of described associative key is corresponding to the corresponding popularization of described target promotion message user, at this, described entry database includes but not limited to: the search database of 1) promoting search engine, 2) comprise by all databases with reference to promoting the corresponding all popularization keywords of user and forming with promoting that user belongs to user of the same type, it can be arranged in popularization equipment 1, also can be arranged in the network equipment being connected via network with popularization equipment 1, as server, also connect example, the IDF value of supposing the entry set that associative key I to V that cluster acquisition device 12 obtains is corresponding is respectively 0.8, 0.9, 0.4, 0.9 and 0.6, the correlation information of the popularization user A that the definite associative key I to V of cluster acquisition device 12 is corresponding with it comprise as: associative key II and IV are high with the correlativity of its corresponding popularization user A, in the correlativity of the popularization user A that associative key I and V are corresponding with it, the correlativity of the popularization user A that associative key III is corresponding with it is low, cluster acquisition device 12 is according to the correlation information of this associative key I to V popularization user A corresponding with it, use k-means algorithm, to associative key, I to V carries out cluster, to obtain one or more keyword clustering, the one or more keyword clustering that obtain comprise as: 1.. the keyword clustering cluster1 that associative key is high with the correlativity of promoting user A, it comprises associative key II and IV, 2.. the keyword clustering cluster2 in the correlativity of associative key and popularization user A, it comprises associative key I and V, 3.. the keyword clustering cluster3 that associative key is low with the correlativity of promoting user A, it comprises associative key III.
It will be understood by those skilled in the art that the mode of the correlation information of corresponding search sequence when above-mentioned definite associative key represents with it is only for giving an example; when other definite associative keys existing or that may occur from now on represent with it, the mode of the correlation information of corresponding search sequence is as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
The mode that it will be understood by those skilled in the art that the popularization user's that above-mentioned definite described associative key is corresponding with it correlation information is only for example; the mode of the popularization user's that other definite described associative keys existing or that may occur are from now on corresponding with it correlation information is as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
It will be understood by those skilled in the art that the mode of above-mentioned acquisition keyword clustering is only for giving an example; the mode of other acquisition keyword clustering existing or that may occur is from now on as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
Preferably, cluster acquisition device 12 also can be according to the keyword correlation information corresponding with the corresponding associative key of described target promotion message, and in conjunction with the classified information of predetermined match pattern, described associative key is carried out to clustering processing, as adopt the supervised learning methods such as decision tree, recurrence, naive Bayesian, SVM, to obtain one or more keyword clustering, wherein, the corresponding promotion message of described associative key is corresponding to the corresponding popularization of described target promotion message user.At this, the classified information of described predetermined match pattern includes but not limited to as comprised 3 kinds of classified informations of broad match, phrase match and exact matching, the classified information of described predetermined match pattern can also be expanded, as increase the senior setting of match pattern, form new classified information, as comprise 4 kinds of classified informations of 4 kinds of match patterns.For example, the corresponding user A that promotes, suppose that the keyword correlation information corresponding with the corresponding associative key of described target promotion message that cluster acquisition device 12 is determined comprises the literal length information as associative key, the popularization user's that when associative key represents with it, correlation information of corresponding search sequence and associative key are corresponding with it correlation information, the classified information of supposing predetermined match pattern is 3 kinds, be respectively broad match, phrase match and exact matching, the keyword correlation information corresponding with the corresponding associative key of described target promotion message that cluster acquisition device 12 is determined according to it, use decision Tree algorithms, to associative key, I to V carries out cluster, the one or more keyword clustering that obtain comprise as: 1.. the keyword clustering cluster1 that associative key is high with the correlativity of promoting user A, it comprises associative key II and IV, 2.. the keyword clustering cluster2 in the correlativity of associative key and popularization user A, it comprises associative key I and V, 3.. the keyword clustering cluster3 that associative key is low with the correlativity of promoting user A, it comprises associative key III.
The mode that the classified information that it will be understood by those skilled in the art that the match pattern that above-mentioned combination is predetermined is carried out clustering processing to described associative key is only for for example; the classified information of the match pattern that other combinations existing or that may occur are from now on predetermined is carried out clustering processing mode to described associative key is as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
The first coupling determining device 13, according to the described keyword clustering under the corresponding target keyword of described target promotion message, is determined the match pattern of described target keyword.At this, described target keyword comprise with the corresponding associative key of described target promotion message in the highest one with described target promotion message matching degree.For example, the number of times that first the first coupling determining device 13 occurs in described target promotion message textual description by the corresponding associative key of described target promotion message is determined the matching degree of this associative key and this target promotion message, then according to this matching degree, determine the corresponding target keyword of described target promotion message, then again according to the described keyword classification being obtained by cluster acquisition device 12 under this target keyword, determine the match pattern of described target keyword, the target keyword of supposing the target promotion message information1 of the popularization user A that the first coupling determining device 13 is definite is associative key II, and the affiliated described keyword clustering of this associative key II that cluster acquisition device 12 obtains is the keyword clustering cluster1 that associative key and the correlativity of promoting user A are high, the match pattern with described target keyword that the first coupling determining device 13 is determined is exact matching.For another example, the target keyword of supposing the target promotion message information1 of the popularization user A that the first coupling determining device 13 is definite is associative key I, and the affiliated described keyword clustering of this associative key I that cluster acquisition device 12 obtains is the keyword clustering cluster2 in associative key and the correlativity of promoting user A, the match patterns with described target keyword that the first coupling determining device 13 is determined are phrase match.
It will be understood by those skilled in the art that the above-mentioned mode of determining the corresponding target keyword of described target promotion message is only for giving an example; the mode of other existing or corresponding target keyword of definite described target promotion message that may occur is from now on as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
The mode that the classified information that it will be understood by those skilled in the art that the above-mentioned match pattern of determining described target keyword is carried out clustering processing to described associative key is only for for example; the classified information of the match pattern of other definite described target keyword existing or that may occur is from now on carried out clustering processing mode to described associative key is as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
The second coupling determining device 14, according to the match pattern of described target keyword, is determined the corresponding keyword match pattern of described target promotion message.At this, described keyword match pattern includes but not limited to following at least any one: 1) broad match, at this, when the search sequence that described broad match intention search subscriber is searched for and the corresponding popularization keyword of target promotion message height correlation, this target promotion message can be triggered and be provided for search subscriber, for example, the popularization keyword that hypothetical target promotion message inforrmation2 is corresponding is " Expert English language training by qualified teachers ", the search sequence that can trigger the search subscriber of this target promotion message information2 comprises: a. search sequence belongs to synonym near synonym with popularization keyword " Expert English language training by qualified teachers ", as Expert English language training by qualified teachers, English training, b. search sequence belongs to related term with popularization keyword " Expert English language training by qualified teachers ", as education on foreign language, English training in summer time, c. search sequence belongs to the variant form word of promoting keyword " Expert English language training by qualified teachers ", and as increased, summer time " is trained English " in space, word order inconsistent " training English ", belong to mistake and do not spell word " hard language training " etc., d. in search sequence, include the consistent phrase of phrase word order of promoting keyword " Expert English language training by qualified teachers ", as " Expert English language training by qualified teachers summer school ", " which Expert English language training by qualified teachers mechanism is good ", 2) phrase match, at this, the search sequence that described phrase match intention search subscriber is searched for comprises and the corresponding popularization keyword of target promotion message phrase completely, or when the synon front and back of the corresponding popularization keyword of target promotion message and this popularization keyword are inserted other words or word order and are put upside down, this target promotion message can be triggered and be provided for search subscriber, connect example, as " Expert English language training by qualified teachers ”，“ Expert English language training by qualified teachers mechanism ", " training English mechanism ", 3) exact matching, at this, when the search sequence that described exact matching intention search subscriber is searched for and the corresponding popularization keyword of target promotion message are in full accord, this target promotion message can be triggered and be provided for search subscriber, also connect example, as " Expert English language training by qualified teachers ", 4) negative match, at this, when described negative match intention comprises predetermined negative keyword in the search sequence that search subscriber is searched for, this target promotion message is not triggered and therefore can be provided for this search subscriber, as supposed, promote keyword for " flower ", the negative keyword that arranges be " express delivery ", while comprising " express delivery " in search sequence, as " fresh flower express delivery ", this target promotion message is not triggered and therefore can be provided for this search subscriber, 5) extensively modifier mates, and at this, the setting of described extensive modifier coupling intention to broad match, triggers target promotion message to limit some word in broad match, 6) senior setting, at this, the described senior senior setting that intention phrase match is set, as limited, promote the necessary words of keyword, while comprising the necessary words of this setting in search sequence, corresponding target promotion message is just triggered and is provided for search subscriber, it will be understood by those skilled in the art that above-mentioned keyword match pattern is only for giving an example, other keyword match patterns existing or that may occur are from now on as applicable to the present invention, also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.For example, the second coalignment 14 is according to the match pattern of described target keyword, and the match pattern of described target keyword is set to the corresponding keyword match pattern of described target promotion message.
Between each device of popularization equipment 1, be constant work.Particularly, promotion message acquisition device 11 continues to obtain the target promotion message of its corresponding keyword match pattern to be determined; Cluster acquisition device 12 continues according to the keyword correlation information corresponding with the corresponding associative key of described target promotion message, described associative key is carried out to clustering processing, to obtain one or more keyword clustering, wherein, the corresponding promotion message of described associative key is corresponding to the corresponding popularization of described target promotion message user; The first coupling determining device 13 continues according to the described keyword clustering under the corresponding target keyword of described target promotion message, determines the match pattern of described target keyword; The second coupling determining device 14 continues according to the match pattern of described target keyword, determines the corresponding keyword match pattern of described target promotion message.At this, those skilled in the art will be understood that " continuing " refers to that each device of popularization equipment 1 constantly carries out respectively the acquisition of determining of the determining of match pattern of the determining of the obtaining of target promotion message, keyword clustering, target keyword, the corresponding keyword match pattern of target promotion message and demand class information, until this popularization equipment 1 stops obtaining of target promotion message in a long time.
(with reference to figure 1) in a preferred embodiment, popularization equipment 1 also comprises classification acquisition device (not shown) and the information of optimization determining device (not shown).Below with reference to Fig. 1, the preferred embodiment is described: particularly, promotion message acquisition device 11 obtains the target promotion message of its corresponding keyword match pattern to be determined; Cluster acquisition device 12 is according to the keyword correlation information corresponding with the corresponding associative key of described target promotion message, described associative key is carried out to clustering processing, to obtain one or more keyword clustering, wherein, the corresponding promotion message of described associative key is corresponding to the corresponding popularization of described target promotion message user; Classification acquisition device, according to the classification dimensional information of described associative key, carries out clustering processing to described associative key, to obtain one or more dimension classification; Optimization information determining device, according to the dimension classification described in described target keyword, is determined the matching optimization information of described target keyword; The first coupling determining device 13 is according to the described keyword clustering under the corresponding target keyword of described target promotion message, and in conjunction with the matching optimization information of described target keyword, determines the match pattern of described target keyword; The second coupling determining device 14, according to the match pattern of described target keyword, is determined the corresponding keyword match pattern of described target promotion message.At this, promotion message acquisition device 11, cluster acquisition device 12 and the second coupling determining device 14 and Fig. 1 the corresponding intrument in corresponding embodiment same or similar, therefore do not repeat them here, and mode is by reference contained in this.
Particularly, classification acquisition device, according to the classification dimensional information of described associative key, carries out clustering processing to described associative key, as adopted the unsupervised learning methods such as k-means, ISODATA, chain method, to obtain one or more dimension classification.At this, the classification of described dimension includes but not limited to following at least any one: 1) the corresponding target promotion message of associative key webpage flow is large and the corresponding target promotion message of this associative key webpage flow mass is low, i.e. the low classification of the large flow mass of flow; 2) the corresponding target promotion message of associative key webpage flow is little and the corresponding target promotion message of this associative key webpage flow mass is high, i.e. flow low discharge quality high-class; 3) classified information to be optimized of associative key, as the classification that need amplify match pattern, need dwindle the classification of match pattern.It will be understood by those skilled in the art that above-mentioned dimension classification is only for giving an example, other dimensions classification existing or that may occur from now on, as applicable to the present invention, also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
Preferably, wherein, described classification dimensional information comprises following at least any one:
The historical Extended Results information of-described associative key;
The matching optimization operation information of-described associative key.
For example, when described classification dimensional information comprises the historical Extended Results information of described associative key, when classification acquisition device carries out clustering processing to described associative key, at this, described historical Extended Results information includes but not limited to following at least any one: 1) the historical Extended Results information of described target promotion message in promoting user, as the amount of representing, click volume, input region, represent the period, average daily amount of representing etc., or the ensemble average Extended Results information generating at the Extended Results in period for example according to described target promotion message, 2) the popularization user's corresponding with this target promotion message user related information, as promoting region, popularization resource information etc., 3) feedback information of the network user to this target promotion message, as clicked, access, access time, access duration etc., 4) access the network user's of this target promotion message user related information, as age, occupation, access IP address etc., described historical Extended Results information includes but not limited to the combination of following one or more dimensions: represent, click, promote record, transform, the attribute of described search target promotion message itself, investigate the period etc., at this, the attribute of described search target promotion message itself is as quality degree, match pattern, promote URL, popularization resource is controlled, popularization plan etc., it will be understood by those skilled in the art that above-mentioned historical Extended Results information is only for giving an example, other historical Extended Results information existing or that may occur are from now on as applicable to the present invention, also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.For example, suppose that the classification dimensional information of associative key I to V comprises: 1) the low classification of the large flow mass of flow for promoting user A; 2) flow low discharge quality high-class, classify acquisition device according to this dimensional information of classifying, use k-means algorithm, described associative key I to V is carried out to clustering processing, one or more dimensions classification of obtaining comprise that it comprises associative key III and V as the low classification of the large flow mass of flow; Flow low discharge quality high-class, it comprises associative key I, II and IV.For another example, when described classification dimensional information comprises the matching optimization operation information of described associative key, when classification acquisition device carries out clustering processing to described associative key, at this, the modification of the feedback information that described matching optimization operation information includes but not limited to the popularization user Network Based user corresponding with target promotion message to this target promotion message, as adjusted, promote keyword quantity, revise searched key word and the match pattern of promoting keyword, adjust and promote the period, adjust and promote region etc., for example, suppose for promoting user A, the classification dimensional information of associative key I to V comprises: the classification that 1) needs to amplify match pattern, 2) need dwindle the classification of match pattern, classify acquisition device according to this dimensional information of classifying, use k-means algorithm, described associative key I to V is carried out to clustering processing, the one or more dimensions classification that obtain comprise as: need dwindle the classification of match pattern, it comprises associative key III and V, the classification that needs to amplify match pattern, it comprises associative key I, II and IV.
It will be understood by those skilled in the art that the mode of above-mentioned acquisition dimension classification is only for giving an example; the mode of other acquisition dimensions existing or that may occur from now on classification is as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
Then, optimize information determining device according to the dimension classification under described target keyword, determine the matching optimization information of described target keyword.At this, described matching optimization information comprises the information to be optimized as target keyword, as need amplify match pattern, need dwindle match pattern.For example, suppose that the target keyword corresponding with associative key I to V is associative key II, and the affiliated dimension classified information of this target keyword that the acquisition device of classifying obtains is the classified information that needs to amplify match pattern, the matching optimization information of optimizing this definite target keyword of information determining device is amplification match pattern.For another example, suppose that the target keyword corresponding with associative key I to V is associative key II, and the affiliated dimension classified information of this target keyword that classification acquisition device obtains is the high classified information of the little quality of flow, optimize the matching optimization information of this definite target keyword of information determining device for amplifying match pattern.
It will be understood by those skilled in the art that the above-mentioned mode according to the matching optimization information of the definite described target keyword of dimension classification under described target keyword is only for example; other existing or modes of matching optimization information of determining described target keyword according to the dimension classification under described target keyword that may occur are from now on as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
Then, the first coupling determining device 13 is according to the described keyword clustering under the corresponding target keyword of described target promotion message, and in conjunction with the matching optimization information of described target keyword, determines the match pattern of described target keyword; For example, suppose for promoting user A, the first coupling determining device 13 determine with the corresponding target keyword of target promotion message information1 be associative key II, and described keyword clustering corresponding to associative key II that cluster acquisition device 12 obtains is the keyword clustering cluster1 that associative key and the correlativity of promoting user A are high, the matching optimization information of this target keyword that optimization information determining device is determined is for amplifying match pattern, and the match pattern of this target keyword that the first coupling determining device 13 is determined is phrase match.
It will be understood by those skilled in the art that the mode of match pattern that the above-mentioned matching optimization information according to target keyword described in described combination determines described target keyword is only for for example; the mode of match pattern that described in other combinations existing or that may occur from now on, the matching optimization information of target keyword is determined described target keyword is as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
Preferably, popularization equipment 1 also comprises type information determining device (not shown).Particularly, type information determining device, according to described popularization user's Extended Results information, determines that described popularization user's popularization resource is controlled type information; The second coupling determining device 14, according to the match pattern of described target keyword, is controlled type information in conjunction with described popularization resource, determines the corresponding keyword match pattern of described target promotion message.
Particularly, type information determining device, according to described popularization user's Extended Results information, determines that described popularization user's popularization resource is controlled type information.At this, described Extended Results information includes but not limited to the Extended Results information of described target promotion message in promoting user, as the amount of representing, click volume, input region, represent the period, the daily amount of representing, rank etc., or the ensemble average Extended Results information generating at the Extended Results such as in region according to described target promotion message etc.At this, described popularization resource is controlled type information and is included but not limited to economizing type user, non-economizing type user etc.For example, it is high that the Extended Results information of supposing to promote user A is that left side represents rate, and type information determining device is according to this Extended Results information, and it is non-economizing type user that the popularization resource of definite popularization user A is controlled type information; The Extended Results information of supposing to promote user A for the amount of representing low, type information determining device is according to this Extended Results information, the popularization resource of definite popularization user A control type information is economizing type user.
Then, the second coupling determining device 14, according to the match pattern of described target keyword, is controlled type information in conjunction with described popularization resource, determines the corresponding keyword match pattern of described target promotion message.For example, suppose for promoting user A, the match pattern of the described target keyword that the first coupling determining device 13 is determined is phrase match, and the popularization resource of the definite popularization user A of type information determining device to control type information be economizing type user, the second coupling determining device 14 determines that the corresponding keyword match pattern of described target promotion message is exact matching.
It will be understood by those skilled in the art that promoting resource described in above-mentioned combination controls mode that type information determines the corresponding keyword match pattern of described target promotion message only for for example; described in other combinations existing or that may occur from now on, promote resource and control mode that type information determines the corresponding keyword match pattern of described target promotion message as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
(with reference to figure 1) in a further advantageous embodiment, popularization equipment 1 also comprises retrieval device (not shown), testing fixture (not shown) and generator (not shown).Below with reference to Fig. 1, the preferred embodiment is described: particularly, promotion message acquisition device 11 obtains the target promotion message of its corresponding keyword match pattern to be determined; Cluster acquisition device 12 is according to the keyword correlation information corresponding with the corresponding associative key of described target promotion message, described associative key is carried out to clustering processing, to obtain one or more keyword clustering, wherein, the corresponding promotion message of described associative key is corresponding to the corresponding popularization of described target promotion message user; The first coupling determining device 13, according to the described keyword clustering under the corresponding target keyword of described target promotion message, is determined the match pattern of described target keyword; The second coupling determining device 14, according to the match pattern of described target keyword, is determined the corresponding keyword match pattern of described target promotion message; Retrieval device obtains the search sequence that search subscriber provides; Testing fixture, according to described keyword match pattern, checks whether the corresponding popularization keyword of described target promotion message matches with described search sequence; If coupling, generator offers described search subscriber by described target promotion message.At this, promotion message acquisition device 11, cluster acquisition device 12, the first coupling determining device 13 and the second coupling determining device 14 and Fig. 1 the corresponding intrument in corresponding embodiment same or similar, therefore do not repeat them here, and mode is by reference contained in this.
Particularly, retrieval device passes through ASP, the dynamic web page techniques such as JSP, obtain the search sequence that search subscriber is inputted by subscriber equipment, using this as search sequence that search subscriber was provided, or by the application programming interfaces (API) that provide such as search engine etc. third party device, obtain the search sequence that user inputs by search engine search column, for example, search subscriber B inputs keyword " fresh flower express delivery " in search engine search column, press "enter" key", the application programming interfaces that retrieval device provides by this search engine (API), just get the search sequence that search subscriber B provides.It will be understood by those skilled in the art that the above-mentioned mode of obtaining the search sequence that search subscriber provides is only for for example; other existing or modes of obtaining the search sequence that search subscriber provides that may occur are from now on as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
Testing fixture, according to described keyword match pattern, checks whether the corresponding popularization keyword of described target promotion message matches with described search sequence.For example, connect example, suppose for promoting user A, the corresponding popularization keyword of its target promotion message information1 is associative key II, the corresponding described keyword match pattern of this target promotion message information1 is exact matching, testing fixture is according to this exact matching pattern, by the mode of text comparison, checks that whether the corresponding popularization keyword of this target promotion message information1 matches with the described search sequence that retrieval device gets.
If coupling, generator offers described search subscriber by described target promotion message.For example, connect example, testing fixture inspection finds that the search sequence that the target corresponding popularization keyword of promotion message information1 " fresh flower express delivery " and search subscriber B provide matches, generator, by dynamic web page techniques such as ASP, JSP or PHP, or the communication mode of other agreements, as communication protocols such as http or https, provide to described search subscriber, as this user's subscriber equipment, for user, browse.
Preferably, if coupling, and meet predetermined promotion message ordering rule, generator offers described search subscriber by described target promotion message.For example, also connect example, testing fixture inspection finds that the search sequence that the target corresponding popularization keyword of promotion message information1 " fresh flower express delivery " and search subscriber B provide matches, and meet the promotion message ordering rule of reservation as promoted keyword click volume, the popularization resource of promoting keyword arranges, or the consumption of estimating of promoting keyword changes, generator, the sequence of the described target promotion message of determining according to the promotion message ordering rule of this reservation in Search Results, by such as ASP, the dynamic web page technique such as JSP or PHP, or the communication mode of other agreements, as communication protocols such as http or https, provide to described search subscriber, as this user's subscriber equipment, for user, browse.
Fig. 2 illustrates the equipment schematic diagram for definite corresponding keyword match pattern of target promotion message in accordance with a preferred embodiment of the present invention.Wherein, popularization equipment 1 comprises promotion message acquisition device 11 ', cluster acquisition device 12 ', the first coupling determining device 13 ' and the second coupling determining device 14 '.Particularly, promotion message acquisition device 11 ' obtains the target promotion message of its corresponding keyword match pattern to be determined; Cluster acquisition device 12 ' is according to the keyword correlation information corresponding with the corresponding associative key of described target promotion message, described associative key is carried out to clustering processing, to obtain one or more keyword clustering, wherein, the corresponding promotion message of described associative key is corresponding to the corresponding popularization of described target promotion message user; The first coupling determining device 13 ', according to the described keyword clustering under the corresponding target keyword of described target promotion message, is determined the match pattern of described target keyword; The second coupling determining device 14 ', according to the match pattern of described target keyword, in conjunction with described popularization user's coupling preference information, is determined the corresponding keyword match pattern of described target promotion message.At this, promotion message acquisition device 11 ', cluster acquisition device 12 ' and the first coupling determining device 13 ' and Fig. 1 the corresponding intrument in corresponding embodiment same or similar, therefore do not repeat them here, and mode is by reference contained in this.
Particularly, the second coupling determining device 14 ', according to the match pattern of described target keyword, in conjunction with described popularization user's coupling preference information, is determined the corresponding keyword match pattern of described target promotion message.For example, suppose for promoting user A, the match pattern of the described target keyword that the first coalignment 13 ' is determined is broad match, and the coupling preference information of promoting user A is exact matching, the corresponding keyword match pattern of described target promotion message information1 that the second coupling determining device 14 ' is determined is phrase match.
It will be understood by those skilled in the art that mode that the coupling preference information of promoting user described in above-mentioned combination determines the corresponding keyword match pattern of described target promotion message is only for for example; the mode that the coupling preference information of promoting user described in other combinations existing or that may occur is from now on determined the corresponding keyword match pattern of described target promotion message is as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
Preferably, popularization equipment 1 also comprises preference information determining device 15 ', and particularly, preference information determining device 15 ', according to described popularization user's popularization operation, is determined described popularization user's coupling preference information; The second coalignment 14 ', according to the match pattern of described target keyword, in conjunction with described coupling preference information, is determined the corresponding keyword match pattern of described target promotion message.
Particularly, preference information determining device 15 ' is according to described popularization user's popularization operation, determine described popularization user's coupling preference information, at this, described popularization operation includes but not limited to that described popularization user promotes the modification of resource setting etc. to the modification of keyword match pattern, keyword.For example, suppose to promote number of times that user A is adjusted into exact matching to the corresponding match pattern of target promotion message information1 by broad match within the scope of 10 days of on June 13rd, 4 days 1 June 2012 time over 10 times, the statistical information of operation is promoted in the modification to keyword match pattern that preference information determining device 15 ' is promoted user A according to this, the frequency that the corresponding match pattern of target promotion message information1 is adjusted into exact matching by broad match as this popularization user A is 1 times/day, preference information determining device 15 ' is according to this statistical information, the coupling preference information of this popularization user A determining is exact matching.
It will be understood by those skilled in the art that the mode of coupling preference information that above-mentioned combination determines described popularization user is only for for example; the mode of other definite described popularization users' existing or that may occur from now on coupling preference information is as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
Then, the second coalignment 14 ', according to the match pattern of described target keyword, in conjunction with described coupling preference information, is determined the corresponding keyword match pattern of described target promotion message.Connect example, suppose for promoting user A, the match pattern of the described target keyword that the first coalignment 13 ' is determined is broad match, and the coupling preference information of the definite popularization user A of preference information determining device 15 ' is exact matching, the corresponding keyword match pattern of described target promotion message information1 that the second coupling determining device 14 ' is determined is phrase match.
Fig. 3 illustrates the method flow diagram for definite corresponding keyword match pattern of target promotion message according to a further aspect of the present invention.
Particularly, in step S1, popularization equipment 1 obtains the target promotion message of its corresponding keyword match pattern to be determined; In step S2, popularization equipment 1 is according to the keyword correlation information corresponding with the corresponding associative key of described target promotion message, described associative key is carried out to clustering processing, to obtain one or more keyword clustering, wherein, the corresponding promotion message of described associative key is corresponding to the corresponding popularization of described target promotion message user; In step S3, popularization equipment 1, according to the described keyword clustering under the corresponding target keyword of described target promotion message, is determined the match pattern of described target keyword; In step S4, popularization equipment 1, according to the match pattern of described target keyword, is determined the corresponding keyword match pattern of described target promotion message.At this, popularization equipment 1 include but not limited to the network equipment, subscriber equipment or the network equipment with subscriber equipment by the mutually integrated equipment forming of network.Wherein, the described network equipment includes but not limited to the cloud that network host, single network server, a plurality of webserver collection or a plurality of server form.At this, cloud consists of a large amount of main frames based on cloud computing (Cloud Computing) or the webserver, and wherein, cloud computing is a kind of of Distributed Calculation, the super virtual machine being comprised of the loosely-coupled computing machine collection of a group.It includes but not limited to described subscriber equipment anyly can by keyboard, telepilot, touch pad or voice-operated device, carry out with user the electronic product of man-machine interaction, such as computing machine, smart mobile phone, PDA, game machine or IPTV etc.Described network includes but not limited to internet, wide area network, Metropolitan Area Network (MAN), LAN (Local Area Network), VPN network, wireless self-organization network (Ad Hoc network) etc.Those skilled in the art will be understood that above-mentioned popularization equipment 1 is only for giving an example; other network equipments existing or that may occur from now on or subscriber equipment are as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
Particularly, in step S1, the application programming interfaces (API) that popularization equipment 1 provides by calling third party devices such as search engine, browser, obtain the target promotion message of its corresponding keyword match pattern to be determined; Or, by based on various communication protocol, can provide the equipment of described popularization unit to carry out alternately with other, to obtain the target promotion message of its corresponding keyword match pattern to be determined; Or by dynamic web page techniques such as JSP, obtain the search sequence that the network user inputs by subscriber equipment, search engine is according to this search sequence, in search promotion database, carry out matching inquiry, the target promotion message using the matching result inquiring as its corresponding keyword match pattern to be determined.At this, described target promotion message includes but not limited to as text link promotion message, shows class promotion message, Email promotion message etc., it comes from same popularization user, or come from a plurality of different popularization users, or come from the reference popularization user who belongs to user of the same type with popularization user.For example, user is input inquiry sequence " fresh flower " in search engine search column, search engine is according to this search sequence " fresh flower ", in search promotion database, carry out matching inquiry, the popularization keyword matching with acquisition and this search sequence " fresh flower " is as " fresh flower ", " fresh flower express delivery " etc., in step S 1, popularization equipment 1 by with this promote the corresponding target promotion message of keyword as " fresh flower, I only choose state's fresh flower express delivery net! 100% quality guarantee ", " fresh flower is to Chinese famous-object fresh flower net " is as the target promotion message of its corresponding keyword match pattern to be determined.It will be understood by those skilled in the art that above-mentioned target promotion message is only for giving an example, other target promotion messages existing or that may occur from now on, as applicable to the present invention, also should be included in protection domain of the present invention, and with way of reference, are contained in this at this.At this, " communication protocol " comprises the transportation protocol of compunication, as TCP/IP, UDP, FTP, ICMP, NetBEUI etc., also comprise other form communications that are present in computing machine, for example the message transmission protocol between distinct program or computing machine disparate modules in the communication between the object of object based programming the inside or operating system simultaneously.
It will be understood by those skilled in the art that the above-mentioned mode of obtaining the target promotion message of its corresponding keyword match pattern to be determined is only for example; the mode of other existing or target promotion messages that obtain its corresponding keyword match pattern to be determined that may occur is from now on as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
In step S2, popularization equipment 1 is according to the keyword correlation information corresponding with the corresponding associative key of described target promotion message, described associative key is carried out to clustering processing, as adopt the unsupervised learning methods such as k-means, ISODATA, chain method, to obtain one or more keyword clustering, wherein, the corresponding promotion message of described associative key is corresponding to the corresponding popularization of described target promotion message user.At this, described associative key includes but not limited to following at least any one: 1) the one or more popularization keywords corresponding with described target promotion message, and wherein, this popularization keyword comes from same popularization user; 2) the whole popularization keywords corresponding with the corresponding popularization of described target promotion message user.At this, described keyword clustering includes but not limited to the popularization user's that described associative key is corresponding with it correlativity analysis category information, popularization user's as corresponding with it in associative key correlativity is high, in associative key and its corresponding popularization user's correlativity, associative key and its corresponding popularization user's correlativity is low etc.It will be understood by those skilled in the art that above-mentioned associative key or keyword clustering are only for giving an example; other associative keys existing or that may occur from now on or keyword clustering are as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
Preferably, described keyword correlation information comprises following at least any one:
The literal length information of-described associative key;
The correlation information of corresponding search sequence when-described associative key represents with it;
The popularization user's that-described associative key is corresponding with it correlation information.
For example, suppose that described keyword correlation information comprises the literal length information of described associative key, in step S2, when 1 pair of described associative key of popularization equipment carries out clustering processing, suppose in step S1, the target promotion message that popularization equipment 1 gets comprises from the target promotion message information1 that promotes user A:
" fresh flower, I only choose state's fresh flower express delivery net! 100% quality guarantee "
The situation of selling well fresh flower seniority among brothers and sisters birthday flower present commercial affairs fresh flower ceremony cartoon bouquet hypothesis associative key corresponding with this target promotion message comprises I to V:
I: fresh flower;
II: fresh flower express delivery;
III: gift;
IV: fresh flower express delivery;
V: flower
The literal length information of associative key I to V is respectively 2 characters, 4 characters, 2 characters, 5 characters and 1 character, in step S2, popularization equipment 1 is according to the literal length information of associative key I to V, use k-means algorithm, to associative key, I to V carries out cluster, the one or more keyword clustering that obtain comprise as: 1.. the keyword clustering cluster1 that associative key is high with the correlativity of promoting user A, it comprises associative key II and IV; 2.. the keyword clustering cluster2 in the correlativity of associative key and popularization user A, it comprises associative key I and III; 3.. the keyword clustering cluster3 that associative key is low with the correlativity of promoting user A, it comprises associative key V.Suppose that described keyword correlation information comprises the correlation information of corresponding search sequence when described associative key represents with it, in step S2, when 1 pair of described associative key of popularization equipment carries out clustering processing, in step S2, when first popularization equipment 1 represent with it according to associative key, corresponding search sequence is carried out semantic analysis, the text matches degree of corresponding search sequence while representing with it according to associative key, determine the correlation information of corresponding search sequence when associative key represents with it, then, in step S2, the correlation information of popularization equipment 1 corresponding search sequence during according to the representing with it of associative key I to V, use k-means algorithm, to associative key, I to V carries out cluster, to obtain one or more keyword clustering, wherein, the corresponding promotion message of described associative key is corresponding to the corresponding popularization of described target promotion message user, for example, connect example, while supposing to represent with associative key I, corresponding search sequence comprises as " fresh flower " and " gift ", while representing with associative key II and IV, corresponding search sequence comprises as " fresh flower ", " fresh flower express delivery ", " fresh flower express delivery " and " flower express delivery ", while representing with associative key III, corresponding search sequence comprises as " gift ", " red-letter day ", while representing with associative key V, corresponding search sequence comprises as " fresh flower ", in step S2, when the definite associative key I to V of popularization equipment 1 represents with it, the correlation information of corresponding search sequence comprises: when associative key II and IV represent with it, the correlativity of corresponding search sequence is high, when associative key I and V represent with it in correlativity of corresponding search sequence, when associative key III represents with it, the correlativity of corresponding search sequence is low, in step S2, the correlation information of corresponding search sequence when popularization equipment 1 represents with it according to this associative key I to V, use k-means algorithm, to associative key, I to V carries out cluster, to obtain one or more keyword clustering, the one or more keyword clustering that obtain comprise as: 1.. the keyword clustering cluster1 that associative key is high with the correlativity of promoting user A, it comprises associative key II and IV, 2.. the keyword clustering cluster2 in the correlativity of associative key and popularization user A, it comprises associative key I and V, 3.. the keyword clustering cluster3 that associative key is low with the correlativity of promoting user A, it comprises associative key III.Suppose that described keyword correlation information comprises the popularization user's that described associative key is corresponding with it correlation information, in step S2, when 1 pair of described associative key of popularization equipment carries out clustering processing, in step S2, first popularization equipment 1 cut to associative key the entry set that word analysis obtains, IDF (Inverse Document Frequency according to the included one or more entries of this entry set in entry database, anti-document frequency) value, the IDF value of each entry is added or according to the predefined weight value of each entry, the IDF value of each entry is weighted to summation, obtain the IDF value of the entry set that associative key is corresponding, determine the popularization user's that described associative key is corresponding with it correlation information, then according to the described associative key of the determining popularization user's corresponding with it correlation information, use k-means algorithm, to associative key, I to V carries out cluster, to obtain one or more keyword clustering, wherein, the corresponding promotion message of described associative key is corresponding to the corresponding popularization of described target promotion message user, at this, described entry database includes but not limited to: the search database of 1) promoting search engine, 2) comprise by all databases with reference to promoting the corresponding all popularization keywords of user and forming with promoting that user belongs to user of the same type, it can be arranged in popularization equipment 1, also can be arranged in the network equipment being connected via network with popularization equipment 1, as server, also connect example, suppose in step S2, the IDF value of the entry set that associative key I to V that popularization equipment 1 obtains is corresponding is respectively 0.8, 0.9, 0.4, 0.9 and 0.6, in step S2, the correlation information of the popularization user A that the definite associative key I to V of popularization equipment 1 is corresponding with it comprise as: associative key II and IV are high with the correlativity of its corresponding popularization user A, in the correlativity of the popularization user A that associative key I and V are corresponding with it, the correlativity of the popularization user A that associative key III is corresponding with it is low, in step S2, popularization equipment 1 is according to the correlation information of this associative key I to V popularization user A corresponding with it, use k-means algorithm, to associative key, I to V carries out cluster, to obtain one or more keyword clustering, the one or more keyword clustering that obtain comprise as: 1.. the keyword clustering cluster1 that associative key is high with the correlativity of promoting user A, it comprises associative key II and IV, 2.. the keyword clustering cluster2 in the correlativity of associative key and popularization user A, it comprises associative key I and V, 3.. the keyword clustering cluster3 that associative key is low with the correlativity of promoting user A, it comprises associative key III.
It will be understood by those skilled in the art that the mode of the correlation information of corresponding search sequence when above-mentioned definite associative key represents with it is only for giving an example; when other definite associative keys existing or that may occur from now on represent with it, the mode of the correlation information of corresponding search sequence is as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
The mode that it will be understood by those skilled in the art that the popularization user's that above-mentioned definite described associative key is corresponding with it correlation information is only for example; the mode of the popularization user's that other definite described associative keys existing or that may occur are from now on corresponding with it correlation information is as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
It will be understood by those skilled in the art that the mode of above-mentioned acquisition keyword clustering is only for giving an example; the mode of other acquisition keyword clustering existing or that may occur is from now on as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
Preferably, in step S2, popularization equipment 1 also can be according to the keyword correlation information corresponding with the corresponding associative key of described target promotion message, and in conjunction with the classified information of predetermined match pattern, described associative key is carried out to clustering processing, as adopt the supervised learning methods such as decision tree, recurrence, naive Bayesian, SVM, to obtain one or more keyword clustering, wherein, the corresponding promotion message of described associative key is corresponding to the corresponding popularization of described target promotion message user.At this, the classified information of described predetermined match pattern includes but not limited to as comprised 3 kinds of classified informations of broad match, phrase match and exact matching, the classified information of described predetermined match pattern can also be expanded, as increase the senior setting of match pattern, form new classified information, as comprise 4 kinds of classified informations of 4 kinds of match patterns.For example, the corresponding user A that promotes, suppose in step S2, the keyword correlation information corresponding with the corresponding associative key of described target promotion message that popularization equipment 1 is determined comprises the literal length information as associative key, the popularization user's that when associative key represents with it, correlation information of corresponding search sequence and associative key are corresponding with it correlation information, the classified information of supposing predetermined match pattern is 3 kinds, be respectively broad match, phrase match and exact matching, in step S2, the keyword correlation information corresponding with the corresponding associative key of described target promotion message that popularization equipment 1 is determined according to it, use decision Tree algorithms, to associative key, I to V carries out cluster, the one or more keyword clustering that obtain comprise as: 1.. the keyword clustering cluster1 that associative key is high with the correlativity of promoting user A, it comprises associative key II and IV, 2.. the keyword clustering cluster2 in the correlativity of associative key and popularization user A, it comprises associative key I and V, 3.. the keyword clustering cluster3 that associative key is low with the correlativity of promoting user A, it comprises associative key III.
The mode that the classified information that it will be understood by those skilled in the art that the match pattern that above-mentioned combination is predetermined is carried out clustering processing to described associative key is only for for example; the classified information of the match pattern that other combinations existing or that may occur are from now on predetermined is carried out clustering processing mode to described associative key is as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
In step S3, popularization equipment 1, according to the described keyword clustering under the corresponding target keyword of described target promotion message, is determined the match pattern of described target keyword.At this, described target keyword comprise with the corresponding associative key of described target promotion message in the highest one with described target promotion message matching degree.For example, in step S3, the number of times that first popularization equipment 1 occur in described target promotion message textual description by the corresponding associative key of described target promotion message is determined the matching degree of this associative key and this target promotion message, then according to this matching degree, determine the corresponding target keyword of described target promotion message, then again according to the described keyword classification being obtained in step S2 by it under this target keyword, determine the match pattern of described target keyword, suppose in step S3, the target keyword of the target promotion message information1 of the popularization user A that popularization equipment 1 is definite is associative key II, and in step S2, described keyword clustering under this associative key II that popularization equipment 1 obtains is the keyword clustering cluster1 that associative key is high with the correlativity of promoting user A, in step S3, the match pattern with described target keyword that popularization equipment 1 is determined is exact matching.For another example, suppose in step S3, the target keyword of the target promotion message information1 of the popularization user A that popularization equipment 1 is definite is associative key I, and in step S2, described keyword clustering under this associative key I that popularization equipment 1 obtains is the keyword clustering cluster2 in associative key and the correlativity of promoting user A,, in step S3, the match pattern with described target keyword that popularization equipment 1 is determined is phrase match.
It will be understood by those skilled in the art that the above-mentioned mode of determining the corresponding target keyword of described target promotion message is only for giving an example; the mode of other existing or corresponding target keyword of definite described target promotion message that may occur is from now on as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
The mode that the classified information that it will be understood by those skilled in the art that the above-mentioned match pattern of determining described target keyword is carried out clustering processing to described associative key is only for for example; the classified information of the match pattern of other definite described target keyword existing or that may occur is from now on carried out clustering processing mode to described associative key is as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
In step S4, popularization equipment 1, according to the match pattern of described target keyword, is determined the corresponding keyword match pattern of described target promotion message.At this, described keyword match pattern includes but not limited to following at least any one: 1) broad match, at this, when the search sequence that described broad match intention search subscriber is searched for and the corresponding popularization keyword of target promotion message height correlation, this target promotion message can be triggered and be provided for search subscriber, for example, the popularization keyword that hypothetical target promotion message information2 is corresponding is " Expert English language training by qualified teachers ", the search sequence that can trigger the search subscriber of this target promotion message information2 comprises: a. search sequence belongs to synonym near synonym with popularization keyword " Expert English language training by qualified teachers ", as Expert English language training by qualified teachers, English training, b. search sequence belongs to related term with popularization keyword " Expert English language training by qualified teachers ", as education on foreign language, English training in summer time, c. search sequence belongs to the variant form word of promoting keyword " Expert English language training by qualified teachers ", and as increased, summer time " is trained English " in space, word order inconsistent " training English ", belong to mistake and do not spell word " hard language training " etc., d. in search sequence, include the consistent phrase of phrase word order of promoting keyword " Expert English language training by qualified teachers ", as " Expert English language training by qualified teachers summer school ", " which Expert English language training by qualified teachers mechanism is good ", 2) phrase match is at this, the search sequence that described phrase match intention search subscriber is searched for comprises and the corresponding popularization keyword of target promotion message phrase completely, or when the synon front and back of the corresponding popularization keyword of target promotion message and this popularization keyword are inserted other words or word order and are put upside down, this target promotion message can be triggered and be provided for search subscriber, connect example, as " Expert English language training by qualified teachers ”，“ Expert English language training by qualified teachers mechanism ", " training English mechanism ", 3) exact matching, at this, when the search sequence that described exact matching intention search subscriber is searched for and the corresponding popularization keyword of target promotion message are in full accord, this target promotion message can be triggered and be provided for search subscriber, also connect example, as " Expert English language training by qualified teachers ", 4) negative match, at this, when described negative match intention comprises predetermined negative keyword in the search sequence that search subscriber is searched for, this target promotion message is not triggered and therefore can be provided for this search subscriber, as supposed, promote keyword for " flower ", the negative keyword that arranges be " express delivery ", while comprising " express delivery " in search sequence, as " fresh flower express delivery ", this target promotion message is not triggered and therefore can be provided for this search subscriber, 5) extensively modifier mates, and at this, the setting of described extensive modifier coupling intention to broad match, triggers target promotion message to limit some word in broad match, 6) senior setting, at this, the described senior senior setting that intention phrase match is set, as limited, promote the necessary words of keyword, while comprising the necessary words of this setting in search sequence, corresponding target promotion message is just triggered and is provided for search subscriber, it will be understood by those skilled in the art that above-mentioned keyword match pattern is only for giving an example, other keyword match patterns existing or that may occur are from now on as applicable to the present invention, also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.For example, in step S4, popularization equipment 1 is according to the match pattern of described target keyword, and the match pattern of described target keyword is set to the corresponding keyword match pattern of described target promotion message.
Between each step of popularization equipment 1, be constant work.Particularly, in step S 1, popularization equipment 1 continues to obtain the target promotion message of its corresponding keyword match pattern to be determined; In step S2, popularization equipment 1 continues according to the keyword correlation information corresponding with the corresponding associative key of described target promotion message, described associative key is carried out to clustering processing, to obtain one or more keyword clustering, wherein, the corresponding promotion message of described associative key is corresponding to the corresponding popularization of described target promotion message user; In step S3, popularization equipment 1 continues according to the described keyword clustering under the corresponding target keyword of described target promotion message, determines the match pattern of described target keyword; In step S4, popularization equipment 1 continues according to the match pattern of described target keyword, determines the corresponding keyword match pattern of described target promotion message.At this, those skilled in the art will be understood that " continuing " refers to that each step of popularization equipment 1 constantly carries out respectively the acquisition of determining of the determining of match pattern of the determining of the obtaining of target promotion message, keyword clustering, target keyword, the corresponding keyword match pattern of target promotion message and demand class information, until this popularization equipment 1 stops obtaining of target promotion message in a long time.
(with reference to figure 3) in a preferred embodiment, popularization equipment 1 also comprises step S6 (not shown) and step S7 (not shown).Below with reference to Fig. 3, the preferred embodiment is described:
Particularly, in step S1, popularization equipment 1 obtains the target promotion message of its corresponding keyword match pattern to be determined; In step S2, popularization equipment 1 is according to the keyword correlation information corresponding with the corresponding associative key of described target promotion message, described associative key is carried out to clustering processing, to obtain one or more keyword clustering, wherein, the corresponding promotion message of described associative key is corresponding to the corresponding popularization of described target promotion message user; In step S6, popularization equipment 1, according to the classification dimensional information of described associative key, carries out clustering processing to described associative key, to obtain one or more dimension classification; In step S7, popularization equipment 1, according to the dimension classification described in described target keyword, is determined the matching optimization information of described target keyword; In step S3, popularization equipment 1 is according to the described keyword clustering under the corresponding target keyword of described target promotion message, and in conjunction with the matching optimization information of described target keyword, determines the match pattern of described target keyword; In step S4, popularization equipment 1, according to the match pattern of described target keyword, is determined the corresponding keyword match pattern of described target promotion message.At this, step S1, step S2 and step S4 and Fig. 3 the corresponding step in corresponding embodiment same or similar, therefore do not repeat them here, and mode is by reference contained in this.
Particularly, in step S6, popularization equipment 1, according to the classification dimensional information of described associative key, carries out clustering processing to described associative key, as adopt the unsupervised learning methods such as k-means, ISODATA, chain method, to obtain one or more dimension classification.At this, the classification of described dimension includes but not limited to following at least any one: 1) the corresponding target promotion message of associative key webpage flow is large and the corresponding target promotion message of this associative key webpage flow mass is low, i.e. the low classification of the large flow mass of flow; 2) the corresponding target promotion message of associative key webpage flow is little and the corresponding target promotion message of this associative key webpage flow mass is high, i.e. flow low discharge quality high-class; 3) classified information to be optimized of associative key, as the classification that need amplify match pattern, need dwindle the classification of match pattern.It will be understood by those skilled in the art that above-mentioned dimension classification is only for giving an example, other dimensions classification existing or that may occur from now on, as applicable to the present invention, also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
Preferably, wherein, described classification dimensional information comprises following at least any one:
The historical Extended Results information of-described associative key;
The matching optimization operation information of-described associative key.
For example, when described classification dimensional information comprises the historical Extended Results information of described associative key, in step S6, when 1 pair of described associative key of popularization equipment carries out clustering processing, at this, described historical Extended Results information includes but not limited to following at least any one: 1) the historical Extended Results information of described target promotion message in promoting user, as the amount of representing, click volume, input region, represent the period, average daily amount of representing etc., or the ensemble average Extended Results information generating at the Extended Results in period for example according to described target promotion message, 2) the popularization user's corresponding with this target promotion message user related information, as promoting region, popularization resource information etc., 3) feedback information of the network user to this target promotion message, as clicked, access, access time, access duration etc., 4) access the network user's of this target promotion message user related information, as age, occupation, access IP address etc., described historical Extended Results information includes but not limited to the combination of following one or more dimensions: represent, click, promote record, transform, the attribute of described search target promotion message itself, investigate the period etc., at this, the attribute of described search target promotion message itself is as quality degree, match pattern, promote URL, popularization resource is controlled, popularization plan etc., it will be understood by those skilled in the art that above-mentioned historical Extended Results information is only for giving an example, other historical Extended Results information existing or that may occur are from now on as applicable to the present invention, also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.For example, suppose that the classification dimensional information of associative key I to V comprises: 1) the low classification of the large flow mass of flow for promoting user A; 2) flow low discharge quality high-class, in step S6, popularization equipment 1 is according to this classification dimensional information, use k-means algorithm, described associative key I to V is carried out to clustering processing, one or more dimensions classification of obtaining comprise that it comprises associative key III and V as the low classification of the large flow mass of flow; Flow low discharge quality high-class, it comprises associative key I, II and IV.For another example, when described classification dimensional information comprises the matching optimization operation information of described associative key, in step S6, when 1 pair of described associative key of popularization equipment carries out clustering processing, at this, the modification of the feedback information that described matching optimization operation information includes but not limited to the popularization user Network Based user corresponding with target promotion message to this target promotion message, as adjusted, promote keyword quantity, revise searched key word and the match pattern of promoting keyword, adjust and promote the period, adjust and promote region etc., for example, suppose for promoting user A, the classification dimensional information of associative key I to V comprises: the classification that 1) needs to amplify match pattern, 2) need dwindle the classification of match pattern, in step S6, popularization equipment 1 is according to this classification dimensional information, use k-means algorithm, described associative key I to V is carried out to clustering processing, the one or more dimensions classification that obtain comprise as: need dwindle the classification of match pattern, it comprises associative key III and V, the classification that needs to amplify match pattern, it comprises associative key I, II and IV.
It will be understood by those skilled in the art that the mode of above-mentioned acquisition dimension classification is only for giving an example; the mode of other acquisition dimensions existing or that may occur from now on classification is as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
Then,, in step S7, popularization equipment 1, according to the dimension classification under described target keyword, is determined the matching optimization information of described target keyword.At this, described matching optimization information comprises the information to be optimized as target keyword, as need amplify match pattern, need dwindle match pattern.For example, suppose that the target keyword corresponding with associative key I to V is associative key II, and in step S6, dimension classified information under this target keyword that popularization equipment 1 obtains, for needing to amplify the classified information of match pattern, is optimized the matching optimization information of this definite target keyword of information determining device for amplifying match pattern.For another example, suppose that the target keyword corresponding with associative key I to V is associative key II, and in step S6, dimension classified information under this target keyword that popularization equipment 1 obtains is the high classified information of the little quality of flow,, in step S7, the matching optimization information of this target keyword that popularization equipment 1 is determined is for amplifying match pattern.
It will be understood by those skilled in the art that the above-mentioned mode according to the matching optimization information of the definite described target keyword of dimension classification under described target keyword is only for example; other existing or modes of matching optimization information of determining described target keyword according to the dimension classification under described target keyword that may occur are from now on as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
Then, in step S3, popularization equipment 1 is according to the described keyword clustering under the corresponding target keyword of described target promotion message, and in conjunction with the matching optimization information of described target keyword, determines the match pattern of described target keyword, for example, suppose for promoting user A, in step S3, popularization equipment 1 determine with the corresponding target keyword of target promotion message information1 be associative key II, and in step S2, described keyword clustering corresponding to associative key II that popularization equipment 1 obtains is the keyword clustering cluster1 that associative key is high with the correlativity of promoting user A, in step S7, the matching optimization information of this target keyword that popularization equipment 1 is determined is for amplifying match pattern, in step S3, the match pattern of this target keyword that popularization equipment 1 is determined is phrase match.
It will be understood by those skilled in the art that the mode of match pattern that the above-mentioned matching optimization information according to target keyword described in described combination determines described target keyword is only for for example; the mode of match pattern that described in other combinations existing or that may occur from now on, the matching optimization information of target keyword is determined described target keyword is as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
Preferably, popularization equipment 1 also comprises step S8 (not shown).Particularly, in step S8, popularization equipment 1, according to described popularization user's Extended Results information, determines that described popularization user's popularization resource is controlled type information; In step S4, popularization equipment 1, according to the match pattern of described target keyword, is controlled type information in conjunction with described popularization resource, determines the corresponding keyword match pattern of described target promotion message.
Particularly, in step S8, popularization equipment 1, according to described popularization user's Extended Results information, determines that described popularization user's popularization resource is controlled type information.At this, described Extended Results information includes but not limited to the Extended Results information of described target promotion message in promoting user, as the amount of representing, click volume, input region, represent the period, the daily amount of representing, rank etc., or the ensemble average Extended Results information generating at the Extended Results such as in region according to described target promotion message etc.At this, described popularization resource is controlled type information and is included but not limited to economizing type user, non-economizing type user etc.For example, it is high that the Extended Results information of supposing to promote user A is that left side represents rate, and, in step S8, popularization equipment 1 is according to this Extended Results information, and it is non-economizing type user that the popularization resource of definite popularization user A is controlled type information; The Extended Results information of supposing to promote user A for the amount of representing low,, in step S8, popularization equipment 1 is according to this Extended Results information, the popularization resource of definite popularization user A control type information is economizing type user.
Then, in step S4, popularization equipment 1, according to the match pattern of described target keyword, is controlled type information in conjunction with described popularization resource, determines the corresponding keyword match pattern of described target promotion message.For example, suppose for promoting user A, in step S3, the match pattern of the described target keyword that popularization equipment 1 is determined is phrase match, and the popularization resource of the definite popularization user A of type information determining device to control type information be economizing type user,, in step S4, popularization equipment 1 determines that the corresponding keyword match pattern of described target promotion message is exact matching.
It will be understood by those skilled in the art that promoting resource described in above-mentioned combination controls mode that type information determines the corresponding keyword match pattern of described target promotion message only for for example; described in other combinations existing or that may occur from now on, promote resource and control mode that type information determines the corresponding keyword match pattern of described target promotion message as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
(with reference to figure 3) in a further advantageous embodiment, popularization equipment 1 also comprises step S9 (not shown), step S10 (not shown) and step S11 (not shown).Below with reference to Fig. 3, the preferred embodiment is described: particularly, in step S1, popularization equipment 1 obtains the target promotion message of its corresponding keyword match pattern to be determined; In step S2, popularization equipment 1 is according to the keyword correlation information corresponding with the corresponding associative key of described target promotion message, described associative key is carried out to clustering processing, to obtain one or more keyword clustering, wherein, the corresponding promotion message of described associative key is corresponding to the corresponding popularization of described target promotion message user; In step S3, popularization equipment 1, according to the described keyword clustering under the corresponding target keyword of described target promotion message, is determined the match pattern of described target keyword; In step S4, popularization equipment 1, according to the match pattern of described target keyword, is determined the corresponding keyword match pattern of described target promotion message; In step S9, popularization equipment 1 obtains the search sequence that search subscriber provides; In step S10, popularization equipment 1, according to described keyword match pattern, checks whether the corresponding popularization keyword of described target promotion message matches with described search sequence; If coupling, in step S11, popularization equipment 1 offers described search subscriber by described target promotion message.At this, step S1, step S2, step S3 and step S4 and Fig. 3 the corresponding intrument in corresponding embodiment same or similar, therefore do not repeat them here, and mode is by reference contained in this.
Particularly, in step S9, popularization equipment 1 passes through ASP, the dynamic web page techniques such as JSP, obtain the search sequence that search subscriber is inputted by subscriber equipment, using this as search sequence that search subscriber was provided, or by the application programming interfaces (API) that provide such as search engine etc. third party device, obtain the search sequence that user inputs by search engine search column, for example, search subscriber B inputs keyword " fresh flower express delivery " in search engine search column, press "enter" key", in step S9, the application programming interfaces that popularization equipment 1 provides by this search engine (API), just get the search sequence that search subscriber B provides.It will be understood by those skilled in the art that the above-mentioned mode of obtaining the search sequence that search subscriber provides is only for for example; other existing or modes of obtaining the search sequence that search subscriber provides that may occur are from now on as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
In step S 10, popularization equipment 1, according to described keyword match pattern, checks whether the corresponding popularization keyword of described target promotion message matches with described search sequence.For example, connect example, suppose for promoting user A, the corresponding popularization keyword of its target promotion message information1 is associative key II, the corresponding described keyword match pattern of this target promotion message information1 is exact matching, in step S10, popularization equipment 1 is according to this exact matching pattern, by the mode of text comparison, check that whether the corresponding popularization keyword of this target promotion message information1 matches with the described search sequence that retrieval device gets.
If coupling, in step S11, popularization equipment 1 offers described search subscriber by described target promotion message.For example, connect example, in step S10, popularization equipment 1 checks finds that the search sequence that the target corresponding popularization keyword of promotion message information1 " fresh flower express delivery " and search subscriber B provide matches, in step S11, popularization equipment 1, by dynamic web page techniques such as ASP, JSP or PHP, or the communication mode of other agreements, as communication protocols such as http or https, provide to described search subscriber, as this user's subscriber equipment, for user, browse.
Preferably, if coupling, and meet predetermined promotion message ordering rule, in step S11,1 of popularization equipment offers described search subscriber by described target promotion message.For example, also connect example, in step S10, popularization equipment 1 checks finds that the search sequence that the target corresponding popularization keyword of promotion message information1 " fresh flower express delivery " and search subscriber B provide matches, and meet the promotion message ordering rule of reservation as promoted keyword click volume, the popularization resource of promoting keyword arranges, or the consumption of estimating of promoting keyword changes, in step S11, popularization equipment 1, the sequence of the described target promotion message of determining according to the promotion message ordering rule of this reservation in Search Results, by such as ASP, the dynamic web page technique such as JSP or PHP, or the communication mode of other agreements, as communication protocols such as http or https, provide to described search subscriber, as this user's subscriber equipment, for user, browse.
Fig. 4 illustrates the method flow diagram for definite corresponding keyword match pattern of target promotion message in accordance with a preferred embodiment of the present invention.
Particularly, in step S1 ', popularization equipment 1 obtains the target promotion message of its corresponding keyword match pattern to be determined; In step S2 ', popularization equipment 1 is according to the keyword correlation information corresponding with the corresponding associative key of described target promotion message, described associative key is carried out to clustering processing, to obtain one or more keyword clustering, wherein, the corresponding promotion message of described associative key is corresponding to the corresponding popularization of described target promotion message user; In step S3 ', popularization equipment 1, according to the described keyword clustering under the corresponding target keyword of described target promotion message, is determined the match pattern of described target keyword; In step S4 ', popularization equipment 1, according to the match pattern of described target keyword, in conjunction with described popularization user's coupling preference information, is determined the corresponding keyword match pattern of described target promotion message.At this, step S1 ', step S2 ' and step S3 ' and Fig. 3 the corresponding step in corresponding embodiment same or similar, therefore do not repeat them here, and mode is by reference contained in this.
Particularly, in step S4 ', popularization equipment 1, according to the match pattern of described target keyword, in conjunction with described popularization user's coupling preference information, is determined the corresponding keyword match pattern of described target promotion message.For example, suppose for promoting user A, in step S3 ', the match pattern of the described target keyword that popularization equipment 1 is determined is broad match, and the coupling preference information of promoting user A is exact matching,, in step S4 ', the corresponding keyword match pattern of described target promotion message information1 that popularization equipment 1 is determined is phrase match.
It will be understood by those skilled in the art that mode that the coupling preference information of promoting user described in above-mentioned combination determines the corresponding keyword match pattern of described target promotion message is only for for example; the mode that the coupling preference information of promoting user described in other combinations existing or that may occur is from now on determined the corresponding keyword match pattern of described target promotion message is as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
Preferably, popularization equipment 1 also comprises step S5 ', and particularly, in step S5 ', popularization equipment 1, according to described popularization user's popularization operation, is determined described popularization user's coupling preference information; In step S4 ', popularization equipment 1, according to the match pattern of described target keyword, in conjunction with described coupling preference information, is determined the corresponding keyword match pattern of described target promotion message.
Particularly, in step S5 ', popularization equipment 1 is according to described popularization user's popularization operation, determine described popularization user's coupling preference information, at this, described popularization operation includes but not limited to that described popularization user promotes the modification of resource setting etc. to the modification of keyword match pattern, keyword.For example, suppose to promote number of times that user A is adjusted into exact matching to the corresponding match pattern of target promotion message information1 by broad match within the scope of 10 days of on June 13rd, 4 days 1 June 2012 time over 10 times, in step S5 ', the statistical information of operation is promoted in the modification to keyword match pattern that popularization equipment 1 is promoted user A according to this, the frequency that the corresponding match pattern of target promotion message information1 is adjusted into exact matching by broad match as this popularization user A is 1 times/day, in step S5 ', popularization equipment 1 is according to this statistical information, the coupling preference information of this popularization user A determining is exact matching.
It will be understood by those skilled in the art that the mode of coupling preference information that above-mentioned combination determines described popularization user is only for for example; the mode of other definite described popularization users' existing or that may occur from now on coupling preference information is as applicable to the present invention; also should be included in protection domain of the present invention, and with way of reference, be contained in this at this.
Then,, in step S4 ', popularization equipment 1, according to the match pattern of described target keyword, in conjunction with described coupling preference information, is determined the corresponding keyword match pattern of described target promotion message.Connect example, suppose for promoting user A, in step S3 ', the match pattern of the described target keyword that popularization equipment 1 is determined is broad match, and in step S5 ', the coupling preference information of the popularization user A that popularization equipment 1 is definite is exact matching, and, in step S4 ', the corresponding keyword match pattern of described target promotion message information1 that popularization equipment 1 is determined is phrase match.
It should be noted that the present invention can be implemented in the assembly of software and/or software and hardware, for example, can adopt special IC (ASIC), general object computing machine or any other similar hardware device to realize.In one embodiment, software program of the present invention can carry out to realize step mentioned above or function by processor.Similarly, software program of the present invention (comprising relevant data structure) can be stored in computer readable recording medium storing program for performing, for example, and RAM storer, magnetic or CD-ROM driver or flexible plastic disc and similar devices.In addition, steps more of the present invention or function can adopt hardware to realize, for example, thereby as coordinate the circuit of carrying out each step or function with processor.
In addition, a part of the present invention can be applied to computer program, and for example computer program instructions, when it is carried out by computing machine, by the operation of this computing machine, can call or provide the method according to this invention and/or technical scheme.And call the programmed instruction of method of the present invention, may be stored in fixing or movably in recording medium, and/or be transmitted by the data stream in broadcast or other signal bearing medias, and/or be stored in according in the working storage of the computer equipment of described programmed instruction operation.At this, comprise according to one embodiment of present invention a device, this device comprises for storing the storer of computer program instructions and for the processor of execution of program instructions, wherein, when this computer program instructions is carried out by this processor, trigger this device and move based on aforementioned according to the method for a plurality of embodiment of the present invention and/or technical scheme.
To those skilled in the art, obviously the invention is not restricted to the details of above-mentioned one exemplary embodiment, and in the situation that not deviating from spirit of the present invention or essential characteristic, can realize the present invention with other concrete form.Therefore, no matter from which point, all should regard embodiment as exemplary, and be nonrestrictive, scope of the present invention is limited by claims rather than above-mentioned explanation, is therefore intended to be included in the present invention dropping on the implication that is equal to important document of claim and all changes in scope.Any Reference numeral in claim should be considered as limiting related claim.In addition, obviously other unit or step do not got rid of in " comprising " word, and odd number is not got rid of plural number.A plurality of unit that device is stated in claim or device also can You Yige unit or device by software or hardware, realize.The first, the second word such as grade is used for representing title, and does not represent any specific order.

Claims (21)

1. for determining a method for the corresponding keyword match pattern of target promotion message, wherein, the method comprises the following steps:
A obtains the target promotion message of its corresponding keyword match pattern to be determined;
B is according to the keyword correlation information corresponding with the corresponding associative key of described target promotion message, described associative key is carried out to clustering processing, to obtain one or more keyword clustering, wherein, the corresponding promotion message of described associative key is corresponding to the corresponding popularization of described target promotion message user;
C, according to the described keyword clustering under the corresponding target keyword of described target promotion message, determines the match pattern of described target keyword;
D, according to the match pattern of described target keyword, determines the corresponding keyword match pattern of described target promotion message.
2. method according to claim 1, wherein, the method also comprises:
-according to the classification dimensional information of described associative key, described associative key is carried out to clustering processing, to obtain one or more dimension classification;
-according to the dimension classification under described target keyword, determine the matching optimization information of described target keyword;
Wherein, described step c comprises:
-according to the described keyword clustering under the corresponding target keyword of described target promotion message, and in conjunction with the matching optimization information of described target keyword, determine the match pattern of described target keyword.
3. method according to claim 2, wherein, described classification dimensional information comprises following at least any one:
The historical Extended Results information of-described associative key;
The matching optimization operation information of-described associative key.
4. according to the method in any one of claims 1 to 3, wherein, described keyword correlation information comprises following at least any one:
The literal length information of-described associative key;
The correlation information of corresponding search sequence when-described associative key represents with it;
The popularization user's that-described associative key is corresponding with it correlation information.
5. according to the method described in any one in claim 1 to 4, wherein, described step b comprises:
-according to the keyword correlation information corresponding with the corresponding associative key of described target promotion message, and in conjunction with the classified information of predetermined match pattern, described associative key is carried out to clustering processing, to obtain one or more keyword clustering, wherein, the corresponding promotion message of described associative key is corresponding to the corresponding popularization of described target promotion message user.
6. according to the method described in any one in claim 1 to 5, wherein, described steps d comprises:
-according to the match pattern of described target keyword, in conjunction with described popularization user's coupling preference information, determine the corresponding keyword match pattern of described target promotion message.
7. method according to claim 6, wherein, the method also comprises:
-according to described popularization user's popularization operation, determine described popularization user's coupling preference information;
Wherein, described steps d comprises:
-according to the match pattern of described target keyword, in conjunction with described coupling preference information, determine the corresponding keyword match pattern of described target promotion message.
8. according to the method described in any one in claim 1 to 7, wherein, the method also comprises:
-according to described popularization user's Extended Results information, determine that described popularization user's popularization resource is controlled type information;
Wherein, described steps d comprises:
-according to the match pattern of described target keyword, in conjunction with described popularization resource, control type information, determine the corresponding keyword match pattern of described target promotion message.
9. according to the method described in any one in claim 1 to 8, wherein, the method also comprises:
-obtain the search sequence that search subscriber provides;
-according to described keyword match pattern, check whether the corresponding popularization keyword of described target promotion message matches with described search sequence;
If x coupling, offers described search subscriber by described target promotion message.
10. method according to claim 9, wherein, described step x comprises:
-Ruo coupling, and meet predetermined promotion message ordering rule, described target promotion message is offered to described search subscriber.
11. 1 kinds of popularization equipment for definite corresponding keyword match pattern of target promotion message, wherein, this popularization equipment comprises:
Promotion message acquisition device, for obtaining the target promotion message of its corresponding keyword match pattern to be determined;
Cluster acquisition device, for the basis keyword correlation information corresponding with the corresponding associative key of described target promotion message, described associative key is carried out to clustering processing, to obtain one or more keyword clustering, wherein, the corresponding promotion message of described associative key is corresponding to the corresponding popularization of described target promotion message user;
The first coupling determining device, for according to the described keyword clustering under the corresponding target keyword of described target promotion message, determines the match pattern of described target keyword;
The second coupling determining device, for according to the match pattern of described target keyword, determines the corresponding keyword match pattern of described target promotion message.
12. popularization equipment according to claim 11, wherein, this popularization equipment also comprises:
Classification acquisition device, for according to the classification dimensional information of described associative key, carries out clustering processing to described associative key, to obtain one or more dimension classification;
Optimization information determining device, for according to the dimension classification under described target keyword, determines the matching optimization information of described target keyword;
Wherein, described the first coupling determining device, for:
-according to the described keyword clustering under the corresponding target keyword of described target promotion message, and in conjunction with the matching optimization information of described target keyword, determine the match pattern of described target keyword.
13. popularization equipment according to claim 12, wherein, described classification dimensional information comprises following at least any one:
The historical Extended Results information of-described associative key;
The matching optimization operation information of-described associative key.
14. according to claim 11 to the popularization equipment described in any one in 13, and wherein, described keyword correlation information comprises following at least any one:
The literal length information of-described associative key;
The correlation information of corresponding search sequence when-described associative key represents with it;
The popularization user's that-described associative key is corresponding with it correlation information.
15. according to claim 11 to the popularization equipment described in any one in 14, and wherein, described cluster acquisition device is used for:
-according to the keyword correlation information corresponding with the corresponding associative key of described target promotion message, and in conjunction with the classified information of predetermined match pattern, described associative key is carried out to clustering processing, to obtain one or more keyword clustering, wherein, the corresponding promotion message of described associative key is corresponding to the corresponding popularization of described target promotion message user.
16. according to claim 11 to the popularization equipment described in any one in 15, and wherein, described the second coupling determining device is used for:
-according to the match pattern of described target keyword, in conjunction with described popularization user's coupling preference information, determine the corresponding keyword match pattern of described target promotion message.
17. popularization equipment according to claim 16, wherein, this popularization equipment also comprises:
Preference information determining device, for according to described popularization user's popularization operation, determines described popularization user's coupling preference information;
Wherein, described the second coalignment is used for:
-according to the match pattern of described target keyword, in conjunction with described coupling preference information, determine the corresponding keyword match pattern of described target promotion message.
18. according to claim 11 to the popularization equipment described in any one in 17, and wherein, this popularization equipment also comprises:
Type information determining device, for according to described popularization user's Extended Results information, determines that described popularization user's popularization resource is controlled type information;
Wherein, described the second coupling determining device is used for:
-according to the match pattern of described target keyword, in conjunction with described popularization resource, control type information, determine the corresponding keyword match pattern of described target promotion message.
19. according to claim 11 to the popularization equipment described in any one in 18, and wherein, this popularization equipment also comprises:
Retrieval device, the search sequence providing for obtaining search subscriber;
Testing fixture, for according to described keyword match pattern, checks whether the corresponding popularization keyword of described target promotion message matches with described search sequence;
Generator, if for coupling, offer described search subscriber by described target promotion message.
20. popularization equipment according to claim 19, wherein, described generator is used for:
-Ruo coupling, and meet predetermined promotion message ordering rule, described target promotion message is offered to described search subscriber.
21. 1 kinds of computer equipments, comprise the popularization equipment as described in any one in claim 11 to 20.
CN201210212013.6A 2012-06-20 2012-06-20 Method and device for determining keyword matching mode of target popularization information Pending CN103514191A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201210212013.6A CN103514191A (en) 2012-06-20 2012-06-20 Method and device for determining keyword matching mode of target popularization information

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201210212013.6A CN103514191A (en) 2012-06-20 2012-06-20 Method and device for determining keyword matching mode of target popularization information

Publications (1)

Publication Number Publication Date
CN103514191A true CN103514191A (en) 2014-01-15

Family

ID=49896927

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201210212013.6A Pending CN103514191A (en) 2012-06-20 2012-06-20 Method and device for determining keyword matching mode of target popularization information

Country Status (1)

Country Link
CN (1) CN103514191A (en)

Cited By (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103955480A (en) * 2014-04-02 2014-07-30 百度在线网络技术（北京）有限公司 Method and equipment for determining target object information corresponding to user
CN104408191A (en) * 2014-12-15 2015-03-11 北京国双科技有限公司 Method and device for obtaining correlated keywords of keywords
CN104462310A (en) * 2014-11-28 2015-03-25 北京国双科技有限公司 Detection method and device for correlation of webpage search keywords
CN104933047A (en) * 2014-03-17 2015-09-23 北京奇虎科技有限公司 Method and device for determining value of search term
CN104951460A (en) * 2014-03-27 2015-09-30 阿里巴巴集团控股有限公司 Ranking parameter value determination method and device based on keyword clustering
CN105808685A (en) * 2016-03-02 2016-07-27 腾讯科技（深圳）有限公司 Promotion information pushing method and device
CN106570019A (en) * 2015-10-10 2017-04-19 北京国双科技有限公司 Key word configuration method and device
CN106909982A (en) * 2015-12-23 2017-06-30 北京奇虎科技有限公司 A kind of method and device for optimizing advertisement keyword match pattern
WO2018050022A1 (en) * 2016-09-13 2018-03-22 腾讯科技（深圳）有限公司 Application program recommendation method, and server
CN108241629A (en) * 2016-12-23 2018-07-03 百度在线网络技术（北京）有限公司 Keyword group technology and device
CN108241628A (en) * 2016-12-23 2018-07-03 百度在线网络技术（北京）有限公司 Keywords matching range control method and device and showing advertisement method and apparatus
CN108268552A (en) * 2016-12-30 2018-07-10 北京国双科技有限公司 The processing method and processing device of site information
CN108537599A (en) * 2018-04-17 2018-09-14 北京三快在线科技有限公司 Query feedback method, apparatus and storage medium based on keyword polymerization
CN109561166A (en) * 2018-11-13 2019-04-02 阿里巴巴集团控股有限公司 Position the method, apparatus and electronic equipment of target object
CN110637316A (en) * 2016-12-22 2019-12-31 奥恩全球运营有限公司,新加坡分公司 System and method for intelligent prospective object recognition using online resources and neural network processing to classify tissue based on published material
US10769159B2 (en) 2016-12-22 2020-09-08 Aon Global Operations Plc, Singapore Branch Systems and methods for data mining of historic electronic communication exchanges to identify relationships, patterns, and correlations to deal outcomes
CN111915339A (en) * 2019-05-09 2020-11-10 阿里巴巴集团控股有限公司 Data processing method, device and equipment
US10951695B2 (en) 2019-02-14 2021-03-16 Aon Global Operations Se Singapore Branch System and methods for identification of peer entities
CN115730595A (en) * 2022-09-30 2023-03-03 上海寰通商务科技有限公司 Method, apparatus and medium for identifying pharmaceutical industry target object to be identified
CN117392826A (en) * 2023-12-11 2024-01-12 吉林大学 Network information early warning method and system based on big data

Cited By (35)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104933047A (en) * 2014-03-17 2015-09-23 北京奇虎科技有限公司 Method and device for determining value of search term
CN104933047B (en) * 2014-03-17 2020-02-04 北京奇虎科技有限公司 Method and device for determining value of search term
CN104951460B (en) * 2014-03-27 2019-02-05 阿里巴巴集团控股有限公司 Method and device is determined based on the ranking parameter value of keyword clustering
CN104951460A (en) * 2014-03-27 2015-09-30 阿里巴巴集团控股有限公司 Ranking parameter value determination method and device based on keyword clustering
CN103955480A (en) * 2014-04-02 2014-07-30 百度在线网络技术（北京）有限公司 Method and equipment for determining target object information corresponding to user
CN104462310A (en) * 2014-11-28 2015-03-25 北京国双科技有限公司 Detection method and device for correlation of webpage search keywords
CN104462310B (en) * 2014-11-28 2018-02-02 北京国双科技有限公司 The correlation detection methods and device of Webpage search keyword
CN104408191A (en) * 2014-12-15 2015-03-11 北京国双科技有限公司 Method and device for obtaining correlated keywords of keywords
CN104408191B (en) * 2014-12-15 2017-11-21 北京国双科技有限公司 The acquisition methods and device of the association keyword of keyword
CN106570019B (en) * 2015-10-10 2021-08-10 北京国双科技有限公司 Keyword configuration method and device
CN106570019A (en) * 2015-10-10 2017-04-19 北京国双科技有限公司 Key word configuration method and device
CN106909982A (en) * 2015-12-23 2017-06-30 北京奇虎科技有限公司 A kind of method and device for optimizing advertisement keyword match pattern
WO2017148355A1 (en) * 2016-03-02 2017-09-08 腾讯科技（深圳）有限公司 Campaign information pushing method and device
US11507975B2 (en) 2016-03-02 2022-11-22 Tencent Technology (Shenzhen) Company Limited Information processing method and apparatus
CN105808685A (en) * 2016-03-02 2016-07-27 腾讯科技（深圳）有限公司 Promotion information pushing method and device
US11157956B2 (en) 2016-09-13 2021-10-26 Tencent Technology (Shenzhen) Company Limited Application recommendation method and server
WO2018050022A1 (en) * 2016-09-13 2018-03-22 腾讯科技（深圳）有限公司 Application program recommendation method, and server
US10769159B2 (en) 2016-12-22 2020-09-08 Aon Global Operations Plc, Singapore Branch Systems and methods for data mining of historic electronic communication exchanges to identify relationships, patterns, and correlations to deal outcomes
US11455313B2 (en) 2016-12-22 2022-09-27 Aon Global Operations Se, Singapore Branch Systems and methods for intelligent prospect identification using online resources and neural network processing to classify organizations based on published materials
CN110637316A (en) * 2016-12-22 2019-12-31 奥恩全球运营有限公司,新加坡分公司 System and method for intelligent prospective object recognition using online resources and neural network processing to classify tissue based on published material
CN110637316B (en) * 2016-12-22 2021-04-13 奥恩全球运营有限公司,新加坡分公司 System and method for prospective object identification
CN108241628B (en) * 2016-12-23 2022-02-18 百度在线网络技术（北京）有限公司 Keyword matching range control method and device and advertisement display method and device
CN108241628A (en) * 2016-12-23 2018-07-03 百度在线网络技术（北京）有限公司 Keywords matching range control method and device and showing advertisement method and apparatus
CN108241629A (en) * 2016-12-23 2018-07-03 百度在线网络技术（北京）有限公司 Keyword group technology and device
CN108268552B (en) * 2016-12-30 2020-08-11 北京国双科技有限公司 Website information processing method and device
CN108268552A (en) * 2016-12-30 2018-07-10 北京国双科技有限公司 The processing method and processing device of site information
CN108537599B (en) * 2018-04-17 2023-11-07 北京三快在线科技有限公司 Query feedback method and device based on keyword aggregation and storage medium
CN108537599A (en) * 2018-04-17 2018-09-14 北京三快在线科技有限公司 Query feedback method, apparatus and storage medium based on keyword polymerization
CN109561166A (en) * 2018-11-13 2019-04-02 阿里巴巴集团控股有限公司 Position the method, apparatus and electronic equipment of target object
CN109561166B (en) * 2018-11-13 2021-10-12 创新先进技术有限公司 Method and device for positioning target object and electronic equipment
US10951695B2 (en) 2019-02-14 2021-03-16 Aon Global Operations Se Singapore Branch System and methods for identification of peer entities
CN111915339A (en) * 2019-05-09 2020-11-10 阿里巴巴集团控股有限公司 Data processing method, device and equipment
CN115730595A (en) * 2022-09-30 2023-03-03 上海寰通商务科技有限公司 Method, apparatus and medium for identifying pharmaceutical industry target object to be identified
CN117392826A (en) * 2023-12-11 2024-01-12 吉林大学 Network information early warning method and system based on big data
CN117392826B (en) * 2023-12-11 2024-02-13 吉林大学 Network information early warning method and system based on big data

Similar Documents

Publication Publication Date Title
CN103514191A (en) Method and device for determining keyword matching mode of target popularization information
US20240029464A1 (en) Method, apparatus, and computer program product for classification of documents
US11870864B2 (en) System and method for automatic storyline construction based on determined breaking news
US9324112B2 (en) Ranking authors in social media systems
US11514063B2 (en) Method and apparatus of recommending information based on fused relationship network, and device and medium
US11153253B2 (en) System and method for determining and delivering breaking news utilizing social media
US7711735B2 (en) User segment suggestion for online advertising
US20160132507A1 (en) Search Intent for Queries on Online Social Networks
US9946775B2 (en) System and methods thereof for detection of user demographic information
Abrol et al. Tweethood: Agglomerative clustering on fuzzy k-closest friends with variable depth for location mining
CN104899322A (en) Search engine and implementation method thereof
WO2018040069A1 (en) Information recommendation system and method
US20160125028A1 (en) Systems and methods for query rewriting
US20170249388A1 (en) Expert Detection in Social Networks
CN103246670A (en) Microblog sorting, searching, display method and system
CN105531701A (en) Personalized trending image search suggestion
CN103150663A (en) Method and device for placing network placement data
US10127322B2 (en) Efficient retrieval of fresh internet content
CN105378717A (en) Method for user categorization in social media, computer program, and computer
CN103886016A (en) Equipment and method for determining junk text messages in page
CN103020141A (en) Method and equipment for providing searching results
US20170235835A1 (en) Information identification and extraction
Wei et al. Online education recommendation model based on user behavior data analysis
CN106462588B (en) Content creation from extracted content
CN105117438A (en) Information processing method and electronic equipment

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C02 Deemed withdrawal of patent application after publication (patent law 2001)
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20140115