CN104503997B - Colleague's localization method, device and computer equipment - Google Patents
Colleague's localization method, device and computer equipment Download PDFInfo
- Publication number
- CN104503997B CN104503997B CN201410740960.1A CN201410740960A CN104503997B CN 104503997 B CN104503997 B CN 104503997B CN 201410740960 A CN201410740960 A CN 201410740960A CN 104503997 B CN104503997 B CN 104503997B
- Authority
- CN
- China
- Prior art keywords
- client
- correlation
- degree
- advertisement
- subgroup
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
- G06Q30/0244—Optimization
-
- 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
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0277—Online advertisement
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides one kind colleague localization method, device and computer equipment, method therein to include：Data are showed according to advertisement putting and determine multiple clients for occurring in same search result；Degree of correlation between client two-by-two is determined in the multiple client according to client's advertisement delivery effect information, and relative clients group is built according to the degree of correlation between the client two-by-two；Subgroup present in the relative clients group is determined based on data mining；Determine that the mark post in the subgroup is gone together according to ad placement service index.Technical scheme provided by the invention improves the reasonability and accuracy of colleague's positioning, and further, the present invention makes it possible to provide the information for more having reference value with behavior client based on mark post.
Description
Technical field
The present invention relates to Internet technical field, more particularly, to one kind colleague localization method, device and computer equipment.
Background technology
The main bodys such as personal or unit may have the demand of colleague's positioning during routine work, such as be produced to improve
Product or the competitiveness of service and need to carry out colleague's positioning.
Existing colleague's localization method mainly includes three kinds：First, colleague's positioning, such as client are carried out using three-level industry system
Three-level industry belonging to first is X, then other clients in X industries are positioned as the colleague of first；2nd, the key paid close attention to by client
Word carries out colleague's positioning, and the keyword as first and second are launched is essentially identical, then first can be positioned as to the colleague of second；3rd, it is based on
Multiple dimensions such as industry, keyword, region and consumption carry out colleague's positioning.
Inventor has found that carrying out colleague's positioning using three-level industry system is often present together in process of the present invention is realized
The problem of row orientation range is excessive；Although it is that business is similar to carry out colleague's positioning to exist using keyword, between the two
Not related problem, such as between the two and it is not present direct competitive relation；And carry out colleague's positioning very using multiple dimensions
It there may be by cross-region and across the client for consuming the type such as section is excluded in same line range the problem of.
The content of the invention
Present invention solves the technical problem that one of be improve colleague positioning reasonability and accuracy.
One embodiment according to an aspect of the present invention, there is provided one kind colleague's localization method, this method include：According to wide
Accuse to launch and show multiple clients that data determine to occur in same search result；Determined according to client's advertisement delivery effect information
Degree of correlation between client, and relative clients are built according to the degree of correlation between the client two-by-two two-by-two in the multiple client
Group；Subgroup present in the relative clients group is determined based on data mining；According to determining ad placement service index
Mark post colleague in subgroup.
One embodiment according to a further aspect of the invention, there is provided one kind colleague's positioner, the device include：It is determined that
Client Model, multiple clients for occurring in same search result are determined suitable for showing data according to advertisement putting；It is it is determined that related
Degree module, suitable for determining in the multiple client the degree of correlation between client two-by-two according to client's advertisement delivery effect information；
Customers and subgroup module are determined, suitable for building relative clients group according to the degree of correlation between the client two-by-two, and based on counting
Subgroup present in the relative clients group is determined according to excavation；Mark post colleague's module is determined, suitable for according to ad placement service
Index determines the mark post colleague in the subgroup.
One embodiment according to another aspect of the present invention, additionally provide a kind of computer equipment, including foregoing colleague
Positioner.
The present invention by according in the multiple clients occurred in same search result two-by-two the degree of correlation between client come structure
Relative clients group is built, and excavates subgroup present in relative clients group, while making the scope of positioning colleague will not be excessive, also
It can realize to search key, cross-region and the abundant measurement across multiple correlation factors such as consumption sections, make Primary Location
There is stronger correlation between each client in the range of the colleague gone out；Finally determined by using ad placement service index
Mark post colleague in subgroup, can be other clients in the range of the colleague oriented it is more targeted orient it is high-quality same
OK, the high-quality colleague oriented is easily of interest by client, so that the relevant information that client is referred to high-quality colleague changes
It is apt to advertisement serving policy of itself etc.；It follows that technical scheme provided by the invention improve colleague positioning reasonability with
And accuracy, and the information for more having reference value can be provided for client.
Those of ordinary skill in the art will be appreciated that although referenced in schematic embodiment and accompanying drawing are entered in following detailed description
OK, but the present invention is not limited in these embodiments.But the scope of the present invention is extensive, and it is intended to be bound only by appended
Claim limits the scope of the present invention.
Brief description of the drawings
By reading the detailed description made to non-limiting example made with reference to the following drawings, of the invention is other
Feature, objects and advantages will become more apparent upon：
Fig. 1 is the flow chart of colleague's localization method according to an embodiment of the invention；
Fig. 2 is colleague's positioning schematic diagram in accordance with another embodiment of the present invention；
Fig. 3 is the schematic diagram of the mark post colleague in accordance with another embodiment of the present invention oriented；
Fig. 4 is colleague's positioner schematic diagram according to further embodiment of the present invention.
Same or analogous reference represents same or analogous part in accompanying drawing.
Embodiment
The present invention is described in further detail below in conjunction with the accompanying drawings.
Fig. 1 and Fig. 2 is the flow chart of the localization method of going together of the embodiment of the present invention one and embodiment two respectively.Embodiment
One and embodiment two method mainly completed by the operating system in computer equipment or processing controller.It will can count
Calculate the operating system in machine equipment or processing controller is referred to as positioner of going together.The computer equipment is including but not limited to following
It is at least one：Single computer, the calculating unit of multiple stage computers composition, single network server, multiple webserver groups
Into server group and the cloud being made up of a large amount of computers or the webserver based on cloud computing；Wherein, cloud computing is point
One kind that cloth calculates, a super virtual computer being made up of the computer collection of a group loose couplings.
Embodiment one, colleague's localization method.
In Fig. 1, S100, show multiple clients that data determine to occur in same search result according to advertisement putting.
Specifically, the advertisement putting in the present embodiment, which shows data, refers to the advertisement putting that the lateral user of network shows
The information of concrete condition, for example, user inputs keyword in the search column of its search engine client, network side is receiving
After the keyword of user's input, corresponding search result information is built according to keyword, and search result information is pushed to
Search engine client, search result information is shown from search engine client to user, in this search procedure, advertisement is thrown
Put and show the search result information that data source is built in network side.Search knot in network side for this search structure of user
Fruit information content it is more, it is necessary to use multipage Pagination Display in the case of, the advertisement putting in the present embodiment shows data can be with
From the search result information for belonging to first page of network side structure, built as advertisement putting shows data source in network side
All advertising messages belonged in first page.
Advertisement putting in the present embodiment, which shows data, to show daily record including advertisement putting.The present embodiment can be by one
Advertisement putting in section time range (such as one month either a season or half a year even 1 year) shows daily record as same
The basic data of row positioning.
S110, the degree of correlation between client two-by-two determined in above-mentioned multiple clients according to client's advertisement delivery effect information.
Specifically, the advertisement delivery effect information in the present embodiment can be sequence position of the client in same ad queue
Put, or ad click rate, can also include client sorting position and advertisement point in same ad queue simultaneously
Hit rate.Certainly, advertisement delivery effect information can also be the other information that can reflect advertisement delivery effect.
The correlation determined according to client's advertisement delivery effect information in above-mentioned multiple clients between client two-by-two of the present embodiment
One specific example of degree is：For in the search result first page of same search keyword simultaneously occur client's first and
For client's second, determined according to sorting position of sorting position and client second of client's first in ad queue in ad queue
Single degree of correlation between client's first and client's second, multiple lists between client's first and client's second are obtained in method as utilization
Secondary degree of correlation (such as obtain single degree of correlation between all the client's first and client's second in some month or in some season or
The single degree of correlation that person obtains has reached pre-determined number) after, all single degrees of correlation based on acquisition calculate client
Degree of correlation between first and client's second, such as can be using the aggregate-value of all single degrees of correlation as between client's first and client's second
Degree of correlation etc..
The correlation determined according to client's advertisement delivery effect information in above-mentioned multiple clients between client two-by-two of the present embodiment
Another specific example of degree is：For the client's first occurred in the search result first page of same search keyword simultaneously
For client's second, determined according to the ad click rate of the ad click rate of client's first and client's second between client's first and client's second
Single degree of correlation, obtain multiple single degrees of correlation between client's first and client's second in method as utilization and (such as obtain
All client's first in some month either in some season are related to the single degree of correlation between client's second or the single of acquisition
Degree has reached pre-determined number) after, all single degrees of correlation based on acquisition calculate the phase between client's first and client's second
Pass degree, such as can be using the aggregate-value of all single degrees of correlation as the degree of correlation between client's first and client's second.
The correlation determined according to client's advertisement delivery effect information in above-mentioned multiple clients between client two-by-two of the present embodiment
Another specific example of degree is：For the client's first occurred in the search result first page of same search keyword simultaneously
For client's second, according to sorting position and client second sorting position in ad queue of client's first in ad queue with
And the ad click rate of client's first and the ad click rate of client's second determine the single degree of correlation between client's first and client's second,
Using such method obtain between client's first and client's second multiple single degrees of correlation (such as obtain in some moon or some
The single degree of correlation of single degree of correlation between all client's first and client's second or acquisition in season has reached predetermined time
Number) after, all single degrees of correlation based on acquisition calculate the degree of correlation between client's first and client's second, as can be by institute
There is the aggregate-value of single degree of correlation as degree of correlation between client's first and client's second etc..
S120, according to the degree of correlation structure relative clients group between client two-by-two, and correlation is determined based on data mining
Subgroup present in customers.
Specifically, the relative clients group of the present embodiment structure can be embodied in the form of relative clients network, certainly,
The customers of the present embodiment structure can also be embodied using other forms such as array or chained lists.The present embodiment does not limit correlation
The specific manifestation form of customers.
Mined massively in relative clients with the form of relative clients network come in the case of embodying, one in relative clients network
Network node represents a client, i.e. a client is a network node in relative clients network；If relative clients net
Line be present between two nodes in network, then it represents that there is correlation between the representative client of the two nodes difference, and
Numeral corresponding to line between two nodes can be the related journey between the two nodes calculated using above-mentioned steps
Degree；If line is not present between two nodes in relative clients network, then it represents that the representative visitor of the two nodes difference
Do not have correlation between family.
In the relative clients group of the present embodiment, correlation between a part of client may by force, but this
Correlation between portions of client and other clients can be weaker；So, may be showed in relative clients group exist it is multiple
Client subgroup (is referred to as multiple custom partitionings being present), has higher phase in subgroup (i.e. in group) between client
Guan Xing, that is, there is higher condensation degree, and there is relatively low correlation between the client of subgroup (i.e. across group), i.e., with relatively low
Condensation degree.The present embodiment can find subgroup present in relative clients group using existing data mining technology.
The present embodiment determines that a specific example of subgroup present in relative clients group is based on data mining：
Relative clients are mined massively with the form of relative clients network come in the case of embodying, subgroup is society present in relative clients network
Group；The present embodiment can excavate corporations present in relative clients network according to existing community discovery algorithm；Afterwards, in order to protect
The reliability of the corporations of foregoing discovery is demonstrate,proved, the condensation degree of community structure can be detected, if detecting community structure
Condensation degree does not meet predetermined coherence condition, then can dismiss such corporations, if detecting the condensation degree symbol of community structure
Predetermined coherence condition is closed, then can retain such corporations.The condensation degree of community structure in this specific example can be based on
The degree of correlation between client inside corporations is calculated using corresponding algorithm to be obtained.This specific example does not limit community discovery calculation
Whether the specific implementation process of method and the condensation degree of detection community structure meet the specific implementation of predetermined coherence condition.
The present embodiment determines that another specific example of subgroup present in relative clients group is based on data mining：
Mined massively in relative clients with the form of relative clients network come in the case of embodying, subgroup is present in relative clients network
Corporations；The present embodiment can excavate corporations present in relative clients network according to existing community discovery algorithm；Afterwards, in order to
Ensure that the scale of the corporations of foregoing discovery should not be excessive, the customer quantity that can be included to corporations detects, if the society
The customer quantity that group includes is not above intended client threshold value, then can retain the corporations, if client's number that the corporations include
Amount exceedes intended client threshold value, then can be using the corporations as currently associated customer network, and again according to community discovery algorithm
Corporations present in current relative clients network are excavated, afterwards, the above-mentioned customer quantity included to corporations is returned to and carries out
The step of detection.It can thus be seen that in this specific example, an iterative process be present, can by using the iterative process
So that each corporations finally remained include the client of fair amount.This specific example does not limit community discovery algorithm
Specific implementation process.
The present embodiment determines that another specific example of subgroup present in relative clients group is based on data mining：
Mined massively in relative clients with the form of relative clients network come in the case of embodying, subgroup is present in relative clients network
Corporations；The present embodiment can excavate corporations present in relative clients network according to existing community discovery algorithm；Afterwards, in order to
Ensure the reliability of the corporations of foregoing discovery, the condensation degree of community structure can be detected, if detecting community structure
Condensation degree do not meet predetermined coherence condition, then can dismiss the corporations, if detect certain community structure condensation degree symbol
Predetermined coherence condition is closed, then further the customer quantity included in the corporations can be detected, if the institute of corporations
Comprising customer quantity be not above intended client threshold value, then can retain the corporations, if client's number that the corporations are included
Amount exceedes intended client threshold value, then can be using the corporations as currently associated customer network, and is sent out again according to existing corporations
Existing algorithm excavates corporations present in currently associated customer network, afterwards, returns to the above-mentioned condensation degree to community structure and carries out
The step of detection.It will thus be seen that in this specific example, an iterative process be present, can be with by using the iterative process
The corporations for making finally to remain are respectively provided with higher condensation degree and include the client of fair amount.Society in this specific example
The condensation degree of unity structure can be calculated using corresponding algorithm based on the degree of correlation between the client inside corporations and obtained.This tool
Style does not limit the specific implementation process of community discovery algorithm and whether detection community structure condensation degree meets predetermined coagulate
The specific implementation of poly- condition.
The present embodiment can perform above-mentioned community structure condensation degree only for the corporations where some specific client and detect
And the operation of corporations' internal customer's quantity control, all corporations that the present embodiment can also be directed in relative clients network perform
Above-mentioned community structure condensation degree detection and the operation of corporations' internal customer's quantity control.
S130, according to ad placement service index determine that mark post in subgroup is gone together.
Specifically, the ad placement service index in the present embodiment can include：Advertisement putting consumption Input factors, advertisement
At least one of quality factor, the advertising conversion factor and Website quality factor.
The present embodiment, can be it is determined that son in order that the mark post colleague the purpose of more meeting the concern direction of client oriented
During mark post colleague in group, further consider that advertisement putting client pays close attention to information, specifically, different advertisement puttings
The concern direction of client may be different, during the positioning mark pole colleague from subgroup, can be directed to different advertisements
Mark post colleague in this direction is oriented respectively in the concern direction of dispensing client；That is, the present embodiment can be first according to wide
Accuse launch client pay close attention to information picked out from subgroup meets advertisement putting client pay close attention to direction client, then, then from these
Mark post colleague is oriented according to ad placement service index in the client picked out, so as to which the mark post colleague oriented can more accord with
Close the concern direction of advertisement putting client.Advertisement putting client in the present embodiment, which pays close attention to information, can include advertisement putting field
It scape, can also include being concerned customer type, advertisement putting scene can also be included simultaneously and be concerned customer type.Advertisement is thrown
It is typically to wish to know that the information of certain type customer is configured for client to put client's concern information.
Advertisement putting scene in the present embodiment can include：Search is promoted scene, wireless popularization scene and net alliance and pushed away
Square scape etc.；Being concerned customer type and can include in the present embodiment：Equal scale of operation client and industry-leading client
Deng.Advertisement putting scene in the present embodiment can change therewith with the change for promoting scene future, similarly, be closed
Note customer type can also change therewith with the change of advertisement putting client's focus.
The present embodiment is thrown during being gone together according to ad placement service index come positioning mark pole for different advertisements
Putting ad placement service index used in scene can differ；For example, for scene is promoted in search, advertisement putting industry
Business index can select advertisement putting consumption Input factors (consumption is promoted in such as search or consumption accounting is promoted in search), advertisement
Quality factor (such as ad click rate) and the advertising conversion factor (such as business's bridge consulting amount and/or offline precious phone amount)；
For another example for wirelessly promoting scene, ad placement service index can select advertisement putting to consume Input factors (such as nothing
Line promotes consumption or wireless promotes consumption accounting etc.), the ad quality factor (such as ad click rate) and Website quality because
Sub (rate and/or website average access duration etc. are jumped out in ad click turnover rate and/or website)；For another example for net alliance
Promote scene for, ad placement service index can select advertisement putting consumption Input factors (as net alliance promote consumption or
Net alliance and promote consumption accounting etc.) and the ad quality factor (such as ad click rate).The present embodiment is according to advertisement putting industry
Business index is come during positioning mark pole is gone together it is also contemplated that the content such as the sorting position of client in each ad queue, example
Such as, after by the way that ad placement service index and sorting position etc. are normalized, using the modes such as weighted scoring come
Determine that mark post is gone together.The present embodiment does not limit the specific implementation process for determining mark post colleague.
The present embodiment can perform the operation of above-mentioned determination mark post colleague only for the corporations where some specific client；
All corporations that the present embodiment can also be directed in relative clients network perform the operation of above-mentioned determination mark post colleague.
Further it is provided with addition, the present embodiment after mark post colleague is determined, can be based on mark post colleague for client
The reference information of value, the reference information that can improve its investment in advertising strategy can be such as provided for client.The present embodiment does not limit
The particular content of the reference information provided for client.
Embodiment two, colleague's localization method.
The present embodiment by advertisement putting is showed big data (such as advertisement putting shows daily record) analyzed it is competing to build
Network (i.e. above-mentioned relative clients network) is striven, then, the competition son group (i.e. corporations) residing for location client, afterwards, can be based on
Different advertisement putting scenes and the client being concerned during customer type is rolled into a ball to competition carry out the further differentiation that becomes more meticulous,
A small amount of mark post colleague (i.e. mark post client) that client most pays close attention to may finally be excavated；Further, the mark post oriented is synchronous
Can be the information that other clients bring reference value, it is such as same by the advertisement promotion scheme and mark post of analyzing client itself
Capable advertisement promotion scheme, it can be found that the problem of advertisement promotion scheme of client itself is present and weak point, so as to
To realize the further perfect of the advertisement promotion scheme of client.
In Fig. 2, first, the recent showing advertisement data (advertisement in such as one month is obtained from phoenix nest showing advertisement daily record
Show data), and build competition network according to the recent showing advertisement data of acquisition.Specifically, when the advertisement of two clients
When promotion message shows in same search result and (showed on the same stage), represent the two clients there occurs once competition (i.e. this
Two client's correlations), the present embodiment can be based on position of the two clients in ad queue and ad click rate synthesis meter
Calculate this competition intensity (i.e. above-mentioned single degree of correlation), in accumulative one month the two clients show on the same stage every time this
Competition intensity, so as to obtain the competition intensity of the two clients.
When two clients occur showing phenomenon on the same stage, it may be said that bright two clients have purchased substantially similar keyword,
So as to trigger the advertisement that the two clients are launched when being scanned for by a certain keyword；Furthermore it is also possible to further illustrate
Two clients have launched advertisement in identical region, so as to triggered by a certain keyword when same region scans for this two
The advertisement that individual client is launched；Further, can also further illustrate, the advertisement that two clients launch has the identical period,
So as to when sometime scanning for while trigger the advertisement that the two clients are launched by a certain keyword.
The present embodiment measures the competition intensity between client by using showing on the same stage, is big in position fixing process of going together
The degree of accuracy that width improves colleague's positioning provides guarantee.
Afterwards, community discovery operation is carried out for competition network.Specifically, community discovery algorithm can be used (such as
Louvain community discoveries algorithm) corporations present in competition network are excavated, and can be (corresponding above-mentioned solidifying by modularity Q indexs
Poly- degree) etc. parameter the corporations excavated are assessed, to decide whether to dismiss corporations, at the same time it can also according to corporations Zhong Bao
The customer quantity contained decides whether to carry out further corporations' excavation to corporations.It is mutually between client in same corporations
Opponent firm, the client in same corporations can form opponent firm's list.
Finally, mark post colleague is found out from opponent firm.Specifically, the advertisement putting scene letter of opponent firm can be obtained
Breath, for example, obtaining the advertisement putting scene information of opponent firm from phoenix nest database and net alliance database；Afterwards, according to
Advertisement putting scene information judges that opponent firm is to belong to search to promote, and still falls within wireless popularization, and also or belonging to net alliance pushes away
Extensively, that is, judge whether opponent firm has search promotional features, wireless promotional features and/or network promotion feature；For above-mentioned
The opponent firm of acquisition is based on advertising business and launches scene information and advertisement putting client focus (i.e. advertisement putting client pass
Note information) further become more meticulous differentiation to opponent firm, and selects respectively from all kinds of opponent firms after differentiation a small amount of
Top-tier customer (such as 5) is gone together as mark post；So as to which the present embodiment can obtain the mark post colleague of 6 types as shown in Figure 3,
The optimal mark post of same scale for the optimal mark post colleague of the same trade under scene is promoted based on search, promoting under scene based on search is same
Go, gone together, based on the optimal mark post of same scale under wireless popularization scene based on the wireless optimal mark post of the same trade promoted under scene
Colleague, promote based on net alliance optimal mark post colleague of the same trade under scene and optimal based on the same scale under net alliance popularization scene
Mark post is gone together.The mark post colleague for six types that the present embodiment is finally determined is the mark post of other clients in corporations where it
Colleague, information can be paid close attention to according to the advertisement putting client of other clients and determines that the mark post of its corresponding types is gone together, passes through and compares
The advertisement promotion scheme of the corresponding mark post colleague of other clients, the advertisement promotion scheme that can find out other clients are deposited
Weak point, be advantageous to improve the advertisement promotion scheme of other clients, such as can be the advertisement that other clients generate optimization
Marketing program etc..
Embodiment three, colleague's positioner.The structure of the device is as shown in Figure 4.
In Fig. 4, colleague's positioner mainly includes：Client Model 400 is determined, degree of correlation module 410 is determined, determines visitor
Family group and subgroup module 420 and determination mark post colleague's module 430.
Determine that Client Model 400 is primarily adapted for showing what data determination occurred in same search result according to advertisement putting
Multiple clients.
Specifically, determine that advertisement putting used in Client Model 400 shows data and refers to that the lateral user of network shows
Advertisement putting concrete condition information, for example, user inputs keyword, net in the search column of its search engine client
Network side builds corresponding search result information after the keyword of user's input is received, according to keyword, and search is tied
Fruit information is pushed to search engine client, and search result information is shown from search engine client to user, in this search
During, advertisement putting shows the search result information that data source is built in network side.Searched in network side for this of user
Rope structure search result information quantity it is more, it is necessary to use multipage Pagination Display in the case of, determine that Client Model 400 is made
Advertisement putting shows the search result information for belonging to first page that data can derive from network side structure, such as determines client
Advertisement putting used in module 400 shows all advertising messages belonged in first page that data source is built in network side.
Determine that advertisement putting used in Client Model 400 shows data and can show daily record including advertisement putting.It is determined that
Client Model 400 can be by the advertisement in a period of time scope (such as one month either a season or half a year even 1 year)
Launch the basic data for showing daily record as colleague's positioning.
Determine that degree of correlation module 410 is primarily adapted for determining in multiple clients two-by-two according to client's advertisement delivery effect information
Degree of correlation between client.
Specifically, determine that advertisement delivery effect information used in degree of correlation module 410 can be client same wide
Accuse the sorting position in queue, or ad click rate, can also include client the row in same ad queue simultaneously
Tagmeme is put and ad click rate.It is of course possible to degree of correlation can also be determined by reflecting the other information of advertisement delivery effect
Module 410 uses as advertisement delivery effect information.
Determine that degree of correlation module 410 determines in above-mentioned multiple clients client two-by-two according to client's advertisement delivery effect information
Between a specific example of degree of correlation be：For what is occurred in the search result first page of same search keyword simultaneously
For client's first and client's second, determine degree of correlation module 410 according to sorting position of client's first in ad queue and client
Sorting position of the second in ad queue determines the single degree of correlation between client's first and client's second, is obtained in method as utilization
The multiple single degrees of correlation obtained between client's first and client's second (such as obtain all clients in some month or in some season
The single degree of correlation of single degree of correlation or acquisition between first and client's second has reached pre-determined number) after, it is determined that related
All single degrees of correlation of the degree module 410 based on acquisition calculate the degree of correlation between client's first and client's second, such as determine
Degree of correlation module 410 can be using the aggregate-value of all single degrees of correlation as the degree of correlation between client's first and client's second
Deng.
Determine that degree of correlation module 410 determines in above-mentioned multiple clients client two-by-two according to client's advertisement delivery effect information
Between another specific example of degree of correlation be：For occurring in the search result first page of same search keyword simultaneously
Client's first and client's second for, determine degree of correlation module 410 according to the ad click rate of client's first and the advertisement of client's second
Clicking rate determines the single degree of correlation between client's first and client's second, and client's first and client's second are obtained in method as utilization
Between multiple single degrees of correlation (such as obtain the single between all the client's first and client's second in some month or in some season
Degree of correlation or the single degree of correlation of acquisition have reached pre-determined number) after, determine that degree of correlation module 410 is based on obtaining
All single degrees of correlation calculate degree of correlation between client's first and client's second, such as determine that degree of correlation module 410 can be with
Using the aggregate-value of all single degrees of correlation as degree of correlation between client's first and client's second etc..
Determine that degree of correlation module 410 determines in above-mentioned multiple clients client two-by-two according to client's advertisement delivery effect information
Between another specific example of degree of correlation be：For occurring in the search result first page of same search keyword simultaneously
Client's first and client's second for, determine degree of correlation module 410 according to sorting position of client's first in ad queue and visitor
The ad click rate of sorting position and client first and the ad click rate of client second of the family second in ad queue determine client
Single degree of correlation between first and client's second, multiple single phases between client's first and client's second are obtained in method as utilization
Pass degree (such as obtains in some month the single degree of correlation between all client's first and client's second in either some season or obtained
The single degree of correlation obtained has reached pre-determined number) after, determine that all singles of the degree of correlation module 410 based on acquisition are related
Degree calculates the degree of correlation between client's first and client's second, such as determines that degree of correlation module 410 can be related by all singles
The aggregate-value of degree is as degree of correlation between client's first and client's second etc..
Determine that customers and subgroup module 420 are primarily adapted for according to the degree of correlation structure relative clients between client two-by-two
Group, and subgroup present in relative clients group is determined based on data mining.
Specifically, relative clients network can be used by determining the relative clients group of customers and the structure of subgroup module 420
Form embodies, certainly, determine customers and customers that subgroup module 420 is built can also use array or chained list etc. its
His form embodies.The present embodiment does not limit the specific manifestation for the relative clients group for determining customers and the structure of subgroup module 420
Form.
It is determined that customers and subgroup module 420 embody the situation of relative clients group in the form of relative clients network
Under, a network node in relative clients network represents a client, i.e. a client is one in relative clients network
Network node；If line be present between two nodes in relative clients network, then it represents that representated by the two nodes difference
Client between there is correlation, and numeral corresponding to the line between two nodes can be to be calculated using above-mentioned steps
The two nodes between degree of correlation；If line is not present between two nodes in relative clients network, then it represents that this
Do not have correlation between the representative client of two nodes difference.
Determine that the correlation between a part of client in customers and relative clients group constructed by subgroup module 420 can
Energy can be strong, but the correlation between this portions of client and other clients can be weaker；So, can in relative clients group
It can show and multiple client subgroups (being referred to as multiple custom partitionings being present) be present, it is objective (i.e. in group) in subgroup
There is higher correlation between family, that is, there is higher condensation degree, and have between the client of subgroup (i.e. across group) relatively low
Correlation, i.e., with relatively low condensation degree.Determine that customers and subgroup module 420 can utilize existing data mining technology
To find subgroup present in relative clients group.
Determine that customers and subgroup module 420 determine one of subgroup present in relative clients group based on data mining
Specific example is：It is determined that customers and subgroup module 420 embody relative clients group in the form of relative clients network
In the case of, subgroup is corporations present in relative clients network；Determine that customers and subgroup module 420 can be according to existing
Community discovery algorithm excavate relative clients network present in corporations；Afterwards, in order to ensure the reliable of the corporations of foregoing discovery
Property, determine that customers and subgroup module 420 can detect to the condensation degree of community structure, if detecting community structure
Condensation degree does not meet predetermined coherence condition, it is determined that customers and subgroup module 420 can dismiss such corporations, if inspection
The condensation degree for measuring community structure meets predetermined coherence condition, it is determined that customers and subgroup module 420 can retain so
Corporations.The condensation degree of community structure in this specific example can be utilized based on the degree of correlation between the client inside corporations
Corresponding algorithm, which calculates, to be obtained.Community discovery is calculated used by this specific example does not limit determination customers and subgroup module 420
It is predetermined whether the condensation degree of the specific implementation process of method and determination customers and the detection community structure of subgroup module 420 meets
The specific implementation of coherence condition.
Determine that customers and subgroup module 420 determine the another of subgroup present in relative clients group based on data mining
Individual specific example is：It is determined that customers and subgroup module 420 embody relative clients in the form of relative clients network
In the case of group, subgroup is corporations present in relative clients network；Determine that customers and subgroup module 420 can be according to existing
Some community discovery algorithms excavate corporations present in relative clients network；Afterwards, in order to ensure to determine customers and subgroup mould
The scale for the corporations that block 420 is currently found should not be excessive, determines customers and the visitor that subgroup module 420 can be included to corporations
Amount amount is detected, if the customer quantity that the corporations include is not above intended client threshold value, it is determined that customers and son
Group's module 420 can retain the corporations, if the customer quantity that the corporations include exceedes intended client threshold value, it is determined that customers
And subgroup module 420 can be using the corporations as currently associated customer network, and excavated currently again according to community discovery algorithm
Relative clients network present in corporations, afterwards, return to above-mentioned determination customers and subgroup module 420 included to corporations
Customer quantity the step of being detected.It can thus be seen that it is determined that the above-mentioned implementation procedure of customers and subgroup module 420
In, an iterative process be present, determine that customers and subgroup module 420 by using the iterative process, can make finally to retain
The each corporations got off include the client of fair amount.This specific example, which does not limit, determines customers and the institute of subgroup module 420
The specific implementation process of the community discovery algorithm of use.
Determine that customers and subgroup module 420 determine the another of subgroup present in relative clients group based on data mining
Individual specific example is：It is determined that customers and subgroup module 420 embody relative clients in the form of relative clients network
In the case of group, subgroup is corporations present in relative clients network；Determine that customers and subgroup module 420 can be according to existing
Some community discovery algorithms excavate corporations present in relative clients network；Afterwards, can in order to ensure the corporations of foregoing discovery
By property, determine that customers and subgroup module 420 can detect to the condensation degree of community structure, if detecting community structure
Condensation degree do not meet predetermined coherence condition, it is determined that customers and subgroup module 420 can dismiss the corporations, if detection
The condensation degree for going out certain community structure meets predetermined coherence condition, it is determined that customers and subgroup module 420 can be further right
Customer quantity included in the corporations is detected, if the customer quantity that the corporations are included is not above intended client threshold
Value, it is determined that customers and subgroup module 420 can retain the corporations, make a reservation for if the customer quantity that the corporations are included exceedes
Client's threshold value, it is determined that customers and subgroup module 420 can using the corporations as currently associated customer network, and again according to
Existing community discovery algorithm excavates corporations present in currently associated customer network, afterwards, determines customers and subgroup module
The step of 420 condensation degrees for returning to above-mentioned all clients to inside corporations detect.It will thus be seen that it is determined that client
Group and subgroup module 420 implementation procedure in, an iterative process be present, determine customers and subgroup module 420 by using
The iterative process, the corporations that can make finally to remain are respectively provided with higher condensation degree and include the client of fair amount.
The condensation degree of community structure in this specific example can be based on the degree of correlation between the client inside corporations using accordingly
Algorithm, which calculates, to be obtained.This specific example does not limit the tool for determining community discovery algorithm used by customers and subgroup module 420
Whether the condensation degree that body implementation process and determination customers and subgroup module 420 detect community structure meets predetermined cohesion bar
The specific implementation of part.
Determine that customers and subgroup module 420 can perform above-mentioned corporations only for the corporations where some specific client
The operation of condensation degree detection and the corporations' internal customer's quantity control of structure, determines that customers and subgroup module 420 can also
Condensation degree detection and the corporations' internal customer's quantity of above-mentioned community structure are performed for all corporations in relative clients network
The operation of control.
Determine that mark post colleague's module 430 is primarily adapted for determining that the mark post in subgroup is gone together according to ad placement service index.
Specifically, ad placement service index can specifically include used by determining mark post colleague's module 430：Advertisement is thrown
Put at least one of consumption Input factors, the ad quality factor, the advertising conversion factor and Website quality factor.
Mark post colleague's module 430 is determined in order that the mark post colleague the purpose of more meeting the concern direction of client oriented,
It can further consider that advertisement putting client pays close attention to information, specifically, no during it is determined that the mark post in subgroup is gone together
The concern direction of same advertisement putting client may be different, it is determined that mark post colleague's module 430 positions mark from subgroup
During bar is gone together, determine that mark post colleague module 430 can position respectively for the concern direction of different advertisement putting clients
The mark post colleague (one or more) gone out in this direction；That is, determine that mark post colleague's module 430 can be first according to advertisement
Launch client and pay close attention to information and picked out from subgroup and meet the client that advertisement putting client pays close attention to direction, then, it is determined that mark post is same
Row module 430 orients mark post colleague from the client that these are picked out according to ad placement service index again, so that it is determined that mark
The mark post colleague that bar colleague's module 430 is oriented can more meet the concern direction of advertisement putting client.Determine mark post colleague's mould
Advertisement putting client, which pays close attention to information, used by block 430 can include advertisement putting scene, can also include being concerned customer class
Type, advertisement putting scene can also be included simultaneously and be concerned customer type.Determine mark post colleague module 430 used by advertisement
It is typically to wish to know that the information of certain type customer is configured for client to launch client and pay close attention to information.
Advertisement putting scene can include used by determining mark post colleague's module 430：Scene, wireless popularization are promoted in search
Scene and net alliance promote scene etc.；Determine that being concerned customer type used by mark post colleague's module 430 can include：On an equal basis
Scale of operation client and industry-leading client etc..Advertisement putting scene can be with used by determining mark post colleague's module 430
And promote the change of scene in the future and change therewith, similarly, determine to be concerned client used by mark post colleague's module 430
Type can also change therewith with the change of advertisement putting client's focus.
Mark post colleague's module 430 is determined during being gone together according to ad placement service index come positioning mark pole, for
Different advertisement putting scenes determines that ad placement service index used in mark post colleague's module 430 can differ；For example,
For scene is promoted in search, determine that mark post colleague's module 430 can select advertisement putting consumption Input factors (as search pushes away
Consumption accounting etc. is promoted in wide consumption or search), the ad quality factor (such as ad click rate) and the advertising conversion factor (such as
Business's bridge consulting amount and/or offline precious phone amount etc.) it is used as ad placement service index；For another example promote scene for wireless
For, determine that mark post colleague's module 430 can select advertisement putting consumption Input factors (as wirelessly promoted consumption or wirelessly pushing away
Wide consumption accounting etc.), the ad quality factor (such as ad click rate) and the Website quality factor (ad click turnover rate and/
Or rate and/or website average access duration etc. are jumped out in website) it is used as ad placement service index；For another example for net alliance
Promote scene for, determine mark post colleague module 430 can select advertisement putting consumption Input factors (as net alliance promote consumption or
Zhe Wang alliances promote consumption accounting etc.) and the ad quality factor (such as ad click rate) be used as ad placement service index.Really
Bar colleague's module 430 is calibrated during being gone together according to ad placement service index come positioning mark pole it is also contemplated that client exists
The contents such as the sorting position in each ad queue, for example, determine mark post colleague module 430 by ad placement service index with
And after sorting position etc. is normalized, determine that mark post is gone together using modes such as weighted scorings.The present embodiment does not limit
Determine that mark post colleague's module 430 determines the specific implementation process of mark post colleague.
Determine that mark post colleague module 430 can perform above-mentioned determination mark post only for the corporations where some specific client
The operation of colleague；All corporations that determining mark post colleague module 430 can also be directed in relative clients network perform above-mentioned determination
The operation of mark post colleague.
In addition, determining mark post colleague's module 430 after mark post colleague is determined, can be based on mark post colleague is further
Client provides valuable reference information, and its investment in advertising can be improved by such as determining that mark post colleague's module 430 can provide for client
The reference information of strategy.The present embodiment, which does not limit, determines that mark post colleague's module 430 is the specific interior of the reference information that client provides
Hold.
Example IV, computer equipment.
The computer equipment can be single computer, multiple stage computers form calculating unit, single network server,
The server group of multiple webserver compositions or the cloud being made up of a large amount of computer/webservers based on cloud computing.
The computer equipment of the present embodiment includes colleague's positioner described in above-described embodiment three, no longer describes in detail herein.
It should be noted that the present invention can be carried out in the assembly of software and/or software and hardware, for example, can adopt
With application specific integrated circuit (ASIC), general purpose computer or any other realized similar to hardware device.In one embodiment
In, software program of the invention can realize steps described above or function by computing device.Similarly, it is of the invention
Software program (including related data structure) can be stored in computer readable recording medium storing program for performing, for example, RAM memory,
Magnetically or optically driver or floppy disc and similar devices.In addition, some steps or function of the present invention can employ hardware to realize, example
Such as, coordinate as with processor so as to perform the circuit of each step or function.
In addition, the part of the present invention can be applied to computer program product, such as computer program instructions, when its quilt
When computer performs, by the operation of the computer, the method according to the invention and/or technical scheme can be called or provided.
And the programmed instruction of the method for the present invention is called, it is possibly stored in fixed or moveable recording medium, and/or pass through
Broadcast or the data flow in other signal bearing medias and be transmitted, and/or be stored according to described program instruction operation
In the working storage of computer equipment.Here, including a device according to one embodiment of present invention, the device includes using
Memory in storage computer program instructions and processor for execute program instructions, wherein, when the computer program refers to
When order is by the computing device, method and/or skill of the plant running based on foregoing multiple embodiments according to the present invention are triggered
Art scheme.
It is obvious to a person skilled in the art that the invention is not restricted to the details of above-mentioned one exemplary embodiment, Er Qie
In the case of without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, embodiment all should be regarded as exemplary, and be nonrestrictive, the scope of the present invention is by appended power
Profit requires rather than described above limits, it is intended that all in the implication and scope of the equivalency of claim by falling
Change is included in the present invention.Any reference in claim should not be considered as to the involved claim of limitation.This
Outside, it is clear that the word of " comprising " one is not excluded for other units or step, and odd number is not excluded for plural number.That is stated in system claims is multiple
Unit or device can also be realized by a unit or device by software or hardware.The first, the second grade word is used for table
Show title, and be not offered as any specific order.
Claims (19)
1. one kind colleague's localization method, including：
Data are showed according to advertisement putting and determine multiple clients for occurring in same search result；
Degree of correlation between client two-by-two is determined in the multiple client according to client's advertisement delivery effect information；
Relative clients group is built according to the degree of correlation between the client two-by-two, and the related visitor is determined based on data mining
Subgroup present in the group of family；
Determine that the mark post in the subgroup is gone together according to ad placement service index.
2. the method according to claim 11, wherein, it is described that data determination is showed in same search result according to advertisement putting
Multiple clients of middle appearance include：
Data are showed according to advertisement putting and determine all clients for occurring in the first page of same search result.
3. according to the method for claim 1, wherein, the advertisement delivery effect information includes：Client is in same advertisement team
Sorting position and/or ad click rate in row.
4. the method according to claim 11, wherein, it is described that the multiple visitor is determined according to client's advertisement delivery effect information
Degree of correlation in family two-by-two between client includes：
For search result each time, client two-by-two is determined in the multiple client all in accordance with the advertisement delivery effect information of client
Between single degree of correlation；
Determined according to multiple single degrees of correlation in the range of the scheduled time or according to the single degree of correlation of predetermined quantity
Degree of correlation between client two-by-two in the multiple client.
5. according to the method for claim 1, wherein, the relative clients group is relative clients network；It is and described based on number
Determine that subgroup present in the relative clients group includes according to excavation：
Corporations present in the relative clients network are excavated according to community discovery algorithm；
The condensation degree of the corporations is detected, and dismisses the corporations that condensation degree does not meet predetermined coherence condition.
6. the method according to claim 11, wherein, it is described to determine exist in the relative clients group based on data mining
Subgroup also include：
Exceed the corporations of intended client threshold value for customer quantity, corporations present in group are excavated according to community discovery algorithm.
7. the method according to any claim in claim 1 to 6, wherein described true according to ad placement service index
Mark post colleague in the fixed subgroup includes：
Gone together according to the mark post that ad placement service index determines to meet advertisement putting client concern information in the subgroup；Its
In, the advertisement putting client, which pays close attention to information, to be included：Advertisement putting scene and/or it is concerned customer type.
8. the method according to claim 11, wherein：The advertisement putting scene includes：Scene, wireless popularization are promoted in search
Scene and net alliance promote scene；And/or the customer type that is concerned includes：Equal scale of operation client and industry neck
First client.
9. the method according to claim 11, wherein：
Scene is promoted for search, the ad placement service index includes：Advertisement putting consumption Input factors, ad quality because
Son and the advertising conversion factor；
Scene is promoted for wireless, the ad placement service index includes：Advertisement putting consumption Input factors, ad quality because
Son and the Website quality factor；
For net, alliance promotes scene, and the ad placement service index includes：Input factors and advertisement matter are consumed in advertisement putting
Measure the factor.
10. one kind colleague's positioner, including：
Client Model is determined, multiple clients for occurring in same search result are determined suitable for showing data according to advertisement putting；
Degree of correlation module is determined, suitable for being determined according to client's advertisement delivery effect information in the multiple client between client two-by-two
Degree of correlation；
Customers and subgroup module are determined, suitable for according to the degree of correlation structure relative clients group between the client two-by-two, and base
Subgroup present in the relative clients group is determined in data mining；
Mark post colleague's module is determined, suitable for determining that the mark post in the subgroup is gone together according to ad placement service index.
11. device according to claim 10, wherein, the determination Client Model is particularly adapted to：According to advertisement putting exhibition
Existing data determine all clients occurred in the first page of same search result.
12. device according to claim 10, wherein, the advertisement delivery effect information includes：Client is in same advertisement
Sorting position and/or ad click rate in queue.
13. device according to claim 10, wherein, the determination degree of correlation module is particularly adapted to：For each time
Search result, single correlation journey between client two-by-two is determined in the multiple client all in accordance with the advertisement delivery effect information of client
Degree；Institute is determined according to multiple single degrees of correlation in the range of the scheduled time or according to the single degree of correlation of predetermined quantity
State in multiple clients the degree of correlation between client two-by-two.
14. device according to claim 10, wherein, the relative clients group is relative clients network；And the determination
Customers and subgroup module are particularly adapted to：Corporations present in the relative clients network are excavated according to community discovery algorithm；Inspection
The condensation degree of the corporations is surveyed, and dismisses the corporations that condensation degree does not meet predetermined coherence condition.
15. device according to claim 14, wherein, the determination customers and subgroup module are particularly adapted to：For visitor
Amount amount exceedes the corporations of intended client threshold value, and corporations present in group are excavated according to community discovery algorithm.
16. the device according to any claim in claim 10 to 15, wherein the determination mark post colleague module tool
Body is suitable to：
Gone together according to the mark post that ad placement service index determines to meet advertisement putting client concern information in the subgroup；Its
In, the advertisement putting client, which pays close attention to information, to be included：Advertisement putting scene and/or it is concerned customer type.
17. device according to claim 16, wherein：The advertisement putting scene includes：Search is promoted scene, wirelessly pushed away
Square scape and net alliance promote scene；And/or the customer type that is concerned includes：Equal scale of operation client and industry
Leading client.
18. device according to claim 17, wherein：
Scene is promoted for search, the ad placement service index includes：Advertisement putting consumption Input factors, ad quality because
Son and the advertising conversion factor；
Scene is promoted for wireless, the ad placement service index includes：Advertisement putting consumption Input factors, ad quality because
Son and the Website quality factor；
For net, alliance promotes scene：The ad placement service index includes：Input factors and advertisement matter are consumed in advertisement putting
Measure the factor.
A kind of 19. colleague's positioner in computer equipment, including claim 10-18 described in any claim.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410740960.1A CN104503997B (en) | 2014-12-05 | 2014-12-05 | Colleague's localization method, device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410740960.1A CN104503997B (en) | 2014-12-05 | 2014-12-05 | Colleague's localization method, device and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104503997A CN104503997A (en) | 2015-04-08 |
| CN104503997B true CN104503997B (en) | 2017-12-26 |
Family
ID=52945395
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410740960.1A Active CN104503997B (en) | 2014-12-05 | 2014-12-05 | Colleague's localization method, device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104503997B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106844402B (en) * | 2015-12-04 | 2020-08-28 | 阿里巴巴集团控股有限公司 | Data processing method and device |
| CN108734493B (en) * | 2017-04-20 | 2022-02-08 | 腾讯科技（北京）有限公司 | Advertisement targeted delivery control method, monitoring method and device |
| CN109325791B (en) * | 2017-07-31 | 2021-11-30 | 北京国双科技有限公司 | SEM advertisement competition analysis method and device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102194149A (en) * | 2010-03-01 | 2011-09-21 | 中国人民解放军国防科学技术大学 | Community discovery method |
| CN104077290A (en) * | 2013-03-26 | 2014-10-01 | 腾讯科技（深圳）有限公司 | Method and device for generating promoted accounts |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8838560B2 (en) * | 2006-08-25 | 2014-09-16 | Covario, Inc. | System and method for measuring the effectiveness of an on-line advertisement campaign |
-
2014
- 2014-12-05 CN CN201410740960.1A patent/CN104503997B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102194149A (en) * | 2010-03-01 | 2011-09-21 | 中国人民解放军国防科学技术大学 | Community discovery method |
| CN104077290A (en) * | 2013-03-26 | 2014-10-01 | 腾讯科技（深圳）有限公司 | Method and device for generating promoted accounts |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104503997A (en) | 2015-04-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | Free market of crowdsourcing: Incentive mechanism design for mobile sensing | |
| Pamucar et al. | Multi-criteria decision analysis towards robust service quality measurement | |
| Zhao et al. | A fuzzy synthetic evaluation approach for risk assessment: a case of Singapore's green projects | |
| Vincent et al. | A simulated annealing heuristic for the open location-routing problem | |
| Park et al. | Developing sustainable rural tourism evaluation indicators | |
| CN104133837B (en) | A kind of internet information based on Distributed Calculation delivers channel optimization systems | |
| Chen et al. | Trajectory simplification method for location-based social networking services | |
| Lan et al. | Dancing with wolves: how value creation and value capture dynamics affect complementor participation in industry platforms | |
| Wadhwa et al. | Decision knowledge sharing: flexible supply chains in KM context | |
| CN106611366A (en) | Method and device for automatically selecting article | |
| CN104503997B (en) | Colleague's localization method, device and computer equipment | |
| JP2007193427A5 (en) | ||
| CN109889891A (en) | Obtain the method, apparatus and storage medium of target media file | |
| Kim et al. | The accuracy of tourism forecasting and data characteristics: a meta-analytical approach | |
| Wall-Tweedie et al. | Is the grass greener on the other side? A review of the Asia-Pacific sport industry’s environmental sustainability practices | |
| Ruiz-Meza et al. | A GRASP to solve the multi-constraints multi-modal team orienteering problem with time windows for groups with heterogeneous preferences | |
| US20120303714A1 (en) | Method for managing a personalized social network map in an application server which provides personalized content, and program recording medium for executing the method | |
| CN108345601A (en) | Search result ordering method and device | |
| CN107038620A (en) | Based on user call a taxi preference information push and device | |
| Dash et al. | A model for planning the product portfolio and launch timings under resource constraints | |
| CN106202371A (en) | The processing method of media file, device and advertisement analysis method | |
| Newell et al. | The significance of development sites in global real estate transactions | |
| Li et al. | Capitalize your data: Optimal selling mechanisms for IoT data exchange | |
| Shalender et al. | Integrating strategic flexibility and marketing system to achieve sustainable competitive advantage: conceptual refinement and framework | |
| Jafary et al. | BIM and real estate valuation: Challenges, potentials and lessons for future directions |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |