CN110189152A - The attribution method and apparatus of channel - Google Patents
The attribution method and apparatus of channel Download PDFInfo
- Publication number
- CN110189152A CN110189152A CN201810155682.1A CN201810155682A CN110189152A CN 110189152 A CN110189152 A CN 110189152A CN 201810155682 A CN201810155682 A CN 201810155682A CN 110189152 A CN110189152 A CN 110189152A
- Authority
- CN
- China
- Prior art keywords
- channel
- access
- promotion message
- target
- path
- 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
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
-
- 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
Abstract
This application discloses a kind of attribution method and apparatus of channel.This method comprises: passing through the access data of multiple support channels access target promotion message in acquisition preset time period, obtain access data acquisition system, wherein, multiple support channels are the channel that targeted promotion information is launched, accessing includes a plurality of data in data acquisition system, channel ID, User ID and the access time by each channel access target promotion message are included at least in every data;Data in access data acquisition system are polymerize according to the User ID of target user and access time sequence, generate the access path net for including at least a paths, wherein include at least a channel in path;Calculate the contribution proportion that each channel in access path net is converted into pre-set level to promotion message.By the application, solves the problems, such as to be difficult in effective evaluation promotion message conversion process each channel in the related technology to the contribution degree of final successful conversion.
Description
Technical field
This application involves internet data analysis fields, in particular to a kind of attribution method and apparatus of channel.
Background technique
During online promotion message in Internet era is launched, a client often passes through multiple media outlets and throws
It puts, and has a difference in the dispensing form of each media outlets, such as what is launched in the media having is search promotion message, is paid
Expense mode is CPC (Cost Per Click), i.e., is that certain is pushed away in the promotion message that the media having are launched with every click primary charging
Wide information bit shows promotion message, and way of paying are CPM (Cost Per Mille), i.e. cost per thousand, are sent to by media
The cost of 1000 people is paid as unit, and there are also internet promotion message DSP (Demand Side Platform), that is, is interconnected
The putting modes such as net promotion message demand platform.Media outlets are launched in face of so more promotion messages, what some media were launched
Promotion message changing effect is very good, and the promotion message that some media are launched is almost absent conversion, still, does not believe popularization
Ceasing the media directly converted might not be to no any effect be converted, for example, user may be believed by the popularization of A media
Promotion message related products are had preliminary understanding by breath, then when seeing the promotion message of the product of B media, point
It hits and has carried out deep understanding, finally carried out product search in media C, official website is entered according to search result, and generate
Buy the behavior of the product.In this case the work that each media outlets play in the conversion of current promotion message how is evaluated
With, if the promotion message for stopping some media is launched, great influence can be generated on final conversion, how clearly each canal
Road correlation, the reasonable promotion message dispensing using each media of historical data effective evaluation produce transformation in planta much
Contribution, be a problem to be solved.
For being difficult in effective evaluation promotion message conversion process each channel in the related technology to final successful conversion
The problem of contribution degree, currently no effective solution has been proposed.
Summary of the invention
The main purpose of the application is to provide a kind of attribution method and apparatus of channel, to solve to be difficult in the related technology
The problem of each channel is to the contribution degree of final successful conversion in effective evaluation promotion message conversion process.
To achieve the goals above, according to the one aspect of the application, a kind of attribution method of channel is provided.This method
Include: to acquire the access data for passing through multiple support channels access target promotion message in preset time period, obtain access data acquisition system,
Wherein, multiple support channels are the channel that targeted promotion information is launched, and accessing includes a plurality of data in data acquisition system, in every data extremely
It less include channel ID, User ID and the access time by each channel access target promotion message;To access data acquisition system
In data according to the User ID of target user and access time sequence polymerize, generate include at least a paths access
Path net a, wherein channel is included at least in path;Each channel is converted into promotion message pre- in calculating access path net
If the contribution proportion of index.
It further, include: to calculate access path net by the contribution margin that promotion message transformation model calculates each channel
In each channel pre-set level is converted into promotion message contribution proportion include: each path pair calculated in access path net
The conversion success rate answered simultaneously is summed, and promotion message conversion total probability is obtained;One channel is set as target channel, calculates access
Promotion message after the net removal target channel of path converts total probability;Total probability and removal target channel are converted according to promotion message
Promotion message afterwards converts total probability, calculates the contribution proportion that target channel is converted into pre-set level to promotion message.
Further, it calculates the corresponding conversion success rate of each path in access path net and sums, obtain promoting letter
Breath conversion total probability includes: to obtain the quantity of the target user by each channel access target promotion message;According to by each
The quantity of the target user of a channel access target promotion message jumps to when calculating access target promotion message from each channel
Next channel jumps rate;It is jumped to down according to when the probability of selection each path, access target promotion message from each channel
The conversion ratio for jumping the last one channel in rate and each path of one channel, calculates that each path is corresponding converts successfully
Rate;It sums to the corresponding conversion success rate of each path in access path net, obtains promotion message conversion total probability.
Further, according to the quantity of the target user by each channel access target promotion message, access mesh is calculated
Jumping to the rate that jumps of next channel from each channel when marking promotion message includes: the next canal that will be jumped to by each channel
The quantity of the target user of road access target promotion message is with the target user's by each channel access target promotion message
The ratio of quantity, jump to next channel from each channel when as access target promotion message jumps rate.
To achieve the goals above, according to the another aspect of the application, a kind of attribution device of channel is provided.The device
Include: acquisition unit, for acquiring the access data for passing through multiple support channels access target promotion message in preset time period, obtains
Access data acquisition system, wherein multiple support channels are the channel that targeted promotion information is launched, and accessing includes a plurality of number in data acquisition system
According to including at least channel ID, User ID and the access time by each channel access target promotion message in every data;
Polymerized unit, for gathering to the data in access data acquisition system according to the User ID of target user and access time sequence
It closes, generates the access path net for including at least a paths, wherein include at least a channel in path;Computing unit is used for
Calculate the contribution proportion that each channel in access path net is converted into pre-set level to promotion message.
Further, computing unit includes: the first computing module, corresponding for calculating each path in access path net
Conversion success rate and sum, obtain promotion message conversion total probability;Second computing module, for a channel to be set as mesh
Channel is marked, the promotion message after calculating access path net removal target channel converts total probability;Third computing module is used for basis
Promotion message converts total probability and removes the promotion message conversion total probability after target channel, calculates target channel to promotion message
It is converted into the contribution proportion of pre-set level.
Further, the first computing module includes: acquisition submodule, is promoted for obtaining by each channel access target
The quantity of the target user of information;Rate computational submodule is jumped, passes through each channel access target promotion message for basis
The quantity of target user, jump to next channel from each channel when calculating access target promotion message jumps rate;Conversion ratio
Computational submodule, for next according to being jumped to when probability, the access target promotion message for selecting each path from each channel
The conversion ratio for jumping the last one channel in rate and each path of channel, calculates that each path is corresponding converts successfully
Rate;Promotion message convert total probability computational submodule, for the corresponding conversion success rate of each path in access path net into
Row summation obtains promotion message conversion total probability.
Further, rate computational submodule is jumped further include: the next channel jumped to by each channel is accessed into mesh
Mark the ratio of the quantity and the quantity of the target user by each channel access target promotion message of the target user of promotion message
Value, jump to next channel from each channel when as access target promotion message jumps rate.
To achieve the goals above, according to the another aspect of the application, a kind of storage medium, the storage medium are provided
Program including storage, wherein described program executes the attribution method of the channel of any one of the above.
To achieve the goals above, according to the another aspect of the application, a kind of processor is provided, the processor is for transporting
Line program, wherein program executes the attribution method of any one of the above channel when running.
By the application, using following steps: passing through multiple support channels access target promotion message in acquisition preset time period
Access data, obtain access data acquisition system, wherein multiple support channels be targeted promotion information launch channel, access data set
Include a plurality of data in conjunction, include at least channel ID in every data, User ID and passes through the popularization of each channel access target
The access time of information;Data in access data acquisition system are gathered according to the User ID of target user and access time sequence
It closes, generates the access path net for including at least a paths, wherein include at least a channel in path;Calculate access path
Each channel is converted into the contribution proportion of pre-set level to promotion message in net.Access is formed by the way that history is accessed data aggregate
In the net of path, the contribution margin of each channel is calculated, and then reached each channel pair in effective evaluation promotion message conversion process
The effect of the contribution degree of final successful conversion.
Detailed description of the invention
The attached drawing constituted part of this application is used to provide further understanding of the present application, the schematic reality of the application
Example and its explanation are applied for explaining the application, is not constituted an undue limitation on the present application.In the accompanying drawings:
Fig. 1 is the flow chart according to the attribution method of channel provided by the embodiments of the present application;
Fig. 2 is the schematic diagram of access path net in the attribution method according to channel provided by the embodiments of the present application;
Fig. 3 is according to the schematic diagram formed after removal target channel in access path net provided by the embodiments of the present application;
Fig. 4 is the schematic diagram according to the attribution device of channel provided by the embodiments of the present application.
Specific embodiment
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application
Attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only
The embodiment of the application a part, instead of all the embodiments.Based on the embodiment in the application, ordinary skill people
Member's every other embodiment obtained without making creative work, all should belong to the model of the application protection
It encloses.
It should be noted that the description and claims of this application and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to embodiments herein described herein.In addition, term " includes " and " tool
Have " and their any deformation, it is intended that cover it is non-exclusive include, for example, containing a series of steps or units
Process, method, system, product or equipment those of are not necessarily limited to be clearly listed step or unit, but may include without clear
Other step or units listing to Chu or intrinsic for these process, methods, product or equipment.
For ease of description, below to the invention relates to part noun or term be illustrated:
Markov Chain: what Markov Chain embodied is the transformational relation in state space, in one group of status switch, often
A state is only related with preceding state.
Removal effect:Removal effect refer to evaluation graph model in a point (in practical applications, I
Be considered as a channel) contribution margin, visually are as follows: include point (channel) when, whole contribution margin, subtract remove the point (canal
Road) when, whole contribution margin.
Channel attribution: channel attribution refers to user before completing conversion, contacts multiple about this conversion commodity
Channels are publicized, these channels are analyzed, this is converted reasonable attribution into multiple support channels.
Below with reference to preferred implementation steps, the present invention will be described, and Fig. 1 is channel according to an embodiment of the present invention
The flow chart of attribution method, as shown in Figure 1, this method comprises the following steps:
Step S101, the interior access data for passing through multiple support channels access target promotion message of acquisition preset time period, obtains
Access data acquisition system, wherein multiple support channels are the channel that targeted promotion information is launched, and accessing includes a plurality of number in data acquisition system
According to including at least channel ID, User ID and the access time by each channel access target promotion message in every data;
For example, preset time period is 3 months, targeted promotion information is the mobile phone advertisement of A brand, businessman in C1 browser,
C2 browser and C3 browser have launched the mobile phone advertisement of A brand;
Each user accesses the mobile phone advertisement of A brand by C1 browser, C2 browser and C3 browser in acquisition 3 months
Access data, obtain access data acquisition system, wherein include a plurality of data in access data acquisition system, at least wrap in every data
It includes C1 browser, the ID of C2 browser and C3 browser, User ID and the mobile phone advertisement of A brand is accessed by each channel
Access time, average access duration, averagely jump the information such as time interval at average access depth.
Step S102 carries out the data in access data acquisition system according to the User ID of target user and access time sequence
Polymerization generates the access path net for including at least a paths, wherein a channel is included at least in path.
The channel that promotion message passes through is accessed to user and is connected into path according to the real time that user accesses promotion message,
One or more channel involved in path, the Markov model that mulitpath polymerization generates is advertisement transformation model, wherein
Advertisement transformation model includes mulitpath, and each path includes at least: jumping relationship between each channel and each channel, respectively
A channel forms the node in path, the directed edge for jumping relationship and forming path between each channel.
Specified target user, if in 3 months preset time periods, the access of partial target user's first passage C1 browser
After the mobile phone advertisement of A brand, and the mobile phone advertisement of C2 browser access A brand is jumped to, finally jumps to C3 browser access A
The mobile phone advertisement of brand, then it includes 3 channels in first path that the access that this time jumps of target user, which constitutes first path,;Portion
After partial objectives for user's first passage C1 browser accesses the mobile phone advertisement of A brand, and jump to the hand of C3 browser access A brand
Machine advertisement, then it includes 2 channels in the second path that the access that this time jumps of target user, which constitutes the second path,;Partial target is used
Family first passage C3 browser accesses the mobile phone advertisement of A brand, then this visit of target user constitutes third path, third road
Include 1 channel in diameter, first path, the second path and third path are polymerized to access path net.
Step S103 calculates the contribution proportion that each channel in access path net is converted into pre-set level to promotion message.
Assuming that the behavior that user scanned for and clicked promotion message has Markov property, i.e. user's current accessed is promoted
Channel used when information, it is only related with channel used when its last time access promotion message, on this basis, the visit of user
Ask that process (channel being related to when access) will meet Markov property, thus, it is possible in difference when user is accessed promotion message
The path to be formed is jumped between channel and is considered as Markov Chain, and the access path net that polymerization generates is considered as Markov model,
It can use removal effect algorithm on this basis and calculate the tribute that each channel is converted into pre-set level to promotion message
Offer ratio.Check after the mobile phone advertisement of A brand that logging in official website places an order as user for example, setting promotion message and turning to pre-set level
The behavior of the brand mobile phone is had purchased, user checks that the behavior of the mobile phone advertisement of A brand is only browsed with upper one in current browser
Device is related, and user jumps the access path that access A brand mobile phone advertisement is formed on C1 browser, C2 browser and C3 browser
Net meets Markov property, can calculate C1 browser, C2 browser and C3 browser three by removal effect algorithm
A channel, which respectively checks user after the mobile phone advertisement of A brand to log in official website and place an order, has purchased the contribution proportion of mobile phone.
Optionally, in the attribution method of channel provided by the embodiments of the present application, each channel in access path net is calculated
It include: to calculate each path in access path net corresponding to be converted to the contribution proportion that promotion message is converted into pre-set level
Power is simultaneously summed, and promotion message conversion total probability is obtained;One channel is set as target channel, calculates the removal of access path net
Promotion message after target channel converts total probability;Popularization letter after converting total probability and removal target channel according to promotion message
Breath conversion total probability, calculates the contribution proportion that target channel is converted into pre-set level to promotion message.
For example, there are 600 target users to check the mobile phone advertisement of A brand in C1 browser for the first time in 3 months,
Wherein 300 users do not check that the mobile phone advertisement of the brand does not buy the mobile phone of the brand yet in other channels later;In addition
300 users have successively checked the mobile phone advertisement in C2 browser and C3 browser after this, wherein 150 users finally step on
Land official website, which places an order, has purchased the mobile phone of the brand, and in addition 150 users do not buy;
In addition, the mobile phone advertisement for thering are 300 users not check A brand in C1 browser, but it is clear in C2 for the first time
Device of looking at has checked the mobile phone advertisement of the brand, the mobile phone advertisement that the brand has been checked on C3 browser is jumped to again later, in C3
After being checked on browser, places an order wherein 150 users log in official website and have purchased the mobile phone of the brand, in addition 150 users do not have
There is purchase;
Fig. 2 is the schematic diagram of access path net in the attribution method according to channel provided by the embodiments of the present application, such as Fig. 2 institute
Show, altogether includes 3 paths, the first paths, by accessing A by C1 browser in the access path net that the above behavior is formed
The data of the mobile phone advertisement of brand are constituted;Second paths, by jumping to C2 browser again to C3 browser by C1 browser
Sequential access A brand mobile phone advertisement data constitute;Third path, by jumping to C3 browser by C2 browser
The data of the mobile phone advertisement of sequential access A brand are constituted.
The user on 3 paths is calculated separately to have checked the mobile phone of A brand and finally had purchased the general of the mobile phone of the brand
Rate sums the purchase probability on 3 paths, obtains the total probability of advertising conversion after the mobile phone advertisement of dispensing A brand;C1 is clear
Device of looking at is set as target channel, calculates the probability that user after removing C1 browser finally has purchased the mobile phone of A brand, and removal C1 is clear
Look at the advertising conversion total probability after device;It is carried out according to the advertising conversion total probability after advertising conversion total probability and removal C1 browser
It calculates, obtains launching advertisement by C1 browser and check after the mobile phone advertisement of A brand the contribution margin for generating buying behavior to user.
Optionally, in the attribution method of channel provided by the embodiments of the present application, the road access path net Zhong Meitiao is calculated
The corresponding conversion success rate of diameter is simultaneously summed, and obtaining promotion message conversion total probability includes: to obtain through each channel access target
The quantity of the target user of promotion message;According to the quantity of the target user by each channel access target promotion message, meter
Jump to next channel from each channel when calculating access target promotion message jumps rate;According to selection each path probability,
The last one canal of next channel jumped in rate and each path is jumped to when access target promotion message from each channel
The conversion ratio in road calculates the corresponding conversion success rate of each path;It is converted successfully to each path is corresponding in access path net
Rate is summed, and promotion message conversion total probability is obtained.
For example, obtaining the probability that user selects the first paths, i.e. the mobile phone of first passage C1 browser access A brand is wide
The probability of announcement;The probability namely first passage C1 browser of user's the second paths of selection access the general of the mobile phone advertisement of A brand
Rate;User selects the probability of the probability of third path namely the mobile phone advertisement of first passage C2 browser access A brand;Together
When, it obtains in the first paths, pass through in the second paths with the conversion ratio of the last one channel of third path, i.e. user
The mobile phone advertisement of the last one channel access A brand of each path and the probability for buying the brand mobile phone.
The quantity that user accesses the mobile phone advertisement of A brand by C1 browser, C2 browser and C3 browser is obtained respectively,
And calculate that user jumps to that next channel checks the mobile phone advertisement after current channel has checked mobile phone advertisement jumps rate;Respectively
User is selected the probability of each path, user working as by three paths that the mobile phone advertisement of A brand is finally had purchased for user
Preceding channel has checked after mobile phone advertisement that jump to that next channel checks mobile phone advertisement jumps rate and in the last of the paths
The mobile phone advertisement of one channel access A brand and the probability multiplication for buying the brand mobile phone, obtain the corresponding conversion of each path
Success rate;For the first paths, user does not generate corresponding purchase finally in the mobile phone advertisement of C1 browser access A brand
It buys behavior, i.e., in the mobile phone advertisement of the last one channel access A brand of the paths and buys the probability of the brand mobile phone and be
0, the corresponding conversion success rate of the first paths is 0;For the second paths, calculates user's first passage C1 browser and look into
See the probability of the mobile phone advertisement of A brand, jumped to from C1 browser C2 browser jump rate, to jump to C3 from C2 browser clear
It lookes at after the jumping rate, check advertisement by C3 browser of device and generates the probability of buying behavior 4 probability multiplications are obtained second
The corresponding conversion success rate of paths;For third path, calculates user's first passage C2 browser and check A brand
The probability of mobile phone advertisement generates purchase after jumping to the jumping rate, check advertisement by C3 browser of C3 browser from C2 browser
3 probability multiplications are obtained the corresponding conversion success rate of third path by the probability for buying behavior;It is corresponding to the first paths
Conversion success rate, the corresponding conversion success rate of the second paths and the corresponding conversion success rate of third path are summed, and are obtained
User produces phase after checking advertisement after to the mobile phone advertisement for launching A brand by C1 browser, C2 browser and C3 browser
Answer the probability of buying behavior, i.e. the conversion total probability of the mobile phone advertisement of A brand.
Optionally, in the attribution method of channel provided by the embodiments of the present application, according to passing through each channel access target
The quantity of the target user of promotion message jumps to jumping for next channel from each channel when calculating access target promotion message
Rate includes: by the quantity of the target user of the next channel access target promotion message jumped to by each channel and by each
The ratio of the quantity of the target user of a channel access target promotion message, from each channel when as access target promotion message
Jump to next channel jumps rate.
For example, businessman has been after C1 browser, C2 browser and C3 browser have launched the mobile phone advertisement of A brand, for the first time
Check that the target user of the mobile phone advertisement of A brand is 900 people, wherein first passage C1 browser checks the mobile phone advertisement of A brand
User quantity be 900 people, wherein first passage C2 browser check the user of the mobile phone advertisement of A brand quantity be 300
People;So, the probability checked for the first time from C1 browser is 2/3, that is, selects the first paths, selects the probability of the second paths equal
It is 2/3, in the first paths, user does not generate corresponding purchase row finally in the mobile phone advertisement of C1 browser access A brand
For the corresponding conversion success rate of the first paths is 0;In the second paths, the use of C2 browser is jumped to from C1 browser
There are 300 people at family, i.e., jumping to the rate that jumps of C2 browser from C1 browser is 1/2, jumps to C3 browser from C2 browser
User has 300 people, i.e., jumping to the rate that jumps of C3 browser from C2 browser is 1, wherein having 150 to produce buying behavior, purchases
Buying rate is 1/2, and C2 browser is jumped to by the probability checked from C1 browser, from C1 browser jumps rate, from C2 browser
The rate that jumps for jumping to C3 browser checks that the buying rate after advertisement is multiplied with from C3 browser, obtains user and looks into from the second path
It sees the mobile phone advertisement of A brand and the probability for generating buying behavior is 1/6, is i.e. the corresponding conversion success rate of the second paths is 1/6;
Similarly, wherein first passage C2 browser check A brand mobile phone advertisement user quantity be 300 people, for the first time from C2 browse
The probability that device is checked is 1/3, that is, selecting the probability of third path is 2/3, in third path, is jumped to from C2 browser
The user of C3 browser has 300 people, i.e., jumping to the rate that jumps of C3 browser from C2 browser is 1, wherein having 150 to produce purchase
Buy behavior, buying rate 1/2, jumped to by the probability checked from C2 browser, from C2 browser C3 browser jump rate with
It checks that the buying rate after advertisement is multiplied from C3 browser, obtains mobile phone advertisement and generation that user checks A brand from the second path
The probability of buying behavior is 1/6, i.e., the corresponding conversion success rate of third path is 1/6.
User is checked into the mobile phone advertisement of A brand from first path and generates the probability of buying behavior, user from the second tunnel
Diameter checks the mobile phone advertisement of A brand and generates the probability of buying behavior and user from third path checks that the mobile phone of A brand is wide
The probability summation for accusing and generating buying behavior, obtains in 3 months through C1 browser, C2 browser and C3 web page access A brand
Mobile phone advertisement after advertising conversion total probability be 1/3.
Fig. 3 is according to the schematic diagram formed after removal target channel in access path net provided by the embodiments of the present application, such as
Shown in Fig. 3, it is assumed that after channel is launched in removal this advertisement of C1 browser, i.e., removal user passes through the visit that C1 browser accesses advertisement
Conversion ratio after the dispensing of C1 browser of the amount of asking, advertisement and probability is jumped according to channel removes the wide of the subsequent channel of C1 browser
It accuses inversion quantity (being considered as the conversion and amount of access drained by C1 browser point), not after C1 browser jumps influence
Continuous channel is unaffected;Access path net only remains a paths in this way: it is made of the sequence of C2 browser to C3 browser,
The third path being equivalent in former access path net, the corresponding conversion success rate of third path are 1/6, and advertising conversion is always general
Rate is also 1/6.
Before removing C1 browser, advertising conversion total probability is 1/3;After removing C1 browser, advertising conversion total probability is
1/6, the difference for removing before C1 browser and removing the transition probability of advertisement after C1 browser is that the contribution margin of 1/6, C1 browser is
1/6。
The attribution method of channel provided by the embodiments of the present application, by being accessed in acquisition preset time period by multiple support channels
The access data of targeted promotion information obtain access data acquisition system, wherein multiple support channels are the canal that targeted promotion information is launched
Road, accessing includes a plurality of data in data acquisition system, includes at least channel ID in every data, User ID and passes through each channel
The access time of access target promotion message;To access data acquisition system in data according to target user User ID and access when
Between sequentially polymerize, generate include at least a paths access path net, wherein in path include at least a channel;
Calculate the contribution proportion that each channel in access path net is converted into pre-set level to promotion message.It is difficult in the related technology to solve
The problem of with each channel in effective evaluation promotion message conversion process to the contribution degree of final successful conversion.By the way that history is visited
It asks that data aggregate is formed in access path net, calculates the contribution margin of each channel, and then reached effective evaluation promotion message and turned
Effect of each channel to the contribution degree of final successful conversion during change.
It should be noted that step shown in the flowchart of the accompanying drawings can be in such as a group of computer-executable instructions
It is executed in computer system, although also, logical order is shown in flow charts, and it in some cases, can be with not
The sequence being same as herein executes shown or described step.
The embodiment of the present application also provides a kind of attribution devices of channel, it should be noted that the canal of the embodiment of the present application
The attribution device in road can be used for executing the attribution method that channel is used for provided by the embodiment of the present application.Below to the application reality
The attribution device for applying the channel of example offer is introduced.
Fig. 4 is the schematic diagram according to the attribution device of the channel of the embodiment of the present application.As shown in figure 4, the device includes: to adopt
Collect unit 10, polymerized unit 20 and computing unit 30.
Specifically, acquisition unit 10, for acquiring in preset time period through multiple support channels access target promotion message
Data are accessed, access data acquisition system is obtained, wherein multiple support channels are the channel that targeted promotion information is launched, and access data acquisition system
In include a plurality of data, include at least channel ID in every data, User ID and letter promoted by each channel access target
The access time of breath;
Polymerized unit 20, for suitable according to the User ID of target user and access time to the data in access data acquisition system
Sequence is polymerize, and the access path net for including at least a paths is generated, wherein a channel is included at least in path;
Computing unit 30, the contribution that pre-set level is converted into promotion message for calculating each channel in access path net
Ratio.
Optionally, in the attribution device of channel provided by the embodiments of the present application, computing unit includes 30: the first calculating moulds
It is total general to obtain promotion message conversion for calculating the corresponding conversion success rate of each path in access path net and summing for block
Rate;Second computing module, for a channel to be set as target channel, pushing away after calculating access path net removal target channel
Guangxin breath conversion total probability;Third computing module, for converting total probability and pushing away after removal target channel according to promotion message
Guangxin breath conversion total probability, calculates the contribution proportion that target channel is converted into pre-set level to promotion message.
Optionally, in the attribution device of channel provided by the embodiments of the present application, the first computing module includes: acquisition submodule
Block, for obtaining the quantity of the target user by each channel access target promotion message;Rate computational submodule is jumped, is used for
According to the quantity of the target user by each channel access target promotion message, from each when calculating access target promotion message
What channel jumped to next channel jumps rate;Conversion ratio computational submodule, for probability, the access mesh according to selection each path
Turning for the last one channel of next channel jumped in rate and each path is jumped to when marking promotion message from each channel
Rate calculates the corresponding conversion success rate of each path;Promotion message converts total probability computational submodule, for access path
The corresponding conversion success rate of each path is summed in net, obtains promotion message conversion total probability.
Optionally, in the attribution device of channel provided by the embodiments of the present application, rate computational submodule is jumped further include: will
The quantity of the target user of the next channel access target promotion message jumped to by each channel is visited with by each channel
The ratio for asking the quantity of the target user of targeted promotion information jumps to down when as access target promotion message from each channel
One channel jumps rate.
The attribution device of channel provided by the embodiments of the present application is acquired and is passed through in preset time period by acquisition unit 10
The access data of multiple support channels access target promotion message obtain access data acquisition system, wherein multiple support channels are targeted promotion letter
The channel launched is ceased, accessing includes a plurality of data in data acquisition system, includes at least channel ID in every data, User ID and logical
Spend the access time of each channel access target promotion message;Polymerized unit 20, for being pressed to the data in access data acquisition system
User ID and access time sequence according to target user polymerize, and generate the access path net for including at least a paths,
In, a channel is included at least in path;Computing unit 30 turns promotion message for calculating each channel in access path net
The contribution proportion for turning to pre-set level solves and is difficult to each channel in effective evaluation promotion message conversion process in the related technology
The problem of to the contribution degree of final successful conversion.It is formed in access path net, is calculated each by the way that history is accessed data aggregate
The contribution margin of channel, and then reached contribution of each channel to final successful conversion in effective evaluation promotion message conversion process
The effect of degree.
The attribution device of the channel includes processor and memory, above-mentioned acquisition unit 10, polymerized unit 20 and calculating
Units 30 etc. store in memory as program unit, execute above procedure unit stored in memory by processor
To realize corresponding function.
Include kernel in processor, is gone in memory to transfer corresponding program unit by kernel.Kernel can be set one
Or more, carry out tribute of each channel to final successful conversion in effective evaluation promotion message conversion process by adjusting kernel parameter
The effect for degree of offering.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, if read-only memory (ROM) or flash memory (flash RAM), memory include that at least one is deposited
Store up chip.
The embodiment of the invention provides a kind of storage mediums, are stored thereon with program, real when which is executed by processor
The attribution method of the existing channel.
The embodiment of the invention provides a kind of processor, the processor is for running program, wherein described program operation
The attribution method of channel described in Shi Zhihang.
The embodiment of the invention provides a kind of equipment, equipment include processor, memory and storage on a memory and can
The program run on a processor, processor are performed the steps of in acquisition preset time period when executing program through multiple canals
The access data of road access target promotion message obtain access data acquisition system, wherein multiple support channels are the dispensing of targeted promotion information
Channel, accessing includes a plurality of data in data acquisition system, includes at least channel ID in every data, User ID and by each
The access time of channel access target promotion message;To the data in access data acquisition system according to the User ID and visit of target user
It asks that time sequencing is polymerize, generates the access path net for including at least a paths, wherein include at least a canal in path
Road;Calculate the contribution proportion that each channel in access path net is converted into pre-set level to promotion message.
It further, include: to calculate in access path net each by the contribution margin that access path net calculates each channel
The contribution proportion that channel is converted into pre-set level to promotion message includes: corresponding turn of each path calculated in access path net
Chemical conversion power is simultaneously summed, and promotion message conversion total probability is obtained;One channel is set as target channel, calculates access path net
Promotion message after removing target channel converts total probability;Total probability and pushing away after removal target channel are converted according to promotion message
Guangxin breath conversion total probability, calculates the contribution proportion that target channel is converted into pre-set level to promotion message.
Further, it calculates the corresponding conversion success rate of each path in access path net and sums, obtain promoting letter
Breath conversion total probability includes: to obtain the quantity of the target user by each channel access target promotion message;According to by each
The quantity of the target user of a channel access target promotion message jumps to when calculating access target promotion message from each channel
Next channel jumps rate;It is jumped to down according to when the probability of selection each path, access target promotion message from each channel
The conversion ratio for jumping the last one channel in rate and each path of one channel, calculates that each path is corresponding converts successfully
Rate;It sums to the corresponding conversion success rate of each path in access path net, obtains promotion message conversion total probability.
Further, according to the quantity of the target user by each channel access target promotion message, access mesh is calculated
Jumping to the rate that jumps of next channel from each channel when marking promotion message includes: the next canal that will be jumped to by each channel
The quantity of the target user of road access target promotion message is with the target user's by each channel access target promotion message
The ratio of quantity, jump to next channel from each channel when as access target promotion message jumps rate.Herein sets
It is standby to can be server, PC, PAD, mobile phone etc..
Present invention also provides a kind of computer program products, when executing on data processing equipment, are adapted for carrying out just
The program of beginningization there are as below methods step: pass through the access number of multiple support channels access target promotion message in acquisition preset time period
According to, obtain access data acquisition system, wherein multiple support channels be targeted promotion information launch channel, access data acquisition system in include
A plurality of data include at least channel ID, User ID and the visit by each channel access target promotion message in every data
Ask the time;Data in access data acquisition system are polymerize according to the User ID of target user and access time sequence, are generated
Including at least the access path net of a paths, wherein include at least a channel in path;It calculates each in access path net
Channel is converted into the contribution proportion of pre-set level to promotion message.
It further, include: to calculate in access path net each by the contribution margin that access path net calculates each channel
The contribution proportion that channel is converted into pre-set level to promotion message includes: corresponding turn of each path calculated in access path net
Chemical conversion power is simultaneously summed, and promotion message conversion total probability is obtained;One channel is set as target channel, calculates access path net
Promotion message after removing target channel converts total probability;Total probability and pushing away after removal target channel are converted according to promotion message
Guangxin breath conversion total probability, calculates the contribution proportion that target channel is converted into pre-set level to promotion message.
Further, it calculates the corresponding conversion success rate of each path in access path net and sums, obtain promoting letter
Breath conversion total probability includes: to obtain the quantity of the target user by each channel access target promotion message;According to by each
The quantity of the target user of a channel access target promotion message jumps to when calculating access target promotion message from each channel
Next channel jumps rate;It is jumped to down according to when the probability of selection each path, access target promotion message from each channel
The conversion ratio for jumping the last one channel in rate and each path of one channel, calculates that each path is corresponding converts successfully
Rate;It sums to the corresponding conversion success rate of each path in access path net, obtains promotion message conversion total probability.
Further, according to the quantity of the target user by each channel access target promotion message, access mesh is calculated
Jumping to the rate that jumps of next channel from each channel when marking promotion message includes: the next canal that will be jumped to by each channel
The quantity of the target user of road access target promotion message is with the target user's by each channel access target promotion message
The ratio of quantity, jump to next channel from each channel when as access target promotion message jumps rate.
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the application, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, calculating equipment includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable Jie
The example of matter.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices
Or any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, it calculates
Machine readable medium does not include temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including element
There is also other identical elements in process, method, commodity or equipment.
It will be understood by those skilled in the art that embodiments herein can provide as method, system or computer program product.
Therefore, complete hardware embodiment, complete software embodiment or embodiment combining software and hardware aspects can be used in the application
Form.It is deposited moreover, the application can be used to can be used in the computer that one or more wherein includes computer usable program code
The shape for the computer program product implemented on storage media (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
Formula.
The above is only embodiments herein, are not intended to limit this application.To those skilled in the art,
Various changes and changes are possible in this application.It is all within the spirit and principles of the present application made by any modification, equivalent replacement,
Improve etc., it should be included within the scope of the claims of this application.
Claims (10)
1. a kind of attribution method of channel characterized by comprising
The access data for passing through multiple support channels access target promotion message in preset time period are acquired, access data acquisition system is obtained,
Wherein, the multiple channel is the channel that the targeted promotion information is launched, and includes a plurality of data in the access data acquisition system,
When including at least channel ID, User ID in every data and accessing the access of the targeted promotion information by each channel
Between;
Data in the access data acquisition system are polymerize according to the User ID of target user and access time sequence, are generated
Including at least the access path net of a paths, wherein include at least a channel in the path;
Calculate the contribution proportion that each channel in the access path net is converted into pre-set level to promotion message.
2. believing the method according to claim 1, wherein calculating each channel in the access path net popularization
Breath is converted into the contribution proportion of pre-set level
It calculates the corresponding conversion success rate of each path in the access path net and sums, it is total general to obtain promotion message conversion
Rate;
One channel is set as target channel, the access path net is calculated and removes the promotion message turn after the target channel
Change total probability;
Promotion message after converting total probability and the removal target channel according to the promotion message converts total probability, calculates institute
State the contribution proportion that target channel is converted into pre-set level to promotion message.
3. according to the method described in claim 2, it is characterized in that, each path calculated in the access path net is corresponding
Conversion success rate is simultaneously summed, and is obtained promotion message conversion total probability and is included:
Obtain the quantity of the target user by each channel access target promotion message;
According to the quantity of the target user by each channel access target promotion message, when calculating access target promotion message from
What each channel jumped to next channel jumps rate;
Jump to next channel from each channel when according to the probability of selection each path, access target promotion message jumps rate
And the conversion ratio of the last one channel in each path, calculate the corresponding conversion success rate of each path;
It sums to the corresponding conversion success rate of each path in the access path net, it is total general to obtain promotion message conversion
Rate.
4. according to the method described in claim 3, it is characterized in that, according to the mesh by each channel access target promotion message
The quantity of user is marked, jumps to jumping for next channel from each channel when calculating access target promotion message
Rate includes:
By the quantity of the target user of the next channel access target promotion message jumped to by each channel with by each
The ratio of the quantity of the target user of channel access target promotion message is jumped when as access target promotion message from each channel
Go to next channel jumps rate.
5. a kind of attribution device of channel characterized by comprising
Acquisition unit is obtained for acquiring the access data for passing through multiple support channels access target promotion message in preset time period
Access data acquisition system, wherein the multiple channel is the channel that the targeted promotion information is launched, in the access data acquisition system
Including a plurality of data, the targeted promotion is accessed including at least channel ID, User ID and by each channel in every data
The access time of information;
Polymerized unit, for it is described access data acquisition system in data according to the User ID of target user and access time sequence
It is polymerize, generates the access path net for including at least a paths, wherein includes at least a channel in the path;
Computing unit, the contribution ratio that pre-set level is converted into promotion message for calculating each channel in the access path net
Example.
6. device according to claim 5, which is characterized in that the computing unit includes:
First computing module is obtained for calculating the corresponding conversion success rate of each path in the access path net and summing
Total probability is converted to promotion message;
Second computing module calculates the access path net and removes the target for a channel to be set as target channel
Promotion message after channel converts total probability;
Third computing module, for converting total probability and the promotion message after the removal target channel according to the promotion message
Total probability is converted, the contribution proportion that the target channel is converted into pre-set level to promotion message is calculated.
7. device according to claim 6, which is characterized in that first computing module includes:
Acquisition submodule, for obtaining the quantity of the target user by each channel access target promotion message;
Rate computational submodule is jumped, for the quantity according to the target user by each channel access target promotion message, meter
Jump to next channel from each channel when calculating access target promotion message jumps rate;
Conversion ratio computational submodule, for according to when probability, the access target promotion message of selection each path from each channel
The conversion ratio for jumping the last one channel in rate and each path of next channel is jumped to, it is corresponding to calculate each path
Convert success rate;
Promotion message converts total probability computational submodule, for converting successfully to each path is corresponding in the access path net
Rate is summed, and promotion message conversion total probability is obtained.
8. device according to claim 7, which is characterized in that described to jump rate computational submodule further include:
By the quantity of the target user of the next channel access target promotion message jumped to by each channel with by each
The ratio of the quantity of the target user of channel access target promotion message is jumped when as access target promotion message from each channel
Go to next channel jumps rate.
9. a kind of storage medium, which is characterized in that the storage medium includes the program of storage, wherein described program right of execution
Benefit require any one of 1 to 4 described in channel attribution method.
10. a kind of processor, which is characterized in that the processor is for running program, wherein right of execution when described program is run
Benefit require any one of 1 to 4 described in channel attribution method.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810155682.1A CN110189152A (en) | 2018-02-23 | 2018-02-23 | The attribution method and apparatus of channel |
PCT/CN2019/073695 WO2019161731A1 (en) | 2018-02-23 | 2019-01-29 | Method and apparatus for channel attribution |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810155682.1A CN110189152A (en) | 2018-02-23 | 2018-02-23 | The attribution method and apparatus of channel |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110189152A true CN110189152A (en) | 2019-08-30 |
Family
ID=67687438
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810155682.1A Pending CN110189152A (en) | 2018-02-23 | 2018-02-23 | The attribution method and apparatus of channel |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN110189152A (en) |
WO (1) | WO2019161731A1 (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111582934A (en) * | 2020-05-07 | 2020-08-25 | 北京点众科技股份有限公司 | Method, terminal and storage medium for determining option contribution degree for purchasing electronic book |
CN111784380A (en) * | 2020-06-05 | 2020-10-16 | 北京沃东天骏信息技术有限公司 | Advertisement putting attribution method and device |
CN112035749A (en) * | 2020-09-04 | 2020-12-04 | 贝壳技术有限公司 | User behavior characteristic analysis method, recommendation method and corresponding devices |
CN112200618A (en) * | 2020-10-29 | 2021-01-08 | 上海优扬新媒信息技术有限公司 | Message channel attribution method, device and system |
CN112215636A (en) * | 2020-01-21 | 2021-01-12 | 华为技术有限公司 | Advertisement attribution method and equipment |
CN112529634A (en) * | 2020-12-18 | 2021-03-19 | 恩亿科(北京)数据科技有限公司 | Transformation link analysis method and system based on big data and computer equipment |
CN113256335A (en) * | 2021-05-27 | 2021-08-13 | 腾讯科技(深圳)有限公司 | Data screening method, multimedia data delivery effect prediction method and device |
CN114693361A (en) * | 2022-03-31 | 2022-07-01 | 北京明略软件系统有限公司 | Method, device, equipment and storage medium for determining contribution degree of channel |
CN116137004A (en) * | 2023-04-19 | 2023-05-19 | 江西时刻互动科技股份有限公司 | Attribution method, attribution system and attribution computer for advertisement putting effect |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110704779A (en) * | 2019-09-27 | 2020-01-17 | 杭州迪普科技股份有限公司 | Website page access compliance detection method, device and equipment |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102663616A (en) * | 2012-03-19 | 2012-09-12 | 北京国双科技有限公司 | Method and system for measuring web advertising effectiveness based on multiple-contact attribution model |
WO2013022852A1 (en) * | 2011-08-05 | 2013-02-14 | Marketshare Partners Llc | Cross-media attribution model for allocation of marketing resources |
CN103562946A (en) * | 2011-05-27 | 2014-02-05 | 谷歌公司 | Multiple attribution models with return on ad spend |
CN107438138A (en) * | 2017-09-12 | 2017-12-05 | 中国联合网络通信集团有限公司 | A kind of channel touches the recommendation method and device up to mode |
CN107563781A (en) * | 2016-06-30 | 2018-01-09 | 阿里巴巴集团控股有限公司 | A kind of information launches effect attribution method and device |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104657882B (en) * | 2015-02-06 | 2018-07-13 | 百度在线网络技术(北京)有限公司 | The acquisition methods and device of promotion effect data |
CN107343047B (en) * | 2017-07-06 | 2021-09-28 | 北京奇虎科技有限公司 | Application promotion system and method |
CN107481062A (en) * | 2017-08-21 | 2017-12-15 | 小草数语(北京)科技有限公司 | The distribution method and device of advertisement putting budget |
-
2018
- 2018-02-23 CN CN201810155682.1A patent/CN110189152A/en active Pending
-
2019
- 2019-01-29 WO PCT/CN2019/073695 patent/WO2019161731A1/en active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103562946A (en) * | 2011-05-27 | 2014-02-05 | 谷歌公司 | Multiple attribution models with return on ad spend |
WO2013022852A1 (en) * | 2011-08-05 | 2013-02-14 | Marketshare Partners Llc | Cross-media attribution model for allocation of marketing resources |
CN102663616A (en) * | 2012-03-19 | 2012-09-12 | 北京国双科技有限公司 | Method and system for measuring web advertising effectiveness based on multiple-contact attribution model |
CN107563781A (en) * | 2016-06-30 | 2018-01-09 | 阿里巴巴集团控股有限公司 | A kind of information launches effect attribution method and device |
CN107438138A (en) * | 2017-09-12 | 2017-12-05 | 中国联合网络通信集团有限公司 | A kind of channel touches the recommendation method and device up to mode |
Non-Patent Citations (1)
Title |
---|
杨德礼: "《电子商务环境下管理理论与方法》", 31 December 2004, 大连理工大学出版社 * |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112215636A (en) * | 2020-01-21 | 2021-01-12 | 华为技术有限公司 | Advertisement attribution method and equipment |
CN111582934A (en) * | 2020-05-07 | 2020-08-25 | 北京点众科技股份有限公司 | Method, terminal and storage medium for determining option contribution degree for purchasing electronic book |
CN111784380A (en) * | 2020-06-05 | 2020-10-16 | 北京沃东天骏信息技术有限公司 | Advertisement putting attribution method and device |
CN112035749A (en) * | 2020-09-04 | 2020-12-04 | 贝壳技术有限公司 | User behavior characteristic analysis method, recommendation method and corresponding devices |
CN112200618A (en) * | 2020-10-29 | 2021-01-08 | 上海优扬新媒信息技术有限公司 | Message channel attribution method, device and system |
CN112529634A (en) * | 2020-12-18 | 2021-03-19 | 恩亿科(北京)数据科技有限公司 | Transformation link analysis method and system based on big data and computer equipment |
CN113256335A (en) * | 2021-05-27 | 2021-08-13 | 腾讯科技(深圳)有限公司 | Data screening method, multimedia data delivery effect prediction method and device |
CN113256335B (en) * | 2021-05-27 | 2021-10-12 | 腾讯科技(深圳)有限公司 | Data screening method, multimedia data delivery effect prediction method and device |
CN114693361A (en) * | 2022-03-31 | 2022-07-01 | 北京明略软件系统有限公司 | Method, device, equipment and storage medium for determining contribution degree of channel |
CN116137004A (en) * | 2023-04-19 | 2023-05-19 | 江西时刻互动科技股份有限公司 | Attribution method, attribution system and attribution computer for advertisement putting effect |
CN116137004B (en) * | 2023-04-19 | 2023-07-07 | 江西时刻互动科技股份有限公司 | Attribution method, attribution system and attribution computer for advertisement putting effect |
Also Published As
Publication number | Publication date |
---|---|
WO2019161731A1 (en) | 2019-08-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110189152A (en) | The attribution method and apparatus of channel | |
CN110033314B (en) | Advertisement data processing method and device | |
CN103823908B (en) | Content recommendation method and server based on user preference | |
CN106649774A (en) | Artificial intelligence-based object pushing method and apparatus | |
CN110245301A (en) | A kind of recommended method, device and storage medium | |
CN105335409A (en) | Target user determination method and device and network server | |
CN104462156A (en) | Feature extraction and individuation recommendation method and system based on user behaviors | |
US20120296783A1 (en) | Automated commission programs | |
CN108537568A (en) | A kind of information recommendation method and device | |
CN109583924A (en) | Advertisement placement method and device | |
CN109615425A (en) | A kind of Products Show method, apparatus, electronic equipment and storage medium | |
CN109345389A (en) | A kind of resource sharing method, device and equipment | |
KR20200129090A (en) | Information processing device that calculates predicted data, etc. | |
CN107403334A (en) | Data processing method and device | |
CN110852798A (en) | Preferential information determination method and device, electronic equipment and medium | |
CN112183818A (en) | Recommendation probability prediction method and device, electronic equipment and storage medium | |
CN110189153A (en) | Attribution method and apparatus | |
CN105262794A (en) | Content delivery method and device | |
CN108268534A (en) | Propagating influence computational methods and device | |
CN106257507A (en) | The methods of risk assessment of user behavior and device | |
CN113689270B (en) | Method for determining black product device, electronic device, storage medium, and program product | |
CN104991935B (en) | A kind for the treatment of method and apparatus of website attention rate | |
CN110209687A (en) | The querying method and device of various dimensions attribution | |
CN112926090A (en) | Service analysis method and device based on differential privacy | |
CN107993078A (en) | For evaluation information bandwagon effect method and apparatus and computing device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190830 |
|
RJ01 | Rejection of invention patent application after publication |